CN112163420A - NLP technology-based RPA process automatic generation method - Google Patents
NLP technology-based RPA process automatic generation method Download PDFInfo
- Publication number
- CN112163420A CN112163420A CN202011010218.7A CN202011010218A CN112163420A CN 112163420 A CN112163420 A CN 112163420A CN 202011010218 A CN202011010218 A CN 202011010218A CN 112163420 A CN112163420 A CN 112163420A
- Authority
- CN
- China
- Prior art keywords
- rpa
- flow
- activity
- neural network
- network model
- 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 50
- 238000005516 engineering process Methods 0.000 title claims abstract description 24
- 230000008569 process Effects 0.000 title claims description 23
- 230000000694 effects Effects 0.000 claims abstract description 55
- 238000003058 natural language processing Methods 0.000 claims abstract description 28
- 230000014509 gene expression Effects 0.000 claims abstract description 18
- 238000003062 neural network model Methods 0.000 claims abstract description 17
- 238000013461 design Methods 0.000 claims abstract description 11
- 238000013480 data collection Methods 0.000 claims abstract description 4
- 230000000875 corresponding effect Effects 0.000 claims description 20
- 238000002372 labelling Methods 0.000 claims description 2
- 238000012216 screening Methods 0.000 claims description 2
- 239000000463 material Substances 0.000 abstract description 5
- 238000006243 chemical reaction Methods 0.000 abstract description 4
- 238000011161 development Methods 0.000 abstract description 4
- 238000013527 convolutional neural network Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000004801 process automation Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013434 data augmentation Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000012634 fragment Substances 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000007500 overflow downdraw method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/216—Parsing using statistical methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- G06Q10/101—Collaborative creation, e.g. joint development of products or services
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Data Mining & Analysis (AREA)
- Entrepreneurship & Innovation (AREA)
- Molecular Biology (AREA)
- Strategic Management (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Biomedical Technology (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Economics (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Probability & Statistics with Applications (AREA)
- Machine Translation (AREA)
Abstract
The invention relates to the technical field of natural language processing, and particularly discloses an RPA flow automatic generation method based on NLP technology, which comprises the following steps: step S1, firstly, data collection is carried out and an expert system is established; step S2, constructing a natural language processing model and a rule base, including data enhancement and data expansion, a neural network model, neural network model selection, activity rule matching and expression rule matching; and step S3, generating an RPA flow code file. The invention combines NLP and RPA flow generation technology, realizes the direct conversion from flow design document to flow code file, enables the user to compile RPA automatic flow only by describing the business flow through natural language, reduces the consumption of manpower, material resources and financial resources of enterprises, and saves the development cost in the implementation of RPA project.
Description
Technical Field
The invention relates to the technical field of natural language processing, in particular to an RPA flow automatic generation method based on NLP technology.
Background
Nlp (natural Language processing), natural Language processing, is a field in which computer science, artificial intelligence, and linguistics focus on the interaction between computer and human (natural) Language. Rpa (robotic Process automation), i.e., robot Process automation, is a technology for compiling a Process by an interface operation on a computer so as to conveniently realize office automation. At present, various RPA products are provided by various manufacturers at home and abroad. These products, while functionally diverse, almost all include a process design platform. The RPA flow design platform is commonly referred to as an "RPA designer. Although most RPA designers have packaged (generally, packaged components are referred to as "activities") the automation operations (such as mouse click, keyboard entry, etc.) commonly used by business users to facilitate the users to compile processes in an interface operation manner, the daily work of business users usually includes data processing and some more complex processing logics, and the method of business processing is difficult to package one by one in a standard product, so that in practical situations, some professional-based implementers are still required to complete a complete compilation of business processes by embedding codes according to specific business requirements. This raises the use threshold of the RPA designer because it is difficult for a business user without the programming infrastructure to independently complete the programming of an automated process.
Disclosure of Invention
The technical problem to be solved by the present invention is to provide an RPA process automatic generation method based on NLP technology, which combines NLP and RPA process generation technologies to realize direct conversion from process design documents to process code files, so that users can compile RPA automation process only by describing business processes through natural language, thereby reducing the consumption of manpower, material resources and financial resources of enterprises and saving the development cost in the implementation of RPA projects.
In order to solve the technical problems, the technical scheme of the invention is as follows:
an RPA flow automatic generation method based on NLP technology comprises the following steps:
step S1, firstly, data collection is carried out and an expert system is established;
step S2, constructing a natural language processing model and a rule base, including data enhancement and data expansion, a neural network model, neural network model selection, activity rule matching and expression rule matching;
and step S3, generating an RPA flow code file.
