CN110909298B - Score mapping creation method and device, computer equipment and readable storage medium - Google Patents
Score mapping creation method and device, computer equipment and readable storage medium Download PDFInfo
- Publication number
- CN110909298B CN110909298B CN201911218610.8A CN201911218610A CN110909298B CN 110909298 B CN110909298 B CN 110909298B CN 201911218610 A CN201911218610 A CN 201911218610A CN 110909298 B CN110909298 B CN 110909298B
- Authority
- CN
- China
- Prior art keywords
- score
- scoring
- original
- target
- final
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/15—Correlation function computation including computation of convolution operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Computational Mathematics (AREA)
- Pure & Applied Mathematics (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Artificial Intelligence (AREA)
- Strategic Management (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Entrepreneurship & Innovation (AREA)
- Algebra (AREA)
- Economics (AREA)
- Educational Administration (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Computing Systems (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Machine Translation (AREA)
Abstract
The application provides a score mapping creation method and device, computer equipment and a readable storage medium, and relates to the field of score card construction. According to the method, the proportion of a first negative sample of a sample set to be matched is determined, the proportion of a second negative sample of the sample set to be matched, which corresponds to different original scoring ranges, is determined according to original scores of all samples, the proportion of a corresponding target negative sample is calculated according to respective target proportion coefficients of a plurality of final scoring preset values and the proportion of the first negative sample, a target original scoring range corresponding to each target negative sample proportion is determined, the original score to be mapped of each final scoring preset value is determined according to a specific target original scoring range, and finally a score mapping function corresponding to the sample set to be matched is constructed according to the corresponding relation between the score of the final preset value and the original score to be mapped, so that the final score determined by the score mapping function can truly reflect the actual condition of the samples, and the score readability is improved.
Description
Technical Field
The application relates to the field of score card construction, in particular to a score mapping creation method, a score mapping creation device, computer equipment and a readable storage medium.
Background
The scoring card is a mechanism capable of comprehensively scoring a sample according to dimensional information (e.g., user basic information, repayment capability information, credit condition information) of the sample, has high discrimination between positive and negative samples and extremely high interpretability, and is widely used in the fields of finance, performance assessment and the like. Generally, the scoring card design includes three main steps: firstly, carrying out data cleaning and discretization grouping on sample characteristics; then, determining respective scoring weights of different groups through manual setting or a machine learning algorithm; and then, determining the original scores expressed by the samples under the corresponding grouping results, and mapping the original scores to a score interval which is more customary for score consultants, so as to ensure that the final scores determined by the score card have extremely high interpretability.
Currently, in the design process of a score card, the mainstream in the industry generally selects a ratio of positive samples to negative samples of two sample groups of a sample set as an independent variable, and directly selects two specified final score values as a dependent variable to perform linear function construction operation, so as to obtain a score mapping function for mapping an original score to a final score. However, the proportion of the positive and negative samples expressed by the score mapping function constructed in the manner under different final scores is greatly different from the proportion of the positive and negative samples expressed by the corresponding real samples, so that the problem of poor data consistency exists, the actual condition of the samples cannot be truly reflected by the obtained final scores, and the score readability needs to be improved.
Disclosure of Invention
In view of this, an object of the present application is to provide a score mapping creating method, apparatus, computer device and readable storage medium, where the constructed score mapping function can ensure data consistency between a final scoring result and an actual condition of a sample, so that a final score can truly reflect the actual condition of the sample, and the scoring readability is improved.
In order to achieve the above object, the embodiments of the present application adopt the following technical solutions:
in a first aspect, an embodiment of the present application provides a score mapping creating method, where the method includes:
obtaining a sample set to be matched, and determining a first negative sample proportion corresponding to the sample set to be matched;
acquiring original scores of all samples in the sample set to be matched, and determining second negative sample proportions of the sample set to be matched, which correspond to different original score ranges, so as to obtain a corresponding relation between the second negative sample proportions and the original score ranges;
acquiring target proportion coefficients corresponding to a plurality of final score preset values respectively, and calculating a target negative sample proportion corresponding to each final score preset value according to the first negative sample proportion;
determining a target original scoring range of each final scoring preset value according to the target negative sample proportion corresponding to each final scoring preset value and the corresponding relation between the second negative sample proportion and the original scoring range;
determining the original score to be mapped corresponding to each final score preset value according to the respective target original score range of all the final score preset values;
and performing function construction according to the corresponding relation between different final score preset values and the original scores to be mapped to obtain a score mapping function between the final scores and the original scores corresponding to the sample set to be matched.
In an optional embodiment, the determining a first negative sample proportion corresponding to the sample set to be matched includes:
counting the number of samples in the sample set to be matched and the number of negative samples in the sample set to be matched;
and carrying out proportional operation on the number of the negative samples in the sample set to be matched and the number of the samples in the sample set to be matched, which are obtained through statistics, so as to obtain the proportion of the first negative samples.
