Management Method and Management System for Aftermarket Services of Numerical Control Machine Tools

Abstract

This application relates to the field of intelligent management, and provides a management method and a management system for the aftermarket service project of a numerical control machine tool. It mainly divides the service project management into pre-sales management, in-sales management, and after-sales management. In the customer feedback management of after-sales management, by extracting the data set of customer feedback and using a data processing algorithm based on deep learning to perform semantic understanding of the customer feedback, so as to automatically evaluate whether the user satisfaction is positive or negative according to the significant dynamic aggregation representation of the distribution field among the semantic features of each customer feedback, which can ensure that the interpretation and classification of customer feedback have higher objectivity and consistency. And it can capture the subtle differences in customer feedback, perceive the underlying customer emotions and potential problems, so as to provide a more comprehensive feedback analysis.

Description

Technical Field

[0001] This application relates to the field of intelligent management, and more specifically, to a management method and system for after-market service projects of numerically controlled machine tools. Background Art

[0002] Modern numerically controlled machine tools usually integrate complex mechanical structures, precise electronic control systems, and advanced software programs, which makes the maintenance and technical support of the equipment become more and more important. Customers' demands for numerically controlled machine tools are no longer just to purchase the equipment itself, but also include a series of service supports, such as pre-sales technical consultation, in-sales project management, and after-sales technical support, etc. These service demands require manufacturers to not only provide high-quality products but also provide comprehensive service guarantees. Therefore, high-quality service has become a key factor in enhancing customer satisfaction and loyalty.

[0003] However, in the traditional management of after-market service projects of numerically controlled machine tools, the data management is scattered, resulting in serious information silo phenomena. It is difficult for various departments to share and synchronize information, which affects the integration and analysis of data. For example, if key data such as customer service records, maintenance history, and spare parts usage cannot be centrally managed, a complete service history record cannot be formed, thus affecting the effectiveness of decision-making and service efficiency. In addition, the customer feedback mechanism is not perfect, so that customers' opinions and suggestions cannot be collected and processed in time, affecting the continuous improvement of service quality.

[0004] Therefore, an optimized management solution for after-market service projects of numerically controlled machine tools is needed. Summary of the Invention

[0005] This application aims at the deficiencies in the prior art and provides a management method and system for after-market service projects of numerically controlled machine tools.

[0006] According to one aspect of this application, a management system for after-market service projects of numerically controlled machine tools is provided, which includes: a pre-sales management module, an in-sales management module, and an after-sales management module;

[0007] Among them, the after-sales management module includes a service request management unit, a repair management unit, a customer feedback management unit, and a maintenance plan unit. The service request management unit is used to record and classify customers' after-sales service requests and track the processing status; the repair management unit is used to manage the repair process; the customer feedback management unit is used to collect customer feedback and analyze customer satisfaction; the maintenance plan unit is used to formulate and execute regular maintenance plans;

[0008] Among them, the customer feedback management unit includes: a customer feedback data collection subunit for extracting a dataset of customer feedback; a customer feedback data semantic encoding subunit for semantically encoding each customer feedback in the dataset of customer feedback to obtain a set of customer feedback semantic encoding feature vectors; a customer feedback significant aggregation subunit for dynamically aggregating the feature distribution fields of the set of customer feedback semantic encoding feature vectors to obtain a customer feedback significant aggregation representation. Among them, the customer feedback significant aggregation subunit includes: a customer feedback semantic static energy factor calculation secondary subunit for calculating the static energy factor of each customer feedback semantic encoding feature vector in the set of customer feedback semantic encoding feature vectors to obtain a set of customer feedback semantic static energy factors; a customer feedback semantic feature aggregation secondary subunit for significantly aggregating the features of the set of customer feedback semantic encoding feature vectors based on the set of customer feedback semantic static energy factors based on an imitation force field to obtain the customer feedback significant aggregation representation; a satisfaction evaluation result generation subunit for obtaining a satisfaction evaluation result based on the customer feedback significant aggregation representation.

[0009] In the above-mentioned after-sales service project management system for CNC machine tools, the pre-sales management module includes a customer demand collection unit, a technical consultation and support unit, a solution design unit, and an estimated quotation unit. The customer demand collection unit is used to record the basic information and demand description of the customer; the technical consultation and support unit is used to provide technical support and consultation services for the customer; the solution design unit is used to provide a customized solution based on the demand description of the customer; the estimated quotation unit is used to determine the estimated cost based on the customized solution and generate a quotation. The in-sales management module includes a contract signing unit, a project allocation unit, and a progress tracking unit. The contract signing unit is used to manage the creation and approval process of the sales contract; the project allocation unit is used to allocate appropriate technical personnel and resources according to the project requirements; the progress tracking unit is used to monitor the project progress in real time.

[0010] In the above-mentioned after-sales service project management system for CNC machine tools, the customer feedback semantic static energy factor calculation secondary subunit is used to: calculate the mean and variance of the customer feedback semantic encoding feature vectors to obtain the customer feedback semantic mean and the customer feedback semantic variance; subtract the customer feedback semantic encoding feature vectors from the customer feedback semantic mean position by position, and calculate the fourth power of each position of the subtracted feature vectors to obtain a customer feedback semantic difference modulation vector; calculate the expected value of the customer feedback semantic difference modulation vector to obtain the customer feedback semantic expected value; divide the customer feedback semantic expected value by the square of the customer feedback semantic variance, and input the obtained value into the sigmoid function to obtain the customer feedback semantic static energy factor.

