CN116628351A - Node-dependency-based flow chart branch recommendation method, device and storage device - Google Patents
Node-dependency-based flow chart branch recommendation method, device and storage device Download PDFInfo
- Publication number
- CN116628351A CN116628351A CN202310921029.2A CN202310921029A CN116628351A CN 116628351 A CN116628351 A CN 116628351A CN 202310921029 A CN202310921029 A CN 202310921029A CN 116628351 A CN116628351 A CN 116628351A
- Authority
- CN
- China
- Prior art keywords
- node
- flow chart
- nodes
- data
- dependency
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 48
- 239000011159 matrix material Substances 0.000 claims description 7
- 230000001419 dependent effect Effects 0.000 claims 5
- 238000002372 labelling Methods 0.000 claims 1
- 230000000694 effects Effects 0.000 abstract description 6
- 230000009286 beneficial effect Effects 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 11
- 238000012706 support-vector machine Methods 0.000 description 7
- 238000005065 mining Methods 0.000 description 3
- 238000010606 normalization Methods 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000005111 flow chemistry technique Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000011144 upstream manufacturing Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/20—Drawing from basic elements, e.g. lines or circles
- G06T11/206—Drawing of charts or graphs
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Medical Informatics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a method, equipment and storage equipment for recommending flow chart branches based on node dependence, and a method, equipment and storage equipment for collecting a historical flow chart data file Q; analyzing the file Q to obtain nodes and attributes thereof, and calculating node similarity; merging nodes with higher similarity; generating features and labels according to the generated directed graph data and the statistical data of the dependency relationship between the nodes, so as to obtain data D; SVM learning is adopted for the data D to obtain a model F; the user flow chart is drawn with nodes, and the rear nodes with strong dependency relationships are recommended to the user according to the model F, so that a complete flow chart is obtained. A flow chart branch recommendation device and a storage device based on node dependence are used for realizing a flow chart branch recommendation method based on node dependence. The beneficial effects of the invention are as follows: the follow-up nodes are recommended to the flow chart drawing personnel through learning the dependency relationship among the flow chart nodes, so that the effect of flow chart branch recommendation is achieved, and the accuracy of flow chart drawing is improved.
Description
Technical Field
The invention relates to the field of big data processing, in particular to a flow chart branch recommendation method, equipment and storage equipment based on node dependence.
Background
In the field of big data, workflow tool methods for handling extraction and processing of massive data have very important industrial uses. In a big data workflow tool system, a user may create different workflow diagrams to depict the flow of different operations based on complex business logic. In most cases, due to the complexity of business logic, a practical operator is often relied on to manually draw a flow chart in flow chart drawing software according to the business logic, but the process is time-consuming, labor-consuming and high in labor cost.
The Chinese patent 'flow recommendation method based on graph mining and graph distance' (CN 201310336606.8) discloses a flow recommendation method based on graph mining and graph distance, which comprises the following steps: the input flow set abstract label is in the form of a directed graph, and a flow subgraph is obtained; the sub-graph mining and decomposing module decomposes the aggregate output by the preprocessing step to obtain an upstream sub-graph and the like; the recommendation module acquires a reference flow and outputs candidate nodes corresponding to the best matching data items as a recommendation flow. The recommendation can be performed with high efficiency and low complexity, and complex structure flow processing is supported, but the dependency relationship between node pairs is not considered in the directed graph, so that part of accuracy can be influenced.
The Chinese patent "a method and apparatus for generating a flowchart and a storage medium" (CN202211182143. X) discloses a method and apparatus for generating a flowchart and a storage medium. The method comprises the following steps: acquiring a dependency relationship among elements in the flow chart, wherein the dependency relationship is used for representing the execution sequence among different elements; checking whether the acquired dependency relationship meets preset rules or not, and the like. The method improves the accuracy and intuitiveness of generating the flow chart and the maintenance efficiency of the flow chart, reduces the maintenance difficulty for the flow chart, but only improves the flow chart generation, and cannot recommend the flow chart branches for the user when the user draws the flow chart.