Preferably, in step S1, the method further includes collecting item data, analyzing the number and frequency of RPA activities used in the real RPA item, and screening all activities with coverage rate of 95%.
Preferably, in the step S1, the method further includes labeling the sentence corresponding to the activity in the flow design document, and constructing the textual description, the metadata describing the type of the corresponding activity, and the segment in the textual description corresponding to the type of the one or more input parameters of the activity.
Preferably, in the step S2, the data enhancement includes synonym replacement, activity parameter replacement, multiple active sentence generation, and nested active sentence generation.
Preferably, in the step S2, the neural network model is used to determine the activities of a sentence, and identify parameters of each activity; the neural network model selection comprises selecting a BERT neural network model; and the active rule matching and the expression rule matching both comprise summarizing common templates, writing out corresponding regular expressions, finally matching texts through the regular expressions, and outputting corresponding results in a JSON format.
Preferably, in step S3, the method further includes parsing the JSON file generated in the above step to obtain the category and attribute content information of the activity to be generated, and obtaining the category and attribute information of all the activities by using the reflection of C #, and ActivityBuilder and xamlmlwriter in Windows Workflow Foundation and generating corresponding Xaml files.
By adopting the technical scheme, the RPA flow automatic generation method based on the NLP technology provided by the invention has the following beneficial effects: by combining NLP and RPA process generation technologies, the results are converted into code files readable by an RPA designer by using the process generation technologies, and an operable automatic process is finally realized by borrowing the code analysis capability of the RPA designer, so that the direct conversion from a process design document to a process code file is realized, a user can compile an RPA automatic process only by describing a business process through a natural language, the consumption of manpower, material resources and financial resources of an enterprise is reduced, and the development cost in the implementation of an RPA project is also saved.
Drawings
FIG. 1 is a flow chart of the present invention;
FIG. 2 is a schematic diagram of the operation of the present invention;
in the figure, S1-step S1, S2-step S2, S3-step S3.
Detailed Description
The following further describes embodiments of the present invention with reference to the drawings. It should be noted that the description of the embodiments is provided to help understanding of the present invention, but the present invention is not limited thereto. In addition, the technical features involved in the embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
As shown in fig. 1-2, the method for automatically generating an RPA flow based on the NLP technology combines the NLP technology with the RPA flow generation technology, understands the user intention through the NLP technology, maintains an expert system at the same time, abstracts the knowledge of an implementer with abundant experience into rules, then fuses the result of analyzing the user intention by the NLP with the rules of the expert system to generate interpretable structural data for an automated flow, finally converts the result into a code file readable by an RPA designer by using the flow generation technology, borrows the code analysis capability of the RPA designer, and finally realizes an executable automated flow, and the main implementation principle is as follows:
1. first, data collection is performed and an expert system is established. Project data completed by ten qualified RPA implementation engineers in a team are collected, the project data comprise project flow documents, flow codes and the like, experience in the implementation process is also collected, the number and the frequency of RPA activities used in a real RPA project are summarized and analyzed according to the experience, and 20 activities with the coverage rate of 95% are screened out. All activities are not included because the data volume of some activities with low use frequency is insufficient, which not only increases the technical complexity, but also affects the construction of subsequent models, resulting in increased errors of the output results. And meanwhile, marking sentences corresponding to the activities in the flow design document, and constructing original text description (namely business instructions described by natural language in the document), and metadata describing the corresponding activity type and fragments in the original text description corresponding to the type of one or more input parameters of the activity.
2. Secondly, a natural language processing model and a rule base are constructed, and the method comprises the following steps:
2.1 data enhancement and data augmentation
Data enhancement is mainly used for expanding a data set and solving some problems existing in the current data set. The current data set suffers from two main problems:
problem 1: deep learning relies on a large amount of data, the amount of existing real service scene data is relatively small (the total amount is 3695 pieces of text data), the distribution is uneven, and a large part of common activities are occupied.
Problem 2: the real data lack the text of a plurality of activities and nested activities, such as 'Click a button, open D: \ RPA \ test. xlsxsxsX' which belongs to a plurality of activities (Click and createExcel) 'If the amount is larger than 0, Click a payment button' which belongs to the nested activities (Click activity is nested in If activity). In order to solve the above problems, 4 methods of data enhancement are adopted:
replacement of a synonym: dividing the command sentence into words, randomly replacing some non-keyword words with similar words, and replacing with synnyms.
