CN114723256A - Method and device for constructing evaluation framework, electronic equipment and computer readable medium - Google Patents

Method and device for constructing evaluation framework, electronic equipment and computer readable medium Download PDF

Info

Publication number
CN114723256A
CN114723256A CN202210309355.3A CN202210309355A CN114723256A CN 114723256 A CN114723256 A CN 114723256A CN 202210309355 A CN202210309355 A CN 202210309355A CN 114723256 A CN114723256 A CN 114723256A
Authority
CN
China
Prior art keywords
indexes
index
level
calculating
weight
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.)
Pending
Application number
CN202210309355.3A
Other languages
Chinese (zh)
Inventor
程琬芸
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China Construction Bank Corp
Original Assignee
China Construction Bank Corp
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by China Construction Bank Corp filed Critical China Construction Bank Corp
Priority to CN202210309355.3A priority Critical patent/CN114723256A/en
Publication of CN114723256A publication Critical patent/CN114723256A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • 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
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/02—Agriculture; Fishing; Mining

Abstract

The invention discloses a method and a device for constructing an evaluation framework, electronic equipment and a computer readable medium, and relates to the technical field of big data. One embodiment of the method comprises: respectively calculating the weight of the first-level index and the weight of the second-level index by adopting an analytic hierarchy process; if no historical sample exists, screening three-level indexes from the alternative indexes by adopting a maximum information coefficient and a variation coefficient, and calculating the weight of the three-level indexes; if the historical samples exist, screening three-level indexes from the alternative indexes by adopting the maximum information coefficient and the information value, and calculating the weight of the three-level indexes; and constructing an evaluation framework through the primary indexes and the weights thereof, the secondary indexes and the weights thereof, and the tertiary indexes and the weights thereof. The embodiment can solve the technical problem that a scientific and practical evaluation framework cannot be constructed under the condition of incomplete data.