[0011] In the above-mentioned after-sales service project management system for CNC machine tools, the secondary subunit for aggregating semantic features of customer feedback includes: a tertiary subunit for determining the initial center vector of customer feedback semantic clustering, which is used to select the customer feedback semantic coding feature vector corresponding to the largest customer feedback semantic static energy factor in the set of customer feedback semantic static energy factors as the initial center vector of customer feedback semantic clustering; a tertiary subunit for calculating the dynamic aggregation energy factor of customer feedback semantic, which is used to calculate the dynamic aggregation energy factor of each customer feedback semantic coding feature vector in the set of customer feedback semantic coding feature vectors based on the spatial span between each customer feedback semantic coding feature vector in the set of customer feedback semantic coding feature vectors and the initial center vector of customer feedback semantic clustering, as well as the static energy factor of each customer feedback semantic coding feature vector and the static energy factor of the initial center vector of customer feedback semantic clustering, so as to obtain a set of dynamic aggregation energy factors of customer feedback semantic; a tertiary subunit for the gating mask of the dynamic aggregation energy factor of customer feedback semantic, which is used to input the set of dynamic aggregation energy factors of customer feedback semantic into the gating mask unit to obtain a set of dynamic aggregation weight factors of customer feedback semantic; a tertiary subunit for generating the significant aggregation representation of customer feedback, which is used to calculate the weighted sum of the set of customer feedback semantic coding feature vectors with the set of dynamic aggregation weight factors of customer feedback semantic to obtain a customer feedback significant aggregation representation vector as the significant aggregation representation of customer feedback.

[0012] In the above-mentioned after-sales service project management system for CNC machine tools, the tertiary subunit for calculating the dynamic aggregation energy factor of customer feedback semantic is used for: multiplying the static energy factor of the customer feedback semantic coding feature vector, the static energy factor of the initial center vector of customer feedback semantic clustering and the first weighting parameter to obtain the first dynamic aggregation energy factor of customer feedback semantic; multiplying the square of the spatial span between the customer feedback semantic coding feature vector and the initial center vector of customer feedback semantic clustering and the second weighting parameter to obtain the second dynamic aggregation energy factor of customer feedback semantic; dividing the first dynamic aggregation energy factor of customer feedback semantic by the second dynamic aggregation energy factor of customer feedback semantic to obtain the dynamic aggregation energy factor of customer feedback semantic.

[0013] In the above-mentioned after-sales service project management system for CNC machine tools, the three-level sub-unit of the gating mask for the semantic dynamic aggregation energy factor of customer feedback includes: a four-level sub-unit for normalizing the semantic dynamic aggregation energy factor of customer feedback, which is used to perform normalization processing on the set of the semantic dynamic aggregation energy factor of customer feedback to obtain a set of normalized semantic dynamic aggregation energy factors of customer feedback; a four-level sub-unit for masking the normalized semantic dynamic aggregation energy factor, which is used to perform masking processing on the set of the normalized semantic dynamic aggregation energy factor of customer feedback to obtain a set of semantic dynamic aggregation weight factors of customer feedback.

[0014] In the above-mentioned after-sales service project management system for CNC machine tools, the four-level sub-unit for normalizing the semantic dynamic aggregation energy factor is used to: calculate the exponential function values with the negative numbers of each semantic dynamic aggregation energy factor in the set of the semantic dynamic aggregation energy factor of customer feedback as exponents, with the natural constant e as the base, to obtain a set of semantic dynamic aggregation energy index factors of customer feedback; after adding the set of the semantic dynamic aggregation energy index factors of customer feedback and the constant one in a position-by-position manner, calculate the reciprocals of each semantic dynamic aggregation energy index modulation factor in the obtained set of semantic dynamic aggregation energy index modulation factors to obtain the set of normalized semantic dynamic aggregation energy factors of customer feedback.

[0015] In the above-mentioned after-sales service project management system for CNC machine tools, the four-level sub-unit for masking the normalized semantic dynamic aggregation energy factor is used to: in response to each normalized semantic dynamic aggregation energy factor in the set of the normalized semantic dynamic aggregation energy factor of customer feedback being greater than a predetermined threshold, set the normalized semantic dynamic aggregation energy factor to its original value and set the rest to zero, to obtain a set of semantic dynamic aggregation weight factors of customer feedback.

[0016] In the above-mentioned after-sales service project management system for CNC machine tools, the sub-unit for generating the satisfaction evaluation result is used to: input the significantly aggregated representation vector of customer feedback into the customer satisfaction evaluation module based on a classifier to obtain the satisfaction evaluation result, and the satisfaction evaluation result is used to indicate that the user satisfaction is positive or negative.

[0017] According to another aspect of the present application, a method for managing after-sales service projects of CNC machine tools is provided, which includes:

[0018] Pre-sales management steps: recording the basic information and requirement descriptions of customers; providing customers with technical support and consulting services; providing customized solutions based on the requirement descriptions of customers; determining the estimated cost and generating a quotation based on the customized solutions;

[0019] After-sales management steps: Manage the creation and approval process of sales contracts; allocate appropriate technical personnel and resources according to project requirements; monitor project progress in real time;

[0020] After-sales management steps: Record and classify customers' after-sales service requests, track the handling status; manage the repair process; collect customer feedback and analyze customer satisfaction; formulate and implement regular maintenance plans.

[0021] Due to the adoption of the above technical solutions, this application has remarkable technical effects:

[0022] This application has at least the following technical effects: Compared with the prior art, the method and system for managing the after-market service projects of a numerically controlled machine tool provided by this application mainly divide the service project management into pre-sales management, in-sales management, and after-sales management. In the customer feedback management of after-sales management, by extracting the data set of customer feedback and using a data processing algorithm based on deep learning to perform semantic understanding of the customer feedback, and thus automatically evaluate whether the user satisfaction is positive or negative according to the significant dynamic aggregation representation of the distribution fields between the semantic features of each customer feedback, it can ensure that the interpretation and classification of customer feedback have higher objectivity and consistency. And it can capture the subtle differences in customer feedback, perceive the underlying customer emotions and potential problems, so as to provide a more comprehensive feedback analysis. Description of the Drawings

[0023] By describing the embodiments of the present application in more detail in conjunction with the drawings, the above and other objects, features, and advantages of the present application will become more obvious. The drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation to the present application. In the drawings, the same reference numerals generally represent the same components or steps.

[0024] Figure 1 It is a block diagram of the customer feedback management unit in the after-market service project management system of a numerically controlled machine tool according to an embodiment of the present application.

[0025] Figure 2 It is a schematic diagram of the data flow of the customer feedback management unit in the after-market service project management system of a numerically controlled machine tool according to an embodiment of the present application.

[0026] Figure 3 It is a block diagram of the customer feedback significant aggregation subunit in the after-market service project management system of a numerically controlled machine tool according to an embodiment of the present application.

[0027] Figure 4 It is a block diagram of the second-level subunit for aggregating semantic features of customer feedback in the after-market service project management system of a numerically controlled machine tool according to an embodiment of the present application.

[0028] Figure 5 It is a block diagram of a three - level sub - unit of a customer feedback semantic dynamic aggregation energy factor gating mask in a post - market service project management system for a numerically controlled machine tool according to an embodiment of the present application.

[0029] Figure 6 It is a flowchart of a method for managing post - market service projects of numerically controlled machine tools according to an embodiment of the present application. Detailed implementation manners

[0030] Next, exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. It should be understood that the present application is not limited by the exemplary embodiments described herein.

[0031] Due to the increasing complexity of numerically controlled machine tools, they not only contain sophisticated mechanical structures but also integrate advanced electronic control and software technologies. This technological advancement makes the maintenance and customer service of machine tools crucial. Customers' expectations for numerically controlled machine tools have gone beyond simple product purchases, and they also seek a series of services including technical consultation, project management, and technical support.

[0032] To meet these needs, manufacturers must provide not only high - quality products but also comprehensive service guarantees. Excellent service is the key to enhancing customer satisfaction and loyalty. However, traditional numerically controlled machine tool service project management faces problems such as data dispersion and information silos, which hinder information sharing and synchronization among different departments and affect the efficiency of data integration and analysis. For example, if key data such as customer service records, repair histories, and spare part usage cannot be centrally managed, a complete service history file cannot be constructed, which will affect the accuracy of decision - making and the response speed of services. In addition, if the customer feedback mechanism is not perfect, customers' opinions and suggestions cannot be collected and processed in a timely manner, which will prevent the continuous improvement of service quality.

[0033] Based on this, the present application proposes an optimized after-sales service project management system for CNC machine tools, which includes: a pre-sales management module, the pre-sales management module includes a customer demand collection unit, a technical consultation and support unit, a solution design unit and an estimated quotation unit. The customer demand collection unit is used to record the basic information and demand description of the customer; the technical consultation and support unit is used to provide technical support and consultation services for the customer; the solution design unit is used to provide a customized solution based on the demand description of the customer; the estimated quotation unit is used to determine the estimated cost and generate a quotation based on the customized solution; a mid-sales management module, the mid-sales management module includes a contract signing unit, a project allocation unit and a progress tracking unit. The contract signing unit is used to manage the creation and approval process of the sales contract; the project allocation unit is used to allocate appropriate technical personnel and resources according to the project requirements; the progress tracking unit is used to monitor the project progress in real time; an after-sales management module, the after-sales management module includes a service request management unit, a maintenance management unit, a customer feedback management unit and a maintenance plan unit. The service request management unit is used to record and classify the after-sales service requests of the customer and track the processing status; the maintenance management unit is used to manage the maintenance process; the customer feedback management unit is used to collect customer feedback and analyze customer satisfaction; the maintenance plan unit is used to formulate and execute a regular maintenance plan.

[0034] The optimized after-sales service project management system for CNC machine tools provided by the present application realizes comprehensive management from pre-sales to after-sales, including multiple links such as customer demand collection, technical consultation and support, solution design, estimated quotation, contract signing, project allocation, progress tracking, service request management, maintenance management, customer feedback management and maintenance plan. By centrally managing all data in pre-sales, mid-sales and after-sales, it breaks the information silos and realizes information sharing and synchronization among departments.

[0035] Among them, in the after-sales service project management system for CNC machine tools, customer feedback management is a crucial step. Specifically, customer feedback directly reflects the problems existing in the service process and the real feelings of the customer. By collecting and analyzing this feedback, service providers can timely discover the problems and take measures to improve, so as to continuously improve the service quality. However, in traditional methods, the interpretation and classification of customer feedback often rely on manual judgment, which makes the results easily affected by personal experience and subjective biases and lack a unified objective standard. In addition, traditional analysis methods usually only stay at the surface text level and are difficult to deeply understand the emotional tendency, implicit needs or root causes of potential problems of the customer, resulting in deviations in the analysis results.

[0036] Accordingly, in the customer feedback management unit, the technical concept of the present application is to extract the dataset of customer feedback and use a data processing and parsing algorithm based on deep learning to perform semantic understanding of the customer feedback, so as to automatically evaluate whether the user satisfaction is positive or negative based on the significant dynamic aggregation representation of the distribution fields between the semantic features of each customer feedback, which can reduce the subjectivity and bias brought by manual judgment and ensure higher objectivity and consistency in the interpretation and classification of customer feedback. And it can capture the subtle differences in customer feedback, perceive the underlying customer emotions and potential problems, so as to provide a more comprehensive feedback analysis and realize the automation of customer feedback management.

[0037] Figure 1 It is a block diagram of the customer feedback management unit in the after-market service project management system of a numerically controlled machine tool according to an embodiment of the present application. Figure 2 It is a schematic diagram of data flow in the customer feedback management unit in the after-market service project management system of a numerically controlled machine tool according to an embodiment of the present application. As Figure 1 and Figure 2 As shown, in the customer feedback management unit 100, it includes: a customer feedback data collection subunit 110 for extracting the dataset of customer feedback; a customer feedback data semantic encoding subunit 120 for semantically encoding each customer feedback in the dataset of the customer feedback to obtain a set of customer feedback semantic encoding feature vectors; a customer feedback significant aggregation subunit 130 for performing feature distribution field dynamic aggregation on the set of customer feedback semantic encoding feature vectors to obtain a customer feedback significant aggregation representation; and a satisfaction evaluation result generation subunit 140 for obtaining a satisfaction evaluation result based on the customer feedback significant aggregation representation.

