Business process management method and device, computer equipment and storage medium

Abstract

The invention relates to the technical field of computers, and discloses a business process management method and device, computer equipment and a storage medium, and the business process management method comprises the steps that a function node matched with a business scene is acquired, and the function node is used for realizing a business function based on a preset language model; determining a target function node matched with a preset service function in the function nodes; and generating a target business process based on the target function node, and performing management operation on the target business process. According to the method and the device, the function node matched with the business scene can be directly called to select the target function node, and the target business process under the business scene is generated based on the target function node, so that coding and debugging required in the business process development process are greatly reduced, the requirement on research and development personnel is reduced, and the development efficiency is improved. Therefore, the business research and development cost and the management difficulty are reduced.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to a business process management method, apparatus, computer equipment, and storage medium. Background Art

[0002] In modern technology applications, large language models play a vital role. Due to their powerful language understanding and generation capabilities, large language models can provide support in a variety of scenarios, such as automated content generation, customer service, data analysis, etc. Therefore, large language models can be integrated into existing business processes to improve the efficiency of business processes and enhance customer experience.

[0003] However, in relevant business process management solutions, when customized development is carried out for business scenarios, R&D personnel are often required to conduct in-depth coding and debugging for specific scenarios, resulting in a long development cycle, more resource investment, and increased overall deployment costs of business processes. At the same time, R&D personnel are required to have strong programming skills and technical background in related industries, which limits the parameters of non-technical personnel and increases the difficulty of business process management. Summary of the invention

[0004] In view of this, the present disclosure provides a business process management method, apparatus, computer equipment and storage medium to solve the problem that when customized development is performed for business scenarios, R&D personnel are required to perform in-depth coding and debugging for specific scenarios.

[0005] In a first aspect, the present disclosure provides a business process management method, the method comprising:

[0006] Acquire a function node that matches the business scenario, wherein the function node is used to implement the business function based on a preset language model;

[0007] Determine a target function node matching a preset business function among the function nodes;

[0008] Based on the target function node, generate the target business process and perform management operations on the target business process.

[0009] In a second aspect, the present disclosure provides a business process management device, the device comprising:

[0010] An acquisition module, used to acquire a function node matching a business scenario, wherein the function node is used to implement a business function based on a preset language model;

[0011] A determination module, used to determine a target function node matching a preset business function among the function nodes;

[0012] The management module is used to generate a target business process based on the target function node and perform management operations on the target business process.

[0013] In a third aspect, the present disclosure provides a computer device, comprising: a memory and a processor, the memory and the processor are communicatively connected to each other, computer instructions are stored in the memory, and the processor executes the business process management method of the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0014] In a fourth aspect, the present disclosure provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the business process management method of the first aspect or any corresponding embodiment thereof.

[0015] In a fifth aspect, the present invention provides a computer program product, comprising computer instructions for causing a computer to execute the business process management method of the first aspect or any corresponding embodiment thereof.

[0016] In the disclosed embodiment, first, a function node matching the business scenario can be obtained, wherein the function node is used to implement the business function based on a preset language model. Next, a target function node matching the preset business function can be determined in the function node. Then, based on the target function node, a target business process can be generated, and management operations can be performed on the target business process, so that the function node matching the business scenario can be directly called to select the target function node therein, so as to generate the target business process under the business scenario based on the target function node, which greatly reduces the coding and debugging required in the business process development process, reduces the requirements for R&D personnel, and thus reduces the business R&D cost and management difficulty. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the specific embodiments of the present disclosure or the technical solutions in the prior art, the drawings required for use in the specific embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0018] Figure 1 is a flowchart of a business process management method according to an embodiment of the present disclosure;

[0019] Figure 2 is a framework diagram of a business process management system according to an embodiment of the present disclosure;

[0020] Figure 3 is a structural diagram of a language model configuration node according to an embodiment of the present disclosure;

[0021] Figure 4 is a schematic diagram of a configuration page of a language model configuration node displayed in a visual interface according to an embodiment of the present disclosure;

[0022] Figure 5 is a schematic diagram of a configuration page of a prompt header generation node displayed in a visual interface according to an embodiment of the present disclosure;

[0023] Figure 6 is a schematic diagram of a configuration page of a language model extension node displayed in a visual interface according to an embodiment of the present disclosure;

[0024] Figure 7 is a schematic diagram of a configuration page of a code editing node displayed in a visual interface according to an embodiment of the present disclosure;

[0025] Figure 8 is a schematic diagram of a data query business process according to an embodiment of the present disclosure;

[0026] Fig. 9 is a structural block diagram of a business process management device according to an embodiment of the present disclosure;

[0027] Fig.10 It is a schematic diagram of the hardware structure of the computer device of the embodiment of the present disclosure. DETAILED DESCRIPTION

[0028] In order to make the purpose, technical solution and advantages of the embodiments of the present disclosure clearer, the technical solution in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, rather than all the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present disclosure.

[0029] In conjunction with the application scenarios on which the execution of the business process management method depends, the application scenarios are described here.

[0030] In modern technology applications, large language models play a vital role. Due to their powerful language understanding and generation capabilities, large language models can provide support in a variety of scenarios, such as automated content generation, customer service, data analysis, etc. Therefore, large language models can be integrated into existing business processes to improve the efficiency of business processes and enhance customer experience.

[0031] However, in related business process management solutions, when customizing and developing for business scenarios, it often requires developers to conduct in-depth coding and debugging for specific scenarios, resulting in a longer development cycle, more resource investment, an increase in the overall deployment cost of business processes, and the need for developers to have strong programming capabilities and technical backgrounds in related industries, which limits the parameters for non-technical personnel and thus increases the difficulty of business process management.

[0032] Based on this, the embodiments of the present disclosure provide a business process management method. First, function nodes matching the business scenario can be obtained, where the function nodes are used to implement business functions based on a pre-set language model. Next, target function nodes matching the preset business function can be determined among the function nodes. Then, based on the target function nodes, a target business process can be generated and management operations can be performed on the target business process, so that function nodes matching the business scenario can be directly called to select target function nodes therefrom to generate the target business process in the business scenario, greatly reducing the coding and debugging required in the business process development process, reducing the requirements for developers, and thus reducing the business R & D cost and management difficulty.

[0033] According to the embodiments of the present disclosure, an embodiment of a business process management method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than here.

[0034] It can be understood that before using the technical solutions disclosed in the embodiments of the present disclosure, the types, usage scopes, usage scenarios, etc. of the personal information involved in the present disclosure should be informed to users and user authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0035] For example, when receiving a user's active request, a prompt message can be sent to the user to clearly prompt the user that the operation requested by the user will require obtaining and using the user's personal information. Thus, the user can autonomously choose whether to provide personal information to software or hardware such as an electronic device, an application program, a server, or a storage medium that executes the operations of the technical solutions of the present disclosure according to the prompt message.

[0036] As an optional but non-limiting implementation manner, the way of sending a prompt message to the user in response to receiving the user's active request can be, for example, in the form of a pop-up window, and the prompt message can be presented in text in the pop-up window. In addition, the pop-up window can also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0037] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that meet the relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0038] It is understandable that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and relevant provisions.

[0039] According to an embodiment of the present disclosure, a business process management method embodiment is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0040] In this embodiment, a business process management method is provided, which can be used in terminal devices, such as personal computers, etc. Figure 1 is a flowchart of a business process management method according to an embodiment of the present disclosure, such as Figure 1 As shown, the process includes the following steps:

[0041] Step S101, obtaining a function node matching a business scenario, wherein the function node is used to implement a business function based on a preset language model.

[0042] In the embodiments of the present disclosure, business scenarios may include scenarios such as automated content generation, customer service, and data analysis. Here, it is possible to adapt to each business scenario and clarify the specific functions of the large language model that need to be encapsulated to obtain functional modules, that is, the above-mentioned functional nodes, such as text generation, sentiment analysis, information extraction, etc. For example, if you want to implement an intelligent writing assistant, you need to encapsulate functions such as text generation and grammar checking.

[0043] Specifically, when encapsulating functional nodes, after clarifying the functional requirements, you can set input and output interfaces for each functional node. For example, the input interface should clearly define the data type and format of the received data, such as text strings, keyword lists, etc.; the output interface defines the form of the returned results, such as generated text paragraphs, sentiment analysis scores and labels, etc. Then, you can design the logic of the functional node to implement the function, and create visual interface elements for the functional node, such as buttons, text boxes, drop-down menus, etc. These elements should intuitively reflect the operation of the function and the display of the results.

[0044] Here, when obtaining a function node matching a business scenario, a visual interface element of the function node may be obtained and displayed in the interface of business process orchestration, so that developers can perform orchestration based on the visual interface element to construct a business process.

[0045] Step S102: determining a target function node matching a preset business function among the function nodes.

[0046] In the disclosed embodiment, the business capabilities required to be implemented by the business process can first be designed based on the business scenario to obtain the preset business functions. Then, the obtained function nodes can be combined to obtain the target business nodes that can implement the preset business functions.

[0047] For example, for a product recommendation business process, you can select a text generation node to generate recommendation words, select a database query node to obtain product information, and then select a decision node to determine the final recommendation result based on the user's preferences and historical behavior.

[0048] Step S103: Generate a target business process based on the target function node, and perform management operations on the target business process.

[0049] In the embodiment of the present disclosure, the visual interface elements corresponding to the target function nodes can be connected in the visual interface to obtain the target business process. Specifically, the selected nodes can be arranged and connected in the visual arrangement interface according to the logical order of the business process, and it is ensured that the data can be correctly transmitted and processed between the nodes to form a coherent target business process.

[0050] For example, in the above product recommendation business process, the user input can be first passed to the text generation node to generate a preliminary recommendation description, and then the description and user information can be passed to the database query node to obtain a list of related products, and finally the product list and user preferences and other information can be passed to the decision node to generate the final recommendation result. Therefore, the target business nodes can be connected in series in the logical order of text generation node-database query node-decision node to obtain the business process.

[0051] After determining the target business process, the target business process can be managed, such as verification and debugging. Specifically, the target business process can be fully verified and debugged, such as by simulating different business scenarios and input data to check whether the business process can be executed correctly, whether the collaboration between various nodes is normal, and whether the final output results meet expectations. Then, the problems found can be adjusted and repaired in a timely manner to ensure the reliability and effectiveness of the business process.

[0052] It can be seen from the above description that in the embodiment of the present disclosure, first, a function node matching the business scenario can be obtained, wherein the function node is used to implement the business function based on a preset language model. Next, a target function node matching the preset business function can be determined in the function node. Then, based on the target function node, a target business process can be generated, and management operations can be performed on the target business process, so that the function node matching the business scenario can be directly called to select the target function node therein, so as to generate the target business process under the business scenario based on the target function node, which greatly reduces the coding and debugging required in the business process development process, reduces the requirements for R&D personnel, and thus reduces the business R&D cost and management difficulty.

[0053] In some optional implementations, the above step S101, obtaining a function node matching the business scenario, includes:

[0054] Step S1011, obtaining a first node for calling a language model function, wherein the first node includes at least one of the following: a language model configuration node, a prompt header generation node, and a language model extension node, the prompt header generation node is used to generate a prompt header input into the language model, and the language model extension node is used to extend the function of the language model.

[0055] Step S1012, obtaining a second node that matches the function of the first node, wherein the second node includes at least one of the following: a code editing node, a message push node, and a query statement node, the code editing node is used to edit variables referenced in the metadata of each functional node, the message push node is used to push the output result of the language model, and the query statement node is used to generate a corresponding query statement based on the input content of the language model.

[0056] Step S1013: determine a functional node according to the first node and the second node.

[0057] In the embodiment of the present disclosure, the first node and the second node may be visual arrangement nodes corresponding to the core functions. Figure 2 The figure shows a framework diagram of a business process management system, wherein a visual orchestration unit is used to manage the above functional nodes.

[0058] Specifically, the language model configuration node is Figure 2 The large model execution node in the prompt header generation node is the text recall node, the query statement node is the atomic capability node, the code editing node is the code conversion node, and the language model extension node is the plugin node.

[0059] In addition, the above-mentioned business process management system also includes: language model application development platform, front-end development kit (Software Development Kit, hereinafter referred to as SDK) embedding, http debugging and process engine. Here, the language model application development platform is used to connect the business process to the language model, the front-end SDK embedding is used to select the corresponding SDK package according to the business process, http (a communication interface) debugging is used to realize the communication between the business process development end and the service end, and the process engine is the engine base that supports process orchestration and process execution. In the language model application development platform, the process engine is used to manage and control the execution process of the business process.

[0060] In the embodiments of the present disclosure, a function node can be determined based on a first node for calling a language model function and a second node that matches the function of the first node, thereby connecting the choreographed business process to the language model, improving the work efficiency of the business process and enhancing the customer experience.

[0061] In some optional implementations, the above step S103, generating a target business process based on the target function node, includes:

[0062] S1031, in response to the modification instruction, obtaining modification content.

[0063] S1032, modify the configuration items of the target function node based on the modified content, and perform orchestration based on the modified target function node to obtain a target business process.

[0064] In the disclosed embodiment, the metadata of the function node and the configuration items in the function node are dynamically configured. Here, when defining the function node, a variety of basic element components can be pre-defined to obtain the configuration items, and the configuration items are assembled to obtain the function node. When the user needs to modify the function node or modify the configuration items of the function node, the modification content can be generated in the visual arrangement node, and the metadata corresponding to the function node or the configuration item can be maintained according to the modification content without the need for front-end development.

[0065] Specifically, Figure 3The figure shows the structure of the above language model configuration node, which consists of 7 configuration items, including input component, language model component, prompt header component, multi-round conversation component, message push component, output component and editor component. Here, the input component is responsible for receiving external input information and passing it to the subsequent language model for processing. The language model component is the core part of the entire configuration, which is used to process and analyze the input information and generate corresponding output results. The prompt header (i.e., prompt) component provides additional prompt information for the language model to help the model better understand the input content and task requirements. The multi-round conversation component is used to manage and maintain multi-round conversation interactions with users. The message push component is used to push the results generated by the language model or other related information to the specified recipient, such as users, other systems or applications. The output component is used to process and format the results generated by the language model to meet specific output requirements and format standards. The editor component is used to build and manage the configuration process of the language model.

[0066] It should be understood that each configuration item in the language model configuration node can be modified by modifying the instruction. Here, the prompt header component is taken as an example. When the user needs to add a configuration item in the prompt header component, it can be achieved by modifying the definition of the prompt header component.

[0067] For example, if you need to add a new "emotional tendency" configuration item to control the emotional color of the generated text. According to the function of the configuration item, determine its data type, such as string, number, Boolean value, list, etc. For the "emotional tendency" configuration item, it may be a string type containing options such as "positive", "negative", and "neutral". Then, you can set a reasonable default value for the newly added configuration item so that the system can run according to the default behavior when no special configuration is performed. For example, the default value of "emotional tendency" can be set to "neutral". Next, you can find the data structure that stores configuration information in the code of the prompt header component, usually a dictionary, object, or configuration file, and add the newly added configuration item to this data structure. Finally, you can find all the places that reference and use the prompt header component configuration in the metadata of the prompt header component, such as model training scripts, prediction functions, data processing processes, etc., and modify the relevant logic code according to the function and purpose of the newly added configuration item. If the newly added "emotional tendency" configuration item affects the style of text generation, then the corresponding judgment and processing code needs to be added in the logic of text generation.

[0068] In the embodiments of the present disclosure, it is possible to respond to a modification instruction for a configuration item, obtain the modification content, and modify the metadata of the configuration item of the target functional node based on the modification content without performing front-end development on the functional node, thereby achieving zero-code or low-code business process orchestration, lowering the technical threshold, and improving the development efficiency of business processes.

[0069] In some optional implementations, the target function node includes: a language model configuration node; the step S1032, modifying the configuration item of the target function node based on the modified content, includes:

[0070] Based on the modified content, modify the model type configuration item and the prompt header configuration item in the target function node, wherein the model type configuration item is used to configure the type of the language model, and the prompt header configuration item is used to configure the prompt header of the language model.

[0071] In the embodiments of the present disclosure, Figure 4 The figure shows a schematic diagram of the configuration page of the language model configuration node displayed in the visual interface, wherein the "model" item is the above-mentioned model type configuration item, and the prompt uses the system identifier to configure whether to use the prompt header.

[0072] When the prompt uses the system flag to be turned on, the prompt header is enabled. The number of characters in the prompt header can be configured through the "MaxToken" item. The default value is usually 2048. The "prompt" item can be used to configure the specific prompt header content. The "Template placeholder" item is used to configure the replaceable content in the prompt header of the language model. Specifically, the replaceable content in the prompt header can be replaced by referencing the current system variables. For example, the replaceable content can be user information, the address of the queried database, etc.

[0073] In the disclosed embodiments, the type of language model and the prompt header of the language model can be configured by modifying the model type configuration item and the prompt header configuration item in the language model configuration node, thereby eliminating the need for front-end development of the language model configuration node, achieving zero-code or low-code business process orchestration, lowering the technical threshold, and improving the development efficiency of business processes.

[0074] In some optional implementations, the target function node includes: a prompt header generation node, which is used to generate a prompt header input into the language model; the step S1032, modifying the configuration items of the target function node based on the modified content, includes:

[0075] Step a1: determine a data set set for the prompt header based on the modified content, wherein the data set includes data for answering the query content.

[0076] Step a2, modify the corresponding configuration items in the prompt header generation node based on the data set.

