A method and system for processing enterprise consulting services

Abstract

The present application relates to the field of data management technology, and specifically to a method and system for processing enterprise consulting services, the method comprising: collecting a valid information data group; obtaining a valid information feature matrix; and then obtaining a relative coefficient of information feature fluctuation; calculating a consulting feature comparison coefficient, obtaining a valid feature point comparison data sequence, and then obtaining a relative feature difference coefficient; constructing a valid information comparison sequence, and then obtaining the confidence weight of each valid information comparison sequence, obtaining a valid classification comparison coefficient for each valid information data, and classifying and managing the valid information data to improve customer consulting services. The present application solves the problem of large errors caused by using a one-time classification method due to different customer data features.

Description

Technical Field

[0001] The present application relates to the field of data management technology, and specifically to a method and system for processing enterprise consulting services. Background Art

[0002] Customer classification in corporate consulting management is a key link in achieving effective customer relationship management (CRM). It involves how to divide customer groups according to their different characteristics and behaviors, and provide differentiated services and products accordingly.

[0003] However, in the traditional enterprise consulting management process, correlation analysis is usually performed based on relevant data of customer consultation to complete customer classification. Traditional clustering algorithms are usually used to complete the classification of enterprise consulting service customers. However, traditional clustering algorithms do not accurately analyze the data characteristics between customers during the customer classification process. For example, the K-means clustering algorithm is used to classify only the classification results obtained through data differences, which has a large error, affecting the subsequent analysis of the customer group and making it difficult to achieve effective customer relationship management in enterprise consulting services. Summary of the invention

[0004] In order to solve the above technical problems, the purpose of this application is to provide a method and system for processing enterprise consulting services. The technical solutions adopted are as follows:

[0005] In a first aspect, an embodiment of the present application provides a method for processing enterprise consulting services, the method comprising the following steps:

[0006] Collect a valid information data group consisting of various valid information data of each customer;

[0007] Obtain each valid feature comparison array and a valid information feature matrix of each valid feature comparison array according to each customer's valid information data group;

[0008] Based on the volatility differences between the data in the effective information feature matrix, the relative coefficient of information feature fluctuation between each column of data in each effective information feature matrix and other columns of data is obtained; based on the relative coefficient of information feature fluctuation, the consulting feature comparison coefficient of each effective information feature matrix is ​​obtained;

[0009] Based on the consulting feature comparison coefficient, obtain the effective feature point comparison data sequence of each effective feature comparison array; based on the difference between the elements of the effective feature point comparison data sequence, obtain the relative feature difference coefficient of each element in the effective feature point comparison data sequence;

[0010] The sequence composed of the relative feature difference coefficients of all elements in the effective feature comparison data sequence is used as the effective information comparison sequence of each effective feature comparison array; based on the difference and similarity between the effective information comparison sequences, the confidence weight of each effective information comparison sequence is obtained;

[0011] Based on the effective information comparison sequence and the confidence weight of the effective information comparison sequence, the effective classification comparison coefficient of each effective information data is obtained;

[0012] Classify and manage valid information data according to the effective classification comparison coefficient to improve customer consulting services.

[0013] Furthermore, the method for obtaining each effective feature comparison array and the effective information feature matrix of each effective feature comparison array is:

[0014] Use clustering algorithms to cluster all customers' valid information data groups, and use the clusters obtained after the division as valid feature comparison arrays;

[0015] For each valid feature comparison array, the valid information data group of each customer in the valid feature comparison array is used as each row of data in the matrix, and the standardized result of the matrix composed of the valid information data groups of all customers in the valid feature comparison array is used as the effective information feature matrix of each valid feature comparison array.

[0016] Furthermore, the method for obtaining the relative coefficient of information feature fluctuation is:

[0017] For the effective information feature matrix of each effective feature comparison array, calculate the coefficient of variation of any column of data in the effective information feature matrix, and use the difference between the coefficient of variation of any column of data and other columns of data as the first difference between any column of data and other columns of data;

[0018] Based on a first difference between any column and data in all other columns except any column, a relative coefficient of information feature fluctuation between any column and data in all other columns except any column is obtained; the relative coefficient of information feature fluctuation is positively correlated with the first difference.

[0019] Furthermore, the method for obtaining the consultation feature comparison coefficient is:

[0020] For the effective information feature matrix of each effective feature comparison array, the mean of the information feature fluctuation relative coefficients between each column of data in the effective information feature matrix and all other columns of data is used as the consulting feature comparison coefficient of each column of data in each effective information feature matrix.

[0021] Furthermore, the method for obtaining the effective feature point comparison data sequence is:

[0022] For each effective information feature matrix, a sequence of consulting feature comparison coefficients corresponding to each column of data in the effective information feature matrix is ​​used as a sequence of effective feature point comparison data of an effective feature comparison array corresponding to each effective information feature matrix.

[0023] Further, the relative characteristic difference coefficient is obtained by:

[0024] For the effective feature point comparison data sequence of each effective feature comparison array, the difference between each element in the effective feature point comparison data sequence and the element at the same position in other effective feature point comparison data sequences is calculated as the second difference; for each element in the effective feature point comparison data sequence, the average of all second differences of the element is calculated as the relative feature difference coefficient of each element in the effective feature point comparison data sequence of each effective feature comparison array.

[0025] Further, the confidence weight is obtained by:

[0026] The difference between the effective information comparison sequence of each effective feature comparison array and the effective information comparison sequences of other effective feature comparison arrays is calculated as the first effective comparison coefficient; the similarity between the effective information feature matrix of each effective feature comparison array and other effective feature comparison arrays is taken as the second effective comparison coefficient; the confidence weight is obtained according to the first effective comparison coefficient and the second effective comparison coefficient, and the confidence weight is proportional to the first effective comparison coefficient, and the confidence weight is inversely proportional to the second effective comparison coefficient.

[0027] Furthermore, the method for obtaining the effective classification contrast coefficient is:

[0028] For each valid information data, the product of the element corresponding to the valid information data in each valid information comparison sequence and the confidence weight of the valid information comparison sequence where the element is located is taken as the first product, and the sum of all the first products is taken as the effective classification comparison coefficient of each valid information data.

[0029] Further, the classification management of the effective information data according to the effective classification comparison coefficient includes:

[0030] A set consisting of normalized results of effective classification comparison coefficients of all types of effective information data is used as an effective information comparison set;

[0031] Calculate the mean of all elements in the valid information comparison set as a first mean, and use the valid information data corresponding to the elements in the valid information comparison set that are greater than the first mean as the first valid information data;

[0032] A clustering algorithm is used to cluster all first valid information data, and the results of the clustering are stored in the enterprise consulting service platform for classification management.

[0033] In a second aspect, an embodiment of the present application also provides an enterprise consulting service processing system, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of any one of the above-mentioned enterprise consulting service processing methods when executing the computer program.

[0034] This application has at least the following beneficial effects:

[0035] The present invention divides the data into customers once by comprehensively analyzing the differences in all kinds of service data in the process of enterprise consulting services, and compares and analyzes the effective data features of different groups of customers based on the results of the one-time division, obtains the consulting feature comparison coefficient after the preliminary division based on the analysis results, and further analyzes the relative feature differences of different groups of customer data through the differences in the consulting feature comparison coefficients, reflecting the relative differences in the features of effective information data under different effective information data after the preliminary division, and can further accurately analyze the effective comparison features of customer division, and determine the effective information data for accurately classifying the obtained customer data through the analysis results of the effective comparison features. The beneficial effect is to avoid the problem of large errors in adopting a one-time classification method due to the differences in customer data features, and at the same time, conduct targeted analysis on the local data features of different customer data, to avoid the problem of large errors in the overall feature difference analysis of customer data, and then adjust the effective information data based on the analysis results to accurately classify enterprise consulting service customers, and improve the management of enterprise consulting services. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present application or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0037] Figure 1 A flowchart of a method for processing enterprise consulting services provided in accordance with an embodiment of the present application;

[0038] Figure 2 Flowchart for obtaining contrast coefficients for effective classification. DETAILED DESCRIPTION

[0039] In order to further explain the technical means and effects adopted by the present application to achieve the predetermined invention purpose, the following is a detailed description of a business consulting service processing method and system proposed in accordance with the present application, its specific implementation method, structure, features and effects, in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0040] 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 application belongs.

[0041] The following is a detailed description of a specific solution of a business consulting service processing method and system provided by the present application in conjunction with the accompanying drawings.

[0042] See also Figure 1 , which shows a flowchart of a method for processing enterprise consulting services provided by an embodiment of the present application, the method comprising the following steps:

[0043] Step S1, obtaining valid information data of customers in the process of enterprise consulting service management.

[0044] The valid information data of each customer is obtained on the enterprise consulting service management platform. The types of the valid information data include the number of customer consultations, total number of transactions, cooperation time, purchase frequency, total transaction amount, average transaction amount and cross-selling volume, where the purchase frequency refers to the number of transactions between the customer and the enterprise in a unit of time; the cross-selling volume is obtained based on the number of product types in the orders generated by the customer and the enterprise. The sequence composed of the valid information data of each customer in the order of the above data is taken as the valid information data group of each customer, where the number of customers who obtain valid information data is , in this embodiment, the value is 500.

[0045] It should be noted that this application completes the processing of customer classification in corporate consulting services based on valid information data obtained according to the set number of customers. The implementer can set the data volume based on the number of customers existing in the actual management process.

[0046] At this point, a valid information data set of each customer in the enterprise consulting service management process has been obtained.

[0047] Step S2, conduct preliminary feature analysis based on the effective information data features of customers during the enterprise consultation process, construct a consulting feature comparison coefficient based on the division results, calculate the relative feature difference coefficient through the difference analysis of the consulting feature comparison coefficient, and obtain the effective classification comparison coefficient based on the relative feature difference coefficient.

[0048] Since the data generated during the consulting service process for each customer is statistically analyzed, the consulting service characteristics of the customer under different indicators can be obtained. In the process of classifying customers by using the differences in the consulting service data of customers under different indicators, since the relevant data information of consulting service customers is complex and diverse, using all the consulting service data characteristics for customer classification cannot achieve accurate classification. Therefore, differential feature analysis based on the differences in data characteristics under all indicators may affect the analysis results of effective customer relationships.

[0049] Normally, the process of dividing customers using clustering algorithms takes into account the values ​​of the extracted customer data features. However, in the process of dividing customers based on all data feature differences, due to the influence of data feature differences with smaller significance differences, the processing of customer service data is not effectively classified. Therefore, the present application introduces a relative significance difference analysis of the extracted customer data features in the process of customer division, and performs secondary classification based on the analysis results to achieve effective classification processing of customers.

[0050] Specifically, a clustering algorithm is used to perform clustering division on the effective information data groups of all customers as a preliminary division according to the differences in the effective information data groups of different customers in the process of enterprise consulting service management, and each cluster cluster obtained after the division is used as each effective feature comparison array; wherein the clustering division method in this embodiment can be an agglomerative hierarchical clustering algorithm, and the difference calculation results between the effective information data groups of each customer are used as the metric distance between each effective feature comparison array during clustering, and the difference calculation results between the effective information data groups can be the DTW distance, Manhattan distance, etc. between each effective information data group, which will not be described in detail here. Among them, the agglomerative hierarchical clustering algorithm is a well-known technology and will not be described in detail here.

[0051] Furthermore, for each effective feature comparison array, the effective information data group of each customer in the effective feature comparison array is used as each row of data in the matrix, and the standardized result of the matrix composed of the effective information data groups of all customers in the effective feature comparison array is used as the effective information feature matrix of each effective feature comparison array.

[0052] Furthermore, the consultation feature comparison coefficient is obtained, and the specific acquisition process is as follows:

[0053] For the effective information feature matrix of each effective feature comparison array, calculate the coefficient of variation of any column of data in the effective information feature matrix, and use the difference between the coefficient of variation of any column of data and other columns of data as the first difference between any column of data and other columns of data;

[0054] Based on a first difference between any column and data in all other columns except any column, a relative coefficient of information feature fluctuation between any column and data in all other columns except any column is obtained; the relative coefficient of information feature fluctuation is positively correlated with the first difference.

[0055] Specifically, the present application proposes an embodiment, for the effective information feature matrix of each effective feature comparison array, the absolute value of the difference between the coefficient of variation of each column of data and each other column of data is used as the relative coefficient of information feature fluctuation between each column of data and each other column of data.

[0056] It should be noted that the positive correlation relationship can be an idempotent relationship of multiplication, addition, or exponential function, which can be determined based on actual conditions and will not be elaborated in this application.

[0057] For the effective information feature matrix of each effective feature comparison array, the mean of the information feature fluctuation relative coefficients between each column of data in the effective information feature matrix and all other columns of data is used as the consulting feature comparison coefficient of each column of data in each effective information feature matrix.

[0058] The larger the consulting feature comparison coefficient is, the greater the volatility difference of all customers in each effective feature comparison array in different types of effective information data after clustering, that is, the relative difference of customer consulting data characteristics in each effective feature comparison array is relatively large. That is, the consulting feature comparison coefficient reflects the comparison results of each type of effective information data of the customer data initially divided in the enterprise consulting process, and then the data feature differences of the initially divided customer information can be obtained through the consulting feature comparison coefficient.

[0059] Normally, the above preliminary division is made by comparing the relative differences of different customers under all valid information data, that is, the above clustering division method is used to take all valid information data as a reference for difference comparison, and customers with large differences in consulting service characteristics may be divided into one category of users. For example, when customers with a large number of consultations and a small number of consultations are significantly divided into one category of users due to other valid data comparison characteristics, there are large differences in the consulting behavior characteristics of the two types of customers. If classified in this way, it may affect the quality of subsequent consulting services.

[0060] It may not be possible to achieve effective classification after a preliminary division. Therefore, based on an overall comparative division, a difference comparison of local data is carried out to obtain the consulting feature comparison coefficient. The relative differences of the consulting data can be further analyzed through the relative differences of the consulting feature comparison coefficient. The relative differences in the consulting data can be used to accurately reflect the relative differences in customer consulting data characteristics after the preliminary division.

[0061] Furthermore, for each effective information feature matrix, a sequence of consulting feature comparison coefficients corresponding to each column of data in the effective information feature matrix is ​​used as an effective feature point comparison data sequence of an effective feature comparison array corresponding to each effective information feature matrix.

[0062] Compare the data sequence based on the effective feature points to obtain the relative feature difference coefficient. The acquisition method is as follows:

[0063] Specifically, for the effective feature point comparison data sequence of each effective feature comparison array, the difference between each element in the effective feature point comparison data sequence and the element at the same position in other effective feature point comparison data sequences is calculated as the second difference; for each element in the effective feature point comparison data sequence, the average of all second differences of the element is calculated as the relative feature difference coefficient of each element in the effective feature point comparison data sequence of each effective feature comparison array.

[0064] Specifically, the present application proposes an embodiment in which the second difference is calculated as the absolute value of the difference between each element in the effective feature point comparison data sequence and the elements at the same position in the effective feature point comparison data sequence of the effective information feature matrix of other effective feature comparison arrays.

[0065] The larger the relative characteristic difference coefficient is, the greater the comparative characteristic difference of the effective information data between each group of customers and other groups of customers after clustering.

[0066] The relative difference in the characteristics of the effective information data after the initial division is reflected by the relative characteristic difference coefficient, which can further accurately analyze the effective comparison characteristics of customer division; it should be noted that the elements in the effective information comparison sequence correspond according to the type of effective information data; the sequence composed of the relative characteristic difference coefficients of all elements in the effective characteristic comparison data sequence is taken as the effective information comparison sequence.

[0067] On the basis of preliminary division, comparative analysis is conducted on each type of valid information data. In addition to combining the differences in the characteristics of valid information data of different groups of customer data, the numerical differences between different groups of customer data should be further analyzed to accurately reflect the relative accuracy of the analysis of valid information characteristics. That is, the analysis results of valid information data with different data difference characteristics are given the same weight. Then, after preliminary division, different groups of customer data with large numerical differences will have less significance when used for the analysis of valid information comparative characteristics, which affects the analysis of customer classification characteristics.

[0068] Furthermore, confidence weights are added to each valid feature comparison array through the valid information comparison sequence. The specific way to obtain the confidence weights is as follows:

[0069] The difference between the effective information comparison sequence of each effective feature comparison array and the effective information comparison sequences of other effective feature comparison arrays is calculated as the first effective comparison coefficient; the similarity between the effective information feature matrix of each effective feature comparison array and other effective feature comparison arrays is taken as the second effective comparison coefficient; the confidence weight is obtained according to the first effective comparison coefficient and the second effective comparison coefficient, and the confidence weight is proportional to the first effective comparison coefficient, and the confidence weight is inversely proportional to the second effective comparison coefficient.

[0070] Specifically, the present application proposes an embodiment, which calculates the DTW distance between the effective information comparison sequence of each effective feature comparison array and the effective information comparison sequence of other effective feature comparison arrays as the first effective comparison coefficient; for the effective information feature matrix of each effective feature comparison array and other effective feature comparison arrays, calculate the absolute value of the difference between the elements in the same position in the two effective information feature matrices as the first absolute value of the difference, calculate the sum of all the first absolute values ​​of the difference between each effective feature comparison array and other effective feature comparison arrays as the second effective comparison coefficient, and take the average of the results of accumulating the ratio of the first effective comparison coefficient to the second effective comparison coefficient over all groups of customer data as the confidence weight of the effective information comparison sequence of each effective feature comparison array.

[0071] Furthermore, the above calculation obtains the effective information comparison sequence of each effective feature comparison array, and each element in the effective information comparison sequence corresponds to a type of effective information data. Therefore, the effective information comparison features of different effective feature comparison arrays under the same effective information data can be used to reflect the effective features of the overall effective information data for customer segmentation. The effective classification comparison coefficient is obtained through the relationship between the effective information comparison sequence elements of different effective feature comparison arrays under the same effective information data. The specific acquisition process includes:

[0072] For each valid information data, the product of the element corresponding to the valid information data in each valid information comparison sequence and the confidence weight of the valid information comparison sequence where the element is located is taken as the first product, and the sum of all the first products is taken as the effective classification comparison coefficient of each valid information data. The flow chart for obtaining the effective classification comparison coefficient is as follows: Figure 2 shown.

[0073] The effective classification contrast coefficient reflects the effective features of the overall effective information data for customer segmentation through the comparison of the information data after preliminary segmentation. The larger the effective classification contrast coefficient, the more significant the features used for effective customer segmentation.

[0074] At this point, the effective classification comparison coefficient of each effective information data is obtained.

[0075] Step S3, accurately classify the enterprise consulting service customers according to the effective classification comparison coefficient, and store the classification results in the enterprise consulting service platform.

[0076] The set consisting of the normalized results of the effective classification comparison coefficients of all types of effective information data is taken as the effective information comparison set, wherein the normalization processing method can be: the proportion of the effective comparison coefficient of each type of effective information data in the effective classification comparison coefficients of all types of effective information data is taken as the normalized result of the effective comparison coefficient of each type of effective information data.

[0077] Furthermore, the data difference comparison in the customer segmentation process can be adjusted according to the effective classification comparison coefficient of the effective information data. Specifically, the mean of all elements in the effective information comparison set is calculated as the first mean, and the effective information data corresponding to the elements in the effective information comparison set that are greater than the first mean is taken as the first effective information data. A clustering algorithm is used to cluster all the first effective information data, and the results of the segmentation are stored in the enterprise consulting service platform for classification management, which will be used as the basic data for subsequent improvement of customer consulting services.

[0078] Based on the same inventive concept as the above method, an embodiment of the present application also provides an enterprise consulting service processing system, including a memory, a processor, and a computer program stored in the memory and running on the processor, and when the processor executes the computer program, the steps of any one of the above-mentioned enterprise consulting service processing methods are implemented.

[0079] It should be noted that the above sequence of the embodiments of the present application is for description only and does not represent the advantages and disadvantages of the embodiments. The above is a description of a specific embodiment of this specification. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0080] The various embodiments in the present application are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0081] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present application should be included in the protection scope of the present application.

Claims

1. A method for processing enterprise consulting services, characterized in that: The method comprises the following steps: Collect a valid information data group consisting of various valid information data of each customer; Obtain each valid feature comparison array and a valid information feature matrix of each valid feature comparison array according to each customer's valid information data group; Based on the volatility differences between the data in the effective information feature matrix, the relative coefficient of information feature fluctuation between each column of data in each effective information feature matrix and other columns of data is obtained; based on the relative coefficient of information feature fluctuation, the consulting feature comparison coefficient of each effective information feature matrix is ​​obtained; Based on the consulting feature comparison coefficient, obtain the effective feature point comparison data sequence of each effective feature comparison array; based on the difference between the elements of the effective feature point comparison data sequence, obtain the relative feature difference coefficient of each element in the effective feature point comparison data sequence; The sequence composed of the relative feature difference coefficients of all elements in the effective feature comparison data sequence is used as the effective information comparison sequence of each effective feature comparison array; based on the difference and similarity between the effective information comparison sequences, the confidence weight of each effective information comparison sequence is obtained; Based on the effective information comparison sequence and the confidence weight of the effective information comparison sequence, the effective classification comparison coefficient of each effective information data is obtained; Classify and manage effective information data according to effective classification comparison coefficients to improve customer consulting services; The method for obtaining each effective feature comparison array and the effective information feature matrix of each effective feature comparison array is: Use clustering algorithms to cluster all customers' valid information data groups, and use the clusters obtained after the division as valid feature comparison arrays; For each effective feature comparison array, the effective information data group of each customer in the effective feature comparison array is used as each row of data in the matrix, and the standardized result of the matrix composed of the effective information data groups of all customers in the effective feature comparison array is used as the effective information feature matrix of each effective feature comparison array; The method for obtaining the relative coefficient of information characteristic fluctuation is: For the effective information feature matrix of each effective feature comparison array, calculate the coefficient of variation of any column of data in the effective information feature matrix, and use the difference between the coefficient of variation of any column of data and other columns of data as the first difference between any column of data and other columns of data; Based on a first difference between any column and data of all other columns except any column, obtaining a relative coefficient of information feature fluctuation between any column and data of all other columns except any column; the relative coefficient of information feature fluctuation is positively correlated with the first difference; The method for obtaining the consultation feature comparison coefficient is: For the effective information feature matrix of each effective feature comparison array, the average of the information feature fluctuation relative coefficients between each column of data in the effective information feature matrix and all other columns of data is used as the consulting feature comparison coefficient of each column of data in each effective information feature matrix; The method for obtaining the relative characteristic difference coefficient is: For the effective feature point comparison data sequence of each effective feature comparison array, the difference between each element in the effective feature point comparison data sequence and the element at the same position in other effective feature point comparison data sequences is calculated as the second difference; for each element in the effective feature point comparison data sequence, the average of all the second differences of the element is calculated as the relative feature difference coefficient of each element in the effective feature point comparison data sequence of each effective feature comparison array; The method for obtaining the confidence weight is: The difference between the effective information comparison sequence of each effective feature comparison array and the effective information comparison sequences of other effective feature comparison arrays is calculated as the first effective comparison coefficient; the similarity between the effective information feature matrix of each effective feature comparison array and other effective feature comparison arrays is taken as the second effective comparison coefficient; the confidence weight is obtained according to the first effective comparison coefficient and the second effective comparison coefficient, and the confidence weight is proportional to the first effective comparison coefficient, and the confidence weight is inversely proportional to the second effective comparison coefficient.

2. A method for processing enterprise consulting services as claimed in claim 1, characterized in that: The method for obtaining the effective feature point comparison data sequence is: For each effective information feature matrix, a sequence of consulting feature comparison coefficients corresponding to each column of data in the effective information feature matrix is ​​used as a sequence of effective feature point comparison data of an effective feature comparison array corresponding to each effective information feature matrix.

3. The enterprise consulting service processing method according to claim 1, characterized in that: The method for obtaining the effective classification contrast coefficient is: For each valid information data, the product of the element corresponding to the valid information data in each valid information comparison sequence and the confidence weight of the valid information comparison sequence where the element is located is taken as the first product, and the sum of all the first products is taken as the valid classification comparison coefficient of each valid information data.

4. The enterprise consulting service processing method according to claim 1, characterized in that: The classifying and managing the valid information data according to the valid classification comparison coefficient includes: A set consisting of normalized results of effective classification comparison coefficients of all types of effective information data is used as an effective information comparison set; Calculate the mean of all elements in the valid information comparison set as a first mean, and use the valid information data corresponding to the elements in the valid information comparison set that are greater than the first mean as the first valid information data; A clustering algorithm is used to cluster all first valid information data, and the results of the clustering are stored in the enterprise consulting service platform for classification management.

5. An enterprise consulting service processing system, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the enterprise consulting service processing method as described in any one of claims 1 to 4 are implemented.

Images