CN111815273A - Configuration method of document approval process, storage medium and electronic equipment - Google Patents
Configuration method of document approval process, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN111815273A CN111815273A CN202010635614.2A CN202010635614A CN111815273A CN 111815273 A CN111815273 A CN 111815273A CN 202010635614 A CN202010635614 A CN 202010635614A CN 111815273 A CN111815273 A CN 111815273A
- Authority
- CN
- China
- Prior art keywords
- algorithm
- document
- user
- solution
- approval process
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 106
- 230000008569 process Effects 0.000 title claims abstract description 76
- 238000012549 training Methods 0.000 claims abstract description 27
- 238000012216 screening Methods 0.000 claims abstract description 9
- 238000005457 optimization Methods 0.000 claims abstract description 4
- 230000006399 behavior Effects 0.000 claims description 26
- 230000002159 abnormal effect Effects 0.000 claims description 20
- 238000012545 processing Methods 0.000 claims description 9
- 238000012795 verification Methods 0.000 claims description 7
- 206010000117 Abnormal behaviour Diseases 0.000 claims description 6
- 230000005856 abnormality Effects 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 6
- 230000008859 change Effects 0.000 abstract description 6
- 238000013473 artificial intelligence Methods 0.000 description 15
- 238000012423 maintenance Methods 0.000 description 5
- 238000013507 mapping Methods 0.000 description 5
- 230000008901 benefit Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/103—Workflow collaboration or project management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/166—Editing, e.g. inserting or deleting
- G06F40/186—Templates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/12—Accounting
- G06Q40/125—Finance or payroll
Abstract
The invention discloses a configuration method, a storage medium and electronic equipment of a document approval process.A modeling operation is carried out in advance, data information related to a document process is briefly screened and pushed to a foreground through a bottom algorithm model, the foreground draws a related process model according to the pushed information, and the selected process model has higher degree of engagement and is subjected to a change operation; along with the increment of the process configuration process training, the AI engine records the behavior habit and the configuration dimension of the user, and along with the increase of the operation times, the optimization of the AI engine on the recommended screening can be continuously increased until the operation times are completely equivalent to the ordinary service configuration of the user, so that the related process data can be pushed more accurately, and the change is less. In addition, when a user wants to optimize the training model, the algorithm packet is only replaced in the algorithm slot, and the training mode is changed and very flexible.
Description
Technical Field
The invention relates to the technical field of Artificial Intelligence (AI), in particular to a configuration method, a storage medium and electronic equipment for a document approval process.
Background
In the current mainstream document flow configuration operation and maintenance work, most of operations are that financial operation and maintenance personnel draw each node of a node flow first and allocate authority to each node, so as to set the approval flow of each post.
When the process is a complex process, the link of approval is very long, the drawing difficulty is high, the distribution difficulty of the personnel authority is high, the error probability is high, in the process approval process, if the information error of a certain link needs to be solved by the analysis error of the service personnel, the new job employees using the process are not friendly, and in conclusion, the longer the process is, the higher the working intensity is, the higher the cost is, and the error probability is continuously increased. In the case of existing problems, the process can only be optimized by the model.
The Chinese patent application with publication number CN107133781A discloses a configurable and expandable document flow management method and device, which is to construct a mapping relation between document parameters and a reference flow; generating a corresponding bill flow according to the mapping relation; and when receiving a modification trigger of the mapping relation, modifying the bill flow corresponding to the mapping relation. This has the advantage that document configuration errors can be quickly modified in the mapping.
Chinese patent application publication No. CN108629017A discloses a method for implementing an interpretive selectively configurable and operational document flow, which adds dynamic configuration to the document flow of an ERP system, dynamically configures the document flow into configured character strings, and after the configured character strings are configured and activated. And the flexible configuration of the flow is increased by setting each flow relation in the flow through the configuration file.
However, the above two patent technologies only simplify some steps due to the change in operation, and cannot fundamentally reduce the complexity of operation and maintenance implementing personnel in process configuration, or require personnel to draw the process, set field information of each document in the process, and give rights.
