Dynamic decision driving method and system based on intelligent rule engine

Abstract

The invention discloses a dynamic decision driving method and system based on an intelligent rule engine, and relates to the technical field of decision automation, and the method comprises the steps: monitoring a financial statement of each investment project under a financial enterprise in real time; collecting investment decision information of the financial enterprise for each investment project, and fusing the investment decision information with the financial statement monitoring data to generate an original data set; personalized configuration of the intelligent rule engine is completed based on the original data set; further perfecting the configured intelligent rule engine in the test environment; and migrating the perfected intelligent rule engine to a production environment, accessing financial statement monitoring data, and dynamically driving the investment decision of each investment project. Through the intelligent rule engine, the system can cope with a complex market environment and make an accurate decision according to real-time data, so that the business process is optimized, the efficiency is improved, and the cost is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of decision automation, and in particular to a dynamic decision-making driving method and system based on an intelligent rule engine. Background Art

[0002] In today's digital age, enterprises are facing an increasingly complex and changing business environment, especially the financial industry, which needs to make decisions quickly and accurately to respond to market changes and customer needs. Traditional decision support systems often rely on hard-coded logic, lack flexibility and scalability, and are difficult to adapt to rapidly changing business needs. Therefore, it is particularly important to develop a dynamic decision-driven method based on an intelligent rule engine. Summary of the invention

[0003] The present invention provides a dynamic decision-making driving method based on an intelligent rule engine, comprising: Step 1: Real-time monitoring of the financial statements of various investment projects under financial enterprises; Step 2: Collect investment decision information of financial enterprises on various investment projects, and integrate the investment decision information with financial statement monitoring data to generate the original data set; Step 3: Complete the personalized configuration of the intelligent rule engine based on the original data set; Step 4: Further improve the configured intelligent rule engine in the test environment; Step 5. Migrate the improved intelligent rule engine to the production environment, access the financial statement monitoring data, and dynamically drive the investment decisions of various investment projects.

[0004] As described above, a dynamic decision-driven method based on an intelligent rule engine is described, in which investment decision information of financial enterprises on various investment projects is collected, and the investment decision information is integrated with financial statement monitoring data to generate an original data set, which is specifically divided into the following sub-steps: Extract and collect investment decision information of financial enterprises on various investment projects from meeting minutes; Create a financial status forecasting model based on monitored historical financial statement data; Calculate the decision support score of the investment project based on the current stage and the financial status of the next stage; The decision support scores are spatially and temporally aligned with the investment decision information, and the aligned data pairs are stored as the original dataset.

[0005] As described above, a dynamic decision-making driven method based on an intelligent rule engine, in which a financial status prediction model is created based on the monitored historical financial statement data, is specifically divided into the following sub-steps: Quantify the financial status of investment projects at various historical stages; The quantified values ​​of the financial status at each stage are grouped in pairs in time series, with the first one used as the model input and the second one as the output, and the training data set is obtained after sorting; A supervised training method is adopted to use the training data set to complete the training and tuning of the financial status prediction model.

[0006] The above-mentioned dynamic decision-making driving method based on the intelligent rule engine, wherein the personalized configuration of the intelligent rule engine is completed based on the original data set, is specifically divided into the following sub-steps: Set the input rules of the intelligent rule engine at the input node; After entering the node, set different judgment entries for different investment projects; Each decision support score in the original data set is used as a rule point, and each investment decision information is used as the return value of the rule point. They are sequentially deployed behind different judgment entrances to form multiple continuous rule lines. Set an output node at the end of each rule line and configure output rules for it as needed.

[0007] The above-mentioned dynamic decision-driven method based on the intelligent rule engine, wherein the configured intelligent rule engine is further improved in the test environment, is specifically divided into the following sub-steps: Create test sets based on real data generated by the production environment; Verify whether the investment decision information generated by the intelligent rule engine for each test data is reasonable; The rule points in the intelligent rule engine are continuously improved according to the verification results until all the test data in the test set are verified.

[0008] The present invention also provides a dynamic decision-driving system based on an intelligent rule engine, comprising: a financial statement monitoring module, a decision collection and fusion module, an intelligent rule engine configuration module, an intelligent rule engine testing module, and a dynamic decision-driving module; Financial statement monitoring module, used to monitor the financial statements of various investment projects under financial enterprises in real time; The decision collection and integration module is used to collect the investment decision information of financial enterprises on various investment projects, and integrate the investment decision information with the financial statement monitoring data to generate the original data set; Intelligent rule engine configuration module, used to complete personalized configuration of the intelligent rule engine based on the original data set; Intelligent rule engine testing module, used to further improve the configured intelligent rule engine in the test environment; The dynamic decision-making driving module is used to migrate the perfected intelligent rule engine to the production environment, access financial statement monitoring data, and dynamically drive investment decisions for various investment projects.

[0009] The beneficial effects achieved by the present invention are as follows: Through the intelligent rule engine, the system can cope with complex market environments and make accurate decisions based on real-time data. Compared with traditional decision support systems, the intelligent rule engine has higher intelligence and adaptability, and can adjust rules in real time according to changes in data, thereby optimizing business processes, improving efficiency and reducing costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0011] Figure 1 This is a flow chart of a dynamic decision-making driving method based on an intelligent rule engine provided in Example 1 of the present application; Figure 2 This is a schematic diagram of a dynamic decision-making driven system based on an intelligent rule engine provided in Example 2 of the present application. DETAILED DESCRIPTION

[0012] The following is a clear and complete description of the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0013] Embodiment 1 like Figure 1 As shown, the first embodiment of the present application provides a dynamic decision-making driving method based on an intelligent rule engine, including: Step S10: Real-time monitoring of the financial statements of various investment projects under the financial enterprise; Financial statements are a decisive factor in evaluating whether an investment project is stable. A project with stable income and expenditure can better cope with market changes and operating risks, and is more worthy of higher investment. Financial companies can require investment projects to provide financial statements regularly to achieve real-time monitoring of project profits and losses.

[0014] Step S20: Collecting the investment decision information of financial enterprises on various investment projects, and integrating the investment decision information with the financial statement monitoring data to generate an original data set; Financial enterprises will make different investment decisions based on the financial statement data of different investment projects. By collecting and integrating these decision information, we can find the correlation and guiding rules, and provide real data support for the intelligent rule engine. Specifically: Step S21: extracting and collecting investment decision information of financial enterprises on various investment projects from the meeting minutes; The investment decisions of financial enterprises on various investment projects are usually decided through meetings. The investment decision information of financial enterprises on various investment projects at different stages can be extracted from the meeting minutes, including: direct investment, diversified investment, abandonment of investment, combination investment, capital increase, capital reduction and other specific decision types. These decision types will be converted into codes through dictionaries, and their specific amounts will be spliced ​​behind the converted codes to form complete investment decision information.

[0015] Step S22: Creating a financial status prediction model based on the monitored historical financial statement data; The financial situation forecasting model can predict the financial situation in the future stage based on the current stage financial situation, which helps enterprises evaluate the profitability of investment projects. Its mathematical expression is: , where Y is the predicted value of the model and X is the input value of the model. is the time value matrix, is the risk factor matrix, is the bias matrix of the model.

[0016] It should be noted that the stage description refers to the investment decision-making cycle of a financial enterprise.

[0017] The training process of the financial status prediction model is as follows: First, the financial status of an investment project at each historical stage needs to be quantified. The quantitative formula is as follows: ,in Quantify the results for the financial status of the investment project at stage d, represents the total income in period t, represents the total expenditure in period t, represents the investment cost in period t, represents the profit in period t, is the sensitivity coefficient of market risk to project profit and loss, K is the discount rate of the investment project, t takes values ​​from 1 to T, and T is the total number of periods in a stage; then the quantitative results of the financial status of each stage are grouped in pairs according to the time sequence, and the previous quantitative result in the group is used as the model input, and the next one is used as the output, and the training data set is obtained after sorting; finally, a supervised training method is adopted to complete the training and tuning of the financial status prediction model using the training data set, and the loss function used in the training process is expressed as: , where L is the returned loss value, is the model prediction value of the jth training data in the training batch, is the expected output value of the jth training data, j ranges from 1 to m, and m is the total number of training data in the training batch.

[0018] Step S23: Calculate the decision support score of the investment project based on the current stage and the financial status of the next stage; Substitute the quantitative values ​​of the current stage and the next stage of financial status into the formula: The decision support score S of the investment project can be obtained, where It represents the quantitative result of the financial status in the future period. Indicates the quantitative results of the current financial situation. Indicates the number of periods between the current stage and the next stage. The weight of the impact of changes in financial conditions on investment decision-making, Indicates the weight of the impact of current financial conditions on investment decision-making.

[0019] Step S24: performing spatiotemporal alignment of the decision support score and the investment decision information, and storing the aligned data pair as the original data set; The decision support scores of the same investment project in the same stage are aligned with the investment decision information, and the aligned data are stored as the original data set.

[0020] Step S30: completing personalized configuration of the intelligent rule engine based on the original data set; The intelligent rule engine can automatically generate the optimal investment decision for the current stage of the investment project based on the input financial statement data. The specific configuration process includes: Step S31: setting input rules of the intelligent rule engine at the input node; The input rules specify how the data should be preprocessed after being input into the intelligent rule engine. In this embodiment, the input data is financial statement data, and the rule point inside the intelligent rule engine is the decision support score. Therefore, the preprocessing part needs to realize the conversion of financial statement data to decision support score, including: extraction of financial statement data at the current stage, quantification of the financial status at the current stage, prediction of the financial status in the next stage, and calculation of decision support score.

[0021] Step S32: after inputting the node, different judgment entries are set for different investment projects; Different investment projects need to be configured with different judgment entries to achieve the effect of project isolation. The pre-processed data will be input into the corresponding judgment entry for subsequent rule judgment.

[0022] Step S33: using each decision support score in the original data set as a rule point and each investment decision information as a return value of the rule point, and sequentially deploying them behind different judgment entrances to form multiple continuous rule lines; In order to achieve low coupling and high cohesion of the intelligent rule engine, each rule point only completes the return of one investment decision information. After the input data enters the corresponding judgment entrance, it will be compared with the rule point data along the rule line. If the absolute difference between the input data and the rule point data is less than the floating threshold, the return flag of the rule point is set to 1 until all the rule points on the rule line are compared. This process is multi-threaded concurrent processing. It should be noted that the floating threshold needs to be configured in advance by the administrator according to the actual situation. If it is not configured in advance, the default floating threshold is 0; the default value of the return flag of the rule point is also 0.

[0023] Step S34: setting an output node at the end of each rule line and configuring output rules for it as needed; The output rule is configured to output the return value set for the rule node with the return identifier 1. The output format can also be configured according to the actual situation. For example, the investment decision information is output together for combined investment for easy reference.

[0024] Step S40: further improving the configured intelligent rule engine in the test environment; To ensure the applicability of the intelligent rule engine, it needs to be further improved based on data generated by real scenarios before it is put into production. The specific steps are as follows: Step S41: Create a test set based on real data generated by the production environment; Pull the financial statement data monitored in real time by the production environment and the investment decision information generated by the meeting at this stage, align them in time and space, and store them as a test set.

[0025] Step S42: Verify whether the investment decision information generated by the intelligent rule engine for each test data is reasonable; Input financial statement data into the intelligent rule engine to verify whether the investment decision information output by the rule engine matches the actual investment decision information. If so, the verification is deemed to have passed; otherwise, the verification is deemed to have failed.

[0026] Step S43: continuously improving the rule points in the intelligent rule engine according to the verification results until all the test data in the test set are verified; Check whether the type coding of the investment decision information output by the intelligent rule engine is consistent with the actual investment decision information. If they are consistent, add a return branch under the rule point involved to return the actual investment decision information corresponding to the input value; if the type coding is inconsistent, add a new rule point for the input value, set the return value of the new rule point to the actual investment decision information, and remove the input value from the floating threshold of the original rule point. Repeated adjustments and verifications are repeated until all test data in the test set are verified.

[0027] Step S50: Migrate the improved intelligent rule engine to the production environment, access the financial statement monitoring data, and dynamically drive the investment decisions of various investment projects; The output interface of the financial statement monitoring data is connected to the input node of the intelligent rule engine, so that it can dynamically output the investment decision information of each investment project at the current stage. The output interface is connected to the specific execution action interface to realize the automatic execution of investment decisions. An approval process can also be added to the output node, which will be automatically executed after approval.

[0028] Embodiment 2 like Figure 2 As shown, the second embodiment of the present application provides a dynamic decision-driving system based on an intelligent rule engine, including: a financial statement monitoring module 21, a decision collection and fusion module 22, an intelligent rule engine configuration module 23, an intelligent rule engine testing module 24, and a dynamic decision driving module 25; The financial statement monitoring module 21 is used to monitor the financial statements of various investment projects of the financial enterprise in real time; Financial statements are a decisive factor in evaluating whether an investment project is stable. A project with stable income and expenditure can better cope with market changes and operating risks, and is more worthy of higher investment. Financial companies can require investment projects to provide financial statements regularly to achieve real-time monitoring of project profits and losses.

[0029] The decision collection and fusion module 22 is used to collect the investment decision information of financial enterprises on various investment projects, and fuse the investment decision information with the financial statement data to generate the original data set; specifically, it includes: a decision information extraction submodule, a financial status prediction submodule, a decision support score calculation submodule, and a data alignment submodule; 1. Decision information extraction submodule, used to extract and collect investment decision information of financial enterprises on various investment projects from meeting records; The investment decisions of financial enterprises on various investment projects are usually decided through meetings. The investment decision information of financial enterprises on various investment projects at different stages can be extracted from the meeting minutes, including: direct investment, diversified investment, abandonment of investment, combination investment, capital increase, capital reduction and other specific decision types. These decision types will be converted into codes through dictionaries, and their specific amounts will be spliced ​​behind the converted codes to form complete investment decision information.

[0030] 2. Financial status forecasting submodule, used to use the financial status forecasting model to forecast the financial status of the next stage; The financial status forecasting model can predict the financial status of the investment project in the future based on the current financial status of the investment project, which helps enterprises evaluate the profitability of investment projects. Its mathematical expression is: , where Y is the predicted value of the model and X is the input value of the model. is the time value matrix, is the risk factor matrix, is the bias matrix of the model.

[0031] It should be noted that the stage description refers to the investment decision-making cycle of a financial enterprise.

[0032] The training process of the financial status prediction model is as follows: First, the financial status of an investment project at each historical stage needs to be quantified. The quantitative formula is as follows: ,in Quantify the results for the financial status of the investment project at stage d, represents the total income in period t, represents the total expenditure in period t, represents the investment cost in period t, represents the profit in period t, is the sensitivity coefficient of market risk to project profit and loss, K is the discount rate of the investment project, t takes values ​​from 1 to T, and T is the total number of periods in a stage; then the quantified results of the financial status of each stage are grouped in pairs according to the time series, the first one is used as the model input, and the second one is used as the output, and the training data set is obtained after sorting; finally, a supervised training method is adopted to complete the training and tuning of the financial status prediction model using the training data set, and the loss function used in the training process is expressed as: , where L is the returned loss value, is the model prediction value of the jth training data in the training batch, is the expected output value of the jth training data, j ranges from 1 to m, and m is the total number of training data in the training batch.

[0033] 3. Decision support score calculation submodule, used to calculate the decision support score of the investment project based on the financial status of the current stage and the next stage; Substitute the quantitative values ​​of the current stage and the next stage of financial status into the formula: The decision support score S of the investment project can be obtained, where It represents the quantitative result of the financial status in the future period. Indicates the quantitative results of the current financial situation. Indicates the number of periods between the current stage and the next stage. The weight of the impact of changes in financial conditions on investment decision-making, Indicates the weight of the impact of current financial conditions on investment decision-making.

[0034] 4. Data alignment submodule, used to align the decision support score with the investment decision information in time and space, and the aligned data pairs are stored as the original data set; The decision support scores of the same investment project in the same stage are aligned with the investment decision information, and the aligned data are stored as the original data set.

[0035] The intelligent rule engine configuration module 23 is used to complete the personalized configuration of the intelligent rule engine based on the original data set; specifically, it includes: an input node configuration submodule, a judgment entry configuration submodule, a rule point configuration submodule, and an output node configuration submodule; 1. Input node configuration submodule, used to set the input rules of the intelligent rule engine input node; The input rules specify how the data should be preprocessed after being input into the intelligent rule engine. In this embodiment, the input data is financial statement data, and the rule point inside the intelligent rule engine is the decision support score. Therefore, the preprocessing part needs to realize the conversion of financial statement data to decision support score, including: extraction of financial statement data at the current stage, quantification of the financial status at the current stage, prediction of the financial status in the next stage, and calculation of decision support score.

[0036] 2. Judgment entry configuration submodule, used to set different judgment entries for different investment projects after inputting the node; Different investment projects need to be configured with different judgment entries to achieve the effect of project isolation. The pre-processed data will be input into the corresponding judgment entry for subsequent rule judgment.

[0037] 3. The rule point configuration submodule is used to use each decision support score in the original data set as a rule point and each investment decision information as the return value of the rule point, and sequentially deploy them behind different judgment entrances to form multiple continuous rule lines; In order to achieve low coupling and high cohesion of the intelligent rule engine, each rule point only completes the return of one investment decision information. After the input data enters the corresponding judgment entrance, it will be compared with the rule point data along the rule line. If the absolute difference between the input data and the rule point data is less than the floating threshold, the return flag of the rule point is set to 1 until all the rule points on the rule line are compared. This process is multi-threaded concurrent processing. It should be noted that the floating threshold needs to be configured in advance by the administrator according to the actual situation. If it is not configured in advance, the default floating threshold is 0; the default value of the return flag of the rule point is also 0.

[0038] 4. Output node configuration submodule, used to set output nodes at the end of each rule line and configure output rules for it as needed; The output rule is configured to output the return value set for the rule node with the return identifier 1. The output format can also be configured according to the actual situation. For example, the investment decision information is output together for combined investment for easy reference.

[0039] The intelligent rule engine testing module 24 is used to further improve the configured intelligent rule engine in the test environment; specifically, it includes: a test set creation submodule, a decision information verification submodule, and an intelligent rule engine tuning submodule; 1. Test set creation submodule, used to create test sets based on real data generated in the production environment; Pull the financial statement data monitored by the real-time environment of the production environment and the investment decision information generated by the meeting at this stage, and store them as a test set after time and space alignment.

[0040] 2. Decision information verification submodule, used to verify whether the investment decision information generated by the intelligent rule engine for each test data is reasonable; Input financial statement data into the intelligent rule engine to verify whether the investment decision information output by the rule engine matches the actual investment decision information. If so, the verification is deemed to have passed; otherwise, the verification is deemed to have failed.

[0041] 3. Intelligent rule engine tuning submodule, which is used to continuously improve the rule points in the intelligent rule engine according to the verification results until all the test data in the test set are verified; Check whether the type coding of the investment decision information output by the intelligent rule engine is consistent with the actual investment decision information. If they are consistent, add a return branch under the rule point involved to return the actual investment decision information corresponding to the input value; if the type coding is inconsistent, add a new rule point for the input value, set the return value of the new rule point to the actual investment decision information, and remove the input value from the floating threshold of the original rule point. Repeated adjustments and verifications are repeated until all test data in the test set are verified.

[0042] Dynamic decision-making driving module 25 is used to migrate the perfected intelligent rule engine to the production environment, access the financial statement monitoring data, and dynamically drive the investment decision of each investment project; The output interface of the financial statement monitoring data is connected to the input node of the intelligent rule engine, so that it can dynamically output the investment decision information of each investment project at the current stage. The output interface is connected to the specific execution action interface to realize the automatic execution of investment decisions. An approval process can also be added to the output node, which will be automatically executed after approval.

[0043] Corresponding to the above embodiment, an embodiment of the present invention provides a computer storage medium, including: at least one memory and at least one processor; The memory is used to store one or more program instructions; The processor is used to run one or more program instructions to execute a dynamic decision-making driving method based on an intelligent rule engine.

[0044] Corresponding to the above-mentioned embodiments, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer storage medium contains one or more program instructions, and the one or more program instructions are used by a processor to execute a dynamic decision-making driven method based on an intelligent rule engine.

[0045] The embodiments disclosed in the present invention provide a computer-readable storage medium, in which computer program instructions are stored. When the computer program instructions are executed on a computer, the computer executes the above-mentioned dynamic decision-making driven method based on an intelligent rule engine.

[0046] In the embodiment of the present invention, the processor may be an integrated circuit chip having the ability to process signals. The processor may be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0047] The methods, steps and logic block diagrams disclosed in the embodiments of the present invention can be implemented or executed. The general processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present invention can be directly embodied as a hardware decoding processor for execution, or can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The processor reads the information in the storage medium and completes the steps of the above method in combination with its hardware.

[0048] The storage medium may be a memory, which may be, for example, a volatile memory or a nonvolatile memory, or may include both volatile and nonvolatile memory.

[0049] Among them, the non-volatile memory can be a read-only memory (ROM), a programmable ROM (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory.

[0050] The volatile memory may be a random access memory (RAM) which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate synchronous DRAM (DDRSDRAM), enhanced synchronous DRAM (ESDRAM), synchronous link DRAM (SLDRAM), and direct RAM bus DRAM (DRRAM).

[0051] The storage media described in the embodiments of the present invention are intended to include, but are not limited to, these and any other suitable types of memory.

[0052] Those skilled in the art will appreciate that in one or more of the above examples, the functions described in the present invention can be implemented using a combination of hardware and software. When software is used, the corresponding functions can be stored in a computer-readable medium or transmitted as one or more instructions or codes on a computer-readable medium. Computer-readable media include computer storage media and communication media, wherein communication media include any media that facilitates the transmission of computer programs from one place to another. Storage media can be any available media that can be accessed by general or special-purpose computers.

[0053] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made on the basis of the technical solution of the present invention should be included in the scope of protection of the present invention.

Claims

1. A dynamic decision-making driving method based on an intelligent rule engine, characterized in that: include: Step 1: Real-time monitoring of the financial statements of various investment projects under financial enterprises; Step 2: Collect investment decision information of financial enterprises on various investment projects, and integrate the investment decision information with financial statement monitoring data to generate the original data set; Step 3: Complete the personalized configuration of the intelligent rule engine based on the original data set; Step 4: Further improve the configured intelligent rule engine in the test environment; Step 5. Migrate the improved intelligent rule engine to the production environment, access the financial statement monitoring data, and dynamically drive the investment decisions of various investment projects.

2. According to claim 1, a dynamic decision-making driving method based on an intelligent rule engine is characterized in that: Collect the investment decision information of financial enterprises on various investment projects, and integrate the investment decision information with the financial statement monitoring data to generate the original data set, which is divided into the following sub-steps: Extract and collect investment decision information of financial enterprises on various investment projects from meeting minutes; Create a financial status forecasting model based on monitored historical financial statement data; Calculate the decision support score of the investment project based on the current stage and the financial status of the next stage; The decision support scores are spatially and temporally aligned with the investment decision information, and the aligned data pairs are stored as the original dataset.

3. A dynamic decision-making driving method based on an intelligent rule engine according to claim 2, characterized in that: Create a financial status forecasting model based on the monitored historical financial statement data, which is divided into the following sub-steps: Quantify the financial status of investment projects at various historical stages; The quantified values ​​of the financial status at each stage are grouped in pairs in time series, with the first one used as the model input and the second one as the output, and the training data set is obtained after sorting; A supervised training method is adopted to use the training data set to complete the training and tuning of the financial status prediction model.

4. The dynamic decision-making driving method based on an intelligent rule engine according to claim 1, characterized in that: Complete the personalized configuration of the intelligent rule engine based on the original data set, which is divided into the following sub-steps: Set the input rules of the intelligent rule engine at the input node; After entering the node, set different judgment entries for different investment projects; Each decision support score in the original data set is used as a rule point, and each investment decision information is used as the return value of the rule point. They are sequentially deployed behind different judgment entrances to form multiple continuous rule lines. Set an output node at the end of each rule line and configure output rules for it as needed.

5. The dynamic decision-making driving method based on an intelligent rule engine according to claim 1, characterized in that: Further improve the configured intelligent rule engine in the test environment, which is divided into the following sub-steps: Create test sets based on real data generated by the production environment; Verify whether the investment decision information generated by the intelligent rule engine for each test data is reasonable; The rule points in the intelligent rule engine are continuously improved according to the verification results until all the test data in the test set are verified.

6. A dynamic decision-making drive system based on an intelligent rule engine, characterized in that: include: Financial statement monitoring module, decision collection and integration module, intelligent rule engine configuration module, intelligent rule engine testing module, dynamic decision driving module; Financial statement monitoring module, used to monitor the financial statements of various investment projects under financial enterprises in real time; The decision collection and integration module is used to collect the investment decision information of financial enterprises on various investment projects, and integrate the investment decision information with the financial statement monitoring data to generate the original data set; Intelligent rule engine configuration module, used to complete personalized configuration of the intelligent rule engine based on the original data set; Intelligent rule engine testing module, used to further improve the configured intelligent rule engine in the test environment; The dynamic decision-making driving module is used to migrate the perfected intelligent rule engine to the production environment, access financial statement monitoring data, and dynamically drive investment decisions for various investment projects.

7. The dynamic decision-making driving system based on an intelligent rule engine according to claim 6, characterized in that: The decision collection and fusion module specifically includes: decision information extraction submodule, financial status prediction submodule, decision support score calculation submodule, and data alignment submodule; The decision information extraction submodule is used to extract and collect the investment decision information of financial enterprises on various investment projects from the meeting records; The financial status forecasting submodule is used to use the financial status forecasting model to forecast the financial status of an investment project in the next stage; The decision support score calculation submodule is used to calculate the decision support score of the investment project in combination with the financial status of the current stage and the next stage; The data alignment submodule is used to align the decision support score with the investment decision information in time and space, and the aligned data pairs are stored as the original data set.

8. The dynamic decision-making driving system based on an intelligent rule engine according to claim 6, characterized in that: The intelligent rule engine configuration module specifically includes: input node configuration submodule, judgment entry configuration submodule, rule point configuration submodule, and output node configuration submodule; The input node configuration submodule is used to set the input rules of the intelligent rule engine input node; The judgment entry configuration submodule is used to set different judgment entries for different investment projects after the input node; The rule point configuration submodule is used to use each decision support score in the original data set as a rule point and each investment decision information as the return value of the rule point, and sequentially deploy them behind different judgment entrances to form multiple continuous rule lines; The output node configuration submodule is used to set the output node at the end of each rule line and configure the output rules for it as needed.

9. The dynamic decision-making driving system based on an intelligent rule engine according to claim 6, characterized in that: The intelligent rule engine test module specifically includes: test set creation submodule, decision information verification submodule, and intelligent rule engine tuning submodule; The test set creation submodule is used to create test sets based on real data generated by the production environment; The decision information verification submodule is used to verify whether the investment decision information generated by the intelligent rule engine for each test data is reasonable; The intelligent rule engine tuning submodule is used to continuously improve the rule points in the intelligent rule engine according to the verification results until all the test data in the test set are verified.

10. A computer storage medium, characterized in that: include: at least one memory and at least one processor; A memory for storing one or more program instructions; A processor, used to run one or more program instructions to execute a dynamic decision-making driving method based on an intelligent rule engine as described in any one of claims 1-5.

Images