[0038] In the embodiment of the present application, the customer feedback data collection subunit 110 is used to extract the dataset of customer feedback. Among them, the dataset of customer feedback usually contains feedback content information on the specific evaluations of the service by different customers, and these contents are text-based comments, ratings, suggestions, etc. By extracting the dataset of customer feedback and analyzing it, it can help service providers deeply understand the emotional tendencies and needs of customers, so as to achieve more effective satisfaction evaluation and promote the continuous improvement of service quality.

[0039] In the embodiment of the present application, the customer feedback data semantic encoding subunit 120 is configured to perform semantic encoding on each customer feedback in the customer feedback data set to obtain a set of customer feedback semantic encoding feature vectors. Accordingly, considering that each customer feedback in the customer feedback data set covers semantic information of various views and feelings of customers on products or services, and in order to help the model better understand the emotional color behind the text and thus automatically evaluate user satisfaction, in the technical solution of the present application, each customer feedback in the customer feedback data set is semantically encoded to obtain a set of customer feedback semantic encoding feature vectors. In particular, in a specific implementable manner of the embodiment of the present application, a semantic encoder including an embedding layer can be used to perform semantic encoding on each customer feedback in the customer feedback data set, so as to obtain a set of customer feedback semantic encoding feature vectors.

[0040] In the embodiment of the present application, the customer feedback significant aggregation subunit 130 is configured to perform feature distribution field dynamic aggregation on the set of customer feedback semantic encoding feature vectors to obtain a customer feedback significant aggregation representation. Among them, there is a mutual semantic association relationship between the customer feedback semantic encoding feature vectors, and different customer feedback semantic information has different roles and influences on the overall satisfaction evaluation. Based on this, in order to better highlight those features that appear frequently or have a greater impact in customer feedback, so as to more accurately reflect the main concerns and opinions of the customer group and thus improve the accuracy of satisfaction evaluation, in the technical solution of the present application, the set of customer feedback semantic encoding feature vectors is subjected to feature distribution field dynamic aggregation to obtain a customer feedback significant aggregation representation vector as the customer feedback significant aggregation representation.

[0041] Specifically, first, calculate the static energy factor of each customer feedback semantic coding feature vector in the set of customer feedback semantic coding feature vectors to obtain the set of customer feedback semantic static energy factors. Specifically, the static energy factor can be used to quantify the importance of each customer feedback semantic coding feature vector and evaluate its stability in the feature space, indicating the status and influence of this feature vector in the dataset, providing data support for the subsequent selection of the aggregation center. Then, based on the set of customer feedback semantic static energy factors, perform feature significant aggregation of the force field on the set of customer feedback semantic coding feature vectors to obtain the customer feedback significant aggregation representation vector. Among them, each feature vector is like a "particle" in the force field, and their mutual influence includes both their positional relationship in the multi-dimensional space and their inherent attributes (such as the static energy factor), and also takes into account the characteristics of the overall data distribution. This method simulates the concept of the force field in physics, and optimizes the layout of feature vectors in the multi-dimensional space by calculating the attractive and repulsive forces between feature vectors, so as to achieve the effect of significant aggregation. Specifically, select the customer feedback semantic coding feature vector corresponding to the maximum energy factor in the set of customer feedback semantic static energy factors as the initial center vector of customer feedback semantic clustering, so as to be the most representative and influential part in the integration set. Then, calculate the dynamic aggregation energy factor of each customer feedback semantic coding feature vector based on the spatial span and static energy factor between the customer feedback semantic coding feature vector and the center vector. Specifically, this dynamic energy factor not only considers the spatial span, but also considers the importance of the inherent characteristics of each data point to more accurately simulate the interaction between samples, and at the same time provides a flexible and detailed method to evaluate the role and importance of a single sample in the overall dataset. Furthermore, considering that the dynamic aggregation energy factor reflects the relative importance and significant features of each feature vector in the dynamic aggregation process, and in order to further dynamically adjust these energy factors and retain those with higher influence and representativeness, input the set of each dynamic aggregation energy factor into the gated mask unit to convert it into the set of dynamic aggregation weight factors. Finally, use the set of weight factors to perform weighted summation on the set of customer feedback semantic coding feature vectors to obtain the final customer feedback significant aggregation representation vector.

[0042] Specifically, Figure 3 Block diagram of the customer feedback significant aggregation subunit in the numerical control machine tool aftermarket service project management system according to an embodiment of the present application. As Figure 3As shown, the customer feedback significant aggregation subunit 130 includes: a customer feedback semantic static energy factor calculation secondary subunit 131, configured to calculate the static energy factor of each customer feedback semantic coding feature vector in the set of customer feedback semantic coding feature vectors to obtain a set of customer feedback semantic static energy factors; and a customer feedback semantic feature aggregation secondary subunit 132, configured to perform feature significant aggregation based on the force field on the set of customer feedback semantic coding feature vectors based on the set of customer feedback semantic static energy factors to obtain the customer feedback significant aggregation representation.

[0043] More specifically, in the embodiment of the present application, the customer feedback semantic static energy factor calculation secondary subunit is configured to: calculate the mean and variance of the customer feedback semantic coding feature vectors to obtain the customer feedback semantic mean and the customer feedback semantic variance; subtract the customer feedback semantic coding feature vectors from the customer feedback semantic mean by position, and calculate the fourth power of each position of the subtracted feature vectors to obtain a customer feedback semantic difference modulation vector; calculate the expected value of the customer feedback semantic difference modulation vector to obtain the customer feedback semantic expected value; divide the customer feedback semantic expected value by the square of the customer feedback semantic variance, and input the obtained value into the sigmoid function to obtain the customer feedback semantic static energy factor.

[0044] More specifically, Figure 4 is a block diagram of the customer feedback semantic feature aggregation secondary subunit in the numerical control machine tool aftermarket service project management system according to the embodiment of the present application. As Figure 4As shown, the second-level sub-unit 132 for aggregating customer feedback semantic features includes: a third-level sub-unit 1321 for determining the initial center vector of customer feedback semantic clustering, which is used to select the customer feedback semantic coding feature vector corresponding to the largest customer feedback semantic static energy factor in the set of customer feedback semantic static energy factors as the initial center vector of customer feedback semantic clustering; a third-level sub-unit 1322 for calculating the dynamic aggregation energy factors of customer feedback semantics, which is used to calculate the dynamic aggregation energy factors of each customer feedback semantic coding feature vector in the set of customer feedback semantic coding feature vectors based on the spatial span between each customer feedback semantic coding feature vector in the set of customer feedback semantic coding feature vectors and the initial center vector of customer feedback semantic clustering, as well as the static energy factor of each customer feedback semantic coding feature vector and the static energy factor of the initial center vector of customer feedback semantic clustering, to obtain a set of dynamic aggregation energy factors of customer feedback semantics; a third-level sub-unit 1323 for gating the mask of the dynamic aggregation energy factors of customer feedback semantics, which is used to input the set of dynamic aggregation energy factors of customer feedback semantics into a gating mask unit to obtain a set of dynamic aggregation weight factors of customer feedback semantics; and a third-level sub-unit 1324 for generating a significant aggregation representation of customer feedback, which is used to calculate the weighted sum of the set of customer feedback semantic coding feature vectors with the set of dynamic aggregation weight factors of customer feedback semantics to obtain a significant aggregation representation vector of customer feedback as the significant aggregation representation of customer feedback.

[0045] More specifically, in the embodiment of the present application, the third-level sub-unit for calculating the dynamic aggregation energy factors of customer feedback semantics is used to: multiply the static energy factor of the customer feedback semantic coding feature vector, the static energy factor of the initial center vector of customer feedback semantic clustering, and a first weighting parameter to obtain a first dynamic aggregation energy factor of customer feedback semantics; multiply the square of the spatial span between the customer feedback semantic coding feature vector and the initial center vector of customer feedback semantic clustering by a second weighting parameter to obtain a second dynamic aggregation energy factor of customer feedback semantics; and divide the first dynamic aggregation energy factor of customer feedback semantics by the second dynamic aggregation energy factor of customer feedback semantics to obtain the dynamic aggregation energy factor of customer feedback semantics.

[0046] More specifically, Figure 5 is a block diagram of the third-level sub-unit for gating the mask of the dynamic aggregation energy factors of customer feedback semantics in the numerical control machine tool aftermarket service project management system according to the embodiment of the present application. As Figure 5As shown, the three - level sub - unit 1323 of the customer feedback semantic dynamic aggregation energy factor gating mask includes: a four - level sub - unit 13231 of dynamic aggregation energy factor normalization, which is used to normalize the set of customer feedback semantic dynamic aggregation energy factors to obtain a set of normalized customer feedback semantic dynamic aggregation energy factors; and a four - level sub - unit 13232 of normalized dynamic aggregation energy factor masking, which is used to mask the set of normalized customer feedback semantic dynamic aggregation energy factors to obtain the set of customer feedback semantic dynamic aggregation weight factors.

[0047] More specifically, in the embodiment of the present application, the four - level sub - unit of dynamic aggregation energy factor normalization is used to: calculate the exponential function values with the negative numbers of each customer feedback semantic dynamic aggregation energy factor in the set of customer feedback semantic dynamic aggregation energy factors as exponents with the natural constant e as the base to obtain a set of customer feedback semantic dynamic aggregation energy exponential factors; after adding the set of customer feedback semantic dynamic aggregation energy exponential factors and the constant 1 in a position - by - position manner, calculate the reciprocals of each customer feedback semantic dynamic aggregation energy exponential modulation factor in the obtained set of customer feedback semantic dynamic aggregation energy exponential modulation factors to obtain the set of normalized customer feedback semantic dynamic aggregation energy factors.

[0048] More specifically, in the embodiment of the present application, the four - level sub - unit of normalized dynamic aggregation energy factor masking is used to: in response to each normalized customer feedback semantic dynamic aggregation energy factor in the set of normalized customer feedback semantic dynamic aggregation energy factors being greater than a predetermined threshold, set the normalized customer feedback semantic dynamic aggregation energy factor to its original value and set the rest to zero to obtain the set of customer feedback semantic dynamic aggregation weight factors.

[0049] In the embodiment of the present application, specifically, the customer feedback significant aggregation sub - unit is used to: perform feature distribution field - domain dynamic aggregation on the set of customer feedback semantic encoding feature vectors according to the following formula; where the formula is:

[0050]

[0051] where, is the set of customer feedback semantic encoding feature vectors, are respectively the 1st, 2nd,..., the th,..., the th customer feedback semantic encoding feature vectors in the set of customer feedback semantic encoding feature vectors, is the feature value at each position in the th customer feedback semantic encoding feature vector, is the calculated expected value, and The mean and variance of respectively, is a function, is the corresponding semantic static energy factor of customer feedback, To select the value corresponding to the maximum value, is the maximum matching value, is the initial center vector of semantic clustering of customer feedback, is the corresponding semantic static energy factor of customer feedback, represents the spatial span between and are weighting parameters, is the corresponding semantic dynamic aggregation energy factor of customer feedback, is the corresponding normalized semantic dynamic aggregation energy factor of customer feedback, is for masking processing, is a predetermined threshold, is the corresponding semantic dynamic aggregation weight factor of customer feedback, is the number of vectors in the set of the semantic encoding feature vectors of the customer feedback, is the significant aggregation representation vector of the customer feedback.

[0052] In an embodiment of the present application, the satisfaction evaluation result generation subunit 140 is configured to obtain a satisfaction evaluation result based on the significant aggregation representation of the customer feedback. Specifically, in an embodiment of the present application, the satisfaction evaluation result generation subunit is configured to: input the significant aggregation representation vector of the customer feedback into a customer satisfaction evaluation module based on a classifier to obtain the satisfaction evaluation result, and the satisfaction evaluation result is used to indicate that the user satisfaction is positive or the user satisfaction is negative. Specifically, by performing classification processing on the significant aggregation representation of the customer feedback obtained through dynamic aggregation of the set of the semantic encoding feature vectors of the customer feedback, it is possible to automatically evaluate whether the user satisfaction is positive or negative, which can reduce the subjectivity and deviation brought by manual judgment, ensure higher objectivity and consistency in the interpretation and classification of customer feedback. And it can capture the subtle differences in customer feedback, perceive the underlying customer emotions and potential problems, thereby providing a more comprehensive feedback analysis and realizing the automation of customer feedback management.

[0053] In particular, this application takes into account that each customer feedback semantic coding feature vector in the set of customer feedback semantic coding feature vectors represents the text semantic coding features of each customer feedback in the customer feedback dataset. Considering that there are relatively significant content and expression differences among the customer feedbacks in the text source domain of the customer feedback dataset, this results in relatively significant semantic feature expression heterogeneity among the customer feedback semantic coding feature vectors in the set of customer feedback semantic coding feature vectors. This makes the distribution of the semantic space uneven when performing dynamic aggregation of the feature distribution field based on the imitation force field, and the semantic dynamic aggregation representation of the customer feedback significant aggregation representation vector also has semantic representation diversity, thus affecting the iterative consistency of the classification mapping and reducing the accuracy of the classification result.

[0054] Preferably, in an example of this application, inputting the customer feedback significant aggregation representation vector into the customer satisfaction evaluation module based on a classifier to obtain a satisfaction evaluation result includes:

[0055] Determine the customer feedback significant aggregation probability value corresponding to the customer feedback significant aggregation representation vector, where the customer feedback significant aggregation probability value represents the probability that the customer satisfaction is positive;

[0056] Calculate the product of the first customer feedback significant aggregation eigenvalue of the customer feedback significant aggregation representation vector and the customer feedback significant aggregation probability value to obtain the first customer feedback significant aggregation feature probability product;

[0057] Calculate the product of the difference between the second customer feedback significant aggregation eigenvalue of the customer feedback significant aggregation representation vector and one minus the customer feedback significant aggregation probability value to obtain the second customer feedback significant aggregation feature inverse probability product;

[0058] Calculate the quotient of the first customer feedback significant aggregation eigenvalue divided by the difference between one and the customer feedback significant aggregation probability value to obtain the first customer feedback significant aggregation feature inverse probability quotient;

[0059] Calculate the quotient of the second customer feedback significant aggregation eigenvalue and the customer feedback significant aggregation probability value to obtain the second customer feedback significant aggregation feature probability quotient;

[0060] After adding the first customer feedback significant aggregation feature probability product and the second customer feedback significant aggregation feature inverse probability product, subtract the difference between the first customer feedback significant aggregation feature inverse probability quotient and the second customer feedback significant aggregation feature probability quotient to obtain the customer feedback significant aggregation correction eigenvalue;

[0061] For each first customer feedback significantly aggregated eigenvalue and second customer feedback significantly aggregated eigenvalue of the significantly aggregated representation vector of the customer feedback, perform matrix multiplication on the customer feedback significantly aggregated correction feature matrix composed of the customer feedback significantly aggregated correction eigenvalues and the significantly aggregated representation vector of the customer feedback to obtain a corrected significantly aggregated representation vector of the customer feedback; and

[0062] Input the corrected significantly aggregated representation vector of the customer feedback into a customer satisfaction evaluation module based on a classifier to obtain a satisfaction evaluation result.

[0063] Wherein, the significantly aggregated feature vector of the customer feedback The correction process is expressed as:

[0064]

[0065] Wherein, Represents the significantly aggregated representation vector of the customer feedback, Represents the first customer feedback significantly aggregated eigenvalue of the significantly aggregated representation vector of the customer feedback, Represents the second customer feedback significantly aggregated eigenvalue of the significantly aggregated representation vector of the customer feedback, Represents the probability that the customer satisfaction is positive, Represents the customer feedback significantly aggregated correction eigenvalue, Represents the customer feedback significantly aggregated correction feature matrix composed of the customer feedback significantly aggregated correction eigenvalues, Represents matrix multiplication, Represents the corrected significantly aggregated representation vector of the customer feedback.

[0066] Therefore, for the region-boundary integral relationship of the high-dimensional feature manifold of the significantly aggregated representation vector of the customer feedback in this application, by defining the probability distribution of the overall feature set of the significantly aggregated representation vector of the customer feedback as the manifold constraint boundary, it approximates the simply connected region representation composed of eigenvalue pairs of the high-dimensional manifold of the feature set of the significantly aggregated representation vector of the customer feedback, so as to avoid the mapping ambiguity of the diverse feature representations of the significantly aggregated representation vector of the customer feedback to the local manifold representation in the high-dimensional feature class convergence space, improve the execution iteration consistency of each local feature distribution in the mapping task, improve the feature classification convergence effect, and improve the accuracy of the satisfaction evaluation result obtained by the significantly aggregated representation vector of the customer feedback through the customer satisfaction evaluation module based on a classifier. In this way, it can reduce the subjectivity and bias brought by manual judgment, ensure higher objectivity and consistency in the interpretation and classification of customer feedback. And it can capture the subtle differences in customer feedback, perceive the underlying customer emotions and potential problems, thereby providing a more comprehensive feedback analysis and realizing the automation of customer feedback management.

[0067] In summary, the after-sales market service project management system for CNC machine tools according to the embodiments of the present application is elucidated. It mainly divides service project management into pre-sales management, in-sales management, and after-sales management. In the customer feedback management of after-sales management, by extracting the data set of customer feedback and using a data processing algorithm based on deep learning to perform semantic understanding of the customer feedback, so as to automatically evaluate that the user satisfaction is positive or the user satisfaction is negative according to the significant dynamic aggregation representation of the distribution field between the semantic features of each customer feedback, it can ensure that the interpretation and classification of customer feedback have higher objectivity and consistency. And it can capture the subtle differences in customer feedback, perceive the underlying customer emotions and potential problems, thus providing a more comprehensive feedback analysis.

[0068] As described above, the after-sales market service project management system for CNC machine tools according to the embodiments of the present application can be implemented in various terminal devices, such as a server for after-sales market service project management of CNC machine tools. In one example, the after-sales market service project management system for CNC machine tools according to the embodiments of the present application can be integrated into the terminal device as a software module and / or a hardware module. For example, the after-sales market service project management system for CNC machine tools can be a software module in the operating system of the terminal device, or can be an application program developed for the terminal device; of course, the after-sales market service project management system for CNC machine tools can also be one of the many hardware modules of the terminal device.

[0069] Alternatively, in another example, the after-sales market service project management system for CNC machine tools and the terminal device can also be separate devices, and the after-sales market service project management system for CNC machine tools can be connected to the terminal device through a wired and / or wireless network and transmit interaction information in accordance with a pre-agreed data format.

[0070] Figure 6 It is a flowchart of the after-sales market service project management method for CNC machine tools according to the embodiments of the present application. As Figure 6 shown, in the after-sales market service project management method for CNC machine tools, it includes: pre-sales management steps: recording the basic information and requirement descriptions of customers; providing technical support and consulting services for customers; providing a customized solution based on the requirement descriptions of the customers; determining the estimated cost and generating a quotation based on the customized solution; in-sales management steps: managing the creation and approval process of sales contracts; allocating appropriate technical personnel and resources according to project requirements; monitoring the project progress in real time; after-sales management steps: recording and classifying the after-sales service requests of customers, tracking the processing status; managing the repair process; collecting customer feedback and analyzing customer satisfaction; formulating and implementing a regular maintenance plan.

[0071] Among them, the specific operations of each step in the above-mentioned after-sales market service project management method for numerical control machine tools have been described in detail in the description of the after-sales market service project management system of the numerical control machine tools with reference to Figures 1 to 5 and thus, the repeated description thereof will be omitted.

[0072] In summary, the after-sales market service project management method based on the embodiments of the present application is clarified. It mainly divides service project management into pre-sales management, in-sales management, and after-sales management. In the customer feedback management of after-sales management, by extracting the data set of customer feedback and using a data processing algorithm based on deep learning to perform semantic understanding of the customer feedback, so as to automatically evaluate whether the user satisfaction is positive or negative according to the significant dynamic aggregation representation of the distribution field among the semantic features of each customer feedback, it can ensure that the interpretation and classification of customer feedback have higher objectivity and consistency. And it can capture the subtle differences in customer feedback, perceive the underlying customer emotions and potential problems, so as to provide a more comprehensive feedback analysis.

[0073] The above is only a preferred embodiment of the present application and does not impose any form of limitation on the present application. Although the present application has been disclosed above with a preferred embodiment, it is not intended to limit the present application. Any person skilled in the art can make some changes or modifications to the equivalent embodiments by using the above-disclosed technical content without departing from the technical solution of the present application. However, as long as it does not depart from the technical solution of the present application, any simple modification, equivalent change, and modification made to the above embodiments according to the technical essence of the present application still fall within the scope of the technical solution of the present application.

Claims

1. A management system for the after-market service project of a numerically controlled machine tool, characterized in that, Including: A pre-sales management module, a sales management module, and an after-sales management module; among them, the after-sales management module includes a service request management unit, a repair management unit, a customer feedback management unit, and a maintenance plan unit. The service request management unit is used to record and classify customers' after-sales service requests and track the processing status; the repair management unit is used to manage the repair process; the customer feedback management unit is used to collect customer feedback and analyze customer satisfaction; the maintenance plan unit is used to formulate and execute regular maintenance plans; Among them, the customer feedback management unit includes: A customer feedback data collection sub-unit, which is used to extract the data set of customer feedback; A customer feedback data semantic encoding sub-unit, which is used to perform semantic encoding on each customer feedback in the data set of customer feedback to obtain a set of customer feedback semantic encoding feature vectors; A customer feedback significant aggregation sub-unit, which is used to perform feature distribution field dynamic aggregation on the set of customer feedback semantic encoding feature vectors to obtain a customer feedback significant aggregation representation; among them, the customer feedback significant aggregation sub-unit includes: a customer feedback semantic static energy factor calculation secondary sub-unit, which is used to calculate the static energy factor of each customer feedback semantic encoding feature vector in the set of customer feedback semantic encoding feature vectors to obtain a set of customer feedback semantic static energy factors. Specifically: calculate the mean and variance of the customer feedback semantic encoding feature vectors to obtain the customer feedback semantic mean and the customer feedback semantic variance; subtract the customer feedback semantic encoding feature vectors from the customer feedback semantic mean in a position-by-position manner, and calculate the fourth power of each position of the subtracted feature vectors to obtain a customer feedback semantic difference modulation vector; calculate the expected value of the customer feedback semantic difference modulation vector to obtain a customer feedback semantic expected value; divide the customer feedback semantic expected value by the square of the customer feedback semantic variance, and input the obtained value into the sigmoid function to obtain the customer feedback semantic static energy factor; A customer feedback semantic feature aggregation secondary sub-unit, which is used to perform feature significant aggregation based on the force field on the set of customer feedback semantic encoding feature vectors based on the set of customer feedback semantic static energy factors to obtain the customer feedback significant aggregation representation; The customer feedback semantic feature aggregation secondary sub-unit includes: A customer feedback semantic clustering initial center vector determination tertiary sub-unit, which is used to select the customer feedback semantic encoding feature vector corresponding to the largest customer feedback semantic static energy factor in the set of customer feedback semantic static energy factors as the customer feedback semantic clustering initial center vector; The customer feedback semantic dynamic aggregation energy factor calculation three - level subunit is used to calculate the dynamic aggregation energy factor of each customer feedback semantic coding feature vector in the set of customer feedback semantic coding feature vectors based on the spatial span between each customer feedback semantic coding feature vector in the set of customer feedback semantic coding feature vectors and the initial center vector of customer feedback semantic clustering, as well as the static energy factor of each customer feedback semantic coding feature vector and the static energy factor of the initial center vector of customer feedback semantic clustering, so as to obtain a set of customer feedback semantic dynamic aggregation energy factors; The customer feedback semantic dynamic aggregation energy factor gating mask three - level subunit is used to input the set of customer feedback semantic dynamic aggregation energy factors into a gating mask unit to obtain a set of customer feedback semantic dynamic aggregation weight factors; The customer feedback significant aggregation representation generation three - level subunit is used to calculate the weighted sum of the set of customer feedback semantic coding feature vectors with the set of customer feedback semantic dynamic aggregation weight factors to obtain a customer feedback significant aggregation representation vector as the customer feedback significant aggregation representation; The satisfaction evaluation result generation subunit is used to obtain a satisfaction evaluation result based on the customer feedback significant aggregation representation.

2. The after-market service project management system for CNC machine tools according to claim 1, characterized in that The pre - sales management module includes a customer demand collection unit, a technical consultation and support unit, a solution design unit, and an estimated quotation unit. The customer demand collection unit is used to record the basic information and demand description of the customer; the technical consultation and support unit is used to provide technical support and consultation services for the customer; The solution design unit is used to provide a customized solution based on the demand description of the customer; the estimated quotation unit is used to determine the estimated cost and generate a quotation based on the customized solution; The in - sales management module includes a contract signing unit, a project allocation unit, and a progress tracking unit. The contract signing unit is used to manage the creation and approval process of sales contracts; the project allocation unit is used to allocate appropriate technical personnel and resources according to project requirements; the progress tracking unit is used to monitor the project progress in real time.

3. The after-sales market service project management system for CNC machine tools according to claim 2, wherein The customer feedback semantic dynamic aggregation energy factor calculation three - level subunit is used for: Multiplying the static energy factor of the customer feedback semantic coding feature vector, the static energy factor of the initial center vector of customer feedback semantic clustering, and a first weighting parameter to obtain a first customer feedback semantic dynamic aggregation energy factor; Multiplying the square of the spatial span between the customer feedback semantic coding feature vector and the initial center vector of customer feedback semantic clustering and a second weighting parameter to obtain a second customer feedback semantic dynamic aggregation energy factor; Dividing the first customer feedback semantic dynamic aggregation energy factor by the second customer feedback semantic dynamic aggregation energy factor to obtain the customer feedback semantic dynamic aggregation energy factor.

4. The after-market service project management system for CNC machine tools according to claim 3, characterized in that The customer feedback semantic dynamic aggregation energy factor gating mask three - level subunit includes: Dynamic Aggregation Energy Factor Normalization Four - level Sub - unit, which is used to normalize the set of customer feedback semantic dynamic aggregation energy factors to obtain a set of normalized customer feedback semantic dynamic aggregation energy factors; Normalized Dynamic Aggregation Energy Factor Masking Four - level Sub - unit, which is used to mask the set of normalized customer feedback semantic dynamic aggregation energy factors to obtain the set of customer feedback semantic dynamic aggregation weight factors.

5. The after-market service project management system for CNC machine tools according to claim 4, characterized in that The Dynamic Aggregation Energy Factor Normalization Four - level Sub - unit is used for: Calculating the exponential function values with the negative numbers of each customer feedback semantic dynamic aggregation energy factor in the set of customer feedback semantic dynamic aggregation energy factors as exponents with the natural constant e as the base to obtain a set of customer feedback semantic dynamic aggregation energy exponential factors; After adding the set of customer feedback semantic dynamic aggregation energy exponential factors and the constant one in a position - by - position manner, calculating the reciprocals of each customer feedback semantic dynamic aggregation energy exponential modulation factor in the obtained set of customer feedback semantic dynamic aggregation energy exponential modulation factors to obtain the set of normalized customer feedback semantic dynamic aggregation energy factors.

6. The after-sales market service project management system for numerically controlled machine tools according to claim 5, wherein The Normalized Dynamic Aggregation Energy Factor Masking Four - level Sub - unit is used for: in response to each normalized customer feedback semantic dynamic aggregation energy factor in the set of normalized customer feedback semantic dynamic aggregation energy factors being greater than a predetermined threshold, setting the normalized customer feedback semantic dynamic aggregation energy factor to its original value and setting the rest to zero to obtain the set of customer feedback semantic dynamic aggregation weight factors.

7. The after-market service project management system for numerically controlled machine tools according to claim 6, characterized in that, The Satisfaction Evaluation Result Generation Sub - unit is used for: inputting the customer feedback significant aggregation representation vector into a customer satisfaction evaluation module based on a classifier to obtain the satisfaction evaluation result, and the satisfaction evaluation result is used to indicate that the user satisfaction is positive or the user satisfaction is negative.

8. A management method for after-market service projects of numerical control machine tools, the management method being applied to the management system as described in claim 7, characterized in that, Including: Pre - sales management steps: Recording the basic information and requirement descriptions of customers; Providing technical support and consulting services for customers; Providing customized solutions based on the requirement descriptions of customers; Determining the estimated cost and generating a quotation based on the customized solution; During - sales management steps: Managing the creation and approval process of sales contracts; Allocating appropriate technical personnel and resources according to project requirements; Monitoring the project progress in real - time; After - sales management steps: Recording and classifying customers' after - sales service requests and tracking the processing status; Managing the repair process; Collecting customer feedback and analyzing customer satisfaction; Formulating and implementing a regular maintenance plan.

Images