CN106651424B - Power user portrait establishing and analyzing method based on big data technology - Google Patents
Power user portrait establishing and analyzing method based on big data technology Download PDFInfo
- Publication number
- CN106651424B CN106651424B CN201610860951.5A CN201610860951A CN106651424B CN 106651424 B CN106651424 B CN 106651424B CN 201610860951 A CN201610860951 A CN 201610860951A CN 106651424 B CN106651424 B CN 106651424B
- Authority
- CN
- China
- Prior art keywords
- portrait
- user
- data
- information
- power
- 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
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
- G06F18/24155—Bayesian classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
Abstract
The invention discloses a method for establishing and analyzing a portrait of a power consumer based on a big data technology, which is used for acquiring historical power consumption information, basic attributes, payment information and appeal information of the power consumer; determining a set of user portrait classification categories and an influence factor set of a classification result, and determining a mapping relation between the influence factor set and the classification set; randomly extracting the acquired data, taking a part of the data as a training sample, and taking the part of the data and the data as a prediction sample; carrying out normalization processing, discretization processing and attribute reduction on the training samples and the prediction samples, and determining a corrected influence factor set; training the training samples, establishing a power user portrait prediction model based on a naive Bayes classifier by taking cross validation as a test mode, and carrying out data classification mining analysis on the prediction samples by using the prediction model to obtain the power user portrait. The invention is helpful for prediction and management of electric power quantity.
Description
Technical Field
The invention relates to a power user portrait establishing and analyzing method based on a big data technology.
Background
Nowadays, more and more industries pay attention to the application of user portrayal, but due to different industries having different industry backgrounds, application scenes and user requirements, the user portrayals of different industries cannot be the same. The reason for users to draw figures in the finance and banking industries is that consumption habits of young customers are changed, the customers do not like going to a financial website for handling business, but choose to carry out financial consumption through intelligent equipment, and nowadays, it is difficult to have a product which can meet the requirements of all people at the same time. The telecommunication industry needs to realize real-time accurate marketing such as flow package, telephone fee package and the like through user figures, and meanwhile, personalized marketing is achieved in the face of a large number of client groups.
With the deep promotion of informatization construction and the rapid development of electric power business, power grid enterprises also accumulate abundant precious data resources, deeply excavate the existing data and fully utilize data analysis results to assist decision making, further research power grid development and customer service rules, and become one of the important ways for driving the innovation development of the power grid enterprises. Therefore, the research on the portrait of the power consumer based on the big data technology is developed, the differentiated and precise marketing strategy is formulated, the competitiveness of products and services is improved, the increasingly diversified power utilization service requirements of the power consumer are met, and the occupation rate of electric energy in the social energy consumption terminal is very urgent.
User images from a business perspective have great value to enterprises, and the user image purposes are two. One is a service scene starting, and a target client is searched. In another example, the user is designed with a product or marketing campaign by referring to the user profile information.
The enterprise utilizes the found target user group to mine data of population attribute, behavior attribute, social network, psychological characteristic, interest and hobby of each user, and through continuous superposition and updating, the complete information label is abstracted, and a three-dimensional user virtual model, namely a user image, is combined and built. For power grid enterprises, the power consumer portrait is characterized in that feature classification and classification are carried out according to the difference of basic attributes, power consumption behaviors, payment behaviors and appeal behaviors of users, typical features are extracted from each type, threshold values of labels are given, and individual portrait and group portrait of power consumers are carried out according to final labels and service demand scenes.
The establishment of the portrait of the power consumer plays a vital role in promoting differentiated services, improving service satisfaction, predicting customer behaviors, reducing enterprise loss and correctly estimating electric quantity in the power industry.
The existing power consumer portrayal comprises successful cases of service customer relationship management, service channel management, customer power failure management, customer portrayal technology application scene planning, customer portrayal label system research and the like. The project of Liaoning electric Anshan power supply company, namely the electric power system payment channel evaluation method based on big data, is characterized in that portrait analysis is performed on user payment behaviors by adopting a K-means clustering algorithm based on questionnaire data, and the corresponding relation between various user attributes and various user payment behaviors is identified. However, this solution has obvious drawbacks both from a business and a technical point of view: in terms of business, the payment behavior is only a part of the user portrait and the credit rating, and can not be equivalent to the user portrait and the credit rating; technically, the determination of the K value in the K-means algorithm is key, the clustering effect is extremely sensitive to the K value, noise points and isolated points, the optimal K value can be determined by many times of experiments, and the efficiency is low; because the influence degrees of all attributes on the user portrait are different, different weights need to be given to the attributes respectively, but the K-means algorithm cannot determine the specific weights, so that the classification result is lack of persuasion.
Disclosure of Invention
The invention provides a power user portrait establishing and analyzing method based on big data technology, which comprises the steps of dividing a personal portrait into two levels of a personal portrait and a group portrait according to user data and business requirements, and objectively and comprehensively obtaining user portrait data, and is beneficial to application of power requirements and power analysis.
In order to achieve the purpose, the invention adopts the following technical scheme:
a power consumer portrait establishing and analyzing method based on big data technology comprises the following steps:
(1) acquiring historical electricity consumption information, basic attributes, payment information and appeal information of a power consumer;
(2) determining a set of user portrait classification categories and an influence factor set of a classification result, and determining a mapping relation between the influence factor set and the classification set;
(3) randomly extracting the acquired data, taking a part of the data as a training sample, and taking the part of the data and the data as a prediction sample;
(4) carrying out normalization processing, discretization processing and attribute reduction on the training samples and the prediction samples, and determining a corrected influence factor set;
(5) training the training samples, establishing a power user portrait prediction model based on a naive Bayes classifier by taking cross validation as a test mode, and carrying out data classification mining analysis on the prediction samples by using the prediction model to obtain the power user portrait.
In the step (1), the influence factors include basic information, power consumption behaviors, payment information, appeal information and social information, wherein the basic information includes the gender, the power consumption type, the industry category, the life of the user, the power supply voltage, the type of the city and/or the load property of the user; the user portrait classification category comprises high-quality users, general users and low-quality users, and the specific quality grades are divided according to set standards.
In the step (1), the electricity consumption behavior comprises the electricity quantity grade of the user, seasonal electricity consumption peak, power supply quality perception condition, default electricity consumption degree and electricity stealing degree.
In the step (1), the payment information includes a meter reading mode, a meter reading period, a bill issuing date, a payment time limit date, a consumption grade and/or a payment channel of the user.
In the step (1), the complaint information includes complaint emotion, tolerance, strength, complaint preference, preference for electricity quantity and electricity charge, and/or preference for power failure warranty.
In the step (1), information strongly related to the portrait of the user is extracted from the information system file of the power system, the division of the correlation degree is divided and distinguished according to an expert system, correlation analysis is carried out on the correlation degree and portrait indexes after key factors are found out, user behavior factors which are strongly related in business are found out, and the data source range of the label is determined based on the user behavior factors.
In the step (2), the basic characteristics of the user are described through the basic attribute tags of the user, the electricity utilization behavior tags of the user are used for describing the electricity utilization characteristics of the user, the habits and characteristics of the user in the electricity consumption process are confirmed, the payment information tags of the user are used for describing the distribution and behavior characteristics of the user in the electricity consumption cost payment process, and the appeal information is used for reflecting various requirements of the electricity user in the electricity service enjoying process.
In the step (3), 20% of data is used as a training sample, and the rest 80% of data is used as a prediction sample.
In the step (4), the data is normalized:
in the formula: x is the number ofijIs the sample before normalization, sijIs a normalized sample; min (x)j) Is the minimum value in the original sample; max (x)j) Is the maximum value in the original sample.
In the step (4), discretizing training sample data:
in the formula: z is a radical ofijFor discretized samples, min(s)j) Is the minimum value of the normalized sample, max(s)j) For the maximum value of the normalized sample, Q is the step size:
in the step (4), the attribute reduction specifically includes: after removing a certain attribute, if no repeated training sample data is found, the indissolvable relationship in the decision table is correspondingly changed, so that the attribute is reserved; and by analogy, finally obtaining the determined influence factor set.
In the step (5), the specific method for establishing the power consumer portrait prediction model comprises the following steps:
(5-1) establishing a power user portrait prediction model based on a naive Bayes classifier, wherein the model takes the determined influence factor set as an input vector and takes the classification category of the user portrait as an output vector;
and (5-2) respectively checking the accuracy of the power consumer portrait prediction model from three aspects of detailed precision, confusion matrix and node error rate.
In the step (5-2), the detailed precision comprises: TP Rate, FP Rate, Precision, Recall, F-Measure, and ROCEARea.
In the step (5), a specific method for performing data classification mining analysis on the prediction samples by using the prediction model is as follows:
(5-a) counting the number S and the class C of the example training samplesiNumber of samples SiK-th attribute AkIs equal to xkAnd is of class CiNumber of training example samples Sik；
(5-b) calculating the probability of each class and the attribute A in each class respectivelykIs equal to xkThe probability of (d);
(5-c) Using a classifier
And obtaining the attribution classification result of the prediction example sample X, and comparing the prediction result of the user portrait with the actual situation.
In the step (5-b), the step (c),
here, ScFor all the number of classes, SkAnd showing the number of k attribute values in the training sample.
The invention has the beneficial effects that:
(1) the invention is helpful to promote differentiated services and improve the service satisfaction. After the user portrait label system is established, each user can have a distinctive label library, and after the client provides basic information such as own name and the like for a front-line employee, the label library of the client can appear in front of the employee, namely all information of the user in the power system, including historical payment behaviors, power utilization records, various appeal records, whether communication is easy or not, and the like can be displayed. The system can provide great help for front-line staff such as customer service staff, business hall staff and the like during service, and the staff can adjust attitude and strategy according to the information in the tag library to serve the customers as far as possible, so that the satisfaction degree of the customers is improved;
(2) the invention can improve the marketing success rate, can easily screen which customers are suitable for which products based on the user portrait label library, and can directionally carry out marketing on some label users according to different channels: for example, a user who frequently calls 95598 customer service hotlines may be more favored to receive calls and short messages for marketing; other customers who often pay and inquire on the palm electric power and the WeChat public number may prefer to accept some APP pushing and WeChat pushing modes for marketing, and recommend suitable products to the customers in a mode that the customers can accept, and the accurate marketing mode can improve the marketing success rate;
(3) the invention is helpful to predicting the behavior of the customer and reducing the loss of the enterprise, and because the information among all departments is not communicated, the front-line personnel can not timely master the bad behaviors of the customer, such as electricity stealing, arrearage, default electricity utilization and the like, thereby causing great loss to the enterprise every year. Through the user portrait label library, a front-line worker can find problems in time, and adopts a power charge loss-stopping marketing strategy for customers with 'bad trails', so that the power charge recovery efficiency and effect are improved;
(4) the method is beneficial to developing user credit rating, providing marketing service data support, establishing a power user credit evaluation system, and carrying out comprehensive evaluation on the credit condition of a power supply service object (user and person) objectively, comprehensively and accurately from user basic information, power utilization behavior, payment behavior and appeal behavior by a power supply company, so that an auxiliary decision is provided for a province company to formulate a differentiated service management strategy of the province user, and guiding reference is provided for the business acceptance process of 95598 levels; the method provides service standards for users to enjoy different power supply services according to different credit levels, and provides data support for various power consumption APP services. Meanwhile, a foundation is laid for the next step of making a differential credit evaluation index system aiming at the economic development and the power consumption level of different city units.
Drawings
FIG. 1 is a schematic view of a user representation creation process of the present invention;
fig. 2 is a diagram illustrating a power consumer behavior tag according to an exemplary embodiment of the present invention.
The specific implementation mode is as follows:
the invention is further described with reference to the following figures and examples.
A power user portrait establishing and analyzing method based on big data technology comprises the following steps
Step 1, determining user portrait classification category C ═ { C ═ C1,C2,…,CiAnd the set of influence factors of the classification results
A＝{A1,A2,A3,A4,…,AnDetermining the mapping relation of the two sets;
step 2, collecting original data, taking 20% of the data as a training sample, and taking the rest 80% of the data as a prediction sample;
step 3, preprocessing the original data, wherein the preprocessing comprises normalization processing and separationThe scattering processing and the attribute reduction are carried out, thereby determining the influence factor set A ═ { A ═ A1,A2,…,AmWherein m is less than or equal to n;
step 4, training the training samples, establishing a power user portrait prediction model based on a naive Bayes classifier by taking cross validation as a test mode, and then verifying the accuracy of the established model so as to ensure the effectiveness of the model;
and 5, carrying out data classification mining analysis on the prediction samples by using the power user portrait prediction model based on the naive Bayesian classifier, thereby obtaining the power user portrait with high accuracy.
The step 1 comprises the following specific steps:
after comprehensively considering 95598 data, power grid reward part data, electric power user categories and other factors, the user portrait classification categories are determined on the basis of listening to opinions of technical professionals and basic service personnel in the electric industry, namely: high quality users, general users and low quality users;
step 1.2, combining effective data of a basic data platform part and 186 system (front end) data, and after detailed discussion and analysis of the user portrait, determining influence factors of the user portrait classification result, namely: basic information, power consumption behavior, payment information, appeal information and social information;
and step 1.3, determining the mapping relation from the influence factor set to the user portrait classification.
The step 2 comprises the following specific steps:
and 2.1, collecting required data from the 95598 data and a basic data platform, wherein 20% of the data are used as training samples, and the rest 80% of the data are used as prediction samples.
The step 3 comprises the following specific steps:
step 3.1, in order to preserve the integrity and the effectiveness of the data, normalization processing needs to be carried out on the sample data, and a normalization formula is as follows:
in the formula: x is the number ofijIs the sample before normalization, sijIs a normalized sample; min (x)j) Is the minimum value in the original sample; max (x)j) Is the maximum value in the original sample.
Step 3.2, carrying out discretization processing on training sample data for a discrete data value of a higher abstraction level, wherein the formula is as follows:
in the formula: z is a radical ofijFor discretized samples, min(s)j) Is the minimum value of the normalized sample, max(s)j) For the maximum value of the normalized sample, Q is the step size:
step 3.3, after a certain attribute is removed, if no repeated training sample data is found, ind (C-C)1) Not being equal to ind (C), the irresolvable relation in the decision table is correspondingly changed, so the attribute is reserved; by analogy, finally obtaining the influence factor set A ═ { A ═ A1,A2,…,Am}。
The step 4 comprises the following specific steps:
step 4.1, establishing a power consumer portrait prediction model based on a naive Bayes classifier, wherein the model is expressed by A ═ A { (A)1,A2,A3,A4,A5Using C as input vector, C as basic information, power consumption behavior, payment information, appeal information and social information1,C2,C3The { high-quality user, general user and low-quality user } is a category output vector;
and 4.2, respectively checking the accuracy of the power consumer portrait prediction model from the three aspects of detailed precision, confusion matrix and node error rate, wherein the detailed precision comprises the following steps: TP Rate, FP Rate, Precision, Recall, F-Measure, and ROCEARea.
The step 5 comprises the following steps:
step 5.1, counting the number S and the class C of the example training samplesiNumber of samples SiK-th attribute AkIs equal to xkAnd is of class CiNumber of training example samples Sik；
Step 5.2, calculating respectively
Here, ScFor all the number of classes, SkAnd showing the number of k attribute values in the training sample.
Step 5.3, utilizing the classifier
And obtaining the attribution classification result of the prediction example sample X.
And 5.4, comparing and analyzing the prediction result of the user portrait with the actual situation, and mining a deeper data value.
The invention carries out user analysis on two levels of personal portrait and group portrait according to user data and business requirements. The personal portrait is that each client is actually labeled with his/her own label according to the labels in the user label library. The group representation is a representation of the group that is formed by the known partial tags and the individual representations satisfying the selected tags are screened from the user system. The individual portrait supports people and users associated with the individual portrait to mine, so that a front-line marketing staff or customer service staff can conveniently and quickly know the characteristics of the users, potential risks are avoided, marketing service cost is saved, and user service satisfaction is improved. The group portrait can analyze the portrait composition difference of the same user group in different regions and different periods, and is convenient for adopting personalized marketing strategies and evaluating marketing effects.
The latitude of user portrait related data needs to be combined with service scenes, and the user portrait needs to be simple and concise and strongly related to the service, and needs to be convenient to screen and further operate. The user portrait needs to adhere to three principles, namely basic attribute, power consumption, payment and appeal information; strongly related information is dominant; the qualitative data is dominant. The following is developed for explanation and analysis, respectively.
(1) Basic attribute and power consumption, payment and appeal information are taken as main parts
The information describing a power consumer is numerous, the basic attribute is important information in a user representation, and the basic attribute is information describing the consumption ability of a person in the society. The purpose of user imaging by any enterprise is to find a target customer, who must be a user with potential consumer capabilities. Part of the key information in the basic attributes can directly prove the consumption capacity of the customer, such as the area where the power consumer lives, the work done, and the information of income, owned property, contract capacity, and the like. Of course, the name, sex, electricity utilization address, contact information and the like of the user are also needed, and the power grid enterprise can contact the customer and promote products and services to the customer.
Besides, in addition to the basic attributes of the users, the consumption conditions (electricity consumption information), payment conditions (payment information), consumption feedback conditions (appeal information) of the users in the power commodity consumption process, and interaction communication conditions (social information) among the consumers in the future need to be known.
(2) Adopt strong relevant information and ignore weak relevant information
The strong relevant information is information directly related to the scene requirements of the power marketing service, and can be causal information or information with high relevance degree.
If the definition adopts 0 to 1 as the value range of the correlation coefficient, the correlation coefficient above 0.6 should be defined as strong correlation information. For example, under the same other conditions, the average wage of people around 35 years old is higher than that of people with the average age of 30 years old, the average wage of students with computer professional graduation is higher than that of students with philosophy professional, the average wage for working in the financial industry is higher than that of the textile industry, and the average wage in Shanghai exceeds that in Hainan province. From the information, the influence of the age, the academic calendar, the occupation and the place of the coming person on the income is large, and the income is strongly related to the income. For example, the information having a large influence on electricity consumption, payment, and appeal actions is strong related information, and otherwise, the information is weak related information.
Other information of the user, such as height, weight, name, constellation and the like of the user, is difficult to analyze the habit influence on electricity consumption, payment and appeal from probability, is weak related information, and the information is not required to be put into a user portrait for analysis, and has no great commercial value.
When the user portrait and the user analysis are performed, strong related information needs to be considered, and weak related information does not need to be considered, which is a principle of user portrait.
(3) Classifying quantitative information as qualitative information
The user portrait aims at screening target customers for the electric power marketing strategy, quantitative information is not beneficial to screening the customers, the quantitative information needs to be converted into qualitative information, and people are screened according to information categories.
For example, the clients may be divided by age groups, 18-25 years defined as young, 25-35 years defined as young, 36-45 as middle-aged, and so on. The population can be defined as a high-income population, a medium-income population and a low-income population by referring to the personal income information. The reference asset information may also define the customer as high, medium, or low. By means of the type and mode of the qualitative information, a power grid enterprise can start from self business without a fixed mode.
The method has the advantages that various kinds of quantitative information in the power marketing business are collected together, the qualitative information is classified and is qualitative, users can be screened favorably, target customers can be located quickly, and the method is another principle of user portrait.
User portrait step
The user portrait aiming at the power industry can be divided into three steps in the process: the method comprises the following steps of obtaining and researching user information, establishing a user behavior tag library and developing a user portrait (as shown in figure 1), and comprises the following specific steps:
(1) obtaining and researching user information
The portrait data of the power consumer is mainly divided into four types, namely basic attribute, power consumption information, payment information and appeal information. The data are distributed in different information system files, for example, basic attributes and payment information of users are in a marketing service system, power utilization information of the users is in a power utilization information acquisition system, and user appeal information is in a 95598 service support system.
The latitude information of the portrait of the user is more and better, and only the information strongly related to four types of portrait information, the information strongly related to the business scene and the product and the target client need to be found. The strongly correlated factor selection suggestion adopts an expert scoring method to reduce the range, correlation analysis is carried out on key factors selected according to the expert scoring and the portrait indexes, user behavior factors which are really strongly correlated in service are found out, and the data source range of the label is determined based on the user behavior factors. Through a large amount of practices, the user portrait is difficult to realize in a short time for a business by drawing 360 degrees, the user cannot be completely known through portrait, and the user can be closely known. In addition, the effectiveness of the data is also considered, and factors with low data quality (accuracy, timeliness and integrity) are not included in the label system, so as not to influence the accuracy of the final user portrait.
(2) Establishing user behavior label library
The label is a highly refined feature identifier obtained by analyzing the user information, and finally, the three-dimensional 'portrait' of the user can be outlined by combining all labels of the user. The core work of constructing the user portrait is to paste a label to the user, wherein part of the label is directly obtained according to the behavior data (the age of the user, the electric quantity level, the payment channel and the like) of the user, and part of the label is obtained by mining through a series of algorithms or rules (appeal tolerance, appeal preference and the like).
The basic information label is used for describing some basic characteristics of the user, and can know the customer by knowing the basic information, and know who the customer is, including name, gender, age, income, occupation, various social relations and the like; the power consumption behavior label mainly shows the power consumption characteristics of the user, and learns the habits and characteristics of the user in the power consumption process, including power consumption, seasonal power consumption peak, power consumption holidays, power supply quality perception and the like. The payment behavior mainly records the distribution and behavior characteristics of the user in the process of paying the electric power consumption cost, and comprises a bill issuing date, a payment time limit date, a consumption grade, payment channel preference, payment timeliness and the like. The appeal behaviors mainly reflect various requirements of power users in the process of enjoying power services, further insights feedback opinions and suggestions of the users on the service quality and efficiency of power supply enterprises, and promotes the improvement of the power industry on business, wherein the feedback opinions and suggestions mainly comprise appeal emotion, appeal tolerance, appeal strength, appeal content preference and the like.
The data of the power system has limitations to a certain extent, and if the user portrait is made only through the internal data of the power system, the portrait is not rich. If some economic data of the user, such as occupation, income, consumption capability, family condition and the like, are possessed, the portrait information of the user can be richer and fuller. The data needs to get through external resources, introduce external data, such as information of the Unionpay and the E-commerce to enrich consumption characteristic information, introduce position information of mobile big data to enrich interest information of customers, introduce data of external manufacturers to enrich social information, and the like.
In the implementation aspect, the data label is combed by a daily accumulated log recording system of each system, and is imported into the HDFS through the Sqoop, or can be implemented by using a code, for example, the JDBC of Spark connects with a traditional database to perform data Cache. In another way, the HDFS may be imported by writing data into a local file, and then importing the data by Load of SparkSQL or Export of Hive.
And (3) splicing ETL according to business logic by using Hive writing UDF or hiveQL, so that the user corresponds to different user label data to generate corresponding source table data, thereby facilitating the data acquisition of a subsequent power user portrait system and generating a label width table according to different rules.
(3) Developing user portrayal
The purpose of user portrayal is to analyze the user's behavior and provide better service to the customer based on the analysis. Quantitative information is not beneficial to analyzing clients, and needs to be converted into qualitative information to analyze different client groups according to information categories.
Through a user label system, user individual portraits and group portraits can be developed. The marketing personnel inputs the unique identification information of the user, and an individual portrait covering the basic attribute, the electricity utilization characteristic, the payment characteristic and the appeal characteristic of an independent user can be obtained. When instructing front-line marketing personnel to perform on-site operation service, individual and differentiated service strategies are adopted, the individual service risk range and degree are reduced, and the user service satisfaction rate is improved. In addition, different label characteristics of user basic information, power utilization behaviors, payment behaviors and appeal behaviors are selected by marketing personnel, the selected labels are surrounded, the user group portrait is drawn, the composition condition of the sub-level label characteristics of the user group portrait is displayed on the user group portrait in a key mode, the portrait composition difference of the same user group in different regions and different periods is observed, the horizontal comparison of user groups of various power supply units is facilitated, or the change trend analysis of the user group of the same power supply unit is facilitated, and then the differentiated marketing strategy and the evaluation marketing effect are adopted.
In order to fully combine the achievement with the actual marketing service, the effect and the significance of the electric power user portrait work based on the big data technology are really exerted, the typical application scene mining and marketing strategy formulation related to the user electricity utilization, payment and appeal are carried out by combining the key work of each year of a power grid enterprise, the accurate marketing developed according to the user electricity utilization behavior, the payment behavior and the appeal behavior is further carried out, and the value of the data productivity is exerted.
Although the embodiments of the present invention have been described with reference to the accompanying drawings, it is not intended to limit the scope of the present invention, and it should be understood by those skilled in the art that various modifications and variations can be made without inventive efforts by those skilled in the art based on the technical solution of the present invention.
Claims (8)
1. A method for establishing and analyzing a portrait of a power consumer based on a big data technology is characterized by comprising the following steps: the method comprises the following steps:
(1) acquiring historical electricity consumption information, basic attributes, payment information and appeal information of a power consumer;
(2) determining a set of user portrait classification categories and an influence factor set of a classification result, and determining a mapping relation between the influence factor set and the classification set;
(3) randomly extracting the acquired data, wherein one part of the acquired data is used as a training sample, and the rest of the acquired data is used as a prediction sample;
(4) carrying out normalization processing, discretization processing and attribute reduction on the training samples and the prediction samples, and determining a corrected influence factor set;
(5) training a training sample, establishing a power user portrait prediction model based on a naive Bayes classifier by taking ten-fold cross validation as a test mode, and carrying out data classification mining analysis on the prediction sample by using the prediction model to obtain a power user portrait;
in the step (5), a specific method for performing data classification mining analysis on the prediction samples by using the prediction model is as follows:
(5-a) counting the number S and the class C of the example training samplesiNumber of samples SiK-th attribute AkIs equal to xkAnd is of class CiNumber of training example samples Sik；
(5-b) calculating the probability of each class and the attribute A in each class respectivelykIs equal to xkThe probability of (d);
(5-c) Using a classifier
Obtaining the attribution classification result of the prediction example sample X, and comparing the prediction result of the user portrait with the actual situation;
the specific method for establishing the power consumer portrait prediction model comprises the following steps:
(5-1) establishing a power user portrait prediction model based on a naive Bayes classifier, wherein the model takes the determined influence factor set as an input vector and takes the classification category of the user portrait as an output vector;
and (5-2) respectively checking the accuracy of the power consumer portrait prediction model from three aspects of detailed precision, confusion matrix and node error rate.
2. The method as claimed in claim 1, wherein the method for creating and analyzing the portrait of the power consumer based on big data technology comprises: in the step (1), the influence factors include basic information, electricity consumption behavior, payment information, appeal information and social information, the user image classification categories include high-quality users, general users and low-quality users, and the specific quality grades are divided according to set standards.
3. The method as claimed in claim 1, wherein the method for creating and analyzing the portrait of the power consumer based on big data technology comprises: in the step (3), 20% of data is used as a training sample, and the rest 80% of data is used as a prediction sample.
4. The method as claimed in claim 1, wherein the method for creating and analyzing the portrait of the power consumer based on big data technology comprises: in the step (4), the data is normalized:
in the formula: x is the number ofijIs the sample before normalization, sijIs a normalized sample; min (x)j) Is the minimum value in the original sample; max (x)j) Is the maximum value in the original sample.
5. The method as claimed in claim 1, wherein the method for creating and analyzing the portrait of the power consumer based on big data technology comprises: in the step (4), discretizing training sample data:
in the formula: z is a radical ofijFor discretized samples, min(s)j) Is the minimum value of the normalized sample, max(s)j) For the maximum value of the normalized sample, Q is the step size:
6. the method as claimed in claim 1, wherein the method for creating and analyzing the portrait of the power consumer based on big data technology comprises: in the step (4), the attribute reduction specifically includes: after removing a certain attribute, if no repeated training sample data is found, the indissolvable relationship in the decision table is correspondingly changed, so that the attribute is reserved; and by analogy, finally obtaining the determined influence factor set.
7. The method as claimed in claim 1, wherein the method for creating and analyzing the portrait of the power consumer based on big data technology comprises: in the step (5-2), the detailed precision comprises: true meta ratio, false positive meta ratio, precision, recall, precision, and harmonic mean of recall.
8. The method as claimed in claim 1, wherein the method for creating and analyzing the portrait of the power consumer based on big data technology comprises: in the step (5-b), the step (c),
here, ScFor all the number of classes, SkAnd showing the number of k attribute values in the training sample.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610860951.5A CN106651424B (en) | 2016-09-28 | 2016-09-28 | Power user portrait establishing and analyzing method based on big data technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610860951.5A CN106651424B (en) | 2016-09-28 | 2016-09-28 | Power user portrait establishing and analyzing method based on big data technology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106651424A CN106651424A (en) | 2017-05-10 |
| CN106651424B true CN106651424B (en) | 2020-05-22 |
Family
ID=58854665
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610860951.5A Active CN106651424B (en) | 2016-09-28 | 2016-09-28 | Power user portrait establishing and analyzing method based on big data technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106651424B (en) |
Families Citing this family (73)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107292513A (en) * | 2017-06-21 | 2017-10-24 | 国网辽宁省电力有限公司 | A kind of method that power customer management is realized based on svm classifier algorithm |
| CN107391645B (en) * | 2017-07-12 | 2018-04-10 | 广州市昊链信息科技股份有限公司 | A kind of logistics information automatic push and practical operation specification form system and method |
| CN107730269A (en) * | 2017-07-21 | 2018-02-23 | 南通大学 | A kind of Electricity customers portrait method of Behavior-based control analysis |
| CN109389138A (en) * | 2017-08-09 | 2019-02-26 | 武汉安天信息技术有限责任公司 | A kind of user's portrait method and device |
| CN107464142B (en) * | 2017-08-09 | 2018-11-09 | 南京甄视智能科技有限公司 | Method, the user's portrait system for system of being drawn a portrait based on marketing feedback result back feeding user |
| CN107578277B (en) * | 2017-08-24 | 2021-04-09 | 国网浙江省电力公司电力科学研究院 | Rental house client positioning method for electric power marketing |
| CN107895015A (en) * | 2017-11-14 | 2018-04-10 | 江苏电力信息技术有限公司 | Power consumer feature tag proportional system construction method based on analytic hierarchy process (AHP) |
| CN107909288A (en) * | 2017-12-05 | 2018-04-13 | 国网内蒙古东部电力有限公司电力科学研究院 | Paying behaviors analysis method based on SOM neural network clustering algorithms |
| CN108038727A (en) * | 2017-12-11 | 2018-05-15 | 囯网河北省电力有限公司电力科学研究院 | A kind of method, system and terminal device that differentiated service is provided |
| CN108399249B (en) * | 2018-03-02 | 2020-12-29 | 上海精数信息科技有限公司 | Data normalization method, user portrait providing device and storage medium |
| CN110309932A (en) * | 2018-03-21 | 2019-10-08 | 国网浙江省电力公司湖州供电公司 | A kind of power customer resource fine-grained management method based on TEM |
| CN108550050A (en) * | 2018-03-27 | 2018-09-18 | 昆山和君纵达数据科技有限公司 | A kind of user's portrait method based on call center data |
| CN108520045B (en) * | 2018-04-03 | 2023-05-30 | 平安健康保险股份有限公司 | Data service response method and device |
| CN108647729B (en) * | 2018-05-11 | 2022-03-04 | 广东省科技基础条件平台中心 | User portrait acquisition method |
| CN108764663B (en) * | 2018-05-15 | 2020-10-16 | 广东电网有限责任公司信息中心 | Method and system for generating and managing power customer portrait |
| CN109063945B (en) * | 2018-06-08 | 2023-12-29 | 广州云标局网络科技有限公司 | Value evaluation system-based 360-degree customer portrait construction method for electricity selling company |
| CN109146539A (en) * | 2018-06-28 | 2019-01-04 | 深圳市彬讯科技有限公司 | The update method and device of user's portrait |
| CN109003127A (en) * | 2018-07-06 | 2018-12-14 | 国网福建省电力有限公司 | A kind of credit rating method based on Electricity customers data |
| CN109615555B (en) * | 2018-08-01 | 2023-05-05 | 美林数据技术股份有限公司 | User abnormal electricity behavior identification method and system based on integrated learning algorithm |
| CN109146707A (en) * | 2018-08-27 | 2019-01-04 | 罗孚电气（厦门）有限公司 | Power consumer analysis method, device and electronic equipment based on big data analysis |
| CN109412832B (en) * | 2018-09-10 | 2022-04-15 | 中国联合网络通信集团有限公司 | User service providing method and system |
| CN109559146B (en) * | 2018-09-25 | 2022-11-04 | 国家电网有限公司客户服务中心 | Provincial and municipal access data center optimization method for predicting number of potential users by electric power customer service center based on logistic model |
| CN109614982A (en) * | 2018-10-18 | 2019-04-12 | 平安科技（深圳）有限公司 | Product analysis method, apparatus, computer equipment and storage medium |
| CN109697626A (en) * | 2018-10-19 | 2019-04-30 | 上海吉贝克信息技术有限公司 | Marketing system, method, electric terminal and medium based on JeeSite quick development platform |
| CN109598479B (en) * | 2018-10-25 | 2024-04-05 | 三六零科技集团有限公司 | Bill extraction method and device, electronic equipment and medium |
| CN109740620B (en) * | 2018-11-12 | 2023-09-26 | 平安科技（深圳）有限公司 | Method, device, equipment and storage medium for establishing crowd figure classification model |
| CN109785034A (en) * | 2018-11-13 | 2019-05-21 | 北京码牛科技有限公司 | User's portrait generation method, device, electronic equipment and computer-readable medium |
| CN111221868A (en) * | 2018-11-26 | 2020-06-02 | 国网上海市电力公司 | Data mining and analyzing method applied to channel preference of power customer |
| CN109636235A (en) * | 2018-12-26 | 2019-04-16 | 北京汽车研究总院有限公司 | The determination method and processing system of driving behavior portrait model |
| CN109948913A (en) * | 2019-03-01 | 2019-06-28 | 长沙理工大学 | A kind of multi-source feature power consumer composite portrait system based on double-deck xgboost algorithm |
| CN109934273A (en) * | 2019-03-01 | 2019-06-25 | 长沙理工大学 | It is a kind of based on the fault characteristic of DML-KNN algorithm and active damage repair technology draw a portrait new method |
| CN111723273A (en) * | 2019-03-18 | 2020-09-29 | 北京中电翔云信息技术有限公司 | Smart cloud retrieval system and method |
| CN110119998B (en) * | 2019-03-27 | 2023-04-28 | 广东浩迪创新科技有限公司 | Renting house information management method and system based on intelligent ammeter |
| CN110046657B (en) * | 2019-03-29 | 2022-06-14 | 武汉大学深圳研究院 | Social security figure image method based on multi-view learning |
| CN110134860B (en) * | 2019-04-12 | 2023-04-07 | 创新先进技术有限公司 | User portrait generation method, device and equipment |
| CN110210018B (en) * | 2019-05-14 | 2023-07-11 | 北京百度网讯科技有限公司 | Matching method and device for registration department |
| CN110191183A (en) * | 2019-05-31 | 2019-08-30 | 深圳市医信科技有限公司 | Accurate intelligent method for pushing, system, device and computer readable storage medium |
| CN110263255A (en) * | 2019-06-21 | 2019-09-20 | 北京字节跳动网络技术有限公司 | Acquisition methods, system, server and the storage medium of customer attribute information |
| CN110276647A (en) * | 2019-06-26 | 2019-09-24 | 中国南方电网有限责任公司 | Online service method based on user integral |
| CN110347923B (en) * | 2019-07-09 | 2022-10-11 | 安徽财贸职业学院 | Traceable fast fission type user portrait construction method |
| CN110334463B (en) * | 2019-07-12 | 2021-06-18 | 无锡锐泰节能系统科学有限公司 | Energy management design method based on energy consumption portrait model |
| CN110472852B (en) * | 2019-08-02 | 2023-03-03 | 上海云扩信息科技有限公司 | Experience evaluation implementation management method for power service application |
| CN110599237A (en) * | 2019-08-15 | 2019-12-20 | 国网山东省电力公司临清市供电公司 | Electric power marketing management information acquisition module based on intelligent monitoring |
| CN110516155A (en) * | 2019-08-29 | 2019-11-29 | 深圳市云积分科技有限公司 | Marketing strategy generation method and system |
| CN110728537A (en) * | 2019-09-24 | 2020-01-24 | 国网河北省电力有限公司信息通信分公司 | Prediction payment method based on power consumer behavior label |
| CN110688580A (en) * | 2019-10-14 | 2020-01-14 | 国网山东省电力公司泰安供电公司 | Power supply service data display system based on customer portrait |
| CN110689385A (en) * | 2019-10-16 | 2020-01-14 | 国网山东省电力公司信息通信公司 | Power customer service user portrait construction method based on knowledge graph |
| CN111080367B (en) * | 2019-12-20 | 2023-11-28 | 深圳市国电科技通信有限公司 | Power consumption behavior analysis method for sensing power consumption state of low-voltage user |
| CN111506636A (en) * | 2020-05-12 | 2020-08-07 | 上海积成能源科技有限公司 | System and method for analyzing residential electricity consumption behavior based on autoregressive and neighbor algorithm |
| CN111666313B (en) * | 2020-05-25 | 2023-02-07 | 中科星图股份有限公司 | Correlation construction and multi-user data matching method based on multi-source heterogeneous remote sensing data |
| CN111401798A (en) * | 2020-06-02 | 2020-07-10 | 南京百敖软件有限公司 | Enterprise waste escaping and debt risk early warning system and construction method |
| CN111738462B (en) * | 2020-06-08 | 2022-08-30 | 国网江苏省电力有限公司常州供电分公司 | Fault first-aid repair active service early warning method for electric power metering device |
| CN111709791A (en) * | 2020-06-19 | 2020-09-25 | 四川中电启明星信息技术有限公司 | Power supply marketing service method based on improved feature word weight algorithm |
| CN112115355A (en) * | 2020-09-02 | 2020-12-22 | 南方电网深圳数字电网研究院有限公司 | Power grid intelligent service system based on user portrait in power industry |
| CN112131475B (en) * | 2020-09-25 | 2023-10-10 | 重庆邮电大学 | Interpretable and interactive user portrayal method and device |
| CN112184313A (en) * | 2020-09-28 | 2021-01-05 | 国网上海市电力公司 | Power marketing business application system based on client portrait data |
| CN112132631A (en) * | 2020-09-29 | 2020-12-25 | 国网上海市电力公司 | Label electricity utilization management method based on power customer portrait |
| CN112053100A (en) * | 2020-10-15 | 2020-12-08 | 东北电力大学 | Big data-based analysis method for electricity utilization behavior of user |
| CN112529630A (en) * | 2020-12-17 | 2021-03-19 | 国网河北省电力有限公司营销服务中心 | Construction method of multi-dimensional informatization label system of power consumer |
| CN112417308A (en) * | 2020-12-17 | 2021-02-26 | 国网河北省电力有限公司营销服务中心 | User portrait label generation method based on electric power big data |
| CN112579721B (en) * | 2020-12-22 | 2023-10-27 | 北京市腾河智慧能源科技有限公司 | Method and system for constructing crowd distribution map, terminal equipment and storage medium |
| CN112862530A (en) * | 2021-02-09 | 2021-05-28 | 江之龙 | Marketing system based on big data |
| CN113159419A (en) * | 2021-04-21 | 2021-07-23 | 成都卫士通信息产业股份有限公司 | Group feature portrait analysis method, device and equipment and readable storage medium |
| CN113487448A (en) * | 2021-05-31 | 2021-10-08 | 国网上海市电力公司 | Power credit labeling method and system based on power big data |
| CN113313470B (en) * | 2021-06-10 | 2023-06-09 | 郑州科技学院 | Employment type assessment method and system based on big data |
| CN113344638B (en) * | 2021-06-29 | 2022-05-24 | 云南电网有限责任公司信息中心 | Power grid user group portrait construction method and device based on hypergraph |
| CN113377760A (en) * | 2021-07-06 | 2021-09-10 | 国网江苏省电力有限公司营销服务中心 | Method and system for establishing low-voltage resident feature portrait based on electric power data and multivariate data |
| CN114154835A (en) * | 2021-11-29 | 2022-03-08 | 海南电网有限责任公司信息通信分公司 | Method for evaluating payment slowness of electricity customer |
| CN114219241A (en) * | 2021-12-01 | 2022-03-22 | 深圳供电局有限公司 | Customer electricity consumption behavior analysis method and system |
| CN114417955B (en) * | 2021-12-02 | 2023-10-31 | 国网浙江省电力有限公司 | Method, device and storage medium for generating power index image suitable for village in real time |
| CN114595323B (en) * | 2022-03-04 | 2023-03-10 | 北京百度网讯科技有限公司 | Portrait construction, recommendation, model training method, apparatus, device and storage medium |
| CN116450952A (en) * | 2023-06-16 | 2023-07-18 | 天津星耀九洲科技有限公司 | Internet user portrait generation method and system based on deep learning technology |
| CN117271905B (en) * | 2023-11-21 | 2024-02-09 | 杭州小策科技有限公司 | Crowd image-based lateral demand analysis method and system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103325067A (en) * | 2013-05-29 | 2013-09-25 | 广东电网公司佛山供电局 | Service recommendation method and system based on electricity customer segmentation |
| CN104408667A (en) * | 2014-11-20 | 2015-03-11 | 深圳供电局有限公司 | Comprehensive assessment method and system of power quality |
| CN104809473A (en) * | 2015-04-30 | 2015-07-29 | 国网智能电网研究院 | Online collected electric power data classifying method |
| CN105023092A (en) * | 2015-06-24 | 2015-11-04 | 国网山东省电力公司电力科学研究院 | Power load monitoring method based on electric quantity feature analysis |
| CN105260815A (en) * | 2015-09-18 | 2016-01-20 | 国网辽宁省电力有限公司鞍山供电公司 | Electric power system payment channel evaluating method based on large data |
-
2016
- 2016-09-28 CN CN201610860951.5A patent/CN106651424B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103325067A (en) * | 2013-05-29 | 2013-09-25 | 广东电网公司佛山供电局 | Service recommendation method and system based on electricity customer segmentation |
| CN104408667A (en) * | 2014-11-20 | 2015-03-11 | 深圳供电局有限公司 | Comprehensive assessment method and system of power quality |
| CN104809473A (en) * | 2015-04-30 | 2015-07-29 | 国网智能电网研究院 | Online collected electric power data classifying method |
| CN105023092A (en) * | 2015-06-24 | 2015-11-04 | 国网山东省电力公司电力科学研究院 | Power load monitoring method based on electric quantity feature analysis |
| CN105260815A (en) * | 2015-09-18 | 2016-01-20 | 国网辽宁省电力有限公司鞍山供电公司 | Electric power system payment channel evaluating method based on large data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106651424A (en) | 2017-05-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106651424B (en) | Power user portrait establishing and analyzing method based on big data technology | |
| CN108154401B (en) | User portrait depicting method, device, medium and computing equipment | |
| CN110704572B (en) | Suspected illegal fundraising risk early warning method, device, equipment and storage medium | |
| CN109063945B (en) | Value evaluation system-based 360-degree customer portrait construction method for electricity selling company | |
| CN103714139B (en) | Parallel data mining method for identifying a mass of mobile client bases | |
| US20150134401A1 (en) | In-memory end-to-end process of predictive analytics | |
| CN108280541A (en) | Customer service strategies formulating method, device based on random forest and decision tree | |
| CN110310163A (en) | A kind of accurate method, equipment and readable medium for formulating marketing strategy | |
| CN112116256A (en) | Data asset management method | |
| CN112632405A (en) | Recommendation method, device, equipment and storage medium | |
| CN111882420A (en) | Generation method of response rate, marketing method, model training method and device | |
| CN114117226A (en) | Product recommendation method, system, device and medium | |
| Dong et al. | Method for ranking the helpfulness of online reviews based on so-iles todim | |
| Kang et al. | City selection for fresh produce e-commerce’s market entry strategy: Based on the perspective of urban logistics competitiveness | |
| CN115130811A (en) | Method and device for establishing power user portrait and electronic equipment | |
| Gerlich et al. | Artificial intelligence as toolset for analysis of public opinion and social interaction in marketing: identification of micro and nano influencers | |
| KR20200054533A (en) | system for providing financial product recommendation service including diagnosing financial tendency | |
| CN115563176A (en) | Electronic commerce data processing system and method | |
| Li | Consumer behavior analysis model based on machine learning | |
| JP6031165B1 (en) | Promising customer prediction apparatus, promising customer prediction method, and promising customer prediction program | |
| Osaysa | Improving the quality of marketing analytics systems | |
| CN112258067A (en) | Low-voltage user payment behavior classification method based on Gaussian mixture model clustering algorithm | |
| Nan et al. | Corporate Marketing Strategy Analysis with Machine Learning Algorithms | |
| Huang et al. | To share or not to share? Revealing determinants of individuals’ willingness to share rides through a big data approach | |
| Sann et al. | Predicting Online Complaining Behavior in the Hospitality Industry: Application of Big Data Analytics to Online Reviews. Sustainability 2022, 14, 1800 |
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 | ||
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 250002 Wang Yue Road, Ji'nan City, Shandong Province, No. 2000 Patentee after: ELECTRIC POWER RESEARCH INSTITUTE OF STATE GRID SHANDONG ELECTRIC POWER Co. Patentee after: SHANDONG LUNENG SOFTWARE TECHNOLOGY Co.,Ltd. Patentee after: STATE GRID CORPORATION OF CHINA Address before: 250002 Wang Yue Road, Ji'nan City, Shandong Province, No. 2000 Patentee before: ELECTRIC POWER RESEARCH INSTITUTE OF STATE GRID SHANDONG ELECTRIC POWER Co. Patentee before: SHANDONG LUNENG SOFTWARE TECHNOLOGY Co.,Ltd. Patentee before: State Grid Corporation of China |
|
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20210407 Address after: No. 150, Jinger Road, Daguanyuan, Shizhong District, Jinan City, Shandong Province Patentee after: Shandong Electric Power Marketing Center Patentee after: ELECTRIC POWER RESEARCH INSTITUTE OF STATE GRID SHANDONG ELECTRIC POWER Co. Patentee after: SHANDONG LUNENG SOFTWARE TECHNOLOGY Co.,Ltd. Patentee after: STATE GRID CORPORATION OF CHINA Address before: 250002 Wang Yue Road, Ji'nan City, Shandong Province, No. 2000 Patentee before: ELECTRIC POWER RESEARCH INSTITUTE OF STATE GRID SHANDONG ELECTRIC POWER Co. Patentee before: SHANDONG LUNENG SOFTWARE TECHNOLOGY Co.,Ltd. Patentee before: STATE GRID CORPORATION OF CHINA |
|
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: No. 150, Jinger Road, Daguanyuan, Shizhong District, Jinan City, Shandong Province Patentee after: Shandong Electric Power Marketing Center Patentee after: ELECTRIC POWER RESEARCH INSTITUTE OF STATE GRID SHANDONG ELECTRIC POWER Co. Patentee after: Shandong luruan Digital Technology Co.,Ltd. Patentee after: STATE GRID CORPORATION OF CHINA Address before: No. 150, Jinger Road, Daguanyuan, Shizhong District, Jinan City, Shandong Province Patentee before: Shandong Electric Power Marketing Center Patentee before: ELECTRIC POWER RESEARCH INSTITUTE OF STATE GRID SHANDONG ELECTRIC POWER Co. Patentee before: SHANDONG LUNENG SOFTWARE TECHNOLOGY Co.,Ltd. Patentee before: STATE GRID CORPORATION OF CHINA |