Detailed Description
The application will be described in detail hereinafter with reference to the drawings in conjunction with embodiments. It should be noted that, without conflict, the embodiments of the present application and features of the embodiments may be combined with each other.
It should be noted that the terms "first," "second," and the like in the description and the claims of the present invention and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order.
The method according to the first embodiment of the present application may be implemented in a computer terminal or a similar computing device. Taking a computer terminal as an example, fig. 1 is a block diagram of a hardware structure of a computer terminal according to a method for determining an evaluation index according to an embodiment of the present application. As shown in fig. 1, the computer terminal may include one or more (only one is shown in the figure) processors 102 (the processors 102 may include, but are not limited to, a processing means such as a microprocessor MCU or a programmable logic device FPGA), a memory 104 for storing data, and a transmission means 106 for communication functions. It will be appreciated by those of ordinary skill in the art that the configuration shown in fig. 1 is merely illustrative and is not intended to limit the configuration of the electronic device described above. For example, the computer terminal may also include more or fewer components than shown in FIG. 1, or have a different configuration than shown in FIG. 1.
The memory 104 may be used to store a computer program, for example, a software program of application software and a module, such as a computer program corresponding to a method for determining an evaluation index in an embodiment of the present invention, and the processor 102 executes the computer program stored in the memory 104 to perform various functional applications and data processing, that is, to implement the above-described method. Memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include memory remotely located relative to the processor 102, which may be connected to the computer terminal via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The transmission means 106 is arranged to receive or transmit data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider of a computer terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, simply referred to as a NIC) that can connect to other network devices through a base station to communicate with the internet. In one example, the transmission device 106 may be a Radio Frequency (RF) module, which is used to communicate with the internet wirelessly.
An embodiment of the present invention provides a method for determining an evaluation index, which is applied to the computer terminal, and fig. 2 is a flowchart of the method for determining an evaluation index according to an embodiment of the present invention, as shown in fig. 2, where the flowchart includes the following steps:
Step S202, a target data structure corresponding to a target object in a strategy analysis module is obtained, wherein the target data structure comprises at least one of information of the target object, application information of the target object, deposit information of the target object and decision data information of the target object, and a decision generated by the strategy analysis module is used for indicating whether resources are provided for the target object or not, and the decision data information comprises grading card return information and triggering rule information;
Step S204, inputting the target data structure into a strategy monitoring model to obtain a target evaluation report of the target data structure, wherein the strategy monitoring model is trained by using a plurality of groups of data through machine learning, each group of data in the plurality of groups of data comprises the target data structure and a target evaluation report corresponding to the target data structure, the target evaluation report corresponds to an analysis report of return information of the grading card, and the analysis report comprises a grading card characteristic quantity IV value analysis report, a grading card stability analysis report, a grading card K-S statistical analysis report and a grading card Nile coefficient statistical analysis report;
Step S206, judging whether the target evaluation index in the target evaluation report reaches an expected index or not so as to determine whether the decision meets a preset condition or not.
The method comprises the steps of obtaining a target data structure corresponding to a target object in a strategy analysis module, wherein the target data structure comprises at least one of information of the target object, application information of the target object, deposit information of the target object and decision data information of the target object, a decision generated by the strategy analysis module is used for indicating whether resources are provided for the target object or not, the target data structure is input into a strategy monitoring model to obtain a target evaluation report of the target data structure, the strategy monitoring model is trained by using a plurality of groups of data through machine learning, each group of data in the plurality of groups of data comprises the target data structure and the target evaluation report corresponding to the target data structure, whether the target evaluation index in the target evaluation report reaches an expected index is judged to determine whether the decision accords with preset conditions or not, the problems that in the related technology, the accuracy of the strategy analysis module is reduced due to various external factors such as economic environment, guest group change, data source acquisition and the like are solved, the strategy analysis module is accurately judged by the strategy analysis module, and the strategy analysis condition is accurately judged by the strategy analysis module is further improved.
Optionally, acquiring the target data structure corresponding to the target object in the policy analysis module comprises acquiring result information of the target object in the policy analysis module after executing a target event, wherein the target event is used for indicating that the target object successfully acquires the record of the resource, and acquiring the target data structure corresponding to the target object from the result information.
