CN111754116A - Credit assessment method and device based on label portrait technology - Google Patents
Credit assessment method and device based on label portrait technology Download PDFInfo
- Publication number
- CN111754116A CN111754116A CN202010590439.XA CN202010590439A CN111754116A CN 111754116 A CN111754116 A CN 111754116A CN 202010590439 A CN202010590439 A CN 202010590439A CN 111754116 A CN111754116 A CN 111754116A
- Authority
- CN
- China
- Prior art keywords
- label
- fact
- model
- meaning
- enterprise
- 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
- 238000000034 method Methods 0.000 title claims abstract description 83
- 238000005516 engineering process Methods 0.000 title claims abstract description 45
- 239000002131 composite material Substances 0.000 claims abstract description 94
- 238000011156 evaluation Methods 0.000 claims abstract description 66
- 230000008569 process Effects 0.000 claims abstract description 34
- 238000004422 calculation algorithm Methods 0.000 claims description 38
- 230000006399 behavior Effects 0.000 claims description 8
- 238000011161 development Methods 0.000 claims description 7
- 150000001875 compounds Chemical class 0.000 claims description 5
- 238000012797 qualification Methods 0.000 claims description 5
- 230000004044 response Effects 0.000 claims description 5
- 238000005457 optimization Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 abstract description 7
- 238000011144 upstream manufacturing Methods 0.000 description 10
- 238000010248 power generation Methods 0.000 description 9
- 238000003860 storage Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 238000010276 construction Methods 0.000 description 6
- 230000005611 electricity Effects 0.000 description 5
- 230000008520 organization Effects 0.000 description 5
- 230000002265 prevention Effects 0.000 description 5
- 238000009826 distribution Methods 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 238000004064 recycling Methods 0.000 description 3
- 238000009825 accumulation Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000011084 recovery Methods 0.000 description 2
- 238000007621 cluster analysis Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000007670 refining Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/285—Selection of pattern recognition techniques, e.g. of classifiers in a multi-classifier system
-
- 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—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Educational Administration (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Artificial Intelligence (AREA)
- Tourism & Hospitality (AREA)
- Public Health (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Water Supply & Treatment (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a credit assessment method and a device based on a label portrait technology, wherein the method comprises the following steps: the method comprises the steps of determining the meaning of each fact label in a pre-established credit label system of an enterprise to be evaluated, generating the meaning of each model label and the meaning of each composite label of the enterprise to be evaluated according to a first corresponding relation between the pre-established fact label and the model label of the enterprise to be evaluated, a second corresponding relation between the pre-established model label and the composite label of the enterprise to be evaluated and the meaning of the fact label, and determining a credit portrait of the enterprise to be evaluated according to the meaning of the fact label, the meaning of the model label and the meaning of the composite label. The credit evaluation method realizes the perfect credit label system and clear calculation rule without depending on subjectivity in the process, thereby improving the accuracy of credit evaluation and forming the unified credit service capability.
Description
Technical Field
The embodiment of the invention relates to the technical field of credit assessment, in particular to a credit assessment method and device based on a label portrait technology.
Background
The enterprises related to interests of the upstream and downstream of the power industry comprise power generation enterprises, power selling companies, power consumers, suppliers and the like. In order to obtain the comprehensive strength and credit level of enterprises related to upstream and downstream benefits in the power industry, credit assessment needs to be performed on the enterprises related to the upstream and downstream benefits in the power industry.
At present, the credit evaluation is mainly performed through the business data and the like of the evaluated enterprise.
However, the evaluation rule of the above evaluation method is unclear and the subjectivity is strong, so that the accuracy of the existing credit evaluation method is low.
Disclosure of Invention
The invention provides a credit assessment method and device based on a label portrait technology, which aim to solve the technical problem of low credit assessment accuracy caused by unclear rules and strong subjectivity of the conventional credit assessment mode.
In a first aspect, an embodiment of the present invention provides a credit assessment method based on a tag portrait technology, including:
determining the meaning of each fact label in a pre-established credit label system of an enterprise to be evaluated;
generating the meaning of each model label and the meaning of each composite label of the enterprise to be evaluated according to a first corresponding relation between a pre-established fact label and a model label of the enterprise to be evaluated, a second corresponding relation between a pre-established model label and a composite label of the enterprise to be evaluated and the meanings of the fact labels;
and determining a credit portrait of the enterprise to be evaluated according to the meanings of the fact label, the model label and the compound label.
In a second aspect, an embodiment of the present invention further provides a credit evaluation apparatus based on a tag portrait technology, where the apparatus includes:
one or more processors;
a memory for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement a method of credit assessment based on tag portrait technology as provided in the first aspect.
In a third aspect, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements the credit evaluation method based on the tag portrait technology as provided in the first aspect.
The embodiment provides a credit assessment method and a device based on a label portrait technology, wherein the method comprises the following steps: the method comprises the steps of determining the meaning of each fact label in a pre-established credit label system of an enterprise to be evaluated, generating the meaning of each model label and the meaning of each composite label of the enterprise to be evaluated according to a first corresponding relation between the pre-established fact label and the model label of the enterprise to be evaluated, a second corresponding relation between the pre-established model label and the composite label of the enterprise to be evaluated and the meaning of the fact label, and determining a credit portrait of the enterprise to be evaluated according to the meaning of the fact label, the meaning of the model label and the meaning of the composite label. The credit portrait of the enterprise to be evaluated is determined through a credit label system of the enterprise to be evaluated, the credit evaluation of the enterprise to be evaluated is realized, and the credit label system is perfect, the calculation rule is clear and does not depend on subjectivity in the process, so that the accuracy of the credit evaluation is improved, and the unified credit service capability is formed.
Drawings
FIG. 1 is a flowchart illustrating a method for credit evaluation based on tag portrait technology according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart illustrating the determination of the meaning of a tag of a first model in a credit evaluation method based on tag representation technology according to an embodiment of the present invention;
FIG. 3 is a schematic flow chart illustrating the determination of the meaning of a second model tag in a credit evaluation method based on tag portrait technology according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a credit representation of an enterprise to be assessed, which is determined by a credit assessment method based on a tag representation technology according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of a credit evaluation apparatus based on tag portrait technology according to an embodiment of the present invention;
FIG. 6 is a schematic diagram of a credit evaluation device based on tag portrait technology according to another embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
FIG. 1 is a flowchart illustrating a method for credit evaluation based on tag portrait technology according to an embodiment of the present invention. The embodiment is suitable for a scene of credit assessment of enterprises related to upstream and downstream interests in the power industry. The embodiment may be implemented by a tag portrait technology-based credit evaluation apparatus, which may be implemented by software and/or hardware, and may be integrated into a computer device. As shown in fig. 1, the credit evaluation method based on the tag portrait technology provided in this embodiment includes the following steps:
step 101: the meaning of each fact tag in the pre-established credit tag hierarchy of the business under evaluation is determined.
