Business rule management method and device, electronic equipment and storage medium

Abstract

The invention discloses a business rule management method and device, electronic equipment and a storage medium, and relates to the field of financial science and technology, and the method comprises the steps: obtaining a rule intention text; sending the rule intention text to the business large model, and obtaining a recommended business rule matched with the rule intention text and fed back by the business large model; and obtaining rule element information in the recommended service rule through a field extraction model, and displaying the rule element information. According to the technical scheme provided by the embodiment of the invention, the degree of dependence of service rule configuration on personal experience of service personnel is reduced, the time cost of service rule configuration is reduced, the service rule configuration efficiency is improved, meanwhile, configuration errors existing in a traditional manual configuration mode are avoided, and the accuracy of a service rule configuration result is improved.

Description

Technical Field

[0001] The present invention relates to the field of financial technology, and in particular to a business rule management method, device, electronic device and storage medium. Background Art

[0002] With the diversification of business types of financial institutions, there are a large number of business rules in the business system to ensure the orderly execution of various businesses, and the configuration and management of business rules has become an important component function of the business system.

[0003] In the prior art, the business system provides a rule configuration interface to business personnel. First, the business personnel enter the relevant business rules in the configuration interface, and then the business system saves the business rules in the database. Later, when a business rule call request is obtained, the matching business rules are displayed to the current user, thereby completing the configuration and management of the business rules.

[0004] However, such a business rule configuration method completely relies on the personal experience of business personnel. Not only does the configuration process require a high time cost and the business rule configuration efficiency is low, but the manual configuration method often has large configuration errors and the accuracy of the business rule configuration results is low. Summary of the invention

[0005] The present invention provides a business rule management method, device, electronic device and storage medium to solve the problems of low business rule configuration efficiency and high reliance on personal experience of business personnel.

[0006] According to another aspect of the present invention, there is provided a business rule management method, comprising:

[0007] Get the rule intent text;

[0008] Sending the rule intention text to the business big model, and obtaining the recommended business rules matched with the rule intention text fed back by the business big model;

[0009] The rule element information in the recommended business rule is obtained through a field extraction model, and the rule element information is displayed.

[0010] After displaying the rule element information, it also includes: obtaining feature keywords based on the acquired feature intent text; sending the feature keywords to the business big model, and obtaining the recommended business features that match the feature keywords fed back by the business big model; displaying the recommended business features, and replacing the target rule element information in the recommended business rule based on the business features selected by the user.

[0011] The business rule management method includes: in response to obtaining input text, obtaining the intent category of the input text through a text classification model; wherein the intent category includes rule intent text and feature intent text.

[0012] After displaying the rule element information, it also includes: obtaining a first user evaluation result that matches the recommended business rule, and constructing a first type of training sample based on the recommended business rule and the first user evaluation result, so as to train the business big model based on the first type of training sample; when displaying the recommended business feature, it also includes: obtaining a second user evaluation result that matches the recommended business feature, and constructing a second type of training sample based on the recommended business feature and the second user evaluation result, so as to train the business big model based on the second type of training sample.

[0013] The business rule management method also includes: displaying a rule entry interface and obtaining compilation element information through the rule entry interface; combining and compiling the obtained compilation element information to obtain matching business rules, and storing the business rules; obtaining a business service request, and displaying matching target business rules according to the business service request.

[0014] After obtaining the business service request, the method further includes: if no matching target business rule is obtained according to the business service request, obtaining a target business rule matching the business service request through the business big model.

[0015] According to another aspect of the present invention, there is provided a business rule management device, comprising:

[0016] A rule intention text acquisition module is used to obtain the rule intention text;

[0017] A recommended business rule acquisition module, used to send the rule intention text to the business big model, and obtain the recommended business rules matched with the rule intention text fed back by the business big model;

[0018] The rule element information acquisition module is used to acquire the rule element information in the recommended business rule through a field extraction model and display the rule element information.

[0019] According to another aspect of the present invention, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the business rule management method described in any embodiment of the present invention.

[0020] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the business rule management method described in any embodiment of the present invention when executed.

[0021] According to another aspect of the present invention, a computer program product is provided, including a computer program, wherein when the computer program is executed by a processor, the business rule management method according to any embodiment of the present invention is implemented.

