CN115907308A - User portrait-based electric power material supplier evaluation method and device - Google Patents
User portrait-based electric power material supplier evaluation method and device Download PDFInfo
- Publication number
- CN115907308A CN115907308A CN202310027854.8A CN202310027854A CN115907308A CN 115907308 A CN115907308 A CN 115907308A CN 202310027854 A CN202310027854 A CN 202310027854A CN 115907308 A CN115907308 A CN 115907308A
- Authority
- CN
- China
- Prior art keywords
- supplier
- index
- evaluation
- comprehensive
- data
- 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.)
- Granted
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 123
- 239000000463 material Substances 0.000 title claims abstract description 101
- 238000013210 evaluation model Methods 0.000 claims abstract description 41
- 238000000034 method Methods 0.000 claims abstract description 37
- 238000012545 processing Methods 0.000 claims abstract description 22
- 238000007689 inspection Methods 0.000 claims abstract description 15
- 238000004140 cleaning Methods 0.000 claims abstract description 13
- 238000005070 sampling Methods 0.000 claims abstract description 8
- 239000013598 vector Substances 0.000 claims description 105
- 239000011159 matrix material Substances 0.000 claims description 86
- 230000008569 process Effects 0.000 claims description 23
- 239000002131 composite material Substances 0.000 claims description 22
- 238000006243 chemical reaction Methods 0.000 claims description 13
- 230000004927 fusion Effects 0.000 claims description 11
- 238000010606 normalization Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 abstract description 3
- 230000006870 function Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 239000000284 extract Substances 0.000 description 4
- 238000013473 artificial intelligence Methods 0.000 description 3
- 238000012797 qualification Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000009960 carding Methods 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000009193 crawling Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000004451 qualitative analysis Methods 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000000547 structure data Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a user portrait technology, and discloses a method and a device for evaluating an electric power material supplier based on a user portrait, wherein the method comprises the following steps: acquiring basic information of a supplier, performing data cleaning on the basic information to obtain first basic information, and performing indexing processing on the first basic information to generate a derivative index system; constructing a supplier comprehensive evaluation model according to a derivative index system; comprehensively evaluating suppliers through a supplier comprehensive evaluation model to obtain comprehensive rating, and extracting index labels in a derivative index system; generating a supplier portrait according to the comprehensive rating and the index label, acquiring auxiliary evaluation of a purchasing part to the supplier according to the supplier portrait, and acquiring the random inspection evaluation of a quality supervision part to the supplier according to the supplier portrait; and determining the final evaluation of the supplier according to the auxiliary evaluation, the sampling inspection evaluation and the comprehensive evaluation. The accuracy of the evaluation of the supplier can be improved.
Description
Technical Field
The invention relates to the technical field of user portrayal, in particular to a method and a device for evaluating an electric power material supplier based on the user portrayal.
Background
With the increasing market competition, the technical innovation and product innovation of enterprises are diversified, and the innovation awareness of enterprises is not supported by suppliers, but in order to establish a long-term stable cooperation relationship between a purchasing department and a supplier, the data from the suppliers needs to be analyzed for supplier evaluation.
The existing supplier evaluation method is a linear weight technology, each evaluation criterion is assigned with a weight, the weight is larger, the more important the evaluation is, and the supplier evaluation is higher. In practical application, the artificial judgment factor is too large, so that the practical application value is lacked, and the accuracy of evaluation of suppliers is low.
Disclosure of Invention
The invention provides a method and a device for evaluating an electric power material supplier based on a user portrait, and mainly aims to solve the problem of low accuracy in supplier evaluation.
In order to achieve the above object, the present invention provides a method for evaluating an electric power material supplier based on a user figure, comprising:
s1, acquiring basic information of an electric power material supplier, performing data cleaning on the basic information to obtain first basic information, and performing indexing processing on the first basic information to generate a derivative index system;
s2, constructing a supplier comprehensive evaluation model according to the derivative index system by using a preset analytic hierarchy process;
s3, comprehensively evaluating the electric power material supplier through the supplier comprehensive evaluation model to obtain a comprehensive rating, and extracting an index tag in the derivative index system, wherein the comprehensively evaluating the electric power material supplier through the supplier comprehensive evaluation model to obtain the comprehensive rating comprises the following steps:
s31, establishing index scores corresponding to the power material suppliers one by one according to indexes in the supplier comprehensive evaluation model through the analytic hierarchy process;
s32, calculating the comprehensive score of the power material supplier according to the index score and the index weight in the supplier comprehensive evaluation model by using the following scoring formula:
wherein ,
is a first
The composite score for each power supply provider,
is as follows
Corresponding to each power material supplier
The index score of each index is calculated,
for the supplier to comprehensively evaluate the model
The weight of each index is calculated according to the weight of each index,
for the number of power supply suppliers,
is the index number;
s33, determining the comprehensive rating of the power material supplier according to the comprehensive rating;
s4, generating a supplier portrait according to the comprehensive rating and the index tag, acquiring auxiliary evaluation of a preset purchasing part on the electric power material supplier according to the supplier portrait, and acquiring a preset quality supervision part on the spot check evaluation of the electric power material supplier according to the supplier portrait;
and S5, determining the final evaluation of the electric power material supplier according to the auxiliary evaluation, the spot check evaluation and the comprehensive evaluation.
Optionally, the performing data cleaning on the basic information to obtain first basic information includes:
correcting the noise data in the basic information to obtain corrected noise data;
correcting the error data in the basic information to obtain corrected data;
filling missing data in the basic information to obtain filling data;
deleting redundant data in the basic information to obtain clean data;
the corrected noise data, the corrected data, the padding data, and the clean data are collected as the first basic information.
Optionally, the performing indexing processing on the first basic information to generate a derivative index system includes:
carrying out data structural conversion on the first basic information to obtain structural data;
carrying out normalization processing on the structural data to obtain normalized data;
performing data fusion on the normalized data to obtain fused data;
generating a derivative index according to the fusion data by using a preset expression;
and collecting the fusion data and the derivative indexes into the derivative index system.
Optionally, the constructing a supplier comprehensive evaluation model according to the derivative index system by using a preset analytic hierarchy process includes:
constructing a judgment matrix of the derivative index system according to a preset weight matrix by utilizing the analytic hierarchy process;
calculating the geometric mean value of each row in the judgment matrix by using a preset sorting principle, wherein the sorting principle is as follows:
wherein ,
is the geometric mean value of the said geometric mean value,
is a first
Go to the first
The matrix value corresponding to the column is determined,
is the matrix column number of the judgment matrix or the matrix row number of the judgment matrix,
is as follows
Go to the first
Matrix values corresponding to the columns;
calculating the index weight of each index in the derived index system according to the geometric mean by using the following weight formula:
wherein ,
is the first in the derivative index system
The weight of the index of each index,
is a first
Geometric mean of the rows;
and determining whether the judgment matrix meets consistency or not by using preset consistency, and when the judgment matrix meets the consistency, generating the supplier comprehensive evaluation model according to the index weight.
Optionally, the constructing a judgment matrix of the derived index system according to a preset weight matrix includes:
counting the number of indexes in the derivative index system;
generating the row and column number of the judgment matrix according to the index number;
comparing the importance of adjacent indexes in the derived index system one by using the important scale in the weight matrix to obtain an index important value;
and adding the index important numerical values to the corresponding row and column numbers to generate the judgment matrix.
Optionally, the determining whether the determination matrix satisfies consistency by using preset consistency includes:
calculating the maximum characteristic root of the judgment matrix;
calculating a consistency index of the judgment matrix according to the maximum feature root by a consistency index formula as follows:
wherein ,
in order to be an indicator of said consistency,
for the root of the largest feature,
the order of the judgment matrix is;
calculating the random consistency ratio of the judgment matrix according to the consistency index and a preset random consistency index by using a consistency ratio formula as follows:
wherein ,
in order to be said random consistency ratio,
in order to be the index of the consistency,
is the random consistency index;
and when the random consistency ratio is smaller than a preset consistency ratio threshold, the judgment matrix meets the consistency.
Optionally, the generating a supplier portrait according to the composite rating and the index tag includes:
carrying out vector conversion on the comprehensive rating to obtain a comprehensive vector;
performing vector conversion on each index label to obtain a label vector;
stitching the composite vector with all of the tag vectors into the vendor portrait.
Optionally, said stitching said composite vector with all said tag vectors as said vendor portrait comprises:
counting the label vector lengths of all vectors in the label vectors, and counting the comprehensive vector length of the comprehensive vector;
determining the maximum value of the label vector length and the comprehensive vector length as a target length;
extending the lengths of all the label vectors and the comprehensive vector to the target length;
and merging the column dimensions of all the label vectors with the extended lengths and the comprehensive vector to obtain the supplier portrait.
Optionally, the determining a final rating of the electric power material supplier according to the auxiliary rating, the spot check rating, and the comprehensive rating includes:
determining an auxiliary rating for the auxiliary rating, and determining a spot rating for the spot rating;
counting the grade numbers of the auxiliary rating, the spot inspection rating and the comprehensive rating;
and selecting the grade with the maximum grade number as the final evaluation of the electric power material supplier.
In order to solve the above problems, the present invention further provides an electric power material supplier evaluation device based on a user figure, the device comprising:
the system comprises a derivative index system generating module, a data processing module and a data processing module, wherein the derivative index system generating module is used for acquiring basic information of an electric power material supplier, performing data cleaning on the basic information to obtain first basic information, and performing indexing processing on the first basic information to generate a derivative index system;
the supplier comprehensive evaluation model building module is used for building a supplier comprehensive evaluation model according to the derivative index system by utilizing a preset analytic hierarchy process;
the comprehensive rating determination module is used for comprehensively evaluating the power material supplier through the supplier comprehensive evaluation model to obtain a comprehensive rating and extracting an index label in the derivative index system;
the supplier portrait generation module is used for generating a supplier portrait according to the comprehensive rating and the index tag, acquiring auxiliary evaluation of a preset purchasing part on the electric power material supplier according to the supplier portrait, and acquiring sampling inspection evaluation of a preset quality supervision part on the electric power material supplier according to the supplier portrait;
and the final evaluation determining module is used for determining the final evaluation of the power material supplier according to the auxiliary evaluation, the spot check evaluation and the comprehensive evaluation.
The embodiment of the invention generates an index system by acquiring data of dimensionalities such as basic information, supply quality, performance condition, bad behavior and the like of a provider, performing operations such as structured transformation, data preprocessing, service carding and the like on the data, constructs a comprehensive evaluation model of the provider according to the data of different dimensionalities by utilizing an analytic hierarchy process, and extracts a label from the index system, thereby forming a label library. Therefore, the supplier portrait is generated according to the labels in the label library, the auxiliary evaluation of the purchasing part can be realized according to the supplier portrait, so that the auxiliary evaluation is obtained, and the selective inspection plan of the quality supervision part can be realized according to the supplier portrait, so that the selective inspection evaluation is obtained. The final evaluation of the power material supplier can be determined according to the auxiliary evaluation, the spot check evaluation and the comprehensive rating, so that the power supplier can be deeply known, and the accuracy of the evaluation of the supplier is improved. Therefore, the method and the device for evaluating the power material supplier based on the user portrait can solve the problem of low accuracy in supplier evaluation.
Drawings
FIG. 1 is a schematic flow chart illustrating a method for evaluating an electric power material supplier based on a user profile according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of generating a derived index system according to an embodiment of the present invention;
FIG. 3 is a schematic flow chart illustrating a process for determining a composite rating according to an embodiment of the present invention;
fig. 4 is a functional block diagram of an electric power material supplier evaluation device based on a user image according to an embodiment of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The embodiment of the application provides an electric power material supplier evaluation method based on user portrait. The execution subject of the user portrait based power supply evaluation method includes, but is not limited to, at least one of a server, a terminal, and other electronic devices that can be configured to execute the method provided by the embodiments of the present application. In other words, the user-portrait-based power supply evaluation method may be performed by software or hardware installed in a terminal device or a server device, and the software may be a block chain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like. The server may be an independent server, or may be a cloud server that provides basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a web service, cloud communication, a middleware service, a domain name service, a security service, a Content Delivery Network (CDN), and a big data and artificial intelligence platform.
Referring to fig. 1, a flow chart of an electric power material supplier evaluation method based on a user image according to an embodiment of the present invention is shown. In this embodiment, the method for evaluating an electric power material supplier based on a user profile includes:
s1, obtaining basic information of an electric power material supplier, carrying out data cleaning on the basic information to obtain first basic information, and carrying out indexing processing on the first basic information to generate a derivative index system;
in the embodiment of the invention, the power material suppliers comprise distribution network material suppliers such as a 10KV transformer, a 10KV power cable, a low-voltage power cable and a ring main unit (high-voltage switch cabinet). The basic information comprises information such as bad behavior, performance behavior, supply quality and the like of the provider.
In detail, a computer sentence with data crawling function (such as java sentence, python sentence, etc.) can be used to crawl the stored basic information from a predetermined storage area, including but not limited to a database, a block chain node, a network cache.
In the embodiment of the invention, data needs to be preprocessed, the data comprises a data cleaning part and an index analysis part, the data is firstly cleaned, and the data quality is mainly processed; and secondly, performing indexing processing on the data to generate a derivative index.
In this embodiment of the present invention, the performing data cleaning on the basic information to obtain first basic information includes:
correcting the noise data in the basic information to obtain corrected noise data;
correcting the error data in the basic information to obtain corrected data;
filling missing data in the basic information to obtain filling data;
deleting redundant data in the basic information to obtain clean data;
the corrected noise data, the corrected data, the padding data, and the clean data are collected as the first basic information.
In detail, the noise-containing data can be identified through a box diagram and a distribution diagram, and the noise-containing data is corrected or deleted; the error data can be identified through data inspection, and the error data is corrected or deleted; missing data can be identified through a statistical method, and filling or deleting processing is carried out on the missing data; the redundant data can be filled or deleted through the service analysis.
Specifically, after data in the basic information is finally subjected to data cleaning, the quality of the data is improved, and the data subjected to data cleaning is collected into the first basic information, so that the data is subjected to indexing processing according to the first basic information, and the data forms an index system.
In the embodiment of the invention, the derivative index system refers to different dimensions of an evaluation system of an electric power material supplier obtained by collecting the existing data indexes and derivative data indexes.
In the embodiment of the present invention, as shown in fig. 2, the performing the indexing processing on the first basic information to generate the derivative index system includes:
s21, performing data structural conversion on the first basic information to obtain structural data;
s22, carrying out normalization processing on the structural data to obtain normalized data;
s23, performing data fusion on the normalized data to obtain fused data;
s24, generating a derivative index according to the fusion data by using a preset expression;
and S25, collecting the fusion data and the derivative index as the derivative index system.
In detail, the first basic information is subjected to data structure conversion, and the first basic information is converted into a structure in the form of a matrix, that is, structure data. And normalizing the first basic information, and mapping all data to the same scale, thereby eliminating data dimension difference. And carrying out data fusion on the normalized data, namely the normalized data, and forming the data into wide table data.
Specifically, the derived index is a new index generated by calculating other indexes, and supports multiple data processing modes such as a mathematical operation expression and a groovy script. And fusing the data to form wide table data, and generating a derivative index through a mathematical operation expression or a conditional expression based on the wide table data.
And further, generating a derivative index system according to the derivative index and the fusion data, and constructing a supplier comprehensive evaluation model and extracting the label from the derivative index system.
S2, constructing a supplier comprehensive evaluation model according to the derivative index system by using a preset analytic hierarchy process;
in the embodiment of the invention, the analytic hierarchy process (AHP for short) is a method for decomposing elements always related to decision into levels such as targets, criteria, schemes and the like, obtaining importance degrees of different indexes through qualitative and quantitative analysis and further making the decision. The supplier comprehensive evaluation model refers to comprehensive evaluation of suppliers according to the indexes acquired before. The derivative index system comprises indexes with different dimensions, such as a bad behavior index, a performance behavior index, a paper certification index, a prequalification index, a reading record index, a supply quality index and the like.
In the embodiment of the present invention, the constructing a supplier comprehensive evaluation model according to the derivative index system by using a preset analytic hierarchy process includes:
constructing a judgment matrix of the derivative index system according to a preset weight matrix by utilizing the analytic hierarchy process;
calculating the geometric mean value of each row in the judgment matrix by using a preset sorting principle, wherein the sorting principle is as follows:
wherein ,
is the geometric mean value of the said geometric mean value,
is as follows
Go to the first
The matrix value corresponding to the column is,
is the number of matrix columns of the decision matrix or the decisionThe number of matrix rows of the broken matrix,
is as follows
Go to the first
Matrix values corresponding to the columns;
calculating the index weight of each index in the derived index system according to the geometric mean by using the following weight formula:
wherein ,
is the first in the derivative index system
The weight of the index of each index,
is as follows
Geometric mean of the rows;
and determining whether the judgment matrix meets the consistency by using preset consistency, and generating the supplier comprehensive evaluation model according to the index weight when the judgment matrix meets the consistency.
In detail, the function of the judgment matrix is to represent the corresponding importance degree grades of the two schemes in the form of the ratio of the two importance degrees between the indexes. And the weight matrix refers to the comparison importance degree of indexes among different indexes, such as indexes
And an index
Index comparison is carried out, and if the indexes are equally important, the scale is 1; equally important, the scale is 3; clearly important, the scale is 5; strongly important, the scale is 7; absolute importance, scale is 9; between the two, the scale may be any one of 2,4,6, 8. Thus, the importance between different indicators is determined for the importance of the indicator of the first level relative to the overall goal. u. of
Specifically, the constructing of the judgment matrix of the derivative index system according to the preset weight matrix includes:
counting the number of indexes in the derivative index system;
generating the row and column number of the judgment matrix according to the index number;
comparing the importance of adjacent indexes in the derived index system one by using the importance scale in the weight matrix to obtain an index important value;
and adding the index important numerical values to the corresponding row and column numbers to generate the judgment matrix.
In detail, regarding the importance of the index of the first layer with respect to the overall target, if the index RC1 is as important as the index RC2, then
If the index RC3 is more strongly less important than RC4, then
If the index RC6 is significantly more important than RC1, then
If the two indexes are in the middle, filling numbers between 2,4,6 and 8, and so on, comparing the importance of every two indexes, and adding the important values of the indexes to the corresponding row and column numbers to generate a complete judgment matrix.
Specifically, the judgment matrix is a symmetric matrix, and only needs to be the symmetric matrixThe part above the extreme diagonal (upper triangle) or below the extreme diagonal (lower triangle), then use the formula
The matrix value of the whole judgment matrix can be calculated, and the efficiency of calculating the judgment matrix can be improved.
Further, the consistency is used for checking whether the judgment matrix meets the consistency, and whether the weight of each index is proper is calculated according to the judgment matrix.
In the embodiment of the present invention, the determining whether the judgment matrix satisfies the consistency by using the preset consistency includes:
calculating the maximum characteristic root of the judgment matrix;
calculating the consistency index of the judgment matrix according to the maximum characteristic root by the following consistency index formula:
wherein ,
in order to be an indicator of said consistency,
for the root of the largest feature,
the order of the judgment matrix is obtained;
calculating the random consistency ratio of the judgment matrix according to the consistency index and a preset random consistency index by using a consistency ratio formula as follows:
wherein ,
in order to be said random consistency ratio,
in order to be an indicator of said consistency,
is the random consistency index;
and when the random consistency ratio is smaller than a preset consistency ratio threshold, the judgment matrix meets the consistency.
In detail, due to the maximum feature root
Continuously depend on
Then, then
Ratio of
The larger the size is, the more the inconsistency of the determination matrix is, and the consistency index
The smaller the size, the greater the consistency of the decision matrix. Using maximum feature root
The corresponding feature vector is a weight vector of the degree of influence of the factor to be compared on a certain factor of an upper layer, and the larger the degree of inconsistency, the larger the judgment error. Thus, can use
The degree of inconsistency of the judgment matrix is measured according to the magnitude of the numerical value, and a consistency index is obtained.
Specifically. The random consistency index and the matrix orderIn this regard, if the order of the matrix is 1,
is 0; the order of the matrix is 4,
is 0.90; the order of the matrix is 8,
was 1.41. Considering that the deviation of the consistency may be due to a random cause, in determining whether the decision matrix satisfies the consistency, it will be determined whether or not the consistency is satisfied
Index of consistency with random
Comparing to obtain random consistency ratio
。
Further, the threshold value of the consistency ratio is 0.1 when the random consistency ratio is achieved
When the weight is less than 0.1, the judgment matrix can be determined to meet the consistency requirement, and the constructed comprehensive evaluation index weight is appropriate. And generating the supplier comprehensive evaluation model according to the index weight, and determining the index weight for different indexes of the supplier, thereby determining the comprehensive rating of the supplier according to the supplier comprehensive evaluation model.
S3, comprehensively evaluating the power material supplier through the supplier comprehensive evaluation model to obtain a comprehensive rating, and extracting an index label in the derivative index system;
in the embodiment of the invention, different power material suppliers can be graded and graded on indexes of different dimensions through the supplier comprehensive evaluation model, so that the comprehensive grade of the power supplier is obtained.
In an embodiment of the present invention, referring to fig. 3, the comprehensively evaluating the power material supplier by the supplier comprehensive evaluation model to obtain a comprehensive rating includes:
s31, constructing index scores corresponding to the power material suppliers one by one according to indexes in the comprehensive evaluation model of the suppliers through the analytic hierarchy process;
s32, calculating the comprehensive score of the power material supplier according to the index score and the index weight in the supplier comprehensive evaluation model by using the following scoring formula:
wherein ,
is a first
The composite score for each power material provider,
is as follows
The first electric power material supplier
The index score of each index is calculated,
for the supplier to comprehensively evaluate the model
The weight of each index is calculated according to the weight of each index,
for the number of power supply suppliers,
is the index number;
and S33, determining the comprehensive rating of the power material supplier according to the comprehensive score.
Specifically, index scores corresponding to the electric power material suppliers are constructed one by one, namely, the electric power material suppliers and different indexes are linked through an analytic hierarchy process, and the index scores of the electric power material suppliers are determined through the different indexes. If scores of different electric power material suppliers on the index 1 are obtained, the comprehensive scores of different electric power material suppliers are obtained according to the index scores and the index weights.
Specifically, the comprehensive grades of different electric power material suppliers can be obtained according to the grading formula, and then the comprehensive grade of each electric power material supplier is determined according to the comprehensive grades. Wherein, the setting standard of each grade is that the grade A-comprehensive score is more than 90 (including 90); grade B-the composite score is below 90 points, and above 75 points (including 75 points); grade C-the composite score is below 75 points, and above 60 points (including 60 points); grade D-the composite score is below 60 points, and above 40 points (including 40 points); grade E-composite score below 40 points. The composite score for each of the electric power material providers can be determined based on the different composite scores.
In the embodiment of the present invention, it is further required to extract the index tags in the derived index system, and extract the indexes in the index system by tag extraction, so as to extract multiple tags of the electric power material supplier, such as qualification capability, operation scope, operation performance, and the like. Wherein, a computer sentence (such as Python) can be used to extract the index tag in the derivative index system.
In detail, a tag library is generated by the tags extracted from the index system, qualification capability, operation range, operation performance and comprehensive rating of the electric power material suppliers, and further a supplier portrait of each electric power material supplier is generated according to the tags, thereby further evaluating the suppliers according to the supplier portrait.
S4, generating a supplier portrait according to the comprehensive rating and the index tag, acquiring auxiliary evaluation of a preset purchasing part on the electric power material supplier according to the supplier portrait, and acquiring a preset quality supervision part on the spot check evaluation of the electric power material supplier according to the supplier portrait;
in the embodiment of the invention, the supplier portrait is a label of the supplier information, is a set of supplier characteristic labels, can reflect the basic information of the supplier, and is convenient for the purchasing department to realize the application in the aspect of auxiliary bid evaluation and the quality supervision department to plan in the aspect of a spot check plan.
In an embodiment of the present invention, the generating a provider image according to the comprehensive rating and the index tag includes:
carrying out vector conversion on the comprehensive rating to obtain a comprehensive vector;
performing vector conversion on each index label to obtain a label vector;
stitching the composite vector with all of the label vectors into the vendor portrait.
In detail, the comprehensive rating and each index tag may be subjected to vector conversion through a preset vector conversion model to obtain a comprehensive vector and a tag vector, where the vector conversion model includes, but is not limited to, a word2vec model and a Bert model.
Specifically, after the composite vector and the tag vectors are obtained, the composite vector and all the tag vectors may be vector-stitched to generate the vendor portrait.
In an embodiment of the present invention, the stitching the integrated vector and all the tag vectors into the vendor portrait includes:
counting the label vector lengths of all vectors in the label vectors, and counting the comprehensive vector length of the comprehensive vector;
determining the maximum value of the label vector length and the comprehensive vector length as a target length;
extending the lengths of all the label vectors and the comprehensive vector to the target length;
and merging the column dimensions of all the label vectors with the extended lengths and the comprehensive vector to obtain the supplier portrait.
In detail, since the lengths of the tag vector and the comprehensive vector may not be the same, in order to perform vector concatenation on the tag vectors, the vector lengths of the tag vectors need to be unified. Vector extension may be performed on vectors of shorter vector length than on all tag vectors, so that all tag vectors are the same vector quantity length as the composite vector.
Illustratively, there is a vector a in the tag vector: [12, 36, 24], vector B: [10, 25, 35, 17], complex vector C: as shown in statistics, the vector length of vector a is 3, the vector length of vector B is 4, the vector length of vector C is 3, and the vector length of vector B is greater than the vector lengths of vector a and vector C, then the vector a and vector C may be vector extended by using a preset parameter (e.g. 0) until the vector lengths of vector a and vector C are equal to the vector length of vector B, so as to obtain an extended vector a: [12, 36, 24,0], C: [15, 33, 20,0].
In the embodiment of the invention, the auxiliary evaluation of the electric power material supplier by the purchasing part is acquired according to the supplier portrait, after the supplier portrait is determined, the purchasing part can evaluate the electric power material supplier according to the qualification capability, the operating range, the operating performance and the comprehensive rating of the supplier portrait, and determine whether the electric power material supplier can score the mark, so that the purchasing part can be helped to carry out the application in the aspect of auxiliary mark evaluation according to the supplier portrait.
Furthermore, due to the problems of large manual processing workload, complicated process and the like of the current spot check plan, the rule of the spot check plan can be made according to the provider portrait, and the automatic generation of the spot check plan is realized, so that the spot check evaluation of the electric power material provider by a preset quality supervision part can be obtained according to the provider portrait. Therefore, the final evaluation of the power material supplier can be obtained according to the grade of the purchasing department to the supplier and the grade of the quality supervision department to the supplier.
And S5, determining the final evaluation of the power material supplier according to the auxiliary evaluation, the spot check evaluation and the comprehensive rating.
In the embodiment of the invention, the final evaluation refers to the comprehensive rating obtained by aiming at the comprehensive evaluation model of the supplier, the auxiliary evaluation of the purchasing part to the supplier according to the supplier portrait and the random inspection evaluation of the quality supervision part to the supplier according to the random inspection plan according to the supplier portrait.
In an embodiment of the present invention, the determining the final evaluation of the electric power material supplier according to the auxiliary evaluation, the spot-check evaluation and the comprehensive rating includes:
determining an auxiliary rating for the auxiliary rating, and determining a spot rating for the spot rating;
counting the grade numbers of the auxiliary rating, the spot inspection rating and the comprehensive rating;
and selecting the grade with the maximum grade number as the final evaluation of the electric power material supplier.
In detail, the auxiliary rating can be determined according to the evaluation level of the auxiliary evaluation, and the auxiliary rating is high when the auxiliary evaluation is high; the auxiliary rating is low and the auxiliary rating is low. Similarly, the sampling rate can be determined according to the evaluation level of the sampling evaluation, and the sampling evaluation is high, so that the sampling rate is high; the spot check rating is low, the low.
Illustratively, if the auxiliary rating is high, the spot check rating is high, and the general rating is high, the final rating of this power provider must be high; if the auxiliary rating is low, the spot check rating is low, and the comprehensive rating is low, the final evaluation of the power supplier must be low; if the auxiliary rating is high, the spot check rating is medium, and the composite rating is medium, the final rating of the power provider is medium. Therefore, the final evaluation is determined by the number of levels in the auxiliary rating, the spot check rating, and the integrated rating, and if the auxiliary rating is high, the spot check rating is medium, the integrated rating is medium, the high-low number is 1, the medium-low number is 2, and the low-low number is 0, the medium-low number with the highest number of levels is selected as the final evaluation of the electric power material provider, and the final evaluation of the electric power provider is medium.
The embodiment of the invention generates an index system by acquiring data of dimensionalities such as basic information, supply quality, performance condition, bad behavior and the like of a provider, performing operations such as structured transformation, data preprocessing, service carding and the like on the data, constructs a comprehensive evaluation model of the provider according to the data of different dimensionalities by utilizing an analytic hierarchy process, and extracts a label from the index system, thereby forming a label library. Therefore, the supplier portrait is generated according to the labels in the label library, the auxiliary evaluation of the purchasing part can be realized according to the supplier portrait, so that the auxiliary evaluation is obtained, and the selective inspection plan of the quality supervision part can be realized according to the supplier portrait, so that the selective inspection evaluation is obtained. The final evaluation of the power material supplier can be determined according to the auxiliary evaluation, the spot check evaluation and the comprehensive rating, so that the power supplier can be deeply known, and the accuracy of the evaluation of the supplier is improved. Therefore, the method and the device for evaluating the power material supplier based on the user portrait can solve the problem of low accuracy in supplier evaluation.
Fig. 4 is a functional block diagram of an electric power material supplier evaluation apparatus based on a user profile according to an embodiment of the present invention.
The electric power material supplier evaluation device 100 based on the user figure can be installed in the electronic equipment. According to the realized functions, the electric power material supplier evaluation device 100 based on the user portrait can comprise a derivative index system generation module 101, a supplier comprehensive evaluation model construction module 102, a comprehensive rating determination module 103, a supplier portrait generation module 104 and a final evaluation determination module 105. The module of the present invention, which may also be referred to as a unit, refers to a series of computer program segments that can be executed by a processor of an electronic device and that can perform a fixed function, and that are stored in a memory of the electronic device.
In the present embodiment, the functions of the respective modules/units are as follows:
the derivative index system generating module 101 is configured to obtain basic information of an electric power material provider, perform data cleaning on the basic information to obtain first basic information, perform indexing processing on the first basic information, and generate a derivative index system;
the supplier comprehensive evaluation model building module 102 is configured to build a supplier comprehensive evaluation model according to the derivative index system by using a preset analytic hierarchy process;
the comprehensive rating determination module 103 is configured to perform comprehensive evaluation on the power material supplier through the supplier comprehensive evaluation model to obtain a comprehensive rating, and extract an index tag in the derivative index system;
the supplier portrait generating module 104 is configured to generate a supplier portrait according to the comprehensive rating and the index tag, obtain an auxiliary evaluation of a preset purchasing part on the electric power material supplier according to the supplier portrait, and obtain a sampling inspection evaluation of a preset quality supervision part on the electric power material supplier according to the supplier portrait;
the final evaluation determining module 105 is configured to determine a final evaluation of the power material supplier according to the auxiliary evaluation, the spot check evaluation, and the comprehensive evaluation.
In detail, in the embodiment of the present invention, each module in the electric power material supplier evaluation apparatus 100 based on the user image adopts the same technical means as the electric power material supplier evaluation method based on the user image described in fig. 1 to 3, and can generate the same technical effect, which is not described herein again.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is only one logical functional division, and other divisions may be realized in practice.
The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
In addition, functional modules in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional module.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof.
The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference signs in the claims shall not be construed as limiting the claim concerned.
The embodiment of the application can acquire and process related data based on an artificial intelligence technology. Among them, artificial Intelligence (AI) is a theory, method, technique and application system that simulates, extends and expands human Intelligence using a digital computer or a machine controlled by a digital computer, senses the environment, acquires knowledge and uses the knowledge to obtain the best result.
Furthermore, it is obvious that the word "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. A plurality of units or means recited in the system claims may also be implemented by one unit or means in software or hardware. The terms first, second, etc. are used to denote names, but not any particular order.
Finally, it should be noted that the above embodiments are only intended to illustrate the technical solutions of the present invention and not to limit the same, and although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.
Claims (10)
1. A user portrait-based evaluation method for power material suppliers, which is characterized by comprising the following steps:
s1, acquiring basic information of an electric power material supplier, performing data cleaning on the basic information to obtain first basic information, and performing indexing processing on the first basic information to generate a derivative index system;
s2, constructing a supplier comprehensive evaluation model according to the derivative index system by using a preset analytic hierarchy process;
s3, comprehensively evaluating the electric power material supplier through the supplier comprehensive evaluation model to obtain a comprehensive rating, and extracting an index tag in the derivative index system, wherein the comprehensively evaluating the electric power material supplier through the supplier comprehensive evaluation model to obtain the comprehensive rating comprises the following steps:
s31, establishing index scores corresponding to the power material suppliers one by one according to indexes in the supplier comprehensive evaluation model through the analytic hierarchy process;
s32, calculating the comprehensive score of the power material supplier according to the index score and the index weight in the supplier comprehensive evaluation model by using the following scoring formula:
wherein ,
is a first
An electricityThe composite score of the force material provider,
is a first
The first electric power material supplier
The index score of each index is calculated,
comprehensively evaluating the supplier with the first one in the model
The weight of each index is calculated according to the index,
for the number of power supply suppliers,
is the index number;
s33, determining the comprehensive rating of the power material supplier according to the comprehensive rating;
s4, generating a supplier portrait according to the comprehensive rating and the index tag, acquiring auxiliary evaluation of a preset purchasing part on the electric power material supplier according to the supplier portrait, and acquiring a preset quality supervision part on the spot check evaluation of the electric power material supplier according to the supplier portrait;
and S5, determining the final evaluation of the electric power material supplier according to the auxiliary evaluation, the spot check evaluation and the comprehensive evaluation.
2. The user representation-based power supply evaluation method of claim 1, wherein the data cleaning of the basic information to obtain the first basic information comprises:
correcting the noise data in the basic information to obtain corrected noise data;
correcting the error data in the basic information to obtain corrected data;
filling missing data in the basic information to obtain filling data;
deleting redundant data in the basic information to obtain clean data;
the corrected noise data, the corrected data, the padding data, and the clean data are collected as the first basic information.
3. The user-portrait-based evaluation method for electric power material suppliers according to claim 1, wherein the indexing process of the first basic information to generate a derivative index system comprises:
carrying out data structural conversion on the first basic information to obtain structural data;
carrying out normalization processing on the structural data to obtain normalized data;
performing data fusion on the normalized data to obtain fused data;
generating a derivative index according to the fusion data by using a preset expression;
and collecting the fusion data and the derivative indexes into the derivative index system.
4. The user representation-based electric power material supplier evaluation method as claimed in claim 1, wherein the building of a supplier comprehensive evaluation model according to the derivative index system by using a preset analytic hierarchy process comprises:
constructing a judgment matrix of the derivative index system according to a preset weight matrix by utilizing the analytic hierarchy process;
calculating the geometric mean value of each row in the judgment matrix by using a preset sorting principle, wherein the sorting principle is as follows:
wherein ,
is the geometric mean value of the said geometric mean value,
is as follows
Go to the first
The matrix value corresponding to the column is,
is the matrix column number of the judgment matrix or the matrix row number of the judgment matrix,
is as follows
Go to the first
Matrix values corresponding to the columns;
calculating the index weight of each index in the derived index system according to the geometric mean by using the following weight formula:
wherein ,
as the first in the derivative index system
The weight of the index of each index,
is as follows
Geometric mean of the rows;
and determining whether the judgment matrix meets the consistency by using preset consistency, and generating the supplier comprehensive evaluation model according to the index weight when the judgment matrix meets the consistency.
5. The user-portrait-based evaluation method for electric power material suppliers of claim 4, wherein the constructing the judgment matrix of the derived index system according to the preset weight matrix comprises:
counting the number of indexes in the derivative index system;
generating the row and column number of the judgment matrix according to the index number;
comparing the importance of adjacent indexes in the derived index system one by using the importance scale in the weight matrix to obtain an index important value;
and adding the index important numerical values to the corresponding row and column numbers to generate the judgment matrix.
6. The user representation-based power supply evaluation method according to any one of claims 1 to 5, wherein the determining whether the determination matrix satisfies consistency with a preset consistency comprises:
calculating the maximum characteristic root of the judgment matrix;
calculating a consistency index of the judgment matrix according to the maximum feature root by a consistency index formula as follows:
wherein ,
in order to be the index of the consistency,
for the root of the largest feature,
the order of the judgment matrix is;
calculating the random consistency ratio of the judgment matrix according to the consistency index and a preset random consistency index by using a consistency ratio formula as follows:
wherein ,
in order to be said random consistency ratio,
in order to be an indicator of said consistency,
is the random consistency index;
and when the random consistency ratio is smaller than a preset consistency ratio threshold value, the judgment matrix meets the consistency.
7. The user representation-based electric power material supplier evaluation method of claim 1, wherein the generating a supplier representation from the composite rating and the indicator tag comprises:
carrying out vector conversion on the comprehensive rating to obtain a comprehensive vector;
performing vector conversion on each index tag to obtain a tag vector;
stitching the composite vector with all of the tag vectors into the vendor portrait.
8. The user representation-based power material provider evaluation method of claim 7, wherein said stitching the composite vector with all of the tag vectors into the provider representation comprises:
counting the label vector lengths of all vectors in the label vectors, and counting the comprehensive vector length of the comprehensive vector;
determining the maximum value of the label vector length and the comprehensive vector length as a target length;
extending the lengths of all the label vectors and the comprehensive vector to the target length;
and merging the column dimensions of all the label vectors with the extended lengths and the comprehensive vector to obtain the supplier portrait.
9. The user profile-based electric utility provider evaluation method of claim 1, wherein said determining a final evaluation of the electric utility provider based on the auxiliary evaluation, the spot check evaluation, and the composite rating comprises:
determining an auxiliary rating for the auxiliary rating, and determining a spot rating for the spot rating;
counting the grade numbers of the auxiliary rating, the spot inspection rating and the comprehensive rating;
and selecting the grade with the maximum grade number as the final evaluation of the electric power material supplier.
10. An electric power material supplier evaluation device based on user figures, characterized in that the device comprises:
the system comprises a derivative index system generating module, a data processing module and a data processing module, wherein the derivative index system generating module is used for acquiring basic information of an electric power material supplier, performing data cleaning on the basic information to obtain first basic information, and performing indexing processing on the first basic information to generate a derivative index system;
the supplier comprehensive evaluation model building module is used for building a supplier comprehensive evaluation model according to the derivative index system by utilizing a preset analytic hierarchy process;
the comprehensive rating determining module is used for comprehensively evaluating the power material supplier through the supplier comprehensive evaluation model to obtain a comprehensive rating and extracting an index tag in the derivative index system;
the supplier portrait generation module is used for generating a supplier portrait according to the comprehensive rating and the index tag, acquiring auxiliary evaluation of a preset purchasing part on the electric power material supplier according to the supplier portrait, and acquiring sampling inspection evaluation of a preset quality supervision part on the electric power material supplier according to the supplier portrait;
and the final evaluation determining module is used for determining the final evaluation of the power material supplier according to the auxiliary evaluation, the spot check evaluation and the comprehensive evaluation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310027854.8A CN115907308B (en) | 2023-01-09 | 2023-01-09 | Electric power material provider evaluation method and device based on user portrait |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310027854.8A CN115907308B (en) | 2023-01-09 | 2023-01-09 | Electric power material provider evaluation method and device based on user portrait |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115907308A true CN115907308A (en) | 2023-04-04 |
| CN115907308B CN115907308B (en) | 2023-05-12 |
Family
ID=85746713
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310027854.8A Active CN115907308B (en) | 2023-01-09 | 2023-01-09 | Electric power material provider evaluation method and device based on user portrait |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115907308B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2011048612A (en) * | 2009-08-27 | 2011-03-10 | Digitalcoast Inc | Decision making support system based on hierarchical analysis method and program for the system |
| CN108241932A (en) * | 2018-01-24 | 2018-07-03 | 国网山东省电力公司泰安供电公司 | A kind of method for building up of electricity provider evaluation model |
| CN109801002A (en) * | 2019-03-01 | 2019-05-24 | 国家电网有限公司 | O&M overhauls the transformer supplier comprehensive performance evaluation method under visual angle |
| CN113886372A (en) * | 2021-09-08 | 2022-01-04 | 天元大数据信用管理有限公司 | User portrait construction method based on improved analytic hierarchy process |
| CN114819618A (en) * | 2022-04-24 | 2022-07-29 | 谭翠萍 | Construction method of enterprise portrait model for assisting government investment decision |
| CN115330555A (en) * | 2022-07-13 | 2022-11-11 | 国网甘肃省电力公司电力科学研究院 | IES comprehensive benefit evaluation method based on digital portrait |
| CN115344767A (en) * | 2022-09-20 | 2022-11-15 | 国机陆原工程设计研究有限公司 | Supplier evaluation method based on network data |
| CN115358549A (en) * | 2022-08-04 | 2022-11-18 | 招银云创信息技术有限公司 | Method, apparatus, device, medium and program product for provider hologram creation |
-
2023
- 2023-01-09 CN CN202310027854.8A patent/CN115907308B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2011048612A (en) * | 2009-08-27 | 2011-03-10 | Digitalcoast Inc | Decision making support system based on hierarchical analysis method and program for the system |
| CN108241932A (en) * | 2018-01-24 | 2018-07-03 | 国网山东省电力公司泰安供电公司 | A kind of method for building up of electricity provider evaluation model |
| CN109801002A (en) * | 2019-03-01 | 2019-05-24 | 国家电网有限公司 | O&M overhauls the transformer supplier comprehensive performance evaluation method under visual angle |
| CN113886372A (en) * | 2021-09-08 | 2022-01-04 | 天元大数据信用管理有限公司 | User portrait construction method based on improved analytic hierarchy process |
| CN114819618A (en) * | 2022-04-24 | 2022-07-29 | 谭翠萍 | Construction method of enterprise portrait model for assisting government investment decision |
| CN115330555A (en) * | 2022-07-13 | 2022-11-11 | 国网甘肃省电力公司电力科学研究院 | IES comprehensive benefit evaluation method based on digital portrait |
| CN115358549A (en) * | 2022-08-04 | 2022-11-18 | 招银云创信息技术有限公司 | Method, apparatus, device, medium and program product for provider hologram creation |
| CN115344767A (en) * | 2022-09-20 | 2022-11-15 | 国机陆原工程设计研究有限公司 | Supplier evaluation method based on network data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115907308B (en) | 2023-05-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112199367B (en) | Long-time scale power balance check and big data analysis method and system | |
| CN112001626A (en) | Method for evaluating toughness of power distribution network in typhoon weather, storage medium and equipment | |
| CN106570778A (en) | Big data-based data integration and line loss analysis and calculation method | |
| CN105471647B (en) | A kind of power communication network fault positioning method | |
| CN103902816A (en) | Electrification detection data processing method based on data mining technology | |
| CN107665172A (en) | A kind of Software Defects Predict Methods based on complicated weighting software network | |
| CN114022005A (en) | BIM technology-based engineering cost management system and method | |
| CN111881124A (en) | Data processing method and system based on state estimation of improved algorithm | |
| CN111782538A (en) | Equipment testability demonstration analysis and simulation evaluation system | |
| CN107146166B (en) | Distribution network planning auxiliary system | |
| CN115907308A (en) | User portrait-based electric power material supplier evaluation method and device | |
| CN115759885B (en) | Material sampling inspection method and device based on distributed material supply | |
| CN111507078A (en) | Test report control method and system | |
| CN115660645A (en) | Method, device, equipment and storage medium for evaluating skills of maintenance personnel | |
| CN115827353A (en) | Fault diagnosis method and device | |
| CN112837177A (en) | Key component basic data source for electric energy metering equipment and quality evaluation method | |
| CN114139408A (en) | Power transformer health state assessment method | |
| CN115598459A (en) | Power failure prediction method for 10kV feeder line fault of power distribution network | |
| CN110399685A (en) | Capacitance type equipment defect rank prediction technique and device | |
| Zhao et al. | Identifying Root-Cause Changes for User-Reported Incidents in Online Service Systems | |
| US20240005259A1 (en) | Index modeling | |
| CN115796459B (en) | Low-voltage transformer area voltage quality analysis method and device based on multi-source data | |
| CN115809761B (en) | Voltage quality analysis method and system based on low-voltage transformer area | |
| CN116821829A (en) | Transformer fault analysis method and device based on association rule analysis | |
| Dai et al. | Transmission line condition assessment technology based on multi-source Parameter Fusion |
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 |