Disclosure of Invention
The invention aims to provide a bill flow configuration method, which aims to simplify the configuration of the flow of financial bills and improve the accuracy of the flow configuration. The invention is realized by the following technical scheme:
a configuration method of a document approval process is characterized by comprising the following steps:
modeling flow templates in advance according to the approval flow of the financial document, and configuring a plurality of modeled flow templates in a fixed model data table;
when the approval process of the financial document is configured specifically, an AI engine screens part of the process template from the fixed model data table through a screening algorithm and pushes the process template to a user for the first time;
the user selects one of the flow templates to draw an approval flow, the flow template is edited, the AI engine stores the operation behaviors edited by the user and performs modeling learning again according to the operation behaviors of the user;
and when the approval process of the financial document is configured next time, the AI engine pushes the process template to the user according to the screening algorithm after modeling and learning again.
As a further technical solution, the method for configuring the document approval process further includes a step of performing algorithm optimization on the training model of the AI engine, specifically: and a pluggable algorithm slot is arranged in the bottom algorithm of the training model, and a training algorithm packet is imported or deleted in a mode of plugging in and out the algorithm slot.
As a specific technical solution, the state of the training algorithm package includes: a sharing algorithm, a priority training algorithm, and a conditional algorithm.
As a specific technical scheme, when the approval process of the financial document is configured next time, firstly, data is obtained through a model bottom layer, whether a newly-introduced training algorithm packet exists is judged through a custom algorithm layer, if yes, learning statistical processing is carried out, and after the processing is finished, the obtained data passes through a simulated user behavior layer which records the operation behavior of a user for changing the document process, and the simulated user behavior layer is the layer; the more operation behavior data that is collected, the more forward the flow template is recommended to the user.
As a further technical solution, the configuration method of the document approval process further includes an automated processing step of checking an abnormal situation, specifically: when the examination and approval process of the financial document is matched and an abnormal situation occurs during verification, recording a solution executed by an operator according to an actual abnormal problem in a user behavior abnormal solution layer; and when similar abnormal problems occur again, calling the information of the corresponding solution in the user behavior abnormal solution layer to solve the similar abnormal problems.
As a specific technical solution, there are various ways for the operator to execute a solution according to an actual abnormal problem, and when similar abnormality occurs again, and information in the user behavior abnormality solution layer is called, a plurality of solution options are recommended for the operator to select.
As a specific technical solution, when a solution in the user behavior anomaly solution layer is called to solve the similar anomaly problem, the steps of the solution are firstly analyzed, and then the steps are executed step by an AI engine in a step-by-step question-and-answer manner.
As a specific technical solution, when a solution in the user behavior anomaly solution layer is called to solve the similar anomaly problem, the steps of the solution are firstly analyzed, then a complete intelligent mode is selected, and the method is realized by automatically executing the whole steps through an AI engine.
The invention also provides a storage medium, wherein the storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the configuration method of the document approval process.
The invention also provides electronic equipment which comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor realizes the configuration method of the document approval process when executing the computer program.
The invention has the beneficial effects that: (1) the configuration problem of the flow of the financial document is simplified; (2) automatically and artificially intelligently solving the abnormal problem found in the bill flow verification; (3) the development process of the algorithm layer is simplified, an algorithm engineer only needs to concentrate on the training problem of the algorithm without paying attention to other coding logic problems, and the efficiency is greatly improved. (4) The operation and maintenance cost of enterprises is saved, and the implementation threshold is reduced.
Drawings
Fig. 1 is a main flow chart of a configuration method of a document approval process according to an embodiment of the present invention.
Detailed Description
The method of the present invention will be described in further detail with reference to the accompanying drawings.
Referring to fig. 1, a configuration method of a document approval process provided in this embodiment mainly includes the following steps:
(1) based on the combination of an artificial intelligent neural network engine frame and financial document big data, modeling a flow template in advance aiming at the approval process of the financial document, and configuring a plurality of flow templates after modeling in a fixed model data table;
(2) when a user clicks the intelligent document generation on a foreground interface, namely the approval process of the financial document is specifically configured, an AI engine screens part of the process template from the fixed model data table through a screening algorithm and pushes the process template to the user for the first time;
(3) a user selects one of the flow templates to draw an approval flow, edits the flow template, and changes the nodes which do not conform to the flow; at the moment, the AI engine stores the operation behaviors edited and processed by the user and performs modeling learning again according to the operation behaviors of the user;
(4) and when the approval process of the financial document is configured next time, the AI engine pushes the process template to the user according to the screening algorithm after modeling and learning again. Specifically, when the approval process of the financial document is configured next time, data is obtained through a model bottom layer, whether a newly-introduced training algorithm package exists is judged through a custom algorithm layer, if yes, learning statistical processing is carried out, the obtained data passes through a user behavior simulation layer after processing is finished, the operation behavior of a user for changing the document process is recorded in the user behavior simulation layer, and the more operation behavior data are collected, the more the process template recommended to the user is.
In the conventional technology, when the algorithm of the AI engine is changed, the algorithm generally needs to be adjusted in a training model, the change is large, and the maintenance cost is high. In order to solve the problem, in the application, a pluggable algorithm is introduced into a training algorithm at the bottom layer, and a pluggable algorithm slot is used, so that the algorithm can be conveniently introduced by introducing a required training algorithm package, whether the algorithm package is introduced or not can be judged in a self-defined algorithm layer, and if the algorithm package is found, the next training can be carried out according to a plurality of states of the algorithm package. The algorithm packet state has the following states: shared algorithms (i.e., all training passes through the algorithm package), priority training algorithms (which achieve training priority by assigning sequence numbers), conditional algorithms (which are conditionally trained based on given logic conditions).
Furthermore, after the configuration of the document approval process is completed, verification is required before approval, abnormal problems that document information inspection is not passed, process post setting is not correct, authority is not assigned and the like often occur during verification, and business personnel are required to analyze and solve the problems according to actual problems in the process of the process. Therefore, the method further comprises an automatic processing step of checking the abnormal situation, specifically comprising the following steps: when the examination and approval process of the financial document is matched and an abnormal situation occurs during verification, recording a solution executed by an operator according to an actual abnormal problem in a user behavior abnormal solution layer, and recording the solution of the operator; and when a similar abnormal problem occurs for the second time, calling the information of the solution in the user behavior abnormal solution layer to solve the similar abnormal problem.
The method comprises the following steps that an operator executes a solution according to an actual abnormal problem in a plurality of modes, and when similar abnormality occurs for the second time and information in the user behavior abnormality solution layer is called, a plurality of solution options are recommended for the operator to select.
In addition, when a solution in the user behavior abnormity solving layer is called to solve the similar abnormity problem, the steps of the solution are firstly analyzed, and then the steps are executed step by step through an AI engine in a step question-and-answer mode. Or selecting a complete intelligent mode, describing a solution step by data provided in an exception solution layer by a user, setting an exception code as an exception monitoring value, and automatically solving the problem according to the set step by the AI engine when the exception occurs for the second time and the exception is set to be the complete intelligent mode.
The configuration method of the document approval process has the advantages that:
(1) modeling operation is carried out in advance, the process initiates a request for the first time, reading financial document data, briefly screening data information related to the single data process through an algorithm model at the bottom layer, a foreground draws a related process model according to the pushed information, and selects a process with high degree of engagement to carry out change operation.
(2) Along with the increment of the process configuration process training, the AI engine records the behavior habit and the configuration dimension of the user, and along with the increase of the operation times, the optimization of the AI engine on the recommended screening can be continuously increased until the operation times are completely equivalent to the ordinary service configuration of the user, so that the related process data can be pushed more accurately, and the change is less.
(3) When a user wants to optimize the training model, the algorithm packet is only replaced in the algorithm slot, and the training mode is changed.
(4) When the document is approved, the business or verification related problems can occur, the problems can be solved only by operating for a plurality of times in the past, the solved action steps can be recorded, the related solution prompt is provided when the problems are encountered next time, and the problems can be quickly solved only by receiving the recommended solution.
The invention also provides a storage medium, wherein the storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the configuration method of the document approval process. The invention also provides electronic equipment which comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor realizes the configuration method of the document approval process when executing the computer program.
The above embodiments are merely provided for full disclosure and not for limitation, and any replacement of equivalent technical features based on the gist of the present invention without creative efforts should be considered as the scope of the present disclosure.