In order to ensure that the target data structure of the obtained target object better accords with the actual financial situation, when the target data structure is obtained, the result information of the target event of the resource successfully obtained by the target object can be obtained, so that the accuracy of the target data structure is ensured.
For example, the information such as the settlement state of the user after the successful loan is determined, the historical overdue condition and the current overdue condition of the user can be evaluated according to the repayment behavior of the user, at this time, the linkage analysis of decision data and credit repayment performance data can be realized by associating the application number in the application information table with the application number in the loan information table, so that the real-time monitoring, the passing rate conditions such as the application number, the success number of credit, the credit passing rate, the anti-fraud refusal and the like are realized, the average credit line condition, the passing rate conditions of the number of hits, the passing number and the refusal number of each policy are combined, and the flexible diversified analysis and the credit repayment performance data tracking are performed by combining the credit performance data, so that the stability and the accuracy of the scoring model are monitored.
Optionally, the strategy monitoring model comprises a plurality of evaluation indexes, the target data structure is input into the strategy monitoring model to obtain a target evaluation report of the target data structure, the strategy monitoring model comprises the steps of determining an evaluation strategy corresponding to the target data structure according to the input target data structure, determining a target evaluation index corresponding to the evaluation strategy from a plurality of target evaluation indexes, analyzing the target data structure through the target evaluation index corresponding to the evaluation strategy, and determining the target evaluation report of the target data structure according to an analysis result.
In short, in order to ensure the pertinence of the policy monitoring model, the evaluation policy of the target data structure may be determined in advance by judging the data information in the target data structure, and then the target evaluation index corresponding to the evaluation policy is determined from multiple target evaluation indexes, the data information is analyzed, and the target evaluation report of the target data structure is determined according to the analysis result.
Optionally, the evaluation index at least comprises one of a score card characteristic quantity IV value, a score card stability contribution index value, a score card K-S statistic value and a score card coefficient value.
Optionally, judging whether the target evaluation index in the target evaluation report reaches an expected index or not to determine whether the decision meets a preset condition or not, wherein the method comprises the steps of acquiring a threshold range of expected indexes corresponding to a plurality of target evaluation indexes in the target evaluation report when the target evaluation indexes in the target evaluation report are multiple, determining that a strategy analysis module corresponding to the target evaluation report meets the preset condition when the target evaluation indexes meet the threshold ranges of the expected indexes, determining that the decision generated by the strategy analysis module meets the requirement when the target evaluation indexes do not meet the threshold ranges of the expected indexes, and determining that the strategy analysis module corresponding to the target evaluation report does not meet the preset condition when the target evaluation indexes do not meet the threshold ranges of the expected indexes, wherein the decision generated by the strategy analysis module does not meet the requirement and resetting the strategy analysis module.
That is, since there may be multiple target evaluation indexes in the target data structure, but the requirements of different target objects on providing resources are different, after the threshold ranges of multiple expected indexes corresponding to multiple target evaluation indexes corresponding to the target data structure are obtained, the multiple target evaluation indexes are further judged, after all target evaluation indexes are determined to meet the threshold ranges of the expected indexes, the decision generated by the policy analysis module is confirmed to meet the requirements, and the policy analysis module can be smoothly executed without adjustment, when the target evaluation indexes which do not meet the threshold ranges of the expected indexes appear, the decision generated by the policy analysis module is not met, and the policy analysis module needs to be reset according to actual situations. The effectiveness of the strategy analysis module is analyzed through the strategy monitoring model, whether the decision made by the strategy analysis module deviates from the expected or not is judged, so that the analysis strategy of the decision analysis module is adjusted, and the accuracy of the strategy analysis module under the condition of changing external conditions is improved.
Optionally, after judging whether the target evaluation index in the target evaluation report reaches the expected index to determine whether the policy analysis module meets the preset condition, the method further comprises executing the decision generated by the policy analysis module and storing decision data information in the target evaluation report corresponding to the policy analysis module under the condition that the policy analysis module is confirmed to meet the preset condition.
In short, after determining that the policy analysis module meets a preset condition, that is, the accuracy of the policy analysis module meets an application threshold, the process of obtaining a decision is not deviated from expectations, further, according to the judgment result of the policy analysis module, it is determined that resources are provided for the target object or resources cannot be provided for the target object, decision data information corresponding to the target object is determined according to the judgment result, when the resources are provided for the target object, reference is made, the time interval of resource release is quickened, and multiple successful records of the target object can be saved, and when the successful records are executed again, the successful records can be processed preferentially, and the records of the number of times of using the validity of the policy analysis module and the target evaluation report corresponding to the policy analysis module are saved in a database in a one-to-one correspondence.
In order to better understand the determination flow of the evaluation index, the following description is provided with reference to an alternative embodiment, but is not limited to the technical solution of the embodiment of the present invention.
An alternative embodiment of the invention provides a consumption finance oriented wind control strategy monitoring system, which comprises a strategy monitoring data structure module 32 and a strategy model monitoring analysis module 34. The policy monitoring data structure module 32 includes information data (corresponding to a target object in the embodiment of the present invention) that needs to be collected when a user consumes a financial application (corresponding to a target data structure in the embodiment of the present invention), and the policy model monitoring analysis module 34 is configured to analyze the user information data stored in the policy monitoring data structure module 32 through a monitoring scoring model (corresponding to a policy monitoring model in the embodiment of the present invention), so as to realize monitoring of a credit wind control policy.
It should be noted that, as shown in fig. 4, the detailed data structure in the policy monitoring data structure module 32 is shown in fig. 4, the application information stored in the policy monitoring data structure module 32 includes user information, deposit information, and decision result information, the decision result information includes a score card return information and trigger rule information, and the score card return information can perform corresponding conversion according to the corresponding feature variable information, and in addition, since the decision result is affected by the derivative variable, the decision result information also includes derivative variable information. The user information also comprises user credit information, contact person information and fraud information, wherein the user credit information comprises user loan sign information and user credit card credit information, and the user inquires information.
Optionally, according to the characteristics of the consumption financial business, by determining input variables and output variables of a decision engine in the consumption financial wind control decision process and log data generated by the decision engine in the risk decision making process, a data structure of corresponding decision data is designed, so that the storage and processing of data monitored by a subsequent risk strategy are facilitated, and a foundation is laid for user portrait change, user asset quality analysis and user behavior analysis in lending.
For example, in the process of risk decision, because one application corresponds to one user, and one user corresponds to multiple credit records, such as checking out and handling multiple credit cards, multiple loans on a pedestrian credit, and a pedestrian credit inquiry record or handling multiple loan products internally, the borrower has multiple contacts, and when the decision engine outputs, the loan application may hit multiple rules and the like in one-to-many condition, at this time, a one-to-many table level association relationship needs to be established to support the input and output of risk decisions, and derived variable data generated in the decision process. When the user finally pays through a risk decision, after the user signs a contract, a consumer financial service institution generates a repayment plan of each period of each contract, wherein the repayment plan comprises repayment date, repayment principal, repayment interest, repayment default interest, daily synchronization repayment statement medium repayment date, repayment principal, repayment interest, repayment penalty information and reduction information, and information such as settlement state is determined, according to the repayment behavior performance of the user, the historical overdue condition and the current overdue condition of the user can be evaluated, at the moment, the association between decision data and credit repayment performance data can be realized through application numbers in an application information form and application numbers in a loan information form, and further real-time monitoring, the passing rate conditions such as the application number, the credit passing rate, the anti-fraud refusal and the like, the average credit line condition, the passing number of each policy, the passing rate conditions of the passing number and the refusal number, and the credit performance data are combined, flexible diversified analysis and repayment data tracking are carried out, and the stability of a grading model is monitored.
As shown in fig. 5, further, the application information of the user in the application information table is compared with the corresponding client information recorded in the system, and the loan information in the system is combined for comprehensive analysis, so that the stability of the monitoring scoring model is ensured.
