Business operation processing method, device, computer equipment and readable storage medium

Abstract

The present application relates to a business operation processing method, apparatus, computer equipment, computer-readable storage medium and computer program product. The method comprises: obtaining a business operation instruction, and determining an operation object, an operation type and an operation parameter based on the business operation instruction; determining an operation interface according to the metadata of the operation object and the operation type; generating a target plug-in corresponding to the business operation instruction based on the operation interface; determining a plug-in parameter corresponding to the target plug-in according to the operation parameter; executing the target plug-in according to the plug-in parameter, and obtaining a business operation result corresponding to the business operation instruction. The use of this method can improve the processing efficiency of business operations.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a business operation processing method, apparatus, computer equipment, computer-readable storage medium, and computer program product. Background Art

[0002] In the current software development and information technology fields, the execution efficiency of business operations such as querying the balance of a certain account, modifying the value of a certain parameter, deleting a specified document, and copying a certain organization's plan is directly related to the company's operating costs and market competitiveness. However, traditional business operation processes are often cumbersome and lack flexibility. With the increase in business volume and complexity, they often cannot meet the needs of real-time, accurate and comprehensive data processing, resulting in low processing efficiency of business operations. Summary of the invention

[0003] Based on this, it is necessary to provide a business operation processing method, apparatus, computer equipment, computer-readable storage medium and computer program product that can improve the efficiency of business operation processing in response to the above technical problems.

[0004] In a first aspect, the present application provides a business operation processing method, comprising:

[0005] Obtaining a business operation instruction, and determining an operation object, operation type, and operation parameters based on the business operation instruction;

[0006] Determine the operation interface based on the metadata of the operation object and the operation type;

[0007] Generate target plug-ins corresponding to business operation instructions based on the operation interface;

[0008] Determine the plug-in parameters corresponding to the target plug-in according to the operation parameters;

[0009] Execute the target plug-in according to the plug-in parameters to obtain the business operation result corresponding to the business operation instruction.

[0010] In a second aspect, the present application further provides a business operation processing device, including:

[0011] An operation instruction acquisition module is used to acquire a business operation instruction and determine an operation object, operation type and operation parameters based on the business operation instruction;

[0012] An operation interface determination module, used to determine the operation interface according to the metadata of the operation object and the operation type;

[0013] A plug-in generation module is used to generate a target plug-in corresponding to a business operation instruction based on an operation interface;

[0014] A plug-in parameter determination module is used to determine the plug-in parameters corresponding to the target plug-in according to the operation parameters;

[0015] The plug-in execution module is used to execute the target plug-in according to the plug-in parameters and obtain the business operation result corresponding to the business operation instruction.

[0016] In a third aspect, the present application further provides a computer device, wherein the computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the above business operation processing method are implemented.

[0017] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the above business operation processing method are implemented.

[0018] In a fifth aspect, the present application further provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the above business operation processing method are implemented.

[0019] The above-mentioned business operation processing method, apparatus, computer equipment, computer-readable storage medium and computer program product determine the operation object, operation type and operation parameters based on the obtained business operation instruction, determine the operation interface according to the metadata of the operation object and the operation type, generate the target plug-in corresponding to the business operation instruction based on the operation interface, determine the plug-in parameters corresponding to the target plug-in according to the operation parameters, and execute the target plug-in according to the plug-in parameters to obtain the business operation result corresponding to the business operation instruction. In the business operation processing process, the metadata of the operation object and the operation type determine the operation interface, generate the corresponding target plug-in through the operation interface, determine the plug-in parameters corresponding to the target plug-in according to the operation parameters, and execute the target plug-in according to the plug-in parameters. The corresponding plug-in can be constructed based on the business operation instruction to implement the corresponding business operation, which can simplify the business operation processing flow, thereby improving the processing efficiency of the business operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0021] Figure 1 An application environment diagram of a business operation processing method in an embodiment;

[0022] Figure 2 A flowchart of a business operation processing method in one embodiment;

[0023] Figure 3 A schematic diagram of a process of parsing a business operation instruction in an embodiment;

[0024] Figure 4 A flowchart of a business operation processing method in another embodiment;

[0025] Figure 5 A schematic diagram of the correspondence between operation types and standard interfaces in an embodiment;

[0026] Figure 6 A schematic diagram of the corresponding relationship between operation parameters and plug-in parameters in an embodiment;

[0027] Figure 7 A schematic diagram of a plug-in construction rule in one embodiment;

[0028] Figure 8 A schematic diagram of the correspondence between operation types and SQL keywords in an embodiment;

[0029] Fig. 9 is a structural block diagram of a business operation processing device in one embodiment;

[0030] Fig.10 is an internal structure diagram of a computer device in one embodiment;

[0031] Fig.11 FIG. 4 is a diagram showing the internal structure of a computer device in yet another embodiment. DETAILED DESCRIPTION

[0032] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0033] The business operation processing method provided in the embodiment of the present application can be applied to Figure 1In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. The user can send a business operation instruction to the server 104 through the terminal 102. After the server 104 obtains the business operation instruction, it can determine the operation object, operation type and operation parameters based on the business operation instruction. The server 104 determines the operation interface according to the metadata of the operation object and the operation type, and generates the target plug-in corresponding to the business operation instruction based on the operation interface. The server 104 determines the plug-in parameters corresponding to the target plug-in according to the operation parameters, and executes the target plug-in according to the plug-in parameters to obtain the business operation result corresponding to the business operation instruction. The server 104 can also feedback the business operation result to the terminal 102, so that the business operation result can be intuitively displayed on the terminal 102.

[0034] In some embodiments, the business operation processing method can be implemented independently by the terminal 102 or the server 104. For example, the terminal 102 can directly perform the corresponding business operation processing based on the business operation instruction, or the server 104 can obtain the business operation instruction from the data storage system and then perform the business operation processing.

[0035] The terminal 102 may be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, IoT devices, and portable wearable devices. The IoT devices may be smart speakers, smart TVs, smart air conditioners, smart car devices, projection devices, etc. Portable wearable devices may be smart watches, smart bracelets, head-mounted devices, etc. Head-mounted devices may be virtual reality (VR) devices, augmented reality (AR) devices, smart glasses, etc. The server 104 may be an independent physical server, or a server cluster or distributed system consisting of multiple physical servers, or a cloud server that provides cloud computing services.

[0036] In an exemplary embodiment, Figure 2 As shown, a business operation processing method is provided, which is applied to Figure 1 The server in the example is used to illustrate, including the following steps 202 to 210. Among them:

[0037] Step 202: Acquire a business operation instruction, and determine an operation object, an operation type, and operation parameters based on the business operation instruction.

[0038] Among them, the business operation instruction can be edited by the user through the terminal, and the business operation instruction can carry the business operation information that the user needs to perform, such as business operation text described in natural language, such as "query the ending balance of account 1001 in this period" and "add 100 entries". The operation object can be the business object targeted by the business operation, such as various objects such as documents, parameters, basic information, and data tables in the business system. The operation type is the type corresponding to the business operation that needs to be triggered for the operation object, and different types of business operations can be processed differently. For example, the operation type can include but is not limited to at least one of query, add, modify, and delete. The operation parameters can include parameters involved in executing the business operation, such as the operation parameters can include but are not limited to at least one of various parameters such as target account information, period, modification target, target value, source scheme, target organization, etc. For business operation instructions that implement different business operation functions, different operation objects, different operation types, or different operation parameters can be corresponding.

[0039] Optionally, the user may send a business operation instruction to the server through the terminal. The business operation instruction may include a description statement expressed in natural language. The server may determine the operation object, operation type, and operation parameters based on the business operation instruction. In some embodiments, the business operation instruction may include different fields, and different data may be stored in different fields. The server may parse the business operation instruction to parse the operation object, operation type, and operation parameters from each field of the business operation instruction. In some embodiments, the server may identify and parse the business operation instruction by calling a pre-trained large language model (LLM) to determine the operation object, operation type, and operation parameters.

[0040] Step 204: determine the operation interface according to the metadata of the operation object and the operation type.

[0041] Metadata refers to data that describes data, which may include information such as the structure, attributes, source, purpose, format, creation time, etc. of the data, and is a model file of an interface, function, or module. For example, metadata may include data that defines an operation object, specifically, it may define the object attributes of the operation object, define the interface corresponding to the operation object, etc. The operation interface is an interface used to implement the business operation to which the operation type belongs. The interface refers to the channel or method for interaction between different parts or different systems in a software system. The interface defines the format of data exchange, the communication protocol, and the specific rules of interaction, so that instruction operations can be executed.

[0042] Exemplarily, the server may obtain metadata of the operation object, such as querying the corresponding metadata based on the object identifier of the operation object, and determine the corresponding operation interface based on the metadata and the operation type to implement business operations for the operation object through the operation interface.

[0043] Step 206: Generate a target plug-in corresponding to the business operation instruction based on the operation interface.

[0044] Among them, plug-ins include functional classes that implement specified interfaces. They are programs written in accordance with certain standardized application program interfaces. Through plug-ins, new functions or features can be added to the main program without modifying the original code, thereby enhancing or expanding the functions of the main program. Target plug-ins are plug-ins built for business operation instructions, which are used to implement business operations corresponding to business operation instructions. Optionally, the server can generate a corresponding target plug-in based on a determined operation interface, such as the server can determine the corresponding plug-in code based on the operation interface, and build a target plug-in corresponding to the business operation instruction based on the plug-in code.

[0045] Step 208: Determine the plug-in parameters corresponding to the target plug-in according to the operation parameters.

