Service data estimation method and device
Patent Information
- Application Number
- CN202411264644.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-10
- Publication Date
- 2025-01-28
AI Technical Summary
The existing technology has low accuracy when estimating business data, especially the growth of business data of supplier companies is greatly affected by cooperative companies. When calculating subsequent business growth directly through its own data derivation in previous years, the accuracy is low.
Provide a business data estimation method. By determining the stable customers and non -stable customers of the enterprise, obtain its characteristic information and enter it to the pre -training models, obtain basic business data and weighing information, and finally determine the target business data.
Through the fundamental traceability from the business business, fully consider the impact of non -stable customers, improve the accuracy of business data estimation, and solve the problem of low accuracy in existing technology.
Smart Images
Figure CN119379353A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of enterprise management, and in particular to a business data estimation method. Background Art
[0002] Business volume, also known as "operation volume", generally refers to the output or sales volume of an enterprise's products during the reporting period. It is the basis for cost behavior research, variable cost calculation, and volume-cost-profit analysis. Therefore, forecasting the business volume of an enterprise within a preset time period before production, such as forecasting the business volume for the next year, can provide guidance for the company's next production scheduling plan.
[0003] In the existing technology, most of the companies that spontaneously sell to individuals calculate the subsequent business growth based on their own data from previous years. However, in reality, there is a special group of companies, namely suppliers, whose business data growth is affected by the cooperating companies. And different from the companies that spontaneously sell to individuals, due to the large base of cooperation between companies, the growth of their business data is greatly affected by the companies. If the subsequent business growth is calculated directly through the data from previous years, the accuracy is low. Summary of the invention
[0004] In view of this, an object of the present invention is to provide a business data estimation method, aiming to solve the problem of low accuracy in business data estimation in the prior art.
[0005] One aspect of the present invention provides a service data estimation method, the method comprising: Determine an enterprise to be estimated for which business data estimation is required, obtain corresponding transaction information of the enterprise to be estimated within a historical period, and determine stable customers and unstable customers of the enterprise to be estimated based on the transaction information; Respectively obtaining characteristic information of the stable customers and the unstable customers, and respectively determining estimated business volumes of the stable customers and the unstable customers according to the characteristic information of the stable customers and the unstable customers; Inputting the characteristic information and estimated business volume of the stable customers into a pre-trained basic business data determination model to obtain basic business data, and inputting the characteristic information, estimated business volume, and the rate of change between the current business volume and the estimated business volume of the unstable customers into a pre-trained trade-off business data determination model to obtain trade-off information; The target business data is determined according to the basic business data and the trade-off information, and the business data is pushed to the corresponding enterprise to be estimated.
[0006] Furthermore, in the above-mentioned business data estimation method, before the step of inputting the characteristic information of the stable customers and the estimated business volume into the pre-trained basic business data determination model to obtain the basic business data, the step further includes: Collecting historical feature information, historical business volume, and corresponding transaction volume of enterprises cooperating with a preset number of stable customers to establish a training data set for the basic business data determination model; The training data set of the basic business data determination model is input into a first preset neural network for deep learning training to obtain the basic business data determination model.
[0007] Furthermore, in the above-mentioned business data estimation method, before the step of inputting the characteristic information of the unstable customer, the estimated business volume, and the rate of change of the current business volume and the estimated business volume into the pre-trained trade-off business data determination model to obtain the trade-off information, the step further includes: Collecting historical feature information, historical business volume, business volume change rate and corresponding historical trade-off information of a preset number of unstable customers to establish a training data set for the trade-off business data determination model; The training data set of the trade-off business data determination model is input into a second preset neural network for deep learning training to obtain the trade-off business data determination model.
[0008] Furthermore, in the above-mentioned business data estimation method, wherein the characteristic information includes a change in the amount of business data in the historical time period and a plurality of influencing factors affecting the change in the amount of business data, the step of determining the estimated business amounts of the stable customers and the unstable customers respectively according to the characteristic information of the stable customers and the unstable customers comprises: Determine a mapping relationship between the business data volume change and the impact factor according to the business data volume change and the historical value of the impact factor; The value of the influencing factor within a preset time period is obtained, and the corresponding estimated business volume is determined according to the mapping relationship.
[0009] Furthermore, in the above-mentioned business data estimation method, the step of determining the stable customers and the unstable customers of the enterprise to be estimated according to the transaction information comprises: Determine the transaction customer and the corresponding cooperation time, transaction quantity, transaction frequency, and repurchase rate based on the transaction information; The stickiness value between the transaction customer and the enterprise to be estimated is determined according to the cooperation time, transaction quantity, transaction frequency, and repurchase rate, and the transaction customer is determined to be a stable customer or an unstable customer according to the stickiness value.
[0010] Furthermore, in the above-mentioned business data estimation method, before the step of determining the stickiness value between the transaction customer and the enterprise to be estimated according to the cooperation time, transaction quantity, transaction frequency, and repurchase rate, the following step is further included: The cooperation time, transaction quantity, transaction frequency, and repurchase rate are processed for missing values, outliers, and normalization.
[0011] Furthermore, in the above-mentioned business data estimation method, the calculation formula of the stickiness value is: ; in, T For cooperation time, C is the transaction quantity, F is the transaction frequency, R is the repurchase rate, α and β They are adjustment parameters respectively.
[0012] Another object of the present invention is to provide a service data estimation device, the device comprising: A collection module is used to determine the enterprise to be estimated that needs to be estimated for business data, obtain the corresponding transaction information of the enterprise to be estimated in a historical time period, and determine the stable customers and unstable customers of the enterprise to be estimated according to the transaction information; A determination module, used to respectively obtain characteristic information of the stable customers and the unstable customers, and respectively determine the estimated business volumes of the stable customers and the unstable customers according to the characteristic information of the stable customers and the unstable customers; An input module, used to input the characteristic information and estimated business volume of the stable customers into a pre-trained basic business data determination model to obtain basic business data, and input the characteristic information, estimated business volume, and the rate of change between the current business volume and the estimated business volume of the unstable customers into a pre-trained trade-off business data determination model to obtain trade-off information; The estimation module is used to determine the target business data according to the basic business data and the trade-off information, and push the business data to the corresponding enterprise to be estimated.
[0013] Another object of the present invention is to provide a readable storage medium having a computer program stored thereon, wherein the program implements the steps of the above method when executed by a processor.
[0014] Another object of the present invention is to provide an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above method when executing the program.
[0015] The present invention obtains the corresponding transaction information of the enterprise to be estimated, and determines the stable customers and unstable customers of the enterprise to be estimated according to the transaction information; obtains the characteristic information of stable customers and unstable customers respectively, and determines the estimated business volume of stable customers and unstable customers respectively according to the characteristic information; inputs the characteristic information of stable customers and the estimated business volume into the basic business data determination model to obtain the basic business data, and inputs the characteristic information of unstable customers, the estimated business volume, and the change rate of the current business volume and the estimated business volume into the weighing business data determination model to obtain the weighing information; determines the target business data according to the basic business data and the weighing information, and pushes the business data to the corresponding enterprise to be estimated. The business of the enterprise is traced back to its origin, and the influence of unstable customers is fully considered, and the business data of the enterprise is finally estimated, thereby improving the accuracy of the business data estimation. The problem of low accuracy in business data estimation in the prior art is solved. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] Figure 1 A flowchart of a business data estimation method provided by a first embodiment of the present invention; Figure 2 This is a structural block diagram of a service data estimation device provided in the third embodiment of the present invention.
[0017] The following specific implementation manner will further illustrate the present invention in conjunction with the above-mentioned drawings. DETAILED DESCRIPTION
[0018] In order to facilitate the understanding of the present invention, the present invention will be described more fully below with reference to the relevant drawings. Several embodiments of the present invention are given in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive.
[0019] It should be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may be a central element. When an element is considered to be "connected to" another element, it may be directly connected to the other element or there may be a central element at the same time. The terms "vertical", "horizontal", "left", "right" and similar expressions used herein are for illustrative purposes only.
[0020] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which the present invention belongs. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed types.
[0021] How to improve the accuracy of business data estimation will be described in detail below with reference to specific embodiments and drawings.
[0022] Embodiment 1 See also Figure 1 , which shows a business data estimation method in a first embodiment of the present invention, and the method includes steps S10 to S13.
[0023] Step S10, determining an enterprise to be estimated that needs to perform business data estimation, obtaining corresponding transaction information of the enterprise to be estimated within a historical time period, and determining stable customers and unstable customers of the enterprise to be estimated based on the transaction information.
[0024] Among them, in the embodiment of the present invention, the enterprises to be estimated are mainly those in the role of "suppliers", whose cooperating customers are basically enterprises, and the business data is greatly affected by customers. For example, a certain enterprise mainly produces a certain component, and the component is mainly supplied to multiple enterprises. The production volume of the component of this enterprise mainly depends on the demand of the cooperating customers.
[0025] In order to facilitate the analysis of the company's cooperative customers, according to the company's transaction information in the historical period, the cooperative customers are divided into stable customers and unstable customers. Specifically, the transaction information of the past three or five years can be selected. The transaction information can include the number of transactions, cooperation time, etc. Through these indicator data, the company's customers can be divided into stable customers and unstable customers. To a certain extent, the traceability of the company's business data is achieved, and the impact of stable customers and unstable customers on business data is considered separately in the future to estimate the company's business data.
[0026] Step S11 , acquiring characteristic information of the stable customers and the unstable customers respectively, and determining estimated business volumes of the stable customers and the unstable customers respectively according to the characteristic information of the stable customers and the unstable customers.
[0027] Among them, characteristic information of stable customers and unstable customers is obtained, and the estimated business volume of stable customers and unstable customers can be determined based on these characteristic information. Since the business volume of stable customers and unstable customers mainly depends on their own spontaneous sales, their respective business estimated volumes can be directly determined through their respective characteristic information. Specifically, the characteristic information includes changes in the amount of business data within a historical time period and influencing factors that affect the amount of business data. The mapping relationship between the changes in the amount of business data and the influencing factors is determined based on historical data, so that the value of the influencing factor can be determined and the estimated business volume can be obtained using the mapping relationship. Exemplarily, the influencing factors may include human resources data, price, whether there are promotional activities, etc.
[0028] Step S12, input the characteristic information and estimated business volume of the stable customers into the pre-trained basic business data determination model to obtain basic business data, and input the characteristic information, estimated business volume and the rate of change of the current business volume and the estimated business volume of the unstable customers into the pre-trained trade-off business data determination model to obtain trade-off information.
[0029] Specifically, the impact of stable customers is first analyzed to obtain characteristic information of stable customers and the corresponding estimated business volume, which are input into the trained basic business data determination model to obtain basic business data, wherein the basic business data determination model is trained with a training data set consisting of characteristic information and business volume of historical stable customers and actual transaction quantities with the enterprise to be estimated. Through training, the model can grasp the inherent logic of the transaction quantity between the characteristic information and corresponding business volume of stable customers and the enterprise to be estimated, so that the transaction quantity with the enterprise to be estimated can be estimated after the characteristic information and corresponding estimated business volume of stable customers are known. Exemplarily, in the specific implementation, the training data set of the basic business data determination model is input into a first preset neural network for deep learning training to obtain the basic business data determination model, wherein the first neural network can select a fully connected neural network (Fully Connected Neural Networks, referred to as FCNNs) or a recurrent neural network (RNN).
[0030] Furthermore, the impact of unstable customers is analyzed. Similarly, historical characteristic information, business volume and business volume change rate of unstable customers are collected to form a training data set for model training to obtain a weighed business data determination model, wherein the business volume change rate is determined by the data period of the predicted business volume. For example, business estimation, information collection and business change rate are all calculated on an annual basis. The difference is that due to the instability of unstable customers, the number of transactions between the enterprise to be estimated and the unstable customers will fluctuate. Therefore, considering the change rate of business volume, the probability distribution information of the number of transactions between the unstable customers and the enterprise to be estimated is obtained. Through training, the model can grasp the characteristic information of unstable customers and the corresponding business volume, the probability distribution information of the number of transactions between the business volume change rate and the enterprise to be estimated, that is, the internal logic of the weighed information, so that the probability distribution information of the transaction number can be reasonably predicted. Specifically, the training data set of the weighed business data determination model is input into the second preset neural network for deep learning training to obtain the weighed business data determination model, wherein the second neural network can adopt convolutional neural networks (Convolutional Neural Networks, referred to as CNNs) or deep neural networks (Deep Neural Networks, referred to as DNNs).
[0031] Step S13, determining target business data according to the basic business data and the trade-off information, and pushing the business data to the corresponding enterprise to be estimated.
[0032] Among them, the basic business data is determined by stable customers, which is the main business data of the enterprise to be estimated. The trade-off information is determined by unstable customers. The trade-off information includes the probability distribution of the transaction quantity with the enterprise to be estimated. For example, the transaction quantity has a 30% probability of being 0 and a 50% probability of being 200, etc., so that the final estimated business data can be determined based on the basic business data and the trade-off information.
[0033] In summary, the business data estimation method in the above embodiment of the present invention obtains the corresponding transaction information of the enterprise to be estimated, and determines the stable customers and unstable customers of the enterprise to be estimated based on the transaction information; obtains the characteristic information of stable customers and unstable customers respectively, and determines the estimated business volume of stable customers and unstable customers respectively based on the characteristic information; inputs the characteristic information of stable customers and the estimated business volume into the basic business data determination model to obtain the basic business data, and inputs the characteristic information of unstable customers, the estimated business volume, and the change rate of the current business volume and the estimated business volume into the weighing business data determination model to obtain the weighing information; determines the target business data based on the basic business data and the weighing information, and pushes the business data to the corresponding enterprise to be estimated. It traces back to the root of the enterprise's business, and fully considers the impact of unstable customers, and finally estimates the business data of the enterprise, thereby improving the accuracy of the business data estimation. It solves the problem of low accuracy in business data estimation in the prior art.
[0034] Embodiment 2 The second embodiment of the present invention further provides a business data estimation method. The business data estimation method in this embodiment is different from the business data estimation method in the first embodiment in that the step of determining the stable customers and the unstable customers of the enterprise to be estimated according to the transaction information includes: Determine the transaction customer and the corresponding cooperation time, transaction quantity, transaction frequency, and repurchase rate based on the transaction information; The stickiness value between the transaction customer and the enterprise to be estimated is determined according to the cooperation time, transaction quantity, transaction frequency, and repurchase rate, and the transaction customer is determined to be a stable customer or an unstable customer according to the stickiness value.
[0035] Specifically, transaction information includes cooperation time, transaction quantity, transaction frequency and repurchase rate. Based on these data, the stickiness value between the customer and the enterprise to be estimated can be calculated. By comparing with the stickiness value standard, it can be determined whether the customer is a stable customer or an unstable customer. In addition, before calculating the stickiness value, data preprocessing is performed, including missing value, outlier and normalization processing.
[0036] Exemplarily, the viscosity value is calculated as: ; in, T For cooperation time, C is the transaction quantity, F is the transaction frequency, R is the repurchase rate, α and β They are adjustment parameters. It should be noted that the influence of cooperation time, transaction quantity, transaction frequency and repurchase rate on customer stickiness is comprehensively considered. Each part has been standardized and different nonlinear functions have been used to reflect the complex effect of various factors on the stickiness value. The adjustment parameters introduced in the formula allow fine-tuning of the model. Specifically, the Sigmoid function can be used to convert the cooperation time T into a value between 0 and 1, which is expressed as the weight of the stickiness value contribution. In this way, the system can flexibly respond to different situations of cooperation time. The use of logarithmic function to calculate the stickiness value contribution of the transaction quantity C can effectively balance the impact of the transaction quantity on the result and prevent the stickiness value from being abnormally high due to extreme quantity. The square root function ensures that the increase in frequency will not increase the stickiness value linearly or even exponentially, thereby avoiding excessive fluctuations in the stickiness value due to changes in frequency and maintaining the stability of the system. The fractional form can delicately adjust the impact of the repurchase rate R on the stickiness value to avoid the impact of extreme situations. By treating time, quantity, frequency and repurchase rate differently, it can avoid abnormal stickiness values caused by extreme values of a certain factor, while accurately reflecting the actual impact of each factor on the stickiness of the cooperative relationship, and through multiplication, the marginal effect of each factor will be reflected in the stickiness value. For example, the increase in transaction frequency will jointly determine the improvement in stickiness value with other factors. This method can reflect the synergy of various factors to a certain extent.
[0037] In summary, the business data estimation method in the above embodiment of the present invention obtains the corresponding transaction information of the enterprise to be estimated, and determines the stable customers and unstable customers of the enterprise to be estimated based on the transaction information; obtains the characteristic information of stable customers and unstable customers respectively, and determines the estimated business volume of stable customers and unstable customers respectively based on the characteristic information; inputs the characteristic information of stable customers and the estimated business volume into the basic business data determination model to obtain the basic business data, and inputs the characteristic information of unstable customers, the estimated business volume, and the change rate of the current business volume and the estimated business volume into the weighing business data determination model to obtain the weighing information; determines the target business data based on the basic business data and the weighing information, and pushes the business data to the corresponding enterprise to be estimated. It traces back to the root of the enterprise's business, and fully considers the impact of unstable customers, and finally estimates the business data of the enterprise, thereby improving the accuracy of the business data estimation. It solves the problem of low accuracy in business data estimation in the prior art.
[0038] Embodiment 3 See also Figure 2 , shown is a service data estimation device proposed in the third embodiment of the present invention, the device comprising: The collection module 100 determines the enterprise to be estimated that needs to be estimated for business data, obtains the corresponding transaction information of the enterprise to be estimated in a historical time period, and determines the stable customers and unstable customers of the enterprise to be estimated according to the transaction information; A determination module 200, configured to respectively obtain characteristic information of the stable customers and the unstable customers, and respectively determine the estimated business volumes of the stable customers and the unstable customers according to the characteristic information of the stable customers and the unstable customers; An input module 300 is used to input the characteristic information and estimated business volume of the stable customers into a pre-trained basic business data determination model to obtain basic business data, and input the characteristic information, estimated business volume, and the rate of change between the current business volume and the estimated business volume of the unstable customers into a pre-trained trade-off business data determination model to obtain trade-off information; The estimation module 400 is used to determine target business data according to the basic business data and the trade-off information, and push the business data to the corresponding enterprise to be estimated.
[0039] Furthermore, the above-mentioned business data estimation device, wherein before the step of inputting the characteristic information of the stable customers and the estimated business volume into the pre-trained basic business data determination model to obtain the basic business data, further comprises: Collecting historical feature information, historical business volume, and corresponding transaction volume of enterprises cooperating with a preset number of stable customers to establish a training data set for the basic business data determination model; The training data set of the basic business data determination model is input into a first preset neural network for deep learning training to obtain the basic business data determination model.
[0040] Furthermore, in the above-mentioned service data estimation device, before the step of inputting the characteristic information of the unstable customer, the estimated service volume, and the rate of change of the current service volume and the estimated service volume into the pre-trained trade-off service data determination model to obtain the trade-off information, the step further includes: Collecting historical feature information, historical business volume, business volume change rate and corresponding historical trade-off information of a preset number of unstable customers to establish a training data set for the trade-off business data determination model; The training data set of the trade-off business data determination model is input into a second preset neural network for deep learning training to obtain the trade-off business data determination model.
[0041] Further, in the above-mentioned service data estimation device, wherein the characteristic information includes a change in the service data volume in the historical time period and a plurality of influencing factors affecting the change in the service data volume, the step of determining the estimated service volumes of the stable customers and the unstable customers respectively according to the characteristic information of the stable customers and the unstable customers comprises: Determine a mapping relationship between the business data volume change and the impact factor according to the business data volume change and the historical value of the impact factor; The value of the influencing factor within a preset time period is obtained, and the corresponding estimated business volume is determined according to the mapping relationship.
[0042] Furthermore, in the above-mentioned business data estimation device, the step of determining the stable customers and the unstable customers of the enterprise to be estimated according to the transaction information comprises: Determine the transaction customer and the corresponding cooperation time, transaction quantity, transaction frequency, and repurchase rate based on the transaction information; The stickiness value between the transaction customer and the enterprise to be estimated is determined according to the cooperation time, transaction quantity, transaction frequency, and repurchase rate, and the transaction customer is determined to be a stable customer or an unstable customer according to the stickiness value.
[0043] Furthermore, the business data estimation device, wherein before the step of determining the stickiness value between the transaction customer and the enterprise to be estimated according to the cooperation time, transaction quantity, transaction frequency, and repurchase rate, further comprises: The cooperation time, transaction quantity, transaction frequency, and repurchase rate are processed for missing values, outliers, and normalization.
[0044] Furthermore, in the above-mentioned service data estimation device, the calculation formula of the viscosity value is: ; in, T For cooperation time, C is the transaction quantity, F is the transaction frequency, R is the repurchase rate, α and β They are adjustment parameters respectively.
[0045] The functions or operation steps implemented when the above modules are executed are substantially the same as those in the above method embodiments, and will not be repeated here.
[0046] Embodiment 4 Another aspect of the present invention further provides a readable storage medium having a computer program stored thereon, and when the program is executed by a processor, the steps of the method described in any one of the above-mentioned embodiments 1 to 2 are implemented.
[0047] Embodiment 5 Another aspect of the present invention provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method described in any one of the above-mentioned embodiments 1 to 2 when executing the program.
[0048] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0049] Those skilled in the art will appreciate that the logic and / or steps represented in the flowchart or otherwise described herein, for example, may be considered as an ordered list of executable instructions for implementing logical functions, and may be specifically implemented in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For purposes of this specification, "computer-readable medium" may be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.
[0050] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.
[0051] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or a combination thereof: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.
[0052] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.
[0053] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.
Claims
1. A method for estimating business data, characterized in that: The method comprises: Determine an enterprise to be estimated for which business data estimation is required, obtain corresponding transaction information of the enterprise to be estimated within a historical period, and determine stable customers and unstable customers of the enterprise to be estimated based on the transaction information; Respectively obtaining characteristic information of the stable customers and the unstable customers, and respectively determining estimated business volumes of the stable customers and the unstable customers according to the characteristic information of the stable customers and the unstable customers; Inputting the characteristic information and estimated business volume of the stable customers into a pre-trained basic business data determination model to obtain basic business data, and inputting the characteristic information, estimated business volume, and the rate of change between the current business volume and the estimated business volume of the unstable customers into a pre-trained trade-off business data determination model to obtain trade-off information; The target business data is determined according to the basic business data and the trade-off information, and the business data is pushed to the corresponding enterprise to be estimated.
2. The service data estimation method according to claim 1, characterized in that: Before the step of inputting the characteristic information and estimated business volume of the stable customers into the pre-trained basic business data determination model to obtain the basic business data, the step further includes: Collecting historical feature information, historical business volume, and corresponding transaction volume of enterprises cooperating with a preset number of stable customers to establish a training data set for the basic business data determination model; The training data set of the basic business data determination model is input into a first preset neural network for deep learning training to obtain the basic business data determination model.
3. The business data estimation method according to claim 1, characterized in that: Before the step of inputting the characteristic information of the unstable customer, the estimated business volume, and the change rate of the current business volume and the estimated business volume into the pre-trained trade-off business data determination model to obtain the trade-off information, the step further includes: Collecting historical feature information, historical business volume, business volume change rate and corresponding historical trade-off information of a preset number of unstable customers to establish a training data set for the trade-off business data determination model; The training data set of the trade-off business data determination model is input into a second preset neural network for deep learning training to obtain the trade-off business data determination model.
4. The business data estimation method according to claim 1, characterized in that: The characteristic information includes a change in the amount of business data in the historical time period and a plurality of influencing factors affecting the change in the amount of business data, and the step of determining the estimated business volumes of the stable customers and the unstable customers respectively according to the characteristic information of the stable customers and the unstable customers includes: Determine a mapping relationship between the business data volume change and the impact factor according to the business data volume change and the historical value of the impact factor; The value of the influencing factor within a preset time period is obtained, and the corresponding estimated business volume is determined according to the mapping relationship.
5. The business data estimation method according to claim 1, characterized in that: The step of determining the stable customers and the unstable customers of the enterprise to be estimated according to the transaction information comprises: Determine the transaction customer and the corresponding cooperation time, transaction quantity, transaction frequency, and repurchase rate based on the transaction information; The stickiness value between the transaction customer and the enterprise to be estimated is determined according to the cooperation time, transaction quantity, transaction frequency, and repurchase rate, and the transaction customer is determined to be a stable customer or an unstable customer according to the stickiness value.
6. The service data estimation method according to claim 5, characterized in that: Before the step of determining the stickiness value between the transaction customer and the enterprise to be estimated according to the cooperation time, transaction quantity, transaction frequency, and repurchase rate, the step further includes: The cooperation time, transaction quantity, transaction frequency, and repurchase rate are processed for missing values, outliers, and normalization.
7. The service data estimation method according to claim 6, characterized in that: The viscosity value is calculated as follows: ； in, T For cooperation time, C is the transaction quantity, F is the transaction frequency, R is the repurchase rate, α and β They are adjustment parameters respectively.
8. A service data estimation device, characterized in that: The device comprises: A collection module is used to determine the enterprise to be estimated that needs to be estimated for business data, obtain the corresponding transaction information of the enterprise to be estimated in a historical time period, and determine the stable customers and unstable customers of the enterprise to be estimated according to the transaction information; A determination module, used to respectively obtain characteristic information of the stable customers and the unstable customers, and respectively determine the estimated business volumes of the stable customers and the unstable customers according to the characteristic information of the stable customers and the unstable customers; An input module, used to input the characteristic information and estimated business volume of the stable customers into a pre-trained basic business data determination model to obtain basic business data, and input the characteristic information, estimated business volume, and the rate of change between the current business volume and the estimated business volume of the unstable customers into a pre-trained trade-off business data determination model to obtain trade-off information; The estimation module is used to determine the target business data according to the basic business data and the trade-off information, and push the business data to the corresponding enterprise to be estimated.
9. A readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.
10. An electronic device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method according to any one of claims 1 to 7 when executing the program.