Enterprise digital management method and system

Abstract

The present invention relates to the field of digital management technology, and in particular to a method and system for digital management of an enterprise, the method comprising: obtaining dimensional data of each customer to be recommended under each preset dimension; determining an initial cluster set and distribution change weight corresponding to the preset dimension, screening out the preset dimension whose distribution change weight is greater than a preset distribution change threshold; determining anomaly scores corresponding to the dimensional data, determining a comprehensive anomaly index and target importance corresponding to the customer to be recommended; performing incremental clustering on the screened target customer group set, determining an interpolation weight index corresponding to the target customer; screening out the customers to be interpolated and performing interpolation processing; and recommending information to each customer to be recommended through a collaborative filtering recommendation algorithm based on the initial data set and the interpolation data set. The present invention expands the data set used for information recommendation, solves the cold start problem in the collaborative filtering recommendation process to a certain extent, and improves the rationality of the recommendation results.

Description

Technical Field

[0001] The present invention relates to the technical field of digital management, and in particular to a method and system for digital management of an enterprise. Background Art

[0002] With the rapid development of information technology and the advancement of enterprise digital transformation, more and more companies are beginning to adopt digital management methods or systems to improve operational efficiency, optimize decision-making, and enhance customer satisfaction. In enterprise digital management, CRM (Customer Relationship Management) systems are widely used in customer information management, sales management, marketing, and other aspects. However, with large amounts of customer data, how to accurately and personalized provide customers with products or services, that is, how to accurately recommend information to customers, is a major challenge. Currently, when making information recommendations, the commonly used method is to collect data from multiple customers and, based on the collected data of all customers, recommend information to each customer through a collaborative filtering recommendation algorithm. Information recommendations can include but are not limited to: business recommendations and item recommendations.

[0003] However, when recommending information to each customer based on the collected customer data through collaborative filtering recommendation algorithms, the following technical problems often arise:

[0004] The collected customer data may lack relevant information about newly added businesses or newly added projects, which may lead to a cold start problem in the collaborative filtering recommendation process, resulting in erroneous recommendation results and poor rationality of the recommendation results. Summary of the Invention

[0005] In order to solve the technical problem of poor rationality of recommendation results, the present invention proposes an enterprise digital management method and system.

[0006] In a first aspect, the present invention provides a method for digital management of an enterprise, the method comprising:

[0007] Obtain the dimension data of each customer to be recommended under each preset dimension and build an initial data set;

[0008] Cluster all customers to be recommended according to their dimensional data under each preset dimension to obtain an initial cluster set corresponding to each preset dimension;

[0009] Determine the distribution change weight corresponding to each preset dimension based on the initial cluster set corresponding to each preset dimension, and select the preset dimension whose distribution change weight is greater than the preset distribution change threshold as the target dimension;

[0010] Determine the anomaly score corresponding to each dimension data, and determine the comprehensive anomaly index corresponding to each customer to be recommended based on the anomaly score corresponding to the dimension data of each customer to be recommended under all preset dimensions;

[0011] Determine the target importance of each customer to be recommended based on the comprehensive abnormality index corresponding to each customer to be recommended and the initial cluster set corresponding to all target dimensions;

[0012] According to the importance of the target, select the target customer group from all the customers to be recommended;

[0013] Perform incremental clustering on the target customer group set based on the dimensional data of all target customers in the target customer group set under all preset dimensions, and determine the interpolation weight index corresponding to each target customer based on the incremental clustering results;

[0014] According to the interpolation weight index, the customers to be interpolated are screened from the target customer group set, and interpolation processing is performed based on the dimensional data of all the customers to be interpolated under all preset dimensions to obtain an interpolation data set;

[0015] According to the union of the initial data set and the interpolated data set, information is recommended to each customer to be recommended through the collaborative filtering recommendation algorithm.

[0016] Optionally, the formula corresponding to the distribution change weight corresponding to the preset dimension is:

[0017] Among them, α i is the distribution change weight corresponding to the i-th preset dimension; i is the serial number of the preset dimension; norm() is the normalization function; d i It is the mean of the absolute values ​​of the differences between the dimensional data of the cluster centers of all initial clusters under the i-th preset dimension in the initial cluster cluster set corresponding to the i-th preset dimension; d i,max It is the maximum value of the absolute value of the difference between the dimensional data of the cluster centers of all initial clusters under the i-th preset dimension in the initial cluster cluster set corresponding to the i-th preset dimension; N i is the number of initial clusters in the initial cluster set corresponding to the i-th preset dimension; j is the sequence number of the initial cluster in the initial cluster set corresponding to the i-th preset dimension; N ij is the number of customers to be recommended in the jth initial cluster in the initial cluster set corresponding to the i-th preset dimension; N is the total number of customers to be recommended; exp() is an exponential function with a natural constant as the base; is the variance of the target differences corresponding to all initial clusters in the initial cluster set corresponding to the i-th preset dimension; d ijis the target difference corresponding to the jth initial cluster in the set of initial clusters corresponding to the i-th preset dimension; d ij1 is the reference difference of the jth initial cluster in the set of initial clusters corresponding to the i-th preset dimension under the i-th preset dimension; the reference difference of the jth initial cluster under the i-th preset dimension is the mean of the absolute values ​​of the differences between the dimensional data of all the recommended customers in the jth initial cluster under the i-th preset dimension; d ij2 It is the mean of the reference differences of the jth initial cluster in the set of initial clusters corresponding to the i-th preset dimension under all preset dimensions except the i-th preset dimension.

[0018] Optionally, determining the anomaly score corresponding to each dimension data, and determining the comprehensive anomaly index corresponding to each customer to be recommended based on the anomaly score corresponding to the dimension data of each customer to be recommended under all preset dimensions, includes:

[0019] Based on the initial data set, determine the anomaly score corresponding to each dimension data using the isolation forest algorithm;

[0020] The average of the abnormality scores corresponding to the dimension data of the customer to be recommended under all preset dimensions is determined as the comprehensive abnormality index corresponding to the customer to be recommended.

[0021] Optionally, the formula corresponding to the target importance of the customer to be recommended is:

[0022] Among them, τ k is the target importance of the kth customer to be recommended; k is the serial number of the customer to be recommended; exp() is the exponential function with a natural constant as the base; F k is the comprehensive abnormality index corresponding to the kth customer to be recommended; n is the number of target dimensions; norm() is the normalization function; m is the sequence number of the target dimension; v km is the mean of the absolute values ​​of the differences between the dimensional data under the n-th target dimension of the cluster center of the initial cluster to which the k-th customer to be recommended belongs in the initial cluster set corresponding to the n-th target dimension and the dimensional data under the n-th target dimension of the cluster centers of all initial clusters other than the initial cluster to which the k-th customer to be recommended belongs in the initial cluster set corresponding to the n-th target dimension; || is the absolute value function; A km1 A is the dimension data of the kth customer to be recommended under the nth target dimension; km2 It is the dimensional data under the nth target dimension of the cluster center of the initial cluster to which the kth customer to be recommended belongs in the initial cluster set corresponding to the nth target dimension.

[0023] Optionally, the step of screening a target customer group set from all customers to be recommended based on target importance includes:

[0024] Randomly forming a group of customers to be recommended with a first preset number of customers to be recommended;

[0025] Screening out a second preset number of recommended customers with the greatest target importance from each group of recommended customers as target customers to form a target customer group, wherein the second preset number is smaller than the first preset number;

[0026] All target customer groups constitute a target customer group set.

[0027] Optionally, performing incremental clustering on the target customer group set according to the dimensional data of all target customers in the target customer group set under all preset dimensions, and determining the interpolation weight index corresponding to each target customer according to the incremental clustering result, includes:

[0028] Randomly selecting a target customer group from the target customer group set as an initial clustering data set for incremental clustering;

[0029] Clustering the initial clustering data set according to the dimension data of all target customers in the initial clustering data set under all preset dimensions, and determining the result of clustering the initial clustering data set as the first clustering result in the incremental clustering process;

[0030] Determine each target customer group in the target customer group set, except the initial clustering data set, as a data set to be incrementally performed each time in the incremental clustering process;

[0031] Based on the dimensional data of all target customers in each incremental data set under all preset dimensions, each incremental data set is added to the previous clustering result in the incremental clustering process, and the clustering result after the addition is determined as another clustering result in the incremental clustering process, wherein the number of clusters in each clustering result in the incremental clustering process is the same;

[0032] Matching the clusters in each of the two adjacent clustering results in the incremental clustering process to obtain a set of matching cluster groups between each of the two adjacent clustering results in the incremental clustering process;

[0033] According to all matching clusters in the matching cluster group set between all two adjacent clustering results in the incremental clustering process, the interpolation weight index corresponding to each target customer is determined.

[0034] Optionally, matching the clusters in every two adjacent clustering results in the incremental clustering process to obtain a set of matching cluster groups between every two adjacent clustering results in the incremental clustering process includes:

[0035] Any two adjacent clustering results in the incremental clustering process are determined as the first candidate clustering result and the second candidate clustering result respectively;

[0036] Determine each cluster in the first candidate clustering result as a first candidate clustering cluster, and determine each cluster in the second candidate clustering result as a second candidate clustering cluster;

[0037] Determine a target edge weight between each first candidate cluster and each second candidate cluster according to an intersection-over-union ratio and a cosine similarity between each first candidate cluster and each second candidate cluster, wherein both the intersection-over-union ratio and the cosine similarity are positively correlated with the target edge weight;

[0038] According to the target edge weights between all first candidate clustering clusters and all second candidate clustering clusters, all first candidate clustering clusters and all second candidate clustering clusters are matched through the KM algorithm, and the mutually matching first candidate clustering clusters and second candidate clustering clusters are formed into a matching clustering cluster group, and a matching clustering cluster group set between the first candidate clustering results and the second candidate clustering results is obtained.

[0039] Optionally, the formula corresponding to the interpolation weight indicator corresponding to the target customer is:

[0040]

[0041] Among them, δ q is the interpolation weight index corresponding to the qth target customer; q is the serial number of the target customer; R is the number of clustering results in the incremental clustering process; n q is the minimum value among the serial numbers of all clustering results with the qth target customer in the incremental clustering process; b is the serial number of the clustering result in the incremental clustering process; δ q,b,b+1 is the sub-weight index between the b-th clustering result and the b+1-th clustering result for the q-th target customer in the incremental clustering process; exp() is an exponential function with a natural constant as the base; || is an absolute value function; g q,b g is the cosine similarity between the dimensional data of the cluster center of the cluster to which the qth target customer belongs in the bth clustering result in the incremental clustering process under all preset dimensions and the dimensional data of the qth target customer under all preset dimensions; g q,b+1 is the cosine similarity between the dimensional data of the cluster center of the cluster to which the qth target customer belongs in the b+1th clustering result in the incremental clustering process under all preset dimensions and the dimensional data of the qth target customer under all preset dimensions; NMI() is the normalized mutual information function; Q q,bis the cluster to which the qth target customer belongs in the bth clustering result during the incremental clustering process; Q q,b+1 is the cluster to which the qth target customer belongs in the b+1th clustering result during the incremental clustering process; if the clusters to which the qth target customer belongs in the bth clustering result and the b+1th clustering result during the incremental clustering process belong to the same matching cluster group, then set f q,b,b+1 is equal to the first preset value; if the clusters to which the qth target customer belongs in the bth clustering result and the b+1th clustering result in the incremental clustering process do not belong to the same matching cluster group, then set f q,b,b+1 is equal to the second preset value; the first preset value is greater than the second preset value.

[0042] Optionally, screening out customers to be interpolated from the target customer group set according to the interpolation weight index includes:

[0043] Target customers with the largest preset proportion of interpolation weight indicators are selected from the target customer group set as customers to be interpolated.

[0044] In a second aspect, the present invention provides an enterprise digital management system, comprising a processor and a memory, wherein the processor is configured to process instructions stored in the memory to implement the above-mentioned enterprise digital management method.

[0045] The present invention has the following beneficial effects:

[0046] The present invention provides a digital enterprise management method that expands the dataset used for information recommendation, addressing the cold start problem in collaborative filtering recommendation processes to a certain extent and improving the rationality of recommendation results. First, dimensional data for each customer to be recommended under each preset dimension is obtained to construct an initial dataset for data expansion. Next, the resulting initial cluster set corresponding to each preset dimension can, to a certain extent, reflect the data distribution of the customer to be recommended under that preset dimension. Then, based on the initial cluster set corresponding to the preset dimension, a larger quantified distribution change weight corresponding to the preset dimension often indicates a greater amount of valid information under that preset dimension, often indicating the importance of that preset dimension; the target dimension is often a relatively important preset dimension. Furthermore, based on the anomaly scores corresponding to the dimensional data of the customer to be recommended under all preset dimensions, a smaller quantified comprehensive anomaly index corresponding to the customer to be recommended often indicates a greater amount of valid information contained in the dimensional data of the customer to be recommended under all preset dimensions, often indicating that the customer to be recommended is more likely to be used for subsequent interpolation. Secondly, based on the comprehensive anomaly index corresponding to the target customer and the initial cluster set corresponding to all target dimensions, the greater the quantified target importance of the target customer, the more important the target customer is for subsequent interpolation processing, and the more likely the target customer is to be used in subsequent interpolation processing. Furthermore, based on the target importance, the target customers in the selected target customer group set may be relatively important customers. Subsequently, based on the dimensional data of all target customers in the target customer group set across all preset dimensions, the target customer group set is incrementally clustered. Based on the incremental clustering results, the greater the interpolation weight index corresponding to the quantified target customer, the more important the target customer is for subsequent interpolation processing, and the more likely the target customer is to be used in subsequent interpolation processing. Subsequently, based on the interpolation weight index, the target customers to be interpolated are selected from the target customer group set, and interpolation processing is performed based on the dimensional data of all target customers to be interpolated across all preset dimensions. The resulting interpolation dataset can be an adaptively added dataset. Finally, based on the union of the initial data set and the interpolated data set, the collaborative filtering recommendation algorithm is used to realize information recommendation for each customer to be recommended. Compared with directly using the initial data set for collaborative filtering recommendation, the present invention realizes the expansion of the data set and enriches the data in the data set. To a certain extent, it solves the cold start problem in the collaborative filtering recommendation process and improves the rationality of the recommendation results. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0048] Figure 1 This is a flow chart of an enterprise digital management method of the present invention. DETAILED DESCRIPTION

[0049] To further illustrate the technical means and effects employed by the present invention to achieve its intended objectives, the following, in conjunction with the accompanying drawings and preferred embodiments, describes in detail the specific implementations, structures, features, and effects of the technical solutions proposed by the present invention. In the following description, references to "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.

[0050] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0051] The present invention provides a method for digital management of an enterprise, the method comprising the following steps:

[0052] Obtain the dimension data of each customer to be recommended under each preset dimension and build an initial data set;

[0053] Cluster all customers to be recommended according to their dimensional data under each preset dimension to obtain an initial cluster set corresponding to each preset dimension;

[0054] Determine the distribution change weight corresponding to each preset dimension based on the initial cluster set corresponding to each preset dimension, and select the preset dimension whose distribution change weight is greater than the preset distribution change threshold as the target dimension;

[0055] Determine the anomaly score corresponding to each dimension data, and determine the comprehensive anomaly index corresponding to each customer to be recommended based on the anomaly score corresponding to the dimension data of each customer to be recommended under all preset dimensions;

[0056] Determine the target importance of each customer to be recommended based on the comprehensive abnormality index corresponding to each customer to be recommended and the initial cluster set corresponding to all target dimensions;

[0057] According to the importance of the target, select the target customer group from all the customers to be recommended;

[0058] Perform incremental clustering on the target customer group set based on the dimensional data of all target customers in the target customer group set under all preset dimensions, and determine the interpolation weight index corresponding to each target customer based on the incremental clustering results;

[0059] According to the interpolation weight index, the customers to be interpolated are screened from the target customer group set, and interpolation processing is performed based on the dimensional data of all the customers to be interpolated under all preset dimensions to obtain an interpolation data set;

[0060] According to the union of the initial data set and the interpolated data set, information is recommended to each customer to be recommended through the collaborative filtering recommendation algorithm.

[0061] The following is a detailed explanation of each of the above steps:

[0062] refer to Figure 1 , showing the process of some embodiments of an enterprise digital management method of the present invention. The enterprise digital management method includes the following steps:

[0063] Step S1: Obtain dimension data of each customer to be recommended under each preset dimension to construct an initial data set.

[0064] In some embodiments, dimensional data of each customer to be recommended under each preset dimension may be obtained to construct an initial data set.

[0065] Among them, the customer to be recommended can be a customer to whom information recommendation is to be made, that is, a user to whom information recommendation is to be made. Information recommendation can be, but is not limited to: business recommendation and product recommendation. The preset dimension can be a pre-set dimension related to information recommendation. The dimensional data can be a normalized preset dimension value. For example, if the customer to be recommended is a customer to whom product recommendation is to be made, then a preset dimension can be a dimension of the number of times the customer to be recommended purchases a certain product, and the dimensional data of the customer to be recommended under the preset dimension can be: the normalized value of the number of times the customer to be recommended purchases the product. The customer to be recommended can have one dimensional data under one preset dimension.

[0066] It should be noted that, by obtaining the dimensional data of each customer to be recommended under each preset dimension, an initial data set to be expanded can be constructed.

[0067] As an example, the dimensional data of each customer to be recommended under each preset dimension can be obtained through an enterprise management system, such as an ERP (Enterprise Resource Planning) system, a CRM (Customer Relationship Management) system, and a financial system, and the dimensional data of all customers to be recommended under all preset dimensions can be combined into an initial data set.

[0068] It should be noted that a CRM system, or customer relationship management system, helps accurately understand customer needs and preferences and recommend new services to them. The data in a CRM system can include basic customer information, historical customer transactions (e.g., interaction and purchase history), and customer feedback.

[0069] Step S2: clustering all the customers to be recommended according to their dimensional data under each preset dimension, and obtaining an initial cluster set corresponding to each preset dimension.

[0070] In some embodiments, all customers to be recommended may be clustered according to their dimensional data under each preset dimension to obtain an initial cluster set corresponding to each preset dimension.

[0071] It should be noted that, based on the dimensional data of all customers to be recommended under each preset dimension, all customers to be recommended are clustered, and the initial cluster set corresponding to each preset dimension obtained can reflect the data distribution of the customers to be recommended under the preset dimension to a certain extent.

[0072] As an example, all customers to be recommended can be clustered according to their dimensional data under a preset dimension using the DBSCAN (Density-Based Spatial Clustering of Applications with Noise) algorithm, and each cluster obtained by clustering at this time is used as the initial cluster cluster to obtain the initial cluster cluster set corresponding to the preset dimension.

[0073] For example, if a preset dimension represents an address, the DBSCAN algorithm can be used to cluster recommended customers with similar addresses into the same cluster as the initial cluster, and all the initial clusters obtained at this time constitute the initial cluster set corresponding to the preset dimension.

[0074] Step S3: Determine the distribution change weight corresponding to each preset dimension based on the initial cluster set corresponding to each preset dimension, and select the preset dimension whose distribution change weight is greater than the preset distribution change threshold as the target dimension.

[0075] In some embodiments, the distribution change weight corresponding to each preset dimension can be determined based on the initial cluster set corresponding to each preset dimension, and the preset dimensions with distribution change weights greater than the preset distribution change threshold can be screened out as target dimensions.

[0076] The preset distribution change threshold may be a preset threshold, for example, 0.65.

[0077] It should be noted that based on the initial cluster set corresponding to the preset dimension, the larger the distribution change weight corresponding to the quantified preset dimension, the greater the effective information content under the preset dimension, and the more important the preset dimension. The target dimension is often a relatively important preset dimension.

[0078] As an example, the formula for determining the distribution change weight corresponding to the preset dimension may be:

[0079] Among them, α i is the distribution change weight corresponding to the i-th preset dimension. i is the serial number of the preset dimension. norm() is the normalization function. i It is the mean of the absolute values ​​of the differences between the dimensional data of all initial cluster centers under the i-th preset dimension in the initial cluster cluster set corresponding to the i-th preset dimension. i,max It is the maximum absolute value of the difference between the dimensional data of all initial clusters in the initial cluster cluster set corresponding to the i-th preset dimension under the i-th preset dimension. i is the number of initial clusters in the initial cluster set corresponding to the i-th preset dimension. j is the sequence number of the initial cluster in the initial cluster set corresponding to the i-th preset dimension. N ij is the number of customers to be recommended in the jth initial cluster of the initial cluster set corresponding to the i-th preset dimension. N is the total number of customers to be recommended. exp() is an exponential function with a natural constant as its base. It is the variance of the target differences corresponding to all initial clusters in the initial cluster set corresponding to the i-th preset dimension. ij is the target difference corresponding to the jth initial cluster in the set of initial clusters corresponding to the i-th preset dimension. ij1The reference difference of the jth initial cluster in the set of initial clusters corresponding to the i-th preset dimension under the i-th preset dimension is the mean of the absolute values ​​of the differences between the dimension data of all the recommended customers in the jth initial cluster under the i-th preset dimension. ij2 It is the mean of the reference differences of the jth initial cluster in the set of initial clusters corresponding to the i-th preset dimension under all preset dimensions except the i-th preset dimension.

[0080] It should be noted that when The larger it is, the more obvious the difference in classification results is when clustering all the dimensional data under the i-th preset dimension for all the recommended customers; the more obvious the difference in classification results is when clustering all the dimensional data under the i-th preset dimension; the larger the amount of effective information under the i-th preset dimension, the more important the i-th preset dimension is, and the larger the weight should be set for the i-th preset dimension. It can represent the weight value of the jth initial cluster in the initial cluster set corresponding to the i-th preset dimension. The larger the value is, the greater the amount of information in the jth initial cluster. It can represent the data distribution difference between the jth initial cluster in the set of initial clusters corresponding to the i-th preset dimension and the distribution in the i-th preset dimension and the other preset dimensions. The larger its value is, the greater the data distribution difference between the distribution of the initial cluster in the i-th preset dimension and the other preset dimensions is, which often means that a smaller weight should be set for the i-th preset dimension. Therefore, when The larger the value, the larger the effective information amount under the i-th preset dimension is, which often means that a larger weight should be set for the i-th preset dimension. i The larger it is, the more important the i-th preset dimension is, and the larger the weight should be set for the i-th preset dimension.

[0081] Step S4: determine the abnormality score corresponding to each dimension data, and determine the comprehensive abnormality index corresponding to each customer to be recommended based on the abnormality score corresponding to the dimension data of each customer to be recommended under all preset dimensions.

[0082] In some embodiments, the abnormality score corresponding to each dimension data can be determined, and the comprehensive abnormality index corresponding to each customer to be recommended can be determined based on the abnormality score corresponding to the dimension data of each customer to be recommended under all preset dimensions.

[0083] It should be noted that, based on the anomaly scores corresponding to the dimensional data of the customer to be recommended under all preset dimensions, the smaller the comprehensive anomaly index corresponding to the quantified customer to be recommended, the greater the amount of effective information contained in the dimensional data of the customer to be recommended under all preset dimensions, and the more likely the customer to be recommended can be used for subsequent interpolation.

[0084] As an example, this step may include the following steps:

[0085] The first step is to determine the anomaly score corresponding to each dimension data based on the above initial data set through the isolation forest algorithm.

[0086] In the second step, the average of the abnormality scores corresponding to the dimension data of the above-mentioned customer to be recommended under all preset dimensions is determined as the comprehensive abnormality index corresponding to the above-mentioned customer to be recommended.

[0087] Step S5: Determine the target importance of each customer to be recommended based on the comprehensive abnormality index corresponding to each customer to be recommended and the initial cluster set corresponding to all target dimensions.

[0088] In some embodiments, the target importance corresponding to each customer to be recommended may be determined based on the comprehensive abnormality index corresponding to each customer to be recommended and the initial cluster set corresponding to all target dimensions.

[0089] It should be noted that, based on the comprehensive abnormality index corresponding to the customer to be recommended and the initial cluster set corresponding to all target dimensions, the greater the target importance corresponding to the quantified customer to be recommended, the more important the customer to be recommended is relative to the subsequent interpolation processing, and the more likely the customer to be recommended can be used in the subsequent interpolation processing.

[0090] As an example, the formula for determining the target importance of the customer to be recommended can be:

[0091] Among them, τ k is the target importance of the kth customer to be recommended. k is the serial number of the customer to be recommended. exp() is an exponential function with a natural constant as the base. F k is the comprehensive abnormality index corresponding to the kth customer to be recommended. n is the number of target dimensions. norm() is the normalization function. m is the sequence number of the target dimension. v kmIt is the mean of the absolute values ​​of the differences between the dimensional data under the n-th target dimension of the cluster center of the initial cluster to which the k-th customer to be recommended belongs in the initial cluster set corresponding to the n-th target dimension and the dimensional data under the n-th target dimension of the cluster centers of all initial clusters other than the initial cluster to which the k-th customer to be recommended belongs in the initial cluster set corresponding to the n-th target dimension; that is, in the initial cluster set corresponding to the n-th target dimension, the mean of the absolute values ​​of the differences between the dimensional data under the n-th target dimension of the cluster center of the initial cluster to which the k-th customer to be recommended belongs and the dimensional data under the n-th target dimension of the cluster centers of all other initial clusters. || is the absolute value function. A km1 A is the dimension data of the kth customer to be recommended under the nth target dimension. km2 It is the dimensional data under the nth target dimension of the cluster center of the initial cluster to which the kth customer to be recommended belongs in the initial cluster set corresponding to the nth target dimension.

[0092] It should be noted that when F k The smaller it is, the greater the information contained in the k-th customer to be recommended is, and the more suitable the k-th customer to be recommended is for subsequent interpolation processing. km The smaller the value, the more important the initial cluster to which the kth customer to be recommended belongs in the initial cluster set corresponding to the nth target dimension is to the data distribution characteristics of other initial clusters under this dimension. This often means that the kth customer to be recommended is more important for subsequent interpolation processing, and the more likely this customer to be recommended is to be used in subsequent interpolation processing. km1 -A km2 The smaller | is, the closer the data of the kth customer to be recommended in the initial cluster set corresponding to the nth target dimension is to the data of its cluster center in this dimension. This often means that the kth customer to be recommended can better represent the cluster center to which it belongs in this dimension. This often means that the kth customer to be recommended is more important for subsequent interpolation processing and can be used for subsequent interpolation processing. Can be used as exp(-F k ) weight value. When τ k The larger the value, the more important the k-th customer to be recommended is relative to the subsequent interpolation processing, and the more the k-th customer to be recommended can be used in the subsequent interpolation processing.

[0093] Step S6: Filter out a target customer group set from all customers to be recommended based on the target importance.

[0094] In some embodiments, a target customer group set may be screened out from all customers to be recommended based on target importance.

[0095] It should be noted that, based on the target importance, the target customers in the screened target customer group set may be relatively important customers.

[0096] As an example, this step may include the following steps:

[0097] In the first step, a first preset number of customers to be recommended are randomly formed into a customer group to be recommended.

[0098] The first preset number may be a pre-set number, for example, 100.

[0099] For example, if the first preset number is 100, every 100 customers to be recommended may be randomly grouped into a customer group to be recommended.

[0100] Optionally, all customers to be recommended may be divided into equal groups, and each of the equal groups may be used as a customer group to be recommended.

[0101] In the second step, a second preset number of customers to be recommended with the greatest target importance are screened out from each customer group to be recommended as target customers to form a target customer group.

[0102] The second preset number may be smaller than the first preset number. For example, if the first preset number is 100, the second preset number may be 50. Each customer group to be recommended has a target customer group.

[0103] The third step is to combine all target customer groups into a target customer group set.

[0104] Step S7: performing incremental clustering on the target customer group set according to the dimensional data of all target customers in the target customer group set under all preset dimensions, and determining the interpolation weight index corresponding to each target customer according to the incremental clustering result.

[0105] In some embodiments, the target customer group set may be incrementally clustered based on the dimensional data of all target customers in the target customer group set under all preset dimensions, and the interpolation weight index corresponding to each target customer may be determined based on the incremental clustering results.

[0106] It should be noted that, based on the dimensional data of all target customers in the target customer group set under all preset dimensions, the target customer group set is incrementally clustered, and according to the incremental clustering results, the larger the interpolation weight index corresponding to the quantified target customer is, the more important the target customer is with respect to the subsequent interpolation processing, and the more the target customer can be used for the subsequent interpolation processing.

[0107] As an example, this step may include the following steps:

[0108] In the first step, a target customer group is randomly selected from the above target customer group set as the initial clustering data set for incremental clustering.

[0109] The initial clustering data set may be the data set used when performing the first clustering in the incremental clustering process.

[0110] In the second step, the initial clustering data set is clustered according to the dimensional data of all target customers in the initial clustering data set under all preset dimensions, and the result of clustering the initial clustering data set is determined as the first clustering result in the incremental clustering process.

[0111] For example, a vector consisting of the target customer's dimensional data under all preset dimensions can be first used as the target customer's feature vector. Then, the initial clustering dataset can be clustered using the k-means (k-means clustering algorithm) algorithm based on the feature vectors of all target customers in the initial clustering dataset. Target customers with similar feature vectors in the initial clustering dataset can be grouped into the same cluster, obtaining the first clustering result in the incremental clustering process. The number of clusters in the k-means algorithm can be set to 8.

[0112] In the third step, each target customer group in the target customer group set except the initial clustering data set is determined as the data set to be incrementally performed each time in the incremental clustering process.

[0113] The fourth step is to add each incremental data set to the previous clustering result in the incremental clustering process based on the dimensional data of all target customers in all preset dimensions in each incremental data set, and determine the clustering result after adding as another clustering result in the incremental clustering process.

[0114] Among them, the number of clusters in each clustering result during the incremental clustering process is the same.

[0115] For example, based on the feature vectors of all target customers in the new incremental data set, the k-means algorithm can be used to add the new incremental data set to the previous clustering result in the incremental clustering process, so that target customers with similar feature vectors can be clustered into the same cluster and a clustering result can be obtained.

[0116] The fifth step is to match the clusters in each two adjacent clustering results in the incremental clustering process to obtain a set of matching cluster groups between each two adjacent clustering results in the incremental clustering process. The matching cluster groups may include the following sub-steps:

[0117] In the first sub-step, any two adjacent clustering results in the incremental clustering process are respectively determined as the first candidate clustering result and the second candidate clustering result.

[0118] In the second sub-step, each cluster in the first candidate clustering result is determined as a first candidate clustering cluster, and each cluster in the second candidate clustering result is determined as a second candidate clustering cluster.

[0119] In the third sub-step, a target edge weight between each first candidate cluster and each second candidate cluster is determined according to the intersection-over-union ratio and the cosine similarity between each first candidate cluster and each second candidate cluster.

[0120] The intersection-over-union ratio and cosine similarity can both be positively correlated with the target edge weight. The target customers in the first candidate cluster can be represented by the target customer's feature vector. The target customers in the second candidate cluster can be represented by the target customer's feature vector.

[0121] It should be noted that a larger IoU ratio between two clusters often indicates more overlap between the two clusters, which often indicates a closer match between the two clusters. A larger cosine similarity between two clusters often indicates more similarity between the two clusters, which often indicates a closer match between the two clusters. Therefore, a larger target edge weight between two clusters often indicates a closer match between the two clusters.

[0122] The fourth sub-step is to match all first candidate clusters and all second candidate clusters according to the target edge weights between all first candidate clusters and all second candidate clusters through the KM (Kuhn and Munkres, bipartite graph matching) algorithm, and form a matching cluster group with the mutually matching first candidate clusters and second candidate clusters to obtain a set of matching cluster groups between the first candidate cluster results and the second candidate cluster results, wherein a matching cluster group includes a first candidate cluster and a second candidate cluster.

[0123] The sixth step is to determine the interpolation weight index corresponding to each target customer based on all matching clusters in the matching cluster group set between all two adjacent clustering results in the incremental clustering process.

[0124] For example, the formula for determining the interpolation weight index corresponding to the target customer can be:

[0125]

[0126] Among them, δ q is the interpolation weight index corresponding to the qth target customer. q is the serial number of the target customer. R is the number of clustering results in the incremental clustering process. nq It is the minimum value among the serial numbers of all clustering results with the qth target customer in the incremental clustering process. b is the serial number of the clustering result in the incremental clustering process. The serial number of the clustering result in the incremental clustering process can be the serial number obtained according to the clustering order from early to late. q,b,b+1 is the sub-weight index between the b-th clustering result and the b+1-th clustering result for the q-th target customer in the incremental clustering process. exp() is an exponential function with a natural constant as the base. || is an absolute value function. g q,b It is the cosine similarity between the dimensional data of the cluster center of the cluster to which the qth target customer belongs in the bth clustering result in the incremental clustering process under all preset dimensions and the dimensional data of the qth target customer under all preset dimensions; that is, the cosine similarity between the characteristic vector of the cluster center of the cluster to which the qth target customer belongs in the bth clustering result in the incremental clustering process and the characteristic vector of the qth target customer, which can represent the centrality of the qth target customer in the bth clustering result in the incremental clustering process. q,b+1 It is the cosine similarity between the dimensional data of the cluster center of the cluster to which the qth target customer belongs in the b+1th clustering result in the incremental clustering process under all preset dimensions and the dimensional data of the qth target customer under all preset dimensions, that is, the cosine similarity between the characteristic vector of the cluster center of the cluster to which the qth target customer belongs in the b+1th clustering result in the incremental clustering process and the characteristic vector of the qth target customer, which can characterize the centrality of the qth target customer in the b+1th clustering result in the incremental clustering process. NMI() is the normalized mutual information function. Q q,b It is the cluster to which the qth target customer belongs in the bth clustering result in the incremental clustering process, and can be represented by the feature vectors of all target customers in the cluster to which the qth target customer belongs in the bth clustering result in the incremental clustering process. q,b+1 is the cluster to which the qth target customer belongs in the b+1th clustering result in the incremental clustering process, and can be represented by the feature vectors of all target customers in the cluster to which the qth target customer belongs in the b+1th clustering result in the incremental clustering process. If the clusters to which the qth target customer belongs in the bth clustering result and the b+1th clustering result in the incremental clustering process belong to the same matching cluster group, then set f q,b,b+1 If the clusters to which the qth target customer belongs in the bth clustering result and the b+1th clustering result in the incremental clustering process do not belong to the same matching cluster group, then set f q,b,b+1 The first preset value is equal to the second preset value. The first preset value is greater than the second preset value. For example, the first preset value may be 1. The second preset value may be -1.

[0127] It should be noted that, if the two clusters to which the same customer belongs in the two adjacent clustering results during the incremental clustering process are in the same matching clustering group, and the difference between the two clusters is large, it indicates that the customer contains more information, that is, the corresponding information weight is larger; on the contrary, if the two clusters to which the same customer belongs in the two adjacent clustering results during the incremental clustering process are not in the same matching clustering group, it indicates that the distribution characteristics of the customer have changed differently. If the center degrees of the two clusters are similar, it indicates that the existence of the customer will disrupt the clustering results, and the customer often contains less information, that is, the corresponding information weight often needs to be reduced. When f q,b,b+1 The larger it is, the greater the possibility that the clusters to which the qth target customer belongs in the bth clustering result and the b+1th clustering result belong to the same matching cluster group. The smaller it is, the more similar the center of the clusters to which the qth target customer belongs in the bth clustering result and the b+1th clustering result is. This often means that the existence of the qth target customer is more likely to disrupt the clustering result, and the corresponding information weight often needs to be reduced. q,b ,Q q,b+1 ) is smaller, it often means that the clusters to which the qth target customer belongs in the bth clustering result and the b+1th clustering result are less similar, which often means that the corresponding information weight needs to be reduced. Therefore, when δ q A larger value indicates a greater need for increasing the corresponding information weight, a greater importance for the qth target customer in subsequent interpolation processing, and a greater likelihood of using the qth target customer in subsequent interpolation processing. Furthermore, during the incremental clustering process, newly added target customers in the last clustering step are not included in the calculation of the interpolation weight indicator and do not participate in subsequent interpolation processing.

[0128] Step S8: Screening out customers to be interpolated from the target customer group set according to the interpolation weight index, and performing interpolation processing on the dimensional data of all customers to be interpolated under all preset dimensions to obtain an interpolation data set.

[0129] In some embodiments, customers to be interpolated may be screened from the target customer group set based on an interpolation weight index, and interpolation processing may be performed based on the dimensional data of all customers to be interpolated under all preset dimensions to obtain an interpolation data set.

[0130] It should be noted that based on the interpolation weight index, customers to be interpolated are screened from the target customer group set, and interpolation processing is performed based on the dimensional data of all customers to be interpolated under all preset dimensions. The obtained interpolation data set can be an adaptively added data set.

[0131] As an example, this step may include the following steps:

[0132] The first step is to select the target customers with the largest preset proportion of interpolation weight indicators from the target customer group set as the customers to be interpolated.

[0133] The preset ratio can be a preset ratio. For example, the preset ratio can be

[0134] For example, if the preset ratio is Then, the target customers in the target customer group set can be sorted in descending order according to the interpolation weight index to obtain the target customer sequence, and the top target customers in the target customer sequence can be sorted. 's target customers as the customers to be interpolated.

[0135] The second step is to perform interpolation processing on the dimensional data of all customers to be interpolated under all preset dimensions to obtain an interpolation data set.

[0136] For example, first, linear interpolation can be performed on the dimensional data of all customers to be interpolated under each preset dimension to obtain an interpolation data sequence under each preset dimension. Then, when the interpolation data in the interpolation data sequence under the preset dimension is greater than the maximum value in the preset range under the preset dimension, the interpolation data is updated to the maximum value in the preset range under the preset dimension. When the interpolation data in the interpolation data sequence under the preset dimension is less than the minimum value in the preset range under the preset dimension, the interpolation data is updated to the minimum value in the preset range under the preset dimension. When the interpolation data in the interpolation data sequence under the preset dimension falls within the preset range under the preset dimension, there is no need to update the interpolation data. The preset range under the preset dimension can be [H max +0.2×H,H min +0.2×H], where H max It is the largest dimension data under the preset dimension. min It is the minimum dimension data under the preset dimension. H=H max -H min Next, a vector consisting of interpolated data at the same position in the final interpolated data sequence under all preset dimensions can be used as a target vector. A target vector can represent a virtual customer obtained by interpolation, that is, the elements in the target vector can be the dimensional data of the virtual customer under the preset dimensions.

[0137] Step S9: Recommend information to each customer to be recommended based on the union of the initial data set and the interpolated data set using a collaborative filtering recommendation algorithm.

[0138] In some embodiments, information recommendation can be performed for each customer to be recommended based on the union of the initial data set and the interpolated data set through a collaborative filtering recommendation algorithm.

[0139] It should be noted that, based on the union of the initial data set and the interpolated data set, information recommendation for each customer to be recommended is achieved through the collaborative filtering recommendation algorithm.

[0140] As an example, if the content to be recommended is a business, the union of the initial data set and the interpolated data set can be used as the final data set. Based on the final data set, the collaborative filtering recommendation algorithm can be used to calculate the score values ​​of multiple businesses, sort the businesses by the score values, and make business recommendations to the recommended customers based on the sorting results.

[0141] Based on the same inventive concept as the above-mentioned method embodiment, the present invention provides an enterprise digital management system, which includes a memory, a processor, and a computer program stored in the memory and runnable on the processor. When the above-mentioned computer program is executed by the processor, it implements the steps of an enterprise digital management method.

[0142] In summary, compared with directly using the initial data set for collaborative filtering recommendation, the present invention achieves the expansion of the data set, enriches the data in the data set, solves the cold start problem in the collaborative filtering recommendation process to a certain extent, and improves the rationality of the recommendation results.

[0143] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present invention, and should all be included in the scope of protection of the present invention.

Claims

1. A digital management method for an enterprise, characterized in that: The following steps are involved: Obtain the dimension data of each customer to be recommended under each preset dimension and build an initial data set; Cluster all customers to be recommended according to their dimensional data under each preset dimension to obtain an initial cluster set corresponding to each preset dimension; Determine the distribution change weight corresponding to each preset dimension based on the initial cluster set corresponding to each preset dimension, and select the preset dimension whose distribution change weight is greater than the preset distribution change threshold as the target dimension; Determine the anomaly score corresponding to each dimension data, and determine the comprehensive anomaly index corresponding to each customer to be recommended based on the anomaly score corresponding to the dimension data of each customer to be recommended under all preset dimensions; Determine the target importance of each customer to be recommended based on the comprehensive abnormality index corresponding to each customer to be recommended and the initial cluster set corresponding to all target dimensions; According to the importance of the target, select the target customer group from all the customers to be recommended; Perform incremental clustering on the target customer group set based on the dimensional data of all target customers in the target customer group set under all preset dimensions, and determine the interpolation weight index corresponding to each target customer based on the incremental clustering results; According to the interpolation weight index, the customers to be interpolated are screened from the target customer group set, and interpolation processing is performed based on the dimensional data of all the customers to be interpolated under all preset dimensions to obtain an interpolation data set; According to the union of the initial data set and the interpolated data set, information is recommended to each customer to be recommended through the collaborative filtering recommendation algorithm.

2. The enterprise digital management method according to claim 1, characterized in that: The formula for the distribution change weight corresponding to the preset dimension is: Among them, α i is the distribution change weight corresponding to the i-th preset dimension; i is the serial number of the preset dimension; norm() is the normalization function; d i It is the mean of the absolute values ​​of the differences between the dimensional data of the cluster centers of all initial clusters under the i-th preset dimension in the initial cluster cluster set corresponding to the i-th preset dimension; d i,max It is the maximum value of the absolute value of the difference between the dimensional data of the cluster centers of all initial clusters under the i-th preset dimension in the initial cluster cluster set corresponding to the i-th preset dimension; N i is the number of initial clusters in the initial cluster set corresponding to the i-th preset dimension; j is the sequence number of the initial cluster in the initial cluster set corresponding to the i-th preset dimension; N ij is the number of customers to be recommended in the jth initial cluster in the initial cluster set corresponding to the i-th preset dimension; N is the total number of customers to be recommended; exp() is an exponential function with a natural constant as the base; is the variance of the target differences corresponding to all initial clusters in the initial cluster set corresponding to the i-th preset dimension; d ij is the target difference corresponding to the jth initial cluster in the set of initial clusters corresponding to the i-th preset dimension; d ij1 is the reference difference of the jth initial cluster in the set of initial clusters corresponding to the i-th preset dimension under the i-th preset dimension; the reference difference of the jth initial cluster under the i-th preset dimension is the mean of the absolute values ​​of the differences between the dimensional data of all the recommended customers in the jth initial cluster under the i-th preset dimension; d ij2 It is the mean of the reference differences of the jth initial cluster in the set of initial clusters corresponding to the i-th preset dimension under all preset dimensions except the i-th preset dimension.

3. The enterprise digital management method according to claim 1, characterized in that: The step of determining the abnormality score corresponding to each dimension data and determining the comprehensive abnormality index corresponding to each customer to be recommended based on the abnormality score corresponding to the dimension data of each customer to be recommended under all preset dimensions includes: Based on the initial data set, determine the anomaly score corresponding to each dimension data using the isolation forest algorithm; The average of the abnormality scores corresponding to the dimension data of the customer to be recommended under all preset dimensions is determined as the comprehensive abnormality index corresponding to the customer to be recommended.

4. The enterprise digital management method according to claim 1, characterized in that: The formula for the target importance of the recommended customers is: Among them, τ k is the target importance of the kth customer to be recommended; k is the serial number of the customer to be recommended; exp() is the exponential function with a natural constant as the base; F k is the comprehensive abnormality index corresponding to the kth customer to be recommended; n is the number of target dimensions; norm() is the normalization function; m is the sequence number of the target dimension; v km is the mean of the absolute values ​​of the differences between the dimensional data under the n-th target dimension of the cluster center of the initial cluster to which the k-th customer to be recommended belongs in the initial cluster set corresponding to the n-th target dimension and the dimensional data under the n-th target dimension of the cluster centers of all initial clusters other than the initial cluster to which the k-th customer to be recommended belongs in the initial cluster set corresponding to the n-th target dimension; || is the absolute value function; A km1 A is the dimension data of the kth customer to be recommended under the nth target dimension; km2 It is the dimensional data under the nth target dimension of the cluster center of the initial cluster to which the kth customer to be recommended belongs in the initial cluster set corresponding to the nth target dimension.

5. The enterprise digital management method according to claim 1, characterized in that: The target customer group set is screened from all customers to be recommended based on the importance of the target, including: Randomly forming a group of customers to be recommended with a first preset number of customers to be recommended; Screening out a second preset number of recommended customers with the greatest target importance from each group of recommended customers as target customers to form a target customer group, wherein the second preset number is smaller than the first preset number; All target customer groups constitute a target customer group set.

6. The enterprise digital management method according to claim 1, characterized in that: The step of performing incremental clustering on the target customer group set according to the dimensional data of all target customers in the target customer group set under all preset dimensions, and determining the interpolation weight index corresponding to each target customer according to the incremental clustering result, includes: Randomly selecting a target customer group from the target customer group set as an initial clustering data set for incremental clustering; Clustering the initial clustering data set according to the dimension data of all target customers in the initial clustering data set under all preset dimensions, and determining the result of clustering the initial clustering data set as the first clustering result in the incremental clustering process; Determine each target customer group in the target customer group set, except the initial clustering data set, as a data set to be incrementally performed each time in the incremental clustering process; Based on the dimensional data of all target customers in each incremental data set under all preset dimensions, each incremental data set is added to the previous clustering result in the incremental clustering process, and the clustering result after the addition is determined as another clustering result in the incremental clustering process, wherein the number of clusters in each clustering result in the incremental clustering process is the same; Matching the clusters in each of the two adjacent clustering results in the incremental clustering process to obtain a set of matching cluster groups between each of the two adjacent clustering results in the incremental clustering process; According to all matching clusters in the matching cluster group set between all two adjacent clustering results in the incremental clustering process, the interpolation weight index corresponding to each target customer is determined.

7. The enterprise digital management method according to claim 6, characterized in that: The step of matching the clusters in each of two adjacent clustering results in the incremental clustering process to obtain a set of matching cluster groups between each of two adjacent clustering results in the incremental clustering process includes: Any two adjacent clustering results in the incremental clustering process are determined as the first candidate clustering result and the second candidate clustering result respectively; Determine each cluster in the first candidate clustering result as a first candidate clustering cluster, and determine each cluster in the second candidate clustering result as a second candidate clustering cluster; Determine a target edge weight between each first candidate cluster and each second candidate cluster according to an intersection-over-union ratio and a cosine similarity between each first candidate cluster and each second candidate cluster, wherein both the intersection-over-union ratio and the cosine similarity are positively correlated with the target edge weight; According to the target edge weights between all first candidate clustering clusters and all second candidate clustering clusters, all first candidate clustering clusters and all second candidate clustering clusters are matched through the KM algorithm, and the mutually matching first candidate clustering clusters and second candidate clustering clusters are formed into a matching clustering cluster group, and a matching clustering cluster group set between the first candidate clustering results and the second candidate clustering results is obtained.

8. The enterprise digital management method according to claim 6, characterized in that: The formula for the interpolation weight indicator corresponding to the target customer is: Among them, δ q is the interpolation weight index corresponding to the qth target customer; q is the serial number of the target customer; R is the number of clustering results in the incremental clustering process; n q is the minimum value among the serial numbers of all clustering results with the qth target customer in the incremental clustering process; b is the serial number of the clustering result in the incremental clustering process; δ q,b,b+1 is the sub-weight index between the b-th clustering result and the b+1-th clustering result for the q-th target customer in the incremental clustering process; exp() is an exponential function with a natural constant as the base; || is an absolute value function; g q,b g is the cosine similarity between the dimensional data of the cluster center of the cluster to which the qth target customer belongs in the bth clustering result in the incremental clustering process under all preset dimensions and the dimensional data of the qth target customer under all preset dimensions; g q,b+1 is the cosine similarity between the dimensional data of the cluster center of the cluster to which the qth target customer belongs in the b+1th clustering result in the incremental clustering process under all preset dimensions and the dimensional data of the qth target customer under all preset dimensions; NMI() is the normalized mutual information function; Q q,b is the cluster to which the qth target customer belongs in the bth clustering result during the incremental clustering process; Q q,b+1 is the cluster to which the qth target customer belongs in the b+1th clustering result during the incremental clustering process; if the clusters to which the qth target customer belongs in the bth clustering result and the b+1th clustering result during the incremental clustering process belong to the same matching cluster group, then set f q,b,b+1 is equal to the first preset value; if the clusters to which the qth target customer belongs in the bth clustering result and the b+1th clustering result in the incremental clustering process do not belong to the same matching cluster group, then set f q,b,b+1 is equal to the second preset value; the first preset value is greater than the second preset value.

9. The enterprise digital management method according to claim 1, characterized in that: The step of selecting customers to be interpolated from the target customer group set according to the interpolation weight index includes: Target customers with the largest preset proportion of interpolation weight indicators are selected from the target customer group set as customers to be interpolated.

10. An enterprise digital management system, characterized in that: The method comprises a processor and a memory, wherein the processor is used to process instructions stored in the memory to implement an enterprise digital management method according to any one of claims 1 to 9.

Images