Optionally, the system monitors the daily feeding amount, the trial batch, the throughput, the paying amount, the trial passing rate, the batch amount, the batch verification, the paying amount and the paying amount in real time, and the specific table structure is shown in table 1:
TABLE 1
Optionally, the analysis of rule offence condition included in the decision result information may take the rule as a unit, count the number of persons triggered by the single rule, and count the final result corresponding to the single rule, and the specific table structure may be as shown in table 2:
TABLE 2
When the approval passing rate suddenly decreases, the service personnel can analyze what causes cause the passing rate to decrease through the monitoring report, whether the passing rate decreases due to the reject rule or not, which causes the passing rate to decrease, and through the policy analysis logic, the reject data distribution ratio of each rule is compared and analyzed to find out the rule with higher ratio, then the variables corresponding to the rule (corresponding to the target feature values in the embodiment of the invention) are analyzed, and finally the air control policy is formulated.
Optionally, the monitoring scoring model corresponds to a score card feature quantity IV (information Value, information value is abbreviated as IV) value analysis report, the feature quantity is a variable corresponding to each score card, the goal of the scoring model is to distinguish good clients and bad clients, and the bad clients are non-target clients identified by a company, for example, overdue times exceeding a set number of times are exceeded. The analysis report of the feature quantity IV of the grading card is further expressed by WOE (Weight Of Evidence, evidence weight, abbreviated as WOE) codes, when WOE codes are calculated, grouping processing is needed according to different variables, and after grouping, the calculation formula of WOE for the ith group is as follows: pyi is the proportion of the offending clients in the group to the offending clients in all samples, pni is the proportion of the non-offending clients in the group to the non-offending clients in all samples. It will also be appreciated that the greater the WOE, the greater the difference in the ratio of offending and non-offending customers in the current group and this ratio in all samples, the greater the likelihood of a sample breach in the group. Further IV values are determined from the value of WOE as follows: And further calculating the IV value of the whole variable, wherein the formula is as follows: in addition, the influence of the number of variables of each group is considered by the IV value, so that the influence of each group level can be comprehensively reflected.
Alternatively, the score card feature IV value analysis report may be as shown in table 3.
TABLE 3 Table 3
Optionally, the monitoring scoring model corresponds to a score card as a stability analysis report, where PS (Population Stability Index, PSI group stability index, abbreviated as PSI) reflects the stability of the distribution of the verification sample in each fraction segment and the distribution of the modeling sample. In modeling, we often use to screen feature variables, evaluate model stability. Stability is referenced and thus two distributions are required-actual and expected. Wherein training samples (IN THE SAMPLE, INS) are typically used as the expected distribution while validation samples are typically used as the actual distribution during modeling. The verification samples generally include Out of Sample (OOS) and cross-Time Sample (Out of Time, OOT). The calculation formula of PSI is as follows: Where A represents actual and E represents expected, the smaller the PSI value, the smaller the difference between the two distributions, and the more stable the representation. The PSI range and recommendations are shown in table 4 below:
TABLE 4 Table 4
Alternatively, the monitoring scoring model corresponds to a scoring card K-S statistical analysis report, KS (Kolmogorov-smirnov, KS for short) is commonly used for evaluating model discrimination. The larger the discrimination, the stronger the risk ranking capability (ranking ability) of the model, the better the definition between good and bad accounts (bad_rate) tends to be fuzzy, continuous, depending on the actual business needs, KS indicators tend to measure the difference between positive and negative sample distributions from a probabilistic perspective. In general, the larger KS indicates the better the positive and negative sample discrimination, expressed by the following formula:
KS=max{|cum(bad_rate)-cum(good_rate)|}
Alternatively, the score card K-S statistical analysis report may be as shown in Table 5.
TABLE 5
Optionally, the monitoring scoring model corresponds to a score card-based coefficient statistical analysis report, and GINI coefficients are also used for evaluating the risk distinguishing capability of the model. GINI the statistical value measures the area between the cumulative distribution of the bad account number on the good account number and the random distribution curve, and the larger the difference between the good account and the bad account distribution is, the higher GINI index is, which indicates that the risk distinguishing capability of the model is stronger.
