Business instruction generation method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention relates to the artificial intelligence technology, in particular to a service instruction generation method and device, electronic equipment and a storage medium. Obtaining a to-be-processed service sent by each user through a mailbox; the business to be processed comprises at least one of a data document and a data image; identifying service elements in the service processing request through a pre-trained large model, and generating a service instruction according to the service elements; and generating a to-be-processed task according to the service instruction. According to the embodiment of the invention, the generation efficiency and accuracy of the service instruction are improved, and the real-time requirement of service processing is met.

Description

Technical Field

[0001] This application relates to artificial intelligence technology, and more particularly to a business instruction generation method, apparatus, electronic device, and storage medium. Background Technology

[0002] As the volume of banking business continues to increase, the amount of data continues to expand, and the demand for business instructions continues to grow.

[0003] In the existing technology, due to the complex systems and back-office processes of banks, as well as legacy systems that are difficult to communicate with, a large number of business instructions must be processed manually.

[0004] However, manual processing is inefficient and cannot guarantee accuracy, failing to meet users' needs for real-time business processing. Summary of the Invention

[0005] This application provides a business instruction generation method, apparatus, electronic device, and storage medium to improve the efficiency and accuracy of business instruction generation and meet the real-time requirements of business processing.

[0006] In a first aspect, embodiments of this application provide a method for generating business instructions, the method comprising:

[0007] Retrieve pending business requests sent by each user via email; the pending business requests include at least one of data documents and data images;

[0008] The pre-trained large model identifies business elements in business processing requests and generates business instructions based on these elements.

[0009] Generate tasks to be processed based on business instructions.

[0010] Secondly, embodiments of this application also provide a business instruction generation apparatus, which includes:

[0011] The pending business acquisition module is used to acquire pending business sent by each user via email; the pending business includes at least one of data documents and data images;

[0012] The business instruction generation module is used to identify business elements in business processing requests through a pre-trained large model and generate business instructions based on these elements.

[0013] The pending task generation module is used to generate pending tasks based on business instructions.

[0014] Thirdly, embodiments of this application also provide an electronic device, which includes:

[0015] One or more processors;

[0016] Storage device for storing one or more programs;

[0017] When one or more programs are executed by one or more processors, the one or more processors implement any of the business instruction generation methods provided in the embodiments of this application.

[0018] Fourthly, embodiments of this application also provide a storage medium including computer-executable instructions, which, when executed by a computer processor, are used to perform any of the business instruction generation methods provided in embodiments of this application.

[0019] This application obtains pending business requests sent by users via email; these pending business requests include at least one of data documents and data images. A pre-trained large-scale model identifies business elements in the business processing requests and generates business instructions based on these elements. Based on the business instructions, pending tasks are generated. Leveraging the contextual understanding capabilities of the large-scale model, business elements are automatically identified, and business instructions are generated, improving the efficiency and accuracy of business instruction generation and thus meeting the real-time requirements of business processing. Therefore, the technical solution of this application solves the problems of low efficiency and inaccuracy in manual processing, failing to meet users' needs for real-time business processing, and achieving the effect of improving the efficiency and accuracy of business instruction generation and meeting the real-time requirements of business processing. Attached Figure Description

[0020] Figure 1 This is a flowchart of a business instruction generation method according to Embodiment 1 of this application;

[0021] Figure 2 This is a flowchart of a business instruction generation method according to Embodiment 2 of this application;

[0022] Figure 3 This is a schematic diagram of the structure of a business instruction generation device according to Embodiment 3 of this application;

[0023] Figure 4 This is a schematic diagram of the structure of an electronic device according to Embodiment 4 of this application. Detailed Implementation

[0024] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0025] It should be noted that the terms "first" and "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0026] Example 1

[0027] Figure 1 This is a flowchart of a business instruction generation method provided in Embodiment 1 of this application. This embodiment can be applied to the situation where processing instructions are automatically generated based on user documents. The method can be executed by a business instruction generation device, which can be implemented in software and / or hardware and specifically configured in an electronic device, such as a business processing platform.

[0028] See Figure 1 The business instruction generation method shown includes the following steps:

[0029] S110. Obtain pending business requests sent by each user via email.

[0030] Users can send pending tasks via email. These pending tasks include at least one of data documents and data images. For example, a dedicated instruction management email address can be set up to receive pending tasks sent by users via email; the instruction management email address retrieves the pending tasks sent by each user via email.

[0031] For example, the instruction management email can be a dedicated email address for receiving instructions and related attachments sent by the management company. It is embedded in the business system and shared online under the premise of localized management (for the banking system, there is localized isolation between the public email systems of the head office and various branches, with each region having a dedicated email address, and email sharing is achieved for users with permissions in the same region).

[0032] The instruction management email system has a sorting function. It can identify the sender's organization by information such as the sender's email domain or suffix, and perform initial email sorting in real time based on the management company. After obtaining the pending business sent by the corresponding user via email, it automatically passes it to a pre-trained large model.

[0033] S120. Identify business elements in business processing requests using a pre-trained large model, and generate business instructions based on the business elements.

[0034] A pre-trained large model can be a large model trained in advance based on historical data, which can identify business elements. For example, historical business processing requests and corresponding business elements extracted manually can be used as samples to train the large model, resulting in a pre-trained large model.

[0035] Business elements can be elements used to generate business instructions. For example, business elements may include business type, account name, and identity identifier, etc., and this application does not specifically limit these. Business instructions can be processing instructions generated according to the language rules of the corresponding business system, used to instruct the business system to perform business processing.

[0036] The business processing request is input into a pre-trained large model to obtain business elements. Based on the business type corresponding to the business elements, business instructions that conform to the rules are automatically generated.

[0037] Optionally, after recognizing the characters in the business to be processed using optical character recognition technology, the semantic understanding capabilities of the large model can be used to identify the business elements in the business processing request, thereby improving the accuracy of business element recognition.

[0038] S130. Generate tasks to be processed based on business instructions.

[0039] The pending tasks can be generated based on business instructions. For example, pending tasks can be generated based on the processing time in the business instructions, and then sent to the corresponding processing system.

[0040] It should be noted that all information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for display, data used for analysis, etc.) involved in this disclosure are information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data comply with the relevant laws, regulations and standards of the relevant regions.

[0041] In recent years, with the continuous increase in banking business volume and data volume, the demand for customer instructions has been growing. The complex systems and back-office processes of banks, as well as legacy systems that are difficult to communicate with, have resulted in a large number of customer instructions having to be processed manually.

[0042] Manual data entry is not only time-consuming and labor-intensive, but also susceptible to subjective interference, leading to data verification errors. Moreover, when faced with massive amounts of data, manual operation is extremely inefficient and cannot meet the needs of rapid development and high-frequency data processing in the financial industry.

[0043] Traditional character recognition technology has low accuracy, mainly relying on image quality. The recognition rate drops significantly when dealing with low-resolution, blurry, or slanted text. It is also sensitive to format and layout, and is prone to errors when recognizing tables, handwritten text, or complex layouts (such as mixed text and images). Furthermore, it lacks semantic understanding, extracting only the text without comprehending the context.

[0044] The technical solution of this embodiment obtains pending business requests sent by users via email; these pending business requests include at least one of data documents and data images; a pre-trained large model identifies business elements in the business processing requests and generates business instructions based on these elements; pending tasks are generated based on the business instructions. Leveraging the contextual understanding capabilities of the large model, business elements are automatically identified and business instructions are generated, improving the efficiency and accuracy of business instruction generation and thus meeting the real-time requirements of business processing. Therefore, the technical solution of this application solves the problems of low efficiency and inaccuracy in manual processing, failing to meet users' needs for real-time business processing, and achieves the effect of improving the efficiency and accuracy of business instruction generation, thus meeting the real-time requirements of business processing.

[0045] Example 2

[0046] Figure 2 This is a flowchart of a business instruction generation method provided in Embodiment 2 of this application. The technical solution of this embodiment is further refined based on the above technical solution.

[0047] Furthermore, the process of "identifying business elements in business processing requests through a pre-trained large model and generating business instructions based on the business elements" is further refined into: "Inputting the business to be processed into a pre-trained large model to obtain business elements; determining whether to generate business instructions based on the business elements according to preset processing rules; if so, generating business instructions based on the business elements" to automatically generate business instructions.

[0048] See Figure 2 A business instruction generation method shown includes:

[0049] S210. Obtain pending business requests sent by each user via email; the pending business requests include at least one of data documents and data images.

[0050] S220. Input the business to be processed into the pre-trained large model to obtain the business elements.

[0051] The business data to be processed is input into a pre-trained large model, and the output is the business elements.

[0052] S230. Based on the preset processing rules, determine whether to generate a business instruction by considering the business elements.

[0053] The preset processing rules can be pre-defined business processing rules used to determine whether to generate a business instruction. For example, preset processing rules may include duplicate checks and business type checks, which are not specifically limited in this application. For instance, preset processing rules may include a pre-defined rule that no business instruction will be generated for a specific business type.

[0054] In one optional embodiment, determining whether to generate a business instruction based on business elements according to preset processing rules includes: performing a duplicate judgment on the business elements to obtain a duplicate judgment result, and performing a manual review judgment on the business elements to obtain a review judgment result; obtaining a generation judgment result based on the duplicate judgment result and the review judgment result; and determining whether to generate a business instruction based on the generation judgment result.

[0055] Duplicate detection can be used to determine whether a business instruction should be generated, based on the repetitive nature of the business being processed. For some pending business transactions, duplicate uploads may occur; therefore, duplicate detection helps prevent the generation of duplicate business instructions. The result of duplicate detection can be either "duplicate" or "not duplicate."

[0056] Manual review can be used to determine the final decision, including whether to generate a business instruction, based on the results of manual verification. For some pending business transactions, manual review may be necessary, such as those that are critical or prone to errors. Therefore, manual review improves the accuracy of the generated business instruction. The review result can be either "pass" or "fail." If manual review is required and confirmed to be error-free, the review result is "pass." If manual review is required but errors are found, the review result is "fail."

[0057] The generation judgment result is the result of determining whether to generate a business instruction based on the duplicate judgment result and the review judgment result. For example, if the duplicate judgment result is duplicate or the review judgment result is not passed, the generation judgment result is not to generate, and it is determined that no business instruction will be generated; if the duplicate judgment result is not duplicate and the review judgment result is passed, the generation judgment result is to generate, and it is determined that a business instruction will be generated.

[0058] The process involves repeatedly judging business elements to obtain a duplicate judgment result, and manually reviewing the business elements to obtain a review judgment result. Based on the duplicate judgment result and the review judgment result, a generation judgment result is obtained. Based on the generation judgment result, it is determined whether to generate a business instruction. The duplicate judgment avoids the repeated generation of business instructions, which would cause waste of resources, and the manual review judgment improves the accuracy of the generated business instructions.

[0059] In one optional embodiment, the business elements are manually reviewed and judged to obtain the review and judgment results, including: sending the business elements to the corresponding display device to obtain the element review results, and determining whether a seal comparison is required based on the business type; if so, calling the reserved seal based on the user identifier in the business element, and performing image comparison to obtain the seal comparison results; and determining the manual review results based on the seal comparison results and the element review results.

[0060] Business elements are sent to the corresponding display devices so that reviewers can verify them and obtain the element verification results. The element verification results can include pass or fail. For example, the instruction verification interface adopts a three-screen or four-screen simultaneous display format, with "Confirm" and "Cancel" buttons at the bottom.

[0061] In the banking system, the left-hand view is used to display the source files of all instructions and related attachments. For example, for an instruction to "withdraw principal from portfolio," a paper copy of the instruction and a transaction summary table should be displayed. Additionally, the email address should be indicated at the bottom of the file; clicking the link will automatically redirect the user to the email containing the instructions.

[0062] The intermediate view is used to fully display the instruction elements extracted after intelligent recognition by the large model. This view includes the elements that need to be filled in and the elements that need to be verified with the system. For example, for the "Combined Principal Withdrawal" instruction, the receiving account information needs to be verified against the receiving account information extracted by the large model from the paper instruction.

[0063] The right-hand view is used to fully display the command input interface. All command elements extracted from the large model should be filled in and compared with the existing system. All elements filled in here after being identified by the large model should be in an "editable" state.

[0064] The decision on whether seal comparison is required is determined based on the business type. If so, and seal comparison is necessary, the reserved seal is retrieved based on the user identifier in the business element, and an image comparison model is used to obtain the seal comparison result. For example, the seal comparison result can include seal matching and seal mismatch.

[0065] If the seal comparison result shows that the seals match and the element verification result is passed, then the manual verification result is passed; otherwise, it is not passed.

[0066] The system obtains the element verification results by sending business elements to the corresponding display devices, and determines whether seal comparison is required based on the business type. If so, it calls the reserved seal based on the user identifier in the business element and performs image comparison to obtain the seal comparison results. Based on the seal comparison results and element verification results, the system determines the manual verification results. Through seal comparison and element verification, the accuracy of business elements is fully guaranteed.

[0067] In one optional embodiment, obtaining a duplicate judgment result by performing a duplicate judgment on business elements includes: determining the judgment element based on the business type in the business element; and comparing the judgment elements to obtain the duplicate judgment result.

[0068] The elements required for duplicate detection may differ depending on the type of business transaction. For example, for money transfers, the elements for duplicate detection could be the recipient, the sender, and the amount; for shopping transactions, the elements could be the buyer, the item name, and the quantity. The key elements are the factors that need to be compared when determining the duplicate detection result. If all key elements are the same, the result is determined to be duplicate; otherwise, the result is determined to be non-duplicate.

[0069] By determining the decision-making elements based on the business type in the business elements, and comparing the decision-making elements, duplicate judgment results are obtained, thus avoiding the repeated generation of business instructions and the waste of computing resources.

[0070] S240. If so, then generate business instructions based on business elements.

[0071] If so, that is, if it is determined that a business instruction will be generated, then the corresponding business instruction can be generated based on the business elements and the rules for generating business instructions.

[0072] In an optional embodiment, if so, generating a business instruction based on a business element includes: if so, determining a target business instruction template based on the business type in the business element; and generating a business instruction based on the business element and the target business instruction template.

[0073] The target business instruction template can be an instruction template corresponding to the business type of the business to be processed, used to generate business instructions. The business elements are then filled into the corresponding positions in the target business instruction template to obtain the business instructions.

[0074] If yes, then based on the business type in the business elements, determine the target business instruction template; generate business instructions based on the business elements and the target business instruction template, automatically generating business instructions and improving the efficiency of business instruction generation.

[0075] S250: Generate tasks to be processed based on business instructions.

[0076] The technical solution of this embodiment obtains business elements by inputting the business to be processed into a pre-trained large model. Based on the analysis capabilities of the large model, the accuracy of the business elements is improved. According to preset processing rules, it is determined whether to generate a business instruction based on the business elements. The accuracy of business instruction generation is improved by judging based on the preset processing rules. If so, a business instruction is generated based on the business elements. This can quickly and automatically generate business instructions and improve the efficiency of business instruction generation.

[0077] Example 3

[0078] Figure 3 The diagram shown is a schematic representation of a business instruction generation device according to Embodiment 3 of this application. This embodiment is applicable to situations where processing instructions are automatically generated based on user documents. The specific structure of the business instruction generation device is as follows:

[0079] The pending business acquisition module 310 is used to acquire pending business sent by each user via email; the pending business includes at least one of data documents and data images;

[0080] The business instruction generation module 320 is used to identify business elements in business processing requests through a pre-trained large model and generate business instructions based on the business elements.

[0081] The pending task generation module 330 is used to generate pending tasks based on business instructions.

[0082] The technical solution of this embodiment obtains pending business requests sent by users via email; these pending business requests include at least one of data documents and data images; a pre-trained large model identifies business elements in the business processing requests and generates business instructions based on these elements; pending tasks are generated based on the business instructions. Leveraging the contextual understanding capabilities of the large model, business elements are automatically identified and business instructions are generated, improving the efficiency and accuracy of business instruction generation and thus meeting the real-time requirements of business processing. Therefore, the technical solution of this application solves the problems of low efficiency and inaccuracy in manual processing, failing to meet users' needs for real-time business processing, and achieves the effect of improving the efficiency and accuracy of business instruction generation, thus meeting the real-time requirements of business processing.

[0083] Optionally, the business instruction generation module 320 includes:

[0084] The business element acquisition unit is used to input the business to be processed into a pre-trained large model to obtain business elements;

[0085] The preset processing rule judgment unit is used to determine whether to generate a business instruction based on the preset processing rules and business elements.

[0086] The business instruction generation unit is used to generate business instructions based on business elements if the conditions are met.

[0087] Optional, a preset processing rule judgment unit includes:

[0088] The judgment result determination subunit is used to perform duplicate judgments on business elements to obtain duplicate judgment results, and to perform manual review judgments on business elements to obtain review judgment results;

[0089] The judgment result determination subunit is used to obtain the judgment result based on the repeated judgment result and the verification judgment result;

[0090] The generation judgment subunit is used to determine whether to generate a business instruction based on the generation judgment result.

[0091] Optionally, the judgment result determines the sub-unit, specifically used for:

[0092] The business elements are sent to the corresponding display device to obtain the element verification results, and it is determined whether seal comparison is required based on the business type.

[0093] If so, the reserved seal is retrieved based on the user identifier in the business element, and the image is compared to obtain the seal comparison result.

[0094] Based on the results of seal comparison and element verification, the results of manual verification are determined.

[0095] Optionally, the judgment result determines the sub-unit, specifically used for;

[0096] Determine the key elements based on the business type within the business elements;

[0097] By comparing the critical factors, the results of repeated judgments are obtained.

[0098] Optionally, the business instruction generation unit includes:

[0099] The target business instruction template determination sub-unit is used to determine the target business instruction template based on the business type in the business element if the condition is met.

[0100] The business instruction generation subunit is used to generate business instructions based on business elements and target business instruction templates.

[0101] The business instruction generation apparatus provided in this application embodiment can execute the business instruction generation method provided in any embodiment of this application, and has the corresponding functional modules and beneficial effects of executing the business instruction generation method.

[0102] According to embodiments of the present invention, the present invention also provides an electronic device, a readable storage medium, and a computer program product.

[0103] Example 4

[0104] Figure 4 This is a schematic diagram of the structure of an electronic device provided in Embodiment 4 of this application, as shown below. Figure 4 As shown, the electronic device includes a processor 410, a memory 420, an input device 430, and an output device 440; the number of processors 410 in the electronic device can be one or more. Figure 4Taking a processor 410 as an example; the processor 410, memory 420, input device 430, and output device 440 in the electronic device can be connected via a bus or other means. Figure 4 Taking the example of a connection between China and Israel via a bus.

[0105] The memory 420, as a computer-readable storage medium, can be used to store software programs, computer-executable programs, and modules, such as the program instructions / modules corresponding to the service instruction generation method in this embodiment (e.g., the service acquisition module 310, the service instruction generation module 320, and the task generation module 330). The processor 410 executes various functional applications and data processing of the electronic device by running the software programs, instructions, and modules stored in the memory 420, thereby implementing the aforementioned service instruction generation method.

[0106] The memory 420 may primarily include a program storage area and a data storage area. The program storage area may store the operating system and at least one application program required for a given function; the data storage area may store data created based on terminal usage. Furthermore, the memory 420 may include high-speed random access memory and non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device. In some instances, the memory 420 may further include memory remotely located relative to the processor 410, which can be connected to the electronic device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0107] Input device 430 can be used to receive input character information and generate key signal inputs related to user settings and function control of the electronic device. Output device 440 may include display devices such as a display screen.

[0108] Example 5

[0109] Embodiment 5 of this application also provides a storage medium containing computer-executable instructions. When executed by a computer processor, the computer-executable instructions are used to execute a business instruction generation method. The method includes: obtaining pending business requests sent by each user via email; the pending business requests include at least one of data documents and data images; identifying business elements in the business processing requests using a pre-trained large model, and generating business instructions based on the business elements; and generating pending tasks based on the business instructions.

[0110] Of course, the computer-executable instructions provided in the embodiments of this application are not limited to the method operations described above, but can also execute related operations in the business instruction generation method provided in any embodiment of this application.

[0111] Based on the above description of the implementation methods, those skilled in the art can clearly understand that this application can be implemented using software and necessary general-purpose hardware, and of course, it can also be implemented using hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk, or optical disk, etc., including several instructions to cause an electronic device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0112] It is worth noting that in the embodiments of the above-mentioned business instruction generation device, the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of each functional unit are only for easy differentiation and are not used to limit the scope of protection of this application.

[0113] Note that the above are merely preferred embodiments and the technical principles employed in this application. Those skilled in the art will understand that this application is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions can be made without departing from the scope of protection of this application. Therefore, although this application has been described in detail through the above embodiments, this application is not limited to the above embodiments, and may include many other equivalent embodiments without departing from the concept of this application, the scope of which is determined by the scope of the appended claims.

Claims

1. A method for generating business instructions, characterized in that, include: Obtain pending tasks sent by each user via email; the pending tasks include at least one of data documents and data images; The pre-trained large model identifies business elements in business processing requests and generates business instructions based on these elements. A task to be processed is generated based on the business instructions.

2. The method according to claim 1, characterized in that, The process of identifying business elements in a business processing request using a pre-trained large model and generating business instructions based on those elements includes: The business to be processed is input into a pre-trained large model to obtain business elements; Based on preset processing rules, it is determined whether to generate a business instruction by using the business elements; If so, then generate business instructions based on the business elements.

3. The method according to claim 2, characterized in that, The step of determining whether to generate a business instruction based on the business elements according to preset processing rules includes: The business elements are subjected to duplicate judgment to obtain duplicate judgment results, and the business elements are subjected to manual review judgment to obtain review judgment results; Based on the duplicate judgment result and the verification judgment result, the generated judgment result is obtained; Based on the generation judgment result, determine whether to generate a business instruction.

4. The method according to claim 3, characterized in that, The manual review and judgment of the business elements to obtain the review and judgment results include: The business elements are sent to the corresponding display device to obtain the element verification results, and it is determined whether seal comparison is required based on the business type. If so, the reserved seal is retrieved based on the user identifier in the business element, and the image is compared to obtain the seal comparison result. Based on the seal comparison results and the element verification results, the manual verification results are determined.

5. The method according to claim 3, characterized in that, The process of obtaining a duplicate judgment result by performing duplicate judgment on the business elements includes: Based on the business type among the aforementioned business elements, determine the judgment elements; By comparing the critical factors, the results of repeated judgments are obtained.

6. The method according to claim 2, characterized in that, If so, then a business instruction is generated based on the business element, including: If so, then determine the target business instruction template based on the business type in the business elements; Generate business instructions based on the business elements and the target business instruction template.

7. A business instruction generation device, characterized in that, include: The pending business acquisition module is used to acquire pending business sent by each user via email. The pending business includes at least one of data documents and data images; The business instruction generation module is used to identify business elements in a business processing request using a pre-trained large model, and generate business instructions based on the business elements. The pending task generation module is used to generate pending tasks according to the business instructions.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the business instruction generation method as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the business instruction generation method as described in any one of claims 1-6.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the business instruction generation method according to any one of claims 1-6.

Images