Disclosure of Invention
In order to solve the problems, the invention provides a flow chart branch recommending method, equipment and storage equipment based on node dependence, which depend on a historical flow chart data file, a node dependence strength judging model is generated by calculating node similarity, combining similar nodes, generating characteristics and labels through node dependence statistical data and other operations, the model can be embedded into flow chart drawing software to assist flow chart drawing personnel, and can recommend subsequent nodes of the flow chart, so that subsequent developers can develop or process secondarily on the basis.
A flow chart branch recommendation method based on node dependence mainly comprises the following steps:
s1: collecting a historical flow chart data file Q;
s2: analyzing the file Q to obtain nodes and attributes thereof, and calculating node similarity;
s3: merging nodes with higher similarity;
s4: generating directed graph data;
s5: generating features and labels according to the directed graph data and the statistical data of the dependency relationship between the nodes, so as to obtain data D;
s6: SVM learning is adopted for the data D to obtain a model F;
s7: the user flow chart is drawn with nodes, and the rear nodes with strong dependency relationships are recommended to the user according to the model F, so that a complete flow chart is obtained.
Further, node similarity is calculated by using the following formula to obtain a node similarity matrix：
wherein ,indicate->Personal node->Indicate->Personal node->Indicating transpose,/->Representing the total number of nodes parsed.
Further, the node merging process is as follows: setting a similarity thresholdAccording to the node similarity matrix, when the calculated node similarity is greater than a threshold +.>The nodes are merged.
Further, generating features for node pairs based on statistical data of node-to-node dependenciesAnd tag->The feature and the tag are normalized and combined to obtain complete data +.>, wherein ,representing the number of pairs of nodes,nfor the number of nodes combined in step S3, < >>Indicate->Personal characteristics (I)>Represents normalized->And (3) labels.
Further, the process of generating features for node pairs according to the directed graph is as follows:
s511: for node pair (a, B) statistics: number of times node a to node BNumber of times node B to node A>；
S512: according to and />Generating characteristics: /> The method is characterized by comprising the following steps:
s513: for node pair (A, B), there are features that After combination, the characteristic ∈>。
Further, the process of generating labels for node pairs according to the directed graph is as follows:
s521: first, the label is attached toInitialized to 0 and then counted for the number of direct connections of node A to node B in the historic flow chart data file Q for the node pair (A, B) with direct connection>The tag adds the number of direct connections, namely:
for node pairs (A, C) that have no direct connection among the node pairs, assume that the number of paths from node A to node C isCalculating an intermediate distance node for each indirect connection>The tag is updated by the following formula>：
S522: after the labels of all node pairs are calculated, normalizing the labels to obtain。
A storage device stores instructions and data for implementing a node dependency based flow diagram branch recommendation method.
A node-dependency-based flow diagram branch recommendation device, comprising: a processor and the storage device; the processor loads and executes the instructions and data in the storage device to implement a node-dependency-based flow chart branch recommendation method.
The technical scheme provided by the invention has the beneficial effects that: and the historical flow chart data file is utilized to learn the dependency relationship among the nodes by vectorizing the node attributes and calculating the node similarity, and meanwhile, the historical flow chart data file is utilized to generate the characteristics and labels for the node pairs, and a Support Vector Machine (SVM) is adopted to learn the dependency relationship among the nodes. In the nodes of the flow chart, strong dependency relations among part of the nodes are observed, and as the history flow chart has a certain reference effect on the current flow chart, subsequent nodes are recommended for the flow chart drawing personnel by learning the dependency relations among the nodes of the flow chart, so that the effect of flow chart branch recommendation is achieved, and the accuracy of flow chart drawing is improved.
Drawings
The invention will be further described with reference to the accompanying drawings and examples, in which:
FIG. 1 is a flow chart of a node dependency based flow chart branch recommendation method in an embodiment of the invention;
FIG. 2 is a schematic diagram of label computation in an embodiment of the invention;
FIG. 3 is a schematic diagram of direct and indirect dependencies in an embodiment of the invention;
FIG. 4 is a schematic diagram of a flowchart branch recommendation in an embodiment of the present invention;
FIG. 5 is a schematic diagram of the operation of a hardware device in an embodiment of the invention.
Detailed Description
For a clearer understanding of technical features, objects and effects of the present invention, a detailed description of embodiments of the present invention will be made with reference to the accompanying drawings.