The GINI coefficients are calculated by calculating the number of good or bad accounts for each scoring interval. The ratio of the number of accumulated accounts to the total number of accumulated good accounts (accumulated good%) and the ratio of the number of accumulated bad accounts to the total number of bad accounts (accumulated bad%) for each scoring interval are calculated. The curve ADC shown in fig. 6 is derived from the accumulated good account duty cycle and the accumulated bad account duty cycle. And calculating the area of the shadow part, wherein the percentage of the shadow area to the area of the right triangle ABC is GINI.
Alternatively, the score card K-S statistical analysis report may be as shown in Table 6.
TABLE 6
According to the method and the system, the accuracy of credit risk assessment of the online running strategy to the user can be dynamically monitored in real time through the intelligent wind control strategy which needs to be continuously optimized, adjusted, iterated and updated, and the complete consumption financial wind control strategy and model system, and the purposes of data driving business, continuous perfection of the wind control strategy and promotion of wind control management differentiation and credit business humanization can be achieved through analysis of the running strategy monitoring.
In summary, the optional embodiment of the invention stores unstructured log data in the risk process through establishing a table of multi-level father-son relations such as application information, applicant information, credit information, decision result, grading return result, trigger rule information and the like, and stores input and output variables of a decision engine and intermediate data generated in the decision process, so that the passing rate conditions such as the application number, credit success number, credit passing rate, anti-fraud rejection and the like are monitored for the pneumatic control in real time, the average credit limit condition, the passing rate condition of the number and the number of the passes of each strategy and the credit performance data are combined, flexible diversified analysis and credit repayment performance data tracking are carried out, the stability and the effectiveness of a monitoring grading model provide technical data and technical support, and approval monitoring, reject reason analysis, grading grade overdue distribution report, grading card characteristic IV value analysis report, grading card stability analysis report, grading card K-S statistical analysis, grading card coefficient analysis report and the like are optimized and policy and statistics and the like, the passing rate condition is provided for the pneumatic control in real time, the monitoring model is further improved by the policy, the real time is better than the actual monitoring model, the real time is better than the actual monitoring and the actual service can be better carried out, the real time is better than the actual monitoring and the service can be better monitored by driving the policy, and the monitoring model is better controlled by the policy, and the monitoring and the service management model is better controlled by the running and the policy is better stored, the customer portrait analysis is more complete, and the risk assessment of the credit customer is more accurate.
From the description of the above embodiments, it will be clear to a person skilled in the art that the method according to the above embodiments may be implemented by means of software plus the necessary general hardware platform, but of course also by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) comprising several instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the method of the various embodiments of the present invention.
The embodiment also provides a device for determining an evaluation index, which is used for implementing the foregoing embodiments and preferred embodiments, and is not described in detail. As used below, the term "module" may be a combination of software and/or hardware that implements a predetermined function. While the means described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and contemplated.
Fig. 7 is a block diagram of a configuration of an apparatus for determining an evaluation index according to an embodiment of the present invention, as shown in fig. 7, the apparatus including:
(1) The obtaining module 72 is configured to obtain a target data structure corresponding to a target object in the policy analysis module, where the target data structure includes at least one of information of the target object, application information of the target object, deposit information of the target object, and decision data information of the target object, where a decision generated by the policy analysis module is used to indicate whether to provide resources for the target object, and the decision data information includes return information of a scoring card and trigger rule information;
(2) The evaluation module 74 is configured to input the target data structure into a policy monitoring model to obtain a target evaluation report of the target data structure, where the policy monitoring model is trained by using multiple sets of data through machine learning, and each set of data in the multiple sets of data includes a target data structure and a target evaluation report corresponding to the target data structure, where the target evaluation report corresponds to an analysis report of return information of the score card, and the analysis report includes an analysis report of a feature value IV of the score card, an analysis report of stability of the score card, a statistical analysis report of a score card K-S, and a statistical analysis report of a score card K-S coefficient;
(3) A determining module 76 is configured to determine whether the target evaluation index in the target evaluation report reaches an expected index, so as to determine whether the decision meets a preset condition.