Claims (10)
1. A configuration method of a document approval process is characterized by comprising the following steps:
modeling flow templates in advance according to the approval flow of the financial document, and configuring a plurality of modeled flow templates in a fixed model data table;
when the approval process of the financial document is configured specifically, an AI engine screens part of the process template from the fixed model data table through a screening algorithm and pushes the process template to a user for the first time;
the user selects one of the flow templates to draw an approval flow, the flow template is edited, the AI engine stores the operation behaviors edited by the user and performs modeling learning again according to the operation behaviors of the user;
and when the approval process of the financial document is configured next time, the AI engine pushes the process template to the user according to the screening algorithm after modeling and learning again.
2. The method for configuring a document approval process according to claim 1, further comprising a step of performing algorithm optimization on the training model of the AI engine, specifically: and a pluggable algorithm slot is arranged in the bottom algorithm of the training model, and a training algorithm packet is imported or deleted in a mode of plugging in and out the algorithm slot.
3. The method of claim 2, wherein the state of the training algorithm package comprises: a sharing algorithm, a priority training algorithm, and a conditional algorithm.
4. The method according to claim 3, wherein when configuring the approval process of the financial document next time, data is first obtained through a model bottom layer, and then the custom algorithm layer is used to determine whether a newly introduced training algorithm package exists, if so, learning statistical processing is performed, after the processing, the obtained data is processed through a simulated user behavior layer in which the operation behavior of the user for changing the document process is recorded, and the more operation behavior data is collected, the more the process template recommended to the user is.
5. The method for configuring a document approval process according to claim 1, further comprising an automated processing step of checking for abnormal situations, specifically: when the examination and approval process of the financial document is matched and an abnormal situation occurs during verification, recording a solution executed by an operator according to an actual abnormal problem in a user behavior abnormal solution layer; and when similar abnormal problems occur again, calling the information of the corresponding solution in the user behavior abnormal solution layer to solve the similar abnormal problems.
6. The method for configuring a document approval process according to claim 5, wherein the operator has multiple modes according to the solution executed by the actual abnormal problem, and when similar abnormality occurs again, and the information in the user behavior abnormality solution layer is called, multiple solution options are recommended for the operator to select.
7. The method for configuring document approval process according to claim 5, wherein when a solution in the user behavior anomaly solution layer is called to solve the similar anomaly problem, the step of resolving the solution is firstly analyzed, and then the step is executed step by an AI engine in a step-by-step question-and-answer manner.
8. The method of claim 5, wherein when a solution in the user behavior anomaly resolution layer is invoked to resolve the similar anomaly problem, the steps of resolving the solution are first parsed, then a fully intelligent mode is selected, and the full steps are automatically executed by an AI engine.
9. A storage medium having stored thereon a plurality of instructions, wherein the instructions are adapted to be loaded by a processor and to perform the method of configuring a document approval process of any one of claims 1 to 8.
10. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements a method of configuring a document approval process according to any one of claims 1 to 8 when executing the computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010635614.2A CN111815273A (en) | 2020-07-03 | 2020-07-03 | Configuration method of document approval process, storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010635614.2A CN111815273A (en) | 2020-07-03 | 2020-07-03 | Configuration method of document approval process, storage medium and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111815273A true CN111815273A (en) | 2020-10-23 |
Family
ID=72856242
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010635614.2A Pending CN111815273A (en) | 2020-07-03 | 2020-07-03 | Configuration method of document approval process, storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111815273A (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100011001A1 (en) * | 2008-07-14 | 2010-01-14 | Oracle International Corporation | Data approval system and method |
| CN103793285A (en) * | 2012-10-29 | 2014-05-14 | 百度在线网络技术（北京）有限公司 | Method and platform server for processing online anomalies |
| CN107886238A (en) * | 2017-11-09 | 2018-04-06 | 金航数码科技有限责任公司 | A kind of business process management system and method based on mass data analysis |
| CN108897587A (en) * | 2018-06-22 | 2018-11-27 | 北京优特捷信息技术有限公司 | Plug type machine learning algorithm operation method, device and readable storage medium storing program for executing |
| WO2019029650A1 (en) * | 2017-08-10 | 2019-02-14 | 成都牵牛草信息技术有限公司 | Form data operation auditing method |
| CN109710772A (en) * | 2018-11-13 | 2019-05-03 | 国云科技股份有限公司 | A kind of question and answer library Knowledge Management System and its implementation based on deep learning |
| CN109840159A (en) * | 2018-12-15 | 2019-06-04 | 中国平安人寿保险股份有限公司 | Abnormality processing project management method, apparatus, computer installation and storage medium |
| CN110502390A (en) * | 2019-07-08 | 2019-11-26 | 中国地质大学（武汉） | A kind of colleges and universities' cloud computing center automation operation management system |
| CN111199381A (en) * | 2019-11-25 | 2020-05-26 | 江苏艾佳家居用品有限公司 | Intelligent work order approval method based on process engine |
-
2020
- 2020-07-03 CN CN202010635614.2A patent/CN111815273A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100011001A1 (en) * | 2008-07-14 | 2010-01-14 | Oracle International Corporation | Data approval system and method |
| CN103793285A (en) * | 2012-10-29 | 2014-05-14 | 百度在线网络技术（北京）有限公司 | Method and platform server for processing online anomalies |
| WO2019029650A1 (en) * | 2017-08-10 | 2019-02-14 | 成都牵牛草信息技术有限公司 | Form data operation auditing method |
| CN107886238A (en) * | 2017-11-09 | 2018-04-06 | 金航数码科技有限责任公司 | A kind of business process management system and method based on mass data analysis |
| CN108897587A (en) * | 2018-06-22 | 2018-11-27 | 北京优特捷信息技术有限公司 | Plug type machine learning algorithm operation method, device and readable storage medium storing program for executing |
| CN109710772A (en) * | 2018-11-13 | 2019-05-03 | 国云科技股份有限公司 | A kind of question and answer library Knowledge Management System and its implementation based on deep learning |
| CN109840159A (en) * | 2018-12-15 | 2019-06-04 | 中国平安人寿保险股份有限公司 | Abnormality processing project management method, apparatus, computer installation and storage medium |
| CN110502390A (en) * | 2019-07-08 | 2019-11-26 | 中国地质大学（武汉） | A kind of colleges and universities' cloud computing center automation operation management system |
| CN111199381A (en) * | 2019-11-25 | 2020-05-26 | 江苏艾佳家居用品有限公司 | Intelligent work order approval method based on process engine |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103150249B (en) | A kind of method and system of automatic test | |
| CN110909039A (en) | Big data mining tool and method based on drag type process | |
| US8434058B1 (en) | Integrated system and method for validating the functionality and performance of software applications | |
| CN103092742B (en) | Program log recording optimization method and system | |
| CN103678110B (en) | The method and apparatus of amendment relevant information is provided | |
| US11733975B1 (en) | System and method for migrating legacy software to a system common architecture | |
| US10387236B2 (en) | Processing data errors for a data processing system | |
| CN113032195A (en) | Chip simulation verification method, system, equipment and storage medium | |
| KR20210149045A (en) | artificial intelligence chip verification | |
| US8898635B2 (en) | System and method for automatic impact variable analysis and field expansion in mainframe systems | |
| CN109656820B (en) | Intelligent automatic test system based on CBTC | |
| AU2019348202B2 (en) | System and method for robotic agent management | |
| CN105022691A (en) | Highly automatic software testing method based on UML diagram | |
| CN112380255A (en) | Service processing method, device, equipment and storage medium | |
| CN114399019A (en) | Neural network compiling method, system, computer device and storage medium | |
| US20220138032A1 (en) | Analysis of deep-level cause of fault of storage management | |
| CN111815273A (en) | Configuration method of document approval process, storage medium and electronic equipment | |
| CN116225377A (en) | Unified development method and device for cross-platform applet and electronic equipment | |
| CN114840418A (en) | Fuzzy test method and device | |
| US20100191710A1 (en) | Network Meta-Data Libraries And Related Methods | |
| CN110427370B (en) | Expert knowledge base and design method of platform thereof | |
| CN110990281B (en) | Automatic static analysis method | |
| Kothari et al. | Minimizing the size of test suite using genetic algorithm for object oriented program | |
| CN111208993B (en) | Flow data analysis processing system | |
| US20230168656A1 (en) | Automatically assigning natural language labels to non-conforming behavior of processes |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |