CN114238615B - Enterprise service result data processing method and system - Google Patents
Enterprise service result data processing method and system Download PDFInfo
- Publication number
- CN114238615B CN114238615B CN202111523184.6A CN202111523184A CN114238615B CN 114238615 B CN114238615 B CN 114238615B CN 202111523184 A CN202111523184 A CN 202111523184A CN 114238615 B CN114238615 B CN 114238615B
- Authority
- CN
- China
- Prior art keywords
- service
- information
- enterprise
- customer
- achievement
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Databases & Information Systems (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a method and a system for processing enterprise service result data, wherein the method comprises the following steps: obtaining first enterprise information; obtaining first enterprise historical service achievement information; constructing a first enterprise service convergence database based on the first enterprise historical service achievement information, wherein the first enterprise service convergence database comprises a plurality of service achievement categories; obtaining first customer portrait information; classifying the first customer portrait information based on a first classification rule to obtain first customer service achievement requirement information; comparing the first customer service achievement requirement information in an enterprise service fusion database based on a second classification rule to obtain a first customer service type, wherein the first customer service type is one of multiple service achievement categories; a first customer is serviced in a first customer service type.
Description
Technical Field
The invention relates to the technical field of enterprise data processing, in particular to a method and a system for processing enterprise service result data.
Background
The service industry is the third industry of the three major industries, and the service industry includes a consultation industry for providing enterprise or personal problem solutions, and plans a proper problem solution through client information, including legal consultation, property management consultation, financial consultation and the like.
Enterprises in the consulting industry generally train and learn employees according to excellent results of the completed consulting service plan and provide better service plans for new clients as experiences.
In the process of implementing the technical scheme of the invention in the application, the technical problems that the technology at least has the following technical problems are found:
in the prior art, completed excellent consultation service scheme achievements are mainly learned as experience cases, a new client needs to re-establish a service scheme, all enterprise service achievements cannot be efficiently managed and utilized, the service scheme of the new client cannot be established according to historical service achievements, and the technical problem of low service achievement data utilization efficiency exists.
Disclosure of Invention
The application provides an enterprise service achievement data processing method and system, which are used for solving the technical problems that all enterprise service achievements cannot be efficiently managed and utilized and the utilization efficiency of service achievement data is low in the prior art.
In view of the foregoing problems, the present application provides a method and a system for processing enterprise service result data.
In a first aspect of the present application, a method for processing enterprise service achievement data is provided, the method includes: obtaining first enterprise information; obtaining the first enterprise historical service achievement information; constructing a first enterprise service convergence database based on the first enterprise historical service achievement information, wherein the first enterprise service convergence database comprises a plurality of service achievement categories; obtaining first customer portrait information; classifying the first customer portrait information based on a first classification rule to obtain first customer service achievement requirement information; comparing first customer service achievement demand information in the first enterprise service fusion database based on a second classification rule to obtain a first customer service type, wherein the first customer service type is one of the multiple service achievement categories; servicing the first customer with the first customer service type.
In a second aspect of the application, an enterprise service achievement data processing system is provided, the system comprising: a first obtaining unit, configured to obtain first enterprise information; a second obtaining unit, configured to obtain the first enterprise historical service achievement information; the first construction unit is used for constructing a first enterprise service convergence database based on the first enterprise historical service achievement information, wherein the first enterprise service convergence database comprises a plurality of service achievement categories; a third obtaining unit for obtaining first client representation information; the first processing unit is used for classifying the first customer portrait information based on a first classification rule to obtain first customer service achievement requirement information; the second processing unit is used for comparing first customer service achievement demand information in the first enterprise service convergence database based on a second classification rule to obtain a first customer service type, wherein the first customer service type is one of the multiple service achievement categories; a third processing unit to service the first customer with the first customer service type.
In a third aspect of the present application, an enterprise service achievement data processing system is provided, including: a processor coupled to a memory for storing a program that, when executed by the processor, causes a system to perform the steps of the method according to the first aspect.
In a fourth aspect of the present application, a computer-readable storage medium is provided, on which a computer program is stored, which computer program, when being executed by a processor, carries out the steps of the method according to the first aspect.
One or more technical solutions provided in the present application have at least the following technical effects or advantages:
according to the method and the system, historical service achievement information of the enterprise is obtained according to enterprise information, then an enterprise service fusion database is built based on the historical service achievement information, when a service scheme needs to be formulated for a new client, portrait information of the new client is obtained, the portrait information is classified, service achievement requirement information of the new client is obtained, then classification comparison is carried out in the enterprise service fusion database according to the service achievement requirement information, the service type of the new client is obtained, and then the new client is served according to the historical service achievement. According to the method, the historical service achievement information of the enterprise is collected, the enterprise service fusion database is constructed, effective management of the historical service achievement information of the enterprise is achieved, the historical achievement information can be called when the historical achievement information is used as an enterprise historical case, two classification rules are established, service requirements needed by customers are obtained by classifying according to customer images, then service schemes in historical service achievement categories are recommended by classifying according to the service requirements, the utilization rate of the historical service achievement data can be provided, the service schemes are recommended according to customer intelligence, the intelligence and accuracy of service scheme formulation are improved, the efficiency of service scheme formulation is improved, and the technical effects of providing the service enterprise historical service achievement data utilization rate and the new service scheme formulation accuracy are achieved.
The above description is only an overview of the technical solutions of the present application, and the present application may be implemented in accordance with the content of the description so as to make the technical means of the present application more clearly understood, and the detailed description of the present application will be given below in order to make the above and other objects, features, and advantages of the present application more clearly understood.
Drawings
FIG. 1 is a schematic flow chart of a method for processing enterprise service result data provided by the present application;
FIG. 2 is a schematic flow chart illustrating a first classification rule in an enterprise service achievement data processing method provided by the present application;
FIG. 3 is a schematic flow chart illustrating a second classification rule in the data processing method for enterprise service achievements provided by the present application;
FIG. 4 is a block diagram of an enterprise service result data processing system according to the present application;
fig. 5 is a schematic structural diagram of an exemplary electronic device of the present application.
In the figure: 11. a first obtaining unit; 12. a second obtaining unit; 13. a first building element; 14. a third obtaining unit; 15. a first processing unit; 16. a second processing unit; 17. a third processing unit; 300. an electronic device; 301. a memory; 302. a processor; 303. a communication interface; 304. a bus architecture.
Detailed Description
The application provides an enterprise service achievement data processing method and system, which are used for solving the technical problems that in the prior art, all enterprise service achievements cannot be efficiently managed and utilized, a service scheme of a new client cannot be made according to historical service achievements, and the utilization efficiency of service achievement data is low.
The service industry, the agriculture industry and the manufacturing industry form three major industries, and along with the development of economy, the service industry becomes the most important industry in economic production in modern society. Besides the business of providing actual material services, the service industry also includes consulting business for providing problem solutions for enterprises or individuals, and the consulting business specifically includes legal consulting, property management consulting, financial consulting and the like. After the consulting industry provides service solutions for clients, the excellent and effective solutions can be stored as excellent service result cases, staff training and repeated learning are conducted, and the excellent service solutions are used as experiences to provide better service solutions for new clients. For general solutions, enterprises do not save, but actually, general solutions have some excellent points for learning and serving as the basis of new service solutions. In the prior art, completed excellent consulting service scheme achievements are mainly learned as experience cases, a new client needs to make a service scheme again, the enterprise service achievements cannot be efficiently managed and utilized, the service scheme of the new client cannot be made according to historical service achievements, and the technical problem of low service achievement data utilization efficiency exists.
In view of the above technical problems, the technical solution provided by the present application has the following general idea:
obtaining first enterprise information; obtaining the first enterprise historical service achievement information; constructing a first enterprise service convergence database based on the first enterprise historical service achievement information, wherein the first enterprise service convergence database comprises a plurality of service achievement categories; obtaining first customer portrait information; classifying the first customer portrait information based on a first classification rule to obtain first customer service achievement requirement information; comparing first customer service achievement requirement information in the first enterprise service fusion database based on a second classification rule to obtain a first customer service type, wherein the first customer service type is one of the multiple service achievement categories; servicing the first customer with the first customer service type.
Having described the basic principles of the present application, the technical solutions in the present application will be described clearly and completely with reference to the accompanying drawings, and it should be understood that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments of the present application, and the present application is not limited to the exemplary embodiments described herein. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present application without making any creative effort, shall fall within the protection scope of the present application. It should be further noted that, for the convenience of description, only some but not all of the relevant portions of the present application are shown in the drawings.
Example one
As shown in fig. 1, the present application provides a method for processing enterprise service achievement data, where the method includes:
s100: obtaining first enterprise information;
s200: obtaining the first enterprise historical service achievement information;
specifically, the first enterprise is any enterprise engaged in the service industry in the prior art, preferably any enterprise engaged in the consulting service, and the first enterprise can specify the customer requirements according to the customer consultation problem, make a problem solution as a customer solution, and after the solution is completed, the solution is the service achievement of the first enterprise. Illustratively, the first enterprise may be a law-counseling enterprise, a financial management-counseling enterprise, a property management-counseling enterprise, or the like, and is further preferably a law-counseling enterprise.
After the first enterprise provides the service scheme for the customer service, the service scheme is used as a service result to perform data processing and storage, and historical service result information of the first enterprise is obtained. And obtaining the historical service achievement information of the first enterprise by calling the historical service achievement information.
S300: constructing a first enterprise service convergence database based on the first enterprise historical service achievement information, wherein the first enterprise service convergence database comprises a plurality of service achievement categories;
specifically, in the process of storing the historical service achievement information of the first enterprise, the historical service achievement information of the first enterprise is adopted to construct a first enterprise service fusion database so as to call the historical service achievement information in the first enterprise later.
In the process of storing the first enterprise historical service achievement information, the first enterprise historical service achievement information can be classified from multiple dimensions and then stored by adopting a database, and the efficiency of calling the first enterprise historical service achievement information is improved.
Step S300 in the method provided by the present application includes:
s310: obtaining M types of service information based on the first enterprise historical service achievement information, wherein M is a positive integer;
s320: obtaining an M-type service information interval based on the M-type service information;
s330: based on the M types of service information intervals, screening and obtaining service information intervals meeting preset conditions, and obtaining M screened enterprise service information intervals;
s340: and constructing the first enterprise service convergence database based on the M screening enterprise service information intervals.
Specifically, as mentioned above, the first enterprise historical service achievement information includes a plurality of pieces of information in service plans historically provided for the client, each service plan includes a plurality of different types of information therein, and each service plan includes: client object, service content, service efficiency, service flow, service effect evaluation and the like. The first enterprise is preferably a law consulting enterprise, and each historical service scenario of the first enterprise may include: consulting legal fields (such as marital law, labor law, real estate law and other fields), legal service contents (consulting analysis service, legal document service, arbitration service and the like), service efficiency, service effect evaluation and other information.
Based on the first enterprise historical service achievement information, obtaining M types of service information, wherein M is a positive integer, and the M types of service information comprise various types of information such as the client object, the service content, the service efficiency, the service flow, the service effect evaluation and the like in each historical service scheme. Based on the M-type service information, an M-type service information interval is obtained. The service information intervals correspond to the service information one by one, and the service information intervals refer to value range intervals which can be reached by the service information in a plurality of service schemes. For example, for the service efficiency class service information, the corresponding service information interval may be [1,10], where 1 represents that the service efficiency is very slow, and 10 represents that the service efficiency is very fast. For the customer object class service information, the values in the corresponding service information interval may refer to different customer objects or different fields, for example, a real estate law field or a labor law field.
And screening and obtaining service information intervals meeting preset conditions based on the M types of service information intervals, obtaining M screened enterprise service information intervals, and specifically screening the value range of the M types of service information intervals to remove part of poor service information data. Illustratively, the service information interval of the service efficiency class service information may be [1,10], in order to screen and remove service information with extremely low service efficiency, and avoid obtaining service information with extremely low service efficiency when calling historical service achievement information, which affects learning historical cases and the effect of service scheme planning according to historical service achievements, the service efficiency service information interval [1,10] is screened, the screened enterprise service information interval obtained after screening is [3,10], and parts of [1,3) are screened and removed. And for the service information of the client object and the service content class, the corresponding service information interval does not comprise better data and worse data, and the service information interval is not screened, so that the preset condition for screening the service information interval is obtained, and the service information interval is screened.
