Business rule data processing method, device, equipment and medium based on big data

Abstract

The embodiment of the present invention relates to the field of artificial intelligence, and discloses a business rule data processing method, device, equipment and medium based on big data, the method comprising: obtaining evaluation data of one or more business rules associated with the business in the database of the big data platform; inputting the evaluation data as a training set into a preset machine learning model for training to obtain a rule priority prediction model; inputting the evaluation data of the first business rule associated with the target business into the rule priority prediction model to determine the target priority of the first business rule; adjusting the current priority of the first business rule according to the target priority, and generating a second business rule, when the second business rule is successfully verified, confirming the release of the second business rule, realizing intelligent adjustment of the priority of the business rules, and improving the accuracy and efficiency of business rule data processing. The present invention relates to blockchain technology, such as writing evaluation data into a blockchain for use in scenarios such as data forensics.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence, and in particular to a business rule data processing method, device, equipment and medium based on big data. Background Art

[0002] At present, with the development of artificial intelligence technology, more and more businesses in life are gradually becoming intelligent to meet users' needs for intelligent and automated services. In the process of intelligentization, various services usually need to set different business rule data to intelligently control the functions of various services according to various business rule data. When various business rule data are not applicable to the latest business functions, it is necessary to adjust the business rule data of various services according to the latest business functions to meet the latest needs of business functions.

[0003] However, the traditional business rule data adjustment method mainly adjusts the business rule data manually through human intervention, which is cumbersome, inefficient and low in accuracy. Therefore, how to more effectively improve the accuracy and efficiency of adjusting business rules has become the focus of research. Summary of the invention

[0004] The embodiments of the present invention provide a business rule data processing method, apparatus, device and medium based on big data, which realizes intelligent adjustment of business rule priorities and can improve the accuracy and efficiency of business rule data processing.

[0005] In a first aspect, an embodiment of the present invention provides a business rule data processing method based on big data, which is applied to a data management platform, wherein the data management platform is communicatively connected with the big data platform, and the method includes:

[0006] Obtaining evaluation data of one or more business rules associated with the business within a preset time range in a database of the big data platform, wherein the evaluation data includes priority data of each of the one or more business rules;

[0007] The evaluation data of each business rule is used as a training set, and the training set is input into a preset machine learning model for training to obtain a rule priority prediction model;

[0008] Obtaining evaluation data of a first business rule associated with a target business in a database of the big data platform, and inputting the evaluation data of the first business rule into the rule priority prediction model to determine a target priority corresponding to the first business rule;

[0009] The current priority of the first business rule is adjusted according to the target priority, and a second business rule is generated according to the adjusted target priority, and the second business rule is verified. When the verification is successful, the second business rule is confirmed to be released.

[0010] Furthermore, inputting the evaluation data of the first business rule into the rule priority prediction model to determine the target priority corresponding to the first business rule includes:

[0011] Inputting the evaluation data of the first business rule into the rule priority prediction model to obtain a priority interval corresponding to the evaluation data of the first business rule;

[0012] Obtain one or more third business rules other than the first business rule from the one or more business rules associated with the business in the database of the big data platform, select a target priority that is not used by the one or more third business rules from the priority interval, and confirm that the target priority is the priority of the first business rule.

[0013] Further, the selecting, from the priority interval, a target priority that is not used by the one or more third business rules includes:

[0014] Detecting whether each priority in the priority interval is used by the one or more business rules;

[0015] If the detection result is yes, determining the business rule to be adjusted from the one or more third business rules, adjusting the priority of the business rule to be adjusted to a candidate priority that is not used by the one or more third business rules, and determining the priority of the business rule to be adjusted before adjustment as the target priority;

[0016] If the detection result is no, then one or more priorities that are not used by the one or more third business rules are obtained, and the maximum priority is selected from each priority of the one or more priorities as the target priority.

[0017] Furthermore, the training set is input into a preset machine learning model for training to obtain a rule priority prediction model, including:

[0018] Extracting an evaluation feature vector from the evaluation data of each business rule in the training set;

[0019] The evaluation feature vector is input into the preset machine learning model for training to obtain the rule priority prediction model.

[0020] Furthermore, the evaluation data also includes priority data, accuracy data and alarm data of each business rule; and extracting the evaluation feature vector from the evaluation data of each business rule in the training set includes:

[0021] Extracting a priority vector from the priority data of each business rule, extracting a precision vector from the precision data, and extracting an alarm vector from the alarm data;

[0022] The step of inputting the evaluation feature vector into the preset machine learning model for training to obtain the rule priority prediction model comprises:

[0023] Inputting the priority vector, accuracy vector and alarm vector corresponding to the evaluation data of each business rule into the machine learning model to obtain a loss function value;

[0024] Comparing the loss function value with the target loss function value, and when the comparison result does not meet the preset conditions, adjusting the model parameters of the machine learning model according to the comparison result;

[0025] Inputting the priority vector, accuracy vector and alarm vector corresponding to the evaluation data of each business rule into the machine learning model after adjusting the model parameters for retraining;

[0026] When the comparison result between the retrained loss function value and the target loss function value meets the preset condition, it is determined that the rule priority prediction model is obtained.

[0027] Furthermore, the priority vector, the accuracy vector and the alarm vector corresponding to the evaluation data of each business rule are input into the machine learning model to obtain the loss function value, including:

[0028] Inputting the priority vector, the accuracy vector and the alarm vector corresponding to the evaluation data of each business rule into the first network layer of the machine learning model to obtain the target vector features corresponding to the evaluation data of each business rule;

[0029] The target vector feature is input into the second network layer of the machine learning model to obtain the loss function value.

[0030] Furthermore, the first network layer includes a first layer, a second layer, and a third layer; the priority vector, the accuracy vector, and the alarm vector corresponding to the evaluation data of each business rule are input into the first network layer of the machine learning model to obtain the target vector features corresponding to the evaluation data of each business rule, including:

[0031] Inputting the priority vector into the first layer to obtain a first vector feature corresponding to the priority vector;

[0032] Inputting the first vector feature and the precision vector into the second layer to obtain a second vector feature corresponding to the first vector feature and the precision vector;

[0033] The first vector feature, the second vector feature and the warning vector are input into the third layer to obtain the target vector feature corresponding to the first vector feature, the second vector feature and the warning vector.

[0034] In a second aspect, an embodiment of the present invention provides a business rule data processing device based on big data, which is applied to a data management platform, wherein the data management platform is communicatively connected with the big data platform, and the device comprises:

[0035] An acquisition unit, used to acquire evaluation data of one or more business rules associated with the business within a preset time range in a database of the big data platform, wherein the evaluation data includes priority data of each business rule in the one or more business rules;

[0036] A training unit, used to use the evaluation data of each business rule as a training set, and input the training set into a preset machine learning model for training to obtain a rule priority prediction model;

[0037] A determination unit, configured to obtain evaluation data of a first business rule associated with a target business in a database of the big data platform, and input the evaluation data of the first business rule into the rule priority prediction model to determine a target priority corresponding to the first business rule;

[0038] An adjustment unit is used to adjust the current priority of the first business rule according to the target priority, generate a second business rule according to the adjusted target priority, and verify the second business rule, and when the verification is successful, confirm the release of the second business rule.

[0039] In a third aspect, an embodiment of the present invention provides a computer device, comprising a processor and a memory, wherein the memory is used to store a computer program, the computer program includes a program, and the processor is configured to call the computer program to execute the method of the first aspect above.

[0040] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer storage medium stores a computer program, and the computer program is executed by a processor to implement the method of the first aspect.

[0041] The embodiment of the present invention can obtain the evaluation data of one or more business rules associated with the business within a preset time range in the database of the big data platform, and the evaluation data includes the priority data of each business rule in the one or more business rules; use the evaluation data of each business rule as a training set, and input the training set into a preset machine learning model for training to obtain a rule priority prediction model; obtain the evaluation data of the first business rule associated with the target business in the database of the big data platform, and input the evaluation data of the first business rule into the rule priority prediction model to determine the target priority corresponding to the first business rule; adjust the current priority of the first business rule according to the target priority, generate a second business rule according to the adjusted target priority, and verify the second business rule, and when the verification is successful, confirm the release of the second business rule. The embodiment of the present invention realizes the intelligent adjustment of the priority of business rules by adding the evaluation data of business rules including priority data in model training, and improves the accuracy and efficiency of business rule data processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying any creative work.

[0043] Figure 1 is a schematic flow chart of a business rule data processing method based on big data provided by an embodiment of the present invention;

[0044] Figure 2 is a schematic diagram of rule information of a business rule provided by an embodiment of the present invention;

[0045] Figure 3 is a schematic block diagram of a business rule data processing device based on big data provided by an embodiment of the present invention;

[0046] Figure 4 It is a schematic block diagram of a computer device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0047] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions 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 ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0048] The business rule data processing method based on big data provided in the embodiments of the present invention can be applied to a business rule data processing device based on big data. In some embodiments, the business rule data processing device based on big data is arranged in a data management platform. In some embodiments, the data management platform establishes a communication connection with the big data platform. In some embodiments, the data management platform can be a computer device. In some embodiments, the computer device includes but is not limited to one or more of a smart phone, a tablet computer, a laptop computer, etc.

[0049] An embodiment of the present invention can obtain evaluation data of one or more business rules associated with a business within a preset time range in a database of a big data platform, wherein the evaluation data includes priority data of each business rule in the one or more business rules; use the evaluation data of each business rule as a training set, and input the training set into a preset machine learning model for training to obtain a rule priority prediction model; obtain evaluation data of a first business rule associated with a target business in the database of the big data platform, and input the evaluation data of the first business rule into the rule priority prediction model to determine a target priority corresponding to the first business rule; adjust the current priority of the first business rule according to the target priority, generate a second business rule according to the adjusted target priority, and verify the second business rule, and when the verification is successful, confirm the release of the second business rule.

[0050] The embodiment of the present invention obtains a rule priority prediction model by adding evaluation data of each business rule including priority data during model training, thereby realizing intelligent adjustment of the priority of business rules and helping to improve the efficiency and accuracy of adjusting business rules.

[0051] The embodiments of the present application can acquire and process relevant data (such as evaluation data, business rules, etc.) based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0052] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0053] The embodiments of the present application can be applied to a variety of different fields, such as the medical business field, the financial business field, etc.

[0054] In a possible implementation, in the field of medical services, the data may be medical data associated with the medical services, such as medical equipment data associated with the medical services, function usage data of the medical services, and the like.

[0055] The following is combined with Figure 1 The business rule data processing method based on big data provided by an embodiment of the present invention is schematically illustrated.

[0056] See also Figure 1 , Figure 1 is a schematic flow chart of a business rule data processing method based on big data provided by an embodiment of the present invention, such as Figure 1 As shown, the method can be executed by a business rule data processing device based on big data, and the business rule data processing device based on big data is set on a data management platform, and the data management platform is connected to the big data platform in communication, and the data management platform can be a computer device. Specifically, the method of the embodiment of the present invention includes the following steps.

[0057] S101: Obtain evaluation data of one or more business rules associated with a business within a preset time range from a database of a big data platform, wherein the evaluation data includes priority data of each of the one or more business rules.

[0058] In an embodiment of the present invention, a business rule data processing device based on big data can obtain evaluation data of one or more business rules associated with the business within a preset time range in a database of a big data platform, and the evaluation data includes priority data of each business rule in the one or more business rules.

[0059] In some embodiments, the evaluation data also includes priority data, accuracy data, alarm data, etc. of each of the one or more business rules.

[0060] In some embodiments, the priority data includes the priority interval corresponding to each business rule in the one or more business rules, for example, the priority interval corresponding to business rule 1 is [8000, 9000); the alarm data includes the alarm quantity of each business rule in the one or more business rules, for example, the alarm quantity of business rule 1 is 20; the accuracy data includes the accuracy of the evaluation data of each business rule in the one or more business rules, and the accuracy can be calculated based on the evaluation data of each business rule and preset evaluation data, for example, the accuracy of business rule 1 is 200.

[0061] In some embodiments, the evaluation data of each business rule stored in the database of the big data platform is calculated by the big data platform based on the information of each business rule. The information of the business rule includes but is not limited to one or more of the rule code, transaction flow information, alarm rule information, etc.

[0062] In some embodiments, the evaluation data includes, but is not limited to, information such as the average daily alarm volume, independent coverage rate, rule coverage rate, and number of counterfeit cards covered by the rules for each business rule.

[0063] In some embodiments, the rule code is used to indicate the identifiers of different business rules. In some embodiments, the identifiers include but are not limited to characters such as Chinese, English, letters, and numbers.

[0064] S102: Using the evaluation data of each business rule as a training set, and inputting the training set into a preset machine learning model for training to obtain a rule priority prediction model.

[0065] In an embodiment of the present invention, a business rule data processing device based on big data can use the evaluation data of each business rule as a training set, and input the training set into a preset machine learning model for training to obtain a rule priority prediction model.

[0066] In one embodiment, when a business rule data processing device based on big data inputs the training set into a preset machine learning model for training to obtain a rule priority prediction model, it can extract an evaluation feature vector from the evaluation data of each business rule in the training set; and input the evaluation feature vector into the preset machine learning model for training to obtain the rule priority prediction model.

[0067] In some embodiments, the evaluation feature vector includes a priority vector, a precision vector, and a warning vector for each business rule.

[0068] In one embodiment, the evaluation data also includes priority data, accuracy data and alarm data of each business rule; when extracting evaluation feature vectors from the evaluation data of each business rule in the training set, the business rule data processing device based on big data can extract the priority vector from the priority data of each business rule, extract the accuracy vector from the accuracy data, and extract the alarm vector from the alarm data.

[0069] In one embodiment, when the business rule data processing device based on big data inputs the evaluation feature vector into the preset machine learning model for training to obtain the rule priority prediction model, the priority vector, precision vector and alarm vector corresponding to the evaluation data of each business rule can be input into the machine learning model to obtain the loss function value; the loss function value is compared with the target loss function value, and when the comparison result does not meet the preset conditions, the model parameters of the machine learning model are adjusted according to the comparison result; the priority vector, precision vector and alarm vector corresponding to the evaluation data of each business rule are input into the machine learning model after the model parameters are adjusted for retraining; when the comparison result of the loss function value obtained by retraining and the target loss function value meets the preset conditions, it is determined that the rule priority prediction model is obtained.

[0070] In one embodiment, when a business rule data processing device based on big data inputs the priority vector, precision vector and alarm vector corresponding to the evaluation data of each business rule into the machine learning model to obtain a loss function value, the priority vector, precision vector and alarm vector corresponding to the evaluation data of each business rule can be input into the first network layer of the machine learning model to obtain a target vector feature corresponding to the evaluation data of each business rule; and the target vector feature can be input into the second network layer of the machine learning model to obtain the loss function value.

[0071] In one embodiment, when a business rule data processing device based on big data inputs the target vector feature into the second network layer of the machine learning model to obtain the loss function value, the target vector feature can be input into the second network layer of the machine learning model to predict the prediction priority corresponding to each business rule in the training set, and the loss function value can be determined based on the predicted prediction priority corresponding to each business rule in the training set.

[0072] In one embodiment, the first network layer includes a first layer, a second layer, and a third layer; when the business rule data processing device based on big data inputs the priority vector, the precision vector, and the alarm vector corresponding to the evaluation data of each business rule into the first network layer of the machine learning model to obtain the target vector feature corresponding to the evaluation data of each business rule, the priority vector can be input into the first layer to obtain the first vector feature corresponding to the priority vector; and the first vector feature and the precision vector are input into the second layer to obtain the second vector feature corresponding to the first vector feature and the precision vector; and the first vector feature, the second vector feature, and the alarm vector are input into the third layer to obtain the target vector feature corresponding to the first vector feature, the second vector feature, and the alarm vector. In some embodiments, the machine learning model may include but is not limited to the Roberta model, etc.

[0073] In one example, a business rule data processing device based on big data can input the priority vector A extracted from the priority data of each business rule into the first layer of the machine learning model to obtain a first vector feature corresponding to the priority vector A; and input the first vector feature and the accuracy vector B extracted from the accuracy data of the evaluation data of each business rule into the second layer of the machine learning model to obtain a second vector feature corresponding to the first vector feature and the accuracy vector B; and input the first vector feature, the second vector feature and the alarm vector C extracted from the alarm data of the evaluation data of each business rule into the third layer to obtain the first vector feature, the second vector feature and the target vector feature D corresponding to the alarm vector C.

[0074] S103: Obtain evaluation data of a first business rule associated with a target business from a database of the big data platform, and input the evaluation data of the first business rule into the rule priority prediction model to determine a target priority corresponding to the first business rule.

[0075] In an embodiment of the present invention, a business rule data processing device based on big data can obtain evaluation data of the first business rule associated with the target business in the database of the big data platform, and input the evaluation data of the first business rule into the rule priority prediction model to determine the target priority corresponding to the first business rule.

[0076] In one embodiment, when the business rule data processing device based on big data inputs the evaluation data of the first business rule into the rule priority prediction model to determine the target priority corresponding to the first business rule, the evaluation data of the first business rule can be input into the rule priority prediction model to obtain the priority interval corresponding to the evaluation data of the first business rule; one or more third business rules other than the first business rule are obtained from the one or more business rules associated with the business in the database of the big data platform, and the target priority that is not used by the one or more third business rules is selected from the priority interval, and the target priority is confirmed to be the priority of the first business rule. In some embodiments, the third business rule is a business rule other than the first business rule associated with the business in the database of the big data platform.

[0077] In one example, it is assumed that a business rule data processing device based on big data inputs the evaluation data of the first business rule F111 (self-service transaction) into a rule priority prediction model, and obtains a priority interval corresponding to the evaluation data of the first business rule of [8000, 9000). If the current priority of the first business rule is 2020, the alarm volume is 20, and the rule precision is 200, if the first business rule F111 meets the alarm volume 20 between [30, 30) and the precision 200 between [300, 300), then a target priority that is not used by a third business rule other than the first business rule can be selected from the priority interval [8000, 9000) of the first business rule F111, and the target priority is confirmed as the priority of the first business rule F111.

[0078] In one embodiment, when a big data-based business rule data processing device selects a target priority that is not used by the one or more third business rules from the priority interval, it can detect whether each priority in the priority interval is used by the one or more business rules; if the detection result is yes, the business rule to be adjusted is determined from the one or more third business rules, and the priority of the business rule to be adjusted is adjusted to a selected priority that is not used by the one or more third business rules, and the priority of the business rule to be adjusted before adjustment is determined as the target priority; if the detection result is no, one or more priorities that are not used by the one or more third business rules are obtained, and the maximum priority is selected from each priority of the one or more priorities as the target priority.

[0079] In one embodiment, if the big data-based business rule data processing device detects that all priorities in the priority interval are used by the one or more third business rules, it can select a business rule to be adjusted that is adjustable from the one or more third business rules, adjust the priority of the business rule to be adjusted to a selected priority that is not used by one or more third business rules in the priority interval corresponding to the business rule to be adjusted, and determine the priority of the business rule to be adjusted before adjustment as the target priority.

[0080] In some embodiments, when selecting a business rule to be adjusted and having adjustable business rules from the one or more third business rules, the big data-based business rule data processing device may randomly select a business rule to be adjusted and having adjustable business rules.

[0081] In some embodiments, when a big data-based business rule data processing device selects a business rule to be adjusted that is adjustable from the one or more third business rules, it can select the highest priority business rule in the priority range from one or more third business rules as the business rule to be adjusted.

[0082] In some embodiments, the embodiments of the present invention do not specifically limit the method of selecting the business rule to be adjusted from other business rules using each priority in the priority interval.

[0083] For example, if the big data-based business rule data processing device detects that each priority in the priority interval [8000, 9000) of the first business rule F111 is used by one or more third business rules, and the current priority of the first business rule F111 is 8600, then a business rule to be adjusted F112 that can be adjusted can be selected from the one or more third business rules, and the priority of the business rule to be adjusted F112 can be adjusted to the selected priority 7300 in the priority interval [7100, 8100) corresponding to the business rule F112 to be adjusted that is not used by one or more third business rules, and the priority 8600 of the business rule to be adjusted before adjustment is determined as the target priority.

[0084] In one embodiment, if the big data-based business rule data processing device detects that there are one or more priorities in the priority interval that are not used by one or more third business rules, it can obtain one or more priorities that are not used by the one or more third business rules, and select the maximum priority from among the one or more priorities as the target priority.

[0085] For example, if the business rule data processing device based on big data detects that there are one or more priorities in the priority interval [8000, 9000) of the first business rule F111 that are not used by one or more third business rules, assuming that the current priority of the first business rule F111 is 8600, one or more priorities 8200, 8200 and 8800 that are not used by the one or more third business rules can be obtained, and the maximum priority 8800 can be selected from among the one or more priorities as the target priority.

[0086] S104: adjusting the current priority of the first business rule according to the target priority, generating a second business rule according to the adjusted target priority, and verifying the second business rule. When the verification is successful, confirming the release of the second business rule.

[0087] In an embodiment of the present invention, a business rule data processing device based on big data can adjust the current priority of the first business rule according to the target priority, generate a second business rule according to the adjusted target priority, and verify the second business rule. When the verification is successful, it confirms the release of the second business rule.

[0088] In one embodiment, when verifying the second business rule, the business rule data processing device based on big data can obtain the rule information of the second business rule and compare the rule information of the second business rule with the preset rule information of the second business rule. If the comparison result is consistent, it is determined that the verification is successful. In some embodiments, the rule information includes but is not limited to rule code, rule name, priority, decision, production version number, edit version number, rule set and other information. Examples of specific rule information are as follows: Figure 2 As shown, Figure 2 It is a schematic diagram of rule information of a business rule provided by an embodiment of the present invention.

[0089] In one embodiment, when the big data-based business rule data processing device confirms the release of the second business rule, it can send a business rule release instruction to the big data platform. The business rule release instruction is used to instruct the big data platform to re-release the second business rule associated with the target business and overwrite the first business rule originally associated with the target business, thereby replacing the first business rule associated with the target business with the second business rule.

[0090] In an embodiment of the present invention, a business rule data processing device based on big data can obtain evaluation data of one or more business rules associated with a business within a preset time range in a database of a big data platform, wherein the evaluation data includes priority data of each business rule in the one or more business rules; the evaluation data of each business rule is used as a training set, and the training set is input into a preset machine learning model for training to obtain a rule priority prediction model; the evaluation data of a first business rule associated with a target business in the database of the big data platform is obtained, and the evaluation data of the first business rule is input into the rule priority prediction model to determine the target priority corresponding to the first business rule; the current priority of the first business rule is adjusted according to the target priority, and a second business rule is generated according to the adjusted target priority, and the second business rule is verified, and when the verification is successful, the second business rule is confirmed to be released. In an embodiment of the present invention, the rule priority prediction model is obtained by optimizing the training by adding the evaluation data of the business rule including the priority data in the model training, so that the priority interval of the business rule can be determined more accurately, and the intelligent adjustment of the priority of the business rule is realized, and the accuracy and efficiency of adjusting the business rule are improved.

[0091] The embodiment of the present invention further provides a business rule data processing device based on big data, and the business rule data processing device based on big data is used to execute a unit of any of the above methods. Figure 3 , Figure 3 The diagram is a schematic block diagram of a business rule data processing device based on big data provided by an embodiment of the present invention. The business rule data processing device based on big data of this embodiment includes: an acquisition unit 301 , a training unit 302 , a determination unit 303 and an adjustment unit 304 .

[0092] An acquisition unit 301 is used to acquire evaluation data of one or more business rules associated with a business within a preset time range in a database of a big data platform, wherein the evaluation data includes priority data of each business rule in the one or more business rules;

[0093] A training unit 302 is used to use the evaluation data of each business rule as a training set, and input the training set into a preset machine learning model for training to obtain a rule priority prediction model;

[0094] A determination unit 303 is used to obtain evaluation data of a first business rule associated with a target business in a database of the big data platform, and input the evaluation data of the first business rule into the rule priority prediction model to determine a target priority corresponding to the first business rule;

[0095] The adjustment unit 304 is used to adjust the current priority of the first business rule according to the target priority, generate a second business rule according to the adjusted target priority, and verify the second business rule. When the verification is successful, confirm the release of the second business rule.

[0096] Furthermore, the determining unit 303 inputs the evaluation data of the first business rule into the rule priority prediction model to determine the target priority corresponding to the first business rule, specifically for:

[0097] Inputting the evaluation data of the first business rule into the rule priority prediction model to obtain a priority interval corresponding to the evaluation data of the first business rule;

[0098] Obtain one or more third business rules other than the first business rule from the one or more business rules associated with the business in the database of the big data platform, select a target priority that is not used by the one or more third business rules from the priority interval, and confirm that the target priority is the priority of the first business rule.

[0099] Further, when the determining unit 303 selects a target priority that is not used by the one or more third business rules from the priority interval, it is specifically used to:

[0100] Detecting whether each priority level in the priority interval is used by the one or more business rules;

[0101] If the detection result is yes, determining the business rule to be adjusted from the one or more third business rules, adjusting the priority of the business rule to be adjusted to a candidate priority that is not used by the one or more third business rules, and determining the priority of the business rule to be adjusted before adjustment as the target priority;

[0102] If the detection result is no, then one or more priorities that are not used by the one or more third business rules are obtained, and the maximum priority is selected from each priority of the one or more priorities as the target priority.

[0103] Furthermore, the training unit 302 inputs the training set into a preset machine learning model for training to obtain a rule priority prediction model, which is specifically used for:

[0104] Extracting an evaluation feature vector from the evaluation data of each business rule in the training set;

[0105] The evaluation feature vector is input into the preset machine learning model for training to obtain the rule priority prediction model.

[0106] Furthermore, the evaluation data also includes priority data, accuracy data and alarm data of each business rule; when the training unit 302 extracts the evaluation feature vector from the evaluation data of each business rule in the training set, it is specifically used to:

[0107] Extracting a priority vector from the priority data of each business rule, extracting a precision vector from the precision data, and extracting an alarm vector from the alarm data;

[0108] The training unit 302 inputs the evaluation feature vector into the preset machine learning model for training to obtain the rule priority prediction model, which is specifically used for:

[0109] Inputting the priority vector, accuracy vector and alarm vector corresponding to the evaluation data of each business rule into the machine learning model to obtain a loss function value;

[0110] Comparing the loss function value with the target loss function value, and when the comparison result does not meet the preset conditions, adjusting the model parameters of the machine learning model according to the comparison result;

[0111] Inputting the priority vector, accuracy vector and alarm vector corresponding to the evaluation data of each business rule into the machine learning model after adjusting the model parameters for retraining;

[0112] When the comparison result between the retrained loss function value and the target loss function value meets the preset condition, it is determined that the rule priority prediction model is obtained.

[0113] Furthermore, the training unit 302 inputs the priority vector, the accuracy vector and the alarm vector corresponding to the evaluation data of each business rule into the machine learning model to obtain the loss function value, which is specifically used for:

[0114] Inputting the priority vector, the accuracy vector and the alarm vector corresponding to the evaluation data of each business rule into the first network layer of the machine learning model to obtain the target vector features corresponding to the evaluation data of each business rule;

[0115] The target vector feature is input into the second network layer of the machine learning model to obtain the loss function value.

[0116] Further, the first network layer includes a first layer, a second layer, and a third layer; the training unit 302 inputs the priority vector, the accuracy vector, and the alarm vector corresponding to the evaluation data of each business rule into the first network layer of the machine learning model, and obtains the target vector feature corresponding to the evaluation data of each business rule, which is specifically used for:

[0117] Inputting the priority vector into the first layer to obtain a first vector feature corresponding to the priority vector;

[0118] Inputting the first vector feature and the precision vector into the second layer to obtain a second vector feature corresponding to the first vector feature and the precision vector;

[0119] The first vector feature, the second vector feature and the warning vector are input into the third layer to obtain the target vector feature corresponding to the first vector feature, the second vector feature and the warning vector.

[0120] In an embodiment of the present invention, a business rule data processing device based on big data can obtain evaluation data of one or more business rules associated with a business within a preset time range in a database of a big data platform, wherein the evaluation data includes priority data of each business rule in the one or more business rules; the evaluation data of each business rule is used as a training set, and the training set is input into a preset machine learning model for training to obtain a rule priority prediction model; the evaluation data of a first business rule associated with a target business in the database of the big data platform is obtained, and the evaluation data of the first business rule is input into the rule priority prediction model to determine the target priority corresponding to the first business rule; the current priority of the first business rule is adjusted according to the target priority, and a second business rule is generated according to the adjusted target priority, and the second business rule is verified, and when the verification is successful, the second business rule is confirmed to be released. In an embodiment of the present invention, the rule priority prediction model is obtained by optimizing the training by adding the evaluation data of the business rule including the priority data in the model training, so that the priority interval of the business rule can be determined more accurately, and the intelligent adjustment of the priority of the business rule is realized, and the accuracy and efficiency of adjusting the business rule are improved.

[0121] See also Figure 4 , Figure 4 is a schematic block diagram of a computer device provided by an embodiment of the present invention. In some embodiments, such as Figure 4 The computer device in the embodiment shown may include: one or more processors 401; one or more input devices 402, one or more output devices 403 and a memory 404. The processor 401, input device 402, output device 403 and memory 404 are connected via a bus 405. The memory 404 is used to store a computer program, the computer program includes a program, and the processor 401 is used to execute the program stored in the memory 404. The processor 401 is configured to call the program to execute:

[0122] Obtaining evaluation data of one or more business rules associated with the business within a preset time range in a database of the big data platform, wherein the evaluation data includes priority data of each of the one or more business rules;

[0123] The evaluation data of each business rule is used as a training set, and the training set is input into a preset machine learning model for training to obtain a rule priority prediction model;

[0124] Obtaining evaluation data of a first business rule associated with a target business in a database of the big data platform, and inputting the evaluation data of the first business rule into the rule priority prediction model to determine a target priority corresponding to the first business rule;

[0125] The current priority of the first business rule is adjusted according to the target priority, and a second business rule is generated according to the adjusted target priority, and the second business rule is verified. When the verification is successful, the second business rule is confirmed to be released.

[0126] Further, the processor 401 inputs the evaluation data of the first business rule into the rule priority prediction model to determine the target priority corresponding to the first business rule, specifically for:

[0127] Inputting the evaluation data of the first business rule into the rule priority prediction model to obtain a priority interval corresponding to the evaluation data of the first business rule;

[0128] Obtain one or more third business rules other than the first business rule from the one or more business rules associated with the business in the database of the big data platform, select a target priority that is not used by the one or more third business rules from the priority interval, and confirm that the target priority is the priority of the first business rule.

[0129] Further, when the processor 401 selects a target priority that is not used by the one or more third business rules from the priority interval, it is specifically configured to:

[0130] Detecting whether each priority in the priority interval is used by the one or more business rules;

[0131] If the detection result is yes, determining the business rule to be adjusted from the one or more third business rules, adjusting the priority of the business rule to be adjusted to a candidate priority that is not used by the one or more third business rules, and determining the priority of the business rule to be adjusted before adjustment as the target priority;

[0132] If the detection result is no, then one or more priorities that are not used by the one or more third business rules are obtained, and the maximum priority is selected from each priority of the one or more priorities as the target priority.

[0133] Furthermore, the processor 401 inputs the training set into a preset machine learning model for training to obtain a rule priority prediction model, which is specifically used to:

[0134] Extracting an evaluation feature vector from the evaluation data of each business rule in the training set;

[0135] The evaluation feature vector is input into the preset machine learning model for training to obtain the rule priority prediction model.

[0136] Furthermore, the evaluation data also includes priority data, accuracy data and alarm data of each business rule; when the processor 401 extracts the evaluation feature vector from the evaluation data of each business rule of the training set, it is specifically used to:

[0137] Extracting a priority vector from the priority data of each business rule, extracting a precision vector from the precision data, and extracting an alarm vector from the alarm data;

[0138] The processor 401 inputs the evaluation feature vector into the preset machine learning model for training to obtain the rule priority prediction model, specifically for:

[0139] Inputting the priority vector, accuracy vector and alarm vector corresponding to the evaluation data of each business rule into the machine learning model to obtain a loss function value;

[0140] Comparing the loss function value with the target loss function value, and when the comparison result does not meet the preset conditions, adjusting the model parameters of the machine learning model according to the comparison result;

[0141] Inputting the priority vector, accuracy vector and alarm vector corresponding to the evaluation data of each business rule into the machine learning model after adjusting the model parameters for retraining;

[0142] When the comparison result between the retrained loss function value and the target loss function value meets the preset condition, it is determined that the rule priority prediction model is obtained.

[0143] Furthermore, the processor 401 inputs the priority vector, the accuracy vector and the alarm vector corresponding to the evaluation data of each business rule into the machine learning model to obtain the loss function value, which is specifically used for:

[0144] Inputting the priority vector, the accuracy vector and the alarm vector corresponding to the evaluation data of each business rule into the first network layer of the machine learning model to obtain the target vector features corresponding to the evaluation data of each business rule;

[0145] The target vector feature is input into the second network layer of the machine learning model to obtain the loss function value.

[0146] Further, the first network layer includes a first layer, a second layer, and a third layer; the processor 401 inputs the priority vector, the accuracy vector, and the alarm vector corresponding to the evaluation data of each business rule into the first network layer of the machine learning model, and obtains the target vector feature corresponding to the evaluation data of each business rule, specifically for:

[0147] Inputting the priority vector into the first layer to obtain a first vector feature corresponding to the priority vector;

[0148] Inputting the first vector feature and the precision vector into the second layer to obtain a second vector feature corresponding to the first vector feature and the precision vector;

[0149] The first vector feature, the second vector feature and the warning vector are input into the third layer to obtain the target vector feature corresponding to the first vector feature, the second vector feature and the warning vector.

[0150] In an embodiment of the present invention, a computer device can obtain evaluation data of one or more business rules associated with a business within a preset time range in a database of a big data platform, wherein the evaluation data includes priority data of each business rule in the one or more business rules; the evaluation data of each business rule is used as a training set, and the training set is input into a preset machine learning model for training to obtain a rule priority prediction model; the evaluation data of a first business rule associated with a target business in the database of the big data platform is obtained, and the evaluation data of the first business rule is input into the rule priority prediction model to determine the target priority corresponding to the first business rule; the current priority of the first business rule is adjusted according to the target priority, and a second business rule is generated according to the adjusted target priority, and the second business rule is verified, and when the verification is successful, the second business rule is confirmed to be released. In an embodiment of the present invention, the rule priority prediction model is obtained by optimizing the training by adding the evaluation data of the business rule including the priority data in the model training, so that the priority interval of the business rule can be determined more accurately, and the intelligent adjustment of the priority of the business rule is realized, and the accuracy and efficiency of adjusting the business rule are improved.

[0151] It should be understood that in the embodiment of the present invention, the processor 401 may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0152] The input device 402 may include a touch pad, a microphone, etc., and the output device 403 may include a display (LCD, etc.), a speaker, etc.

[0153] The memory 404 may include a read-only memory and a random access memory, and provide instructions and data to the processor 401. A portion of the memory 404 may also include a non-volatile random access memory. For example, the memory 404 may also store information about the device type.

[0154] In a specific implementation, the processor 401, the input device 402, and the output device 403 described in the embodiment of the present invention can execute the Figure 1 The implementation described in the method embodiment can also implement the embodiment of the present invention. Figure 3 The implementation of the described business rule data processing device based on big data will not be described in detail here.

[0155] The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, Figure 1 The business rule data processing method based on big data described in the corresponding embodiment can also realize the present invention Figure 3 The business rule data processing device based on big data of the corresponding embodiment will not be described in detail here.

[0156] The computer-readable storage medium may be an internal storage unit of the business rule data processing device based on big data described in any of the aforementioned embodiments, such as a hard disk or memory of the business rule data processing device based on big data. The computer-readable storage medium may also be an external storage device of the business rule data processing device based on big data, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the business rule data processing device based on big data. Further, the computer-readable storage medium may also include both an internal storage unit and an external storage device of the business rule data processing device based on big data. The computer-readable storage medium is used to store the computer program and other programs and data required by the business rule data processing device based on big data. The computer-readable storage medium may also be used to temporarily store data that has been output or is to be output.

[0157] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or partly contributed to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a computer-readable storage medium, including several instructions for a computer device (which can be a personal computer, terminal, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned computer-readable storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes. The computer-readable storage medium may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, at least one application required for a function, etc.; the storage data area may store data created according to the use of blockchain nodes, etc.

[0158] It should be emphasized that in order to further ensure the privacy and security of the above data, the above data can also be stored in a node of a blockchain. Among them, the blockchain referred to in the present invention is a new application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, encryption algorithm, etc. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. The blockchain can include the blockchain underlying platform, the platform product service layer, and the application service layer.

[0159] The above descriptions are only partial implementation modes of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or substitutions within the technical scope disclosed by the present invention, and these modifications or substitutions should be included in the protection scope of the present invention.

Claims

1. A business rule data processing method based on big data, characterized in that: Applied to a data management platform, the data management platform is communicatively connected with a big data platform, the method comprises: Obtaining evaluation data of one or more business rules associated with the business within a preset time range in a database of the big data platform, wherein the evaluation data includes priority data of each of the one or more business rules; The evaluation data of each business rule is used as a training set, and the training set is input into a preset machine learning model for training to obtain a rule priority prediction model; Obtaining evaluation data of a first business rule associated with a target business in a database of the big data platform, and inputting the evaluation data of the first business rule into the rule priority prediction model to determine a target priority corresponding to the first business rule; Adjusting the current priority of the first business rule according to the target priority, generating a second business rule according to the adjusted target priority, and verifying the second business rule, and confirming the release of the second business rule when the verification is successful; The step of inputting the evaluation data of the first business rule into the rule priority prediction model to determine the target priority corresponding to the first business rule includes: Inputting the evaluation data of the first business rule into the rule priority prediction model to obtain a priority interval corresponding to the evaluation data of the first business rule; Obtain one or more third business rules other than the first business rule from the one or more business rules associated with the business in the database of the big data platform, select a target priority that is not used by the one or more third business rules from the priority interval, and confirm that the target priority is the priority of the first business rule; The selecting, from the priority interval, a target priority that is not used by the one or more third business rules comprises: Detecting whether each priority level in the priority interval is used by the one or more third business rules; If the detection result is yes, determining the business rule to be adjusted from the one or more third business rules, adjusting the priority of the business rule to be adjusted to a candidate priority that is not used by the one or more third business rules, and determining the priority of the business rule to be adjusted before adjustment as the target priority; If the detection result is no, then one or more priorities that are not used by the one or more third business rules are obtained, and the maximum priority is selected from each priority of the one or more priorities as the target priority.

2. The method according to claim 1, characterized in that The step of inputting the training set into a preset machine learning model for training to obtain a rule priority prediction model includes: Extracting an evaluation feature vector from the evaluation data of each business rule in the training set; The evaluation feature vector is input into the preset machine learning model for training to obtain the rule priority prediction model.

3. The method according to claim 2, characterized in that The evaluation data also includes priority data, accuracy data and alarm data of each business rule; the extraction of evaluation feature vectors from the evaluation data of each business rule in the training set includes: Extracting a priority vector from the priority data of each business rule, extracting a precision vector from the precision data, and extracting an alarm vector from the alarm data; The step of inputting the evaluation feature vector into the preset machine learning model for training to obtain the rule priority prediction model comprises: Inputting the priority vector, accuracy vector and alarm vector corresponding to the evaluation data of each business rule into the machine learning model to obtain a loss function value; Comparing the loss function value with the target loss function value, and when the comparison result does not meet the preset conditions, adjusting the model parameters of the machine learning model according to the comparison result; Inputting the priority vector, accuracy vector and alarm vector corresponding to the evaluation data of each business rule into the machine learning model after adjusting the model parameters for retraining; When the comparison result between the retrained loss function value and the target loss function value meets the preset condition, it is determined that the rule priority prediction model is obtained.

4. The method according to claim 3, characterized in that The step of inputting the priority vector, the accuracy vector and the alarm vector corresponding to the evaluation data of each business rule into the machine learning model to obtain the loss function value includes: Inputting the priority vector, the accuracy vector and the alarm vector corresponding to the evaluation data of each business rule into the first network layer of the machine learning model to obtain the target vector features corresponding to the evaluation data of each business rule; The target vector feature is input into the second network layer of the machine learning model to obtain the loss function value.

5. The method according to claim 4, characterized in that The first network layer includes a first layer, a second layer, and a third layer; the priority vector, the accuracy vector, and the alarm vector corresponding to the evaluation data of each business rule are input into the first network layer of the machine learning model to obtain the target vector features corresponding to the evaluation data of each business rule, including: Inputting the priority vector into the first layer to obtain a first vector feature corresponding to the priority vector; Inputting the first vector feature and the precision vector into the second layer to obtain a second vector feature corresponding to the first vector feature and the precision vector; The first vector feature, the second vector feature and the warning vector are input into the third layer to obtain the target vector feature corresponding to the first vector feature, the second vector feature and the warning vector.

6. A business rule data processing device based on big data, characterized in that: Applied to a data management platform, the data management platform is communicatively connected with a big data platform, and the device comprises: An acquisition unit, used to acquire evaluation data of one or more business rules associated with the business within a preset time range in a database of the big data platform, wherein the evaluation data includes priority data of each business rule in the one or more business rules; A training unit, used to use the evaluation data of each business rule as a training set, and input the training set into a preset machine learning model for training to obtain a rule priority prediction model; A determination unit, configured to obtain evaluation data of a first business rule associated with a target business in a database of the big data platform, and input the evaluation data of the first business rule into the rule priority prediction model to determine a target priority corresponding to the first business rule; an adjusting unit, configured to adjust the current priority of the first business rule according to the target priority, generate a second business rule according to the adjusted target priority, and verify the second business rule, and when the verification is successful, confirm the release of the second business rule; The determination unit inputs the evaluation data of the first business rule into the rule priority prediction model to determine the target priority corresponding to the first business rule, specifically inputting the evaluation data of the first business rule into the rule priority prediction model to obtain a priority interval corresponding to the evaluation data of the first business rule; obtaining one or more third business rules other than the first business rule from the one or more business rules associated with the business in the database of the big data platform, selecting a target priority that is not used by the one or more third business rules from the priority interval, and confirming that the target priority is the priority of the first business rule; When the determination unit selects a target priority that is not used by the one or more third business rules from the priority interval, it is specifically used to detect whether each priority in the priority interval is used by the one or more business rules; if the detection result is yes, determine the business rule to be adjusted from the one or more third business rules, and adjust the priority of the business rule to be adjusted to the selected priority that is not used by the one or more third business rules, and determine the priority of the business rule to be adjusted before adjustment as the target priority; if the detection result is no, obtain one or more priorities that are not used by the one or more third business rules, and select the maximum priority from each priority of the one or more priorities as the target priority.

7. A computer device, characterized in that: The method comprises a processor and a memory, wherein the memory is used to store a computer program, and the processor is configured to call the computer program to execute the method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the method according to any one of claims 1 to 5.

Images