[0046] Among them, the plug-in parameters are the parameters required by the plug-in during execution, that is, the plug-in parameters are the parameters involved in the operation of the plug-in. The plug-in parameters correspond to the operation parameters, and the specific plug-in parameters can be determined according to the operation parameters, such as mapping and determining based on the operation parameters. Exemplarily, the server can determine the plug-in parameters corresponding to the target plug-in based on the operation parameters, such as the server can map the operation parameters to the plug-in parameters corresponding to the target plug-in based on the pre-configured parameter construction rules.

[0047] Step 210: Execute the target plug-in according to the plug-in parameters to obtain the business operation result corresponding to the business operation instruction.

[0048] The business operation result is the result of executing the corresponding business operation according to the business operation instruction. Optionally, the server may execute the target plug-in according to the plug-in parameters, so as to obtain the business operation result corresponding to the business operation instruction. In some embodiments, the server may import the plug-in parameters into the target plug-in, and execute the target plug-in after the plug-in parameters are imported, so as to obtain the business operation result corresponding to the business operation instruction. In some embodiments, the server may obtain the plug-in code of the target plug-in, and execute the plug-in code after importing the plug-in parameters into the plug-in code, so as to obtain the business operation result corresponding to the business operation instruction.

[0049] In some embodiments, the server may also pre-configure a plug-in template, and the plug-in template may correspond to different operation objects and operation types. After determining the operation object, operation type and operation parameter based on the business operation instruction, the server may query the plug-in template database, and match the plug-in templates in the plug-in template database based on the operation object and operation type to determine the plug-in template that matches the operation object and operation type. The server may use the matching plug-in template as the target plug-in corresponding to the business operation instruction, and implement the business operation of the business operation instruction by executing the target plug-in. In some embodiments, when the server does not query the plug-in template that matches the operation object and operation type in the plug-in template database, the server may perform processing to determine the operation interface according to the metadata of the operation object and the operation type, thereby dynamically generating the corresponding target plug-in. In some embodiments, for the generated target plug-in corresponding to the business operation instruction, the server may generate a corresponding plug-in template based on the target plug-in, and update the generated plug-in template to the plug-in template database, so that the plug-in template can be matched from the plug-in template database for business operation processing later.

[0050] In some embodiments, the server can implement a business operation processing method based on a pre-trained large language model. For example, the server can determine the operation object, operation type, and operation parameters through the large language model, and generate a target plug-in corresponding to the business operation instruction based on the operation interface through the large language model, determine the plug-in parameters corresponding to the target plug-in according to the operation parameters, execute the target plug-in according to the plug-in parameters through the large language model, and obtain the business operation result corresponding to the business operation instruction.

[0051] In the above-mentioned business operation processing method, the operation object, operation type and operation parameters are determined based on the obtained business operation instruction, the operation interface is determined according to the metadata of the operation object and the operation type, the target plug-in corresponding to the business operation instruction is generated based on the operation interface, the plug-in parameters corresponding to the target plug-in are determined according to the operation parameters, and the target plug-in is executed according to the plug-in parameters to obtain the business operation result corresponding to the business operation instruction. In the business operation processing process, the metadata of the operation object and the operation type determine the operation interface, the corresponding target plug-in is generated through the operation interface, the plug-in parameters corresponding to the target plug-in are determined according to the operation parameters, and the target plug-in is executed according to the plug-in parameters. The corresponding plug-in can be constructed based on the business operation instruction to realize the corresponding business operation, which can simplify the business operation processing flow, thereby improving the processing efficiency of the business operation.

[0052] In an exemplary embodiment, Figure 3 As shown, the process of parsing the business operation instruction, that is, determining the operation object, operation type and operation parameters based on the business operation instruction, includes steps 302 to 306. Among them:

[0053] Step 302: determine a pre-trained large language model and instruction recognition prompt words corresponding to the large language model.

[0054] Among them, the large language model is an advanced artificial intelligence model with large-scale parameters and training data, which can understand and generate natural language, such as but not limited to the GPT (Generative Pre-trained Transformer) model, the Wenxinyiyan model, etc. The instruction recognition prompt word is a prompt word for the large language model, which is used to instruct the large language model to perform instruction recognition for the input business operation instruction, so as to determine the operation object, operation type and operation parameters.

[0055] Optionally, the server may determine a pre-trained large language model and determine a corresponding instruction recognition prompt word. The instruction recognition prompt word may be configured according to actual needs. Different instruction recognition prompt words may be configured for different large language models or for different business system scenarios. In some embodiments, the server may determine the current business system scenario and determine the instruction recognition prompt word corresponding to the large language model based on the business system scenario.

[0056] Step 304 , using the large language model, the business operation instruction is recognized based on the instruction recognition prompt words to obtain formatted instruction information encapsulated in the target format.

[0057] The target format refers to the information encapsulation format, such as but not limited to the JSON (JavaScript Object Notation) format, and the formatted instruction information is the formatted information obtained by encapsulating the instruction recognition result according to the target format. The formatted instruction information may carry information such as the operation object, operation type, and operation parameters recognized by the large language model from the business operation instruction.