The embodiment of the invention provides an RPA flow discovery method and device based on multi-view clustering.
Referring to fig. 1, fig. 1 is a flowchart of a method for recommending branches of a flow chart based on node dependency in an embodiment of the invention, which specifically includes:
s1: collecting a historical flow chart data file Q;
s2: reading and analyzing the historical flow chart data file Q to obtainThe individual nodes calculate node similarity and the attribute thereof according to the node text attribute;
analyzing the historical flow chart data file Q to obtain the historical flow chart nodes and attribute information thereof, wherein the node part attributes and the values thereof are shown in a table 1;
table 1 node part attributes and description
Wherein the node set is represented as，/>Representing the total number of parsed nodes, each node +.>，/>Representing the j-th attribute value of the i-th node, vectorizing the attribute of each node, and vectorizing each attribute by adopting One-Hot independent coding; then, calculating the similarity of the nodes by adopting cosine similarity to obtain a node similarity matrix +.>：
Because there is a slight difference in the attribute of some nodes in the same class of nodes, for example, the node A name is "obtain xx account number and password", the node B name is "obtain yy account number and password", the accuracy of the nodes identified as different classes is reduced, and therefore the nodes with higher similarity need to be combined.
S3: merging nodes with higher similarity; setting a similarity thresholdAccording to the node similarity matrix, if the calculated similarity of two nodes is greater than a threshold +.>When the nodes are combined, the combined node set is +.>Where n is the number of nodes after merging.
S4: generating directed graph data; after analyzing the data file Q of the historical flow chart and merging similar nodes, the node and the node connection relation can be obtained and represented by a directed graph, wherein />Represents the merged node set, E represents the adjacency matrix,>representing an ith node;
s5: generating features from statistical data of nodes and inter-node (i.e., node pair) dependenciesAnd tag->Normalizing the tag, and combining to obtain complete data +.>, wherein />Representing the number of node pairs>Indicate->The characteristics of the device are that,represents normalized->And (3) labels.
Constructing characteristics and labels of each node:
s51: from directed graphsGenerating features for node pairs>The method comprises the following specific steps:
s511: since the method can learn from the historical flow chart data file Q, in order to facilitate the following learning of the dependency relationship among the nodes in the flow chart, features and labels need to be generated from the directed graph abstracted from the flow chart, and the prior art [1,2 ] is referred to in the learning of the dependency relationship generation features]For node pair (a, B) statistics: number of times node a to node BNumber of times node B to node A>；
S512: according to and />Generating characteristics: /> The method is characterized by comprising the following steps:
s513: for node pair (A, B), there are features that After combination, the characteristic ∈>；
S52: from directed graphsGenerating labels for node pairs>；
S521: in order to facilitate the subsequent learning of the dependency relationships between nodes in the flow chart, features and labels need to be generated from the directed graph abstracted from the flow chart; in generating the tag, the tag is first of all attached toInitialized to 0 and then, as shown in FIG. 3, for the node pair (A, B) with direct connection, the number of direct connection of node A to node B in the statistical history flow chart data file Q +.>The tag adds the number of direct connections, namely:
as shown in FIG. 3, for node pairs that have no direct connection among the node pairsA,C) Assume that the number of paths from node A to node C isCalculating an intermediate distance node for each indirect connection>And update node pairsA,C) Label->：
As in fig. 2, when it is desired to calculate the labels of node pairs (a, E)In the case of a direct connection, there is first of all the number of times +.>1, i.e.)>The method comprises the steps of carrying out a first treatment on the surface of the Then there is node pairA,E) The indirect connection path has two, namely +.>2, and the number of intermediate nodes is 2 and 1 respectively, namely +.> and />Finally there is，/>；
S522: after the labels of all node pairs are calculated, normalizing the labels to obtainThe method comprises the steps of carrying out a first treatment on the surface of the The specific normalization process comprises the following steps: for non-normalized labelsPerforming linear transformation to map data values to [0, 1]]The linear mapping formula is:
wherein , and />The i-th tag before and after normalization, respectively,> and />Respectively representing the minimum value and the maximum value in the label set before normalization;
s6: learning the data D by adopting a Support Vector Machine (SVM) to obtain a model F; inputting the node pair (A, B) into a model F, and recording as；/>Returning a fraction between 0 and 1, a ∈>The closer the value is to 1, the stronger the dependency of the node pair (A, B), the +.>The closer the value is to 0, the weaker the node pair (a, B) dependency is;
s7: the user flow chart is drawn with nodes, and a rear node with a strong dependency relationship is recommended to the user according to the model F; when a user draws a flow chart on the basis of the historical flow chart data file Q, if the user draws the node A, the model F recommends a section for the userPoint A is the first k successor nodes with stronger dependency relationship of the predecessorAs shown in fig. 4, the solid line indicates recommendation, the broken line indicates non-recommendation, and the subsequent node having a weak dependency does not recommend.
Referring to fig. 5, fig. 5 is a schematic working diagram of a hardware device according to an embodiment of the present invention, where the hardware device specifically includes: a node dependency based flow diagram branch recommendation device 401, a processor 402, and a storage device 403.
Node dependency based flow diagram branch recommendation device 401: the flow chart branch recommendation device 401 based on node dependency realizes the flow chart branch recommendation method based on node dependency.
Processor 402: the processor 402 loads and executes instructions and data in the memory device 403 for implementing the one node dependency based flow diagram branch recommendation method.
Storage device 403: the storage device 403 stores instructions and data; the storage device 403 is configured to implement the node dependency-based flowchart branch recommendation method.
The beneficial effects of the invention are as follows: and the historical flow chart data file is utilized to learn the dependency relationship among the nodes by vectorizing the node attributes and calculating the node similarity, and meanwhile, the historical flow chart data file is utilized to generate the characteristics and labels for the node pairs, and a Support Vector Machine (SVM) is adopted to learn the dependency relationship among the nodes. In the nodes of the flow chart, strong dependency relations among part of the nodes are observed, and as the history flow chart has a certain reference effect on the current flow chart, subsequent nodes are recommended for the flow chart drawing personnel by learning the dependency relations among the nodes of the flow chart, so that the effect of flow chart branch recommendation is achieved, and the accuracy of flow chart drawing is improved.
The foregoing description of the preferred embodiments of the invention is not intended to limit the invention to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and scope of the invention are intended to be included within the scope of the invention.
The prior art referred to in the present invention is:
[1] hu Cheng, chen, shouq. A small microcomputer system, 43 (10): 2078-2083, uses the concept dependency identification method of wikipedia click stream [ J ].
[2] LiangC, Ye J, Wang S, et al. Investigating active learning for concept prerequisitelearning[C]//32nd AAAI Conference on Artificial Intelligence, AAAI 2018. AAAIpress, 2018: 7913-7919.
Claims (8)
1. A flow chart branch recommendation method based on node dependence is characterized in that: comprising the following steps:
s1: collecting a historical flow chart data file Q;
s2: analyzing the file Q to obtain nodes and attributes thereof, and calculating node similarity;
s3: merging nodes with higher similarity;
s4: generating directed graph data;
s5: generating features and labels according to the directed graph data and the statistical data of the dependency relationship between the nodes, so as to obtain data D;
s6: SVM learning is adopted for the data D to obtain a model F;
s7: the user flow chart is drawn with nodes, and the rear nodes with strong dependency relationships are recommended to the user according to the model F, so that a complete flow chart is obtained.
2. The node-dependent flowchart branch recommendation method of claim 1, wherein: in step S2, node similarity is calculated by using the following formula to obtain a node similarity matrix：
wherein ,indicate->Personal node->Indicate->Personal node->Indicating transpose,/->Representing the total number of nodes parsed.
3. The node-dependent flowchart branch recommendation method of claim 1, wherein: in step S3, the node merging process is as follows: setting a similarity thresholdAccording to the node similarity matrix, when the calculated node similarity is greater than a threshold +.>The nodes are merged.
4. The node-dependent flowchart branch recommendation method of claim 1, wherein: in step S5, features are generated for the node pairs according to the statistical data of the node-node dependency relationshipAnd tag->The feature and the tag are normalized and combined to obtain complete data +.>, wherein ,/>Representing the number of pairs of nodes,nfor the number of nodes combined in step S3, < >>Indicate->Personal characteristics (I)>Representing normalized firstAnd (3) labels.
5. The node-dependent flowchart branch recommendation method of claim 4, wherein:
the process of generating features for node pairs according to the directed graph is as follows:
s511: for node pair (a, B) statistics: number of times node a to node BNumber of times node B to node A>；
S512: according to and />Generating characteristics: /> The method is characterized by comprising the following steps:
s513: for node pair (A, B), there are features that After combination, the characteristic ∈>。
6. The node-dependent flowchart branch recommendation method of claim 4, wherein:
the process of generating labels for node pairs according to the directed graph is as follows:
s521: first, the label is attached toInitialized to 0 and then counted for the number of direct connections of node A to node B in the historic flow chart data file Q for the node pair (A, B) with direct connection>By labelling the number of direct connectionsUpdating the tag, namely:
for node pairs (A, C) that have no direct connection among the node pairs, assume that the number of paths from node A to node C isCalculating an intermediate distance node for each indirect connection>The tag is updated by the following formula>：
S522: after the labels of all node pairs are calculated, normalizing the labels to obtain。
7. A memory device, characterized by: the storage device stores instructions and data for implementing the node-dependency-based flow chart branch recommendation method according to any one of claims 1 to 6.
8. A node-dependency-based flow chart branch recommendation device, characterized by: comprising the following steps: a processor and a storage device; the processor loads and executes the instructions and data in the storage device to implement the node-dependency-based flowchart branch recommendation method of any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310921029.2A CN116628351B (en) | 2023-07-26 | 2023-07-26 | Node-dependency-based flow chart branch recommendation method, device and storage device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310921029.2A CN116628351B (en) | 2023-07-26 | 2023-07-26 | Node-dependency-based flow chart branch recommendation method, device and storage device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116628351A true CN116628351A (en) | 2023-08-22 |
| CN116628351B CN116628351B (en) | 2023-10-20 |
Family
ID=87610309
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310921029.2A Active CN116628351B (en) | 2023-07-26 | 2023-07-26 | Node-dependency-based flow chart branch recommendation method, device and storage device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116628351B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103400227A (en) * | 2013-08-05 | 2013-11-20 | 浙江大学 | Graph mining and graph distance-based flow recommendation method |
| US20140109106A1 (en) * | 2012-10-17 | 2014-04-17 | Microsoft Corporation | Code dependency calculation |
| WO2014143878A1 (en) * | 2013-03-15 | 2014-09-18 | The Board Of Trustees Of The Leland Stanford Junior University | Systems and methods for recommending relationships within a graph database |
| US20140358720A1 (en) * | 2013-05-31 | 2014-12-04 | Yahoo! Inc. | Method and apparatus to build flowcharts for e-shopping recommendations |
| CN104380344A (en) * | 2013-03-12 | 2015-02-25 | 梦工厂动画公司 | Visualization tool for parallel dependency graph evaluation |
| WO2016192604A1 (en) * | 2015-06-05 | 2016-12-08 | 阿里巴巴集团控股有限公司 | Visualization method, device and system for global task node dependence relationship |
| CN109409848A (en) * | 2018-11-28 | 2019-03-01 | 厦门市美亚柏科信息股份有限公司 | Node intelligent recommended method, terminal device and the storage medium of open process |
| WO2022068189A1 (en) * | 2020-09-30 | 2022-04-07 | 平安科技（深圳）有限公司 | Flow visualization monitoring method and apparatus, computer device, and storage medium |
| CN116226220A (en) * | 2022-11-14 | 2023-06-06 | 河南大学 | Remote sensing flow recommendation method based on logic structure and attribute characteristics |
| US20230195742A1 (en) * | 2021-12-21 | 2023-06-22 | Hitachi, Ltd. | Time series prediction method for graph structure data |
-
2023
- 2023-07-26 CN CN202310921029.2A patent/CN116628351B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170278290A1 (en) * | 2012-08-03 | 2017-09-28 | Dreamworks Animation Llc | Visualization tool for parallel dependency graph evaluation |
| US20140109106A1 (en) * | 2012-10-17 | 2014-04-17 | Microsoft Corporation | Code dependency calculation |
| CN104380344A (en) * | 2013-03-12 | 2015-02-25 | 梦工厂动画公司 | Visualization tool for parallel dependency graph evaluation |
| WO2014143878A1 (en) * | 2013-03-15 | 2014-09-18 | The Board Of Trustees Of The Leland Stanford Junior University | Systems and methods for recommending relationships within a graph database |
| US20140358720A1 (en) * | 2013-05-31 | 2014-12-04 | Yahoo! Inc. | Method and apparatus to build flowcharts for e-shopping recommendations |
| CN103400227A (en) * | 2013-08-05 | 2013-11-20 | 浙江大学 | Graph mining and graph distance-based flow recommendation method |
| WO2016192604A1 (en) * | 2015-06-05 | 2016-12-08 | 阿里巴巴集团控股有限公司 | Visualization method, device and system for global task node dependence relationship |
| CN109409848A (en) * | 2018-11-28 | 2019-03-01 | 厦门市美亚柏科信息股份有限公司 | Node intelligent recommended method, terminal device and the storage medium of open process |
| WO2022068189A1 (en) * | 2020-09-30 | 2022-04-07 | 平安科技（深圳）有限公司 | Flow visualization monitoring method and apparatus, computer device, and storage medium |
| US20230195742A1 (en) * | 2021-12-21 | 2023-06-22 | Hitachi, Ltd. | Time series prediction method for graph structure data |
| CN116226220A (en) * | 2022-11-14 | 2023-06-06 | 河南大学 | Remote sensing flow recommendation method based on logic structure and attribute characteristics |
Non-Patent Citations (3)
| Title |
|---|
| MOHSEN SAYYADIHARIKANDEH.ET AL: "Finding Prerequisite Relations using the Wikipedia Clickstream", WWW \'19: COMPANION PROCEEDINGS OF THE 2019 WORLD WIDE WEB CONFERENCE, pages 1240 * |
| 周洋等: "面向维基百科的概念依赖关系挖掘方法", 重庆大学学报, pages 110 - 120 * |
| 胡成等: "利用维基百科点击流的概念依赖关系识别方法", 小型微型计算机系统, pages 2078 - 2083 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116628351B (en) | 2023-10-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Meng et al. | Semi-supervised software defect prediction model based on tri-training. | |
| CN112035453B (en) | Recommendation method, device and storage medium based on GBDT high-order feature combination | |
| CN110532542B (en) | Invoice false invoice identification method and system based on positive case and unmarked learning | |
| Shu et al. | Incremental feature selection based on rough set in dynamic incomplete data | |
| Qian et al. | Fusing monotonic decision trees | |
| CN111461164B (en) | Sample data set capacity expansion method and model training method | |
| Zou et al. | Text2math: End-to-end parsing text into math expressions | |
| CN110390014B (en) | Theme mining method and device and storage medium | |
| Huang et al. | Efficient business process consolidation: combining topic features with structure matching | |
| Bae et al. | Process mining by measuring process block similarity | |
| CN110110213A (en) | Excavate method, apparatus, computer readable storage medium and the terminal device of user's occupation | |
| Liang et al. | The generic genetic algorithm incorporates with rough set theory–An application of the web services composition | |
| Zaidi et al. | Learning graph representation of bug reports to triage bugs using graph convolution network | |
| Wang et al. | Exploring semantics of software artifacts to improve requirements traceability recovery: a hybrid approach | |
| Daw et al. | Machine learning applications using Waikato environment for knowledge analysis | |
| CN116628351B (en) | Node-dependency-based flow chart branch recommendation method, device and storage device | |
| Dendek et al. | Evaluation of features for author name disambiguation using linear support vector machines | |
| CN116662991A (en) | Intelligent contract intention detection method based on artificial intelligence | |
| CN112988699B (en) | Model training method, and data label generation method and device | |
| Liu et al. | A Bayesian classifier learning algorithm based on optimization model | |
| CN111045716A (en) | Related patch recommendation method based on heterogeneous data | |
| Soni et al. | An fp-growth approach to mining association rules | |
| CN114936220B (en) | Search method and device for Boolean satisfiability problem solution, electronic equipment and medium | |
| Phukon | Incorporation of contextual information through Graph Modeling in Web content mining | |
| CN116502140B (en) | Encryption algorithm identification method and device based on similarity of control flow graphs |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |