Operation guidance generation method and system, computer equipment and storage medium

Abstract

The invention provides an operation guidance generation method and system, computer equipment and a storage medium, and the method comprises the steps: receiving an examination and approval process template file through a rear-end processing module, and analyzing the examination and approval process template file to obtain an examination and approval process template analysis result; the back-end processing module obtains an operation database, and generates operation guidance of each approval step based on operation data in the operation database and the analysis result of the approval process template; and the front-end display module displays the operation guidance to a user. By adopting the method, the effectiveness, timeliness and accuracy of approval operation guidance are improved, and the approval experience of the user is improved.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to an operation guide generating method, system, computer equipment and storage medium. Background Art

[0002] In the existing technology, enterprises usually rely on paper documents or emails to manually track and manage the approval process, and then managers write operating instructions based on the approval process. However, the study found that the above process has the following defects: First, when manually tracking and managing the approval process, operational errors are prone to occur, resulting in low approval efficiency. Even if there are some forms of approval templates, they are often static and cannot be dynamically adjusted according to real-time operational data, which will cause the obtained operating instructions to lack timeliness and reduce their effectiveness. In addition, during the approval process, there is a lack of clear operating instructions, and users cannot promptly obtain information such as the approval method, resulting in unclear approval steps and low approval efficiency. Summary of the invention

[0003] In view of this, the purpose of the present invention is to provide an operation guide generation method, system, computer device and storage medium to improve the effectiveness, timeliness and accuracy of the approval operation guide and improve the user's approval experience.

[0004] In a first aspect, an embodiment of the present application provides an operation guide generation method, which is applied to an operation guide generation system, wherein the system includes a backend processing module and a frontend display module, and the method includes:

[0005] The back-end processing module receives the approval process template file, and parses the approval process template file to obtain the approval process template parsing result;

[0006] The backend processing module obtains an operation database, and generates an operation guide for each approval step based on the operation data in the operation database and the analysis result of the approval process template;

[0007] The front-end display module displays the operation instructions to the user.

[0008] Optionally, the parsing of the approval process template file to obtain an approval process template parsing result includes:

[0009] Parsing the format of the approval process template file to obtain a plurality of nodes and edges of the approval process template, wherein the nodes represent approval process steps, and the edges represent the flow logic between the approval process steps;

[0010] Perform field analysis on each node to obtain step information of each approval process step;

[0011] The approval process template parsing result is generated based on the step information of each approval process step and the flow logic between each approval process step.

[0012] Optionally, the generating of the operation guide for each approval step based on the operation data in the operation database and the parsing result of the approval process template includes:

[0013] Extracting features from the operation data and the analysis result of the approval process template to obtain operation data features and analysis result features;

[0014] Based on the operational data features, generating first operational information using a target NLP model;

[0015] Based on the analysis result features, generating second operation information using the target GNN model;

[0016] An operation guide for each approval step is generated based on the first operation information and the second operation information.

[0017] Optionally, the extracting features of the operation data and the parsing result of the approval process template to obtain operation data features and parsing result features respectively includes:

[0018] Performing text data cleaning on the operation data to obtain preferred operation data;

[0019] Extracting the features of the preferred operation data and performing feature encoding to obtain the operation data features;

[0020] Performing structured data cleaning on the parsing result of the approval process template to obtain preferred template data;

[0021] The features of the preferred template data are extracted and feature encoded to obtain the features of the parsing result.

[0022] Optionally, the method further comprises:

[0023] The backend processing module obtains the historical approval process template file and the historical operation database;

[0024] The backend processing module performs model training on the initial GNN model based on the historical approval process template file to obtain the target GNN model;

[0025] The backend processing module performs model training on the initial NLP model based on the historical operation data in the historical operation database to obtain the target NLP model.

[0026] Optionally, the operational data characteristics include production authority characteristics and database characteristics.

[0027] Optionally, the parsing result features include data node features, form field features, approval link features, branch logic features and permission features.

[0028] In a second aspect, an embodiment of the present application provides an operation guide generation system, the system comprising a backend processing module and a frontend display module;

[0029] The back-end processing module is used to receive the approval process template file, and parse the approval process template file to obtain the approval process template parsing result;

[0030] The backend processing module is used to obtain an operation database, and generate operation instructions for each approval step based on the operation data in the operation database and the analysis result of the approval process template;

[0031] The front-end display module is used to display the operation instructions to the user.

[0032] Optionally, the parsing of the approval process template file to obtain an approval process template parsing result includes:

[0033] Parsing the format of the approval process template file to obtain a plurality of nodes and edges of the approval process template, wherein the nodes represent approval process steps, and the edges represent the flow logic between the approval process steps;

[0034] Perform field analysis on each node to obtain step information of each approval process step;

[0035] The approval process template parsing result is generated based on the step information of each approval process step and the flow logic between each approval process step.

[0036] Optionally, the generating of the operation guide for each approval step based on the operation data in the operation database and the parsing result of the approval process template includes:

[0037] Extracting features from the operation data and the analysis result of the approval process template to obtain operation data features and analysis result features;

[0038] Based on the operational data features, generating first operational information using a target NLP model;

[0039] Based on the analysis result features, generating second operation information using the target GNN model;

[0040] An operation guide for each approval step is generated based on the first operation information and the second operation information.

[0041] Optionally, the extracting features of the operation data and the parsing result of the approval process template to obtain operation data features and parsing result features respectively includes:

[0042] Performing text data cleaning on the operation data to obtain preferred operation data;

[0043] Extracting the features of the preferred operation data and performing feature encoding to obtain the operation data features;

[0044] Performing structured data cleaning on the parsing result of the approval process template to obtain preferred template data;

[0045] The features of the preferred template data are extracted and feature encoded to obtain the features of the parsing result.

[0046] Optionally, the backend processing module is used to obtain historical approval process template files and historical operation databases;

[0047] The backend processing module is used to perform model training on the initial GNN model based on the historical approval process template file to obtain the target GNN model;

[0048] The backend processing module is used to perform model training on the initial NLP model based on the historical operation data in the historical operation database to obtain the target NLP model.

[0049] Optionally, the operational data characteristics include production authority characteristics and database characteristics.

[0050] Optionally, the parsing result features include data node features, form field features, approval link features, branch logic features and permission features.

[0051] In a third aspect, an embodiment of the present application provides a computer device, comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the computer device is running, the processor and the memory communicate through the bus, and when the machine-readable instructions are executed by the processor, the steps of the operation guide generation method described in any optional implementation manner of the first aspect are performed.

[0052] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the operation guide generating method described in any optional implementation manner in the above-mentioned first aspect are executed.

[0053] The technical solution provided by this application includes but is not limited to the following beneficial effects:

[0054] This application parses the approval process template file through the back-end processing module, which can ensure that the definition and execution of the approval process follow a unified template and standard, reducing process differences and errors caused by human factors; and the generated approval step operation guide can guide users to operate according to the established process, improving the efficiency and accuracy of the approval process. The back-end processing module can obtain real-time operation data in the operation database and generate operation guides for the approval steps based on these data. This means that the approval process can dynamically adapt to changes in corporate operations, such as increases and decreases in business volume, adjustments to approval authority, etc., thereby maintaining the effectiveness and flexibility of the approval process. In addition, the front-end display module clearly displays the operation guide to the user, allowing the user to intuitively understand the various steps and required operations of the approval process, reducing the user's learning cost. The friendly user interface and intuitive operation guide can improve user satisfaction and participation, thereby promoting the smooth progress of the approval process.

[0055] To sum up, this application realizes the standardization, dynamism, user-friendliness and transparency of the approval process through the collaborative work of the back-end processing module and the front-end display module, improves the effectiveness, timeliness and accuracy of the approval operation guidelines, and improves the user's approval experience.

[0056] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0058] Figure 1 A flow chart of a method for generating vehicle operation instructions provided by the first embodiment of the present invention is shown;

[0059] Figure 2 A flow chart of a template file parsing method provided by the first embodiment of the present invention is shown;

[0060] Figure 3 A flowchart of a specific operation guide generating method provided by the first embodiment of the present invention is shown;

[0061] Figure 4 A flow chart of a feature extraction method provided by the first embodiment of the present invention is shown;

[0062] Figure 5A flow chart of a model training method provided in Embodiment 1 of the present invention is shown;

[0063] Figure 6 A schematic diagram of a model training process provided by Embodiment 1 of the present invention is shown;

[0064] Figure 7 A flowchart of an operation guide display method provided by Embodiment 1 of the present invention is shown;

[0065] Figure 8 A schematic diagram showing the structure of an operation guide generating system provided by a second embodiment of the present invention is shown;

[0066] Fig. 9 A schematic diagram of the structure of a computer device provided in Embodiment 3 of the present invention is shown. DETAILED DESCRIPTION

[0067] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. The components of the embodiments of the present invention generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present invention.

[0068] Embodiment 1

[0069] To facilitate understanding of this application, Figure 1 The flowchart of an operation guide generating method provided in the first embodiment of the present invention is shown to describe the contents of the first embodiment of the present application in detail.

[0070] See also Figure 1 As shown, Figure 1 A flowchart of a method for generating vehicle operation instructions provided by a first embodiment of the present invention is shown, wherein the method is applied to an operation instruction generating system, the system includes a back-end processing module and a front-end display module, and the method includes steps S101 to S103:

[0071] S101: The backend processing module receives an approval process template file, and parses the approval process template file to obtain an approval process template parsing result.

[0072] Specifically, the backend processing module is responsible for receiving and parsing the approval process template JSON file, which defines the complete approval process including field permissions, approval steps, conditional branches, etc.

[0073] S102: The backend processing module obtains an operation database, and generates an operation guide for each approval step based on the operation data in the operation database and the parsing result of the approval process template.

[0074] Specifically, the parsed data is fed into the AI ​​big model for further processing, and the operational data in the operational database is introduced at the same time, and the operational data in the operational database is fed into the AI ​​big model for further processing. Combined with the processing results obtained above, the operation guidelines for each approval step are obtained. These guidelines include but are not limited to field filling instructions, permission prompts, personnel information for subsequent approval links, and process branch predictions based on current conditions.

[0075] The AI ​​big model uses natural language processing (NLP) and machine learning technologies to understand the structure and semantics of the process template through a pre-trained language model. For each approval step, the model can generate detailed and precise operational instructions.

[0076] S103: The front-end display module displays the operation instructions to the user.

[0077] Specifically, the front-end display module is responsible for presenting the operation instructions generated by the AI ​​large model to users in an intuitive and friendly manner, so that users can understand the entire approval process and its details at a glance, thereby completing the approval task efficiently.

[0078] In an alternative embodiment, see Figure 2 As shown, Figure 2 A flow chart of a template file parsing method provided in the first embodiment of the present invention is shown, wherein the parsing of the approval process template file to obtain the approval process template parsing result includes steps S201 to S203:

[0079] S201: parse the format of the approval process template file to obtain a plurality of nodes and edges of the approval process template, wherein the nodes represent approval process steps, and the edges represent the flow logic between the approval process steps.

[0080] Specifically, parse the approval process template file, which is a JSON format process template, and identify the various steps, fields, permissions, and branch conditions in the process.

[0081] The process template contains the following basic elements: (1) Process name: such as operation and maintenance changes; (2) Process description: including the previous version information and serial number, as well as a brief description of the process; (3) Creator: the identifier is the administrator number who created the process; (4) Version number: for example, version 196; (5) Node: contains multiple nodes, each node contains a node type (such as start, user task, exclusive gateway, etc.) and specific attributes (such as label, type, allocation strategy, etc.); (6) Edge: defines the flow logic between nodes, including conditional judgment and flow direction.

[0082] The above JSON structure data is parsed to obtain the various components of the process template, mainly including the nodes and edges in the basic elements of the process template.

[0083] S202: parse the fields of each node to obtain step information of each approval process step.

[0084] Specifically, first identify the node type: Each node in the process template may represent different process steps, such as start task, user task, exclusive gateway, convergence gateway, and end task. It is necessary to identify the type of each node and execute different parsing strategies based on the type.

[0085] Then extract the permission information: For the user task node, you need to check the permission assignment (assignee) field in the data object, which contains the role-based assignment or the ID of a specific user to determine which users or roles have permission to perform the task.

[0086] Next, the field filling instructions are as follows: For the user task node, the form field in the data object contains the form fields related to the step. These fields need to be parsed to extract the field ID, label, default value, required, field type, and other information.

[0087] Then analyze the process branches: By analyzing the edges array, you can determine the branches and decision points in the process. Each edge object contains a source and a target, indicating the direction of the process, and a decision point field, indicating the branch condition.

[0088] Finally, process the conditional logic: For process branches that contain conditions, the conditional expressions need to be parsed and associated with the corresponding process steps.

[0089] S203: Generate the approval process template parsing result based on the step information of each approval process step and the flow logic between each approval process step.

[0090] Specifically, based on the step information (corresponding to points) and conditional judgments and flow directions (corresponding to edges) of each approval process step obtained above, a structured representation is output, which contains detailed information on each step of the process, authority requirements, field filling instructions, and process branches as the parsing result of the approval process template.

[0091] In an alternative embodiment, see Figure 3 As shown, Figure 3 A flowchart of a specific method for generating operation instructions provided in the first embodiment of the present invention is shown, wherein the operation instructions for each approval step are generated based on the operation data in the operation database and the parsing result of the approval process template, including steps S301 to S304:

[0092] S301: Extracting features from the operation data and the analysis result of the approval process template respectively to obtain operation data features and analysis result features.

[0093] Specifically, feature extraction is performed on the parsing results of the approval process template to obtain the features of the parsing results, including: (1) Node feature extraction: extracting features from each process node, such as node type (start, end, decision point, etc.), node connection (which node it points to); (2) Form field feature extraction: extracting features from form fields, such as field type (text box, drop-down list, check box, etc.), field validation rules (required, format requirements, etc.), field dependencies (how the value of a field affects other fields); (3) Approval link feature extraction: extracting features of the approval link, such as the approver role, approval conditions, and approval actions (approval, rejection, rollback, etc.); (4) Branch logic feature extraction: extracting branch logic features in the process, such as branch conditions, branch results, and branch target nodes; (5) Permission feature extraction: extracting features related to permissions, such as user approval roles and user roles in technology products.

[0094] Feature extraction of operational data is performed to obtain operational data features, including: (1) Host permission extraction: extracting features related to production host permissions, such as access and control capabilities of hosts in the production environment; (2) Database definition permissions: extracting features related to database definitions, such as pooled deployment databases, OB databases, Gaussian databases, and independent databases.

[0095] S302: Based on the operation data characteristics, generate first operation information using a target NLP model.

[0096] Specifically, the operational data features are input into the trained target NLP model to obtain the first operation information. The first operation information includes host permissions, pooled deployment database, OB database, Gaussian database, and independent database.

[0097] S303: Based on the analysis result features, generate second operation information using the target GNN model.

[0098] Specifically, the parsing result features are input into the trained target GNN model to obtain the second operation information. The second operation information includes node type (start, end, decision point, etc.), node connection (which node it points to), field type (text box, drop-down list, check box, etc.), field validation rules (required, format requirements, etc.), field dependencies (how the value of a field affects other fields), approver role, approval conditions, approval actions (approval, rejection, rollback, etc.), branch conditions, branch results, branch target nodes, user approval roles, user roles in technology products, etc.

[0099] S304: Generate operation instructions for each approval step based on the first operation information and the second operation information.

[0100] Specifically, the first operation information and the second operation information are integrated to obtain the operation guide of each approval step. The integration is to combine the information and merge the content.

[0101] In an alternative embodiment, see Figure 4 As shown, Figure 4 A flow chart of a feature extraction method provided in the first embodiment of the present invention is shown, wherein the feature extraction of the operation data and the analysis result of the approval process template is performed to obtain the operation data feature and the analysis result feature respectively, including steps S401 to S404:

[0102] S401: Perform text data cleaning on the operation data to obtain preferred operation data.

[0103] Specifically, the text data in the operation knowledge base is preprocessed, including word segmentation, removal of discontinued knowledge, etc.

[0104] S402: extracting the features of the preferred operation data and performing feature encoding to obtain the operation data features.

[0105] Specifically, the categorical features of the preferred operation data are converted into numerical features, and then the numerical features are normalized to be on the same scale.

[0106] S403: Perform structured data cleaning on the parsing result of the approval process template to obtain preferred template data.

[0107] Specifically, the process template parsing results are cleaned, including removing invalid data, filling missing values, and performing data type conversion.

[0108] S404: extracting the features of the preferred template data and performing feature encoding to obtain the analysis result features.

[0109] Specifically, the classification features of the preferred template data are converted into numerical features, and then the numerical features are normalized to be on the same scale.

[0110] In an alternative embodiment, see Figure 5 As shown, Figure 5 A flow chart of a model training method provided in the first embodiment of the present invention is shown, wherein the method further comprises steps S501 to S503:

[0111] S501: The backend processing module obtains a historical approval process template file and a historical operation database.

[0112] Specifically, the backend processing module obtains the historical approval process template file and the historical operation database for constructing the model training data set.

[0113] S502: The backend processing module performs model training on the initial GNN model based on the historical approval process template file to obtain the target GNN model.

[0114] Specifically, the backend processing module parses, preprocesses, extracts features, and encodes the historical approval process template file to construct a first model training data set, and uses the first model training data set to train the initial GNN model.

[0115] S503: The backend processing module performs model training on the initial NLP model based on the historical operation data in the historical operation database to obtain the target NLP model.

[0116] Specifically, the backend processing module preprocesses, extracts features, and encodes the historical operation data in the historical operation database to construct a second model training data set, and uses the second model training data set to train the initial NLP model.

[0117] See also Figure 6 As shown, Figure 6A schematic diagram of a model training process provided by the first embodiment of the present invention is shown, wherein firstly, the text data in the operation database and the structured data in the process template parsing result are obtained; the structured data includes the node ID, node type, field type, field authority, field verification rule, approver and approval action; the text data includes the upstream node, downstream node, branch judgment condition of each node and the questions and answers in the operation database. The GNN model is trained with the structured data, and the NLP model is trained with the text data, and finally a large model based on the GNN model and the NLP model that can output the node ID and operation instructions is obtained.

[0118] In an optional embodiment, the operational data characteristics include production authority characteristics and database characteristics.

[0119] In an optional implementation scheme, the parsing result features include data node features, form field features, approval link features, branch logic features and authority features.

[0120] The operation guide generation method provided in this application can also display the approval node ID and operation guide of each approval step to the user in a unified manner through the front-end display module. Figure 7 As shown, Figure 7 A flowchart of an operation guide display method provided by the first embodiment of the present invention is shown, wherein first, the back-end processing module obtains the approval process template in JSON format, parses it through the template parsing module to obtain the process information, formats it and inputs it into the AI ​​big model (including the GNN model and the NLP model) with the data in the operation database to generate the approval node ID and operation guide. Then the front-end display module generates a page according to the operation guide, and finally forms an approval page for display to the user. In the above display process, based on the understanding of the AI ​​model, detailed and accurate operation guides for each link are generated in the approval interface according to the approval link ID, including field permission reminders and precautions. The user can view the operation guide of this link by moving the mouse to the preset position in the current approval link, and the model is called once for each approval process. This application can parse the imported JSON format process template and generate corresponding user operation guides at the front end in combination with the AI ​​big model. Through the AI ​​big model technology, the system can better understand the structure of the process template, generate detailed and accurate operation guides for each step, and help users complete tasks efficiently. Through the automatically generated operation guides, users can quickly understand the approval process, reduce operation errors, and improve operation efficiency. Detailed operation guides improve user satisfaction and transparency of the approval process, and enhance user experience. The system can automatically adapt to various complex approval processes, including authority management and branch processes, and can be updated in a timely manner and is easy to maintain and update.

[0121] Embodiment 2

[0122] See also Figure 8 As shown, Figure 8 A schematic diagram of the structure of an operation guide generating system provided by the second embodiment of the present invention is shown, wherein the system includes a back-end processing module 801 and a front-end display module 802;

[0123] The back-end processing module is used to receive the approval process template file, and parse the approval process template file to obtain the approval process template parsing result;

[0124] The backend processing module is used to obtain an operation database, and generate operation instructions for each approval step based on the operation data in the operation database and the analysis result of the approval process template;

[0125] The front-end display module is used to display the operation instructions to the user.

[0126] In an optional implementation scheme, the parsing of the approval process template file to obtain the approval process template parsing result includes:

[0127] Parsing the format of the approval process template file to obtain a plurality of nodes and edges of the approval process template, wherein the nodes represent approval process steps, and the edges represent the flow logic between the approval process steps;

[0128] Perform field analysis on each node to obtain step information of each approval process step;

[0129] The approval process template parsing result is generated based on the step information of each approval process step and the flow logic between each approval process step.

[0130] In an optional implementation scheme, the generating of the operation guide for each approval step based on the operation data in the operation database and the parsing result of the approval process template includes:

[0131] Extracting features from the operation data and the analysis result of the approval process template to obtain operation data features and analysis result features;

[0132] Based on the operational data features, generating first operational information using a target NLP model;

[0133] Based on the analysis result features, generating second operation information using the target GNN model;

[0134] An operation guide for each approval step is generated based on the first operation information and the second operation information.

[0135] In an optional implementation scheme, the extracting features of the operation data and the parsing result of the approval process template to obtain operation data features and parsing result features respectively includes:

[0136] Performing text data cleaning on the operation data to obtain preferred operation data;

[0137] Extracting the features of the preferred operation data and performing feature encoding to obtain the operation data features;

[0138] Performing structured data cleaning on the parsing result of the approval process template to obtain preferred template data;

[0139] The features of the preferred template data are extracted and feature encoded to obtain the features of the parsing result.

[0140] In an optional implementation scheme, the backend processing module is used to obtain a historical approval process template file and a historical operation database;

[0141] The backend processing module is used to perform model training on the initial GNN model based on the historical approval process template file to obtain the target GNN model;

[0142] The backend processing module is used to perform model training on the initial NLP model based on the historical operation data in the historical operation database to obtain the target NLP model.

[0143] In an optional embodiment, the operational data characteristics include production authority characteristics and database characteristics.

[0144] In an optional implementation scheme, the parsing result features include data node features, form field features, approval link features, branch logic features and authority features.

[0145] Embodiment 3

[0146] Based on the same application concept, see Fig. 9 As shown, Fig. 9 FIG. 4 shows a schematic diagram of the structure of a computer device provided by Embodiment 3 of the present invention, wherein: Fig. 9 As shown, a computer device 900 provided in Embodiment 3 of the present application includes:

[0147] A processor 901, a memory 902 and a bus 903, wherein the memory 902 stores machine-readable instructions executable by the processor 901. When the computer device 900 is running, the processor 901 communicates with the memory 902 via the bus 903. When the processor 901 is running, the machine-readable instructions execute the steps of the operation guide generation method shown in the above-mentioned embodiment 1.

[0148] Embodiment 4

[0149] Based on the same application concept, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the operation guide generation method described in any one of the above embodiments are executed.

[0150] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system and device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0151] The computer program product for generating operation instructions provided in the embodiments of the present invention includes a computer-readable storage medium storing program code. The instructions included in the program code can be used to execute the methods described in the previous method embodiments. The specific implementation can be found in the method embodiments and will not be repeated here.

[0152] The operation guide generation system provided in the embodiment of the present invention can be specific hardware on the device or software or firmware installed on the device. The system provided in the embodiment of the present invention has the same implementation principle and technical effects as the aforementioned method embodiment. For the sake of brief description, for matters not mentioned in the system embodiment, reference can be made to the corresponding contents in the aforementioned method embodiment. Technical personnel in the relevant field can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, devices and units described above can all refer to the corresponding processes in the aforementioned method embodiment, and will not be repeated here.

[0153] In the embodiments provided by the present invention, it should be understood that the disclosed systems and methods can be implemented in other ways. The system embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some communication interface, device or unit, which can be electrical, mechanical or other forms.

[0154] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0155] In addition, each functional unit in the embodiment provided by the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0156] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0157] It should be noted that similar numbers and letters represent similar items in the following figures. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. In addition, the terms "first", "second", "third", etc. are only used to distinguish the description and are not to be understood as indicating or implying relative importance.

[0158] Finally, it should be noted that the above-described embodiments are only specific implementations of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The protection scope of the present invention is not limited thereto. Although the present invention is described in detail with reference to the above-described embodiments, those skilled in the art should understand that any person skilled in the art can still modify the technical solutions described in the above-described embodiments within the technical scope disclosed by the present invention, or can easily think of changes, or perform equivalent replacements on some of the technical features thereof; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention. They should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A method for generating an operation guide, characterized in that: Applied to an operation guide generation system, the system includes a back-end processing module and a front-end display module, and the method includes: The back-end processing module receives the approval process template file, and parses the approval process template file to obtain the approval process template parsing result; The backend processing module obtains an operation database, and generates an operation guide for each approval step based on the operation data in the operation database and the analysis result of the approval process template; The front-end display module displays the operation instructions to the user.

2. The method according to claim 1, characterized in that The parsing of the approval process template file to obtain the approval process template parsing result includes: Parsing the format of the approval process template file to obtain a plurality of nodes and edges of the approval process template, wherein the nodes represent approval process steps, and the edges represent the flow logic between the approval process steps; Perform field analysis on each node to obtain step information of each approval process step; The approval process template parsing result is generated based on the step information of each approval process step and the flow logic between each approval process step.

3. The method according to claim 1, characterized in that The generating of the operation guide for each approval step based on the operation data in the operation database and the parsing result of the approval process template includes: Extracting features from the operation data and the analysis result of the approval process template to obtain operation data features and analysis result features; Based on the operational data features, generating first operational information using a target NLP model; Based on the analysis result features, generating second operation information using the target GNN model; An operation guide for each approval step is generated based on the first operation information and the second operation information.

4. The method according to claim 3, characterized in that The extracting features of the operation data and the parsing result of the approval process template to obtain operation data features and parsing result features respectively includes: Performing text data cleaning on the operation data to obtain preferred operation data; Extracting the features of the preferred operation data and performing feature encoding to obtain the operation data features; Performing structured data cleaning on the parsing result of the approval process template to obtain preferred template data; The features of the preferred template data are extracted and feature encoded to obtain the features of the parsing result.

5. The method according to claim 3, characterized in that: The method further comprises: The backend processing module obtains the historical approval process template file and the historical operation database; The backend processing module performs model training on the initial GNN model based on the historical approval process template file to obtain the target GNN model; The backend processing module performs model training on the initial NLP model based on the historical operation data in the historical operation database to obtain the target NLP model.

6. The method according to claim 3, characterized in that The operational data characteristics include production authority characteristics and database characteristics.

7. The method according to claim 3, characterized in that The analysis result features include data node features, form field features, approval link features, branch logic features and permission features.

8. An operation guide generation system, characterized in that: The system includes a back-end processing module and a front-end display module; The back-end processing module is used to receive the approval process template file, and parse the approval process template file to obtain the approval process template parsing result; The backend processing module is used to obtain an operation database, and generate operation instructions for each approval step based on the operation data in the operation database and the analysis result of the approval process template; The front-end display module is used to display the operation instructions to the user.

9. A computer device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the computer device is running, the processor and the memory communicate via the bus, and when the machine-readable instructions are executed by the processor, the steps of the operation guide generation method as described in any one of claims 1 to 7 are performed.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the operation guide generating method as described in any one of claims 1 to 7 are executed.

Images