Classification method and applicable online ordering collaboration platform thereof

Abstract

The invention provides a classification method and an applicable online ordering collaboration platform thereof, and the method comprises the following steps: carrying out the preprocessing of original data, and carrying out the feature extraction of the original data, so as to obtain different types of dimension data points; randomly selecting a preset number of dimension data points from different types of dimension data points to form a plurality of cluster groups, wherein each cluster group comprises a plurality of cluster vertexes; the cluster center of each cluster group is calculated, and the cluster center with the difference value range of 0%-1% between the cluster center and all cluster vertexes in the corresponding cluster group is selected as the final cluster center; and calculating the distance between the dimension data point and the cluster center, and carrying out final classification on the clients according to the distance. According to the classification method and the applicable online ordering collaboration platform provided by the invention, grade classification can be carried out on the customers, so that differentiated price management can be carried out on different customers, and a more personalized and effective marketing strategy can be formulated for an enterprise.

Description

Technical Field

[0001] The present application mainly relates to the field of online transactions, and in particular to a classification method and an online ordering collaboration platform applicable thereto. Background Art

[0002] Transactions between enterprises are different from transactions between individual merchants and enterprises. Commodity transactions between enterprises often involve huge transaction volumes, with orders of tens of thousands. As the volume of business continues to increase, the complexity of business management has also increased significantly. For merchants who trade with enterprises, since some corporate customers tend to have large demands and high cooperative stickiness, while others have small demands and low cooperative stickiness, how to grade and manage different customers, and thus formulate personalized and effective marketing strategies for different corporate customers, is an urgent problem for merchants who trade with enterprises. Summary of the invention

[0003] The technical problem to be solved by this application is to provide a classification method and an applicable online ordering collaboration platform, which can classify customers into different levels, thereby performing differentiated price management for different customers and formulating more personalized and effective marketing strategies for enterprises.

[0004] To solve the above technical problems, the present application provides a classification method, which is applicable to an online ordering collaboration platform, and includes the following steps: preprocessing the original data, and performing feature extraction on the original data to obtain different types of dimensional data points; randomly selecting multiple cluster centers, and assigning each of the dimensional data points and the cluster center closest to the dimensional data point to the same cluster group, each of the cluster groups including one cluster center and multiple cluster vertices; recalculating the cluster center of each cluster group, and selecting the cluster center whose difference value between the cluster center and all the cluster vertices in the corresponding cluster group is in the range of 0% to 1% as the final cluster center; calculating the distance between the dimensional data point and the cluster center, and finally classifying the customers according to the distance.

[0005] Optionally, the preprocessing includes data cleaning and / or data conversion of the original data, wherein the data cleaning includes deleting duplicate data, filling in missing data values ​​and / or deleting missing data values.

[0006] Optionally, the different types of dimensional data points include order quantity data points (TO), order amount data points (AOV), order frequency data points (OF) and / or product diversity data points (PD).

[0007] Optionally, the classification method further comprises calculating the order quantity data point (TO) by the following formula:

[0008]

[0009] Wherein, n is the total number of customer orders; i ) is the indicator function.

[0010] Optionally, the classification method further comprises calculating the order amount data point (AOV) by the following formula:

[0011]

[0012] Among them, the amount i is the amount of the i-th order, and n is the total number of customer orders.

[0013] Optionally, the classification method further comprises calculating the order frequency data point (OF) by the following formula:

[0014]

[0015] Wherein, n is the total number of customer orders; and t is the preset time.

[0016] Optionally, the classification method further comprises calculating the commodity diversity data point (PD) by the following formula:

[0017]

[0018] Among them, the 1(SKU j ) is an indicator function, m is the total number of SKUs of the products purchased by the customer, and Total SKUs is the total number of SKUs of all products.

[0019] Optionally, the classification method further comprises recalculating the cluster center of each cluster group by the following formula:

[0020]

[0021] Among them, the N j is the number of all cluster vertices in the cluster group, and the x i is the i-th cluster vertex in the cluster group.

[0022] Optionally, the classification method further comprises calculating the distance between the dimension data point and the final cluster center by the following formula:

[0023]

[0024] Wherein, a is the number of the dimensional data point types, k is the kth cluster group, and x ik is the ith cluster vertex in the kth cluster group, the cjk is the cluster center of the kth cluster group.

[0025] To solve the above technical problems, the present application provides a classification system, comprising: a memory for storing instructions executable by a processor; and a processor for executing the instructions to implement the above method.

[0026] In order to solve the above technical problem, the present application provides a computer-readable medium storing a computer program code, and the computer program code implements the above method when executed by a processor.

[0027] In order to solve the above technical problems, the present application provides an online ordering collaboration platform, including a client side and an enterprise side. The classification method described above is suitable for classifying customers at the enterprise side.

[0028] Compared with the prior art, the present application classifies and analyzes corporate customers based on dimensions such as the number of orders, order amount, order frequency, and diversity of purchased goods. By dividing all customers into different cluster groups, the information of each customer, such as the number of orders, order amount, and order frequency, is used as the cluster vertices of the cluster group, and the distance between the cluster center and the dimensional data points of the corporate customer is calculated to measure the transaction status of each corporate customer. Customers can be classified in different dimensions, thereby performing differentiated price management for different customers, and more personalized and effective marketing strategies can be formulated for enterprises. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The accompanying drawings are included to provide a further understanding of the present application. They are included and constitute a part of the present application. The accompanying drawings illustrate embodiments of the present application and together with the present specification serve to explain the principles of the present application. In the accompanying drawings:

[0030] Figure 1 It is a flow chart of a classification method applicable to an online ordering collaborative platform in one embodiment of the present application;

[0031] Figure 2 It is a module diagram of a classification system in one embodiment of the present application. DETAILED DESCRIPTION

[0032] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of the present application. For ordinary technicians in this field, the present application can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0033] As shown in this application and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "include" and "comprise" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0034] Unless otherwise specifically stated, the relative arrangement, numerical expressions and numerical values ​​of the parts and steps set forth in these embodiments do not limit the scope of the present application. At the same time, it should be understood that, for ease of description, the sizes of the various parts shown in the accompanying drawings are not drawn according to the actual proportional relationship. The technology, method and equipment known to those of ordinary skill in the relevant field may not be discussed in detail, but in appropriate cases, the technology, method and equipment should be considered as a part of the authorization specification. In all examples shown and discussed here, any specific value should be interpreted as being merely exemplary, rather than as a limitation. Therefore, other examples of exemplary embodiments may have different values. It should be noted that similar reference numerals and letters represent similar items in the following drawings, so that once a certain item is defined in an accompanying drawing, it does not need to be further discussed in subsequent drawings.

[0035] In the description of the present application, it should be understood that the directions or positional relationships indicated by directional words such as "front, back, up, down, left, right", "lateral, vertical, perpendicular, horizontal" and "top, bottom" are usually based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present application and simplifying the description. Unless otherwise specified, these directional words do not indicate or imply that the device or element referred to must have a specific direction or be constructed and operated in a specific direction, and therefore cannot be understood as limiting the scope of protection of the present application; the directional words "inside and outside" refer to the inside and outside relative to the contours of each component itself.

[0036] For ease of description, spatially relative terms such as "above", "above", "on the upper surface of", "above", etc. may be used here to describe the spatial positional relationship between a device or feature and other devices or features as shown in the figure. It should be understood that spatially relative terms are intended to include different orientations of the device in use or operation in addition to the orientation described in the figure. For example, if the device in the accompanying drawings is inverted, the device described as "above other devices or structures" or "above other devices or structures" will be positioned as "below other devices or structures" or "below other devices or structures". Thus, the exemplary term "above" can include both "above" and "below". The device can also be positioned in other different ways (rotated 90 degrees or in other orientations), and the spatially relative descriptions used here are interpreted accordingly.

[0037] In addition, it should be noted that the use of words such as "first" and "second" to define components is only for the convenience of distinguishing the corresponding components. If not otherwise stated, the above words have no special meaning and cannot be understood as limiting the scope of protection of this application. In addition, although the terms used in this application are selected from well-known and commonly used terms, some terms mentioned in the specification of this application may be selected by the applicant at his or her discretion, and their detailed meanings are explained in the relevant parts of the description of this article. In addition, it is required to understand this application not only by the actual terms used, but also by the meaning implied by each term.

[0038] This application refers to Figure 1 A classification method10 is proposed, which is applicable to online ordering collaborative platform. Figure 1 A flow chart of the classification method 10 is shown. The flow chart is used in the present application to illustrate the operations performed by the system according to the embodiment of the present application. It should be understood that the previous or following operations are not necessarily performed precisely in order. On the contrary, various steps can be processed in reverse order or simultaneously. At the same time, other operations may be added to these processes, or one or more operations may be removed from these processes. Specifically, the classification method 10 includes the following steps:

[0039] S1: preprocess the raw data and extract features from the raw data to obtain different types of dimensional data points;

[0040] S2: randomly selecting a preset number of dimension data points from different types of dimension data points to form a plurality of cluster groups, each cluster group including a plurality of cluster vertices;

[0041] S3: Calculate the cluster center of each cluster group, and select the cluster center whose difference value between the cluster center and all cluster vertices in the corresponding cluster group is in the range of 0% to 1% as the final cluster center;

[0042] S4: Calculate the distance between the dimension data point and the cluster center, and finally classify the customers based on the distance.

[0043] Steps S1 to S4 will now be described in detail.

[0044] In step S1, preprocessing includes data cleaning and / or data conversion of the original data, wherein data cleaning includes deleting duplicate data, filling in missing data values, and / or deleting missing data values. Exemplarily, the original data may include data such as the total amount of order transactions, the total number of order transactions, the order frequency, and the total order category of a certain corporate customer within a certain period of time, and may also be information such as the number of SKUs of an order of a certain corporate customer within a certain period of time, and this application does not limit this. The diversity of the original data can conduct a refined analysis of corporate customers from different angles and dimensions, and can better classify corporate customers.

[0045] Furthermore, the classification method 10 also includes extracting features from the original data to obtain different types of dimensional data points. In this embodiment, the feature extraction of the original data is explained by taking the order quantity, order amount, order frequency and the diversity of ordered goods as examples. After the feature extraction of the order quantity, order amount, order frequency and the diversity of ordered goods, dimensional data points will be formed. In this embodiment, the dimensional data points include order quantity data points (Total Orders, referred to as TO), order amount data points (Average Order Value, referred to as AOV), order frequency data points (Order Frequency, referred to as OF) and product diversity data points (Product Diversity, referred to as PD). In other embodiments of the present application, different original data can also be selected to classify corporate customers according to different needs of actual applications, and the present application does not limit this.

[0046] Specifically, the order quantity data point (TO) can be calculated by the following formula:

[0047]

[0048] Where n is the total number of customer orders; 1(Order i ) is the indicator function, 1(Order i ) means that if the order of the enterprise customer exists, its function value is 1, and if the order of the enterprise customer does not exist, its function value is 0. Selecting the number of orders as the dimension data point can measure the total number of orders of the customer, which is a direct reflection of the customer's activity and can better reflect the probability that the customer may purchase goods. It is an important indicator for classifying customers.

[0049] Furthermore, the order value data point (AOV) can be calculated using the following formula:

[0050]

[0051] Among them, Amount i is the amount of the i-th order, and n is the total number of customer orders. Selecting the order amount as the dimension data point can accurately measure the average consumption amount of each customer order, which can reflect the customer's consumption capacity. Customers with high consumption capacity are often the customers that the company focuses on. Classifying customers by order amount can better screen out potential high-level customers of the company.

[0052] On the other hand, the order frequency data point (OF) can be calculated by the following formula:

[0053]

[0054] Where n is the total number of customer orders; t is the preset time. For example, the unit of t is days. If t can be selected according to the actual situation, for example, if you want to classify all corporate customers in the past year, then t can be selected as 365 days. If you want to classify all customers of the company in the past ten years, then t is 3650 days. You can select the preset time according to the actual classification needs, and this application does not impose any restrictions on this. Selecting order frequency as a dimensional data point can measure the frequency of customer purchases within a certain period of time, which can well reflect customer loyalty and purchasing habits.

[0055] In this embodiment, the product diversity data point (PD) may also be calculated by the following formula:

[0056]

[0057] Among them, 1(SKU j ) is the indicator function, m is the total number of SKUs of the products purchased by the customer, and Total SKUs is the total number of SKUs of all products, where 1 (SKU j ) reflects that if the enterprise customer has purchased the product, then 1 (SKU j ) is 1. If the enterprise customer has not purchased the product, then 1 (SKU j ) is 0. Selecting the total number of product SKUs as the measurement standard can better reflect the diversity of the types of goods purchased by the company's customers, reflect the customers' purchasing preferences and exploration, and improve the diversity of refined customer classification.

[0058] Step S2 includes randomly selecting multiple cluster centers, assigning each dimensional data point and the cluster center closest to the dimensional data point to the same cluster group, and each cluster group includes a cluster center and multiple cluster vertices. Different types of dimensional data points can be obtained through the calculation of step S1, where in this embodiment, the dimensional data points are order quantity data points (TO), order amount data points (AOV), order frequency data points (OF) and product diversity data points (PD). For example, the dimensional data points assigned to the same cluster group can be one of the order amount data points of customer A, one of the order quantity data points and the order frequency data points of customer B. At this time, one of the order amount data points of customer A, one of the order quantity data points of customer B and one of the order frequency data points of customer B are the cluster vertices of the cluster group; one of the product diversity data points of customer C and one of the order amount data points of customer A can also be assigned to the same cluster group according to the distance from the cluster center.

[0059] This embodiment is preferred because the classification method 10 is aimed at transactions between corporate customers and corporate merchants, so the transaction volume is huge, and usually the number of dimensional data points can reach tens of millions. The same dimensional data point in the classification method 10 can repeatedly participate in the formation of cluster groups. A cluster group can include only one type of dimensional data point or multiple types of dimensional data points. It can include as many customer samples as possible, which can improve the accuracy of customer classification and formulate more personalized and effective marketing strategies for customers.

[0060] Step S3 includes recalculating the cluster center of each cluster group, and selecting the cluster center whose difference value between the cluster center and all cluster vertices in the corresponding cluster group is in the range of 0% to 1% as the final cluster center. In this embodiment, the cluster center of each cluster group can be recalculated by the following formula:

[0061]

[0062] Among them, N j is the number of all cluster vertices in the cluster group, X i is the i-th cluster vertex in the cluster group. The multiple cluster groups formed in step S2 can continuously recalculate the cluster centers of the cluster groups through the above formula. When a cluster center appears with a difference value ranging from 0% to 1% between the cluster center and all the cluster vertices in its corresponding cluster group, that is, the cluster center is no longer changing or the change is very small, the cluster center is selected as the final cluster center of all dimensional data points. Preferably, the number of cluster center iterations in the calculation process can be recorded in this embodiment as an empirical value for other classifications later.

[0063] Step S4 includes calculating the distance between the dimension data point and the cluster center, and finally classifying the customers according to the distance. In this embodiment, the distance between the dimension data point and the final cluster center can be calculated by the following formula:

[0064]

[0065] Where a is the number of dimension data point types, k is the kth cluster group, and x ik is the i-th cluster vertex in the k-th cluster group, c jk is the cluster center of the kth cluster group. Each customer corresponds to a different dimensional data point. Step S4 can calculate the distance between all dimensional data points of each customer and the final cluster center, which can reflect the transaction situation of the customer and classify the customer level according to the transaction situation of the customer. For example, if you want to classify customers from the perspective of order amount, at this time, the distance between customer A's order amount data point and the cluster center is a1, the distance between customer B's order amount data point and the cluster center is b1, and the distance between customer C's order amount data point and the cluster center is c1. Customer A, customer B and customer C can be classified by comparing the sizes of a1, b1 and c1.

[0066] Classification method 10 can classify customers into different levels by analyzing factors such as customer behavior, preferences, and transaction history. Customers of different levels have high similarities in certain characteristics. For example, customers can be classified into high-spending customers, mid-end spending customers, and low-end spending customers by the amount of their orders. Different classifications can help business merchants effectively identify high-value customers, mid-value customers, and low-value customers, and can formulate different marketing strategies for customers of different consumer groups.

[0067] In this embodiment, targeted marketing can be carried out for classified customers, that is, special marketing activities can be designed for customers of different levels, such as coupons, discounts or new product promotions, and personalized recommendations and timing marketing can be carried out for different registered customers, that is, the best time for customers to buy can be identified and time-effective marketing activities can be carried out. Through more effective marketing strategies, not only customer satisfaction can be improved, but also customer loyalty can be enhanced.

[0068] In this embodiment, customized services can also be provided to customers of different levels. For example, high-value customers can be assigned exclusive account managers, customized after-sales support, quick response services, and help with risk management, risk solutions and other exclusive services.

[0069] Furthermore, the classification method 10 can also identify risks for different customers, identify customer groups that may be lost, and take preventive measures in a timely manner. The classification method 10 can also design loyalty reward programs for customers of different levels to improve customer stickiness, and at the same time, it can establish a feedback mechanism to adjust services and products in a timely manner to meet customer needs. On the other hand, by classifying customers by level, it is also possible to analyze the needs of different customer groups and discover market opportunities, which is helpful for the next development of enterprises and merchants.

[0070] This application classifies and analyzes corporate customers by dimensions such as the number of orders, order amount, order frequency, and diversity of purchased goods. By dividing all customers into different cluster groups, the information of each customer, such as the number of orders, order amount, and order frequency, is used as the cluster vertices of the cluster group, and the distance between the cluster center and the dimensional data points of the corporate customer is calculated to measure the transaction status of each corporate customer. Customers can be classified in different dimensions, thereby performing differentiated price management for different customers, and formulating more personalized and effective marketing strategies for enterprises.

[0071] An embodiment of the present application also proposes a method such as Figure 2 The classification system shown is 20. Figure 2 The classification system 20 may include an internal communication bus 21, a processor 22, a read-only memory (ROM) 23, a random access memory (RAM) 24, and a communication port 25. When applied to a personal computer, the classification system 20 may also include a hard disk 26.

[0072] The internal communication bus 21 can realize data communication between the components of the classification system 20. The processor 22 can make judgments and issue prompts. In some embodiments, the processor 22 can be composed of one or more processors. The communication port 25 can realize data communication between the classification system 20 and the outside. In some embodiments, the classification system 20 can send and receive information and data from the network through the communication port 25.

[0073] The classification system 20 may also include different forms of program storage units and data storage units, such as a hard disk 26, a read-only memory (ROM) 23 and a random access memory (RAM) 24, which can store various data files used for computer processing and / or communication, and possible program instructions executed by the processor 22. The processor executes these instructions to implement the main part of the method. The results processed by the processor are transmitted to the user device through the communication port and displayed on the user interface.

[0074] In addition, the present application also proposes a computer-readable medium storing computer program codes, and the computer program codes implement the above classification method when executed by a processor.

[0075] On the other hand, the present application also provides an online ordering collaboration platform, including a client side and an enterprise side. The classification method proposed in any embodiment of the present application is suitable for classifying customers at the enterprise side, such as the above-mentioned classification method 10.

[0076] The basic concepts have been described above. Obviously, for those skilled in the art, the above application disclosure is only an example and does not constitute a limitation of the present application. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements and amendments to the present application. Such modifications, improvements and amendments are suggested in the present application, so such modifications, improvements and amendments still belong to the spirit and scope of the exemplary embodiments of the present application.

[0077] At the same time, the present application uses specific words to describe the embodiments of the present application. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of the present application. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, some features, structures or characteristics in one or more embodiments of the present application can be appropriately combined.

[0078] Some aspects of the present application may be performed entirely by hardware, entirely by software (including firmware, resident software, microcode, etc.), or by a combination of hardware and software. The above hardware or software may be referred to as "data blocks", "modules", "engines", "units", "components" or "systems". The processor may be one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DAPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), processors, controllers, microcontrollers, microprocessors, or combinations thereof. In addition, various aspects of the present application may be expressed as computer products located in one or more computer-readable media, which include computer-readable program codes. For example, computer-readable media may include, but are not limited to, magnetic storage devices (e.g., hard disks, floppy disks, tapes ...), optical disks (e.g., compact disks CDs, digital versatile disks DVDs ...), smart cards, and flash memory devices (e.g., cards, sticks, key drives ...).

[0079] A computer-readable medium may include a propagated data signal containing computer program code, such as in baseband or as part of a carrier wave. The propagated signal may have a variety of manifestations, including electromagnetic, optical, etc., or a suitable combination. A computer-readable medium may be any computer-readable medium other than a computer-readable storage medium, which may be connected to an instruction execution system, device or apparatus to communicate, propagate or transmit a program for use. The program code on the computer-readable medium may be propagated via any suitable medium, including radio, cable, fiber optic cable, radio frequency signal, or similar medium, or any combination of the above mediums.

[0080] Similarly, it should be noted that in order to simplify the description of the disclosure of this application and thus help understand one or more application embodiments, in the above description of the embodiments of this application, multiple features are sometimes merged into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the object of this application are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0081] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise specified, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may change according to the required features of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of the present application are approximate values, in specific embodiments, the setting of such numerical values ​​is as accurate as possible within the feasible range.

[0082] Although the present application has been described with reference to the current specific embodiments, ordinary technicians in this technical field should recognize that the above embodiments are only used to illustrate the present application, and various equivalent changes or substitutions may be made without departing from the spirit of the present application. Therefore, as long as the changes and modifications to the above embodiments are within the essential spirit of the present application, they will fall within the scope of the claims of the present application.

Claims

1. A classification method, applicable to an online ordering collaboration platform, characterized in that: The steps include: Preprocessing the original data and performing feature extraction on the original data to obtain different types of dimensional data points; Randomly select multiple cluster centers, assign each of the dimensional data points and the cluster center closest to the dimensional data point to the same cluster group, each of the cluster groups includes one cluster center and multiple cluster vertices; Recalculating the cluster center of each cluster group, and selecting the cluster center whose difference value between the cluster center and all the cluster vertices in the corresponding cluster group is in the range of 0% to 1% as the final cluster center; The distance between the dimension data point and the cluster center is calculated, and the customers are finally classified according to the distance.

2. The classification method according to claim 1, characterized in that: The preprocessing includes data cleaning and / or data conversion of the original data, wherein the data cleaning includes deleting duplicate data, filling in missing data values ​​and / or deleting missing data values.

3. The classification method according to claim 1, characterized in that: The different types of dimensional data points include order quantity data points (TO), order amount data points (AOV), order frequency data points (OF) and / or product diversity data points (PD).

4. The classification method according to claim 3, characterized in that: Also included is calculating the order quantity data point (TO) by the following formula: Wherein, n is the total number of customer orders; i ) is the indicator function.

5. The classification method according to claim 3, characterized in that: It also includes calculating the order value data point (AOV) by the following formula: Among them, the amount i is the amount of the i-th order, and n is the total number of customer orders.

6. The classification method according to claim 3, characterized in that: Also included is calculating the order frequency data point (OF) by the following formula: Wherein, n is the total number of customer orders; t is the preset time.

7. The classification method according to claim 3, characterized in that: It also includes calculating the product diversity data point (PD) by the following formula: Among them, the 1(SKU j ) is an indicator function, m is the total number of SKUs of the goods purchased by the customer, and TotalSKUs is the total number of SKUs of all goods.

8. The classification method according to claim 1, characterized in that: It also includes calculating the cluster center of each cluster group by the following formula: Among them, the N j is the number of all cluster vertices in the cluster group, and the x i is the i-th cluster vertex in the cluster group.

9. The classification method according to claim 1, wherein: It also includes calculating the distance between the dimension data point and the final cluster center by the following formula: Wherein, a is the number of the dimensional data point types, k is the kth cluster group, and x ik is the ith cluster vertex in the kth cluster group, the c jk is the cluster center of the kth cluster group.

10. A classification system comprising: a memory for storing instructions executable by a processor; and a processor, configured to execute the instructions to implement the method according to any one of claims 1 to 9.

11. A computer readable medium storing computer program code, wherein the computer program code, when executed by a processor, implements the method according to any one of claims 1 to 9.

12. An online ordering collaboration platform, characterized in that: Comprising a client end and an enterprise end, the classification method as described in any one of claims 1 to 9 is suitable for classifying customers at the enterprise end.

Images