[0022] The technical solution of the embodiment of the present invention first obtains the rule intent text, then sends the rule intent text to the business big model, obtains the recommended business rules matched with the rule intent text fed back by the business big model, and finally obtains the rule element information in the recommended business rules through the field extraction model, and displays the rule element information. In this way, the dependence of business rule configuration on the personal experience of business personnel is reduced, the time cost of business rule configuration is reduced, the efficiency of business rule configuration is improved, and the configuration errors existing in the traditional manual configuration method are avoided, and the accuracy of business rule configuration results is improved.

[0023] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0025] Figure 1 is a flow chart of a business rule management method provided according to Embodiment 1 of the present invention;

[0026] Figure 2 is a flow chart of another business rule management method provided according to Embodiment 2 of the present invention;

[0027] Figure 3 is a structural diagram of a business rule management device provided according to Embodiment 3 of the present invention;

[0028] Figure 4 This is a schematic diagram of the structure of a business rule management system provided according to Embodiment 4 of the present invention;

[0029] Figure 5is a schematic diagram of the structure of another business rule management system provided according to Embodiment 4 of the present invention;

[0030] Figure 6 It is a structural diagram of an electronic device for implementing the business rule management method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0031] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only 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 should fall within the scope of protection of the present invention.

[0032] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0033] Embodiment 1

[0034] Figure 1 This is a flowchart of a business rule management method provided in the first embodiment of the present invention. This embodiment is applicable to the case where recommended business rules are obtained through a business big model based on the rule intent text. The method can be executed by a business rule management device, which can be implemented in the form of hardware and / or software. The business rule management device can be configured in the business rule management system of any embodiment of the present invention, and the business rule management system can be configured in an electronic device such as a server. Figure 1 As shown, the method includes:

[0035] S101. Obtain rule intention text.

[0036] The rule intent text is the text information sent by the user to obtain business rules through the business big model; after obtaining the business rule query instruction issued by the user, the business rule management system displays the rule configuration interface to the user, and obtains the rule intent text entered by the current user through the displayed rule configuration interface.

[0037] S102: Send the rule intention text to the business big model, and obtain the recommended business rules matched with the rule intention text fed back by the business big model.

[0038] The business big model is a model optimized and generated based on the training of business data on the basis of the general big model to meet specific business needs. It can generate output through input, and the output results can support the effective development of business activities and business operations. After obtaining the rule intent text, the business rule management system sends it to the business big model. The business big model generates matching recommended business rules based on the rule intent text, and feeds back the recommended business rules to the business rule management system.

[0039] For example, the rule intent text entered by the user is "Please provide some risk control rules that can prevent and control third-party risk operations in mobile banking at night." Based on the above rule intent text, the business big model obtains the relevant recommended business rules: "Recommended business rule 1: The mobile banking login area is included in the high-risk area; Recommended business rule 2: The device for mobile banking login is not in the common device list; Recommended business rule 3: The number of mobile banking logins in the last N minutes is greater than M times," and feeds back the above recommended business rules to the business rule management system.

[0040] S103: Obtain rule element information in the recommended business rule through a field extraction model, and display the rule element information.

[0041] After obtaining the recommended business rules, the business rule management system extracts the various rule element information in the recommended business rules through the field extraction model; wherein the rule element information may include scenario fields, logical operator fields, and judgment threshold fields, etc.; the field extraction model may include Hidden Markov Model (HMM), Object Relational Mapping (ORM) model, conditional random field (CRF) model, and Maximum Entropy Markov Model (MEMM), etc.

[0042] The scenario field indicates the business scenario to which the business rule applies; the logical operator field is a field in the business rule that enables the literal vocabulary to function normally in the sentence, in addition to the literal vocabulary and state vocabulary (for example, time and tense, etc.), such as vocabulary that represents relative relationships; the judgment threshold field is a field in the business rule that is used to judge whether a certain indicator or variable reaches or exceeds the set limit value.

[0043] Taking the above technical solution as an example, if the recommended business rule is "the mobile banking login area is included in the high-risk area", the scenario field extracted by the business rule management system is "mobile banking login area", the logical operator field is "included in", and the judgment threshold field is "high-risk area"; the above rule element information is displayed to the user through the rule configuration interface, and the user can freely combine or modify the information of each rule element to obtain customized business rules.

[0044] Optionally, in an embodiment of the present invention, after displaying the rule element information, it also includes: obtaining feature keywords based on the acquired feature intent text; sending the feature keywords to the business big model, and obtaining recommended business features that match the feature keywords and are fed back by the business big model; displaying the recommended business features, and replacing the target rule element information in the recommended business rule based on the business features selected by the user.

[0045] Specifically, feature intent text is text information sent by users who intend to obtain business features through the business big model; business features are the sum of all feature information related to business rules, including the rule element information of the above technical solution; without understanding the specific business features, users need to obtain the feature information they want through feature intent text in order to build business rules based on the acquired feature information.

[0046] Feature intent text can be input independently without obtaining any recommended business rules. The business rule management system will directly send the obtained feature intent text to the business big model. The business big model will generate matching recommended business features based on the feature intent text and feed back the recommended business features to the business rule management system. It can also be input in combination after the recommended business rules have been obtained. The business rule management system will obtain the feature intent text based on the input information and the currently displayed recommended business rules.

[0047] Taking the above technical solution as an example, on the basis of the recommended business rule "Recommendation Rule 1: The mobile banking login area is included in the high-risk area", the characteristic intention text sent by the user is "Replace the characteristic field 'high-risk area' with the abnormal area announced by institution A". After obtaining the above characteristic intention text, the business rule management system extracts the characteristic keyword "abnormal area announced by institution A" through the keyword extraction model, and sends the characteristic keyword to the business big model; wherein the keyword extraction model may include the TF-IDF (term frequency-inverse document frequency) keyword extraction model, the TextRank (text sorting algorithm) keyword extraction model and the LDA (Latent Dirichlet Allocation) keyword extraction model.

[0048] Based on the above-mentioned feature keywords, the business big model obtains the text information of the relevant recommended business features, which is "Recommend the feature data related to abnormal areas published by the following three types of institution A: Recommended feature 1: areas with high frequency of abnormal behavior; Recommended feature 2: areas with medium frequency of abnormal behavior; Recommended feature 3: areas with low frequency of abnormal behavior"; the business rule management system will obtain the above-mentioned recommended business features and display them to the user.

[0049] If the user selects "Recommended Feature 1" from the recommended business features displayed, the business rule management system will replace the target rule element information (i.e., "high-risk area") in the recommended business rule with the target business feature (i.e., "area with high frequency of abnormal behavior") selected by the user, thereby obtaining the business rule "the mobile banking login area is included in the area with high frequency of abnormal behavior". Based on this, on the premise that the user does not know the specific content of the relevant business features, the specific content of the relevant business features is obtained through the business big model, and based on the obtained recommended business rules, the target rule element information is replaced by the target business feature to obtain the configured new business rules. This not only improves the convenience of business rule configuration, but also reduces the requirements for user personal experience and reduces the difficulty of business rule configuration.

[0050] In particular, users can send out rule intent text and feature intent text respectively through different text boxes. The business rule management system can determine whether the current input text is rule intent text or feature intent text through the text box source of the current input text; users can also enter rule intent text and feature intent text through the same text box, and then trigger the search command through different buttons. The business rule management system can also determine whether the current input text is rule intent text or feature intent text through the trigger button of the current input text.

[0051] Optionally, in an embodiment of the present invention, the business rule management method includes: in response to obtaining input text, obtaining the intent category of the input text through a text classification model; wherein the intent category includes rule intent text and feature intent text. The user can input rule intent text and feature intent text through the same text box, and the business rule management system classifies the current input text through a pre-trained text classification model to determine whether it is a rule intent text or a feature intent text; wherein the text classification model may include a convolutional neural network model and a recurrent neural network model, which extracts text features from the input text information to obtain a feature vector, and then outputs the classification result of the current input text by identifying the feature vector, thereby effectively distinguishing between rule intent text and feature intent text, simplifying the user's operation complexity, and further improving the configuration convenience of business rules.

[0052] In particular, a knowledge base can be configured for the business big model to provide the business big model with rule element information of multiple business rules and multiple business features through the knowledge base, so as to improve the knowledge level and answer accuracy of the business big model; the business big model can also update and expand the knowledge base to adapt to new business rule requirements and business feature requirements.

[0053] Optionally, in an embodiment of the present invention, after displaying the rule element information, it also includes: obtaining a first user evaluation result that matches the recommended business rule, and constructing a first type of training sample based on the recommended business rule and the first user evaluation result, so as to train the business big model based on the first type of training sample; when displaying the recommended business feature, it also includes: obtaining a second user evaluation result that matches the recommended business feature, and constructing a second type of training sample based on the recommended business feature and the second user evaluation result, so as to train the business big model based on the second type of training sample.

[0054] Specifically, the business rule management system can obtain the user's evaluation results for recommended business rules or recommended business features, and combine the recommended business rules with the corresponding user evaluation results to form a first type of training samples, and combine the recommended business features with the corresponding user evaluation results to form a second type of training samples, and the above types of training samples all include positive training samples and negative training samples; through the iterative training of the business big model with the first type of training samples, the business rule construction function of the business big model can be improved, and through the iterative training of the business big model with the second type of training samples, the business feature construction function of the business big model can be improved, thereby improving the learning ability of the business big model and improving the accuracy of the obtained recommended business rules and recommended business features.

[0055] The technical solution of the embodiment of the present invention first obtains the rule intent text, then sends the rule intent text to the business big model, obtains the recommended business rules matched with the rule intent text fed back by the business big model, and finally obtains the rule element information in the recommended business rules through the field extraction model, and displays the rule element information. In this way, the dependence of business rule configuration on the personal experience of business personnel is reduced, the time cost of business rule configuration is reduced, the efficiency of business rule configuration is improved, and the configuration errors existing in the traditional manual configuration method are avoided, and the accuracy of business rule configuration results is improved.

[0056] Embodiment 2

[0057] Figure 2 The second embodiment of the present invention provides a flowchart of a business rule management method. The relationship between this embodiment and the above embodiment is that the user can also directly enter the business rules through the rule entry interface. Figure 2 As shown, the method also includes:

[0058] S201, displaying a rule entry interface, and obtaining compilation element information through the rule entry interface.

[0059] The rule entry interface is an interface provided by the business rule management system to users for inputting custom business rules; users can directly complete the entry operation of editing element information through the rule entry interface.

[0060] S202: Combine and compile the obtained compilation element information to obtain matching business rules, and store the business rules.

[0061] The business rule management system combines the compiled element information input by the user according to a pre-set arrangement and compiles it into a complete statement, thereby obtaining the business rules customized by the user; similarly, the user can enter the rule element information in a text box that is different from the rule intent text box and the feature intent text box. The business rule management system can determine whether the current input information is the rule intent text, the feature intent text, or the customized compiled element information through the specific text box source.

[0062] Users can also input rule intent text, feature intent text and editing element information through the same text box, and then trigger the editing element information entry instruction through a trigger button different from the rule intent text button and the feature intent text button. The business rule management system can also determine whether the current input information is rule intent text, feature intent text, or customized editing element information through the currently triggered button.

[0063] S203: Obtain a business service request, and display matching target business rules according to the business service request.

[0064] When a business service request from a user is obtained, the matching target business rule is searched among the stored business rules, and the target business rule is displayed to the current user; this enables custom entry, compilation, storage and query of business rules, simplifies the business rule entry process, and ensures timely response to business rule call requests.

[0065] Optionally, in an embodiment of the present invention, after obtaining the business service request, it also includes: if no matching target business rule is obtained according to the business service request, obtaining the target business rule that matches the business service request through the business big model. Specifically, the business rule management system queries each stored business rule according to the business service request. If no target business rule that matches the request is obtained, the business service request is sent to the business big model to obtain the target business rule through the business big model and display it to the user. In this way, when the matching business rule cannot be directly called, the target business rule can be obtained in real time through the business big model, ensuring a timely response to each business service request and meeting the user's business rule calling needs.

[0066] The technical solution of the embodiment of the present invention first displays the rule entry interface, obtains the compilation element information through the rule entry interface, combines and compiles the obtained compilation element information to obtain matching business rules, and stores the business rules; then obtains the business service request, and displays the matching target business rules according to the business service request. In this way, the custom entry, compilation, storage and query of business rules are realized, the business rule entry process is simplified, and the timely response to the business rule call request is ensured.

[0067] Embodiment 3

[0068] Figure 3 : is a structural block diagram of a business rule management device provided by Embodiment 3 of the present invention, and the device specifically includes:

[0069] A rule intention text acquisition module 301 is used to acquire the rule intention text;

[0070] The recommended business rule acquisition module 302 is used to send the rule intention text to the business big model and obtain the recommended business rules matched with the rule intention text fed back by the business big model;

[0071] The rule element information acquisition module 303 is used to acquire the rule element information in the recommended business rule through a field extraction model and display the rule element information.

[0072] The technical solution of the embodiment of the present invention first obtains the rule intent text, then sends the rule intent text to the business big model, obtains the recommended business rules matched with the rule intent text fed back by the business big model, and finally obtains the rule element information in the recommended business rules through the field extraction model, and displays the rule element information. In this way, the dependence of business rule configuration on the personal experience of business personnel is reduced, the time cost of business rule configuration is reduced, the efficiency of business rule configuration is improved, and the configuration errors existing in the traditional manual configuration method are avoided, and the accuracy of business rule configuration results is improved.

[0073] Optionally, the business rule management device is also used to obtain feature keywords based on the acquired feature intent text; send the feature keywords to the business big model, and obtain recommended business features that match the feature keywords and are fed back by the business big model; display the recommended business features, and replace the target rule element information in the recommended business rules based on the business features selected by the user.

[0074] Optionally, the business rule management device is further used to obtain the intent category of the input text through a text classification model in response to obtaining the input text; wherein the intent category includes rule intent text and feature intent text.

[0075] Optionally, the business rule management device is also used to obtain a first user evaluation result that matches the recommended business rule, and construct a first type of training sample based on the recommended business rule and the first user evaluation result, so as to train the business big model based on the first type of training sample; and obtain a second user evaluation result that matches the recommended business feature, and construct a second type of training sample based on the recommended business feature and the second user evaluation result, so as to train the business big model based on the second type of training sample.

[0076] Optionally, the business rule management device is also used to display a rule entry interface and obtain compilation element information through the rule entry interface; combine and compile the obtained compilation element information to obtain matching business rules, and store the business rules; obtain a business service request, and display the matching target business rules according to the business service request.

[0077] Optionally, the business rule management device is further used to obtain a target business rule matching the business service request through the business big model if no matching target business rule is obtained according to the business service request.

[0078] The above device can execute the business rule management method provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method. For technical details not described in detail in this embodiment, please refer to the business rule management method provided by any embodiment of the present invention.

[0079] Embodiment 4

[0080] Figure 4 is a schematic diagram of the structure of a business rule management system provided in Embodiment 4 of the present invention, wherein the business rule management system is used to execute the business rule management method in any of the above embodiments, such as Figure 4 As shown, the business rule management system includes: an information input module 100 and a rule recommendation module 200. The information input module 100 is connected to the rule recommendation module 200 to obtain the rule intention text and send the rule intention text to the business big model 300 through the rule recommendation module 200.

[0081] The rule recommendation module 200 is used to obtain the recommended business rules that match the rule intention text fed back by the business big model 300, and send the recommended business rules to the information entry module 100; the information entry module 100 is also used to obtain the rule element information in the recommended business rules through the field extraction model, and display the rule element information.

[0082] like Figure 5 As shown, the business rule management system also includes a feature recommendation module 400; the information entry module 100 is connected to the feature recommendation module 400, and is also used to obtain feature intent text and send the feature intent text to the feature recommendation module 400; the feature recommendation module 400 is used to obtain feature keywords based on the feature intent text, send the feature keywords to the business big model 300, and obtain the recommended business features fed back by the business big model 300; the information entry module 100 is also used to display the recommended business features, and replace the target rule element information in the recommended business rules based on the business features selected by the user.

[0083] The information input module 100 is also used to obtain the intent category of the current input text through a text classification model. If the current input text is determined to be a rule intent text, the current input text is sent to the rule recommendation module 200; if the current input text is determined to be a feature intent text, the current input text is sent to the feature recommendation module 400.

[0084] The business rule management system also includes a recommendation evaluation module 500, a sample marking module 600 and a training module 700; the recommendation evaluation module 500 is connected to the sample marking module 600, and is used to obtain a first user evaluation result that matches the recommended business rule, and to obtain a second user evaluation result that matches the recommended business feature; the sample marking module 600 is connected to the training module 700, and is used to construct a first type of training sample according to the recommended business rule and the first user evaluation result, and to construct a second type of training sample according to the recommended business feature and the second user evaluation result; the training module 700 is used to train the business big model 300 based on the first type of training samples and the second type of training samples.

[0085] The business rule management system also includes a translation storage module 800, a rule database module 900 and a rule calculation module 901; the information entry module 100 is also used to display a rule entry interface and obtain compilation element information through the rule entry interface; the translation storage module 800 is connected to the information entry module 100 and is used to combine and compile the obtained compilation element information to obtain matching business rules; the rule database module 900 is connected to the translation storage module 800 and is used to store the business rules; the rule calculation module 901 is connected to the rule database module 900 and is used to obtain business service requests and display matching target business rules according to the business service requests.

[0086] The rule calculation module 901 is connected to the business big model 300, and is also used to obtain the target business rule matching the business service request through the business big model 300 if no matching target business rule is obtained according to the business service request.

[0087] The technical solution of the embodiment of the present invention, the business rule management system reduces the dependence of business rule configuration on the personal experience of business personnel, reduces the time cost of business rule configuration, improves the efficiency of business rule configuration, and at the same time avoids the configuration errors existing in traditional manual configuration methods, thereby improving the accuracy of business rule configuration results.

[0088] Embodiment 5

[0089] Figure 6A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, electronic devices, blade electronic devices, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0090] like Figure 6 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0091] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0092] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the business rule management method.

[0093] In some embodiments, the business rule management method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit. In some embodiments, part or all of the computer program may be loaded and / or installed on a heterogeneous hardware accelerator via a ROM and / or a communication unit. When the computer program is loaded into RAM and executed by a processor, one or more steps of the business rule management method described above may be performed. Alternatively, in other embodiments, the processor may be configured to perform the business rule management method in any other appropriate manner (e.g., by means of firmware).

[0094] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0095] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0096] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0097] To provide interaction with a user, the systems and techniques described herein may be implemented on a heterogeneous hardware accelerator having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and pointing device (e.g., a mouse or trackball) through which a user can provide input to the heterogeneous hardware accelerator. Other types of devices may also be used to provide interaction with a user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0098] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0099] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0100] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0101] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A business rule management method, characterized in that: include: Get the rule intent text; Sending the rule intention text to the business big model, and obtaining the recommended business rules matched with the rule intention text fed back by the business big model; The rule element information in the recommended business rule is obtained through a field extraction model, and the rule element information is displayed.

2. The business rule management method according to claim 1, characterized in that: After displaying the rule element information, it also includes: Obtain feature keywords based on the acquired feature intent text; Sending the feature keyword to the business big model, and obtaining the recommended business features matched with the feature keyword fed back by the business big model; The recommended service features are displayed, and target rule element information in the recommended service rules is replaced based on the service features selected by the user.

3. The business rule management method according to claim 2, characterized in that: The business rule management method comprises: In response to obtaining the input text, the intent category of the input text is obtained through a text classification model; wherein the intent category includes a regular intent text and a feature intent text.

4. The business rule management method according to claim 2, characterized in that: After displaying the rule element information, it also includes: Acquire a first user evaluation result that matches the recommended business rule, and construct a first type of training sample according to the recommended business rule and the first user evaluation result, so as to train the business big model based on the first type of training sample; When displaying the recommended service features, it also includes: A second user evaluation result matching the recommended service feature is obtained, and a second type of training sample is constructed according to the recommended service feature and the second user evaluation result, so as to train the large service model based on the second type of training sample.

5. The business rule management system according to claim 1, characterized in that: The business rule management method further includes: Displaying a rule entry interface, and obtaining compilation element information through the rule entry interface; Combining and compiling the obtained compilation element information to obtain matching business rules, and storing the business rules; Obtain a business service request, and display matching target business rules according to the business service request.

6. The business rule management method according to claim 5, characterized in that: After obtaining the business service request, it also includes: If no matching target business rule is obtained according to the business service request, the target business rule matching the business service request is obtained through the business big model.

7. A business rule management device, characterized in that: include: A rule intention text acquisition module is used to obtain the rule intention text; A recommended business rule acquisition module, used to send the rule intention text to the business big model, and obtain the recommended business rules matched with the rule intention text fed back by the business big model; The rule element information acquisition module is used to acquire the rule element information in the recommended business rule through a field extraction model and display the rule element information.

8. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the business rule management method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the business rule management method according to any one of claims 1 to 6 when executed.

10. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the business rule management method according to any one of claims 1 to 6 is implemented.

Images