Further, according to M screened enterprise service information intervals obtained through screening, partial inferior service information is screened and removed, a first enterprise service fusion database is built on the basis, M types of enterprise service information in the M screened enterprise service information intervals are combined with data in each type of enterprise service information to obtain new historical service scheme information, the first enterprise service fusion database is built, the database is used for storing, and SQL sentences are built for inquiring historical service results.
The built first enterprise service fusion database comprises a plurality of historical service schemes to form a plurality of service achievement categories, illustratively, the plurality of service achievement categories comprise categories with high service rate, less service content and common service effect, categories with low service rate, high service price, complex service content and good service effect, and the like, and the historical service achievements can be recommended and customized according to the requirements of new customers when the service schemes are formulated for the new customers.
According to the method and the system, historical service achievement information data are divided, data in each historical service scheme are classified into M-type service information data, intervals of the M-type service information data are screened according to business requirements, inferior service information data are removed, new service scheme data are formed, a first enterprise service fusion database is built, service scheme data in the first enterprise service fusion database can be called according to information and requirements of new customers, service schemes are recommended for the new customers, service efficiency is improved, poor service information data can be prevented from being called, and service effects are improved.
S400: obtaining first customer portrait information;
step S400 in the method provided by the present application includes:
s410: performing dimension reduction processing on the first enterprise historical service result information;
s420: classifying the first enterprise historical service result information after dimension reduction according to the types of clients to obtain multi-family client information;
s430: obtaining first customer information;
s440: mapping and matching the first customer information in the multi-family customer information to obtain first family customer information;
s450: based on the first family client information, first client representation information is obtained.
Specifically, a first client representation is representation information of a new client for which a first enterprise currently needs to service to provide a problem solution, a representation refers to a tagging of a type of client data, the first client representation information includes various data involved in a consultation service process for a client group to which the new client belongs, and exemplarily includes: client type, client budget, client size, client realm, client requirements, etc., client type may be a private or business client, client realm may be a real estate enterprise or personal owner, etc., client requirements may be a consultation of legal issues or draft legal documents, etc.
In order to construct various kinds of customer portrait information, service object information and corresponding service scheme information in first enterprise historical service achievement information need to be adopted for construction, and problems of overlarge data volume and dimension breakdown may occur in the process of constructing basic customer portrait information by data in the first enterprise historical service achievement information, so that dimension reduction needs to be performed on the first enterprise historical service achievement information.
Preferably, in the present application, a principal component analysis method is used to perform dimension reduction processing on the first enterprise historical service achievement information, and first, data in the first enterprise historical service achievement information is subjected to numerical processing, then, the numerical characteristic data is subjected to centralized processing, for example, the service object characteristic data is averaged, then, for all service object characteristic data samples, the average value is subtracted to obtain a new characteristic value, and all characteristic data are processed to form new first enterprise historical service achievement information. And calculating the new first enterprise historical service result information into a data matrix by adopting a covariance formula to obtain a covariance matrix, and then calculating an eigenvector corresponding to each eigenvalue in the covariance matrix through matrix operation. And selecting a plurality of maximum characteristic values and corresponding characteristic vectors from the characteristic value data and the corresponding characteristic vectors, projecting the original numerical characteristic data of the first enterprise historical service result information onto the selected characteristic vectors, and finishing the dimension reduction processing.
According to the method and the device, the dimension reduction processing is carried out on the first enterprise historical service achievement information, the number dimension in the processed first enterprise historical service achievement information is small, the subsequent calculation efficiency can be improved, the characteristics of data in the original first enterprise historical service achievement information can be guaranteed to the maximum extent, and the accuracy of customer portrait establishment is not affected.
And for the first enterprise historical service achievement information after dimensionality reduction, obtaining a plurality of historical service scheme information in the first enterprise historical service achievement information, further obtaining service object information in the first enterprise historical service achievement information, dividing and classifying the plurality of service scheme information according to the client type of the service object, and obtaining a plurality of groups of client information. Each family of customer information within the plurality of sets of customer information represents a class of customers. Illustratively, a certain family of customer information within the plurality of groups of customer information includes information such as private, high budget, personal owner, and real estate legal domain legal issue consultations, from which all service plan information made by the first enterprise for that type of customer is available.
After obtaining the multi-family customer information, obtaining new customer information which needs to be served currently, then mapping and matching the new customer information in the multi-family customer information to obtain first family customer information, using the family customer information as first customer portrait information of the first customer to complete construction of customer portrait, and enabling the first customer to be capable of using the family customer information.
According to the method and the system, the client portrait information is constructed through the historical service information data, the service scheme recommendation can be provided for the client according to the client data label, and the service scheme formulation efficiency and recommendation accuracy can be improved.
S500: classifying the first customer portrait information based on a first classification rule to obtain first customer service achievement requirement information;
as shown in fig. 2, step S500 in the method provided by the present application includes:
s510: constructing and training to obtain a classified forest model;
s520: inputting the first customer portrait information into the classified forest model to obtain a plurality of output results;
s530: obtaining a first output result based on the plurality of output results, wherein the first output result is an output result with the highest occurrence probability;
s540: and using the first output result as the first customer service result requirement information.
Wherein, step S510 includes:
s511: obtaining a historical service achievement information set;
s512: constructing the classified forest model, wherein the classified forest model comprises X classified trees, and X is a positive integer;
s513: randomly selecting N pieces of service achievement information in the historical service achievement information set in a putting-back mode, wherein N is a positive integer;
s514: obtaining a first data set in the N pieces of service result information, and training a classification root node;
s515: obtaining a second data set in the N pieces of service result information, and training classification branch nodes until a first classification tree is trained;
s516: and randomly selecting N pieces of service result information in the historical service result information set in a back-to-back mode, training a second classification tree until the X classification tree is trained, and obtaining the classification forest model.
Specifically, after obtaining the first client representation information, since the range of the data tag in the first client representation information is still large, it is known from the first client representation information that the first user needs to consult the legal aspects of the real estate, for example, but does not know which kind of legal issues need to consult the legal fields of the real estate, and therefore, the first client representation information needs to be further classified.
In the application, a classification forest model is adopted to classify the first user portrait, and firstly, the classification forest model needs to be constructed and trained to obtain. Firstly, a historical service achievement information set is obtained, the historical service achievement information set is a set of all historical service information in a plurality of consulting service companies in the same industry field as a first enterprise, the service information in the historical service achievement information set is the same as the service information in the historical service achievement information of the first enterprise in type, the historical service achievement information set can be obtained through federal learning, the historical service information of all the companies is encrypted, obtained and used, and data volume is improved.
Firstly, a classification forest model is constructed, wherein the classification forest model comprises X classification trees, X is a positive integer, each classification tree comprises a classification root node, a classification branch node and a classification leaf node, and the number of the classification branch nodes and the number of the classification leaf nodes can be multiple. Each classification branch node and each classification leaf node respectively comprise a classification characteristic, and a part of data can be classified twice and finally classified into a final category.
After the classification forest model is built, service information data in the historical service result information set can be selected as training data to train the classification forest model, specifically, classification trees in the classification forest model are trained one by one, and training of the classification forest model is finally completed. Firstly, N pieces of service achievement information in the historical service achievement information set are selected randomly in a put-back mode, wherein N is a positive integer and is smaller than the number of the service achievement information in the randomly selected historical service achievement information set, and therefore not all the service achievement information in the historical service achievement information set is selected to conduct training of a single classification tree.
Obtaining a first data set in the N pieces of service achievement information, first, calculating an information entropy of the first data set to determine whether the first data set can classify all the N pieces of service achievement information, which is calculated by an information entropy calculation formula, as follows:
wherein t represents a random variable, and corresponds to a set of all possible outputs, which is defined as a symbol set, the output of the random variable is represented by t, p (i-t) represents an output probability function, and the larger the uncertainty of the variable is, the larger the entropy is. The smaller the information entropy is, the better the corresponding data set can classify all the service achievement information. And calculating the information entropies of all data sets in the N pieces of service result information, sequencing the data sets from small to large according to the information entropies, and then training the root nodes to the leaf nodes of the classification tree in sequence.
A classification root node of a first classification tree is trained using a first data set. Illustratively, the classification root node is: the client type is a private client or an enterprise client, the first data set comprises information of service objects in the N pieces of service achievement information, and the N pieces of service achievement information can be classified twice according to the classification root node.
Then, a second data set in the N pieces of service achievement information is obtained, the information entropy of the second data set is larger than that of the first data set, the second data set is used as training data to train classification branch nodes of the first classification tree, and the two pieces of service achievement information classified by the classification root nodes can be further classified according to the classification branch nodes.
And repeating the steps, and training the root node of the first classification tree to the final leaf node by adopting a plurality of groups of data sets in the N pieces of service result information until the N pieces of service result information are classified to a preset requirement or cannot be classified continuously, thereby finishing the training of the first classification tree. After the training is finished, the first customer portrait information can be input into a root node of the first classification tree, the first portrait information is classified according to customer service requirement information included in the first portrait information, and finally a customer service achievement requirement corresponding to the first portrait information is obtained.
However, the classification result of one classification tree may be inaccurate, and therefore, the classification forest model is adopted to construct a plurality of classification trees. Furthermore, N pieces of service result information are randomly selected from the historical service result information set in a replacement mode, the N pieces of service result information randomly selected for the second time are possibly the same as N pieces of service result information of the first classification tree for the first time, possibly partially the same and completely random, and the purpose of training each classification tree by the random service result information of the historical service result information set is achieved.
And (4) training root nodes, branch nodes and leaf nodes of the second classification tree by adopting the N service result information selected for the second time, and finishing the training of the second classification tree. And then, randomly selecting N pieces of service result information from the historical service result information set again to train a third classification tree until the training reaches the X classification tree, and finishing the training of the classification forest model.
After training of the classified forest model is completed, the first customer portrait information is classified into the forest model, namely X classification trees are input simultaneously, and the training data in each classification tree are completely random, so that the output results of the classification trees are not completely the same, and X output results can be obtained, but the training data of the classification trees are all selected from the same database, namely a historical service result information set, and a value N which is more than half of the value of the quantity of the service result information in the historical service result information set can be set, preferably 2/3 of the value of the quantity of the service result information in the historical service result information set, so that a certain intersection exists between the training data of the classification trees. Therefore, the output results of most classification trees are the same or similar, an output result with the highest occurrence probability in the X output results is obtained as a first data result, and the first output result is used as the first customer service result requirement information, namely, the service result requirement information of the first customer is obtained according to the first customer portrait information classification.
The method and the device have the advantages that massive historical service result information is collected, training of the classified forest model is carried out, the classified forest model can process high-dimensional data samples without dimension reduction, the classified forest model comprises a plurality of classified trees, the output result with the highest probability is obtained according to the output results, the classification accuracy is high, the portrait information of a first customer can be accurately classified according to the historical service result information, the first service result information which is most possibly needed for serving the first customer is obtained, calling and reference of the historical service result information of a first enterprise are carried out based on the first service result information, and the technical effect of improving the management efficiency of the historical service result information is achieved.
S600: comparing first customer service achievement demand information in the first enterprise service fusion database based on a second classification rule to obtain a first customer service type, wherein the first customer service type is one of the multiple service achievement categories;
as shown in fig. 3, step S600 in the method provided by the present application includes:
s610: preprocessing the first customer service achievement requirement information to obtain first customer service requirement text information;
s620: constructing a second classification rule classifier;
s630: performing word segmentation on the first customer service requirement text information to obtain first customer service requirement characteristics;
s640: and inputting the first customer service requirement characteristic into the second classification rule classifier to obtain the first customer service type.
