WO2022161050A1 - 推广任务处理方法及装置、存储介质和电子设备 - Google Patents
推广任务处理方法及装置、存储介质和电子设备 Download PDFInfo
- Publication number
- WO2022161050A1 WO2022161050A1 PCT/CN2021/140836 CN2021140836W WO2022161050A1 WO 2022161050 A1 WO2022161050 A1 WO 2022161050A1 CN 2021140836 W CN2021140836 W CN 2021140836W WO 2022161050 A1 WO2022161050 A1 WO 2022161050A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- promotion
- task
- promoter
- promoters
- promoted
- Prior art date
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 33
- 238000012545 processing Methods 0.000 claims abstract description 22
- 230000007704 transition Effects 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 4
- 238000000034 method Methods 0.000 abstract description 41
- 230000008569 process Effects 0.000 abstract description 16
- 230000001737 promoting effect Effects 0.000 description 19
- 238000010586 diagram Methods 0.000 description 12
- 238000004422 calculation algorithm Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 6
- 230000000694 effects Effects 0.000 description 6
- 238000012821 model calculation Methods 0.000 description 6
- 230000003287 optical effect Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
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
- G06Q30/0241—Advertisements
- G06Q30/0249—Advertisements based upon budgets or funds
-
- 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
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06312—Adjustment or analysis of established resource schedule, e.g. resource or task levelling, or dynamic rescheduling
Definitions
- the present disclosure relates to the field of computer technologies, and in particular, to a promotion task processing method, an promotion task processing apparatus, a computer-readable storage medium, and an electronic device.
- Most of the existing methods of publicizing and promoting a promotion task are to select a promoter to complete the promotion task according to the target promotion volume of the promotion task, such as advertising on an Internet platform, etc.
- the task is freely promoted by multiple promoters, and finally the corresponding rewards are given according to the promotion volume of multiple promoters.
- a method for processing a promotion task including: acquiring a task to be promoted; using promotion parameters to determine a subset of promoters with the lowest cost of executing the task to be promoted from a set of promoters; The parameters are obtained based on the historical promotion records of each promoter in the promoter set; the tasks to be promoted are allocated to promoters in the promoter sub-set.
- a promotion task processing device comprising: a task acquisition module, a task determination module, and a task assignment module.
- the task acquisition module is configured to acquire tasks to be promoted;
- the task determination module is configured to use the promotion parameters to determine, from the set of promoters, a subset of promoters with the lowest cost of executing the tasks to be promoted; wherein the promotion parameters are based on the promotion parameters.
- the historical promotion records of each promoter in the promoter set are obtained;
- the task allocation module is configured to allocate the tasks to be promoted to the promoters in the promoter sub-set.
- a storage medium is provided on which a computer program is stored, and when the computer program is executed by a processor, the above promotion task processing method is implemented.
- an electronic device comprising: a processor; and a memory configured to store executable instructions of the processor; wherein the processor is configured to perform the above promotion task processing by executing the executable instructions method.
- FIG. 1 schematically shows a flowchart of a promotion task processing method according to an exemplary embodiment of the present disclosure
- FIG. 2 schematically shows a schematic diagram of a set of promoters according to an exemplary embodiment of the present disclosure
- FIG. 3 schematically shows a schematic diagram of promotion parameters according to an exemplary embodiment of the present disclosure
- FIG. 4 schematically shows a schematic diagram of solving a problem using a dynamic programming algorithm according to an exemplary embodiment of the present disclosure
- FIG. 5 schematically shows a schematic diagram of implementing a promotion task processing method according to an exemplary embodiment of the present disclosure
- Fig. 6 schematically shows the overall flow chart of implementing the promotion task processing method according to an exemplary embodiment of the present disclosure
- FIG. 7 schematically shows a technical flow chart of promotion task processing according to an exemplary embodiment of the present disclosure
- FIG. 8 schematically shows a block diagram of an apparatus for processing promotion tasks according to an exemplary embodiment of the present disclosure
- FIG. 9 schematically shows a block diagram of an electronic device according to an exemplary embodiment of the present disclosure.
- Example embodiments will now be described more fully with reference to the accompanying drawings.
- Example embodiments can be embodied in various forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art.
- the described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
- numerous specific details are provided in order to give a thorough understanding of the embodiments of the present disclosure.
- those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced without one or more of the specific details, or other methods, components, devices, steps, etc. may be employed.
- well-known solutions have not been shown or described in detail to avoid obscuring aspects of the present disclosure.
- a promotion goal is to promote 1 million traffic
- the cost of promoting 400,000 traffic through company A is 20
- the cost of promoting 1 million traffic through company A is 80
- the cost of promoting 600,000 traffic through company B is 30.
- the cost of promoting 1 million traffic through Company B is 90.
- the existing technology usually simply compares the total cost required to promote 1 million traffic of company A and company B, and finally chooses to spend 80 cost to promote 1 million traffic through company A to complete this promotion task, while ignoring the use of two.
- the promotion tasks are handled in a combined way. There is no way to choose a lower-cost promotion plan.
- the present disclosure proposes a promotion task processing method.
- FIG. 1 schematically shows a flowchart of a promotion task processing method according to an exemplary embodiment of the present disclosure.
- the device for acquiring the task and processing the task may be a server, a computer, a smart phone, or other devices.
- the promotion task processing method may include the following steps:
- a task to be promoted is a promotion task waiting to be executed, and the promotion task may be a target number of people to promote for one or more promoted contents, and may also be a target for one or more promoted contents
- the promotion traffic, the promotion content can be the promotion of the company's brand, the promotion of a certain product, or the promotion of a certain live broadcast room.
- the specific promotion content is not limited in this disclosure;
- the number of people to promote the promotion content to, and the target promotion traffic is how much traffic you plan to promote the promotion content to.
- the task to be promoted can be to promote a certain live broadcast room to 100,000 people within 3 days.
- promotion parameters determine a sub-collection of promoters with the lowest cost of performing the task to be promoted from the set of promoters; wherein, the promotion parameters are obtained based on the historical promotion records of each promoter in the set of promoters .
- the promotion parameter is calculated according to the historical promotion records of each promoter in the promoter set, and the historical promotion record is a record table including the corresponding relationship between the number of people promoted by each promoter and the promotion cost
- the promoter set is the set of promoters that can be used to perform promotion tasks.
- the promoter can be a person, or a platform that can be used to promote tasks such as TV stations, application software, and web pages.
- the promoter subset is from the promoter set.
- the selected part of the promoters used to complete the promotion task, the cost of executing the task to be promoted refers to the time cost, that is, the time required to complete the task to be promoted, and the subset of promoters with the lowest cost is the part selected from the set of promoters
- the promoters complete the tasks to be promoted, wherein some selected promoters consume the least time to complete the tasks to be promoted. It should be noted that the cost in the present disclosure may be not only the time cost, but also the price cost such as points, virtual currency, money, etc., that is, the lowest cost may also be the lowest monetary cost.
- FIG. 2 schematically shows a schematic diagram of a set of promoters according to an exemplary embodiment of the present disclosure.
- the set of promoters may be promoter A, promoter B, promoter A collection of promoters such as Person C.
- the promotion parameter is calculated according to the historical promotion records of each promoter in the promoter set, and the historical promotion record is a record table including the corresponding relationship between the number of people promoted by each promoter and the promotion cost , Table 1 is a promotion record of Promoter A.
- the number of promotions refers to the number of people promoted by Promoter A
- the promotion cost refers to the total cost that Promoter A has to pay to promote the corresponding number of people.
- the promotion record record When Promoter A promotes one person, the total promotion cost used is 1, the total promotion cost used when promoting 2 people is 1, the total promotion cost used when promoting 3 people is 2, and so on. Because usually, when we want to promote an advertisement, we can promote the advertisement to a few people without paying any cost, such as our family members, good friends, etc., but when we need to expand the scope of promotion, we need to pay A certain amount of resources is needed to promote the ad to more people, so the promotion cost in the table is the same when promoting 1 person and promoting 2 people.
- the promotion cost can be time cost. For example, it takes 1 hour to promote 1 person, and 1 hour to promote 2 people. It takes 2 hours to promote 3 people, and it can also be points, virtual currency, money, etc.
- the historical promotion record may include the promotion records of each promoter in each promotion process. In the case of a large amount of data, it may also be set to include a certain number of promotion records, for example, It can be set to include the promotion records of each promoter during 100 promotions.
- the historical promotion records can also be saved in the form of an array
- Table 2 is a table for saving the historical promotion records of the promoters in the form of an array.
- the first number "1" in the array represents the need to promote 1 person The total cost of , and so on, the fifth number "6" represents the total cost of promoting 5 people.
- the promotion cost required by each promoter in the promoter set to promote different numbers of objects is obtained; according to the promotion cost, the promotion parameters are obtained.
- the object may be a user or traffic, etc., which is not limited in the present disclosure.
- the four promotion records of Promoter A are shown in Table 2, which are [1, 1, 2, 3, 4, 5] , [1, 2, 3], [1, 2, 3, 4, 5, 6, 7], [1, 3, 4, 6].
- One person starts to promote the maximum number of people, and calculate the average promotion cost in turn.
- the promotion parameters of promoter A are [1,2, 3,...].
- the promotion parameters of promoters such as Promoter B and Promoter C can be obtained, and the set of promotion parameters of each promoter is the final required promotion parameters.
- FIG. 3 schematically shows a schematic diagram of promotion parameters according to an exemplary embodiment of the present disclosure.
- the promotion parameters include the average cost of each promoter starting from promoting the first user, and each additional user needs to be promoted.
- using the promotion parameters to assign the tasks to be promoted to one or more promoters in the set of promoters includes: determining from the set of promoters to complete the tasks to be promoted at the lowest cost according to the promotion parameters The required promoter; if the required number of promoters is one, the to-be-promoted task is allocated to a promoter corresponding to the required promoter in the promoter set; if the required number of promoters is more The tasks to be promoted are allocated to a plurality of promoters corresponding to the desired promoters in the promoter set.
- the task to be promoted is allocated to the promoter; if multiple promoters are required to complete the task to be promoted at the lowest cost, then Assign tasks to be promoted to these multiple promoters.
- determining the number of promoters required to complete the task to be promoted at the lowest cost from the set of promoters according to the promotion parameters includes: determining the state transition equation of the task to be promoted according to the promotion parameters; wherein , the state transition equation is the equation for calculating the lowest cost; according to the state transition equation, determine the allocation plan to complete the task to be promoted with the lowest cost; according to the allocation plan, determine the number of promoters.
- the state transition equation is that the state of the current stage in dynamic programming is often the result of the state of the previous stage and the decision of the previous stage. If the state and decision of the Kth stage are given, the state of the K+1th stage is also completely determined.
- an allocation plan for completing the tasks to be promoted at the lowest cost can be obtained.
- the content of the allocation plan includes which promoters are assigned the tasks to be promoted, how many tasks are allocated to each promoter, and the number of tasks to be allocated to each promoter. How much to allocate.
- the knapsack problem in the dynamic programming algorithm conforms to the task promotion scenario in the present disclosure, and the idea of solving the problem is divided into four steps. Referring to FIG. 4, FIG. 4 schematically shows the use of the dynamic programming algorithm according to an exemplary embodiment of the present disclosure. Diagram of problem solving.
- the determining state stage 41 refers to resolving the general problem into sub-problems by confirming the last step.
- n people need to be promoted, it can be decomposed into n-
- the cost of 1 person and the cost of the nth person can be decomposed into the cost of the 1st, 2nd, 3rd...
- i][v] min ⁇ f[i-1][v],f[i-1][v–Ci]+Wi ⁇ , that is, the function to obtain the minimum cost; the start and boundary conditions 45 are to judge the last The cost of the promoted user cannot exceed the total cost, and this problem can be ignored in practical scenarios (because the cost of a single user is very low); the calculation sequence 47 adopts the memo mode starting from f(0), and the specific calculation method is recursion.
- a method for allocating a task to be promoted to promoters in a subset of promoters may be, according to an allocation scheme, decomposing the task to be promoted into a plurality of subtasks; wherein the subtasks include promotion costs and the number of promotions; assign multiple subtasks to the corresponding promoters.
- the content of the sub-tasks includes which promoters are assigned the task to be promoted, how many tasks are assigned to each promoter, and how much cost is assigned to each promoter.
- the task to be promoted may be to promote a certain live broadcast room to 100,000 people within 3 days.
- the distribution plan can be that Promoter A can promote 30,000 people within 2 days, Promoter B can promote 40,000 people within 3 days, and Promoter C can promote 30,000 people within 3 days.
- the task to be promoted is decomposed into 3 subtasks, and each subtask corresponds to a promoter.
- the task to be promoted may also be to promote a certain live broadcast room to 100,000 people using 600,000 yuan.
- the allocation plan can be: Allocate 150,000 yuan to Promoter A to promote 30,000 people, allocate 200,000 yuan to Promoter B to promote 30,000 people, and allocate 250,000 yuan to Promoter C to promote Promoted to 40,000 people.
- the task to be promoted is decomposed into 3 subtasks, and each subtask corresponds to a promoter.
- the promotion task processing method includes: determining a promotion result corresponding to the promoters according to the task completion status of the promoters ; According to the promotion result, determine the reward corresponding to the promotion result, so as to send the reward to the promoter.
- the promotion results corresponding to the promoters can be determined according to the task execution data of the promoters; according to the promotion results, A reward corresponding to the promotion result is determined for sending the reward to the promoter.
- the task execution data is the data generated by the promoter performing the task, which can record the completion of the promoter's task, for example, the number of people promoted by promoter A when performing the promotion task, the time consumed, the cost of use, etc.
- the promoter if the promoter completes all the assigned tasks, more rewards may be sent to the promoter, and if the promoter does not complete all the assigned tasks , you can send less rewards to that promoter.
- This method of sending rewards can to a certain extent facilitate the promoters to complete the task.
- the rewards sent can be in the form of money or virtual items such as points.
- the promotion task processing method further includes: sending a task stop notification to the promoter, so that the promoter can stop the task promotion operate.
- a notification for stopping the execution of the promotion task may be sent to the promoter, so that the promoter can stop performing the promotion task.
- This method can immediately stop the promotion task in some emergency situations, so that the upper limit of the number of people or traffic to be promoted is controllable.
- the promotion task processing method further includes: recording the current promotion record corresponding to the promoter, so as to update the historical promotion record and obtain the updated historical promotion record; The updated historical promotion record, update the promotion parameters, and obtain the updated promotion parameters.
- the system automatically analyzes which promoter the traffic source belongs to, and after a promotion ends, the traffic situation is counted according to the categories of promoters, and written into the historical promotion record table. As the amount of data in the historical promotion record table increases, the use of promotion parameters to assign tasks will be more accurate, so as to achieve a benign closed-loop iteration of the system.
- a promotion activity organized by a company is taken as an example to further illustrate the promotion task processing method proposed in the present disclosure.
- the original promotion target is 800,000 traffic, and 6,000 promoters can be used to promote the promotion, which can promote 200,000-1.2 million traffic.
- the active server can handle limited traffic, traffic exceeding a certain value (such as more than 800,000 traffic) at the same time will cause the server to crash or not work properly, so it is very important to ensure that the promoted traffic is within 800,000.
- a certain value such as more than 800,000 traffic
- the promotion target can only be determined as 400,000 traffic, while the actual promotion traffic may be 480,000, which is far lower. Due to the target of 800,000 traffic to be promoted, it will cause economic losses.
- the actual promotion task can be set more accurately according to the target promotion flow by configuring the promotion center, the model calculation engine, the promotion capability model, and the task assignment module.
- the promotion center is used to assign tasks and control the start and stop of the promotion tasks
- the model calculation engine is used to calculate the promotion capability model
- the promotion capability model is used to calculate how the tasks are allocated. Allocated to Promoters.
- FIG. 5 schematically shows a schematic diagram of a method for implementing promotion task processing according to an exemplary embodiment of the present disclosure.
- the historical operation records are input into the model calculation engine, and step 2 calculates the promotion capability model through the model calculation engine, wherein the data saved in the promotion capability model is the promotion parameter.
- step 3 the promotion center calls the promotion capability model, and completes step 4 to obtain The lowest cost task allocation plan, step 5, according to the task allocation plan, assign promotion tasks to designated promoters, and promote according to the task, in step 6, the promotion center can terminate the task promotion according to the specific situation, in order to deal with emergencies, in step 7 , according to the completion of the task, the promotion records of the designated promoters will be saved to the historical operation records, and the system will automatically analyze which promoter the traffic source belongs to. , as the data volume of the historical promotion record table increases, the promotion capability model will be more accurate, so as to achieve a benign closed-loop iteration of the system.
- a complete promotion task processing process includes 5 stages.
- FIG. 6 schematically shows the overall flow of implementing the promotion task processing method according to the exemplary embodiment of the present disclosure.
- the overall process includes the sub-promotion capability model generation stage 61, the promotion center confirming the demand and carrying out the dynamic planning stage 63, the promoters receiving tasks according to the assignment results and carrying out the promotion stage 65, the promotion center intervention stage 67, the promotion stage Result recording stage 69.
- the promotion capability model is the promotion parameter
- the model calculation engine obtains the data required by each promoter in the promoter set to promote different numbers of objects according to the historical promotion records of each promoter in the promoter set Promotion cost; according to the promotion cost, the promotion parameters are obtained.
- the object may be a user or traffic, etc., which is not limited in the present disclosure.
- the model generation process in the promotion capability model generation stage 61 may include the following five steps.
- Step 1 Query the full historical promotion records through the model calculation engine
- Step 2 Categorize promotion records by promoter
- Step 3 For each promoter, find the average cost of promoting the first user each time in the historical promotion record, as the average cost of the promoter to promote the first user; and so on, find the promotion The average cost of promoting each user from the first to the largest number of promoters;
- Step 4 According to Step 3, process the historical promotion records of each promoter in turn;
- Step 5 Obtain a two-dimensional matrix, the two-dimensional matrix is the same as the promotion parameters, that is, the promotion ability model.
- the generation process of the model in the promotion capability model generation stage 61 is described by taking the calculation of the promotion cost of the promoter A as an example.
- the promotion capability model determines the minimum cost allocation scheme according to the promotion parameters. .
- the process of the promotion center confirming the demand and performing the dynamic planning stage 63 may include the following 4 steps.
- Step 1 When the promotion center receives a promotion task, confirm the promotion budget (cost) and promotion target number;
- Step 2 Based on the promotion capability model, the promotion center uses the dynamic programming algorithm to plan the lowest-cost promotion task allocation plan;
- Step 3 The dynamic programming algorithm focuses on three elements: who is assigned to, how many task goals are assigned to him, and how much cost is assigned to him;
- Step 4 The dynamic programming algorithm outputs the results according to the above elements.