And (3) activity parameter replacement: the marked real command sentence comprises an activity type, a parameter type and a specific parameter, and the parameter of the corresponding parameter type can be replaced. For example, "www.baidu.com" in "navigate to www.baidu.com" is a Url parameter, which is randomly replaced with another Url using campaign parameter replacement.
Multiple active sentence generation: two sentences belonging to different activities are found at random and then spliced together. For example, two command sentences, namely "click button" and "input RPA in text box" are spliced together to obtain a multi-active sentence "click button and input RPA in text box".
Nested active sentence generation: the If and ForEach activities can contain nested activities, and a simple nested activity sentence can be generated by randomly replacing the Then and Else parameters of the If with another activity sentence.
2.2 neural network model
The neural network model is used for judging the activity of a sentence and identifying the parameter of each activity, and can be suitable for multi-activity and nested activity identification. For example, given an active sentence "enter password in password column and Click login button", it is necessary to identify two activities (typeInto and Click) to which the sentence belongs, and then identify the parameters corresponding to the two activities respectively (typeInto selector is password column, text is password; Click selector is login button).
2.2.1 neural network model selection
The document analysis task comprises two subtasks of text classification and named entity identification, and the selectable mainstream neural network models comprise BilSTM, CNN, BERT and the like, and the three models are realized through codes. The results in the validation phase found that BERT was far more effective than BilSTM and CNN, and was about 30% higher than BilSTM and CNN on the F1 score. Therefore, the BERT model is mainly adopted, and the advantages and the disadvantages of the BERT model comprise:
BERT has more parameter models which are pre-trained in a large-scale Chinese pre-material library, and the pre-training model is better to be used for retraining under the condition of less data volume.
BERT can be used for longer text sequences than BiLSTM and CNN.
A multi-layer Attention fusion method is adopted in BERT, and each word can be better combined with information of other words.
BERT, however, has some drawbacks in that its model is relatively large (with 1 hundred million parameters) and is trained for a long time, and thus takes a long time to verify the effectiveness of some optimizations.
2.2.2 Activity rule matching and expression rule matching
In addition to the neural network model mentioned above, the activity and parameter identification also uses a rule matching method for processing complex activity descriptions and automatically generating code expressions (for example, "yesterday" will be transformed into "new. adddays (-1)") so as to further generate available flow codes, which also partially solves the problem that business users have no programming basis and are often troubled by some code expressions when programming flows.
The activity is similar to the rule matching method of the expression, and the activities and the rule matching method of the expression are that some common templates are summarized firstly, then the corresponding regular expression is written out, and finally the text is matched through the regular expression. For example, there is a regular expression 'at (input)' of typeInto, the command sentence "input text in text box" can be matched with the regular expression, and the corresponding parameters "text box" and "text" can be identified.
And outputting the result in a JSON format to form an input file for generating the flow code file.
3. And finally generating an RPA flow code file.
Analyzing the JSON file generated in the steps to obtain information such as the category, the attribute content and the like of the activity to be generated, acquiring the category and the attribute information of all the activities by using the reflection of C #, and ActivityBuilder and XamlXmlWriter in Windows Workflow Foundation, and generating a corresponding Xaml file. This file is a flow file readable by the RPA designer, and the flow that can be run can be seen by opening the file using the RPA designer. From the perspective of an end user, only the flow design document needs to be input to obtain the executable RPA flow file.
It can be understood that the invention has reasonable design and unique structure, realizes the direct conversion from the flow design document to the flow code file by combining the NLP and the RPA flow generation technology, enables the user to compile the RPA automatic flow only by describing the business flow through the natural language, reduces the consumption of the manpower, material resources and financial resources of the enterprise, and also saves the development cost in the implementation of the RPA project.
The embodiments of the present invention have been described in detail with reference to the accompanying drawings, but the present invention is not limited to the described embodiments. It will be apparent to those skilled in the art that various changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, and the scope of protection is still within the scope of the invention.
Claims (6)
1. An RPA process automatic generation method based on NLP technology is characterized in that: the method comprises the following steps:
step S1, firstly, data collection is carried out and an expert system is established;
step S2, constructing a natural language processing model and a rule base, including data enhancement and data expansion, a neural network model, neural network model selection, activity rule matching and expression rule matching;
and step S3, generating an RPA flow code file.