The device is used for acquiring a target data structure corresponding to a target object in a strategy analysis module, wherein the target data structure comprises at least one of information of the target object, application information of the target object, deposit information of the target object and decision data information of the target object, a decision generated by the strategy analysis module is used for indicating whether resources are provided for the target object or not, the target data structure is input into a strategy monitoring model to obtain a target evaluation report of the target data structure, the strategy monitoring model is trained by using a plurality of groups of data through machine learning, each group of data in the plurality of groups of data comprises the target data structure and the target evaluation report corresponding to the target data structure, whether the target evaluation index in the target evaluation report reaches an expected index is judged to determine whether the decision accords with preset conditions or not, the technical scheme is adopted, the problems that in the related technology, the accuracy of the strategy analysis module is reduced due to various external factors such as economic environment, guest group change, data source acquisition and the like are solved, the strategy analysis module is effectively judged by the strategy analysis module, and whether the strategy analysis condition is accurately adjusted by the strategy analysis module is further judged by the strategy analysis module.
Optionally, the obtaining module is further configured to obtain result information of the target object in the policy analysis module after executing the target event, where the target event is used to indicate that the target object successfully obtains a record of the resource, and obtain a target data structure corresponding to the target object from the result information.
In order to ensure that the target data structure of the obtained target object better accords with the actual financial situation, when the target data structure is obtained, the result information of the target event of the resource successfully obtained by the target object can be obtained, so that the accuracy of the target data structure is ensured.
For example, the information such as the settlement state of the user after the successful loan is determined, the historical overdue condition and the current overdue condition of the user can be evaluated according to the repayment behavior of the user, at this time, the linkage analysis of decision data and credit repayment performance data can be realized by associating the application number in the application information table with the application number in the loan information table, so that the real-time monitoring, the passing rate conditions such as the application number, the success number of credit, the credit passing rate, the anti-fraud refusal and the like are realized, the average credit line condition, the passing rate conditions of the number of hits, the passing number and the refusal number of each policy are combined, and the flexible diversified analysis and the credit repayment performance data tracking are performed by combining the credit performance data, so that the stability and the accuracy of the scoring model are monitored.
Optionally, the evaluation module further comprises a plurality of evaluation indexes, wherein the evaluation indexes are further used for determining an evaluation strategy corresponding to the target data structure according to the input target data structure, determining target evaluation indexes corresponding to the evaluation strategy from a plurality of target evaluation indexes, analyzing the target data structure through the target evaluation indexes corresponding to the evaluation strategy, and determining a target evaluation report of the target data structure according to an analysis result.
In short, in order to ensure the pertinence of the policy monitoring model, the evaluation policy of the target data structure may be determined in advance by judging the data information in the target data structure, and then the target evaluation index corresponding to the evaluation policy is determined from multiple target evaluation indexes, the data information is analyzed, and the target evaluation report of the target data structure is determined according to the analysis result.
Optionally, the evaluation module at least comprises one of a score card characteristic quantity IV value, a score card stability contribution index value, a score card K-S statistic value and a score card coefficient value.
Optionally, the determining module is further configured to obtain a threshold range of expected indexes corresponding to a plurality of target evaluation indexes when the target evaluation indexes in the target evaluation report are multiple, determine that a policy analysis module corresponding to the target evaluation report meets a preset condition when the target evaluation indexes meet the threshold ranges of the expected indexes, and determine that the policy analysis module corresponding to the target evaluation report does not meet the preset condition when the target evaluation indexes do not meet the threshold ranges of the expected indexes, where the policy analysis module needs to be reset.
That is, since there may be multiple target evaluation indexes in the target data structure, but the requirements of different target objects on providing resources are different, after the threshold ranges of multiple expected indexes corresponding to multiple target evaluation indexes corresponding to the target data structure are obtained, the multiple target evaluation indexes are further judged, after all target evaluation indexes are determined to meet the threshold ranges of the expected indexes, the decision generated by the policy analysis module is confirmed to meet the requirements, and the policy analysis module can be smoothly executed without adjustment, when the target evaluation indexes which do not meet the threshold ranges of the expected indexes appear, the decision generated by the policy analysis module is not met, and the policy analysis module needs to be reset according to actual situations. The effectiveness of the strategy analysis module is analyzed through the strategy monitoring model, whether the decision made by the strategy analysis module deviates from the expected or not is judged, so that the analysis strategy of the decision analysis module is adjusted, and the accuracy of the strategy analysis module under the condition of changing external conditions is improved.
Optionally, the device further comprises a storage module, wherein the storage module is used for executing the decision generated by the policy analysis module and storing the decision data information in the target evaluation report corresponding to the policy analysis module under the condition that the policy analysis module meets the preset condition.
In short, after determining that the policy analysis module meets a preset condition, that is, the accuracy of the policy analysis module meets an application threshold, the process of obtaining a decision is not deviated from expectations, further, according to the judgment result of the policy analysis module, it is determined that resources are provided for the target object or resources cannot be provided for the target object, decision data information corresponding to the target object is determined according to the judgment result, when the resources are provided for the target object, reference is made, the time interval of resource release is quickened, and multiple successful records of the target object can be saved, and when the successful records are executed again, the successful records can be processed preferentially, and the records of the number of times of using the validity of the policy analysis module and the target evaluation report corresponding to the policy analysis module are saved in a database in a one-to-one correspondence.
It should be noted that each of the above modules may be implemented by software or hardware, and the latter may be implemented by, but not limited to, the above modules all being located in the same processor, or each of the above modules being located in different processors in any combination.
An embodiment of the present invention also provides a storage medium including a stored program, wherein the program executes the method of any one of the above.
Alternatively, in the present embodiment, the above-described storage medium may be configured to store program code for performing the steps of:
S1, acquiring a target data structure corresponding to a target object in a strategy analysis module, wherein the target data structure comprises at least one of information of the target object, application information of the target object, deposit information of the target object and decision data information of the target object, and a decision generated by the strategy analysis module is used for indicating whether resources are provided for the target object;
S2, inputting the target data structure into a strategy monitoring model to obtain a target evaluation report of the target data structure, wherein the strategy monitoring model is trained by using a plurality of groups of data through machine learning, and each group of data in the plurality of groups of data comprises the target data structure and the target evaluation report corresponding to the target data structure;
and S3, judging whether a target evaluation index in the target evaluation report reaches an expected index or not so as to determine whether the decision meets a preset condition or not.
An embodiment of the present invention also provides a storage medium including a stored program, wherein the program executes the method of any one of the above.
An embodiment of the invention also provides an electronic device comprising a memory having stored therein a computer program and a processor arranged to run the computer program to perform the steps of any of the method embodiments described above.
Optionally, the electronic apparatus may further include a transmission device and an input/output device, where the transmission device is connected to the processor, and the input/output device is connected to the processor.
Alternatively, in the present embodiment, the above-described processor may be configured to execute the following steps by a computer program:
S1, acquiring a target data structure corresponding to a target object in a strategy analysis module, wherein the target data structure comprises at least one of information of the target object, application information of the target object, deposit information of the target object and decision data information of the target object, and a decision generated by the strategy analysis module is used for indicating whether resources are provided for the target object;
S2, inputting the target data structure into a strategy monitoring model to obtain a target evaluation report of the target data structure, wherein the strategy monitoring model is trained by using a plurality of groups of data through machine learning, and each group of data in the plurality of groups of data comprises the target data structure and the target evaluation report corresponding to the target data structure;
and S3, judging whether a target evaluation index in the target evaluation report reaches an expected index or not so as to determine whether the decision meets a preset condition or not.
Alternatively, in the present embodiment, the storage medium may include, but is not limited to, a U disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory RAM), a removable hard disk, a magnetic disk, or an optical disk, etc. which can store program codes.
Alternatively, specific examples in this embodiment may refer to examples described in the foregoing embodiments and optional implementations, and this embodiment is not described herein.
It will be appreciated by those skilled in the art that the modules or steps of the invention described above may be implemented in a general purpose computing device, they may be concentrated on a single computing device, or distributed across a network of computing devices, they may alternatively be implemented in program code executable by computing devices, so that they may be stored in a memory device for execution by computing devices, and in some cases, the steps shown or described may be performed in a different order than that shown or described, or they may be separately fabricated into individual integrated circuit modules, or multiple modules or steps within them may be fabricated into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the principle of the present invention should be included in the protection scope of the present invention.