Specifically, the credit assessment method based on the tag portrait technology provided by the embodiment can converge data resources of the power industry, apply the big data mining technology and the tag portrait technology, construct an enterprise credit tag library and an enterprise multidimensional credit portrait based on the data of the power industry in the whole service field, and provide the credit assessment method based on the tag portrait technology. The comprehensive strength and credit level of enterprises related to upstream and downstream interests in the power industry are accurately depicted through the enterprise credit portrait, and meanwhile, a unified power credit access, convergence and sharing access and exit is formed at the national network headquarters level, so that more convenient power credit capability support is provided for departments, units of the base level, governments at all levels and all circles of the society of the company.
The enterprise to be evaluated in this embodiment may be an enterprise related to interests in the upstream and downstream of the power industry, for example, a power generation enterprise, a power selling company, a power consumer, a supplier, and other market entities. In the present embodiment, a plurality of power generation enterprises are referred to as the same type of enterprise, a plurality of power selling companies are referred to as the same type of enterprise, a plurality of power consumers are referred to as the same type of enterprise, and a plurality of suppliers are referred to as the same type of enterprise.
Optionally, before step 101, the method further includes: and establishing a credit label system of the enterprise to be evaluated. Wherein, the credit label system includes: primary dimension, secondary dimension, fact label, model label, and composite label. The first-level dimensionality corresponds to at least one second-level dimensionality, the second-level dimensionality corresponds to at least one fact label, the model labels correspond to at least two fact labels, and the composite labels correspond to at least two model labels. The fact label may also be referred to as a tertiary indicator.
In one implementation, the primary dimension includes at least one of: enterprise speciality, performance ability, performance, risk behavior, and development trend. The second dimension is further refined on the basis of the first dimension.
The secondary dimensions include at least one of: basic information, enterprise qualification, internal evaluation, business capability, business level, technical level, capital guarantee, fulfillment response, quality of service, product quality, fulfillment evaluation, factual risk, potential risk, market environment, and enterprise potential. More specifically, the secondary dimensions corresponding to the enterprise trait include at least one of: basic information, enterprise qualification, internal evaluation; the secondary dimension corresponding to the performance capability comprises at least one of the following: business capacity, business level, technical level and capital guarantee; the secondary dimension corresponding to the performance includes at least one of the following: performing response, service quality, product quality and performing evaluation; the secondary dimension corresponding to the risk behavior comprises at least one of the following: factual risk, potential risk; the secondary dimension corresponding to the development trend comprises at least one of the following: market environment, enterprise potential.
The three-level indexes are comprehensively analyzed and designed from the first-level dimension and the second-level dimension to form 264 aspects of enterprise properties, stockholder types, total annual production values, near two-year bid amount, agent user amount, accumulated bid amount, supply timeliness rate, equipment failure rate, total historical bad account amount, historical electricity stealing frequency, electricity utilization accident records, potential safety hazard information, the overall trend of industrial electricity consumption, the trend of enterprise signing contract amount and the like. The tertiary metrics for each type of business include at least one of the 264 tertiary metrics.
In the embodiment, a credit label system covering enterprises related to upstream and downstream benefits of the power industry can be designed and constructed according to data resource accumulation of the national power grid company in the business fields of electricity utilization marketing, power transaction, material purchasing, safety production and the like and by combining the internal and external credit construction requirements of the power industry.
Examples of the first, second, and third level metrics in the credit label hierarchy for each market entity are described in detail below.
TABLE 1 example tables of first, second and third level indices in a Power Generation Enterprise Credit Label System
Table 2 example table of first-level dimension, second-level dimension and third-level index in credit label system of power selling company
Table 3 example table of first-level dimension, second-level dimension and third-level index in power consumer credit label system
Table 4 example tables of first, second and third level metrics in a supplier credit label system
In the specific execution of step 101, when the first fact tag in the fact tags has a clear business rule or source data meaning, the meaning of the first fact tag is determined according to the business rule or the source data meaning.
For convenience of description, a fact tag having a definite business rule or meaning of source data is referred to as a first fact tag. Taking the first fact label "organization type" as an example for explanation, the relationship between the organization type and the organization code is clear and objective, so the fact label "organization type" has clear business rules or source data meaning, and the meaning of the first fact label is determined according to the business rules or the source data meaning. For example, when the fact tag is 910, the organization type is determined to be a civil non-business entity.
And when the second fact label in the fact labels does not have an explicit business rule or source data meaning, discretizing the second fact labels of a plurality of enterprises belonging to the same type as the enterprise to be evaluated, and determining the meaning of the second fact label according to the section where the second fact label of the enterprise to be evaluated is located in the plurality of discretized sections.
For convenience of description, a fact tag having no explicit business rule or meaning of source data is referred to as a second fact tag. The second fact label "total installed capacity" is taken as an example for explanation. The total installed capacity of the enterprise to be evaluated is a specific numerical value, and the capability of the total installed capacity of the enterprise to be evaluated in the total installed capacities of all enterprises of the same type cannot be described according to the specific numerical value. Therefore, in order to determine the meaning of the specific numerical value, discretization is performed on the second fact tags of a plurality of enterprises belonging to the same type as the enterprise to be evaluated, that is, the total installed capacity of the plurality of power generation enterprises is discretized, for example, by mapping, or statistical quantity test-determining a discrete or concentrated distribution trend, discretization is performed on the total installed capacity, for example, the total installed capacity is divided into a plurality of sections, for example, 4 sections, and the meaning of the total installed capacity of the enterprise to be evaluated is determined according to the section where the total installed capacity of the enterprise to be evaluated is located in the plurality of discretized sections. Assuming that the total installed capacity of the enterprise to be evaluated is in the third interval, it can be determined that the total installed capacity of the enterprise to be evaluated is higher.
Step 102: and generating the meaning of each model label and the meaning of each composite label of the enterprise to be evaluated according to the first corresponding relation between the pre-established fact labels and the model labels of the enterprise to be evaluated, the second corresponding relation between the pre-established model labels and the composite labels of the enterprise to be evaluated and the meanings of the fact labels.
Specifically, when a credit tag system is constructed, 264 fact tags are constructed according to the basic or behavior data distribution, the business rules and the source data meanings of various market main bodies in the aspects of user basic information, electricity payment arrearage, material purchasing, contract signing, bid inviting, safe production and the like. Constructing a model through algorithms such as comprehensive weight, cluster analysis and the like according to the fact labels and the processed basic or behavior data of the features to obtain a plurality of model labels; and according to the service analysis dimension emphasis point, clustering or fusing the model labels to obtain a plurality of composite labels. For example, in this embodiment, the number of model tags obtained for all market entities is 34, and the number of composite tags obtained for all market entities is 15.
Therefore, the credit label system of the enterprise to be evaluated in the embodiment is composed of a fact label, a model label and a composite label, wherein the type of the label is 3. In the system design, the credit evaluation system is formed by combining the accumulation of the annual credit construction results of national grid companies, combing the credit evaluation rules of the whole service field of the power industry such as safety, production, marketing, scheduling, material and transaction one by one on the basis of the credit identification standard of the power field by referring to the organizations such as state courtyards, national energy bureaus, middle and electric couplings, and combining the related requirements of internal and external credit evaluation and being guided by the experts in the external credit field and the experts in the internal service of the power. The constructed index system has the characteristics of specialty, authority, objectivity and the like.
The fact label and the model label of the enterprise to be evaluated have a first corresponding relation, and the model label and the composite label of the enterprise to be evaluated have a second corresponding relation. For example, a composite tag-generation credit level, may correspond to 4 model tags: comprehensive power generation capacity, transaction performance, contract performance and development trend. Based on the meaning of the fact label determined in step 101, the meaning of the model label may be determined according to the first corresponding relationship and the meaning of the fact label, and the meaning of the composite label may be determined according to the second corresponding relationship and the meaning of the model label.
In principle, the model label and the composite label are obtained by fusing and refining objective data information, and the meanings of the model label and the composite label are determined by adopting an unsupervised algorithm (such as clustering, dimension reduction and the like) conventionally. And determining the meanings of the model label and the composite label based on the following principles in consideration of the operation and maintenance cost, the time cost and the rationality of the construction method of the model label and the composite label.
When the fact labels corresponding to the first model labels in the model labels are determined to be larger than the preset label number according to the first corresponding relation, determining the meaning of the first model labels by combining a Self-organizing mapping (SOM) algorithm and a K-means algorithm;
when the number of fact labels corresponding to a second model label in the model labels is determined to be less than or equal to the number of preset labels according to the first corresponding relation, combining an analytic hierarchy process, an entropy weight process and the minimum relative information entropy to determine the meaning of the second model label;
when the number of the model labels corresponding to the first composite label in the composite labels is larger than the preset label number according to the second corresponding relation, determining the meaning of the first composite label by combining an SOM algorithm and a K-means algorithm;
and when the number of the model labels corresponding to the second composite label in the composite labels is determined to be less than or equal to the preset label number according to the second corresponding relation, combining an analytic hierarchy process, an entropy weight process and the minimum relative information entropy to determine the meaning of the second composite label.
Illustratively, the preset number of tags may be 5. For convenience of description, in this embodiment, the model tags whose number of corresponding fact tags is greater than the preset number of tags are referred to as a first model tag, the model tags whose number of corresponding fact tags is less than or equal to the preset number of tags are referred to as a second model tag, the composite tags whose number of corresponding model tags is greater than the preset number of tags are referred to as a first composite tag, and the composite tags whose number of corresponding model tags is less than or equal to the preset number of tags are referred to as a second composite tag.
That is, the model labels or composite labels related to the number of the lower layer label types of 5 or less are classified by the comprehensive weight classification method, and the model labels or composite labels related to the number of the lower layer label types of 5 or more are classified by two stages, so that the method has certain practicability and advancement.
FIG. 2 is a schematic flow chart illustrating the process of determining the meaning of a tag of a first model in a credit evaluation method based on tag portrait technology according to an embodiment of the present invention. As shown in fig. 2, the process of determining the meaning of the first model tag includes the steps of:
step 201: and roughly clustering a data set formed by scores of the fact labels corresponding to the first model labels of a plurality of enterprises of the same type with the enterprise to be evaluated by an SOM algorithm to obtain the number of the preliminarily divided groups.
Step 202: and determining the average value of the data set consisting of the scores of the fact labels corresponding to the first model labels of the plurality of enterprises of which the enterprises to be evaluated belong to the same type.
Wherein the score of the fact tag is determined according to the meaning of the fact tag.
The fact labels related to the first model label can be constructed, scoring processing is carried out according to discretized values of the fact labels, the full score is 100, the minimum score is 0, and the score is determined according to actual requirements in the scoring interval.
For example, assuming that the enterprise to be evaluated is a power generation enterprise, the average value of the data set composed of the scores of the fact tags corresponding to the first model tags of a plurality of power generation enterprises may be determined.
Step 203: and assigning the cluster number to an initial value of a K-means algorithm, selecting a data point which is close to the average value of the data set in the data set as a central point, and clustering the data set by using the K-means algorithm to obtain the finally determined class number and each class of the first model label division of a plurality of enterprises which belong to the same type as the enterprise to be evaluated.
Step 204: and determining the meaning of the first model label according to the number of the classes and the class to which the first model label of the enterprise to be evaluated belongs.
For example, assuming that the number of divided classes is 4 and the contract performance of the enterprise to be evaluated belongs to a third class, the first model tags of a plurality of enterprises belonging to the same type as the enterprise to be evaluated, such as the contract performance, may determine that the meaning of the contract performance of the enterprise to be evaluated is that the contract performance is high.
Step 201-step 204 are processes for determining the meaning of the tag by means of two-segment clustering. By SOM + K-means two-stage clustering analysis, on one hand, the problems of long SOM network training time and multiple iteration times of the K-means algorithm are solved, and the operation efficiency of the algorithm is optimized; on the other hand, the SOM network eliminates the influence of noise points and isolated points on the K-means algorithm, solves the problem that the initial value of the K-means algorithm is difficult to select, and the K-means algorithm enables the SOM division result to be more accurate. Thus, the method can provide the accuracy of the determined meaning of the label, and further, the accuracy of credit assessment is improved.
In determining the meaning of the first composite label, the implementation process and technical principles are similar to steps 201-204. The specific process is as follows: roughly clustering a data set formed by scores of model labels corresponding to first composite labels of a plurality of enterprises belonging to the same type with the enterprise to be evaluated through an SOM algorithm to obtain the number of preliminarily divided groups, wherein the scores of the model labels are determined according to the meaning of the model labels; determining an average value of a data set consisting of scores of model labels corresponding to first composite labels of a plurality of enterprises of the same type with the enterprise to be evaluated; assigning the cluster number to an initial value of a K-means algorithm, selecting a data point which is close to the average value of a data set in the data set as a central point, and clustering the data set by using the K-means algorithm to obtain the finally determined class number and each class of the first composite label division of a plurality of enterprises which belong to the same type as the enterprise to be evaluated; and determining the meaning of the first composite label according to the number of the classes and the class to which the first composite label of the enterprise to be evaluated belongs.
FIG. 3 is a schematic flow chart illustrating the process of determining the meaning of a second model tag in a credit evaluation method based on tag portrait technology according to an embodiment of the present invention. As shown in fig. 3, the process of determining the meaning of the second model tag includes the steps of:
step 301: and determining the subjective weight of each fact label corresponding to the second model label according to an analytic hierarchy process.
Step 302: and determining the objective weight of each fact label corresponding to the second model label according to an entropy weight method.
Step 303: by the formula
A composite weight for each fact tag corresponding to the second model tag is determined.
Wherein, wiRepresents the composite weight, x, of the ith fact label corresponding to the second model labeliIs the subjective weight, u, of the ith fact label corresponding to the second model labeliThe objective weight of the ith fact label corresponding to the second model label is obtained, n is a preset optimization factor, and m is the total number of the fact labels corresponding to the second model label. The range of n is 0-1, and the value is generally 0.5.
The formula in step 303 is a specific implementation manner for determining the comprehensive weight through the minimum relative entropy. The comprehensive weight is determined through the minimum relative information entropy, the credit index service attribute is considered, and the index value data distribution characteristics are considered, so that the accuracy of the determined label meaning is improved, and further, the accuracy of credit evaluation is improved.
Step 304: and determining the meaning of the second model label according to the sum of the comprehensive values of all the fact labels corresponding to the second model label.
Wherein the integrated value of each fact tag is a product of the integrated weight of the fact tag and a score determined according to the meaning of the fact tag.
The process of determining the score according to the meaning of the fact label is similar to that in step 202, and is not described herein again.
In step 304, the total score is divided by a ranking method according to the sum of the comprehensive values of all the fact labels corresponding to the second model labels and the score ranking condition of the second model labels of all the market subjects, and the number of the divided types is determined. And then determining the meaning of the second model label of the enterprise to be evaluated based on the position of the second model label of the enterprise to be evaluated.
In determining the meaning of the second composite label, the implementation process and technical principles are similar to steps 301-304. The specific process is as follows: determining the subjective weight of each model label corresponding to the second composite label according to an analytic hierarchy process; determining the objective weight of each model label corresponding to the second composite label according to an entropy weight method; by the formula
Determining the comprehensive weight of each model label corresponding to the second composite label; wherein, w'jRepresents the composite weight, x 'of the jth model label corresponding to the second composite label'jIs the subjective weight, u 'of the jth model label corresponding to the second composite label'jThe objective weight of the jth model label corresponding to the second composite label is obtained, n is a preset optimization factor, and m' is the total number of the model labels corresponding to the second composite label; and determining the meaning of the second composite label according to the sum of the comprehensive values of all the model labels corresponding to the second composite label, wherein the comprehensive value of each model label is the product of the comprehensive weight of the model label and the score determined according to the meaning of the model label.
After the meaning of the model label is determined, when the meaning of the composite label is determined, the model label related to the composite label is constructed, grading is carried out according to the classified types of the model label, the full score is 100, the minimum score is 0, and the score is determined among the sections according to actual requirements.
The implementation processes of step 101 and step 102 can be dynamically optimized in terms of index number, calculation rules, algorithm models, and the like, and are continuously improved according to actual business requirements and application effects.
Step 103: and determining the credit portrait of the enterprise to be evaluated according to the meanings of the fact tags, the model tags and the compound tags.
Specifically, the credit representation of the enterprise to be evaluated comprises: a credit panorama image and a credit scene image.
The credit panorama portrait is around all business activities of the market subject, and the characteristics of the credit panorama portrait are comprehensively and comprehensively described by using all tags.
The credit scene image is an electric charge recovery risk prevention and control scene for selecting a part of labels with strong correlation with a service scene to describe the characteristics of the specific service scene, emphasizing on showing the concerned content of the service scene, such as labels for selecting default power consumption grade, arrearage grade, payment mode and the like, and using the labels for predicting the arrearage risk level of a power consumer.
The credit scene picture comprises: and (3) by combining credit evaluation requirements of industry internal and external specific business scenes such as supplier evaluation, electric charge recovery risk prevention and control, enterprise internal credit system construction, trading market subject credit evaluation, financial wind control client credit evaluation and the like, determining market subject characteristics of enterprises related to upstream and downstream benefits of the power industry, and determining rules, algorithms and contents of label portrayal.
When the credit portrait of the enterprise to be evaluated is a credit scene portrait, the step 103 is implemented as follows:
selecting a target fact label, a target model label and a target composite label related to a preset service scene from a fact label, a model label and a composite label corresponding to an enterprise to be evaluated; and generating a credit scene image corresponding to the advanced business scene of the enterprise to be evaluated according to the meaning of the target fact label, the meaning of the target model label and the meaning of the target composite label.
Based on an enterprise credit label library, combining with the clear concept and type of the business portrait, through the technologies and methods of label screening, feature calculation, portrait generation, portrait visualization and the like, the corresponding enterprise credit portrait is quickly constructed, the credit level and the comprehensive strength of the enterprise are objectively reflected, credit evaluation aiming at enterprises related to the upstream and downstream benefits of power industries such as power generation, power selling, power utilization, suppliers and the like is developed, and business scene applications such as credit evaluation of power transaction main bodies, prevention and control of power charge recycling risks, evaluation of suppliers, credit evaluation of financial wind-controlled customers and the like are supported. When the method is applied to scenes such as electric charge recycling risk prevention and control, supplier evaluation, financial wind control client credit evaluation and the like, the method can directly refer to details and portrait reports of enterprise credit portraits of related market subjects, check comprehensive credit levels of the enterprise credit portraits and support business scene credit evaluation requirements.
Fig. 4 is a schematic diagram of a credit portrait of an enterprise to be assessed determined by a credit assessment method based on a tag portrait technology according to an embodiment of the present invention. As shown in fig. 4, a schematic diagram of a credit image of a certain power plant is shown.
The enterprise credit label library related in the embodiment is a fact label, a model label and a compound label in a credit label system of an enterprise.
The invention firstly and comprehensively constructs a credit label system aiming at enterprises related to upstream and downstream interests in the power industry, generates a credit scene portrait, provides a certain practical theoretical basis, is beneficial to ensuring the integrity and scientificity of the top-level design of the label portrait technology, and supports the rapid construction and application of business application scenes such as credit evaluation of power transaction main bodies, risk prevention and control of electric charge recycling, supplier evaluation, credit evaluation of financial wind-controlled customers and the like.
More importantly, aiming at the fact label, the invention provides a calculation rule defined according to the label index value data distribution, the business rule and the source data meaning. Aiming at the construction of a model label and a composite label, two algorithm implementation modes of comprehensive weight division and two-section clustering are provided. The invention provides a label calculation rule method which is beneficial to ensuring the reasonability and low cost of the practical application of the portrait technology.
The credit evaluation method based on the label portrait technology provided by the embodiment comprises the following steps: the method comprises the steps of determining the meaning of each fact label in a pre-established credit label system of an enterprise to be evaluated, generating the meaning of each model label and the meaning of each composite label of the enterprise to be evaluated according to a first corresponding relation between the pre-established fact label and the model label of the enterprise to be evaluated, a second corresponding relation between the pre-established model label and the composite label of the enterprise to be evaluated and the meanings of the fact labels, and determining a credit portrait of the enterprise to be evaluated according to the meanings of the fact labels, the meanings of the model labels and the meanings of the composite labels. The credit portrait of the enterprise to be evaluated is determined through a credit label system of the enterprise to be evaluated, the credit evaluation of the enterprise to be evaluated is realized, and the credit label system is perfect, the calculation rule is clear and does not depend on subjectivity in the process, so that the accuracy of the credit evaluation is improved, and the unified credit service capability is formed.
FIG. 5 is a schematic diagram of a credit evaluation apparatus based on tag portrait technology according to an embodiment of the present invention. As shown in fig. 5, the credit evaluation apparatus based on the tag portrait technology provided by this embodiment includes: a first determining module 51, a second determining module 52 and a third determining module 53.
A first determining module 51, configured to determine the meaning of each fact tag in a pre-established credit tag hierarchy of the enterprise to be evaluated.
Optionally, the first determining module 51 is specifically configured to: when a first fact tag in the fact tags has a clear business rule or source data meaning, determining the meaning of the first fact tag according to the business rule or the source data meaning; and when the second fact label in the fact labels does not have an explicit business rule or source data meaning, discretizing the second fact labels of a plurality of enterprises belonging to the same type as the enterprise to be evaluated, and determining the meaning of the second fact label according to the section where the second fact label of the enterprise to be evaluated is located in the plurality of discretized sections.
The second determining module 52 is configured to generate a meaning of each model tag and a meaning of each composite tag of the enterprise to be evaluated according to the first corresponding relationship between the pre-established fact tags and the model tags of the enterprise to be evaluated, the second corresponding relationship between the pre-established model tags and the composite tags of the enterprise to be evaluated, and the meanings of the fact tags.
Optionally, the second determining module 52 is specifically configured to:
when the fact labels corresponding to the first model labels in the model labels are determined to be larger than the preset label number according to the first corresponding relation, determining the meaning of the first model labels by combining an SOM algorithm and a K-means algorithm;
when the number of fact labels corresponding to a second model label in the model labels is determined to be less than or equal to the number of preset labels according to the first corresponding relation, combining an analytic hierarchy process, an entropy weight process and the minimum relative information entropy to determine the meaning of the second model label;
when the number of the model labels corresponding to the first composite label in the composite labels is larger than the preset label number according to the second corresponding relation, determining the meaning of the first composite label by combining an SOM algorithm and a K-means algorithm;
and when the number of the model labels corresponding to the second composite label in the composite labels is determined to be less than or equal to the preset label number according to the second corresponding relation, combining an analytic hierarchy process, an entropy weight process and the minimum relative information entropy to determine the meaning of the second composite label.
In determining the meaning of the first model label in combination with the SOM algorithm and the K-means algorithm, the second determining module 52 is specifically configured to:
roughly clustering a data set formed by scores of fact labels corresponding to first model labels of a plurality of enterprises of the same type with the enterprise to be evaluated through an SOM algorithm to obtain the number of preliminarily divided groups; wherein the score of the fact label is determined according to the meaning of the fact label;
determining an average value of a data set consisting of scores of fact labels corresponding to first model labels of a plurality of enterprises of the same type with the enterprise to be evaluated;
assigning the cluster number to an initial value of a K-means algorithm, selecting data points in a data set close to the average value of the data set as central points, and clustering by using the data set of the K-means algorithm to obtain the number of classes and each class of the first model label division of a plurality of enterprises which belong to the same type as the enterprise to be evaluated and are finally determined;
and determining the meaning of the first model label according to the number of the classes and the class to which the first model label of the enterprise to be evaluated belongs.
In determining the meaning of the second model label in combination with the analytic hierarchy process, the entropy weight process, and the minimum relative entropy, the second determining module 52 is specifically configured to:
determining the subjective weight of each fact label corresponding to the second model label according to an analytic hierarchy process;
determining the objective weight of each fact label corresponding to the second model label according to an entropy weight method;
by the formula
Determining the comprehensive weight of each fact label corresponding to the second model label; wherein, wiRepresenting the ith fact label corresponding to the second model labelComposite weight of label, xiIs the subjective weight, u, of the ith fact label corresponding to the second model labeliThe objective weight of the ith fact label corresponding to the second model label is obtained, n is a preset optimization factor, and m is the total number of the fact labels corresponding to the second model label;
determining the meaning of the second model label according to the sum of the comprehensive values of all the fact labels corresponding to the second model label; wherein the integrated value of each fact tag is a product of the integrated weight of the fact tag and a score determined according to the meaning of the fact tag.
And the third determining module 53 is used for determining the credit portrait of the enterprise to be evaluated according to the meaning of the fact label, the meaning of the model label and the meaning of the composite label.
Optionally, the apparatus further comprises: and the establishing module is used for establishing a credit label system of the enterprise to be evaluated. Wherein, the credit label system includes: the system comprises a first-level dimension, a second-level dimension, fact labels, model labels and composite labels, wherein the first-level dimension corresponds to at least one second-level dimension, the second-level dimension corresponds to at least one fact label, the model labels correspond to at least two fact labels, and the composite labels correspond to at least two model labels.
In one implementation, the primary dimension includes at least one of: enterprise speciality, performance ability, performance, risk behavior, and development trend.
The secondary dimensions include at least one of: basic information, enterprise qualification, internal evaluation, business capability, business level, technical level, capital guarantee, fulfillment response, quality of service, product quality, fulfillment evaluation, factual risk, potential risk, market environment, and enterprise potential. More specifically, the secondary dimensions corresponding to the enterprise trait include at least one of: basic information, enterprise qualification, internal evaluation; the secondary dimension corresponding to the performance capability comprises at least one of the following: business capacity, business level, technical level and capital guarantee; the secondary dimension corresponding to the performance includes at least one of the following: performing response, service quality, product quality and performing evaluation; the secondary dimension corresponding to the risk behavior comprises at least one of the following: factual risk, potential risk; the secondary dimension corresponding to the development trend comprises at least one of the following: market environment, enterprise potential.
Optionally, the credit representation of the enterprise to be evaluated comprises: a credit panorama image and a credit scene image.
When the credit portrait of the enterprise to be evaluated is a credit scene portrait, the third determining module 53 is specifically configured to: selecting a target fact label, a target model label and a target composite label related to a preset service scene from a fact label, a model label and a composite label corresponding to an enterprise to be evaluated; and generating a credit scene image corresponding to the advanced business scene of the enterprise to be evaluated according to the meaning of the target fact label, the meaning of the target model label and the meaning of the target composite label.
The credit evaluation device based on the label portrait technology provided by the embodiment of the invention can execute the credit evaluation method based on the label portrait technology provided by any embodiment of the invention, and has corresponding functional modules and beneficial effects of the execution method.
FIG. 6 is a schematic diagram of a credit evaluation device based on tag portrait technology according to another embodiment of the present invention. As shown in fig. 6, the apparatus comprises a processor 60 and a memory 61. The number of the processors 60 in the device may be one or more, and one processor 60 is taken as an example in fig. 6; the processor 60 and the memory 61 of the device may be connected by a bus or other means, as exemplified by the bus connection in fig. 6.
The memory 61 may be used as a computer-readable storage medium for storing software programs, computer-executable programs, and modules, such as program instructions and modules corresponding to the tag portrait technology-based credit evaluation method in the embodiment of the present invention (for example, the first determination module 51, the second determination module 52, and the third determination module 53 in the tag portrait technology-based credit evaluation apparatus). Processor 60 implements the above described tag representation technology based credit assessment method by running software programs, instructions and modules stored in memory 61 to execute various functional applications of the device and tag representation technology based credit assessment.
The memory 61 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the device, and the like. Further, the memory 61 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some embodiments, the memory 61 may further include memory located remotely from the processor 60, which may be connected to the device over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The present invention also provides a storage medium containing computer-executable instructions which, when executed by a computer processor, perform a method of credit assessment based on tag portrayal techniques, the method comprising:
determining the meaning of each fact label in a pre-established credit label system of an enterprise to be evaluated;
generating the meaning of each model label and the meaning of each composite label of the enterprise to be evaluated according to a first corresponding relation between a pre-established fact label and a model label of the enterprise to be evaluated, a second corresponding relation between a pre-established model label and a composite label of the enterprise to be evaluated and the meanings of the fact labels;
and determining a credit portrait of the enterprise to be evaluated according to the meanings of the fact label, the model label and the compound label.
Of course, the embodiments of the present invention provide a storage medium containing computer-executable instructions, which are not limited to the operations of the method described above, but may also perform related operations in the tag portrait technology-based credit evaluation method provided in any embodiments of the present invention.
From the above description of the embodiments, it is obvious for those skilled in the art that the present invention can be implemented by software and necessary general hardware, and certainly, can also be implemented by hardware, but the former is a better embodiment in many cases. Based on such understanding, the technical solution of the present invention or portions thereof that contribute to the prior art may be embodied in the form of a software product, where the computer software product may be stored in a computer-readable storage medium, such as a floppy disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a FLASH Memory (FLASH), a hard disk, or an optical disk of a computer, and includes several instructions for enabling a device (which may be a personal computer or a network device, etc.) to execute the credit evaluation method based on the tag portrait technology according to the embodiments of the present invention.
It should be noted that, in the embodiment of the credit evaluation apparatus based on the tag portrait technology, the included units and modules are only divided according to the functional logic, but not limited to the above division, as long as the corresponding functions can be realized; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (10)
1. A credit assessment method based on a label portrait technology is characterized by comprising the following steps:
determining the meaning of each fact label in a pre-established credit label system of an enterprise to be evaluated;
generating the meaning of each model label and the meaning of each composite label of the enterprise to be evaluated according to a first corresponding relation between a pre-established fact label and a model label of the enterprise to be evaluated, a second corresponding relation between a pre-established model label and a composite label of the enterprise to be evaluated and the meanings of the fact labels;
and determining a credit portrait of the enterprise to be evaluated according to the meanings of the fact label, the model label and the compound label.
2. The method of claim 1, wherein prior to determining the meaning of each fact tag in a pre-established credit tag hierarchy for a business under evaluation, the method further comprises:
establishing a credit label system of the enterprise to be evaluated; wherein the credit label system comprises: the system comprises a first-level dimension, a second-level dimension, fact labels, model labels and composite labels, wherein the first-level dimension corresponds to at least one second-level dimension, the second-level dimension corresponds to at least one fact label, the model labels correspond to at least two fact labels, and the composite labels correspond to at least two model labels.
3. The method of claim 2, wherein the primary dimension comprises at least one of: enterprise speciality, performance ability, performance, risk behavior, and development trend;
wherein, the secondary dimension corresponding to the enterprise speciality comprises at least one of the following items: basic information, enterprise qualification, internal evaluation;
the secondary dimension corresponding to the performance capability comprises at least one of the following: business capacity, business level, technical level and capital guarantee;
the secondary dimension corresponding to the performance includes at least one of the following: performing response, service quality, product quality and performing evaluation;
the secondary dimension corresponding to the risk behavior comprises at least one of the following: factual risk, potential risk;
the secondary dimension corresponding to the development trend comprises at least one of the following: market environment, enterprise potential.
4. The method of any of claims 1-3, wherein determining the meaning of each fact tag in a pre-established credit tag hierarchy for the business under evaluation comprises:
when a first fact tag in the fact tags has a clear business rule or source data meaning, determining the meaning of the first fact tag according to the business rule or the source data meaning;
when a second fact label in the fact labels does not have an explicit business rule or source data meaning, discretizing the second fact labels of a plurality of enterprises belonging to the same type as the enterprise to be evaluated, and determining the meaning of the second fact label according to the section where the second fact label of the enterprise to be evaluated is located in the plurality of discretized sections.
5. The method according to any one of claims 1 to 3, wherein the generating the meaning of each model label and the meaning of each composite label of the enterprise to be evaluated according to the first corresponding relationship between the pre-established fact label and the model label of the enterprise to be evaluated, the second corresponding relationship between the pre-established model label and the composite label of the enterprise to be evaluated and the meaning of the fact label comprises:
when the fact labels corresponding to the first model labels in the model labels are determined to be more than the number of preset labels according to the first corresponding relation, determining the meaning of the first model labels by combining a self-organizing map (SOM) algorithm and a K-means algorithm;
when the number of fact labels corresponding to a second model label in the model labels is determined to be less than or equal to the preset label number according to the first corresponding relation, combining an analytic hierarchy process, an entropy weight process and a minimum relative information entropy to determine the meaning of the second model label;
when the number of the model labels corresponding to the first composite label in the composite labels is larger than the preset label number according to the second corresponding relation, determining the meaning of the first composite label by combining an SOM algorithm and a K-means algorithm;
and when the number of the model labels corresponding to the second composite label in the composite labels is determined to be less than or equal to the preset label number according to the second corresponding relation, combining an analytic hierarchy process, an entropy weight process and the minimum relative information entropy to determine the meaning of the second composite label.
6. The method of claim 5, wherein determining the meaning of the first model label in combination with a SOM algorithm and a K-means algorithm comprises:
roughly clustering a data set formed by scores of fact labels corresponding to first model labels of a plurality of enterprises of the same type with the enterprise to be evaluated through an SOM algorithm to obtain the number of preliminarily divided groups; wherein the score of the fact tag is determined according to the meaning of the fact tag;
determining an average value of a data set consisting of scores of fact labels corresponding to first model labels of a plurality of enterprises of the same type with the enterprise to be evaluated;
assigning the cluster number to an initial value of a K-means algorithm, selecting a data point which is close to the average value of the data set in the data set as a central point, and clustering the data set by using the K-means algorithm to obtain the finally determined number of classes and each class of the first model label division of a plurality of enterprises which belong to the same type as the enterprise to be evaluated;
and determining the meaning of the first model label according to the number of the classes and the class to which the first model label of the enterprise to be evaluated belongs.
7. The method of claim 5, wherein determining the meaning of the second model label in combination with the analytic hierarchy process, the entropy weight process, and the minimum relative entropy comprises:
determining the subjective weight of each fact label corresponding to the second model label according to an analytic hierarchy process;
determining the objective weight of each fact label corresponding to the second model label according to an entropy weight method;
by the formula
Determining the comprehensive weight of each fact label corresponding to the second model label; wherein, wiRepresents the integrated weight, x, of the ith fact label corresponding to the second model labeliIs the subjective weight, u, of the ith fact label corresponding to the second model labeliThe objective weight of the ith fact label corresponding to the second model label is obtained, n is a preset optimization factor, and m is the total number of the fact labels corresponding to the second model label;
determining the meaning of a second model label according to the sum of the comprehensive values of all fact labels corresponding to the second model label; wherein the integrated value of each fact tag is a product of the integrated weight of the fact tag and a score determined according to the meaning of the fact tag.
8. The method of any of claims 1-3, wherein the representation of credit for the business under evaluation comprises: a credit panorama image and a credit scene image.
9. The method of claim 8, wherein when the representation of credit for the enterprise to be assessed is a representation of a credit scene, said determining the representation of credit for the enterprise to be assessed based on the meaning of the fact tag, the meaning of the model tag, and the meaning of the composite tag comprises:
selecting a target fact label, a target model label and a target composite label related to a preset service scene from the fact label, the model label and the composite label corresponding to the enterprise to be evaluated;
and generating a credit scene image corresponding to the advanced business scene of the enterprise to be evaluated according to the meaning of the target fact label, the meaning of the target model label and the meaning of the target composite label.
10. A credit evaluation apparatus based on tag portrait technology, the apparatus comprising:
one or more processors;
a memory for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement a method for credit assessment based on tag portrait technology as recited in any of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010590439.XA CN111754116B (en) | 2020-06-24 | 2020-06-24 | Credit evaluation method and device based on label portrait technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010590439.XA CN111754116B (en) | 2020-06-24 | 2020-06-24 | Credit evaluation method and device based on label portrait technology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111754116A true CN111754116A (en) | 2020-10-09 |
| CN111754116B CN111754116B (en) | 2023-10-17 |
Family
ID=72677175
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010590439.XA Active CN111754116B (en) | 2020-06-24 | 2020-06-24 | Credit evaluation method and device based on label portrait technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111754116B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113052434A (en) * | 2021-02-26 | 2021-06-29 | 一智科技(成都)有限公司 | Construction object portrait labeling method and system |
| CN113190731A (en) * | 2021-05-31 | 2021-07-30 | 国家电网有限公司大数据中心 | Label construction method, device, equipment and storage medium |
| CN113327048A (en) * | 2021-06-16 | 2021-08-31 | 力合科创集团有限公司 | Enterprise portrait calculation method, medium, and program based on big data and multidimensional features |
| 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 |
| CN113538133A (en) * | 2021-07-26 | 2021-10-22 | 天元大数据信用管理有限公司 | Credit evaluation method, device and medium based on limited Boltzmann machine |
| CN113837859A (en) * | 2021-08-25 | 2021-12-24 | 天元大数据信用管理有限公司 | Small and micro enterprise portrait construction method |
| CN114090854A (en) * | 2022-01-24 | 2022-02-25 | 佰聆数据股份有限公司 | Intelligent label weight updating method and system based on information entropy and computer equipment |
| CN114547482A (en) * | 2022-03-03 | 2022-05-27 | 智慧足迹数据科技有限公司 | Service feature generation method and device, electronic equipment and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108288229A (en) * | 2018-03-02 | 2018-07-17 | 北京邮电大学 | A kind of user's portrait construction method |
| CN108898154A (en) * | 2018-09-29 | 2018-11-27 | 华北电力大学 | A kind of electric load SOM-FCM Hierarchical clustering methods |
| CN109063945A (en) * | 2018-06-08 | 2018-12-21 | 广州亦云信息技术股份有限公司 | A kind of 360 degree of customer portrait construction methods of sale of electricity company based on Value accounting system |
| CN110413787A (en) * | 2019-07-26 | 2019-11-05 | 腾讯科技（深圳）有限公司 | Text Clustering Method, device, terminal and storage medium |
| CN110826886A (en) * | 2019-10-29 | 2020-02-21 | 南京华盾电力信息安全测评有限公司 | Electric power customer portrait construction method based on clustering algorithm and principal component analysis |
| KR102084389B1 (en) * | 2019-06-18 | 2020-03-04 | 한국과학기술정보연구원 | Company evaluation system and evaluation method therefor |
| WO2020053846A2 (en) * | 2019-11-22 | 2020-03-19 | Symbiosis International (Deemed University) | A system and method for analysis of smart meter data |
| CN111080117A (en) * | 2019-12-12 | 2020-04-28 | 国家电网有限公司大数据中心 | Method and device for constructing equipment risk label, electronic equipment and storage medium |
-
2020
- 2020-06-24 CN CN202010590439.XA patent/CN111754116B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108288229A (en) * | 2018-03-02 | 2018-07-17 | 北京邮电大学 | A kind of user's portrait construction method |
| CN109063945A (en) * | 2018-06-08 | 2018-12-21 | 广州亦云信息技术股份有限公司 | A kind of 360 degree of customer portrait construction methods of sale of electricity company based on Value accounting system |
| CN108898154A (en) * | 2018-09-29 | 2018-11-27 | 华北电力大学 | A kind of electric load SOM-FCM Hierarchical clustering methods |
| KR102084389B1 (en) * | 2019-06-18 | 2020-03-04 | 한국과학기술정보연구원 | Company evaluation system and evaluation method therefor |
| CN110413787A (en) * | 2019-07-26 | 2019-11-05 | 腾讯科技（深圳）有限公司 | Text Clustering Method, device, terminal and storage medium |
| CN110826886A (en) * | 2019-10-29 | 2020-02-21 | 南京华盾电力信息安全测评有限公司 | Electric power customer portrait construction method based on clustering algorithm and principal component analysis |
| WO2020053846A2 (en) * | 2019-11-22 | 2020-03-19 | Symbiosis International (Deemed University) | A system and method for analysis of smart meter data |
| CN111080117A (en) * | 2019-12-12 | 2020-04-28 | 国家电网有限公司大数据中心 | Method and device for constructing equipment risk label, electronic equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 裘华东等: "基于标签库系统的电力企业客户画像构建与信用评估及电费风险防控应用", 《电信科学》, vol. 33, no. 1, pages 206 - 213 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113052434A (en) * | 2021-02-26 | 2021-06-29 | 一智科技(成都)有限公司 | Construction object portrait labeling method and system |
| CN113190731A (en) * | 2021-05-31 | 2021-07-30 | 国家电网有限公司大数据中心 | Label construction method, device, equipment and 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 |
| CN113327048A (en) * | 2021-06-16 | 2021-08-31 | 力合科创集团有限公司 | Enterprise portrait calculation method, medium, and program based on big data and multidimensional features |
| CN113538133A (en) * | 2021-07-26 | 2021-10-22 | 天元大数据信用管理有限公司 | Credit evaluation method, device and medium based on limited Boltzmann machine |
| CN113837859A (en) * | 2021-08-25 | 2021-12-24 | 天元大数据信用管理有限公司 | Small and micro enterprise portrait construction method |
| CN113837859B (en) * | 2021-08-25 | 2024-05-14 | 天元大数据信用管理有限公司 | Image construction method for small and micro enterprises |
| CN114090854A (en) * | 2022-01-24 | 2022-02-25 | 佰聆数据股份有限公司 | Intelligent label weight updating method and system based on information entropy and computer equipment |
| CN114090854B (en) * | 2022-01-24 | 2022-04-19 | 佰聆数据股份有限公司 | Intelligent label weight updating method and system based on information entropy and computer equipment |
| CN114547482A (en) * | 2022-03-03 | 2022-05-27 | 智慧足迹数据科技有限公司 | Service feature generation method and device, electronic equipment and storage medium |
| CN114547482B (en) * | 2022-03-03 | 2023-01-20 | 智慧足迹数据科技有限公司 | Service feature generation method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111754116B (en) | 2023-10-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111754116A (en) | Credit assessment method and device based on label portrait technology | |
| Xiong et al. | An approach for resilient‐green supplier selection based on WASPAS, BWM, and TOPSIS under intuitionistic fuzzy sets | |
| Tarei et al. | A hybrid approach for quantifying supply chain risk and prioritizing the risk drivers: A case of Indian petroleum supply chain | |
| US20220343433A1 (en) | System and method that rank businesses in environmental, social and governance (esg) | |
| Kamali Saraji et al. | A novel Pythagorean fuzzy-SWARA-TOPSIS framework for evaluating the EU progress towards sustainable energy development | |
| Seki et al. | News-based business sentiment and its properties as an economic index | |
| CN104321794A (en) | A system and method using multi-dimensional rating to determine an entity's future commercial viability | |
| Louizi et al. | Evaluation of corporate governance systems by credit rating agencies | |
| Baig et al. | Enhancing resilience of oil supply chains in context of developing countries | |
| Yao et al. | Enterprise credit risk prediction using supply chain information: A decision tree ensemble model based on the differential sampling rate, Synthetic Minority Oversampling Technique and AdaBoost | |
| Park | Expansion of servitization in the energy sector and its implications | |
| Makui et al. | Project risk identification and analysis based on group decision making methodology in a fuzzy environment | |
| KR100713546B1 (en) | Method of technology evaluation | |
| Brintrup et al. | Digital supply chain surveillance: concepts, challenges, and frameworks | |
| Liang et al. | Credit rating of sustainable agricultural supply chain finance by integrating heterogeneous evaluation information and misclassification risk | |
| Zhu et al. | TOPSIS method for quality credit evaluation: A case of air-conditioning market in China | |
| JP2023027741A (en) | Real-time enterprise footprint automated system | |
| Jakšić et al. | Fuzzy approach in ranking of banks according to financial performances | |
| Xu et al. | Tail dependence network of new energy vehicle industry in mainland China | |
| Brown | Influence of Artificial Intelligence on Credit Risk Assessment in Banking Sector | |
| Elena | News sentiment in bankruptcy prediction models: Evidence from Russian retail companies | |
| Smith | Integrating AI to Increase the Effectiveness of ESG Projects | |
| Guang et al. | [Retracted] Bayesian Network‐Based Marketing Risk Warning Method for Integrated Energy Companies | |
| Kubenka et al. | Implementation of standards into predictors of financial stability | |
| Ding et al. | LSTM Deep Neural Network Based Power Data Credit Tagging Technology. |
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 |