2. The RPA flow automatic generation method based on NLP technology according to claim 1, characterized in that: in step S1, the method further includes collecting item data, analyzing the number and frequency of RPA activities used in the real RPA item, and screening all activities with coverage rate of 95%.
3. The RPA flow automatic generation method based on NLP technology according to claim 1, characterized in that: in step S1, the method further includes labeling the sentence corresponding to the activity in the flow design document, and constructing the textual description, the metadata describing the type of the corresponding activity, and the segment in the textual description corresponding to the type of the one or more input parameters of the activity.
4. The RPA flow automatic generation method based on NLP technology according to claim 1, characterized in that: in the step S2, the data enhancement includes synonym replacement, activity parameter replacement, multiple active sentence generation, and nested active sentence generation.
5. The RPA flow automatic generation method based on NLP technology according to claim 1, characterized in that: in step S2, the neural network model is used to determine the activities of a sentence, and identify the parameters of each activity; the neural network model selection comprises selecting a BERT neural network model; and the active rule matching and the expression rule matching both comprise summarizing common templates, writing out corresponding regular expressions, finally matching texts through the regular expressions, and outputting corresponding results in a JSON format.
6. The RPA process automatic generation method based on NLP technology according to claim 5, wherein: in step S3, the method further includes parsing the JSON file generated in the above steps to obtain the category and attribute content information of the activity to be generated, and obtaining the category and attribute information of all the activities by using the reflection of C #, and actitybuilder and xamlmwriter in Windows Workflow Foundation and generating corresponding Xaml files.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011010218.7A CN112163420A (en) | 2020-09-23 | 2020-09-23 | NLP technology-based RPA process automatic generation method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011010218.7A CN112163420A (en) | 2020-09-23 | 2020-09-23 | NLP technology-based RPA process automatic generation method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112163420A true CN112163420A (en) | 2021-01-01 |
Family
ID=73863450
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011010218.7A Pending CN112163420A (en) | 2020-09-23 | 2020-09-23 | NLP technology-based RPA process automatic generation method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112163420A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113159951A (en) * | 2021-04-23 | 2021-07-23 | 平安证券股份有限公司 | Financial data clearing method, device, equipment and storage medium |
| CN113360649A (en) * | 2021-06-04 | 2021-09-07 | 湖南大学 | Flow error control method and system based on natural language processing in RPA system |
| CN113434798A (en) * | 2021-06-21 | 2021-09-24 | 湖南大学 | Method and system for generating codeless RPA (resilient packet Access) automatic flow file |
| CN113535551A (en) * | 2021-06-30 | 2021-10-22 | 杭州电子科技大学 | Text model construction method for 6016B rule test based on json format specification description |
| CN114926151A (en) * | 2022-06-21 | 2022-08-19 | 中关村科学城城市大脑股份有限公司 | RPA flow automatic generation method and device based on reinforcement learning |
| CN115098205A (en) * | 2022-06-17 | 2022-09-23 | 来也科技(北京)有限公司 | Control method for realizing IA flow editing interface based on RPA and AI |
| CN116719514A (en) * | 2023-08-08 | 2023-09-08 | 安徽思高智能科技有限公司 | Automatic RPA code generation method and device based on BERT |
| WO2023226129A1 (en) * | 2022-05-24 | 2023-11-30 | 来也科技(北京)有限公司 | Item-rule code generation method and apparatus combining rpa and ai, and electronic device |
| CN117311798A (en) * | 2023-11-28 | 2023-12-29 | 杭州实在智能科技有限公司 | RPA flow generation system and method based on large language model |
| CN117421414A (en) * | 2023-12-18 | 2024-01-19 | 珠海金智维信息科技有限公司 | Design method of RPA intelligent interactive system based on AIGC |
-
2020
- 2020-09-23 CN CN202011010218.7A patent/CN112163420A/en active Pending
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113159951B (en) * | 2021-04-23 | 2022-10-14 | 平安证券股份有限公司 | Financial data clearing method, device, equipment and storage medium |
| CN113159951A (en) * | 2021-04-23 | 2021-07-23 | 平安证券股份有限公司 | Financial data clearing method, device, equipment and storage medium |