[0077] In the disclosed embodiments, the query content is used for the process in which the user makes a request to the language model to find specific information. Specifically, the user can enter keywords or conditions, and the language model searches based on these inputs and returns relevant results. The data set is used to define the query scope corresponding to the query content, such as a database.

[0078] Here, if Figure 5 The diagram shows a configuration page of the prompt header generation node displayed in the visualization interface, wherein the prompt header generation node provides the Retrieval-Augmented Generation (RAG) capability, which can quickly and accurately find document content closely related to the user's question or topic in a dataset containing a large amount of document data. For example, when a user asks about "the latest application of artificial intelligence in the medical field", the RAG capability can filter out relevant content related to the application of artificial intelligence in the medical field from a large amount of medical literature, research reports and other documents.

[0079] Specifically, users can set a data set for the prompt header through the "Knowledge Group" item in the above configuration page, for example, specify the range of the recalled data set, such as the database address, etc. In addition, the corresponding functions in the prompt header generation node can be set through the "Recall Query" item, "Recall Quantity" item, "Recall Data Type" item, "Filter Label" item, "Recall Threshold" item, and "Recall Maximum Token" item and other configuration items.

[0080] In the disclosed embodiment, the data set corresponding to the prompt header can be set by modifying the content, and the corresponding configuration items in the prompt header generation node can be modified based on the data set, thereby eliminating the need for front-end development of the language model configuration node, achieving zero-code or low-code business process orchestration, lowering the technical threshold, and improving the development efficiency of business processes.

[0081] In some optional implementations, the target function node includes: a message push node, the message push node is used to push the output result of the language model, and the step S1032, modifying the configuration item of the target function node based on the modified content, includes:

[0082] Step b1, based on the modified content, determine the data type configured for the output result.

[0083] Step b2: determine the corresponding sub-configuration item based on the data type.

[0084] Step b3: Based on the reference relationship between data types, configure the association relationship between sub-configuration items.

[0085] In the disclosed embodiment, the data type may be the type of data output by the language model, such as text, picture, audio, video, etc. Here, a corresponding sub-configuration item may be generated for each data type, and a corresponding visual interface element may be generated for the sub-configuration item. Here, considering that when rendering the output result, there may be a reference and referenced relationship between the data of each data type, for example, a chart is referenced in the text, therefore, the association relationship between the sub-configuration items may be configured based on the reference relationship between the data types.

[0086] Specifically, the parent-child relationship of the sub-configuration items can be defined based on the reference relationship between the sub-configuration items. For example, if a chart is referenced in a text, the sub-configuration item corresponding to the text is the parent node of the sub-configuration item corresponding to the picture.

[0087] It should be understood that a well-arranged sub-configuration item can be used as a child node in the business process. In addition to core variables that can be directly passed between parent and child nodes, other parameters can also be transferred through configuration input and output. For example, the variables of the parent node can be passed as input parameters of the child node, and the output of the child node can be applied in the parent node through referral.

[0088] In addition, such as Figure 6 Shown is a schematic diagram of the configuration page of the language model extension node displayed in the visual interface, wherein the configuration page can be used to configure the plug-in. It should be understood that the use of functional plug-ins can enhance the functionality of the language model, such as enabling the language model to search for data online, etc., to meet some needs that require accurate or instant information, and make up for the shortcomings of the language model in real-time data access and interaction. Through custom plug-in functions, data exchange between workflows and business systems can be achieved, which helps to complete the orchestration and application construction of business processes more quickly, thereby improving the use efficiency and operation efficiency of the platform. Specifically, functional plug-ins can be added through the functional extension identifier in the configuration page to expand the functionality of the intents configuration item.

[0089] In the embodiments of the present disclosure, the data type configured for the output result can be modified and the corresponding sub-configuration items can be determined based on the data type, so that the association relationship between the sub-configuration items can be configured based on the reference relationship between the data types. This eliminates the need for front-end development of the message push node, thereby achieving zero-code or low-code business process orchestration, lowering the technical threshold, and improving the development efficiency of the business process.

[0090] In some optional implementations, the target function node includes: a query statement node, the query statement node is used to generate a corresponding query statement based on the input content of the language model, and the step S1032, modifying the configuration item of the target function node based on the modified content, includes:

[0091] Step c1, determining generation parameters of the query statement based on the modified content, wherein the generation parameters are used to indicate a parameter range when the query statement is generated based on the query content.

[0092] Step c2: modify the configuration item corresponding to the query statement node based on the generated parameters.

[0093] In the disclosed embodiment, the query statement may include a SQL (Structured Query Language) statement and a DSL (Domain-Specific Language) statement generation parameter for specifying a scope when generating the query language.

[0094] Specifically, taking SQL statements as an example, in actual applications, we often encounter situations where similar SQL statements need to be executed multiple times, but only certain conditions or parameters are different each time. By using custom parameters, the unchanged parts can be written as a common SQL statement template, and the changed parts can be passed in as parameters, thus avoiding the repetition of writing a large amount of similar code and improving the maintainability of the code.

[0095] In addition, users can dynamically specify different parameter values ​​for SQL statements at runtime according to different needs and inputs, thereby implementing queries under different conditions. For example, in a search function, users can choose different search keywords, time ranges, locations, etc. as query conditions according to their preferences. The system passes these conditions as parameters to the SQL statement and returns the corresponding query results.

[0096] Or, consider that different database management systems may have some subtle differences in SQL syntax and format. By using custom parameters, you can flexibly adjust the parameter value or format according to different database systems without modifying the SQL statement body, so that SQL statements can run normally in multiple database environments.

[0097] In addition, such as Figure 7 The following is a schematic diagram of the configuration page of the code editing node displayed in the visual interface, where the code editing node supports writing expressions or scripts to convert variables in the context or add new variables. This low-code approach enables business processes to handle some complex variables, and the variables output by the node can be directly referenced in subsequent nodes.

[0098] Specifically, you can Figure 7 In the "Input" item condition, you can reference the variable, and in the output processor, you can assign a value to the variable through the "Assignment Type" in the "Edit Rule" item, for example, the gtoovy script.

[0099] In the disclosed embodiments, the generation parameters of the query statement can be determined by modifying the content, and the configuration items corresponding to the query statement nodes can be modified based on the generation parameters, thereby eliminating the need for front-end development of the query statement nodes, achieving zero-code or low-code business process orchestration, lowering the technical threshold, and improving the development efficiency of business processes.

[0100] In some optional implementations, the above step S103, performing management operations on the business process, includes:

[0101] Step S11, obtaining historical version data, wherein the historical version data includes a historical version of a business process generated for a business scenario.

[0102] Step S12: Update historical version data based on the target business process.

[0103] In the disclosed embodiment, the rapid deployment and evaluation of business processes can be supported to facilitate business version upgrades and rollbacks, thereby improving the stability and maintainability of the system. Specifically, several historical versions of business processes, for example, 50, can be saved in the historical version data, and when the target business process evaluation result fails or a problem occurs during operation, the business process version can be rolled back based on the historical version data.

[0104] In addition, the present disclosure also provides comprehensive operation and maintenance capabilities, such as providing business process execution record viewing, exception troubleshooting, log viewing and variable tracking functions, so as to analyze the cause of business process errors and instantly perform business process version rollback and business process iteration. For example, the user's recent conversation with the language model can be saved, based on the detailed execution steps corresponding to the output results of each conversation, the input and output of each execution, and the variable tracking results of execution failure cases (such as output result mismatch).

[0105] Here, in order to better understand the business process management prevention in the present disclosure, a construction case of building a data query business process is also provided in this embodiment, and the case is as follows:

[0106] like Figure 8 Shown is a schematic diagram of the data query business process, wherein the target function nodes of the data query business process include two query statement nodes, a message push node, a code editing node and a language model configuration node.

[0107] Specifically, the Text2DSL node in the query statement node is used to configure the generation parameters of the query statement, and the data acquisition node is used to configure the data input to the language model. The message push node is used to configure the push of the output results of the language model. The code editing node is used to edit the variables referenced in the metadata of each function node. The language model configuration node is used to configure the parameters of the language model.

[0108] In the configured data query business process, users can enter query content to obtain output results that match the query content. For example, the query content entered by the user can be "XX's sales in the last 7 days", and the output results of the language model can include a line chart of XX's daily sales in the last 7 days, as well as analysis results for XX's sales in the last 7 days, such as "The following is an analysis of XX's sales data in the last 7 days: overall data summary (specific content is not shown in this disclosure), data trend (specific content is not shown in this disclosure), abnormal situation analysis (specific content is not shown in this disclosure)".

[0109] In summary, in the disclosed embodiments, first, a function node matching the business scenario can be obtained, wherein the function node is used to implement the business function based on a preset language model. Next, a target function node matching the preset business function can be determined in the function node. Then, based on the target function node, a target business process can be generated, and management operations can be performed on the target business process, so that the function node matching the business scenario can be directly called to select the target function node therein, so as to generate the target business process under the business scenario based on the target function node, which greatly reduces the coding and debugging required in the business process development process, reduces the requirements for R&D personnel, and thus reduces the business R&D cost and management difficulty.

[0110] In the present embodiment, a business process management device is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware of a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware is also possible and conceived.

[0111] This embodiment provides a business process management device, such as Fig. 9 As shown, including:

[0112] An acquisition module 901 is used to acquire a function node that matches a business scenario, wherein the function node is used to implement a business function based on a preset language model;

[0113] A determination module 902 is used to determine a target function node matching a preset business function among the function nodes;

[0114] The management module 903 is used to generate a target business process based on the target function node and perform management operations on the target business process.

[0115] In some optional implementations, the acquisition module 901 is further used to:

[0116] Acquire a first node for invoking a language model function, wherein the first node includes at least one of the following: a language model configuration node, a prompt header generation node, and a language model extension node, wherein the prompt header generation node is used to generate a prompt header input into the language model, and the language model extension node is used to extend the function of the language model;

[0117] Acquire a second node that matches the function of the first node, wherein the second node includes at least one of the following: a code editing node, a message push node, and a query statement node, the code editing node is used to edit variables referenced in metadata of each function node, the message push node is used to push output results of the language model, and the query statement node is used to generate a corresponding query statement based on input content of the language model;

[0118] A functional node is determined according to the first node and the second node.

[0119] In some optional implementations, the management module 903 is further configured to:

[0120] In response to a modification instruction for a configuration item, obtaining modification content;

[0121] The configuration items of the target function node are modified based on the modified content, and the target business process is obtained by performing orchestration based on the modified target function node.

[0122] In some optional implementations, the target function node includes: a language model configuration node; and a management module 903, further configured to:

[0123] Based on the modified content, modify the model type configuration item and the prompt header configuration item in the target function node, wherein the model type configuration item is used to configure the type of the language model, and the prompt header configuration item is used to configure the prompt header of the language model.

[0124] In some optional implementations, the target function node includes: a prompt header generation node, the prompt header generation node is used to generate a prompt header input into the language model; the management module 903 is also used to:

[0125] Based on the modified content, determining a data set set for the prompt header, wherein the data set includes data for answering the query content;

[0126] Modify the corresponding configuration items in the prompt header generation node based on the data set.

[0127] In some optional implementations, the target function node includes: a message push node, which is used to push the output result of the language model; and a management module 903, which is also used to:

[0128] Based on the modified content, determine the data type configured for the output result;

[0129] Determine the corresponding sub-configuration item based on the data type;

[0130] Based on the reference relationship between data types, configure the association relationship between sub-configuration items.

[0131] In some optional implementations, the target function node includes: a query statement node, the query statement node is used to generate a corresponding query statement based on the input content of the language model; the management module 903 is also used to:

[0132] Determine, based on the modified content, generation parameters of the query statement, wherein the generation parameters are used to indicate a parameter range when the query statement is generated based on the query content;

[0133] Modify the configuration items corresponding to the query statement node based on the generated parameters.

[0134] In some optional implementations, the management module 903 is further configured to:

[0135] Obtaining historical version data, wherein the historical version data includes a historical version of a business process generated for a business scenario;

[0136] Update historical version data based on the target business process.

[0137] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0138] The business process management device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0139] The present disclosure also provides a computer device having the above Fig. 9 The business process management device shown.

[0140] See also Fig.10 , Fig.10 is a schematic diagram of a computer device provided by an optional embodiment of the present disclosure, such as Fig.10As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Fig.10 A processor 10 is taken as an example.

[0141] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0142] The memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0143] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0144] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0145] The input device 30 can receive input digital or character information, and generate key signal input related to the user settings and function control of the computer device, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, an indicator bar, one or more mouse buttons, a trackball, a joystick, etc. The output device 40 may include a display device, an auxiliary lighting device (e.g., an LED) and a tactile feedback device (e.g., a vibration motor), etc. The above-mentioned display device includes but is not limited to a liquid crystal display, a light emitting diode, a display and a plasma display. In some optional embodiments, the display device can be a touch screen.

[0146] The computer device further comprises a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0147] The embodiments of the present disclosure also provide a computer-readable storage medium. The above-mentioned method according to the embodiments of the present disclosure can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium and downloaded through a network, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state drive, etc.; further, the storage medium can also include a combination of the above-mentioned types of memory. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0148] It is understandable that before using the technical solutions disclosed in the embodiments of the present disclosure, the types, scope of use, usage scenarios, etc. of the personal information involved in the present disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0149] For example, in response to receiving an active request from a user, a prompt message is sent to the user to clearly prompt the user that the operation requested to be performed will require obtaining and using the user's personal information. Thus, the user can autonomously choose whether to provide personal information to software or hardware such as an electronic device, application, server, or storage medium that performs the operation of the technical solution of the present disclosure according to the prompt message.

[0150] As an optional but non-limiting implementation, in response to receiving an active request from the user, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. In addition, the pop-up window may also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0151] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that meet the relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0152] A part of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the existence of the computer program instruction in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc., and accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium accessible to the computer.

[0153] Although the embodiments of the present disclosure are described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present disclosure, and such modifications and variations are all within the scope defined in the present application.

Claims

1. A business process management method, characterized in that: The method comprises: Acquire a function node matching the business scenario, wherein the function node is used to implement the business function based on a preset language model; Determining a target functional node matching a preset business function among the functional nodes; Based on the target function node, a target business process is generated, and management operations are performed on the target business process.

2. The method according to claim 1, characterized in that The obtaining of a function node matching the business scenario includes: Acquire a first node for calling the language model function, wherein the first node includes at least one of the following: a language model configuration node, a prompt header generation node, and a language model extension node, wherein the prompt header generation node is used to generate a prompt header input into the language model, and the language model extension node is used to extend the function of the language model; Acquire a second node that matches the function of the first node, wherein the second node includes at least one of the following: a code editing node, a message push node, and a query statement node, the code editing node is used to edit variables referenced in metadata of each function node, the message push node is used to push the output result of the language model, and the query statement node is used to generate a corresponding query statement based on the input content of the language model; The functional node is determined according to the first node and the second node.

3. The method according to claim 1, characterized in that The generating a target business process based on the target function node includes: In response to the modification instruction, obtaining modification content; The configuration items of the target function node are modified based on the modified content, and the target function node is orchestrated based on the modified configuration items to obtain a target business process.

4. The method according to claim 3, characterized in that The target function node includes: a language model configuration node; The modifying the configuration item of the target function node based on the modification content includes: Based on the modified content, the model type configuration item and the prompt header configuration item in the target function node are modified, wherein the model type configuration item is used to configure the type of the language model, and the prompt header configuration item is used to configure the prompt header of the language model.

5. The method according to claim 3, characterized in that: The target function node includes: a prompt header generation node, the prompt header generation node is used to generate a prompt header input into the language model; The modifying the configuration item of the target function node based on the modification content includes: Based on the modified content, determining a data set to be set for the prompt header, wherein the data set includes data for answering the query content; The corresponding configuration item in the prompt header generation node is modified based on the data set.

6. The method according to claim 3, characterized in that The target function node includes: a message push node, the message push node is used to push the output result of the language model; The modifying the configuration item of the target function node based on the modification content includes: Based on the modified content, determining a data type configured for the output result; Determine a corresponding sub-configuration item based on the data type; Based on the reference relationship between the data types, the association relationship between the sub-configuration items is configured.

7. The method according to claim 3, characterized in that The target function node includes: a query statement node, the query statement node is used to generate a corresponding query statement based on the input content of the language model; The modifying the configuration item of the target function node based on the modification content includes: Determining generation parameters of the query statement based on the modified content, wherein the generation parameters are used to indicate a parameter range when generating a query statement based on the query content; The configuration item corresponding to the query statement node is modified based on the generated parameter.

8. The method according to claim 1, characterized in that The management operation on the business process includes: Acquire historical version data, wherein the historical version data includes a historical version of a business process generated for the business scenario; Based on the target business process, the historical version data is updated.

9. A business process management device, characterized in that: The device comprises: An acquisition module, used to acquire a function node matching a business scenario, wherein the function node is used to implement a business function based on a preset language model; A determination module, used to determine a target functional node matching a preset business function among the functional nodes; The management module is used to generate a target business process based on the target function node and perform management operations on the target business process.

10. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the business process management method according to any one of claims 1 to 8 by executing the computer instructions.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the business process management method according to any one of claims 1 to 8.

12. A computer program product, characterized in that The method comprises computer instructions, wherein the computer instructions are used to enable a computer to execute the business process management method according to any one of claims 1 to 8.

Images