Description

Method and device for constructing evaluation framework, electronic equipment and computer readable medium
Technical Field
The invention relates to the technical field of big data, in particular to a method and a device for constructing an evaluation framework, electronic equipment and a computer readable medium.
Background
At present, a credit evaluation framework of a novel agricultural operation main body has no mature construction scheme, and agricultural related data has no acknowledged reliable source. Therefore, the data of the new agricultural business entity is usually incomplete, that is, the amount of the new agricultural business entity loans accumulated in the line is only a small amount, and most of the new agricultural business entity loans do not obtain the comprehensive data of the customers. However, the prior art cannot construct a scientific and practical evaluation framework under the condition of incomplete data.
Disclosure of Invention
In view of this, embodiments of the present invention provide a method, an apparatus, an electronic device, and a computer-readable medium for constructing an evaluation framework, so as to solve the technical problem that a scientific and practical evaluation framework cannot be constructed under the condition of incomplete data.
To achieve the above object, according to an aspect of an embodiment of the present invention, there is provided a method of constructing an evaluation framework, including:
respectively calculating the weight of the first-level index and the weight of the second-level index by adopting an analytic hierarchy process;
if no historical sample exists, screening three-level indexes from the alternative indexes by adopting a maximum information coefficient and a variation coefficient, and calculating the weight of the three-level indexes; if the historical samples exist, screening three-level indexes from the alternative indexes by adopting the maximum information coefficient and the information value, and calculating the weight of the three-level indexes;
and constructing an evaluation framework through the primary indexes and the weights thereof, the secondary indexes and the weights thereof, and the tertiary indexes and the weights thereof.
Optionally, the step of calculating the weight of the first-level indicator and the weight of the second-level indicator by using an analytic hierarchy process includes:
acquiring importance ranking of the first-level indexes so as to construct a judgment matrix;
calculating the weight of the first-level index according to the judgment matrix;
for each primary index, acquiring importance ranking of secondary indexes corresponding to the primary indexes, and constructing a judgment matrix;
and for each primary index, calculating the weight of a secondary index corresponding to the primary index according to the judgment matrix corresponding to the primary index.
Optionally, calculating the weight of the primary indicator according to the determination matrix includes:
for each row of the judgment matrix, multiplying each N element of the row, and then calculating the square root of the product of the N elements for N times to obtain the characteristic value of the first-level index corresponding to the row; wherein N is the number of primary indexes;
and normalizing the characteristic value of each primary index to obtain the weight of the primary index.
Optionally, for each primary index, after calculating a weight of a secondary index corresponding to the primary index according to a determination matrix corresponding to the primary index, the method further includes:
and eliminating the secondary indexes without the historical samples, and normalizing the weights of the rest secondary indexes.
Optionally, screening a third-level index from the candidate indexes by using a maximum information coefficient and a variation coefficient, and calculating a weight of the third-level index, including:
calculating the maximum information coefficient between any two optional indexes;
calculating the variation coefficient of each alternative index;
screening out three-level indexes according to the maximum information coefficient between any two optional indexes and the variation coefficient of each optional index;
and calculating the weight of the three-level index according to the variation coefficient of the three-level index.
Optionally, screening out three-level indexes according to the maximum information coefficient between any two candidate indexes and the variation coefficient of each candidate index, including:
for any two candidate indexes, if the maximum information coefficient between the any two candidate indexes is greater than 0.5, the candidate index with the large variation coefficient in the any two candidate indexes is reserved as a three-level index.
Optionally, calculating the weight of the three-level index according to the coefficient of variation of the three-level index includes:
and normalizing the variation coefficient of each three-level index to obtain the weight of each three-level index.
Optionally, screening a third-level index from the candidate indexes by using a maximum information coefficient and an information value, and calculating a weight of the third-level index, including:
calculating the maximum information coefficient between any two optional indexes;
calculating the information value of each alternative index;
screening out three-level indexes according to the maximum information coefficient between any two optional indexes and the information value of each optional index;
and calculating the weight of the three-level indexes according to the information value of the three-level indexes.
Optionally, calculating the information value of each candidate index includes:
a label identifying each historical sample; wherein the label comprises a positive swatch and a negative swatch;
and performing box separation on the alternative indexes by adopting a decision tree mode, and calculating the information value of the alternative indexes by adopting the following formula:
Figure BDA0003567324960000031
wherein, giRepresenting the age of the sample tree labeled as positive in bin i, biRepresenting the number of samples labeled negative in bin i, G being the total number of samples labeled positive, and B being the total number of samples labeled negative.
Optionally, screening out three-level indexes according to the maximum information coefficient between any two candidate indexes and the information value of each candidate index, including:
and for any two optional indexes, if the maximum information coefficient between any two optional indexes is greater than 0.5, reserving the optional index with high information value in any two optional indexes as a three-level index.
Optionally, calculating the weight of the tertiary index according to the information value of the tertiary index includes:
and normalizing the information value of each three-level index to obtain the weight of each three-level index.
In addition, according to another aspect of the embodiments of the present invention, there is provided an apparatus for constructing an evaluation framework, including:
the first calculation module is used for calculating the weight of the first-level index and the weight of the second-level index by adopting an analytic hierarchy process;
the second calculation module is used for screening three-level indexes from the alternative indexes by adopting the maximum information coefficient and the variation coefficient and calculating the weight of the three-level indexes if no historical sample exists; if the historical samples exist, screening three-level indexes from the alternative indexes by adopting the maximum information coefficient and the information value, and calculating the weight of the three-level indexes;
a construction module for constructing an evaluation frame by the first-level index and the weight thereof, the second-level index and the weight thereof, and the third-level index and the weight thereof
Optionally, the first computing module is further configured to:
acquiring importance ranking of the first-level indexes so as to construct a judgment matrix;
calculating the weight of the first-level index according to the judgment matrix;
for each primary index, acquiring importance ranking of secondary indexes corresponding to the primary indexes, and constructing a judgment matrix;
and for each primary index, calculating the weight of a secondary index corresponding to the primary index according to the judgment matrix corresponding to the primary index.
Optionally, the first computing module is further configured to:
for each row of the judgment matrix, multiplying each N element of the row, and then calculating the square root of the product of the N elements for N times to obtain the characteristic value of the first-level index corresponding to the row; wherein N is the number of primary indexes;
and normalizing the characteristic value of each primary index to obtain the weight of the primary index.
Optionally, the first computing module is further configured to:
and for each primary index, calculating the weight of a secondary index corresponding to the primary index according to a judgment matrix corresponding to the primary index, removing the secondary index without a historical sample, and normalizing the weight of the rest secondary indexes.
Optionally, the second computing module is further configured to:
calculating the maximum information coefficient between any two optional indexes;
calculating the variation coefficient of each alternative index;
screening out three-level indexes according to the maximum information coefficient between any two optional indexes and the variation coefficient of each optional index;
and calculating the weight of the three-level index according to the variation coefficient of the three-level index.
Optionally, the second computing module is further configured to:
for any two candidate indexes, if the maximum information coefficient between the any two candidate indexes is greater than 0.5, the candidate index with the large variation coefficient in the any two candidate indexes is reserved as a three-level index.
Optionally, the second computing module is further configured to:
and normalizing the variation coefficient of each three-level index to obtain the weight of each three-level index.
Optionally, the second computing module is further configured to:
calculating the maximum information coefficient between any two optional indexes;
calculating the information value of each alternative index;
screening out three-level indexes according to the maximum information coefficient between any two optional indexes and the information value of each optional index;
and calculating the weight of the three-level indexes according to the information value of the three-level indexes.
Optionally, the second computing module is further configured to:
a label identifying each historical sample; wherein the label comprises a positive swatch and a negative swatch;
and performing box separation on the alternative indexes by adopting a decision tree mode, and calculating the information value of the alternative indexes by adopting the following formula:
Figure BDA0003567324960000061
wherein, giRepresenting the age of the sample tree labeled as positive in bin i, biRepresenting the number of samples labeled negative in bin i, G being the total number of samples labeled positive, and B being the total number of samples labeled negative.
Optionally, the second computing module is further configured to:
and for any two optional indexes, if the maximum information coefficient between any two optional indexes is greater than 0.5, reserving the optional index with high information value in any two optional indexes as a three-level index.
Optionally, the second computing module is further configured to:
and normalizing the information value of each three-level index to obtain the weight of each three-level index.
According to another aspect of the embodiments of the present invention, there is also provided an electronic device, including:
one or more processors;
a storage device for storing one or more programs,
when the one or more programs are executed by the one or more processors, the one or more processors implement the method of any of the embodiments described above.
According to another aspect of the embodiments of the present invention, there is also provided a computer readable medium, on which a computer program is stored, which when executed by a processor implements the method of any of the above embodiments.
According to another aspect of the embodiments of the present invention, there is also provided a computer program product comprising a computer program which, when executed by a processor, implements the method of any of the above embodiments.
One embodiment of the above invention has the following advantages or benefits: if no historical sample exists, the three-level index is screened from the alternative indexes by adopting the maximum information coefficient and the variation coefficient, and the weight of the three-level index is calculated, and if the historical sample exists, the three-level index is screened from the alternative indexes by adopting the maximum information coefficient and the information value, and the weight of the three-level index is calculated, so that the technical problem that a scientific and practical evaluation framework cannot be constructed under the condition of incomplete data in the prior art is solved. According to the embodiment of the invention, a scientific and practical evaluation frame can be constructed by adopting a combination mode of objective variation coefficient/information value + maximum information coefficient under the condition of incomplete data, the defect that the evaluation frame is constructed only by subjective expert experience when data is lost in the past is solved, excessive subjective factor interference is avoided, the existing data is fully utilized, and the stability, accuracy and integrity of the whole structure of the evaluation frame can be ensured.
Further effects of the above-mentioned non-conventional alternatives will be described below in connection with the embodiments.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the embodiments or the prior art descriptions will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts. Wherein:
fig. 1 is a schematic diagram of a main flow of a method of constructing an evaluation framework according to a first embodiment of the present invention;
FIG. 2 is a schematic illustration of a multi-level index according to an embodiment of the invention;
FIG. 3 is a schematic view of a main flow of a method of constructing an evaluation framework according to a second embodiment of the present invention;
FIG. 4 is a schematic diagram of the main modules of an apparatus for constructing an evaluation framework according to an embodiment of the present invention;
FIG. 5 is an exemplary system architecture diagram in which embodiments of the present invention may be employed;
fig. 6 is a schematic block diagram of a computer system suitable for use in implementing a terminal device or server of an embodiment of the invention.
Detailed Description
Exemplary embodiments of the present invention are described below with reference to the accompanying drawings, in which various details of embodiments of the invention are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the invention. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
According to the technical scheme, the data acquisition, storage, use, processing and the like meet the relevant regulations of national laws and regulations.
Fig. 1 is a schematic diagram of a main flow of a method of constructing an evaluation framework according to a first embodiment of the present invention. As an embodiment of the present invention, as shown in fig. 1, the method for constructing an evaluation framework may include:
and 101, respectively calculating the weight of the first-level index and the weight of the second-level index by adopting an analytic hierarchy process.
In the embodiment of the present invention, for the first-level indexes, the weight of each first-level index may be calculated by using an analytic hierarchy process, and for the second-level indexes under each first-level index, the weight of each second-level index may also be calculated by using an analytic hierarchy process. Alternatively, as shown in FIG. 2, the primary indicators may include basic qualifications, production operations, liability and credit history, and social responsibility; taking basic qualification as an example, the secondary indexes under the primary index may include stockholder conditions, employee composition, enterprise management conditions, continuous operation conditions, and actual person control conditions.
Optionally, step 101 may comprise: acquiring importance ranking of the first-level indexes so as to construct a judgment matrix; calculating the weight of the first-level index according to the judgment matrix; for each primary index, acquiring importance ranking of secondary indexes corresponding to the primary indexes, and constructing a judgment matrix; and for each primary index, calculating the weight of a secondary index corresponding to the primary index according to the judgment matrix corresponding to the primary index. Firstly, importance ranking of primary indexes is obtained, then a judgment matrix is constructed according to the importance ranking of the primary indexes, and in the judgment matrix, rows and columns represent all the primary indexes. Wherein, each numerical value in the judgment matrix is quantitative representation of relative importance between every two indexes at the same level. Then calculating the weight of each primary index according to the judgment matrix; then, for each primary index, the weight of each secondary index under the primary index is calculated by adopting a similar method.
Optionally, calculating the weight of the primary indicator according to the determination matrix includes: for each row of the judgment matrix, multiplying each N element of the row, and then calculating the square root of the product of the N elements for N times to obtain the characteristic value of the first-level index corresponding to the row; wherein N is the number of primary indexes; and normalizing the characteristic value of each primary index to obtain the weight of the primary index.
Taking the above judgment matrix as an example, the number of the first-level indexes is 5. For each row in the judgment matrix, multiplying 5 elements of the row, and then calculating the root of the product of 5 times, thereby obtaining the characteristic value of the first-level index corresponding to the row:
Figure BDA0003567324960000091
wherein x isijIs the element in the ith row and the jth column.
Then, normalizing the characteristic value of each primary index to obtain the weight of the primary index:
Figure BDA0003567324960000092
each first-level index is composed of a plurality of second-level indexes, and the second-level indexes are determined by the analytic hierarchy process and are not repeated.
Optionally, for each primary index, after calculating a weight of a secondary index corresponding to the primary index according to a determination matrix corresponding to the primary index, the method further includes: and eliminating the secondary indexes without the historical samples, and normalizing the weights of the rest secondary indexes. In practical application, due to the fact that various data are incomplete, secondary indexes may not acquire or acquire data at the same time, and therefore the weights of the secondary indexes need to be adjusted again.
If the primary index "basic qualification" includes 5 secondary indexes (stockholder condition, employee composition, enterprise management condition, continuous operation condition, real person control condition), in a specific scene, only data in 3 aspects of the stockholder condition, continuous operation condition and real person control condition can be obtained, then the primary index "basic qualification" in the scene only uses the secondary indexes (stockholder condition, continuous operation condition, real person control), and the corresponding weight is adjusted:
step 102, if no historical sample exists, screening a third-level index from alternative indexes by adopting a maximum information coefficient and a variation coefficient, and calculating the weight of the third-level index; and if the historical samples exist, screening three-level indexes from the alternative indexes by adopting the maximum information coefficient and the information value, and calculating the weight of the three-level indexes.
In an embodiment of the invention, each tertiary index is screened from a plurality of candidate indices. However, different methods are adopted to calculate the weight for different three-level indexes, if a historical sample exists, the historical sample is fully utilized, and the maximum information coefficient and the information value are adopted to carry out the screening of the indexes and the calculation of the weight; and if no historical sample exists, screening indexes and calculating weight by adopting the maximum information coefficient and the variation coefficient.
Optionally, screening a third-level index from the candidate indexes by using a maximum information coefficient and a variation coefficient, and calculating a weight of the third-level index, including: calculating the maximum information coefficient between any two optional indexes; calculating the variation coefficient of each alternative index; screening out three-level indexes according to the maximum information coefficient between any two optional indexes and the variation coefficient of each optional index; and calculating the weight of the three-level index according to the variation coefficient of the three-level index.
At present, methods commonly used for judging the correlation between two indexes include Pearson correlation coefficient, Spearman correlation coefficient, and the like, but these methods can only analyze the correlation expressed by functions, and cannot find the implicit logical relationship between the indexes. The embodiment of the invention uses the maximum information coefficient to identify the correlation between the two indexes, and can overcome the defects of the two methods.
Firstly, processing a plurality of alternative indexes, taking a secondary index 'stockholder situation' as an example, and processing alternative indexes such as 'the number of stockholders', 'the change frequency of the stockholders in nearly 6 months', 'the change frequency of the legal person in nearly 6 months', 'the stockholder proportion of the legal person' and the like according to source data; then calculating pairwise maximum information coefficients between the alternative indexes and the variation coefficient of each alternative index; and then, screening indexes and calculating weight according to pairwise maximum information coefficients between the alternative indexes and the variation coefficient of each alternative index. The embodiment of the invention screens the indexes and calculates the weight by using the variation coefficient and the maximum information coefficient, the variation coefficient can judge the distinguishing degree of the indexes to the clients, and the maximum information coefficient can judge the strength (including linear relation and nonlinear relation) of the relation of the indexes represented by any function.
The maximum information coefficient is an improved method for analyzing the correlation based on mutual information, and mutual information I (X, Y) represents the degree of randomness reduction brought by X occurrence when Y has occurred, and the degree of reduction is used for representing the correlation between X and Y. The maximum information coefficient is obtained by carrying out data discretization on X and Y through barrier segmentation, so that mutual information values under different segmentations are calculated, and the maximum mutual information value is taken to represent the correlation between X and Y. The larger the maximum information coefficient of the two indexes is, the more closely the correlation relationship between the two indexes is. The Coefficient of Variation (Coefficient of Variation) is the ratio of the standard deviation to the mean, and is an index for normalizing the degree of dispersion of the measurement data.
Optionally, screening out three-level indexes according to the maximum information coefficient between any two candidate indexes and the variation coefficient of each candidate index, including: for any two candidate indexes, if the maximum information coefficient between the any two candidate indexes is greater than 0.5, the candidate index with the large variation coefficient in the any two candidate indexes is reserved as a three-level index. For example, if the maximum information coefficient is greater than 0.5, the candidate index having a large coefficient of variation is retained as the three-level index. Alternatively, the number of the upper lines of the three-level indexes, such as 5, may be configured, and then the number of the three-level indexes does not exceed 5.
Optionally, calculating the weight of the three-level index according to the coefficient of variation of the three-level index includes: and normalizing the variation coefficient of each three-level index to obtain the weight of each three-level index.
The method comprises the following steps: the weight of the second-level index of the shareholder situation is determined to be 0.31 in the previous step, and finally, the third-level index (the number of shareholders, the shareholder change frequency in nearly 6 months and the shareholder proportion of the legal person) is kept, and the coefficient of variation is (0.53, 1.07 and 0.11);
then, the weight of the number of shareholders
Figure BDA0003567324960000121
After normalization, the weights of the three-level indexes (number of shareholders, change frequency of shareholders in nearly 6 months, shareholders proportion of legal) are (0.30,0.63 and 0.07).
Optionally, screening a third-level index from the candidate indexes by using a maximum information coefficient and an information value, and calculating a weight of the third-level index, including: calculating the maximum information coefficient between any two optional indexes; calculating the information value of each alternative index; screening out three-level indexes according to the maximum information coefficient between any two optional indexes and the information value of each optional index; and calculating the weight of the three-level indexes according to the information value of the three-level indexes.
Firstly, processing a plurality of alternative indexes, taking a secondary index 'stockholder situation' as an example, and processing alternative indexes such as 'the number of stockholders', 'the change frequency of the stockholders in nearly 6 months', 'the change frequency of the legal person in nearly 6 months', 'the stockholder proportion of the legal person' and the like according to source data; then, calculating pairwise maximum information coefficients between the alternative indexes and the information value of each alternative index; and then, screening indexes and calculating weight according to pairwise maximum information coefficients between the alternative indexes and the information value of each alternative index.
Optionally, calculating the information value of each candidate index includes: a label identifying each historical sample; wherein the label comprises a positive swatch and a negative swatch; and performing box separation on the alternative indexes by adopting a decision tree mode, and calculating the information value of the alternative indexes by adopting the following formula:
Figure BDA0003567324960000122
wherein, giRepresenting the age of the sample tree labeled as positive in bin i, biRepresenting the number of samples labeled negative in bin i, G being the total number of samples labeled positive, and B being the total number of samples labeled negative.
The evidence weight WOE is a method of binning the metrics according to the target. The essence of WOE is the difference between "the proportion of target customers to all target customers in the current bin" and "the proportion of non-target customers to all non-target customers in the current bin". By calculating the evidence weights of different indicators, the ability of different indicator pairs to identify target customers can be obtained and compared. However, the WOE does not consider the number of target clients, so that the information value IV additionally considers the difference between the number of target clients in the current sub-box and the number of non-target clients in the current sub-box on the basis of the evidence weight, and the capability of the index pair for identifying the target clients can be more integrally measured.
Firstly, selecting historical samples from historical stock samples, wherein the historical samples comprise negative samples in a certain proportion, respectively labeling the historical samples, and processing alternative indexes on the historical samples. Then according to the negative sample label, using a decision tree mode to perform box separation on each alternative index, calculating the evidence weight WOE, and then calculating to obtain the information value IV:
Figure BDA0003567324960000131
Figure BDA0003567324960000132
it should be noted that the IV value corresponds to a weighted sum of the WOE, and the size of the IV indicates how much the indicator affects the sample overdue.
In the embodiment of the invention, under the condition of labeled data, the method of information value plus maximum information coefficient is used for screening the three-level indexes and determining the weight of the three-level indexes, and the stock loan data is fully utilized for objective judgment.
Optionally, screening out three-level indexes according to the maximum information coefficient between any two candidate indexes and the information value of each candidate index, including: and for any two optional indexes, if the maximum information coefficient between any two optional indexes is greater than 0.5, reserving the optional index with high information value in any two optional indexes as a three-level index. For example, if the maximum information coefficient is greater than 0.5, the candidate index having a large coefficient of variation is retained as the three-level index. Alternatively, the number of the upper lines of the three-level indexes, such as 8, may be configured, and then the number of the three-level indexes does not exceed 8.
Optionally, calculating the weight of the tertiary index according to the information value of the tertiary index includes: and normalizing the information value of each three-level index to obtain the weight of each three-level index. The calculation method of the weight is similar to the above, and is not repeated.
And 103, constructing an evaluation framework through the primary indexes and the weights thereof, the secondary indexes and the weights thereof, and the tertiary indexes and the weights thereof.
And (4) constructing an evaluation framework by adopting each primary index and the weight thereof, each secondary index and the weight thereof, and each tertiary index and the weight thereof which are calculated in the steps.
According to the various embodiments described above, it can be seen that the technical means of screening the third-level indexes from the candidate indexes and calculating the weights of the third-level indexes by using the maximum information coefficient and the variation coefficient if no history sample exists, and screening the third-level indexes from the candidate indexes and calculating the weights of the third-level indexes by using the maximum information coefficient and the information value if a history sample exists solve the technical problem that a scientific and practical evaluation framework cannot be constructed under the condition of incomplete data in the prior art. According to the embodiment of the invention, a scientific and practical evaluation frame can be constructed by adopting a combination mode of objective variation coefficient/information value + maximum information coefficient under the condition of incomplete data, the defect that the evaluation frame is constructed only by subjective expert experience in the past data loss process is solved, excessive subjective factor interference is avoided, the existing data is fully utilized, and the stability, the accuracy and the integrity of the whole structure of the evaluation frame can be ensured.
Fig. 3 is a schematic diagram of a main flow of a method of constructing an evaluation framework according to a second embodiment of the present invention. As still another embodiment of the present invention, as shown in fig. 3, the method for constructing an evaluation framework may include:
and 301, calculating the weight of the first-level index by adopting an analytic hierarchy process.
Specifically, the importance ranking of the primary indexes is obtained, so that a judgment matrix is constructed, and then the weight of each primary index is calculated according to the judgment matrix.
And 302, calculating the weight of the secondary indexes under the primary indexes by adopting an analytic hierarchy process for each primary index.
For each first-level index, the importance sequence of the second-level indexes under the first-level index is obtained, so that a judgment matrix corresponding to the first-level index is constructed, and then the weight of each second-level index under the first-level index is calculated according to the judgment matrix corresponding to the first-level index.
Step 303, judging whether a history sample exists; if not, executing step 304 for each secondary index; if so, for each secondary index, go to step 307.
In the embodiment of the invention, weights are calculated by adopting different methods for different three-level indexes, and if no historical sample exists, the maximum information coefficient and the variation coefficient are adopted to carry out index screening and weight calculation; and if the historical samples exist, the historical samples are fully utilized, and the maximum information coefficient and the information value are adopted to carry out screening of indexes and calculation of weight.
And step 304, calculating the maximum information coefficient between any two candidate indexes, and calculating the variation coefficient of each candidate index.
The embodiment of the invention screens the indexes and calculates the weight by using the variation coefficient and the maximum information coefficient, the variation coefficient can judge the distinguishing degree of the indexes to the clients, and the maximum information coefficient can judge the strength (including linear relation and nonlinear relation) of the relation of the indexes represented by any function.
And 305, screening out three-level indexes according to the maximum information coefficient between any two optional indexes and the variation coefficient of each optional index.
Specifically, for any two candidate indexes, if the maximum information coefficient between the any two candidate indexes is greater than 0.5, the candidate index with a large variation coefficient in the any two candidate indexes is reserved as a three-level index.
And step 306, calculating the weight of the three-level index according to the variation coefficient of the three-level index.
Specifically, the coefficient of variation of each of the three-level indicators may be normalized, so as to obtain a weight of each of the three-level indicators.
And 307, calculating the maximum information coefficient between any two candidate indexes, and calculating the information value of each candidate index.
And 308, screening out three-level indexes according to the maximum information coefficient between any two optional indexes and the information value of each optional index.
Specifically, for any two candidate indexes, if the maximum information coefficient between the any two candidate indexes is greater than 0.5, the candidate index with a high information value in the any two candidate indexes is reserved as a tertiary index.
And 309, constructing an evaluation framework through the primary indexes and the weights thereof, the secondary indexes and the weights thereof, and the tertiary indexes and the weights thereof.
In addition, the detailed implementation of the method for constructing the evaluation framework in the second embodiment of the present invention has been explained in detail in the above-mentioned method for constructing the evaluation framework, and therefore, the repeated contents will not be explained.
Fig. 4 is a schematic diagram of main modules of an apparatus for constructing an evaluation framework according to an embodiment of the present invention. As shown in fig. 4, the apparatus 400 for building an evaluation framework includes a first calculation module 401, a second calculation module 402, and a building module 403; the first calculating module 401 is configured to calculate the weight of the first-level index and the weight of the second-level index by using an analytic hierarchy process; the second calculating module 402 is configured to, if there is no history sample, screen a third-level index from the candidate indexes by using the maximum information coefficient and the variation coefficient, and calculate a weight of the third-level index; if the historical samples exist, screening three-level indexes from the alternative indexes by adopting the maximum information coefficient and the information value, and calculating the weight of the three-level indexes; the construction module 403 is configured to construct an evaluation framework according to the first-level indicator and the weight thereof, the second-level indicator and the weight thereof, and the third-level indicator and the weight thereof
Optionally, the first computing module 401 is further configured to:
acquiring importance ranking of the first-level indexes so as to construct a judgment matrix;
calculating the weight of the first-level index according to the judgment matrix;
for each primary index, acquiring importance ranking of secondary indexes corresponding to the primary indexes, and constructing a judgment matrix;
and for each primary index, calculating the weight of a secondary index corresponding to the primary index according to the judgment matrix corresponding to the primary index.
Optionally, the first computing module 401 is further configured to:
for each row of the judgment matrix, multiplying each N element of the row, and then calculating the square root of the product of the N elements for N times to obtain the characteristic value of the first-level index corresponding to the row; wherein N is the number of primary indexes;
and normalizing the characteristic value of each primary index to obtain the weight of the primary index.
Optionally, the first computing module 401 is further configured to:
and for each primary index, calculating the weight of a secondary index corresponding to the primary index according to a judgment matrix corresponding to the primary index, removing the secondary index without a historical sample, and normalizing the weight of the rest secondary indexes.
Optionally, the second computing module 402 is further configured to:
calculating the maximum information coefficient between any two optional indexes;
calculating the variation coefficient of each alternative index;
screening out three-level indexes according to the maximum information coefficient between any two optional indexes and the variation coefficient of each optional index;
and calculating the weight of the three-level index according to the variation coefficient of the three-level index.
Optionally, the second calculating module 402 is further configured to:
for any two candidate indexes, if the maximum information coefficient between the any two candidate indexes is greater than 0.5, the candidate index with the large variation coefficient in the any two candidate indexes is reserved as a three-level index.
Optionally, the second computing module 402 is further configured to:
and normalizing the variation coefficient of each three-level index to obtain the weight of each three-level index.
Optionally, the second computing module 402 is further configured to:
calculating the maximum information coefficient between any two optional indexes;
calculating the information value of each alternative index;
screening out three-level indexes according to the maximum information coefficient between any two optional indexes and the information value of each optional index;
and calculating the weight of the three-level indexes according to the information value of the three-level indexes.
Optionally, the second computing module 402 is further configured to:
a label identifying each historical sample; wherein the label comprises a positive swatch and a negative swatch;
and adopting a decision tree mode to divide the boxes of the alternative indexes, and adopting the following formula to calculate the information value of the alternative indexes:
Figure BDA0003567324960000181
wherein, giRepresenting the age of the sample tree labeled as positive in bin i, biRepresenting the number of samples labeled negative in bin i, G being the total number of samples labeled positive, and B being the total number of samples labeled negative.
Optionally, the second computing module 402 is further configured to:
and for any two alternative indexes, if the maximum information coefficient between the any two alternative indexes is larger than 0.5, reserving the alternative index with high information value in the any two alternative indexes as a three-level index.
Optionally, the second calculating module 402 is further configured to:
and normalizing the information value of each three-level index to obtain the weight of each three-level index.
It should be noted that, in the embodiment of the apparatus for constructing an evaluation framework according to the present invention, details have been described in detail in the above method for constructing an evaluation framework, and therefore, the details are not repeated here.
Fig. 5 illustrates an exemplary system architecture 500 of a method of building an evaluation framework or an apparatus for building an evaluation framework to which embodiments of the present invention may be applied.
As shown in fig. 5, the system architecture 500 may include terminal devices 501, 502, 503, a network 504, and a server 505. The network 504 serves to provide a medium for communication links between the terminal devices 501, 502, 503 and the server 505. Network 504 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.
The user may use the terminal devices 501, 502, 503 to interact with a server 505 over a network 504 to receive or send messages or the like. The terminal devices 501, 502, 503 may have installed thereon various communication client applications, such as shopping-like applications, web browser applications, search-like applications, instant messaging tools, mailbox clients, social platform software, etc. (by way of example only).
The terminal devices 501, 502, 503 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like.
The server 505 may be a server providing various services, such as a background management server (for example only) providing support for shopping websites browsed by users using the terminal devices 501, 502, 503. The background management server can analyze and process the received data such as the article information query request and feed back the processing result to the terminal equipment.
It should be noted that the method for constructing the evaluation framework provided by the embodiment of the present invention is generally performed by the server 505, and accordingly, the apparatus for constructing the evaluation framework is generally disposed in the server 505. The method for constructing the evaluation framework provided by the embodiment of the present invention may also be executed by the terminal devices 501, 502, 503, and accordingly, the apparatus for constructing the evaluation framework may be disposed in the terminal devices 501, 502, 503.
It should be understood that the number of terminal devices, networks, and servers in fig. 5 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
Referring now to FIG. 6, a block diagram of a computer system 600 suitable for use with a terminal device implementing an embodiment of the invention is shown. The terminal device shown in fig. 6 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present invention.
As shown in fig. 6, the computer system 600 includes a Central Processing Unit (CPU)601 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM)602 or a program loaded from a storage section 608 into a Random Access Memory (RAM) 603. In the RAM603, various programs and data necessary for the operation of the system 600 are also stored. The CPU 601, ROM 602, and RAM603 are connected to each other via a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.
The following components are connected to the I/O interface 605: an input portion 606 including a keyboard, a mouse, and the like; an output portion 607 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage section 608 including a hard disk and the like; and a communication section 609 including a network interface card such as a LAN card, a modem, or the like. The communication section 609 performs communication processing via a network such as the internet. The driver 610 is also connected to the I/O interface 605 as needed. A removable medium 611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 610 as necessary, so that a computer program read out therefrom is mounted in the storage section 608 as necessary.
In particular, according to the embodiments of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 609, and/or installed from the removable medium 611. The computer program performs the above-described functions defined in the system of the present invention when executed by the Central Processing Unit (CPU) 601.
It should be noted that the computer readable medium shown in the present invention can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of the present invention, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present invention, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer programs according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems that perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The modules described in the embodiments of the present invention may be implemented by software or hardware. The described modules may also be provided in a processor, which may be described as: a processor includes a first computing module, a second computing module, and a building module, where the names of the modules do not in some way constitute a limitation on the modules themselves.
As another aspect, the present invention also provides a computer-readable medium that may be contained in the apparatus described in the above embodiments; or may be separate and not assembled into the device. The computer readable medium carries one or more programs which, when executed by a device, implement the method of: respectively calculating the weight of the first-level index and the weight of the second-level index by adopting an analytic hierarchy process; if no historical sample exists, screening three-level indexes from the alternative indexes by adopting a maximum information coefficient and a variation coefficient, and calculating the weight of the three-level indexes; if the historical samples exist, screening three-level indexes from the alternative indexes by adopting the maximum information coefficient and the information value, and calculating the weight of the three-level indexes; and constructing an evaluation framework through the primary indexes and the weights thereof, the secondary indexes and the weights thereof, and the tertiary indexes and the weights thereof.
As another aspect, an embodiment of the present invention further provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the computer program implements the method described in any of the above embodiments.
According to the technical scheme of the embodiment of the invention, because the technical means that the maximum information coefficient and the variation coefficient are adopted to screen the three-level indexes from the alternative indexes and calculate the weights of the three-level indexes if no historical sample exists and the maximum information coefficient and the information value are adopted to screen the three-level indexes from the alternative indexes and calculate the weights of the three-level indexes if the historical sample exists are adopted, the technical problem that a scientific and practical evaluation framework cannot be constructed under the condition of incomplete data in the prior art is solved. According to the embodiment of the invention, a scientific and practical evaluation frame can be constructed by adopting a combination mode of objective variation coefficient/information value + maximum information coefficient under the condition of incomplete data, the defect that the evaluation frame is constructed only by subjective expert experience in the past data loss process is solved, excessive subjective factor interference is avoided, the existing data is fully utilized, and the stability, the accuracy and the integrity of the whole structure of the evaluation frame can be ensured.
The above-described embodiments should not be construed as limiting the scope of the invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions can occur, depending on design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims (25)

1. A method of constructing an evaluation framework, comprising:
respectively calculating the weight of the first-level index and the weight of the second-level index by adopting an analytic hierarchy process;
if no historical sample exists, screening three-level indexes from the alternative indexes by adopting a maximum information coefficient and a variation coefficient, and calculating the weight of the three-level indexes; if the historical samples exist, screening three-level indexes from the alternative indexes by adopting the maximum information coefficient and the information value, and calculating the weight of the three-level indexes;
and constructing an evaluation framework through the primary indexes and the weights thereof, the secondary indexes and the weights thereof, and the tertiary indexes and the weights thereof.
2. The method of claim 1, wherein the step of calculating the weight of the primary index and the weight of the secondary index by using an analytic hierarchy process comprises:
acquiring importance ranking of the first-level indexes so as to construct a judgment matrix;
calculating the weight of the first-level index according to the judgment matrix;
for each primary index, acquiring importance ranking of secondary indexes corresponding to the primary indexes, and constructing a judgment matrix;
and for each primary index, calculating the weight of a secondary index corresponding to the primary index according to the judgment matrix corresponding to the primary index.
3. The method of claim 2, wherein calculating the weight of the primary indicator according to the decision matrix comprises:
for each row of the judgment matrix, multiplying each N element of the row, and then calculating the square root of the product of the N elements for N times to obtain the characteristic value of the first-level index corresponding to the row; wherein N is the number of primary indexes;
and normalizing the characteristic value of each primary index to obtain the weight of the primary index.
4. The method according to claim 3, wherein for each primary index, after calculating the weight of the secondary index corresponding to the primary index according to the judgment matrix corresponding to the primary index, the method further comprises:
and eliminating the secondary indexes without the historical samples, and normalizing the weights of the rest secondary indexes.
5. The method of claim 1, wherein screening three-level indexes from the candidate indexes by using a maximum information coefficient and a variation coefficient and calculating weights of the three-level indexes comprise:
calculating the maximum information coefficient between any two optional indexes;
calculating the variation coefficient of each alternative index;
screening out three-level indexes according to the maximum information coefficient between any two optional indexes and the variation coefficient of each optional index;
and calculating the weight of the three-level index according to the variation coefficient of the three-level index.
6. The method of claim 5, wherein screening out three levels of indexes according to the maximum information coefficient between any two candidate indexes and the variation coefficient of each candidate index comprises:
for any two candidate indexes, if the maximum information coefficient between the any two candidate indexes is greater than 0.5, the candidate index with the large variation coefficient in the any two candidate indexes is reserved as a three-level index.
7. The method of claim 5, wherein calculating the weight of the three-level indicator according to the coefficient of variation of the three-level indicator comprises:
and normalizing the variation coefficient of each three-level index to obtain the weight of each three-level index.
8. The method of claim 1, wherein screening the candidate indexes for a third-level index and calculating weights of the third-level index by using the maximum information coefficient and the information value comprises:
calculating the maximum information coefficient between any two optional indexes;
calculating the information value of each alternative index;
screening out three-level indexes according to the maximum information coefficient between any two optional indexes and the information value of each optional index;
and calculating the weight of the three-level indexes according to the information value of the three-level indexes.
9. The method of claim 8, wherein calculating the information value of each candidate indicator comprises:
a label identifying each historical sample; wherein the label comprises a positive swatch and a negative swatch;
and adopting a decision tree mode to divide the boxes of the alternative indexes, and adopting the following formula to calculate the information value of the alternative indexes:
Figure FDA0003567324950000031
wherein, giRepresenting the age of the sample tree labeled as positive in bin i, biRepresenting the number of samples labeled negative in bin i, G being the total number of samples labeled positive, and B being the total number of samples labeled negative.
10. The method of claim 8, wherein screening out three levels of indicators according to the maximum information coefficient between any two candidate indicators and the information value of each candidate indicator comprises:
and for any two optional indexes, if the maximum information coefficient between any two optional indexes is greater than 0.5, reserving the optional index with high information value in any two optional indexes as a three-level index.
11. The method of claim 8, wherein calculating the weight of the tertiary index according to the information value of the tertiary index comprises:
and normalizing the information value of each three-level index to obtain the weight of each three-level index.
12. An apparatus for constructing an evaluation framework, comprising:
the first calculation module is used for calculating the weight of the first-level index and the weight of the second-level index by adopting an analytic hierarchy process;
the second calculation module is used for screening three-level indexes from the alternative indexes by adopting a maximum information coefficient and a variation coefficient and calculating the weight of the three-level indexes if no historical sample exists; if the historical samples exist, screening three-level indexes from the alternative indexes by adopting the maximum information coefficient and the information value, and calculating the weight of the three-level indexes;
and the construction module is used for constructing an evaluation framework through the primary indexes and the weights thereof, the secondary indexes and the weights thereof, and the tertiary indexes and the weights thereof.
13. The apparatus of claim 12, wherein the first computing module is further configured to:
acquiring importance ranking of the first-level indexes so as to construct a judgment matrix;
calculating the weight of the first-level index according to the judgment matrix;
for each primary index, acquiring importance ranking of secondary indexes corresponding to the primary indexes, and constructing a judgment matrix;
and for each primary index, calculating the weight of a secondary index corresponding to the primary index according to the judgment matrix corresponding to the primary index.
14. The apparatus of claim 13, wherein the first computing module is further configured to:
for each row of the judgment matrix, multiplying each N element of the row, and then calculating the square root of the product of the N elements for N times to obtain the characteristic value of the first-level index corresponding to the row; wherein N is the number of primary indexes;
and normalizing the characteristic value of each primary index to obtain the weight of the primary index.
15. The apparatus of claim 14, wherein the first computing module is further configured to:
and for each primary index, calculating the weight of a secondary index corresponding to the primary index according to a judgment matrix corresponding to the primary index, removing the secondary index without a historical sample, and normalizing the weight of the rest secondary indexes.
16. The apparatus of claim 12, wherein the second computing module is further configured to:
calculating the maximum information coefficient between any two optional indexes;
calculating the variation coefficient of each alternative index;
screening out three-level indexes according to the maximum information coefficient between any two optional indexes and the variation coefficient of each optional index;
and calculating the weight of the three-level index according to the variation coefficient of the three-level index.
17. The apparatus of claim 16, wherein the second computing module is further configured to:
for any two candidate indexes, if the maximum information coefficient between the any two candidate indexes is greater than 0.5, the candidate index with the large variation coefficient in the any two candidate indexes is reserved as a three-level index.
18. The apparatus of claim 16, wherein the second computing module is further configured to:
and normalizing the variation coefficient of each three-level index to obtain the weight of each three-level index.
19. The apparatus of claim 12, wherein the second computing module is further configured to:
calculating the maximum information coefficient between any two optional indexes;
calculating the information value of each alternative index;
screening out three-level indexes according to the maximum information coefficient between any two optional indexes and the information value of each optional index;
and calculating the weight of the three-level indexes according to the information value of the three-level indexes.
20. The apparatus of claim 19, wherein the second computing module is further configured to:
a label identifying each historical sample; wherein the label comprises a positive swatch and a negative swatch;
and adopting a decision tree mode to divide the boxes of the alternative indexes, and adopting the following formula to calculate the information value of the alternative indexes:
Figure FDA0003567324950000061
wherein, giRepresenting the age of the sample tree labeled as positive in bin i, biRepresenting the number of samples labeled negative in bin i, G being the total number of samples labeled positive, and B being the total number of samples labeled negative.
21. The apparatus of claim 19, wherein the second computing module is further configured to:
and for any two optional indexes, if the maximum information coefficient between any two optional indexes is greater than 0.5, reserving the optional index with high information value in any two optional indexes as a three-level index.
22. The apparatus of claim 19, wherein the second computing module is further configured to:
and normalizing the information value of each three-level index to obtain the weight of each three-level index.
23. An electronic device, comprising:
one or more processors;
a storage device for storing one or more programs,
the one or more programs, when executed by the one or more processors, implement the method of any of claims 1-11.
24. A computer-readable medium, on which a computer program is stored, which, when being executed by a processor, carries out the method according to any one of claims 1-11.
25. A computer program product comprising a computer program, characterized in that the computer program realizes the method according to any of claims 1-11 when executed by a processor.
CN202210309355.3A 2022-03-28 2022-03-28 Method and device for constructing evaluation framework, electronic equipment and computer readable medium Pending CN114723256A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210309355.3A CN114723256A (en) 2022-03-28 2022-03-28 Method and device for constructing evaluation framework, electronic equipment and computer readable medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210309355.3A CN114723256A (en) 2022-03-28 2022-03-28 Method and device for constructing evaluation framework, electronic equipment and computer readable medium

Publications (1)

Publication Number Publication Date
CN114723256A true CN114723256A (en) 2022-07-08

Family

ID=82239120

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210309355.3A Pending CN114723256A (en) 2022-03-28 2022-03-28 Method and device for constructing evaluation framework, electronic equipment and computer readable medium

Country Status (1)

Country Link
CN (1) CN114723256A (en)

Similar Documents

Publication Publication Date Title
CN110738527A (en) feature importance ranking method, device, equipment and storage medium
CN112950359B (en) User identification method and device
CN113361959A (en) Method and device for calculating maturity of centralized operation of banking business
CN111724185A (en) User maintenance method and device
CN113505990A (en) Enterprise risk assessment method and device, electronic equipment and storage medium
CN112860672A (en) Method and device for determining label weight
CN114511022B (en) Feature screening, behavior recognition model training and abnormal behavior recognition method and device
CN115796585A (en) Enterprise operation risk assessment method and system
CN114723256A (en) Method and device for constructing evaluation framework, electronic equipment and computer readable medium
CN114092230A (en) Data processing method and device, electronic equipment and computer readable medium
CN114493851A (en) Risk processing method and device
CN114493853A (en) Credit rating evaluation method, credit rating evaluation device, electronic device and storage medium
CN114202309A (en) Method for determining matching parameters of user and enterprise, electronic device and program product
CN112907141A (en) Pressure testing method, device, equipment and storage medium
CN112990311A (en) Method and device for identifying admitted client
CN112231299A (en) Method and device for dynamically adjusting feature library
CN112734352A (en) Document auditing method and device based on data dimensionality
CN111915115A (en) Execution policy setting method and device
CN111652501B (en) Financial product evaluation device and method, electronic equipment and storage medium
CN116739756A (en) Financial data processing method, apparatus, device, medium and program product
CN115293903A (en) Guarantee risk prediction method, guarantee risk prediction device, guarantee risk prediction equipment and storage medium
CN114092229A (en) Method and device for calculating credit line, electronic equipment and computer readable medium
CN115271927A (en) Bad loan recovery prediction method, device, apparatus, medium, and program product
CN113034270A (en) Credit risk early warning method and device
Erdey et al. The nonlinear relationship between digital affordances and firm‐level export performance: The moderating role of organizational ambidexterity

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