| CN113360649A (en) * | 2021-06-04 | 2021-09-07 | 湖南大学 | Flow error control method and system based on natural language processing in RPA system |
| CN113360649B (en) * | 2021-06-04 | 2024-01-05 | 湖南大学 | Natural language processing-based flow error control method and system in RPA system |
| CN113434798A (en) * | 2021-06-21 | 2021-09-24 | 湖南大学 | Method and system for generating codeless RPA (resilient packet Access) automatic flow file |
| CN113434798B (en) * | 2021-06-21 | 2023-05-23 | 湖南大学 | Code-free RPA automatic process file generation method and system |
| CN113535551A (en) * | 2021-06-30 | 2021-10-22 | 杭州电子科技大学 | Text model construction method for 6016B rule test based on json format specification description |
| WO2023226129A1 (en) * | 2022-05-24 | 2023-11-30 | 来也科技(北京)有限公司 | Item-rule code generation method and apparatus combining rpa and ai, and electronic device |
| CN115098205A (en) * | 2022-06-17 | 2022-09-23 | 来也科技(北京)有限公司 | Control method for realizing IA flow editing interface based on RPA and AI |
| CN114926151A (en) * | 2022-06-21 | 2022-08-19 | 中关村科学城城市大脑股份有限公司 | RPA flow automatic generation method and device based on reinforcement learning |
| CN116719514A (en) * | 2023-08-08 | 2023-09-08 | 安徽思高智能科技有限公司 | Automatic RPA code generation method and device based on BERT |
| CN116719514B (en) * | 2023-08-08 | 2023-10-20 | 安徽思高智能科技有限公司 | Automatic RPA code generation method and device based on BERT |
| CN117311798A (en) * | 2023-11-28 | 2023-12-29 | 杭州实在智能科技有限公司 | RPA flow generation system and method based on large language model |
| CN117421414A (en) * | 2023-12-18 | 2024-01-19 | 珠海金智维信息科技有限公司 | Design method of RPA intelligent interactive system based on AIGC |
| CN117421414B (en) * | 2023-12-18 | 2024-03-26 | 珠海金智维信息科技有限公司 | Design method of RPA intelligent interactive system based on AIGC |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112163420A (en) | NLP technology-based RPA process automatic generation method | |
| Fu et al. | A survey on complex question answering over knowledge base: Recent advances and challenges | |
| JP7486250B2 (en) | Domain-specific language interpreter and interactive visual interface for rapid screening | |
| Wang et al. | Asking the right questions to elicit product requirements | |
| Gannod et al. | A framework for classifying and comparing software reverse engineering and design recovery techniques | |
| Meziane et al. | Artificial intelligence applications for improved software engineering development: New prospects: New Prospects | |
| CN111221881B (en) | User characteristic data synthesis method and device and electronic equipment | |
| Jackson et al. | From natural language to simulations: Applying gpt-3 codex to automate simulation modeling of logistics systems | |
| Rokis et al. | Exploring Low-Code Development: A Comprehensive Literature Review | |
| Pittaras et al. | A taxonomic system for failure cause analysis of open source AI incidents | |
| Chiarello et al. | Generative large language models in engineering design: opportunities and challenges | |
| CN115469860B (en) | Method and system for automatically generating demand-to-software field model based on instruction set | |
| Chioaşcă | Using machine learning to enhance automated requirements model transformation | |
| Jubair et al. | A multi‐agent K‐means with case‐based reasoning for an automated quality assessment of software requirement specification | |
| De Kinderen | Using Grounded Theory for Domain Specific Modelling Language Design: Lessons Learned from the Smart Grid Domain | |
| Li et al. | How to manage a task-oriented virtual assistant software project: an experience report | |
| Kovalenko et al. | Towards evaluation and comparison of tools for ontology population from spreadsheet data | |
| Fill | Semantic evaluation of business processes using SeMFIS | |
| Sonje et al. | draw2code: Ai based auto web page generation from hand-drawn page mock-up | |
| Marques-Lucena et al. | A semantic wiki approach to enable behaviour driven requirements management | |
| Zhang et al. | Predicting Relations in SG-CIM Model Based on Graph Structure and Semantic Information | |
| Buttinger et al. | JobOlize Headhunting by Information Extraction in the Era of Web 2.0 | |
| Alam | AI-HUB 2.0 PROJECT REPORT: Application Of Large Language | |
| Kim | Designing of domain modeling for mobile applications development | |
| Gupta | Test Case Selection from Test Specifications using Natural Language Processing |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20210101 |
|
| WD01 | Invention patent application deemed withdrawn after publication |