Wherein, step S620 includes:
s621: obtaining a plurality of service achievement categories as classification labels based on the first enterprise service fusion database;
s622: obtaining a plurality of first enterprise service achievement information based on the first enterprise service convergence database, wherein each first enterprise service achievement information comprises a plurality of service requirement characteristics;
s623: and calculating the probability that the first enterprise service achievement information containing different service requirement characteristics is classified into a certain classification label to obtain the second classification rule classifier.
Specifically, the first customer service achievement requirement information obtained after being classified by the first classification rule is requirement information of a service achievement required by the corresponding first customer portrait information, and the first customer service achievement requirement information data is converted into text information, where the first customer service achievement requirement information exemplarily includes: consulting the real estate tax legal problem in the real estate legal field in the legal field, according to the first client service achievement requirement information, further determining the corresponding service scheme type, and recommending a historical service scheme, so that the first client service achievement requirement information needs to be further classified.
Firstly, preprocessing the first client service achievement requirement information, specifically, performing text processing on the first client service achievement requirement information, removing part of Stop words (Stop words) in the first client service achievement requirement information, exemplarily, removing Stop words such as ' inner ' and ' side ' in ' a real estate tax legal problem in the field of consulting laws, and then performing word segmentation to obtain characteristic word segments in the first client service achievement requirement information. Illustratively, the "real estate tax legal problem in real estate law in consulting law field" is segmented into "law field", "real estate tax", "legal problem", and these segments are taken as the first customer service requirement characteristic in the first customer service achievement requirement information.
Based on the preprocessing result, a second classification rule classifier needs to be constructed and trained to classify the first customer service result requirement information. Firstly, obtaining a plurality of service achievement categories in the first enterprise service fusion database, and taking the plurality of service achievement categories as classification labels for classifying and classifying the first customer service achievement requirement information, namely, after classifying the first customer service achievement requirement information, the first customer service achievement requirement information can be classified into a certain service achievement category.
Further, a plurality of first enterprise service achievement information is obtained based on the first enterprise service fusion database, each first enterprise service achievement information comprises a plurality of service requirement characteristics, the plurality of service requirement characteristics are in one-to-one correspondence with the M types of service information and comprise service requirement characteristics such as service content, service efficiency, service flow and service effect evaluation, and according to the plurality of service requirement characteristics, the corresponding first enterprise service achievement information can be determined.
And calculating the probability of classifying the first enterprise service achievement information comprising different service requirement characteristics into a certain service achievement category based on the plurality of service requirement characteristics and the first enterprise service achievement information to obtain a second classification rule classifier. The second classification rule classifier is as follows:
wherein, a is the first enterprise service achievement information, c _ i is the classification label, P (c _ i-a) is the probability that the classification label of a certain first enterprise service achievement information is c _ i, P (c _ i) is the probability distribution of c _ i in all the classification labels, a _ j is the jth service requirement characteristic in the first enterprise service achievement information, and P (a _ j | c _ i) is the probability that the service requirement characteristic a _ j in c _ i appears.
Therefore, based on the second classification rule classifier, the first customer service requirement characteristics obtained after the first customer service requirement text information is participled are input into the second classification rule classifier, the first customer service achievement requirement information is classified according to the first customer service requirement characteristics, the corresponding classification labels are obtained, the classification labels are corresponding first customer service types, and the first customer service types are one of multiple service achievement categories in the first enterprise service fusion database.
Illustratively, the classification label corresponding to the first customer service achievement requirement information is calculated according to the first customer service requirement characteristics of the above-mentioned "legal field", "real estate tax", "legal problem", and the like, as follows:
and c _ i is the first customer service type, and after calculating the probability that the first customer service result requirement information is correspondingly classified into all the sample labels, selecting the sample label with the maximum probability as the first customer service type to finish the classification of the first customer service result requirement information.
S700: servicing the first customer with the first customer service type.
According to the method, the second classification rule classifier is adopted to classify the first customer service achievement demand information, an accurate first customer service type can be obtained according to the first customer service achievement demand information, customer requirements can be obtained according to customer portrait classification, then service types can be obtained according to customer demand classification, finally a service scheme of a service achievement category in the first enterprise historical service achievement information is called according to the service types, a service scheme is recommended for a first customer and serves as a basis for formulating a new service scheme to carry out customer service, and the technical effect of improving historical service achievement information management calling efficiency and accuracy is achieved.
In summary, the application realizes effective management of the historical service achievement information of the enterprise by collecting the historical service achievement information of the enterprise and constructing the service fusion database of the enterprise, and when the historical service achievement information of the enterprise is used as the historical case of the enterprise, the historical achievement information can be called, the application also obtains the service requirement required by the customer by establishing two classification rules and classifying according to the customer image, then, service schemes in the historical service achievement category are classified and recommended according to service requirements, the utilization rate of the historical service achievement data can be provided, according to the intelligent service proposal recommended by the client, the intelligence and the accuracy of the service proposal formulation are improved, the efficiency of the service proposal formulation is improved, and the technical effects of providing the service enterprise historical service achievement data management utilization efficiency, improving the historical service achievement data recommendation accuracy and improving the new service proposal formulation accuracy are achieved.
Example two
Based on the same inventive concept as the method for processing the enterprise service result data in the foregoing embodiment, as shown in fig. 4, the present application provides an enterprise service result data processing system, wherein the system includes:
a first obtaining unit 11, where the first obtaining unit 11 is configured to obtain first enterprise information;
a second obtaining unit 12, where the second obtaining unit 12 is configured to obtain the first enterprise historical service achievement information;
a first constructing unit 13, where the first constructing unit 13 is configured to construct a first enterprise service convergence database based on the first enterprise historical service achievement information, where the first enterprise service convergence database includes multiple service achievement categories;
a third obtaining unit 14, wherein the third obtaining unit 141 is used for obtaining the first client portrait information;
a first processing unit 15, where the first processing unit 15 is configured to classify the first customer portrait information based on a first classification rule, and obtain first customer service achievement requirement information;
a second processing unit 16, where the second processing unit 16 is configured to compare, based on a second classification rule, first customer service achievement requirement information in the first enterprise service convergence database to obtain a first customer service type, where the first customer service type is one of the multiple service achievement categories;
a third processing unit 17, said third processing unit 17 being adapted to serve said first customer with said first customer service type.
Further, the system further comprises:
a fourth obtaining unit, configured to obtain, based on the first enterprise historical service achievement information, M-class service information, where M is a positive integer;
a fifth obtaining unit, configured to obtain an M-class service information interval based on the M-class service information;
a fourth processing unit, configured to, based on the M-class service information intervals, screen and obtain service information intervals that meet a preset condition, and obtain M screened enterprise service information intervals;
a second constructing unit, configured to construct the first enterprise service convergence database based on the M filtered enterprise service information intervals.
Further, the system further comprises:
a fifth processing unit, configured to perform dimension reduction processing on the first enterprise historical service achievement information;
the sixth processing unit is used for classifying the first enterprise historical service result information after dimensionality reduction according to the client type to obtain multi-family client information;
a sixth obtaining unit configured to obtain the first customer information;
a seventh processing unit, configured to map and match the first customer information in the multiple families of customer information, to obtain first family-related customer information;
an eighth processing unit to obtain first client portrait information based on the first family client information.
Further, the system further comprises:
the third construction unit is used for constructing and training to obtain a classified forest model;
a ninth processing unit, configured to input the first customer portrait information into the classified forest model, and obtain a plurality of output results;
a tenth processing unit, configured to obtain a first output result based on the multiple output results, where the first output result is an output result with a highest occurrence probability;
a seventh obtaining unit, configured to use the first output result as the first customer service achievement demand information.
Further, the system further comprises:
obtaining a historical service achievement information set;
the fourth construction unit is used for constructing the classified forest model, the classified forest model comprises X classified trees, and X is a positive integer;
an eighth obtaining unit, configured to randomly select N pieces of service achievement information in the historical service achievement information set in a replacement manner, where N is a positive integer;
an eleventh processing unit, configured to obtain a first data set in the N pieces of service achievement information, and train a classification root node;
a twelfth processing unit, configured to obtain a second data set in the N pieces of service result information, train classification branch nodes, until the training completes the first classification tree;
and the thirteenth processing unit is used for randomly selecting N pieces of service achievement information in the historical service achievement information set in a putting-back mode again, training a second classification tree until the X classification tree is trained, and obtaining the classification forest model.
Further, the system further comprises:
a fourteenth processing unit, configured to preprocess the first customer service achievement requirement information, to obtain first customer service requirement text information;
a fifth constructing unit, configured to construct a second classification rule classifier;
a fifteenth processing unit, configured to perform word segmentation on the first customer service requirement text information to obtain a first customer service requirement characteristic;
a sixteenth processing unit, configured to input the first customer service requirement characteristic into the second classification rule classifier, to obtain the first customer service type.
Further, the system further comprises:
a ninth obtaining unit, configured to obtain, based on the first enterprise service convergence database, a plurality of service achievement categories as classification tags;
a tenth obtaining unit, configured to obtain, based on the first enterprise service convergence database, a plurality of first enterprise service achievement information, where each of the first enterprise service achievement information includes a plurality of service requirement characteristics;
a seventeenth processing unit, configured to calculate a probability that the first enterprise service achievement information including the different service requirement characteristics is classified as a certain classification label, and obtain the second classification rule classifier.
EXAMPLE III
Based on the same inventive concept as the method for processing the enterprise service result data in the foregoing embodiment, the present application further provides a computer-readable storage medium, on which a computer program is stored, and the computer program, when executed by a processor, implements the method in the first embodiment.
The electronic device of the present application is described below with reference to figure 5,
based on the same inventive concept as the method for processing the enterprise service result data in the foregoing embodiment, the present application further provides an enterprise service result data processing system, including: a processor coupled to a memory, the memory for storing a program that, when executed by the processor, causes the system to perform the steps of the method of embodiment one.
The electronic device 300 includes: processor 302, communication interface 303, memory 301. Optionally, the electronic device 300 may also include a bus architecture 304. Wherein, the communication interface 303, the processor 302 and the memory 301 may be connected to each other through a bus architecture 304; the bus architecture 304 may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The bus architecture 304 may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, only one thick line is shown in FIG. 5, but that does not indicate only one bus or one type of bus.
The communication interface 303 may be any device, such as a transceiver, for communicating with other devices or communication networks, such as an ethernet, a Radio Access Network (RAN), a Wireless Local Area Network (WLAN), a wired access network, and the like.
The memory 301 may be, but is not limited to, a ROM or other type of static storage device that can store static information and instructions, a RAM or other type of dynamic storage device that can store information and instructions, an Electrically Erasable Programmable Read Only Memory (EEPROM), a compact disc read only memory (CD ROM) or other optical disk storage, optical disk storage (including compact disc, laser disc, optical disc, digital versatile disc, blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer. The memory may be self-contained and coupled to the processor through a bus architecture 304. The memory may also be integral to the processor.
The memory 301 is used for storing computer-executable instructions for implementing the present application, and is controlled by the processor 302 to execute. The processor 302 is configured to execute the computer execution instructions stored in the memory 301, so as to implement an enterprise service achievement data processing method provided by the above-mentioned embodiment of the present application.
Those of ordinary skill in the art will understand that: the various numbers of the first, second, etc. mentioned in this application are for convenience of description and are not intended to limit the scope of this application nor to indicate the order of precedence. "and/or" describes the association relationship of the associated objects, meaning that there may be three relationships, e.g., a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship. "at least one" means one or more. At least two means two or more. "at least one," "any," or similar expressions refer to any combination of these items, including any combination of singular or plural items. For example, at least one (one ) of a, b, or c, may represent: a, b, c, a b, a c, b c or a b c, wherein a, b and c can be single or multiple.
In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the present application are generated in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer finger
The instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another computer readable storage medium, for example, where the computer instructions may be transmitted from one website site, computer, server, or data center to another website site, computer, server, or data center by wire (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wirelessly (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device including one or more available media integrated servers, data centers, and the like. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.
The various illustrative logical units and circuits described in this application may be implemented or operated through the design of a general purpose processor, a digital signal processor, an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof. A general-purpose processor may be a microprocessor, but in the alternative, the processor may be any conventional processor, controller, microcontroller, or state machine. A processor may also be implemented as a combination of computing devices, e.g., a digital signal processor and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a digital signal processor core, or any other similar configuration.
The steps of a method or algorithm described in this application may be embodied directly in hardware, in a software element executed by a processor, or in a combination of the two. The software cells may be stored in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, a removable disk, a CD ROM, or any other form of storage medium known in the art. For example, a storage medium may be coupled to the processor such the processor can read information from, and write information to, the storage medium. In the alternative, the storage medium may be integral to the processor. The processor and the storage medium may reside in an ASIC, which may be disposed in a terminal. In the alternative, the processor and the storage medium may reside in different components within the terminal. These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Although the present application has been described in conjunction with specific features and embodiments thereof, it will be evident that various modifications and combinations can be made thereto without departing from the spirit and scope of the application. Accordingly, the specification and figures are merely exemplary of the application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of the application. It will be apparent to those skilled in the art that various changes and modifications may be made in the present application without departing from the scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the present application and its equivalent technology, it is intended that the present application include such modifications and variations.
Claims (7)
1. An enterprise service achievement data processing method, characterized in that the method comprises:
obtaining first enterprise information;
obtaining the first enterprise historical service achievement information;
constructing a first enterprise service convergence database based on the first enterprise historical service achievement information, wherein the first enterprise service convergence database comprises a plurality of service achievement categories;
obtaining first customer portrait information;
classifying the first customer portrait information based on a first classification rule to obtain first customer service achievement requirement information;
comparing first customer service achievement demand information in the first enterprise service fusion database based on a second classification rule to obtain a first customer service type, wherein the first customer service type is one of the multiple service achievement categories;
servicing the first customer with the first customer service type;
the constructing of the first enterprise service convergence database based on the first enterprise historical service achievement information comprises:
obtaining M types of service information based on the first enterprise historical service achievement information, wherein M is a positive integer;
obtaining an M-type service information interval based on the M-type service information;
based on the M types of service information intervals, screening and obtaining service information intervals meeting preset conditions, and obtaining M screened enterprise service information intervals;
constructing the first enterprise service fusion database based on the M screened enterprise service information intervals;
the classifying the first customer portrait information based on the first classification rule to obtain first customer service achievement requirement information includes:
constructing and training to obtain a classified forest model;
inputting the first customer portrait information into the classified forest model to obtain a plurality of output results;
obtaining a first output result based on the plurality of output results, wherein the first output result is an output result with the highest occurrence probability;
using the first output result as the first customer service achievement requirement information;
the constructing and training of the classified forest model to obtain the classified forest model comprises the following steps:
obtaining a historical service achievement information set;
constructing the classified forest model, wherein the classified forest model comprises X classified trees, and X is a positive integer;
randomly selecting N pieces of service achievement information in the historical service achievement information set in a putting-back mode, wherein N is a positive integer;
obtaining a first data set in the N pieces of service result information, and training a classification root node;
obtaining a second data set in the N pieces of service result information, and training classification branch nodes until a first classification tree is trained;
and randomly selecting N pieces of service result information in the historical service result information set in a put-back mode, and training a second classification tree until the X classification tree is trained to obtain the classification forest model.
2. The method of claim 1, wherein obtaining first client representation information comprises:
performing dimensionality reduction processing on the first enterprise historical service achievement information;
classifying the first enterprise historical service result information after dimension reduction according to the types of clients to obtain multi-family client information;
obtaining first customer information;
mapping and matching the first customer information in the multi-family customer information to obtain first family customer information;
based on the first family client information, first client representation information is obtained.
3. The method of claim 1, wherein comparing the first customer service achievement requirement information in the enterprise service convergence database based on the second classification rule to obtain a first customer service type comprises:
preprocessing the first customer service achievement requirement information to obtain first customer service requirement text information;
constructing a second classification rule classifier;
performing word segmentation on the first customer service requirement text information to obtain first customer service requirement characteristics;
and inputting the first customer service requirement characteristic into the second classification rule classifier to obtain the first customer service type.
4. The method of claim 3, wherein constructing a second classification rule classifier comprises:
obtaining a plurality of service achievement categories as classification labels based on the first enterprise service fusion database;
obtaining a plurality of first enterprise service achievement information based on the first enterprise service convergence database, wherein each first enterprise service achievement information comprises a plurality of service requirement characteristics;
and calculating the probability that the first enterprise service achievement information containing different service requirement characteristics is classified into a certain classification label to obtain the second classification rule classifier.
5. An enterprise service achievement data processing system, the system comprising:
a first obtaining unit, configured to obtain first enterprise information;
a second obtaining unit, configured to obtain the first enterprise historical service achievement information;
a first construction unit, configured to construct a first enterprise service convergence database based on the first enterprise historical service achievement information, where the first enterprise service convergence database includes multiple service achievement categories;
a third obtaining unit configured to obtain first client portrait information;
the first processing unit is used for classifying the first customer portrait information based on a first classification rule to obtain first customer service achievement requirement information;
the second processing unit is used for comparing first customer service achievement demand information in the first enterprise service convergence database based on a second classification rule to obtain a first customer service type, wherein the first customer service type is one of the multiple service achievement categories;
a third processing unit for servicing the first customer with the first customer service type;
a fourth obtaining unit, configured to obtain, based on the first enterprise historical service achievement information, M-class service information, where M is a positive integer;
a fifth obtaining unit, configured to obtain an M-class service information interval based on the M-class service information;
a fourth processing unit, configured to filter, based on the M types of service information intervals, service information intervals that meet preset conditions, and obtain M filtered enterprise service information intervals;
a second constructing unit, configured to construct the first enterprise service convergence database based on the M filtered enterprise service information intervals;
the third construction unit is used for constructing and training to obtain a classified forest model;
a ninth processing unit, configured to input the first customer portrait information into the classified forest model, to obtain a plurality of output results;
a tenth processing unit, configured to obtain a first output result based on the plurality of output results, where the first output result is an output result with a highest probability of occurrence;
a seventh obtaining unit, configured to use the first output result as the first customer service achievement requirement information;
an eighth obtaining unit, configured to obtain a historical service achievement information set;
the fourth construction unit is used for constructing the classified forest model, the classified forest model comprises X classified trees, and X is a positive integer;
a ninth obtaining unit, configured to randomly select N pieces of service achievement information in the historical service achievement information set in a replacement manner, where N is a positive integer;
an eleventh processing unit, configured to obtain a first data set in the N pieces of service result information, and train a classification root node;
a twelfth processing unit, configured to obtain a second data set in the N pieces of service result information, train classification branch nodes, until the training completes the first classification tree;
and the thirteenth processing unit is used for randomly selecting N pieces of service achievement information in the historical service achievement information set in a putting-back mode again, training a second classification tree until the X classification tree is trained, and obtaining the classification forest model.