[0058] Exemplarily, the server can perform instruction recognition for business operation instructions through a large language model, such as the server can input the business operation instructions and instruction recognition prompt words into the large language model, so that the large language model can perform instruction recognition on the business operation instructions based on the instruction recognition prompt words to obtain instruction recognition results. The large language model can encapsulate the instruction recognition results according to the target format to obtain corresponding formatted instruction information. In some embodiments, the target format can be flexibly configured according to actual needs, such as being configured to at least one of CSV (Comma-Separated Values) format, XML (eXtensible Markup Language) format, JSON format, and BSON (Binary JSON) format.

[0059] Step 306: Determine the operation object, operation type and operation parameters based on the formatted instruction information.

[0060] Exemplarily, the formatted instruction information carries information identified from the business operation instruction, and the server can determine the operation object, operation type, and operation parameters based on the business operation instruction. In some embodiments, the large language model can output formatted instruction information encapsulated in the target format, and the server can determine the operation object, operation type, and operation parameters from the formatted instruction information. For example, the business operation instruction includes an instruction to query the account balance, and the formatted instruction information output by the large language model can be in JSON format, which can specifically include {"action": "QUERY ACCOUNTBALANCE","target account": 1001,"period": "current period","balance column":"period end"}, and the server can determine the operation object, operation type, and operation parameters from the formatted instruction information.

[0061] In this embodiment, the server uses a large language model to perform instruction recognition on business operation instructions, and determines the operation object, operation type and operation parameters based on the formatted instruction information obtained by the large language model. Therefore, the operation object, operation type and operation parameters can be accurately determined through the large language model, which can improve the efficiency of business operation processing while ensuring the reliability of business operation instruction execution.

[0062] In an exemplary embodiment, the operation interface is determined based on the metadata of the operation object and the operation type, including: obtaining the interface metadata of the operation object, the interface metadata including the standard interface for the operation object; determining the target standard interface corresponding to the operation type from the interface metadata, and obtaining the operation interface based on the target standard interface.

[0063] The interface metadata is the metadata that defines the standard interface corresponding to the operation object. The interface metadata includes the standard interface for the operation object, such as the query class interface, the add class interface, the update class interface, and the remove class interface. The target standard interface is the interface corresponding to the operation type determined from various standard interfaces, and the operation interface can be obtained based on the target standard interface.

[0064] Optionally, the server may obtain interface metadata of the operation object, such as the server may query based on the object identifier of the operation object to query the interface metadata corresponding to the operation object, the interface metadata includes at least one standard interface for the operation object, and different standard interfaces may correspond to different operation types. The server may determine the corresponding target standard interface from the interface metadata according to the operation type, such as the server may match the operation type with each standard interface in the interface metadata respectively, and determine the standard interface matching the operation type as the target standard interface. The server may obtain the operation interface according to the target standard interface, such as the server may directly use the target standard interface as the operation interface, and the server may also use the target standard interface after the configuration is updated as the operation interface in response to the user's configuration operation on the target standard interface.

[0065] In this embodiment, the server determines the target standard interface from the interface metadata of the operation object based on the operation type, and obtains the operation interface based on the target standard interface. The operation interface can be obtained by using the standard interface of the operation object, and the standard interface of the operation object can be accurately reused, which is beneficial to improving the processing efficiency of business operations.

[0066] In an exemplary embodiment, the business operation processing method further includes: when the interface metadata does not include a target standard interface corresponding to the operation type, configuring a corresponding custom interface for the operation object according to the operation type; and obtaining the operation interface according to the custom interface.

[0067] Among them, the custom interface is an interface directly configured for the operation object according to the operation type, and the operation interface can be obtained based on the custom interface. Exemplarily, when it is determined that the target standard interface corresponding to the operation type is not included in the interface metadata, such as when the server does not determine the target standard interface that matches the operation type from the interface metadata, the server can directly configure the custom interface for the operation object, such as the server can configure the corresponding custom interface for the operation object according to the operation type. In some embodiments, the server can configure the corresponding custom interface based on the operation type, the data table of the operation object, parameters, etc. The server can obtain the operation interface based on the custom interface, such as the server can directly use the custom interface as the operation interface, or it can respond to the user's configuration operation on the custom interface and use the updated custom interface as the operation interface.

[0068] In this embodiment, when the target standard interface corresponding to the operation type is not obtained, the server configures the corresponding custom interface for the operation object according to the operation type, and obtains the operation interface based on the custom interface. The custom interface can be configured according to the actual needs of the operation type to obtain the operation interface, which can ensure the targeted nature of the operation interface and is conducive to improving the processing efficiency of business operations.

[0069] In an exemplary embodiment, a target plug-in corresponding to a business operation instruction is generated based on an operation interface, including: determining an interface code corresponding to the operation interface according to an interface type to which the operation interface belongs; generating a plug-in code based on the interface code and a general processing code, and obtaining a target plug-in corresponding to the business operation instruction according to the plug-in code.

[0070] Among them, the interface type is the type of interface classification, such as standard interface type and custom interface type. The interface code is the code that defines the interface. Interfaces of different interface types can obtain corresponding interface codes in different ways. The general processing code is the code required for generating the pre-processing and post-processing in the plug-in code, such as pre-codes such as permission verification and security verification, and post-codes such as resource release and result information encapsulation. The plug-in code is the code used to implement the plug-in function. The corresponding function of the plug-in can be realized by executing the plug-in code corresponding to the plug-in.

[0071] Exemplarily, the server can determine the interface type to which the operation interface belongs, such as determining whether the operation interface belongs to a standard interface type or a custom interface type, and the server can determine the interface code corresponding to the operation interface based on the interface type. For example, for an operation interface of a standard interface type, the server can directly query and obtain the interface code corresponding to the operation interface. For another example, for an operation interface of a custom interface type, the server can obtain the corresponding interface code for the configuration. The server can obtain a general processing code, which may include but is not limited to at least one of the pre-codes including permission verification, security verification, and post-codes including resource release, result information encapsulation, etc. The server can generate a plug-in code based on the interface code and the general processing code, and obtain a target plug-in corresponding to the business operation instruction based on the plug-in code. The target plug-in may include the plug-in code, and the business function corresponding to the target plug-in may be implemented by executing the plug-in code, such as executing the business operation instruction.

[0072] In this embodiment, the server determines the corresponding interface code according to the interface type to which the operation interface belongs, and generates the plug-in code in combination with the general processing code to obtain the target plug-in. The corresponding plug-in code can be generated for the operation interface to ensure the reliability of the target plug-in, which is conducive to ensuring the reliability of business operation processing.

[0073] In an exemplary embodiment, determining the interface code corresponding to the operation interface according to the interface type to which the operation interface belongs includes: when the interface type to which the operation interface belongs is a standard interface type, querying the interface code corresponding to the operation interface.

[0074] Optionally, for an operation interface that is a standard interface type, the server can directly query the interface code corresponding to the operation interface. In some embodiments, the server can generate corresponding interface codes for various standard interfaces in advance. When the server determines a target standard interface from various standard interfaces and obtains an operation interface based on the target standard interface, the interface type of the operation interface is a standard interface type, and the server can directly query the interface code corresponding to the target standard interface, thereby obtaining the interface code corresponding to the operation interface.

[0075] In this embodiment, for the operation interface of the standard interface type, the server directly queries the corresponding interface code, which can improve the efficiency of obtaining the interface code, thereby facilitating improving the processing efficiency of the business operation.

[0076] In an exemplary embodiment, the interface code corresponding to the operation interface is determined according to the interface type to which the operation interface belongs, including: when the interface type to which the operation interface belongs is a custom interface type, the interface code corresponding to the operation interface is constructed based on the operation object, operation type, operation parameters and code mapping relationship.

[0077] Among them, the code mapping relationship may record the mapping relationship between different operation types and operation parameters and codes. Based on the code mapping relationship, the corresponding interface code may be constructed using the operation type and operation parameters. Exemplarily, for an operation interface belonging to a custom interface type, that is, the operation interface is obtained based on the custom interface, the server may obtain a pre-set code mapping relationship, and the code mapping relationship may include a direct correspondence between the operation type and the operation parameter and the code. The server may construct an interface code corresponding to the operation interface based on the operation object, operation type, operation parameter and code mapping relationship.

[0078] In this embodiment, for the operation interface of the custom interface type, the server constructs the corresponding interface code based on the operation object, operation type, operation parameters and code mapping relationship, which can ensure the reliability of the interface code and thus ensure the reliability of business operation processing.

[0079] In an exemplary embodiment, determining the plug-in parameters corresponding to the target plug-in according to the operation parameters includes: obtaining parameter construction rules, the parameter construction rules including the correspondence between the operation parameters in the business operation instructions and the plug-in parameters; determining the plug-in parameters corresponding to the target plug-in based on the operation parameters and the parameter construction rules.

[0080] The parameter construction rule includes the correspondence between the operation parameters and the plug-in parameters, and the operation parameters in the business operation instruction can be mapped into plug-in parameters applicable to the plug-in through the parameter construction rule. Exemplarily, the server can obtain the pre-constructed parameter construction rule, and perform parameter mapping on the operation parameters based on the parameter construction rule to obtain the plug-in parameters corresponding to the target plug-in. In some embodiments, the server can map the operation parameters according to the parameter construction rule to map the operation parameters into the plug-in parameters corresponding to the target plug-in.

[0081] In this embodiment, the server determines the plug-in parameters corresponding to the target plug-in by using the parameter construction rules and the operation parameters, which can ensure the accuracy of the plug-in parameters and thus ensure the reliability of the business operation processing.

[0082] The present application also provides an application scenario, and the application scenario applies the above-mentioned business operation processing method. Specifically, the application of the business operation processing method in the application scenario is as follows:

[0083] For functions (micro-functions) with relatively simple business logic, such as querying the balance of a certain account, modifying the value of a certain parameter, deleting a specified document, copying a plan of an organization, and other micro-functions, if the standard GPT development model is also followed, prompt words, tasks, and plug-ins are configured separately, similar plug-ins will be repeatedly developed, which will waste manpower and time resources. Moreover, similar tasks are repeatedly configured and switched during use, which affects the processing efficiency of business operations. Based on this, the business operation processing method provided in the embodiment of the present application allows GPT to identify instructions and parameters through prompt words, and then dynamically generates plug-ins to perform corresponding tasks based on the identified instructions and parameters according to the construction rules, thereby avoiding repeated development through the real-time dynamic generation of task plug-ins, and improving the efficiency and intelligence of GPT function development.

[0084] Specifically, the business operation processing method provided in the embodiment of the present application can be configured with GPT model recognition instructions and operation parameters, wherein the prompt word of GPT needs to be set to a general form, that is, different types of business operation instructions can be identified, and multiple examples can be configured in the prompt word to explain which of them are instructions and which are operation parameters. For example, a query instruction: query the end-of-period balance of account 1001 in this period; wherein the instruction is to query the account balance, and the operation parameters include the target account - 1001, period - this period, and balance column - end-of-period balance. For example, a modification instruction: modify the system parameter GL001 to true; wherein the instruction is to modify the system parameter, and the operation parameters include modification target - GL001, target value - true. For example, a copy instruction: copy the 001 carry-forward profit and loss plan of organization A to organization B; wherein the instruction is to copy the carry-forward profit and loss plan, and the operation parameters include the source organization - organization A, the source plan - 001, and the target organization - organization B.

[0085] In order to accurately build subsequent plug-ins, GPT needs to output the recognized instructions and operation parameters in the specified target format, such as encapsulating them in JSON format.

[0086] For example, the command to query the account balance:

[0087] {

[0088] "action": "QUERY ACCOUNT BALANCE",

[0089] "target account": 1001,

[0090] "period": "current period",

[0091] "balance column": "period end"

[0092] }

[0093] Such as modifying system parameter commands:

[0094] {

[0095] "action": "UPDATE SYSTEM PARAM",

[0096] "target param": "GL001",

[0097] "target value": true

[0098] }

[0099] For example, copy the instruction of carry-forward profit and loss plan:

[0100] {

[0101] "action": "COPY PL PLAN",

[0102] "source org": "A",

[0103] "source plan": "001",

[0104] "target org": "B"

[0105] }

[0106] Specifically, in the business operation processing method provided in the embodiment of the present application, Figure 4As shown, after the server obtains the business operation instruction, it can input it into the GPT model, and determine the operation object and the operation type for the operation object according to the instruction returned by GPT, and determine the function performed on the operation object based on the operation type. The server can obtain metadata such as Façade (interface metadata) and Entity (entity metadata). When it is determined that the function performed on the operation object belongs to a standard function according to the operation type, the server can directly obtain the standard interface from the metadata to obtain the operation interface, otherwise the server can determine the custom interface to obtain the operation interface, and the server can generate the target plug-in based on the obtained operation interface. The server can construct the plug-in parameters required by the target plug-in based on the parameter construction rules and the operation parameters of GPT; and after executing the target plug-in, it returns the execution result, thereby realizing the business operation processing corresponding to the business operation instruction.

[0107] Among them, first of all, it is necessary to confirm the operation object according to the business operation instruction. The operation object refers to the documents, parameters, basic information, data tables, etc. in the system. Documents can include electronic documents entered through the computer system, and basic information can include basic data required for the operation of the business system, including accounting subjects, customers, suppliers and other data. For systems built with metadata modeling drive, after determining the operation object and knowing what operation to perform on the operation object, you can use the metadata of the operation object to obtain its existing standard interface. For example, query operations obtain query-related interfaces. Facade and Entity in the figure are aliases for interface metadata and entity metadata, respectively. This metadata defines the standard interface of the function (operation object). For systems that are not built with metadata drive, the corresponding operation interface can be determined by configuration files, registry tables, etc. All instruction operations can ultimately be classified into four major types: query, add, modify and delete. For example, copying can be classified as a new instruction operation. Each type of instruction corresponds to the corresponding type of interface. For example Figure 5 As shown, the operation types may include query, add, modify and delete, and the corresponding standard interfaces may be Query class interface, Add class interface, Update class interface and Remove class interface.

[0108] If the corresponding standard interface can be found in the metadata, the target plug-in is directly constructed using the corresponding standard interface. If there is no corresponding standard interface, the data table of the operation object is directly obtained and the target plug-in is constructed through the custom interface. The generated target plug-in can be loaded into the system in real time and wait for invocation.

[0109] Furthermore, the operation parameters returned by GPT need to correspond to the plug-in parameters in the target plug-in, that is, the parameters required for the plug-in method to run should be obtained from the GPT return parameters. The ideal situation is that the GPT parameters and the parameter names and types of the plug-in methods completely correspond one to one, but in practice it may be difficult to achieve the ideal state, so you can set parameter construction rules to make the parameters of the two correspond correctly. Figure 6 As shown in the figure, among the operation parameters output by GPT, "target account:String" can correspond to the plug-in parameter "accountNumber:String"; "period:String" can correspond to the plug-in parameter "periodStr:String"; "balance column:String" can correspond to the plug-in parameter "columnStr:String". After the parameters are matched, the target plug-in can be executed, such as the method of the plug-in class, and the execution result is finally returned.

[0110] Among them, plug-in construction rules are divided into two categories: standard interface and custom interface, such as Figure 7 As shown, for the standard interface, before the formal call, the plugin code of the target plugin should also include pre-processing and post-processing content, including pre-processing code such as permission verification and security verification, and post-processing code such as resource release and result information encapsulation. For example, the plugin code generated for the standard interface can include:

[0111] / / T0D0: permission processing functionA()

[0112] / / TOD0: security processing functionB()

[0113] / / TOD0: parameter processing functionc()

[0114] / / TOD0: standard interface call processing functionD()

[0115] / / TOD0: Resource release processing functionE()

[0116] / / TOD0: return result processing functionF()

[0117] The pre- and post-processing of the custom interface is the same as that of the standard interface. The difference is that it has no standard interface to call, and needs to build an executable SQL (Structured Query Language) script based on the instruction operation, the data table of the operation object, parameters, etc. For example, the plug-in code generated for the custom interface can include:

[0118] / / T0D0: permission processing functionA()

[0119] / / TOD0: security processing functionB()

[0120] / / T0D0: parameter processing functionc()

[0121] / / TOD0: custom interface processing functionD()

[0122] / / TOD0: Resource release processing functionE()

[0123] / / TOD0: return result processing functionF()

[0124] The processing contents of the pre-code and post-code in the above examples are only for common scenarios. The specific implementation should be combined with the actual functional scenario. Figure 8 As shown, the correspondence rules between different operation types and SQL keywords, among which "query" can correspond to "select", "add" can correspond to "insert", "modify" can correspond to "update", and "delete" can correspond to "delete". The business operation processing method provided in the embodiment of the present application can realize a functional plug-in with relatively simple business logic. When there are the correspondence rules between the four major types of operations of adding, deleting, modifying and checking and the SQL keywords, as well as the data tables and columns corresponding to the operation objects contained in the instructions, it is enough to build an executable SQL script, so the custom interface code can be generated according to the actual application scenario.

[0125] The business operation processing method provided in the embodiment of the present application can improve the development efficiency and intelligence of GPT applications, avoid repeated development of plug-ins, save resources, and improve the user experience of using smart applications.

[0126] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0127] Based on the same inventive concept, the embodiment of the present application also provides a business operation processing device for implementing the business operation processing method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the one or more business operation processing device embodiments provided below can refer to the limitations on the business operation processing method above, and will not be repeated here.

[0128] In an exemplary embodiment, Fig. 9 As shown, a business operation processing device 900 is provided, including: an operation instruction acquisition module 902, an operation interface determination module 904, a plug-in generation module 906, a plug-in parameter determination module 908 and a plug-in execution module 910, wherein:

[0129] The operation instruction acquisition module 902 is used to acquire the business operation instruction and determine the operation object, operation type and operation parameters based on the business operation instruction;

[0130] An operation interface determination module 904 is used to determine the operation interface according to the metadata of the operation object and the operation type;

[0131] A plug-in generation module 906 is used to generate a target plug-in corresponding to the business operation instruction based on the operation interface;

[0132] A plug-in parameter determination module 908, configured to determine plug-in parameters corresponding to a target plug-in according to the operation parameters;

[0133] The plug-in execution module 910 is used to execute the target plug-in according to the plug-in parameters to obtain the business operation result corresponding to the business operation instruction.

[0134] In an exemplary embodiment, the operation instruction acquisition module 902 is also used to determine the pre-trained large language model and the instruction recognition prompt words corresponding to the large language model; through the large language model, the business operation instructions are recognized based on the instruction recognition prompt words to obtain formatted instruction information encapsulated according to the target format; based on the formatted instruction information, the operation object, operation type and operation parameters are determined.

[0135] In an exemplary embodiment, the operation interface determination module 904 is also used to obtain interface metadata of the operation object, which includes a standard interface for the operation object; determine the target standard interface corresponding to the operation type from the interface metadata, and obtain the operation interface based on the target standard interface.

[0136] In an exemplary embodiment, the operation interface determination module 904 is also used to configure a corresponding custom interface for the operation object according to the operation type when the interface metadata does not include a target standard interface corresponding to the operation type; and obtain the operation interface according to the custom interface.

[0137] In an exemplary embodiment, the plug-in generation module 906 is also used to determine the interface code corresponding to the operation interface according to the interface type to which the operation interface belongs; generate the plug-in code based on the interface code and the general processing code, and obtain the target plug-in corresponding to the business operation instruction according to the plug-in code.

[0138] In an exemplary embodiment, the plug-in generation module 906 is further configured to query the interface code corresponding to the operation interface when the interface type to which the operation interface belongs is a standard interface type.

[0139] In an exemplary embodiment, the plug-in generation module 906 is further used to construct an interface code corresponding to the operation interface based on the operation object, operation type, operation parameters and code mapping relationship when the interface type to which the operation interface belongs is a custom interface type.

[0140] In an exemplary embodiment, the plug-in parameter determination module 908 is also used to obtain parameter construction rules, which include the correspondence between operation parameters in the business operation instruction and plug-in parameters; and determine the plug-in parameters corresponding to the target plug-in based on the operation parameters and the parameter construction rules.

[0141] Each module in the above-mentioned business operation processing device can be implemented in whole or in part by software, hardware or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each module above.

[0142] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Fig.10As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store various data involved in the business operation processing method. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a business operation processing method is implemented.

[0143] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Fig.11 As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, near field communication (NFC) or other technologies. When the computer program is executed by the processor, a business operation processing method is implemented. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0144] Those skilled in the art will understand that Fig.10 or Fig.11The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0145] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0146] In one embodiment, a computer-readable storage medium is provided, storing a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0147] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0148] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0149] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0150] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0151] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A business operation processing method, characterized in that: The method comprises: Obtaining a business operation instruction, and determining an operation object, an operation type, and an operation parameter based on the business operation instruction; Determine an operation interface according to the metadata of the operation object and the operation type; Generate a target plug-in corresponding to the business operation instruction based on the operation interface; Determine a plug-in parameter corresponding to the target plug-in according to the operation parameter; The target plug-in is executed according to the plug-in parameters to obtain a business operation result corresponding to the business operation instruction.

2. The method according to claim 1, characterized in that The determining of the operation object, operation type and operation parameters based on the business operation instruction includes: Determine a pre-trained large language model and an instruction recognition prompt word corresponding to the large language model; Using the large language model, the business operation instruction is identified based on the instruction identification prompt word to obtain formatted instruction information encapsulated in a target format; An operation object, an operation type and an operation parameter are determined based on the formatted instruction information.

3. The method according to claim 1, characterized in that The determining the operation interface according to the metadata of the operation object and the operation type includes: Acquire interface metadata of the operation object, wherein the interface metadata includes a standard interface for the operation object; A target standard interface corresponding to the operation type is determined from the interface metadata, and an operation interface is obtained according to the target standard interface.

4. The method according to claim 3, characterized in that The method further comprises: When the interface metadata does not include a target standard interface corresponding to the operation type, configuring a corresponding custom interface for the operation object according to the operation type; An operation interface is obtained according to the custom interface.

5. The method according to claim 1, characterized in that The generating a target plug-in corresponding to the business operation instruction based on the operation interface includes: Determine the interface code corresponding to the operation interface according to the interface type to which the operation interface belongs; A plug-in code is generated based on the interface code and the general processing code, and a target plug-in corresponding to the business operation instruction is obtained according to the plug-in code.

6. The method according to claim 5, characterized in that The determining, according to the interface type to which the operation interface belongs, an interface code corresponding to the operation interface includes at least one of the following: When the interface type to which the operation interface belongs is a standard interface type, querying the interface code corresponding to the operation interface; When the interface type to which the operation interface belongs is a user-defined interface type, an interface code corresponding to the operation interface is constructed based on the operation object, the operation type, the operation parameters and the code mapping relationship.

7. The method according to any one of claims 1 to 6, characterized in that: The determining the plug-in parameter corresponding to the target plug-in according to the operation parameter includes: Acquire parameter construction rules, wherein the parameter construction rules include a correspondence between operation parameters in the business operation instruction and plug-in parameters; A plug-in parameter corresponding to the target plug-in is determined based on the operation parameter and the parameter construction rule.

8. A business operation processing device, characterized in that: The device comprises: An operation instruction acquisition module is used to acquire a business operation instruction and determine an operation object, an operation type and an operation parameter based on the business operation instruction; An operation interface determination module, used to determine the operation interface according to the metadata of the operation object and the operation type; A plug-in generation module, used to generate a target plug-in corresponding to the business operation instruction based on the operation interface; A plug-in parameter determination module, used to determine the plug-in parameters corresponding to the target plug-in according to the operation parameters; The plug-in execution module is used to execute the target plug-in according to the plug-in parameters to obtain the business operation result corresponding to the business operation instruction.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images