In an alternative embodiment, the determining a second negative sample proportion corresponding to different raw score ranges of the sample set to be matched includes:
aiming at each original scoring range, screening out a target sample with the corresponding original score in the original scoring range from the sample set to be matched according to the original score of each sample in the sample set to be matched;
and carrying out proportional operation on the number of the negative samples included in the target sample and the number of the target sample to obtain a second negative sample proportion corresponding to the original scoring range.
In an optional embodiment, the calculating a target negative sample ratio corresponding to each final score preset value according to the first negative sample ratio includes:
and for each final score preset value, multiplying a target proportion coefficient corresponding to the final score preset value by the first negative sample proportion to obtain a target negative sample proportion corresponding to the final score preset value.
In an optional embodiment, the determining, according to the target raw score range of each of all the final score preset values, a raw score to be mapped corresponding to each of the final score preset values includes:
detecting whether a target original scoring range corresponding to each final scoring preset value is a double-boundary numerical range or not according to each final scoring preset value;
and if the target original scoring range is detected to be a double-boundary numerical range, performing mean value calculation on the upper limit value and the lower limit value of the scoring of the target original scoring range, and taking the calculated scoring mean value as the original scoring to be mapped corresponding to the final scoring preset value.
In an optional embodiment, the determining, according to the target raw score range of each of all the final score preset values, a raw score to be mapped corresponding to each of the final score preset values further includes:
if the target original scoring range is not detected to be a double-boundary numerical range, detecting whether the target original scoring range is a single-boundary numerical range with a scoring upper limit value;
and when the target original scoring range is detected to be a single-boundary numerical range with a scoring upper limit value, taking the scoring upper limit value of the target original scoring range as the original score to be mapped corresponding to the final scoring preset value.
In an optional embodiment, the determining, according to the target raw score range of each of all the final score preset values, a raw score to be mapped corresponding to each of the final score preset values further includes:
and when the target original scoring range is detected not to be a single-boundary numerical range with the upper scoring limit, taking the lower scoring limit of the target original scoring range as the original score to be mapped corresponding to the final scoring preset value.
In a second aspect, an embodiment of the present application provides a score map creating apparatus, where the apparatus includes:
the sample proportion determining module is used for acquiring a sample set to be matched and determining a first negative sample proportion corresponding to the sample set to be matched;
the sample proportion determining module is further used for obtaining original scores of all samples in the sample set to be matched, determining second negative sample proportions of the sample set to be matched, which correspond to different original score ranges, and obtaining a corresponding relation between the second negative sample proportions and the original score ranges;
the sample proportion determining module is also used for acquiring target proportion coefficients corresponding to the plurality of final score preset values respectively and calculating a target negative sample proportion corresponding to each final score preset value according to the first negative sample proportion;
the target range determining module is used for determining a target original scoring range of each final scoring preset value according to a target negative sample ratio corresponding to each final scoring preset value and a corresponding relation between the second negative sample ratio and the original scoring range;
the mapping score determining module is used for determining the original score to be mapped corresponding to each final score preset value according to the respective target original score range of all the final score preset values;
and the mapping function construction module is used for performing function construction according to the corresponding relation between different final score preset values and the original scores to be mapped to obtain a score mapping function between the final scores and the original scores corresponding to the sample set to be matched.
In a third aspect, an embodiment of the present application provides a computer device, including a processor and a memory, where the memory stores machine executable instructions that can be executed by the processor, and the processor can execute the machine executable instructions to implement the score map creation method described in any one of the foregoing embodiments.
In a fourth aspect, an embodiment of the present application provides a readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the score map creation method described in any one of the foregoing embodiments is implemented.
Compared with the background art, the method has the following beneficial effects:
according to the method, a first negative sample proportion of a sample set to be matched is determined, a second negative sample proportion of the sample set to be matched, corresponding to different original scoring ranges, is determined according to original scores of all samples in the sample set to be matched, then a target negative sample proportion corresponding to each final scoring preset value is calculated according to a target proportion coefficient corresponding to each final scoring preset value and the first negative sample proportion, a target original scoring range corresponding to the target negative sample proportion of each final scoring preset value is correspondingly determined, then a corresponding original score to be mapped is determined according to each final scoring preset value and the corresponding target original scoring range, finally a score mapping function corresponding to the sample set to be matched, which can ensure data consistency between a final scoring result and actual conditions of the samples, is constructed according to a corresponding relation between the final scoring preset values and the original scores to be mapped, so that the final scores determined by the score mapping function can truly reflect the actual conditions of the samples, and scoring readability is improved.
In order to make the aforementioned objects, features and advantages of the present application more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.
FIG. 1 is a block diagram illustrating a computer device according to an embodiment of the present disclosure;
fig. 2 is a schematic flowchart of a score mapping creation method according to an embodiment of the present application;
FIG. 3 is a flowchart illustrating the sub-steps included in step S210 of FIG. 2;
FIG. 4 is a flowchart illustrating the sub-steps included in step S220 in FIG. 2;
FIG. 5 is a flowchart illustrating the sub-steps included in step S250 of FIG. 2;
fig. 6 is a functional module diagram of a score map creation apparatus according to an embodiment of the present application.
Icon: 10-a computer device; 11-a memory; 12-a processor; 13-a communication unit; 100-score map creation means; 110-sample proportion determination module; 120-target range determination module; 130-a mapping score determination module; 140-mapping function building block.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. The components of the embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the present application, as presented in the figures, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present application without making any creative effort, shall fall within the protection scope of the present application.
It is noted that relational terms such as "first" and "second," and the like, may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising a … …" does not exclude the presence of another identical element in a process, method, article, or apparatus that comprises the element.
Some embodiments of the present application will be described in detail below with reference to the accompanying drawings. The embodiments described below and the features of the embodiments can be combined with each other without conflict.
Referring to fig. 1, fig. 1 is a schematic block diagram of a computer device 10 according to an embodiment of the present disclosure. In the embodiment of the present application, the computer device 10 may construct, for the sample set to be matched, a matching score mapping function capable of ensuring data consistency between the final scoring result and the actual condition of the sample, so that the final score determined by the score mapping function truly reflects the actual condition of the sample, and the scoring readability is improved. In the embodiment, the computer device 10 may be, but is not limited to, a personal computer, a tablet computer, a server, and the like.
In the present embodiment, the computer device 10 includes a score map creation apparatus 100, a memory 11, a processor 12, and a communication unit 13. The respective elements of the memory 11, the processor 12 and the communication unit 13 are directly or indirectly electrically connected to each other to realize data transmission or interaction. For example, the memory 11, the processor 12 and the communication unit 13 may be electrically connected to each other through one or more communication buses or signal lines.
In this embodiment, the memory 11 may be used for storing a program, and the processor 12 may execute the program accordingly after receiving the execution instruction. The Memory 11 may be, but is not limited to, a Random Access Memory (RAM), a Read Only Memory (ROM), a Programmable Read-Only Memory (PROM), an Erasable Read-Only Memory (EPROM), an electrically Erasable Read-Only Memory (EEPROM), and the like. The memory 11 may further be configured to store a plurality of final score preset values configured by the score card designer according to the score card design criteria, and a target scaling factor of each final score preset value. Each target scale factor is greater than 1, and the larger the value of the final score preset value is, the larger the corresponding target scale factor is.
In this embodiment, the processor 12 may be an integrated circuit chip having signal processing capabilities. The Processor 12 may be a general-purpose Processor including a Central Processing Unit (CPU), a Network Processor (NP), and the like. The general purpose processor may be a microprocessor or the processor may be any conventional processor or the like that implements or executes the methods, steps and logic blocks disclosed in the embodiments of the present application.
In this embodiment, the communication unit 13 is configured to establish a communication connection between the computer device 10 and another device through a network, and to transmit and receive data through the network. For example, the computer device 10 obtains the specific data of each sample in the sample set to be matched through the communication unit 13.
In this embodiment, the score map creation apparatus 100 includes at least one software functional module capable of being stored in the memory 11 in the form of software or firmware or being solidified in the operating system of the computer device 10. The processor 12 may be used to execute executable modules stored by the memory 11, such as software functional modules and computer programs included by the score map creation apparatus 100. The computer device 10 creates a score mapping function capable of ensuring data consistency between a final scoring result and an actual condition of a sample for the sample set to be matched through the score mapping creating device 100, so that the final scoring determined by the score mapping function truly reflects the actual condition of the sample, and the scoring readability is improved.
It will be appreciated that the block diagram shown in fig. 1 is merely a structural component diagram of the computer device 10, and that the computer device 10 may include more or fewer components than shown in fig. 1, or have a different configuration than shown in fig. 1. The components shown in fig. 1 may be implemented in hardware, software, or a combination thereof.
In the present application, in order to ensure that the final score output by the score mapping function created for the sample set to be matched by the computer device 10 keeps data consistency with the actual situation of a specific sample, so as to improve the readability of the score, the present application provides a score mapping creation method applied to the computer device 10 to achieve the above functions. The score mapping creation method provided by the present application is described below.
Referring to fig. 2, fig. 2 is a flowchart illustrating a score mapping creating method according to an embodiment of the present disclosure. In the embodiment of the present application, the specific flow and steps of the score map creation method shown in fig. 2 are as follows.
Step S210, a sample set to be matched is obtained, and a first negative sample proportion corresponding to the sample set to be matched is determined.
In this embodiment, the first negative sample proportion is used to represent a ratio between the number of negative samples and the total number of samples in the entire sample set to be matched. After the sample set to be matched is obtained, the computer device 10 may read the sample type flag of each sample in the sample set to be matched to determine how many negative samples and positive samples exist in the sample set to be matched, and then correspondingly calculate a first negative sample ratio of the sample set to be matched.
Optionally, referring to fig. 3, fig. 3 is a flowchart illustrating the sub-steps included in step S210 in fig. 2. In this embodiment, the step S210 includes a sub-step S211 and a sub-step S212.
And a substep S211 of counting the number of samples in the sample set to be matched and the number of negative samples in the sample set to be matched.
And a substep S212 of performing proportional operation on the number of the negative samples in the sample set to be matched and the number of the samples in the sample set to be matched, wherein the number of the negative samples is obtained through statistics, so that a first negative sample proportion is obtained.
Referring to fig. 2 again, in step S220, the raw scores of all samples in the sample set to be matched are obtained, and the second negative sample proportion of the sample set to be matched, which corresponds to different raw score ranges, is determined, so as to obtain the corresponding relationship between the second negative sample proportion and the raw score range.
In this embodiment, the original scoring range may be a single-boundary numerical range in which a certain original scoring value is used as the upper scoring limit, a single-boundary numerical range in which a certain original scoring value is used as the lower scoring limit, or a double-boundary numerical range in which two different original scoring values are used as the lower scoring limit and the upper scoring limit, respectively. The computer device 10 may perform data processing on the specific data of each sample in the acquired sample set to be matched to obtain an original score corresponding to the sample; the computer device 10 may also calculate the raw score for each sample in the set of samples to be matched by obtaining the raw score from the raw score calculating device.
The computer device 10 may directly generate a plurality of raw scoring ranges according to the double-boundary value range, and only the configuration process for such raw scoring ranges requires that the length of the scoring interval is unchanged, and the mean value between the upper scoring limit and the lower scoring limit is increased by a preset scoring interval (e.g., 3 or 4), so as to obtain a plurality of different raw scoring ranges.
The computer device 10 may also generate a plurality of raw scoring ranges directly from a single bounded numerical range having an upper scoring limit, i.e., such raw scoring ranges are expressed in terms of scoring values less than the upper scoring limit, which may be incremented at preset scoring intervals (e.g., 5 or 9) to provide a plurality of different raw scoring ranges.
The computer device 10 may also generate a plurality of raw scoring ranges in a single bounded numerical range having a lower scoring limit, i.e., such raw scoring ranges are expressed in terms of scoring values greater than the lower scoring limit, which may be incremented by a preset scoring interval (e.g., 3 or 7) to provide a plurality of different raw scoring ranges.
After the computer device 10 obtains the original score value of each sample in the sample set to be matched, the negative sample proportion of the target sample corresponding to the sample set to be matched in different original score ranges, that is, the second negative sample proportion of the sample set to be matched corresponding to different original score ranges, can be calculated according to the original score value of each sample, and the corresponding relationship between the different original score ranges and the second negative sample proportion is determined.
Optionally, referring to fig. 4, fig. 4 is a flowchart illustrating the sub-steps included in step S220 in fig. 2. In this embodiment, the step of determining the second negative sample proportion corresponding to different raw score ranges of the sample set to be matched in step S220 may include sub-steps S221 and S222.
And a substep S221, aiming at each original scoring range, screening out a target sample with the corresponding original scoring in the original scoring range from the sample set to be matched according to the original scoring of each sample in the sample set to be matched.
In the substep S222, a proportional operation is performed on the number of negative samples included in the target sample and the number of target samples to obtain a second negative sample proportion corresponding to the original scoring range.
Referring to fig. 2 again, in step S230, a target proportion coefficient corresponding to each of the plurality of final score default values is obtained, and a target negative sample proportion corresponding to each of the final score default values is calculated according to the first negative sample proportion.
In this embodiment, the computer device 10 may obtain a plurality of final score preset values configured by a score card designer according to a score card design standard and a target scaling factor of each final score preset value by reading data from the memory 11. After the computer device 10 obtains the target scaling factor of each final score preset value, the target negative sample proportion corresponding to each final score preset value can be obtained by multiplying each target scaling factor by the first negative sample proportion.
Step S240, determining a target raw scoring range of each final scoring preset value according to the target negative sample ratio corresponding to each final scoring preset value and the corresponding relationship between the second negative sample ratio and the raw scoring range.
In this embodiment, after the computer device 10 obtains the target negative sample proportion corresponding to each final score preset value, the original score range corresponding to the target negative sample proportion may be queried in the corresponding relationship between the determined second negative sample proportion and the original score range, and the queried original score range is used as the target original score range of the final score preset value corresponding to the target negative sample proportion.
And step S250, determining the original score to be mapped corresponding to each final score preset value according to the respective target original score range of all the final score preset values.
In this embodiment, after the computer device 10 obtains the target raw scoring range corresponding to each final scoring preset value, the type of the target raw scoring range is determined, and the raw score to be mapped corresponding to the target raw scoring range is determined according to the determination result.
Optionally, referring to fig. 5, fig. 5 is a flowchart illustrating the sub-steps included in step S250 in fig. 2. In this embodiment, the step S250 includes a substep S251 to a substep S255.
And a substep S251, detecting whether the target original scoring range corresponding to each final scoring preset value is a double-boundary numerical range or not according to each final scoring preset value.
In this embodiment, the computer device 10 determines whether each target raw scoring range is a double-boundary numerical range by detecting whether the number of boundaries of the target raw scoring range of each final scoring preset value is two. When the number of the boundaries of a certain target original scoring range is two, determining that the target original scoring range is a double-boundary numerical range, and at this time, the computer device 10 correspondingly performs the substep S252; when the number of the boundaries of a certain target raw scoring range is single, it is determined that the target raw scoring range is not a double-boundary numerical range, and at this time, the computer device 10 correspondingly performs the sub-step S253.
And a substep S252, performing mean calculation on the upper limit value and the lower limit value of the target original score range, and taking the calculated mean value of the scores as the original score to be mapped corresponding to the final score preset value.
In this embodiment, when the computer device 10 detects that the number of the boundaries of a certain target raw score range is two, the computer device 10 calculates an average value between a score upper limit value and a score lower limit value corresponding to the target raw score range, and uses the calculated score average value as a raw score to be mapped of a final score preset value corresponding to the target raw score range.
And a substep S253 of detecting whether the target original scoring range is a single-boundary numerical range with a scoring upper limit value.
In this embodiment, when the computer device 10 detects that the number of the boundaries of a certain target raw scoring range is not two, the computer device 10 will correspondingly determine whether the scoring limit of the target raw scoring range belongs to the upper scoring limit or the lower scoring limit, and at this time, the computer device 10 will determine whether the target raw scoring range is a single-boundary numerical range with the upper scoring limit by detecting the scoring numerical distribution trend of the target raw scoring range. When the computer device 10 determines that the target original scoring range is a single-boundary numerical range with a scoring upper limit value, the computer device 10 correspondingly performs substep S254; when the computer device 10 determines that the target raw score range is not a single-boundary numerical range with a score upper limit, the computer device 10 correspondingly performs the sub-step S255.
And a substep S254, taking the score upper limit value of the target original score range as the original score to be mapped corresponding to the final score preset value.
In this embodiment, when the computer device 10 detects that a target raw score range belongs to a single-boundary numerical range having a score upper limit, the computer device 10 will use the score upper limit of the target raw score range as a raw score to be mapped of a final score preset value corresponding to the target raw score range.
And a substep S255, taking the lower score limit value of the target original score range as the original score to be mapped corresponding to the final score preset value.
In this embodiment, when the computer device 10 detects that a certain target raw scoring range does not belong to the single-boundary numerical range with the upper scoring limit, and does not belong to the double-boundary numerical range, the target raw scoring range corresponds to the single-boundary numerical range with the lower scoring limit, and at this time, the computer device 10 takes the lower scoring limit of the target raw scoring range as the raw score to be mapped of the final scoring preset value corresponding to the target raw scoring range.
Referring to fig. 2 again, in step S260, function construction is performed according to the corresponding relationship between the different final score preset values and the original scores to be mapped, so as to obtain a score mapping function between the final scores and the original scores corresponding to the sample set to be matched.
In this embodiment, after the computer device 10 obtains the original scores to be mapped corresponding to each preset value of final score, the original scores to be mapped are sorted in an ascending manner, and the association relationship between each sorted original score to be mapped and the corresponding preset value of final score is correspondingly established, so that for all the original scores to be mapped, a linear gradient relationship between the preset values of final scores corresponding to two original scores to be mapped which are adjacent in value is obtained, and thus all the linear gradient relationships are directly combined to obtain a score mapping function between the final score and the original score corresponding to the sample set to be matched, thereby ensuring that the final score determined by the score mapping function truly reflects the actual condition of the sample, and improving the score readability.
In an implementation manner of this embodiment, when the number of the obtained linear gradient relationships is multiple, the computer device 10 may output a score mapping function capable of ensuring data consistency between the final scoring result and the actual condition of the sample by performing curve fitting on the linear gradient relationships.
The number of the final score preset values is two, and the two final score preset values are score1 and score2 respectively, where score1 is smaller than score2, the target scale coefficient corresponding to score1 is n1, and the target scale coefficient corresponding to score2 is n 2.
When the computer device 10 acquires a sample set to be matched and determines a first negative sample proportion P1 of the sample set to be matched, a plurality of different original scoring ranges are determined according to a double-boundary numerical value range, a second negative sample proportion P2 of the sample set to be matched, which corresponds to the plurality of original scoring ranges, is calculated according to an original score th of each sample in the sample set to be matched, and the computer device 10 obtains a target negative sample proportion P3 corresponding to score1 by multiplying n1 by P1 and obtains a target negative sample proportion P4 corresponding to score2 by multiplying n2 by P2. Then, the computer device 10 determines a target raw scoring range (th 1-delta, th1+ delta) corresponding to P3 and a target raw scoring range (th 2-delta, th2+ delta) corresponding to P4 according to a corresponding relationship between different raw scoring ranges and different second negative sample ratios P2, where 2 × delta represents a scoring interval length corresponding to the raw scoring range, at this time, the raw score to be mapped corresponding to score1 is th1, and the raw score to be mapped corresponding to score2 is th2. Finally, the computer device 10 calculates the linear association relationship between th1 and score1, and between th2 and score2, to obtain a score mapping function score = a + b × th for expressing the mapping relationship between the final score and the original score corresponding to the sample set to be matched, where b = (score 2-score 1)/(th 2-th 1), and a = score1-b × th1.
After the computer device 10 acquires a sample set to be matched and determines a first negative sample proportion P1 of the sample set to be matched, a plurality of different original scoring ranges are determined according to a single-boundary numerical range with a scoring upper limit value, a second negative sample proportion P2 of the sample set to be matched, which corresponds to the plurality of original scoring ranges, is calculated according to an original score th of each sample in the sample set to be matched, and the computer device 10 multiplies n1 by P1 to obtain a target negative sample proportion P3 corresponding to score1, and multiplies n2 by P2 to obtain a target negative sample proportion P4 corresponding to score 2. Then, the computer device 10 determines a target original scoring range (th < th 1) corresponding to P3 and a target original scoring range (th < th 2) corresponding to P4 according to the corresponding relationship between the different original scoring ranges and the different second negative sample ratios P2, where at this time, the original score to be mapped corresponding to score1 is th1, and the original score to be mapped corresponding to score2 is th2. Finally, the computer device 10 calculates linear correlations between th1 and score1, and between th2 and score2, to obtain a score mapping function score = a + b th for expressing a mapping relationship between the final score and the original score corresponding to the sample set to be matched, where b = (score 2-score 1)/(th 2-th 1), and a = score1-b th1.
After the computer device 10 acquires a sample set to be matched and determines a first negative sample proportion P1 of the sample set to be matched, a plurality of different original scoring ranges are determined according to a single-boundary numerical range with a scoring lower limit value, a second negative sample proportion P2 of the sample set to be matched, which corresponds to the plurality of original scoring ranges, is calculated according to an original score th of each sample in the sample set to be matched, and the computer device 10 multiplies n1 by P1 to obtain a target negative sample proportion P3 corresponding to score1, and multiplies n2 by P2 to obtain a target negative sample proportion P4 corresponding to score 2. Then, the computer device 10 determines a target original scoring range (th > th 1) corresponding to P3 and a target original scoring range (th > th 2) corresponding to P4 according to the corresponding relationship between the different original scoring ranges and the different second negative sample ratios P2, where at this time, the original score to be mapped corresponding to score1 is th1, and the original score to be mapped corresponding to score2 is th2. Finally, the computer device 10 calculates the linear association relationship between th1 and score1, and between th2 and score2, to obtain a score mapping function score = a + b × th for expressing the mapping relationship between the final score and the original score corresponding to the sample set to be matched, where b = (score 2-score 1)/(th 2-th 1), and a = score1-b × th1.
In the present application, in order to ensure that the score map creation device 100 included in the computer device 10 can be normally implemented, the present application implements the functions of the score map creation device 100 by dividing functional modules. The specific components of the score map creation apparatus 100 provided in the present application are described below accordingly.
Optionally, referring to fig. 6, fig. 6 is a schematic functional module diagram of a score mapping creating device 100 according to an embodiment of the present application. In the embodiment of the present application, the score map creation device 100 includes a sample scale determination module 110, a target range determination module 120, a mapping score determination module 130, and a mapping function construction module 140.
The sample proportion determining module 110 is configured to obtain a sample set to be matched, and determine a first negative sample proportion corresponding to the sample set to be matched.
The sample proportion determining module 110 is further configured to obtain original scores of all samples in the sample set to be matched, and determine a second negative sample proportion of the sample set to be matched, where the second negative sample proportion corresponds to different original score ranges, to obtain a corresponding relationship between the second negative sample proportion and the original score range.
The sample proportion determining module 110 is further configured to obtain a target proportion coefficient corresponding to each of the multiple final score preset values, and calculate a target negative sample proportion corresponding to each final score preset value according to the first negative sample proportion.
The target range determining module 120 is configured to determine a target raw scoring range of each final scoring preset value according to a target negative sample ratio corresponding to each final scoring preset value and a corresponding relationship between the second negative sample ratio and the raw scoring range.
The mapping score determining module 130 is configured to determine, according to the target raw score range of each of all the final score preset values, a raw score to be mapped corresponding to each of the final score preset values.
The mapping function constructing module 140 is configured to perform function construction according to a corresponding relationship between different final score preset values and original scores to be mapped, so as to obtain a score mapping function between a final score and an original score corresponding to the sample set to be matched.
It should be noted that the basic principle and the generated technical effect of the score map creation apparatus 100 provided in the embodiment of the present application are the same as those of the score map creation method described above, and for a brief description, reference may be made to the corresponding description content for the score map creation method described above for the sake of brevity.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The apparatus embodiments described above are merely illustrative, and for example, the flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to embodiments of the present application. 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 and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, functional modules in the embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a readable storage medium. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a readable storage medium, which includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method described in the embodiments of the present application. And the aforementioned readable storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In summary, in the score mapping creation method, the score mapping creation device, the computer device, and the readable storage medium provided by the present application, a first negative sample proportion of a sample set to be matched is determined, second negative sample proportions corresponding to different original score ranges of the sample set to be matched are determined according to original scores of all samples in the sample set to be matched, then, a target negative sample proportion corresponding to each final score preset value is calculated according to a target proportion coefficient corresponding to each of a plurality of final score preset values and the first negative sample proportion, a target original score range corresponding to the target negative sample proportion scored by each final preset value is correspondingly determined, then, for each final score preset value, a corresponding original score to be mapped is determined based on the corresponding target original score range, and finally, a score mapping function corresponding to the sample set to be matched, which can ensure data consistency between a final score result and an actual condition of the sample, is constructed according to a corresponding relationship between the final score preset value and the original score to be mapped, so that the final score determined by the score mapping function can reflect an actual condition of the sample, and readability of the sample is improved.
The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (7)
1. A score map creation method, the method comprising:
obtaining a sample set to be matched, and determining a first negative sample proportion corresponding to the sample set to be matched;
acquiring original scores of all samples in the sample set to be matched, and determining second negative sample proportions of the sample set to be matched, which correspond to different original score ranges, so as to obtain a corresponding relation between the second negative sample proportions and the original score ranges;
acquiring target proportion coefficients corresponding to a plurality of final score preset values respectively, and calculating a target negative sample proportion corresponding to each final score preset value according to the first negative sample proportion;
determining a target original scoring range of each final scoring preset value according to the target negative sample proportion corresponding to each final scoring preset value and the corresponding relation between the second negative sample proportion and the original scoring range;
determining original scores to be mapped corresponding to the final score preset values according to the respective target original score ranges of all the final score preset values;
performing function construction according to the corresponding relation between different final score preset values and original scores to be mapped to obtain a score mapping function between the final scores and the original scores corresponding to the sample set to be matched;
determining the original score to be mapped corresponding to each final score preset value according to the respective target original score range of all the final score preset values, wherein the determining comprises the following steps:
detecting whether a target original scoring range corresponding to each final scoring preset value is a double-boundary numerical range or not according to each final scoring preset value;
if the target original scoring range is detected to be a double-boundary numerical range, performing mean value calculation on the upper limit value and the lower limit value of the scoring of the target original scoring range, and taking the calculated scoring mean value as the original scoring to be mapped corresponding to the final scoring preset value;
if the target original scoring range is not detected to be a double-boundary numerical range, detecting whether the target original scoring range is a single-boundary numerical range with a scoring upper limit value;
when the target original scoring range is detected to be a single-boundary numerical range with a scoring upper limit value, taking the scoring upper limit value of the target original scoring range as the original score to be mapped corresponding to the final scoring preset value;
and when the target original scoring range is detected not to be a single-boundary numerical range with the upper scoring limit, taking the lower scoring limit of the target original scoring range as the original score to be mapped corresponding to the final scoring preset value.
2. The method of claim 1, wherein determining the first negative sample proportion corresponding to the set of samples to be matched comprises:
counting the number of samples in the sample set to be matched and the number of negative samples in the sample set to be matched;
and carrying out proportional operation on the number of the negative samples in the sample set to be matched and the number of the samples in the sample set to be matched, which are obtained through statistics, so as to obtain the proportion of the first negative samples.
3. The method of claim 1, wherein the determining a second negative sample proportion of the sample set to be matched corresponding to different raw score ranges comprises:
aiming at each original scoring range, screening out a target sample with the corresponding original score in the original scoring range from the sample set to be matched according to the original score of each sample in the sample set to be matched;
and carrying out proportional operation on the number of the negative samples included in the target sample and the number of the target sample to obtain a second negative sample proportion corresponding to the original scoring range.
4. The method of claim 1, wherein the calculating a target negative sample proportion for each final score preset value according to the first negative sample proportion comprises:
and for each final score preset value, multiplying a target proportion coefficient corresponding to the final score preset value by the first negative sample proportion to obtain a target negative sample proportion corresponding to the final score preset value.
5. A score map creation apparatus, the apparatus comprising:
the sample proportion determining module is used for acquiring a sample set to be matched and determining a first negative sample proportion corresponding to the sample set to be matched;
the sample proportion determining module is further used for obtaining original scores of all samples in the sample set to be matched, determining second negative sample proportions of the sample set to be matched, which correspond to different original score ranges, and obtaining a corresponding relation between the second negative sample proportions and the original score ranges;
the sample proportion determining module is further used for obtaining target proportion coefficients corresponding to the plurality of final score preset values respectively, and calculating a target negative sample proportion corresponding to each final score preset value according to the first negative sample proportion;
the target range determining module is used for determining a target original scoring range of each final scoring preset value according to a target negative sample proportion corresponding to each final scoring preset value and a corresponding relation between the second negative sample proportion and the original scoring range;
the mapping score determining module is used for determining the original score to be mapped corresponding to each final score preset value according to the respective target original score range of all the final score preset values;
the mapping function construction module is used for performing function construction according to the corresponding relation between different final score preset values and original scores to be mapped to obtain a score mapping function between the final scores and the original scores corresponding to the sample set to be matched;
the mapping score determining module determines a to-be-mapped original score mode corresponding to each final score preset value according to the respective target original score ranges of all the final score preset values, and the method comprises the following steps:
aiming at each final score preset value, detecting whether a target original score range corresponding to the final score preset value is a double-boundary numerical value range or not;
if the target original scoring range is detected to be a double-boundary numerical range, performing mean value calculation on the upper scoring limit value and the lower scoring limit value of the target original scoring range, and taking the calculated scoring mean value as the original score to be mapped corresponding to the final scoring preset value;
if the target original scoring range is detected not to be a double-boundary numerical range, detecting whether the target original scoring range is a single-boundary numerical range with a scoring upper limit value;
when the target original scoring range is detected to be a single-boundary numerical range with a scoring upper limit value, taking the scoring upper limit value of the target original scoring range as an original score to be mapped corresponding to the final scoring preset value;
and when the target original scoring range is detected not to be a single-boundary numerical range with the upper scoring limit, taking the lower scoring limit of the target original scoring range as the original score to be mapped corresponding to the final scoring preset value.
6. A computer device comprising a processor and a memory, the memory storing machine executable instructions executable by the processor to implement the score map creation method of any one of claims 1 to 4.
7. A readable storage medium on which a computer program is stored, the computer program, when executed by a processor, implementing the score map creation method of any one of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911218610.8A CN110909298B (en) | 2019-12-03 | 2019-12-03 | Score mapping creation method and device, computer equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911218610.8A CN110909298B (en) | 2019-12-03 | 2019-12-03 | Score mapping creation method and device, computer equipment and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110909298A CN110909298A (en) | 2020-03-24 |
| CN110909298B true CN110909298B (en) | 2023-04-07 |
Family
ID=69821503
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911218610.8A Active CN110909298B (en) | 2019-12-03 | 2019-12-03 | Score mapping creation method and device, computer equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110909298B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108153829A (en) * | 2017-12-12 | 2018-06-12 | 北京字节跳动网络技术有限公司 | A kind of resume appraisal procedure and device |
| CN109889891A (en) * | 2019-03-05 | 2019-06-14 | 腾讯科技（深圳）有限公司 | Obtain the method, apparatus and storage medium of target media file |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170220935A1 (en) * | 2016-01-28 | 2017-08-03 | Linkedin Corporation | Member feature sets, group feature sets and trained coefficients for recommending relevant groups |
-
2019
- 2019-12-03 CN CN201911218610.8A patent/CN110909298B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108153829A (en) * | 2017-12-12 | 2018-06-12 | 北京字节跳动网络技术有限公司 | A kind of resume appraisal procedure and device |
| CN109889891A (en) * | 2019-03-05 | 2019-06-14 | 腾讯科技（深圳）有限公司 | Obtain the method, apparatus and storage medium of target media file |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110909298A (en) | 2020-03-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Buonocore et al. | Measuring multiscaling in financial time-series | |
| CN108833458B (en) | Application recommendation method, device, medium and equipment | |
| CN112734559B (en) | Enterprise credit risk evaluation method and device and electronic equipment | |
| CN110705718A (en) | Model interpretation method and device based on cooperative game and electronic equipment | |
| CN111144941A (en) | Merchant score generation method, device, equipment and readable storage medium | |
| CN111062642A (en) | Method and device for identifying industrial risk degree of object and electronic equipment | |
| CN110688433A (en) | Path-based feature generation method and device | |
| CN110909298B (en) | Score mapping creation method and device, computer equipment and readable storage medium | |
| CN110059749B (en) | Method and device for screening important features and electronic equipment | |
| JP6581282B1 (en) | Bankruptcy probability calculation system using artificial intelligence | |
| WO2017073446A1 (en) | Device, method, and program for calculating explanatory variable value | |
| JP4777941B2 (en) | Demand forecasting method and apparatus | |
| CN110796115A (en) | Image detection method and device, electronic equipment and readable storage medium | |
| CN114461899A (en) | Collaborative filtering recommendation method and device for user, electronic equipment and storage medium | |
| CN109242354B (en) | Machining effect evaluation method and machining effect evaluation device | |
| CN111767938A (en) | Abnormal data detection method and device and electronic equipment | |
| CN112835952A (en) | Stock index-based calculation analysis method and system | |
| CN111639195A (en) | Display method and display device of knowledge graph and readable storage medium | |
| CN111128304A (en) | Quality detection method and device for second-generation sequencing data | |
| CN112115316A (en) | Box separation method and device, electronic equipment and storage medium | |
| CN115511014B (en) | Information matching method, device, equipment and storage medium | |
| CN108805692B (en) | Variable selection method and device and server | |
| CN114299043B (en) | Point cloud quality evaluation method and device, electronic equipment and storage medium | |
| CN111125192B (en) | Method and device for determining similarity between objects | |
| JP7089646B2 (en) | Programs, anomaly detection methods and systems |
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 |