6. An enterprise service achievement data processing system, comprising: a processor coupled to a memory, the memory for storing a program that, when executed by the processor, causes a system to perform the steps of the method of any of claims 1 to 4.
7. A computer-readable storage medium, characterized in that the storage medium has stored thereon a computer program which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 4.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111523184.6A CN114238615B (en) | 2021-12-14 | 2021-12-14 | Enterprise service result data processing method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111523184.6A CN114238615B (en) | 2021-12-14 | 2021-12-14 | Enterprise service result data processing method and system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114238615A CN114238615A (en) | 2022-03-25 |
CN114238615B true CN114238615B (en) | 2022-07-22 |
Family
ID=80755518
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111523184.6A Active CN114238615B (en) | 2021-12-14 | 2021-12-14 | Enterprise service result data processing method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114238615B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117992676B (en) * | 2024-04-02 | 2024-06-07 | 福建省君诺科技成果转化服务有限公司 | Intelligent scientific and technological achievement recommendation method based on big data |
Family Cites Families (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8874728B2 (en) * | 2010-08-31 | 2014-10-28 | Dell Products L.P. | System and method for customizing information handling system product and service offerings based on usage profiles |
CN109993553B (en) * | 2017-12-30 | 2021-09-03 | ***通信集团山西有限公司 | Data analysis method, device, equipment and medium based on reverse funnel |
CN108388955A (en) * | 2018-01-11 | 2018-08-10 | 国网山东省电力公司 | Customer service strategies formulating method, device based on random forest and logistic regression |
CN110580259A (en) * | 2018-05-22 | 2019-12-17 | 上海大学 | Customer demand mining method and equipment based on process management big data |
CN109785020A (en) * | 2019-03-26 | 2019-05-21 | 广州市番禺信息技术投资发展有限公司 | A kind of big data method of servicing |
CN110135901A (en) * | 2019-05-10 | 2019-08-16 | 重庆天蓬网络有限公司 | A kind of enterprise customer draws a portrait construction method, system, medium and electronic equipment |
CN110427418A (en) * | 2019-07-04 | 2019-11-08 | 深圳供电局有限公司 | Customer analysis grouping method based on customer energy value index system |
CN110458435A (en) * | 2019-08-01 | 2019-11-15 | 深圳市遇住信息科技有限公司 | A kind of business data intelligent analysis method and platform |
CN112232909A (en) * | 2020-10-13 | 2021-01-15 | 汉唐信通(北京)科技有限公司 | Business opportunity mining method based on enterprise portrait |
CN112837087A (en) * | 2020-12-16 | 2021-05-25 | 北京交通大学 | User portrait construction method oriented to consultation service system |
CN113435912A (en) * | 2021-06-29 | 2021-09-24 | 平安科技(深圳)有限公司 | Data analysis method, device, equipment and medium based on client portrait |
CN113610566A (en) * | 2021-07-22 | 2021-11-05 | 浙江惠瀜网络科技有限公司 | Intelligent recommendation method based on airport customer portrait and service scene |
CN113706220A (en) * | 2021-09-15 | 2021-11-26 | 华人运通(上海)自动驾驶科技有限公司 | User portrait determination, user demand prediction method, and data processing system |
-
2021
- 2021-12-14 CN CN202111523184.6A patent/CN114238615B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN114238615A (en) | 2022-03-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Rouyendegh | The intuitionistic fuzzy ELECTRE model | |
WO2020119272A1 (en) | Risk identification model training method and apparatus, and server | |
CN111461180B (en) | Sample classification method, device, computer equipment and storage medium | |
Marqués et al. | Ranking-based MCDM models in financial management applications: analysis and emerging challenges | |
CN105744005A (en) | Client positioning and analyzing method and server | |
CN111401777A (en) | Enterprise risk assessment method and device, terminal equipment and storage medium | |
CN113360780A (en) | Big data based information recommendation method and system | |
Wang et al. | Evaluating financial performance of Taiwan container shipping companies by strength and weakness indices | |
CN113554175B (en) | Knowledge graph construction method and device, readable storage medium and terminal equipment | |
CN107622326A (en) | User's classification, available resources Forecasting Methodology, device and equipment | |
WO2023103527A1 (en) | Access frequency prediction method and device | |
Mo et al. | An interval efficiency measurement in DEA when considering undesirable outputs | |
CN114238615B (en) | Enterprise service result data processing method and system | |
CN111126629B (en) | Model generation method, brush list identification method, system, equipment and medium | |
Lo et al. | An emperical study on application of big data analytics to automate service desk business process | |
CN116523301A (en) | System for predicting risk rating based on big data of electronic commerce | |
Deng et al. | A novel method for elimination of inconsistencies in ordinal classification with monotonicity constraints | |
CN116861226A (en) | Data processing method and related device | |
CN113269610A (en) | Bank product recommendation method and device and storage medium | |
CN113256173A (en) | Routing method, routing device, electronic equipment and storage medium | |
Yuan | [Retracted] Analysis of Consumer Behavior Data Based on Deep Neural Network Model | |
Mahalle et al. | Data Acquisition and Preparation | |
CN112308419A (en) | Data processing method, device, equipment and computer storage medium | |
CN112182320A (en) | Clustering data processing method and device, computer equipment and storage medium | |
Zhang | Research on recognition of accounting information distortion of listed companies based on classification regression tree algorithm |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |