Advertisement channel optimal distribution method and device, electronic equipment and medium

Abstract

The invention provides an optimal distribution method and device of advertisement channels, equipment and a medium. The method comprises the steps of obtaining historical development data of each employee in different advertisement channels, feature information of each advertisement channel and identity information of each employee; calculating a historical development rate of each employee in each advertisement channel based on the historical development data; inputting the obtained various information into a preset development rate prediction model to obtain predicted development rates of each employee in different advertisement channels; performing weighted calculation on the historical development rate and the predicted development rate of each employee to calculate target development rates of each employee in different advertisement channels; and inputting the target development rate of each employee in different advertisement channels into the channel distribution model to obtain an optimal advertisement channel distribution scheme of each employee. Potential performance of each employee in different advertisement channels can be evaluated more scientifically, so that scientificity and accuracy of a distribution result are improved.

Description

Technical Field

[0001] The present disclosure relates to the technical field of data processing, and in particular to an optimization allocation method, device, electronic device and medium for advertising channels. Background Art

[0002] With the rapid development of the Internet advertising industry, the way companies acquire potential customers has changed from traditional marketing methods to relying on third-party advertising platforms. These platforms include but are not limited to search engine advertising, social media advertising, and display advertising, which provide companies with a variety of channels to reach potential customers. However, this shift also brings new challenges: how to effectively allocate potential customers generated by these channels to different sales staff to achieve the best sales results.

[0003] Traditional channel allocation methods mainly rely on personal experience and some simple rules, which often lack systematic scientific support. Due to the lack of full use of historical sales data and customer data, these traditional methods cannot guarantee the scientificity and accuracy of decision-making when allocating potential customers. In addition, due to the lack of effective data support, it is difficult for enterprises to quantitatively evaluate the effects of different allocation plans, which makes it extremely difficult to optimize existing allocation plans. In a rapidly changing market environment, this deficiency makes it impossible for enterprises to adjust their strategies in time to adapt to changes in market and customer needs, resulting in waste of resources and low efficiency. Summary of the invention

[0004] The purpose of the present disclosure is to provide an optimized allocation method, device, electronic device and medium for advertising channels, aiming to use big data and artificial intelligence technology to achieve a more scientific, flexible and efficient channel allocation strategy, thereby improving sales conversion rate and resource utilization efficiency.

[0005] A first aspect of the present disclosure provides a method for optimizing allocation of advertising channels, comprising:

[0006] Obtain each employee's historical development data on different advertising channels, characteristic information of each advertising channel, and identity information of each employee;

[0007] Based on the historical development data, calculate the historical development rate of each employee in each advertising channel;

[0008] Inputting the historical development data, the characteristic information of each advertising channel and the identity information of each employee into a preset development rate prediction model to obtain the predicted development rate of each employee in different advertising channels;

[0009] Performing weighted calculation on the historical development rate and the predicted development rate of each employee to calculate the target development rate of each employee in different advertising channels;

[0010] The target development rate of each employee in different advertising channels is input into the channel allocation model to obtain an advertising channel allocation plan for each employee.

[0011] In an embodiment of the first aspect, it further includes: the historical development data includes the number of historical closed customers and the number of historical total customers of the employee on each advertising channel;

[0012] The characteristic information of each advertising channel includes one or more combinations of video tag characteristics, HTML5 characteristics, crowd package characteristics, and platform characteristics;

[0013] The identity information of each employee includes one or more combinations of work experience, age, gender, time of employment, and whether or not a qualification certificate is available.

[0014] In an embodiment of the first aspect, the calculation formula of the target development rate is:

[0015] Target development rate = α*historical development rate + (1-α)*predicted development rate

[0016] Among them, α is the weight coefficient, which is used to adjust the relative importance of historical development rate and predicted development rate in the calculation of target development rate.

[0017] In an embodiment of the first aspect, the preset development rate prediction model is a DeepFM model, wherein:

[0018] The DeepFM model processes the historical development data containing discrete features and continuous variable features through factorization machines and deep neural networks;

[0019] The DeepFM model is configured with an embedding layer for mapping the characteristic information of the advertising channel and the identity information of the employee into a high-dimensional space to achieve vectorized representation of the information;

[0020] The DeepFM model is designed as a deep structure to extract nonlinear relationships and interactions between multiple features in the historical development data to improve the accuracy of prediction;

[0021] The output of the DeepFM model is the predicted development rate of each employee in different advertising channels, and the predicted development rate is used for the subsequent calculation of the target development rate.

[0022] In an embodiment of the first aspect, the objective function of the channel allocation model is:

[0023]

[0024] Among them, A represents the optimal development rate; R ij represents the target development rate of employee i in advertising channel j; Wj represents the importance of advertising channel j; X ij ∈{0,1} indicates whether employee i is assigned to advertising channel j, which is 1 if assigned and 0 if not.

[0025] In an embodiment of the first aspect, the constraints of the objective function include:

[0026] Channel capacity constraints are used to ensure that the number of employees assigned to each advertising channel does not exceed the capacity limit of the advertising channel;

[0027] Employee allocation constraints are used to ensure that each employee is assigned to at least one advertising channel and at most m advertising channels, where m is an integer greater than 1, representing the maximum number of advertising channels that the employee can effectively manage; it is also used to ensure that if an employee does not have an account for a certain advertising channel, he or she will not be assigned to that advertising channel;

[0028] A framework capacity constraint is used to ensure that the total number of advertising channels assigned to an employee does not exceed the number of accounts that the employee owns or can manage under a specific framework.

[0029] In an embodiment of the first aspect, the calculation formula for the importance of the advertising channel is:

[0030] W j = Advertising channel j historical number of customers / historical total number of customers

[0031] Among them, W j Represents the importance of advertising channel j.

[0032] A second aspect of the present disclosure discloses an optimized distribution device for advertising channels, comprising:

[0033] An acquisition module is used to obtain the historical development data of each employee in different advertising channels, the characteristic information of each advertising channel, and the identity information of each employee;

[0034] A historical development rate calculation module, used to calculate the historical development rate of each employee in each advertising channel based on the historical development data;

[0035] A predicted development rate calculation module, used for inputting the historical development data, the characteristic information of each advertising channel and the identity information of each employee into a preset development rate prediction model to obtain the predicted development rate of each employee in different advertising channels;

[0036] A target development rate calculation module, used for performing weighted calculation on the historical development rate and the predicted development rate of each employee to calculate the target development rate of each employee in different advertising channels;

[0037] The allocation module is used to input the target development rate of each employee in different advertising channels into the channel allocation model to obtain an advertising channel allocation plan for each employee.

[0038] The third aspect of the present disclosure discloses an electronic device, comprising: a processor and a memory; wherein the memory is used to store a computer program; the processor is used to execute the computer program stored in the memory, so that the electronic device executes the method for optimizing the allocation of advertising channels as described in any one of the first aspects.

[0039] A fourth aspect of the present disclosure discloses a computer-readable storage medium having a computer program stored thereon, which, when executed by an electronic device, implements the method for optimizing the allocation of advertising channels as described in any one of the first aspects.

[0040] As described above, the method, device, electronic device and medium for optimizing the allocation of advertising channels disclosed in the present invention at least include the following technical effects:

[0041] (1) By comprehensively utilizing employees’ historical development data, advertising channel feature information, and employee identity information, a data-driven advertising channel allocation method is implemented. This enables a more scientific and accurate assessment of each employee’s potential performance in different advertising channels, thereby improving the scientificity and accuracy of the allocation results.

[0042] (2) It allows for quantitative evaluation of the effects of different advertising channel allocation schemes. By setting objective functions and constraints, it can continuously monitor and optimize allocation strategies. This provides companies with a way to continuously improve and optimize advertising channel allocation to achieve maximum sales results.

[0043] (3) By using the DeepFM model to predict the employee development rate and calculate the target development rate, it is possible to respond to market changes and customer needs in real time and dynamically adjust the advertising channel allocation plan. This enables companies to quickly adapt to market fluctuations, optimize resource allocation, and reduce resource waste.

[0044] (4) Through precise target development rate calculation and optimized channel allocation model, we can ensure that each employee can realize their greatest potential in the most suitable channel, thereby maximizing the development efficiency of each employee, improving overall resource utilization and reducing operating costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 Shown is a schematic diagram of a scene of an electronic device in an embodiment of the present disclosure;

[0046] Figure 2 A flowchart showing a method for optimizing allocation of advertising channels in an embodiment of the present disclosure is shown.

[0047] Figure 3A module schematic diagram showing an optimized allocation device for advertising channels in one embodiment of the present disclosure.

[0048] Figure 4 A schematic diagram of the circuit structure of an electronic device in an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0049] The following describes the embodiments of the present invention by specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.

[0050] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present invention, and thus the drawings only show components related to the present invention rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0051] The following embodiments of the present invention provide a method for recognizing multilingual text, which can be applied to Figure 1 The electronic device shown. The electronic device described in the present invention may include a mobile phone 11 with a wireless charging function, a tablet computer 12, a laptop computer 13, a wearable device, a vehicle-mounted device, an augmented reality (AR) / virtual reality (VR) device, an ultra-mobile personal computer (UMPC), a netbook, a personal digital assistant (PDA), etc. The embodiment of the present invention does not impose any restrictions on the specific type of the electronic device.

[0052] For example, the electronic device may be a station (STAION, ST) in a WLAN with a wireless charging function, a cellular phone, a cordless phone, a Session Initiation Protocol (SIP) phone, a Wireless Local Loop (WLL) station, a Personal Digital Assistant (PDA) device, a handheld device with a wireless charging function, a computing device or other processing device, a computer, a laptop computer, a handheld communication device, a handheld computing device, and / or other devices for communicating on a wireless system and a next generation communication system, such as a mobile terminal in a 5G network, a mobile terminal in a future evolved Public Land Mobile Network (PLMN), or a mobile terminal in a future evolved Non-terrestrial Network (NTN).

[0053] The technical solutions in the embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0054] like Figure 2 As shown, a flow chart of the method for optimizing allocation of advertising channels in an embodiment of the first aspect of the present disclosure is shown, including steps S21-S25.

[0055] Step S21: Obtain the historical development data of each employee in different advertising channels, the characteristic information of each advertising channel, and the identity information of each employee.

[0056] In some embodiments, step S21 involves collecting historical sales data of each employee on different advertising channels. Specifically, the data includes the historical number of customers and the historical total number of customers of the employee on each advertising channel. The data reflects the sales efficiency and effectiveness of the employee on a specific advertising channel and is a key indicator for evaluating the performance and potential of the employee.

[0057] The collection of historical development data involves aggregating and analyzing sales records over a period of time to identify trends and patterns in each employee's performance across different channels.

[0058] Furthermore, characteristic information of each advertising channel is collected, and the characteristic information includes but is not limited to:

[0059] Video tag features: Metadata related to video content, such as tags, categories, and topics, which can help understand the audience positioning and market performance of video content.

[0060] HTML5 features: refers to the HTML5 features supported by the advertising channel, such as animation, graphics, and interactivity, which affect the attractiveness of the advertisement and user engagement.

[0061] Crowd characteristics: Describe the demographic characteristics of the target audience, such as age, gender, geographic location, and consumption habits, which is crucial for precision marketing.

[0062] Platform characteristics: These include the characteristics of the platform where the advertising channel is located, such as the user base, user activity, and platform algorithms, which affect the visibility and effectiveness of the advertisement.

[0063] This feature information can be collected and integrated from advertising platform APIs, market research reports, and user feedback through data analysis tools.

[0064] In addition, it involves collecting the identity information of each employee, including but not limited to:

[0065] Work experience: The number of years an employee has worked in their current position or in a related field, which affects their ability and efficiency in handling complex tasks.

[0066] Age and gender: These demographic characteristics can affect how effectively an employee communicates with a particular audience.

[0067] Time on board: The length of time an employee has served in a company, which may be related to their familiarity with the company’s products and culture.

[0068] Qualifications and certifications: Whether the employee has specific industry qualifications or certifications, which may affect their professional capabilities and credibility in a particular field.

[0069] The collection of employee identity information can be achieved through human resource management systems, employee files and professional certification databases.

[0070] By integrating these multi-dimensional data, the present invention can build a comprehensive data analysis framework for each employee and advertising channel, thereby achieving a more accurate prediction model and a more optimized channel allocation strategy.

[0071] Step S22: Based on the historical development data, calculate the historical development rate of each employee in each advertising channel.

[0072] Specifically, the historical development rate refers to the ratio of the number of customers that an employee has closed deals with on a specific advertising channel to the total number of customers. The calculation formula can be expressed as: Historical development rate = number of closed customers / total number of customers. The number of closed customers refers to the number of customers who actually purchased products or services through a specific advertising channel during a specific period. The total number of customers refers to the number of all potential customers reached through the channel during the same period.

[0073] For example, suppose that in August 2024, employee A reaches 500 potential customers through the search engine advertising channel, and 100 of them complete the purchase. Then, the historical development rate of employee A on this channel will be: 100 / 500 = 0.2

[0074] Step S23: inputting the historical development data, the characteristic information of each advertising channel and the identity information of each employee into a preset development rate prediction model to obtain the predicted development rate of each employee in different advertising channels.

[0075] Specifically, we firstly conduct strict preprocessing on the historical development data of each employee on different advertising channels, the characteristic information of each channel and the identity information data of the employee, including data cleaning to remove noise and outliers, format unification for comparison and analysis, and missing value processing to ensure data integrity. After preprocessing, we will screen out key features that have a significant impact on the predicted development rate from these data, which may include the number of customers the employee has closed, the total number of customers, the click-through rate and conversion rate of the advertising channel, as well as the employee's work experience, age, etc.

[0076] In some embodiments, we use the DeepFM model as the development rate prediction model. The DeepFM model is a powerful tool that can process data sets containing discrete features and continuous variable features, and is particularly suitable for processing complex prediction tasks. The model is trained on historical data and can learn and capture patterns and relationships in the data. Parameter tuning is also performed during the training process to further improve the prediction accuracy of the model. For non-numerical features such as characteristic information of advertising channels and employee identity information, the embedding layer of the DeepFM model can convert them into numerical vectors, allowing the model to process them effectively.

[0077] The preprocessed and vectorized data is then fed into the DeepFM model, which predicts the predicted development rate of each employee in different advertising channels based on the previously learned patterns. These predicted development rates become the key indicators for matching employees and advertising channels, and they will be used in subsequent channel allocation decisions to ensure that each employee is assigned to the channel where they are most likely to succeed.

[0078] Through this detailed and systematic process, the present implementation method can predict each employee's future performance in different advertising channels, provide a scientific basis for the optimal allocation of advertising channels, thereby improving the accuracy and effectiveness of channel allocation, and helping enterprises achieve optimal resource allocation and maximize sales efficiency.

[0079] Step S24: performing weighted calculation on the historical development rate and the predicted development rate of each employee to calculate the target development rate of each employee in different advertising channels.

[0080] Specifically, the purpose of the weighted calculation is to balance the employee's historical performance and predicted potential to provide a more comprehensive performance indicator. This approach allows us to consider both the employee's past sales performance and the forecast model's estimate of their future performance in the allocation decision.

[0081] In the weighted calculation, α is a weight coefficient between 0 and 1, which represents the relative importance of the historical development rate in the target development rate. The higher the value of α, the greater the impact of the historical development rate on the target development rate; the lower the value of α, the greater the impact of the predicted development rate.

[0082] In some embodiments, the target development rate is calculated as follows:

[0083] Target development rate = α*historical development rate + (1-α)*predicted development rate

[0084] Among them, α is the weight coefficient, which is used to adjust the relative importance of historical development rate and predicted development rate in the calculation of target development rate.

[0085] Specifically, this formula combines the historical development rate and the predicted development rate. By adjusting the value of α, it can flexibly reflect the credibility and importance of historical data and predicted data in different situations. The choice of α value can be based on a variety of factors, including the reliability of data, the speed of market changes, the stability of employees, etc. In the case of rapid market changes or large employee turnover, it may be necessary to lower the α value and give more weight to the predicted development rate. On the contrary, in a stable market and workforce, the α value can be increased and more reliance can be placed on historical data. For example, the α value for new employees is 0.8; the α value for old employees is 0.4.

[0086] For each employee on each advertising channel, first determine its historical development rate and predicted development rate, and then apply the above formula to calculate the target development rate based on the selected α value.

[0087] For example, if an employee's historical development rate is 0.15 (i.e. 15%), the predicted development rate is 0.20 (i.e. 20%), and we choose an α value of 0.6, then the target development rate will be calculated as target development rate = 0.6×0.15+0.4×0.20=0.16.

[0088] Step S25: inputting the target development rate of each employee in different advertising channels into the channel allocation model to obtain the optimal advertising channel allocation plan for each employee.

[0089] Specifically, the channel assignment problem is transformed into an integer programming problem, which is a mathematical optimization problem in which the decision variables are integers. In this case, the decision variable represents whether the employee is assigned to a specific advertising channel. The objective function aims to maximize the overall development efficiency. This is usually expressed as the sum of the product of the employee's target development rate and the importance of the advertising channel, multiplied by the decision variable of whether the employee is assigned to the channel.

[0090] In some implementations, the objective function of the channel allocation model is:

[0091]

[0092] Among them, A represents the optimal development rate; R ij represents the target development rate of employee i in advertising channel j; W j represents the importance of advertising channel j; X ij ∈{0,1} represents the decision variable of whether employee i is assigned to advertising channel j, which is 1 if assigned and 0 if not; N represents the total number of employees; M represents the total number of advertising channels.

[0093] Furthermore, in integer programming problems, a series of constraints need to be set to ensure the feasibility and practicality of the solution. In some embodiments, the constraints of the objective function include: channel capacity constraints, employee allocation constraints, and architecture capacity constraints, where:

[0094] The channel capacity constraint ensures that the number of employees assigned to each advertising channel does not exceed the capacity limit of the channel. Channel capacity may be determined by a variety of factors, including the size of the channel, processing power, or budget constraints. This constraint can be expressed as:

[0095]

[0096] Among them, X ij Indicates whether employee i is assigned to advertising channel j, C j is the capacity limit of advertising channel j, and N is the total number of employees.

[0097] The employee assignment constraint consists of two parts: first, ensure that each employee is assigned to at least one advertising channel to fully utilize the potential of each employee; second, ensure that each employee is assigned to at most m advertising channels, where m is a preset parameter representing the maximum number of advertising channels that an employee can effectively manage. In addition, if an employee does not have an account for a certain advertising channel, he should not be assigned to that channel. This constraint can be expressed as:

[0098] and

[0099] Among them, X ijrepresents the decision variable whether employee i is assigned to advertising channel j, and M is the total number of channels.

[0100] The architecture capacity constraint is used to ensure that the total number of advertising channels assigned to an employee does not exceed the number of accounts that the employee owns or can manage under a specific architecture. This constraint can be expressed as:

[0101]

[0102] Among them, A k is the set of all channels under architecture k, A i is the number of accounts owned by employee i under architecture k, and Xij represents the decision variable of whether employee i is assigned to advertising channel j.

[0103] These constraints together constitute a complex integer programming problem, whose goal is to maximize the overall development efficiency while satisfying these constraints. By solving this optimization problem, an optimal employee advertising channel allocation plan can be obtained, which not only takes into account the development efficiency of employees and the importance of channels, but also considers various limiting factors in actual operations, ensuring the feasibility and practicality of the solution.

[0104] In some implementations, the calculation formula for the importance of the advertising channel is:

[0105] W j = Advertising channel j historical number of customers / historical total number of customers

[0106] Among them, W j Represents the importance of advertising channel j.

[0107] Specifically, the importance of advertising channels refers to the relative importance of advertising channel j in historical development activities. This indicator is calculated by comparing the historical number of closed customers and the historical total number of customers of advertising channel j, thereby quantifying the efficiency and effectiveness of each channel.

[0108] The number of customers who completed a purchase refers to the number of customers who actually completed a purchase through advertising channel j during a specific period. This number directly reflects the conversion effect of advertising channel j. The total number of customers refers to the number of all potential customers that advertising channel j reached during the same period. This number includes all customers who saw the ad but did not make a purchase, as well as customers who completed a purchase.

[0109] The calculated importance W jIt will be used in the channel allocation model as a weight parameter for advertising channel j. The higher the importance of a channel, the more attention and resources it should be given in the overall sales strategy. By considering the importance of advertising channels, companies can more scientifically allocate sales personnel to various channels, giving priority to those channels with high efficiency and good results, thereby improving overall sales efficiency and performance. In addition, the importance of advertising channels is a dynamically changing indicator that changes with changes in the market environment and consumer behavior. Therefore, companies need to update this data regularly and re-evaluate the importance of each channel to ensure the timeliness and effectiveness of the channel allocation strategy.

[0110] In order to better illustrate the implementation of the present application, a complete example is listed below.

[0111] Consider an online e-commerce company that attracts potential customers through multiple advertising channels (such as search engine advertising, social media advertising, video platform advertising, etc.). The company has three salespeople (A, B, C) who are responsible for converting these potential customers into actual purchasing customers. The company hopes to optimize advertising channel allocation to improve sales efficiency and conversion rate.

[0112] First, collect each salesperson’s historical sales data on different advertising channels, including the number of closed customers and total number of customers. Collect characteristic information of each advertising channel, such as click-through rate, conversion rate, audience characteristics, etc. Collect each salesperson’s identity information, such as work experience, age, gender, time of employment, qualification certification, etc.

[0113] The historical number of customers and the total number of customers for each salesperson on each advertising channel are calculated to obtain the historical development rate. The DeepFM model is then used to train the prediction model in combination with historical data and the characteristic information of employees and channels to obtain the predicted development rate of each salesperson in different advertising channels. Combining the historical development rate and the predicted development rate, the target development rate of each salesperson in different advertising channels is obtained through weighted calculation. The details are shown in the following table.

[0114] Employees / Channels Historical development rate Predicted development rate Target development rate (α=0.6) AX 0.10 0.15 0.13 AY 0.20 0.18 0.19 AZ 0.15 0.12 0.14 BX 0.08 0.11 0.09 BY 0.18 0.21 0.19 BZ 0.12 0.17 0.14 CX 0.11 0.14 0.12 CY 0.22 0.19 0.21 CZ 0.16 0.13 0.15

[0115] Considering the channel capacity constraint, assuming that the capacity of channels X, Y, and Z are 3, 2, and 2 respectively, it is also necessary to ensure that the employee allocation of each channel does not exceed its capacity. According to the target development rate, the target advertising channel to which each employee should be assigned can be determined:

[0116] Employee A: should be assigned to channel Y because AY has the highest target development rate of 0.19.

[0117] Employee B: should also be assigned to channel Y because BY has the highest target development rate of 0.19.

[0118] Employee C: should be assigned to channel Y, because CY has the highest target development rate of 0.21

[0119] It should be particularly noted that the process or method represented by the flowchart of the above embodiment of the present disclosure can be understood as representing a module, fragment or part of a code including one or more sets of executable instructions configured to implement the steps of a specific logical function or process. And the scope of the preferred embodiment of the present disclosure includes other implementations, in which the functions may not be performed in the order shown or discussed, including performing the functions in a substantially simultaneous manner or in a reverse order according to the functions involved.

[0120] like Figure 3 As shown, the optimized distribution device 30 of the advertising channel disclosed in the present invention is shown. It should be noted that the principle and technical implementation of the optimized distribution device of the advertising channel can refer to the multilingual text recognition method embodiment in the previous embodiment (for example Figure 2 ), so it will not be repeated in this embodiment.

[0121] Specifically, the advertising channel optimization allocation device 30 includes: an acquisition module 31, a historical development rate calculation module 32, a predicted development rate calculation module 33, a target development rate calculation module 34, and an allocation module 35, wherein:

[0122] The acquisition module 31 is used to acquire the historical development data of each employee in different advertising channels, the characteristic information of each advertising channel and the identity information of each employee;

[0123] The historical development rate calculation module 32 is used to calculate the historical development rate of each employee in each advertising channel based on the historical development data;

[0124] The predicted development rate calculation module 33 is used to input the historical development data, the characteristic information of each advertising channel and the identity information of each employee into a preset development rate prediction model to obtain the predicted development rate of each employee in different advertising channels;

[0125] The target development rate calculation module 34 is used to perform weighted calculation on the historical development rate and the predicted development rate of each employee to calculate the target development rate of each employee in different advertising channels;

[0126] The allocation module 35 is used to input the target development rate of each employee in different advertising channels into the channel allocation model to obtain the optimal advertising channel allocation plan for each employee.

[0127] It should be noted that Figure 3Each functional module in the embodiment can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a program instruction product. The program instruction product includes one or a group of program instructions. When the program instruction is loaded and executed on a computer, the process or function according to the present disclosure is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable devices. The program instruction can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium.

[0128] and, Figure 3 The device disclosed in the embodiment can be implemented by other module division methods. The device embodiments shown above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as a group of modules or modules can be combined or dynamically added to another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or modules can be electrical or other forms.

[0129] like Figure 4 As shown, a schematic diagram of the structure of an electronic device in an embodiment of the present disclosure is shown.

[0130] The electronic device can execute the following steps by running the computer program instructions: Figure 2 The method in any one of the items. Exemplarily, the electronic device may be a server group / server, a desktop computer, a laptop computer, etc., or a server / server group in the cloud that communicates remotely with a local terminal, a distributed computing node system, etc.

[0131] The electronic device 40 includes a bus 41, a processor 42, and a memory 43. The processor 42 and the memory 43 can communicate with each other through the bus 41. The memory 43 may store program instructions. The processor 42 implements the method steps in the previous embodiment by running the program instructions in the memory 43, such as Figure 2 Any method.

[0132] The bus 41 may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, although only one thick line is used in the figure, it does not mean that there is only one bus or one type of bus.

[0133] In some embodiments, the processor 42 may be implemented as a central processing unit (CPU), a microprocessing unit (MCU), a system on chip (System On Chip), or a field programmable logic array (FPGA). The memory 73 may include a volatile memory (Volatile Memory) for temporary storage of data when running a program, such as a random access memory (Random Access Memory, RAM).

[0134] The memory 43 may also include a non-volatile memory (non-volatile memory) for data storage, such as a read-only memory (ROM), a flash memory, a hard disk drive (HDD) or a solid-state disk (SSD).

[0135] In some embodiments, the electronic device 40 may further include a communicator 44. The communicator 44 is used to communicate with the outside. In a specific example, the communicator 44 may include one or a group of wired and / or wireless communication circuit modules. For example, the communicator 44 may include one or more of a wired network card, a USB module, a serial interface module, etc. In the embodiment of the present disclosure, a computer-readable storage medium may be provided, characterized in that program instructions are stored, and the program instructions are executed by running, for example Figure 1 The method for optimizing allocation of advertising channels in the embodiment.

[0136] That is, the method steps in the above embodiments are implemented as software or computer code that can be stored in a recording medium (such as a CD ROM, RAM, floppy disk, hard disk or magneto-optical disk), or are implemented as computer code originally stored in a remote recording medium or a non-temporary machine-readable medium downloaded via a network and to be stored in a local recording medium, so that the method represented herein can be stored in such software processing on a recording medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware (such as an ASIC or FPGA).

[0137] In summary, the disclosed method, device, equipment and medium for optimizing the allocation of advertising channels, by comprehensively analyzing employees' historical sales data, advertising channel characteristics and employee identity information, uses a development rate prediction model to predict employees' development rates in different channels, and calculates the target development rate of each employee in combination with historical and predicted data. The method further inputs the target development rate as a key parameter into the channel allocation model, and optimizes the optimal advertising channel allocation plan for each employee by considering constraints such as channel capacity, employee allocation and architecture capacity. The present application improves the accuracy and effectiveness of advertising resource allocation and reduces operating costs through a scientific decision support system.

[0138] The above embodiments are merely illustrative of the principles and effects of the present disclosure, and are not intended to limit the present disclosure. Anyone familiar with the technology may modify or change the above embodiments without violating the spirit and scope of the present disclosure. Therefore, all equivalent modifications or changes made by a person of ordinary skill in the art without departing from the spirit and technical ideas disclosed in the present disclosure shall still be covered by the claims of the present disclosure.

Claims

1. A method for optimizing the allocation of advertising channels, characterized in that: include: Obtain each employee's historical development data on different advertising channels, characteristic information of each advertising channel, and identity information of each employee; Based on the historical development data, calculate the historical development rate of each employee in each advertising channel; Inputting the historical development data, the characteristic information of each advertising channel and the identity information of each employee into a preset development rate prediction model to obtain the predicted development rate of each employee in different advertising channels; Performing weighted calculation on the historical development rate and the predicted development rate of each employee to calculate the target development rate of each employee in different advertising channels; The target development rate of each employee in different advertising channels is input into the channel allocation model to obtain an advertising channel allocation plan for each employee.

2. The method for optimizing the allocation of advertising channels according to claim 1, characterized in that: The historical development data includes the number of historical closed customers and the total number of historical customers of the employee on various advertising channels; The characteristic information of each advertising channel includes one or more combinations of video tag characteristics, HTML5 characteristics, crowd package characteristics, and platform characteristics; The identity information of each employee includes one or more combinations of work experience, age, gender, time of employment, and whether or not there is a qualification certificate.

3. The method for optimizing the allocation of advertising channels according to claim 1, characterized in that: The target development rate is calculated as follows: Target development rate = α*historical development rate + (1-α)*predicted development rate Among them, α is the weight coefficient, which is used to adjust the relative importance of historical development rate and predicted development rate in the calculation of target development rate.

4. The method for optimizing the allocation of advertising channels according to claim 2, characterized in that: The preset development rate prediction model is the DeepFM model, where: The DeepFM model processes the historical development data containing discrete features and continuous variable features through factorization machines and deep neural networks; The DeepFM model is configured with an embedding layer for mapping the characteristic information of the advertising channel and the identity information of the employee into a high-dimensional space to achieve vectorized representation of the information; The DeepFM model is designed as a deep structure to extract nonlinear relationships and interactions between multiple features in the historical development data to improve the accuracy of prediction; The output of the DeepFM model is the predicted development rate of each employee in different advertising channels, and the predicted development rate is used for the subsequent calculation of the target development rate.

5. The method for optimizing the allocation of advertising channels according to claim 2, characterized in that: The objective function of the channel allocation model is: Among them, A represents the optimal development rate, R ij represents the target development rate of employee i in advertising channel j; W j represents the importance of advertising channel j; X ij ∈{0,1} indicates whether employee i is assigned to advertising channel j, which is 1 if assigned and 0 if not.

6. The method for optimizing the allocation of advertising channels according to claim 5, characterized in that: The constraints of the objective function include: Channel capacity constraints are used to ensure that the number of employees assigned to each advertising channel does not exceed the capacity limit of the advertising channel; Employee allocation constraints are used to ensure that each employee is assigned to at least one advertising channel and at most m advertising channels, where m is an integer greater than 1, representing the maximum number of advertising channels that the employee can effectively manage; it is also used to ensure that if an employee does not have an account for a certain advertising channel, he or she will not be assigned to that advertising channel; A framework capacity constraint is used to ensure that the total number of advertising channels assigned to an employee does not exceed the number of accounts that the employee owns or can manage under a specific framework.

7. The method for optimizing the allocation of advertising channels according to claim 5, characterized in that: The calculation formula for the importance of the advertising channel is: W j = Advertising channel j historical number of customers / historical total number of customers Among them, W j Represents the importance of advertising channel j.

8. An optimized distribution device for advertising channels, characterized in that: include: An acquisition module is used to obtain the historical development data of each employee in different advertising channels, the characteristic information of each advertising channel, and the identity information of each employee; A historical development rate calculation module, used for calculating the historical development rate of each employee in each advertising channel based on the historical development data; A predicted development rate calculation module, used for inputting the historical development data, the characteristic information of each advertising channel and the identity information of each employee into a preset development rate prediction model to obtain the predicted development rate of each employee in different advertising channels; A target development rate calculation module, used for performing weighted calculation on the historical development rate and the predicted development rate of each employee to calculate the target development rate of each employee in different advertising channels; The allocation module is used to input the target development rate of each employee in different advertising channels into the channel allocation model to obtain an advertising channel allocation plan for each employee.

9. An electronic device, characterized in that: The electronic device comprises: Processor and memory; Wherein, the memory is used to store computer programs; The processor is used to execute the computer program stored in the memory so that the electronic device executes the method for optimizing allocation of advertising channels as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by an electronic device, the method for optimizing the allocation of advertising channels described in any one of claims 1 to 7 is implemented.

Images