- the output result can be allocated to Promoter A with a cost of 50 to promote 38 people, allocated to Promoter B to promote 13 people with a cost of 15, and allocated to Promoter C to promote 20 people with a cost of 35.
- the promotion center uses the dynamic programming algorithm to plan the specific process of the promotion task allocation plan with the lowest cost.
- the determination state stage 41 refers to the confirmation
- the method of the last step resolves the general problem into sub-problems.
- n people need to be promoted, it can be decomposed into the cost of n-1 person and the cost of the nth person, and so on.
- the solution is the cost of the 1st, 2nd, 3rd...
- the calculation sequence 47 adopts the memo mode starting from f(0), and the specific calculation method is recursion.
- the stage 65 for the promoter to receive the task according to the assignment result and perform the promotion may include the following five steps.
- Step 1 Promoters first query the task allocation module of the promotion center to see if there are promotion tasks assigned to them;
- Step 2 If not, then the process result, if there is a promotion task assigned to you, browse your own promotion task list;
- Step 3 Promoters choose a promotion task that suits them, and receive the promotion task on the system.
- the promotion task will limit the time limit, promotion target requirements, and promotion cost (for the promoter, it is a promotion reward);
- Step 4 Promoters promote according to the task requirements and introduce traffic for the overall promotion task
- Step 5 The system automatically confirms the source of traffic, and if it is confirmed that the promoter has completed the task, it will automatically issue a reward to the promoter.
- FIG. 7 schematically shows a technical flow chart of promotion task processing according to an exemplary embodiment of the present disclosure.
- jimdb is a memory-based The central key-value database
- the promoter calls the start promotion interface (step 1)
- the activity engine writes the data into the jimdb cache (step 4), and asynchronously starts the promotion into the database (step 5), and the promotion information is stored in the jimdb cache and In the mysql database
- the helper interface is called (step 2)
- the activity engine retrieves the jimdb cache (step 4), if there is corresponding promotion information, the promotion information is extracted, and the helper result is also written into jimdb
- asynchronous storage step 5
- asynchronous events step 6) are simultaneously performed.
- the asynchronous events are the follow-up events for the promotion to reach the target, such as issuing virtual item rewards (step 9), and WeChat pushes the target message (step 10). , pay attention to the store (step 11), etc.; promoters and helpers regularly sign in (step 3), call the sign-in interface to maintain the user's daily activity, this function will directly trigger the asynchronous event (step 6) in the sending reward (step 9) ), giving out a small reward.
- the consistency check (step 7) is performed on the database data (step 5) and the jimdb cache data (step 4) to avoid the problem of data inconsistency; if the problem of data inconsistency is triggered, the underlying logic will be executed (step 8) ), lock the entire function, then read the data from the database and write it into the jimdb cache. After confirming that the data is consistent, unlock it and continue to provide services.
- the promotion center intervention stage 67 is for the promotion center to urgently interfere with the promotion tasks, and terminate all the promotion tasks on the way of promotion, so as to avoid risks in emergency situations.
- the promoter performs the promotion task, he needs to query the status control module of the promotion center first. If the verification status is ON, the promotion is allowed, and if the verification status is OFF, the promotion is prohibited. Therefore, when the promotion center is closed, all promotions are terminated to ensure that the upper limit of traffic is controllable.
- the promotion result recording stage 69 automatically analyzes which promoter the traffic source belongs to through the system. As the amount of data in the historical promotion record table increases, the promotion capability model will be more accurate, so as to achieve a benign closed-loop iteration of the system.
- the promotion cost can be reduced, and the problem of excessive use of the promotion cost by the promoters with high cost can be solved.
- the cost of promoting each user by the promoter is calculated, so as to obtain the cost required by the promoter to promote to n users, namely the promotion capability.
- it can control social traffic more accurately, and solve the mutually exclusive contradiction between goal achievement and customer complaints caused by uncontrollable social traffic.
- the above promotion capability model is dynamically allocated, so that the achievable flow can be calculated in the early stage of the allocation task, and the threshold of the promotion center can be set accordingly, so that each promoter can obtain the Expected benefits and avoid customer complaints.
- the present exemplary embodiment also provides a promotion task processing apparatus.
- FIG. 8 schematically shows a block diagram of a promotion task processing apparatus according to an exemplary embodiment of the present disclosure.
- the promotion task processing apparatus 8 may include a task acquisition module 81 , a task determination module 83 , and a task assignment module 85 .
- the task obtaining module 81 may be configured to obtain the tasks to be promoted; the task determination module 83 may be configured to use the promotion parameters to determine, from the set of promoters, a subset of promoters that has the lowest cost of executing the tasks to be promoted; wherein, The promotion parameters are obtained based on the historical promotion records of each promoter in the promoter set; the task assignment module 85 may be configured to assign tasks to be promoted to promoters in the promoter subset.
- the task determination module 83 may be configured to perform: obtaining the promotion cost required by each promoter in the promoter set to promote different numbers of objects according to the historical promotion records of each promoter in the promoter set ; According to the promotion cost, get the promotion parameters.
- the task determination module 83 may be configured to perform: according to the promotion parameters, determine the state transition equation of the task to be promoted; wherein, the state transition equation is an equation for calculating the lowest cost; according to the state transition equation, determine The allocation plan for completing the tasks to be promoted at the lowest cost; according to the allocation plan, a subset of promoters is determined.
- the task allocation module 85 may be configured to perform: according to the allocation scheme, decompose the task to be promoted into a plurality of subtasks; wherein the subtasks include the promotion cost and the promotion quantity; assign the plurality of subtasks to to the corresponding promoter.
- the task assignment module 85 may be configured to perform: according to the task performance data of the promoter, determine the promotion result corresponding to the promoter; according to the promotion result, determine the reward corresponding to the promotion result, so that the Rewards are sent to promoters.
- the task assignment module 85 may be configured to perform: sending a notification of task stop to the promoter so that the promoter can stop the task promotion operation.
- the task determination module 83 may be configured to perform: record the promotion record corresponding to the promoter for completing the task to be promoted, so as to update the historical promotion record and obtain the updated historical promotion record; The historical promotion records of , update the promotion parameters, and get the updated promotion parameters.
- a computer-readable storage medium on which a program product capable of implementing the above-described method of the present specification is stored.
- aspects of the present invention can also be implemented in the form of a program product comprising program code for enabling the program product to run on a terminal device The terminal device performs the steps according to various exemplary embodiments of the present invention described in the "Example Method" section above in this specification.
- a program product for implementing the above method according to an embodiment of the present invention may employ a portable compact disc read only memory (CD-ROM) and include program codes, and may run on a terminal device such as a personal computer.
- CD-ROM compact disc read only memory
- the program product of the present invention is not limited thereto, and in this document, a readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.
- the program product may employ any combination of one or more readable media.
- the readable medium may be a readable signal medium or a readable storage medium.
- the readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or a combination of any of the above. More specific examples (non-exhaustive list) of readable storage media include: electrical connections with one or more wires, portable disks, hard disks, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical disks, portable compact disk read only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.
- a computer readable signal medium may include a propagated data signal in baseband or as part of a carrier wave with readable program code embodied thereon. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing.
- a readable signal medium can also be any readable medium, other than a readable storage medium, that can transmit, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.
- Program code embodied on a readable medium may be transmitted using any suitable medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
- Program code for carrying out operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages—such as Java, C++, etc., as well as conventional procedural Programming Language - such as the "C" language or similar programming language.
- the program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server execute on.
- the remote computing device may be connected to the user computing device through any kind of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (eg, using an Internet service provider business via an Internet connection).
- LAN local area network
- WAN wide area network
- an external computing device eg, using an Internet service provider business via an Internet connection
- an electronic device capable of implementing the above method is also provided.
- aspects of the present invention may be implemented as a system, method or program product. Therefore, various aspects of the present invention can be embodied in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software aspects, which may be collectively referred to herein as implementations "circuit", “module” or "system”.
- FIG. 9 An electronic device 900 according to this embodiment of the present invention is described below with reference to FIG. 9 .
- the electronic device 900 shown in FIG. 9 is only an example, and should not impose any limitations on the function and scope of use of the embodiments of the present invention.
- electronic device 900 takes the form of a general-purpose computing device.
- Components of the electronic device 900 may include, but are not limited to: the above-mentioned at least one processing unit 910 , the above-mentioned at least one storage unit 920 , a bus 930 connecting different system components (including the storage unit 920 and the processing unit 910 ), and a display unit 940 .
- the storage unit stores program codes, and the program codes can be executed by the processing unit 910, so that the processing unit 910 executes various exemplary methods according to the present invention described in the above-mentioned “Exemplary Methods” section of this specification Implementation steps.
- the storage unit 920 may include a readable medium in the form of a volatile storage unit, such as a random access storage unit (RAM) 9201 and/or a cache storage unit 9202 , and may further include a read only storage unit (ROM) 9203 .
- RAM random access storage unit
- ROM read only storage unit
- the storage unit 920 may also include a program/utility 9204 having a set (at least one) of program modules 9205 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, An implementation of a network environment may be included in each or some combination of these examples.
- the bus 930 may be representative of one or more of several types of bus structures, including a memory cell bus or memory cell controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local area using any of a variety of bus structures bus.
- the electronic device 900 may also communicate with one or more external devices 1000 (eg, keyboards, pointing devices, Bluetooth devices, etc.), with one or more devices that enable a user to interact with the electronic device 900, and/or with Any device (eg, router, modem, etc.) that enables the electronic device 900 to communicate with one or more other computing devices. Such communication may take place through input/output (I/O) interface 950 . Also, the electronic device 900 may communicate with one or more networks (eg, a local area network (LAN), a wide area network (WAN), and/or a public network such as the Internet) through a network adapter 960 . As shown, network adapter 960 communicates with other modules of electronic device 900 via bus 930 . It should be understood that, although not shown, other hardware and/or software modules may be used in conjunction with electronic device 900, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives and data backup storage systems.
- the exemplary embodiments described herein may be implemented by software, or by a combination of software and necessary hardware. Therefore, the technical solutions according to the embodiments of the present disclosure may be embodied in the form of software products, and the software products may be stored in a non-volatile storage medium (which may be CD-ROM, U disk, mobile hard disk, etc.) or on the network , including several instructions to cause a computing device (which may be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to an embodiment of the present disclosure.
- a computing device which may be a personal computer, a server, a terminal device, or a network device, etc.
- modules or units of the apparatus for action performance are mentioned in the above detailed description, this division is not mandatory. Indeed, according to embodiments of the present disclosure, the features and functions of two or more modules or units described above may be embodied in one module or unit. Conversely, the features and functions of one module or unit described above may be further divided into multiple modules or units to be embodied.
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Development Economics (AREA)
- General Physics & Mathematics (AREA)
- Game Theory and Decision Science (AREA)
- Marketing (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Educational Administration (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
一种推广任务处理方法、推广任务处理装置、计算机可读存储介质和电子设备,涉及计算机技术领域。该推广任务处理方法包括:获取待推广任务(S12);利用推广参数,从推广者集合中确定出使执行待推广任务成本最低的推广者子集合;其中,推广参数基于推广者集合中各推广者的历史推广记录而得到(S14);将待推广任务分配给推广者子集合中的推广者(S16)。该方法实现了在推广者历史推广记录的基础上,得到以最低成本完成待推广任务的方案,解决了在完成推广任务的过程中成本较高的推广者占用太多推广成本的问题。
Description
相关申请的交叉引用
本申请要求于2021年01月29日提交的申请号为202110126981.4、名称为“推广任务处理方法及装置、存储介质和电子设备”的中国专利申请的优先权,该中国专利申请的全部内容通过引用全部并入本文。
本公开涉及计算机技术领域,具体而言,涉及一种推广任务处理方法、推广任务处理装置、计算机可读存储介质和电子设备。
随着互联网技术的不断发展,网络平台为用户提供的信息也越来越丰富,越来越多的公司或个人选择通过互联网平台对公司品牌、产品或网络直播间进行宣传推广。
现有的对推广任务进行宣传推广的方式大多是根据推广任务的目标推广量,选取一个推广者完成该推广任务,如在某个互联网平台进行广告宣传等;除此之外,还可以发布推广任务,由多个推广者进行自由推广,最后根据多个推广者的推广量给予相应的奖励。
然而,现有技术无法根据各个推广者的推广能力确定出成本最低的一套推广任务处理方案。
发明内容
根据本公开的第一方面,提供一种推广任务处理方法,包括:获取待推广任务;利用推广参数,从推广者集合中确定出使执行待推广任务成本最低的推广者子集合;其中,推广参数基于推广者集合中各推广者的历史推广记录而得到;将待推广任务分配给推广者子集合中的推广者。
根据本公开的第二方面,提供一种推广任务处理装置,包括:任务获取模块、任务确定模块、任务分配模块。具体的,任务获取模块被配置为获取待推广任务;任务确定模块被配置为利用推广参数,从推广者集合中确定出使执行待推广任务成本最低的推广者子集合;其中,推广参数基于推广者集合中各推广者的历史推广记录而得到;任务分配模块被配置为将待推广任务分配给推广者子集合中的推广者。
根据本公开的第三方面,提供一种存储介质,其上存储有计算机程序,计算机程序被处理器执行时实现上述推广任务处理方法。
根据本公开的第四方面,提供一种电子设备,包括:处理器;以及存储器,被配置为存储处理器的可执行指令;其中,处理器配置为经由执行可执行指令来执行上述推广任务处理方法。
图1示意性示出了根据本公开的示例性实施方式的推广任务处理方法的流程图;
图2示意性示出了根据本公开的示例性实施方式的推广者集合的示意图;
图3示意性示出了根据本公开的示例性实施方式的推广参数的示意图;
图4示意性示出了根据本公开的示例性实施方式的利用动态规划算法解决问题的示意图;
图5示意性示出了根据本公开的示例性实施方式的实现推广任务处理方法的示意图;
图6示意性示出了根据本公开的示例性实施方式的实现推广任务处理方法的整体流程 图;
图7示意性示出了根据本公开的示例性实施方式的推广任务处理的技术流程图;
图8示意性示出了根据本公开的示例性实施方式的推广任务处理装置的方框图;
图9示意性示出了根据本公开的示例性实施方式的电子设备的方框图。
现在将参考附图更全面地描述示例实施方式。然而,示例实施方式能够以多种形式实施,且不应被理解为限于在此阐述的范例;相反,提供这些实施方式使得本公开将更加全面和完整,并将示例实施方式的构思全面地传达给本领域的技术人员。所描述的特征、结构或特性可以以任何合适的方式结合在一个或更多实施方式中。在下面的描述中,提供许多具体细节从而给出对本公开的实施方式的充分理解。然而,本领域技术人员将意识到,可以实践本公开的技术方案而省略所述特定细节中的一个或更多,或者可以采用其它的方法、组元、装置、步骤等。在其它情况下,不详细示出或描述公知技术方案以避免喧宾夺主而使得本公开的各方面变得模糊。
此外,附图仅为本公开的示意性图解,并非一定是按比例绘制。图中相同的附图标记表示相同或类似的部分,因而将省略对它们的重复描述。附图中所示的一些方框图是功能实体,不一定必须与物理或逻辑上独立的实体相对应。可以采用软件形式来实现这些功能实体,或在一个或多个硬件模块或集成电路中实现这些功能实体,或在不同网络和/或处理器装置和/或微控制器装置中实现这些功能实体。
附图中所示的流程图仅是示例性说明,不是必须包括所有的步骤。例如,有的步骤还可以分解,而有的步骤可以合并或部分合并,因此实际执行的顺序有可能根据实际情况改变。
目前对推广信息进行宣传推广的方式大多是根据推广任务的目标推广量,选取一个推广者完成该推广任务,如在某个互联网平台进行广告宣传等;除此之外,还可以发布推广任务,由多个推广者进行自由推广,最后根据多个推广者的推广量给予相应的奖励。但是现有的推广任务处理方法,存在较多的缺陷。
例如某次推广目标为推广100万流量,通过A公司推广40万流量所需的成本为20,通过A公司推广100万流量所需的成本为80,通过B公司推广60万流量所需成本为30,通过B公司推广100万流量所需成本为90。现有技术通常只是单纯的对比推广100万流量A公司和B公司所需的总成本进行对比,最终选择花费80成本通过A公司来推广100万流量来完成本次推广任务,而忽略了使用两者结合的方式进行推广任务处理。无法选择出一种成本较低的推广方案。再例如,某次推广时,当用户领取推广任务,精心制作推广视频/文章并进行推广时,推广的总目标已达成,推广终止,则推广者无法获得奖励,从而产生客户投诉事件。并且这种推广方法,无法对推广活动进行有效控制,当出现紧急情况时,无法及时停止推广活动,进而造成严重后果的情况。
鉴于此,本公开提出了一种推广任务处理方法。
图1示意性示出了本公开的示例性实施方式的推广任务处理方法的流程图。在本公开提出的推广任务处理方法中,获取任务与处理任务的设备可以为服务器、计算机、智能手机等设备。参考图1,所述推广任务处理方法可以包括以下步骤:
S12.获取待推广任务。
在本公开的示例性实施方式中,待推广任务为等待被执行的推广任务,该推广任务可以为针对一个或多个推广内容的目标推广人数,还可以为针对一个或多个推广内容的目标推广流量,推广内容可以为对公司品牌的推广,可以为对某产品的推广,还可以为对某个直播间的推广,具体推广内容在本公开中不做限制;目标推广人数为计划将该推广内容推广给多少数量的人,目标推广流量为计划将该推广内容推广多少流量。例如,待推广任务 可以为将某一直播间在3天内推广给10万人。
S14.利用推广参数,从推广者集合中确定出使执行所述待推广任务成本最低的推广者子集合;其中,所述推广参数基于所述推广者集合中各推广者的历史推广记录而得到。
在本公开的示例性实施方式中,推广参数为根据推广者集合中各推广者的历史推广记录进行计算而得到的,历史推广记录为包含有各个推广者推广人数与推广成本对应关系的记录表,推广者集合为可以用来执行推广任务的推广者的集合,推广者可以为人,也可以为电视台、应用软件、网页等可以用来推广任务的平台,推广者子集合为从推广者集合中选取的部分用来完成推广任务的推广者,执行待推广任务的成本指的是时间成本,即完成待推广任务所需的时间,成本最低的推广者子集合为从推广者集合中选取的部分推广者来完成待推广任务,其中,所选取的部分推广者完成待推广任务所消耗的时间最少。需要说明的是,本公开中的成本除了可以为时间成本之外,也可以为还可以为积分、虚拟货币、金钱等价格成本等,即成本最低还可以为金钱成本最低。
在本公开的示例性实施方式中,图2示意性示出了根据本公开的示例性实施方式的推广者集合的示意图,参考图2,推广者集合可以为推广人员A,推广人员B,推广人员C等推广人员的集合。
在本公开的示例性实施方式中,推广参数为根据推广者集合中各推广者的历史推广记录进行计算而得到的,历史推广记录为包含有各个推广者推广人数与推广成本对应关系的记录表,表1为推广者A的某一次推广记录。
表1
推广人数 | 1 | 2 | 3 | 4 | 5 | 6 |
推广成本 | 1 | 1 | 2 | 3 | 4 | 5 |
如表1所示,推广人数指的是推广者A将推广内容推广给了多少人,推广成本指的是推广者A推广相应人数时所需付出的总成本,在该次推广记录中,记录了推广者A推广一个人时,所用的总推广成本为1,推广2个人时所用的总推广成本为1,当推广3个人时所用的总推广成本为2,以此类推。因为通常情况下,当我们要推广一个广告时,往往不需要付出什么成本就可以将该广告推广给少数几个人,例如我们的家人,好朋友等,但是当需要扩大推广范围时,就需要付出一定的资源来将该广告推广到更多的人,因此,表格中在推广1个人和推广2个人时所需要的推广成本相同。需要说明的是,表格中的数字只是为了方便描述而列举的数字,实际情况可能与表格中的数字不同,该推广成本可以为时间成本,例如,推广1人需要1小时,推广2人需要1小时,推广3人需要2小时,还可以为积分、虚拟货币、金钱等。
在本公开的示例性实施方式中,历史推广记录可以包含各个推广者每一次推广过程中的推广记录,在数据量较大的情况下,也可以设置为包含某一数量的推广记录,例如,可以设置为包含每个推广者100次推广过程中的推广记录。
在本公开的示例性实施方式中,历史推广记录还可以通过数组的方式进行保存,表2为使用数组的方式保存推广者历史推广记录的表格。
表2
如表2所示,以推广者C的第二次推广记录[1,2,2,3,6,7]为例,数组中的第一个数字“1”代表的是推广1个人所需的总成本,以此类推,第5个数字“6”代表的为推广5个人所需的总成本。
在本公开的示例性实施方式中,根据推广者集合中各推广者的历史推广记录,得到推广者集合中各推广者推广不同数量的对象所需的推广成本;根据推广成本,得到推广参数。其中,对象可以为用户、也可以为流量等,本公开中不做限制。
在本公开的示例性实施方式中,以计算推广者A的推广成本为例,推广者A的4次推广记录如表2所示,分别为[1,1,2,3,4,5],[1,2,3],[1,2,3,4,5,6,7],[1,3,4,6],将推广者A在这4次推广过程中,从推广第一个人开始到推广最大人数,依次计算平均推广成本,例如,推广者A推广一个人的平均推广成本为(1+1+1+1)÷4=1,推广两个人的平均成本为(1+2+2+3)÷4=2,推广三个人的平均成本为(2+3+3+4)÷4=3依次计算即可得到推广者A的推广参数为[1,2,3,···]。采用相同的方法,即可求得推广者B、推广者C等推广者的推广参数,各个推广者的推广参数的集合即为最终需要的推广参数。
图3示意性示出了根据本公开的示例性实施方式的推广参数的示意图。如图3所示,推广参数包含有各个推广者从推广第一个用户开始,每多推广一个用户所需的平均成本。
在本公开的示例性实施方式中,利用推广参数,将待推广任务分配给推广者集合中一个或多个推广者,包括:根据推广参数,从推广者集合中确定以最低成本完成待推广任务所需的推广者;若所需的推广者的数量为一个,则将待推广任务分配给推广者集合中与所需的推广者对应的一个推广者;若所需的推广者的数量为多个,则将待推广任务分配给推广者集合中与所需的推广者对应的多个推广者。
在本公开的示例性实施方式中,若以最低成本完成待推广任务只需要一个推广者,则将待推广任务分配给该推广者;若以最低成本完成待推广任务需要多个推广者,则将待推广任务分配给这多个推广者。
在本公开的示例性实施方式中,根据推广参数,从推广者集合中确定以最低成本完成待推广任务所需的推广者数量,包括:根据推广参数,确定待推广任务的状态转移方程;其中,状态转移方程为计算最低成本的方程;根据状态转移方程,确定以最低成本完成待推广任务的分配方案;根据分配方案,确定推广者数量。
在本公开的示例性实施方式中,状态转移方程是动态规划中本阶段的状态往往是上一阶段状态和上一阶段决策的结果。如果给定了第K阶段的状态以及决策,则第K+1阶段的状态也就完全确定。通过状态转移方程,可以得到以最低成本完成待推广任务的分配方案,其中,分配方案的内容包括将待推广任务分配给哪几个推广者,每个推广者分配多少任务以及给每个推广者分配多少成本。动态规划算法中的背包问题符合本公开中的任务推广场景,解决问题的思路共分为四步,参考图4,图4示意性示出了根据本公开的示例性实施方式的利用动态规划算法解决问题的示意图。
如图4所示,确定状态阶段41指的是通过确认最后一步的方式将总问题化解为子问题,在本公开中进行任务推广的场景中,假设需要推广n个人,则可以分解为n-1个人的成本和第n个人的成本,依次类推可以拆解为第1,2,3...n的成本;确定转移方程阶段43为通过上述状态确认阶段,得出状态转移方程为f[i][v]=min{f[i-1][v],f[i-1][v–Ci]+Wi},即求得最小成本的函数;开始和边界条件45是判断最后一个被推广用户的成本不能超出总成本,该问题在实际场景中可以忽略(因为单个用户成本很低);计算顺序47即采用从f(0)开始的备忘录模式,具体计算方式为递归。
S16.将所述待推广任务分配给所述推广者子集合中的推广者。
在本公开的示例性实施方式中,将待推广任务分配给推广者子集合中的推广者的方法 可以为,根据分配方案,将待推广任务分解为多个子任务;其中,子任务包含推广成本和推广数量;将多个子任务,分配给对应的推广者。其中,子任务的内容包括将待推广任务分配给哪几个推广者,每个推广者分配多少任务以及给每个推广者分配多少成本。
在本公开的示例性实施方式中,待推广任务可以为将某一直播间在3天内推广给10万人。分配方案可以为让推广者A在2天内推广3万人,让推广者B在3天内推广4万人,让推广者C在3天内推广3万人。待推广任务被分解为3个子任务,每个子任务都对应一个推广者。
在本公开的示例性实施方式中,待推广任务还可以为使用60万元将某一直播间推广给10万人。此时分配方案可以为,给推广者A分配15万元的成本来推广3万人,给推广者B分配20万元的成本来推广3万人,给推广者C分配25万元的成本来推广4万人。待推广任务被分解为3个子任务,每个子任务都对应一个推广者。
在本公开的示例性实施方式中,将待推广任务分配给推广者集合中一个或多个推广者后,推广任务处理方法包括:根据推广者的任务完成情况,确定与推广者对应的推广结果;根据推广结果,确定与推广结果对应的奖励,以便将奖励发送给推广者。
在本公开的示例性实施方式中,将待推广任务分配给推广者子集合中的推广者后,可以根据推广者的任务执行数据,确定与推广者对应的推广结果;根据所述推广结果,确定与所述推广结果对应的奖励,以便将所述奖励发送给所述推广者。任务执行数据为推广者执行任务所产生的数据,该数据可以记录推广者的任务完成情况,例如,推广者A在执行推广任务时推广的人数,消耗的时间,使用的成本等。
在本公开的示例性实施方式中,根据推广者的任务完成情况,若推广者将分配的任务全部完成,则可以给该推广者发送较多的奖励,若推广者未将分配的任务全部完成,则可以给该推广者发送较少的奖励。这种发送奖励的方法可以在一定程度上促进推广者完成任务。发送的奖励可以为金钱,也可以为积分等虚拟物品。
在本公开的示例性实施方式中,将待推广任务分配给推广者集合中一个或多个推广者后,推广任务处理方法还包括:向推广者发送任务停止的通知,以便推广者停止任务推广操作。
在本公开的示例性实施方式中,在推广者执行推广任务的过程中,可以向推广者发送停止执行推广任务的通知,让推广者停止执行推广任务。此方法可以在一些紧急的情况下立即停止推广任务,使推广的人数或流量上限可控。
在本公开的示例性实施方式中,在完成待推广任务后,推广任务处理方法还包括:记录与推广者对应的本次推广记录,以便更新历史推广记录,得到更新后的历史推广记录;根据更新后的历史推广记录,更新推广参数,得到更新后的推广参数。
在本公开的示例性实施方式中,***自动分析流量来源属于哪个推广者,当一次推广结束后,根据推广者分类统计流量情况,写入历史推广记录表。随着历史推广记录表数据量增大,使用推广参数进行任务的分配会更加精准,从而达到***的良性闭环迭代。
在本公开的示例性实施方式中,以某公司组织的一次促销活动为例,对本公开中提出的推广任务处理方法做进一步说明。
在一次促销活动中,原始推广目标为80万流量,有6000名推广者可用于进行促销活动的推广,可以推广20-120万流量。
由于活动服务器可处理的流量有限,同一时间的流量超过某一数值(如超过80万流量)则会导致服务器崩溃或无法正常工作,因此确保推广的流量在80万以内是非常重要的。
因为无法确定应给每个推广者分配多少任务可以保证将推广的流量控制在80万流量以内,为了稳妥只能将推广目标确定为40万流量,而实际推广的流量可能为48万,远低于目标要推广的80万流量,进而造成经济损失。
在本公开的示例性实施方式中,可以通过配置推广中心、模型计算引擎、推广能力模型、任务分配模块来更加精确的根据目标推广流量设置实际推广任务。其中,推广中心用于分配任务和控制推广任务的开始和停止,模型计算引擎用于计算推广能力模型,推广能力模型用于计算任务如何分配,其中保存有推广参数,任务分配模块用于将任务分配给推广者。
在本公开的示例性实施方式中,参考图5,图5示意性示出了根据本公开的示例性实施方式的实现推广任务处理方法的示意图,如图5所示,步骤1将各个推广者的历史操作记录输入模型计算引擎,步骤2通过模型计算引擎计算出推广能力模型,其中,推广能力模型中保存的数据为推广参数,在步骤3中推广中心调用推广能力模型,完成步骤4,得到最低成本的任务分配方案,步骤5按照任务分配方案将推广任务分配给指定推广者,按任务进行推广,在步骤6中,推广中心可以根据具体情况终止任务推广,以应对紧急情况,在步骤7中,按任务完成情况将指定推广者的推广记录保存至历史操作记录中,***自动分析流量来源属于哪个推广者,当一次推广结束后,根据推广者分类统计流量情况,写入历史推广记录表,随着历史推广记录表数据量增大,推广能力模型会更加精准,从而达到***的良性闭环迭代。
在本公开的示例性实施方式中,一次完整的推广任务处理过程包括5个阶段,参考图6,图6示意性示出了根据本公开的示例性实施方式的实现推广任务处理方法的整体流程图,如图6所示,整体流程包括分推广能力模型生成阶段61、推广中心确认需求并进行动态规划阶段63、推广者按照分配结果领取任务并进行推广阶段65、推广中心干涉阶段67、推广结果记录阶段69。
在本公开的示例性实施方式中,推广能力模型即为推广参数,模型计算引擎根据推广者集合中各推广者的历史推广记录,得到推广者集合中各推广者推广不同数量的对象所需要的推广成本;根据推广成本,得到推广参数。其中,对象可以为用户、也可以为流量等,本公开中不做限制。
在本公开的示例性实施方式中,推广能力模型生成阶段61中模型的生成过程可以包括以下5个步骤。
第1步:通过模型计算引擎查询全量历史推广记录;
第2步:按照推广者对推广记录进行分类;
第3步:针对每个推广者,求出历史推广记录中每次推广第一个用户的成本的平均值,作为该推广者推广第一个用户的平均成本;以此类推,求出该推广者从第一个到最大推广人数,推广每一个用户的平均成本;
第4步:按照第3步,依次处理每个推广者的历史推广记录;
第5步:得到一个二维矩阵,该二维矩阵与推广参数相同,即为推广能力模型。
在本公开的示例性实施方式中,以计算推广者A的推广成本为例,说明推广能力模型生成阶段61中模型的生成过程。推广者A的4次推广记录如表2所示,分别为[1,1,2,3,4,5],[1,2,3],[1,2,3,4,5,6,7],[1,3,4,6],将推广者A在这4次推广过程中,从推广第一个人开始到推广最大人数,依次计算平均推广成本,例如,推广者A推广第一个人的平均推广成本为(1+1+1+1)÷4=1,推广第二个人的平均成本为(1+2+2+3)÷4=2,依次计算即可得到推广者A的推广参数。采用相同的方法,即可求得推广者B、推广者C等推广者的推广参数,各个推广者的推广参数的集合即为最终需要的推广参数,推广能力模型根据推广参数确定最小成本分配方案。
在本公开的示例性实施方式中,推广中心确认需求并进行动态规划阶段63的过程可以包括以下4个步骤。
第1步:推广中心接到一次推广任务时,确认推广预算(成本)和推广目标人数;
第2步:推广中心基于推广能力模型,使用动态规划算法,规划最低成本的推广任务 分配方案;
第3步:动态规划算法关注三个要素:分配给谁、分配给他多少任务目标、分配给他多少成本;
第4步:动态规划算法按照上述要素,输出结果。例如,输出的结果可以为分配给推广者A使用50成本推广38人,分配给推广者B使用15成本推广13人,分配给推广者C使用35成本推广20人。
其中,在第2步中,推广中心基于推广能力模型,使用动态规划算法,规划最低成本的推广任务分配方案的具体过程参考图4,如图4所示,确定状态阶段41指的是通过确认最后一步的方式将总问题化解为子问题,在本公开中进行任务推广的场景中,假设需要推广n个人,则可以分解为n-1个人的成本和第n个人的成本,依次类推可以拆解为第1,2,3...n的成本;确定转移方程阶段43为通过上述状态确认阶段,得出状态转移方程为f[i][v]=min{f[i-1][v],f[i-1][v–Ci]+Wi},即求得最小成本的函数;开始和边界条件45是判断最后一个被推广用户的成本不能超出总成本,该问题在实际场景中可以忽略(因为单个用户成本很低);计算顺序47即采用从f(0)开始的备忘录模式,具体计算方式为递归。
在本公开的示例性实施方式中,推广者按照分配结果领取任务并进行推广阶段65可以包括以下5个步骤。
第1步:推广者先查询推广中心的任务分配模块,查看是否有分配给自己的推广任务;
第2步:如果没有则流程结果,如果有分配给自己的推广任务,则浏览自己的推广任务列表;
第3步:推广者选择适合自己的推广任务,在***上领取该推广任务,该推广任务会限制时效、推广目标要求、推广成本(对推广者来说是推广奖励);
第4步:推广者按照任务要求进行推广,为整体推广任务引入流量;
第5步:***自动确认流量来源,如确认推广者完成任务则自动给推广者发放奖励。
在本公开的示例性实施方式中,参考图7,图7示意性示出了根据本公开的示例性实施方式的推广任务处理的技术流程图,如图7所示,jimdb是一个以内存为中心的键值数据库,推广者调用开始推广接口(步骤1),活动引擎将数据写入jimdb缓存(步骤4),同时异步将开始推广入库(步骤5),推广信息同时存储在jimdb缓存和mysql数据库中;助力者点击推广者链接时,调用助力接口(步骤2),活动引擎检索jimdb缓存(步骤4),如果有对应的推广信息,则提取推广信息,并将助力结果也写入jimdb(步骤4)中,同时执行异步入库(步骤5),异步事件(步骤6),异步事件是推广达标的后续事件,例如发放虚拟物品奖励(步骤9)、微信推送达标消息(步骤10)、关注店铺(步骤11)等;推广者和助力者定期签到(步骤3),调用签到接口,以维持用户日活跃度,该功能会直接触发异步事件(步骤6)中的发送奖励(步骤9),发放少额奖励。通过定时任务,对数据库数据(步骤5)和jimdb缓存数据(步骤4)进行一致性校验(步骤7),避免出现数据不一致问题;如果触发数据不一致的问题,会执行托底逻辑(步骤8),对整个功能加锁,然后从数据库读取数据并写入jimdb缓存,确认数据一致后,解锁,继续提供服务。
在本公开的示例性实施方式中,推广中心干涉阶段67是用于推广中心紧急干涉推广任务,将正在推广途中的全部推广任务终止,用于紧急情况下的避险。推广者进行推广任务时,需要先查询推广中心的状态控制模块,如果校验状态为开,则允许推广,如果校验状态为关,则禁止推广。因此,当推广中心状态关闭时,所有推广即终止,以保证流量上限可控。
在本公开的示例性实施方式中,推广结果记录阶段69通过***自动分析流量来源属于哪个推广者,当一次推广结束后,根据推广者分类统计流量情况,写入历史推广记录表。随着历史推广记录表数据量增大,推广能力模型会更加精准,从而达到***的良性闭环迭代。
在本公开的示例性实施方式中,使用本公开提出的推广任务处理方法,一方面,可以降低推广成本,解决了成本较高的推广者过量占用推广成本的问题。基于每个推广者历史推广记录,计算该推广者推广每一个用户的成本,从而得出该推广者推广到n个用户分别需要的成本,即推广能力。将每个推广者的推广能力模型聚合,利用动态规划算法,计算一次推广时,指定哪些推广者,为这些推广者分别分配多少推广任务时,总成本最低。另一方面,能够较为精准的控制社交流量,解决了社交流量不可控导致的目标达成和客诉的互斥矛盾。基于动态规划算法,对上述推广能力模型动态分配,从而在分配任务初期,即可计算可达成流量,并依此设置推广中心的阈值,从而在完成总推广目标的同时,使每个推广者获得预期收益,避免客户投诉。
应当注意,尽管在附图中以特定顺序描述了本公开中方法的各个步骤,但是,这并非要求或者暗示必须按照该特定顺序来执行这些步骤,或是必须执行全部所示的步骤才能实现期望的结果。附加的或备选的,可以省略某些步骤,将多个步骤合并为一个步骤执行,以及/或者将一个步骤分解为多个步骤执行等。
进一步的,本示例实施方式中还提供了一种推广任务处理装置。
图8示意性示出了本公开的示例性实施方式的推广任务处理装置的方框图。参考图8,根据本公开的示例性实施方式的推广任务处理装置8可以包括任务获取模块81、任务确定模块83、任务分配模块85。
具体的,任务获取模块81可以被配置为获取待推广任务;任务确定模块83可以被配置为利用推广参数,从推广者集合中确定出使执行待推广任务成本最低的推广者子集合;其中,推广参数基于推广者集合中各推广者的历史推广记录而得到;任务分配模块85可以被配置为将待推广任务分配给推广者子集合中的推广者。
根据本公开的示例性实施例,任务确定模块83可以被配置为执行:根据推广者集合中各推广者的历史推广记录,得到推广者集合中各推广者推广不同数量的对象所需的推广成本;根据推广成本,得到推广参数。
根据本公开的示例性实施例,任务确定模块83可以被配置为执行:根据推广参数,确定待推广任务的状态转移方程;其中,状态转移方程为计算最低成本的方程;根据状态转移方程,确定以最低成本完成待推广任务的分配方案;根据分配方案,确定推广者子集合。
根据本公开的示例性实施例,任务分配模块85可以被配置为执行:根据分配方案,将待推广任务分解为多个子任务;其中,子任务包含推广成本和推广数量;将多个子任务,分配给对应的推广者。
根据本公开的示例性实施例,任务分配模块85可以被配置为执行:根据推广者的任务执行数据,确定与推广者对应的推广结果;根据推广结果,确定与推广结果对应的奖励,以便将奖励发送给推广者。
根据本公开的示例性实施例,任务分配模块85可以被配置为执行:向推广者发送任务停止的通知,以便推广者停止任务推广操作。
根据本公开的示例性实施例,任务确定模块83可以被配置为执行:记录与推广者对应的完成待推广任务的推广记录,以便更新历史推广记录,得到更新后的历史推广记录;根据更新后的历史推广记录,更新推广参数,得到更新后的推广参数。
在本公开的示例性实施例中,还提供了一种计算机可读存储介质,其上存储有能够实现本说明书上述方法的程序产品。在一些可能的实施方式中,本发明的各个方面还可以实现为一种程序产品的形式,其包括程序代码,当所述程序产品在终端设备上运行时,所述程序代码用于使所述终端设备执行本说明书上述“示例性方法”部分中描述的根据本发明各种示例性实施方式的步骤。
根据本发明的实施方式的用于实现上述方法的程序产品可以采用便携式紧凑盘只读 存储器(CD-ROM)并包括程序代码,并可以在终端设备,例如个人电脑上运行。然而,本发明的程序产品不限于此,在本文件中,可读存储介质可以是任何包含或存储程序的有形介质,该程序可以被指令执行***、装置或者器件使用或者与其结合使用。
所述程序产品可以采用一个或多个可读介质的任意组合。可读介质可以是可读信号介质或者可读存储介质。可读存储介质例如可以为但不限于电、磁、光、电磁、红外线、或半导体的***、装置或器件,或者任意以上的组合。可读存储介质的更具体的例子(非穷举的列表)包括:具有一个或多个导线的电连接、便携式盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光盘、便携式紧凑盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。
计算机可读信号介质可以包括在基带中或者作为载波一部分传播的数据信号,其中承载了可读程序代码。这种传播的数据信号可以采用多种形式,包括但不限于电磁信号、光信号或上述的任意合适的组合。可读信号介质还可以是可读存储介质以外的任何可读介质,该可读介质可以发送、传播或者传输用于由指令执行***、装置或者器件使用或者与其结合使用的程序。
可读介质上包含的程序代码可以用任何适当的介质传输,包括但不限于无线、有线、光缆、RF等等,或者上述的任意合适的组合。
可以以一种或多种程序设计语言的任意组合来编写用于执行本发明操作的程序代码,所述程序设计语言包括面向对象的程序设计语言—诸如Java、C++等,还包括常规的过程式程序设计语言—诸如“C”语言或类似的程序设计语言。程序代码可以完全地在用户计算设备上执行、部分地在用户设备上执行、作为一个独立的软件包执行、部分在用户计算设备上部分在远程计算设备上执行、或者完全在远程计算设备或服务器上执行。在涉及远程计算设备的情形中,远程计算设备可以通过任意种类的网络,包括局域网(LAN)或广域网(WAN),连接到用户计算设备,或者,可以连接到外部计算设备(例如利用因特网服务提供商来通过因特网连接)。
在本公开的示例性实施例中,还提供了一种能够实现上述方法的电子设备。
所属技术领域的技术人员能够理解,本发明的各个方面可以实现为***、方法或程序产品。因此,本发明的各个方面可以具体实现为以下形式,即:完全的硬件实施方式、完全的软件实施方式(包括固件、微代码等),或硬件和软件方面结合的实施方式,这里可以统称为“电路”、“模块”或“***”。
下面参照图9来描述根据本发明的这种实施方式的电子设备900。图9显示的电子设备900仅仅是一个示例,不应对本发明实施例的功能和使用范围带来任何限制。
如图9所示,电子设备900以通用计算设备的形式表现。电子设备900的组件可以包括但不限于:上述至少一个处理单元910、上述至少一个存储单元920、连接不同***组件(包括存储单元920和处理单元910)的总线930、显示单元940。
其中,所述存储单元存储有程序代码,所述程序代码可以被所述处理单元910执行,使得所述处理单元910执行本说明书上述“示例性方法”部分中描述的根据本发明各种示例性实施方式的步骤。
存储单元920可以包括易失性存储单元形式的可读介质,例如随机存取存储单元(RAM)9201和/或高速缓存存储单元9202,还可以进一步包括只读存储单元(ROM)9203。
存储单元920还可以包括具有一组(至少一个)程序模块9205的程序/实用工具9204,这样的程序模块9205包括但不限于:操作***、一个或者多个应用程序、其它程序模块以及程序数据,这些示例中的每一个或某种组合中可能包括网络环境的实现。
总线930可以为表示几类总线结构中的一种或多种,包括存储单元总线或者存储单元控制器、***总线、图形加速端口、处理单元或者使用多种总线结构中的任意总线结构的局域总线。
电子设备900也可以与一个或多个外部设备1000(例如键盘、指向设备、蓝牙设备等)通信,还可与一个或者多个使得用户能与该电子设备900交互的设备通信,和/或与使得该电子设备900能与一个或多个其它计算设备进行通信的任何设备(例如路由器、调制解调器等等)通信。这种通信可以通过输入/输出(I/O)接口950进行。并且,电子设备900还可以通过网络适配器960与一个或者多个网络(例如局域网(LAN),广域网(WAN)和/或公共网络,例如因特网)通信。如图所示,网络适配器960通过总线930与电子设备900的其它模块通信。应当明白,尽管图中未示出,可以结合电子设备900使用其它硬件和/或软件模块,包括但不限于:微代码、设备驱动器、冗余处理单元、外部磁盘驱动阵列、RAID***、磁带驱动器以及数据备份存储***等。
通过以上的实施方式的描述,本领域的技术人员易于理解,这里描述的示例实施方式可以通过软件实现,也可以通过软件结合必要的硬件的方式来实现。因此,根据本公开实施方式的技术方案可以以软件产品的形式体现出来,该软件产品可以存储在一个非易失性存储介质(可以是CD-ROM,U盘,移动硬盘等)中或网络上,包括若干指令以使得一台计算设备(可以是个人计算机、服务器、终端装置、或者网络设备等)执行根据本公开实施方式的方法。
此外,上述附图仅是根据本发明示例性实施例的方法所包括的处理的示意性说明,而不是限制目的。易于理解,上述附图所示的处理并不表明或限制这些处理的时间顺序。另外,也易于理解,这些处理可以是例如在多个模块中同步或异步执行的。
应当注意,尽管在上文详细描述中提及了用于动作执行的设备的若干模块或者单元,但是这种划分并非强制性的。实际上,根据本公开的实施方式,上文描述的两个或更多模块或者单元的特征和功能可以在一个模块或者单元中具体化。反之,上文描述的一个模块或者单元的特征和功能可以进一步划分为由多个模块或者单元来具体化。
本领域技术人员在考虑说明书及实践这里公开的发明后,将容易想到本公开的其他实施例。本申请旨在涵盖本公开的任何变型、用途或者适应性变化,这些变型、用途或者适应性变化遵循本公开的一般性原理并包括本公开未公开的本技术领域中的公知常识或惯用技术手段。说明书和实施例仅被视为示例性的,本公开的真正范围和精神由权利要求指出。
应当理解的是,本公开并不局限于上面已经描述并在附图中示出的精确结构,并且可以在不脱离其范围进行各种修改和改变。本公开的范围仅由所附的权利要求来限。
Claims (10)
- 一种推广任务处理方法,包括:获取待推广任务;利用推广参数,从推广者集合中确定出使执行所述待推广任务成本最低的推广者子集合;其中,所述推广参数基于所述推广者集合中各推广者的历史推广记录而得到;将所述待推广任务分配给所述推广者子集合中的推广者。
- 根据权利要求1所述的推广任务处理方法,其中,所述推广任务处理方法包括:根据所述推广者集合中各推广者的历史推广记录,得到所述推广者集合中各推广者推广不同数量的对象所需的推广成本;根据所述推广成本,得到所述推广参数。
- 根据权利要求1所述的推广任务处理方法,其中,利用推广参数,从推广者集合中确定出使执行所述待推广任务成本最低的推广者子集合,包括:根据所述推广参数,确定所述待推广任务的状态转移方程;其中,所述状态转移方程为计算最低成本的方程;根据所述状态转移方程,确定以最低成本完成所述待推广任务的分配方案,以确定出所述推广者子集合。
- 根据权利要求3所述的推广任务处理方法,其中,将所述待推广任务分配给所述推广者子集合中的推广者,包括:根据所述分配方案,将所述待推广任务分解为多个子任务;其中,所述子任务包含推广成本和推广数量;将多个所述子任务,分配给对应的所述推广者。
- 根据权利要求1所述的推广任务处理方法,其中,将所述待推广任务分配给所述推广者子集合中的推广者后,所述推广任务处理方法包括:根据所述推广者的任务执行数据,确定与所述推广者对应的推广结果;根据所述推广结果,确定与所述推广结果对应的奖励,以便将所述奖励发送给所述推广者。
- 根据权利要求1所述的推广任务处理方法,其中,将所述待推广任务分配给所述推广者子集合中的推广者后,所述推广任务处理方法还包括:向所述推广者发送任务停止的通知,以便所述推广者停止任务推广操作。
- 根据权利要求1所述的推广任务处理方法,其中,在完成所述待推广任务后,所述推广任务处理方法还包括:记录与所述推广者对应的完成所述待推广任务的推广记录,以便更新所述历史推广记录,得到更新后的历史推广记录;根据所述更新后的历史推广记录,更新所述推广参数,得到更新后的推广参数。
- 一种推广任务处理装置,包括:任务获取模块,被配置为获取待推广任务;任务确定模块,被配置为利用推广参数,从推广者集合中确定出使执行所述待推广任务成本最低的推广者子集合;其中,所述推广参数基于所述推广者集合中各推广者的历史推广记录而得到;任务分配模块,被配置为将所述待推广任务分配给所述推广者子集合中的推广者。
- 一种计算机可读存储介质,其上存储有计算机程序,所述计算机程序被处理器执行时实现权利要求1-7任一项所述的推广任务处理方法。
- 一种电子设备,包括:处理器;以及存储器,被配置为存储所述处理器的可执行指令;其中,所述处理器配置为经由执行所述可执行指令来执行权利要求1-7任一项所述的推广任务处理方法。
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110126981.4A CN113793166A (zh) | 2021-01-29 | 2021-01-29 | 推广任务处理方法及装置、存储介质和电子设备 |
CN202110126981.4 | 2021-01-29 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2022161050A1 true WO2022161050A1 (zh) | 2022-08-04 |
Family
ID=78876873
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2021/140836 WO2022161050A1 (zh) | 2021-01-29 | 2021-12-23 | 推广任务处理方法及装置、存储介质和电子设备 |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN113793166A (zh) |
WO (1) | WO2022161050A1 (zh) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113793166A (zh) * | 2021-01-29 | 2021-12-14 | 北京沃东天骏信息技术有限公司 | 推广任务处理方法及装置、存储介质和电子设备 |
CN114786025B (zh) * | 2022-04-01 | 2024-01-02 | 北京达佳互联信息技术有限公司 | 直播数据处理方法、装置、计算机设备及介质 |
CN114997746B (zh) * | 2022-07-28 | 2022-11-11 | 深圳要易云科技服务有限公司 | 基于医药平台的信息处理方法、装置、设备及存储介质 |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102254276A (zh) * | 2011-06-27 | 2011-11-23 | 百度在线网络技术(北京)有限公司 | 一种用于分配推广应用的推广预算的方法与设备 |
CN102663519A (zh) * | 2012-04-01 | 2012-09-12 | 浙江盘石信息技术有限公司 | 网络广告投放中媒体选择的优化***及方法 |
US20150100295A1 (en) * | 2013-10-09 | 2015-04-09 | Fujitsu Limited | Time series forecasting ensemble |
CN109299940A (zh) * | 2018-08-23 | 2019-02-01 | 众安信息技术服务有限公司 | 一种基于区块链的点对点营销方法及营销*** |
CN111460282A (zh) * | 2020-03-06 | 2020-07-28 | 深圳市元征科技股份有限公司 | 一种产品内容推送方法、装置、服务器及终端设备 |
CN113793166A (zh) * | 2021-01-29 | 2021-12-14 | 北京沃东天骏信息技术有限公司 | 推广任务处理方法及装置、存储介质和电子设备 |
Family Cites Families (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101739639A (zh) * | 2008-11-07 | 2010-06-16 | ***通信集团公司 | 业务推广的方法及*** |
CN109213924B (zh) * | 2017-07-07 | 2023-01-03 | 腾讯科技(深圳)有限公司 | 推广任务分配方法、装置和计算机设备 |
CN107730324A (zh) * | 2017-11-07 | 2018-02-23 | 深圳市玖昔科技发展股份有限公司 | 基于互联网广告推广的流量交易***及方法 |
CN109003146B (zh) * | 2018-08-31 | 2022-07-29 | 百度在线网络技术(北京)有限公司 | 业务数据推广方法、装置、终端和计算机可读存储介质 |
CN110415010A (zh) * | 2019-05-23 | 2019-11-05 | 上海大犀角信息科技有限公司 | 一种互联网广告投放***、方法及其应用*** |
CN110264275B (zh) * | 2019-06-24 | 2020-11-13 | 济南北通信息科技有限公司 | 一种自助式广告分发方法、***、设备及可读存储介质 |
CN112256998B (zh) * | 2019-07-22 | 2024-03-22 | 百度时代网络技术(北京)有限公司 | 一种推广信息管理方法、装置及电子设备 |
CN111127112A (zh) * | 2019-12-30 | 2020-05-08 | 深圳市赛维网络科技有限公司 | 广告投放的方法、装置、设备及存储介质 |
CN112184338B (zh) * | 2020-10-29 | 2021-09-07 | 杭州次元岛科技有限公司 | 一种基于大数据的广告交易*** |
-
2021
- 2021-01-29 CN CN202110126981.4A patent/CN113793166A/zh active Pending
- 2021-12-23 WO PCT/CN2021/140836 patent/WO2022161050A1/zh active Application Filing
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102254276A (zh) * | 2011-06-27 | 2011-11-23 | 百度在线网络技术(北京)有限公司 | 一种用于分配推广应用的推广预算的方法与设备 |
CN102663519A (zh) * | 2012-04-01 | 2012-09-12 | 浙江盘石信息技术有限公司 | 网络广告投放中媒体选择的优化***及方法 |
US20150100295A1 (en) * | 2013-10-09 | 2015-04-09 | Fujitsu Limited | Time series forecasting ensemble |
CN109299940A (zh) * | 2018-08-23 | 2019-02-01 | 众安信息技术服务有限公司 | 一种基于区块链的点对点营销方法及营销*** |
CN111460282A (zh) * | 2020-03-06 | 2020-07-28 | 深圳市元征科技股份有限公司 | 一种产品内容推送方法、装置、服务器及终端设备 |
CN113793166A (zh) * | 2021-01-29 | 2021-12-14 | 北京沃东天骏信息技术有限公司 | 推广任务处理方法及装置、存储介质和电子设备 |
Also Published As
Publication number | Publication date |
---|---|
CN113793166A (zh) | 2021-12-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2022161050A1 (zh) | 推广任务处理方法及装置、存储介质和电子设备 | |
CN113656179B (zh) | 云计算资源的调度方法及装置、电子设备和存储介质 | |
CN109753356A (zh) | 一种容器资源调度方法、装置及计算机可读存储介质 | |
US20150026430A1 (en) | Virtual data storage service with sparse provisioning | |
US10678594B2 (en) | System and method for optimizing resource allocation using GPU | |
US20110010343A1 (en) | Optimization and staging method and system | |
WO2024016596A1 (zh) | 容器集群调度的方法、装置、设备及存储介质 | |
CN111752944B (zh) | 数据分摊方法、装置、计算机设备及存储介质 | |
US20200117448A1 (en) | Methods and Systems for Managing Agile Development | |
CN105574141A (zh) | 一种对数据库进行数据迁移的方法和装置 | |
WO2022216490A1 (en) | Intelligent scheduling using a prediction model | |
CN111309712A (zh) | 基于数据仓库的优化任务调度方法、装置、设备及介质 | |
CN102970355B (zh) | 通过挂起承租人来管理数据中心的容量的方法和设备 | |
CN114020469A (zh) | 基于边缘节点的多任务学习方法、装置、介质与设备 | |
US20230186180A1 (en) | Information processing system, information processing device, control method of information processing device, and control program of information processing device | |
US20180247273A1 (en) | Dynamic schedule creation based on knowledge | |
US11140512B1 (en) | System for location-based determinations using common regions | |
CN115729687A (zh) | 任务调度方法、装置、计算机设备、存储介质 | |
US20210295206A1 (en) | Power awareness systems and processes | |
US20200293977A1 (en) | System and method for concurrent processing of work items | |
US20230352939A1 (en) | Cognitive framework for improving responsivity in demand response programs | |
US11409561B2 (en) | System and method for schedule optimization | |
US12052265B1 (en) | Generating resources based on timestamps | |
CN111680867B (zh) | 一种资源配给的方法、装置和电子设备 | |
CN110147943B (zh) | 一种人员管理方法和相关装置 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 21922640 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 21922640 Country of ref document: EP Kind code of ref document: A1 |