CN104462414A - Topological structure based flow chart similarity method - Google Patents
Topological structure based flow chart similarity method Download PDFInfo
- Publication number
- CN104462414A CN104462414A CN201410768419.1A CN201410768419A CN104462414A CN 104462414 A CN104462414 A CN 104462414A CN 201410768419 A CN201410768419 A CN 201410768419A CN 104462414 A CN104462414 A CN 104462414A
- Authority
- CN
- China
- Prior art keywords
- flow chart
- similarity
- mrow
- msub
- bfs
- 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 57
- 239000004576 sand Substances 0.000 claims description 12
- 239000010432 diamond Substances 0.000 claims description 3
- 238000005259 measurement Methods 0.000 abstract description 7
- 238000000691 measurement method Methods 0.000 abstract description 4
- 230000000694 effects Effects 0.000 abstract description 3
- 230000002411 adverse Effects 0.000 abstract 1
- 238000011160 research Methods 0.000 description 7
- 238000002474 experimental method Methods 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000004088 simulation Methods 0.000 description 4
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000004451 qualitative analysis Methods 0.000 description 1
- 238000011524 similarity measure Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000001131 transforming effect Effects 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
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a topological structure based flow chart similarity method and relates to the field of digital image retrieval. The method includes: converting a flow chart into a graph model; constructing a minimum BFS (breadth first search) code tree for the graph model; according to the hierarchical relation of the minimum BFS code tree, weighting nodes and measuring similarity of the flow chart model. All the nodes of the flow chart are weighted according to the hierarchical structure of the minimum BFS code tree corresponding to the flow chart, adverse impact of the low-relevancy nodes on similarity measurement effect is avoided effectively, precision of the flow chart similarity measurement method is improved, meanwhile matching number of the nodes of the flow chart is reduced greatly, time efficiency of the flow chart similarity measurement method is improved, and accordingly the method has high practical value.
Description
Technical Field
The invention relates to the field of digital image retrieval, in particular to a topological structure-based flow chart similarity method.
Background
The flow chart is a graphic description of the flow, process and algorithm, and has wide application in the fields of technical design, communication, scientific research, commercial bulletin and the like, particularly in scientific research, the flow chart is one of the most popular qualitative analysis tools in the aspects of making a research conclusion and describing the conclusion, has stronger intuitiveness and high generalization on scientific research results, and has become a main means for researchers to efficiently search, know and describe the process of the research results. In the face of massive flow chart data, how to quickly and effectively retrieve interesting flow charts and relevant information from massive flow chart data is a research hotspot in artificial intelligence and pattern recognition.
The basic principle of flowchart retrieval is to search the most similar flowchart according to the flowchart to be retrieved provided by the user and feed back the retrieval result to the user, so the core of flowchart retrieval is the similarity measurement technology of the flowcharts, and many scholars successively develop research work on the similarity of the flowcharts. The flow chart similarity method widely adopted at present mainly measures the behavior similarity, the structure similarity and the text similarity, wherein the text similarity measures the similarity of texts of a flow chart model by adopting the ideas of character string editing distance and semantics; the behavior similarity is the similarity of execution semantics of the calculation flow chart model; the structural similarity is based on a graph editing distance method, and the similarity of the flow chart model is calculated by combining the text similarity.
At present, a graph edit distance method is widely applied to flow chart similarity measurement and achieves good effects, and is proposed by S.Nejati and M.Sabetzadeh in the documents of Matching and planning of statistical properties, Proceedings of the 29th international reference on software Engineering,2007, 54-64. The graph edit distance of the method refers to the minimum number of deformation operations required for transforming two graphs into each other, wherein the deformation is completed by node replacement, deletion and addition of edges or nodes, and the like, but the graph edit distance method is an NP-hard problem, the complexity of the graph is rapidly increased along with the increase of the number of nodes of the graph, and the polynomial time O (n) of the lower limit and the upper limit is the polynomial time O (n) of the graph3)□O(n7) The retrieval efficiency is low.
Based on the defects of the classification method, the scheme of the invention provides a flow chart similarity method based on a topological structure, the minimum coding tree is generated by using breadth-first search coding, the hierarchical relation of the nodes in the flow chart is effectively realized, the thought of the topological structure is utilized, the corresponding weight is given according to the hierarchical relation of the nodes, the influence of the nodes with strong correlation on the flow chart similarity is improved, and the efficiency of flow chart similarity measurement is effectively improved.
Disclosure of Invention
The invention aims to provide a similarity measurement method for a flow chart, which can solve the problems that the classification speed of the current supervision classification method is low, the complexity exponentially increases along with the increase of the number of features, and the classification precision is influenced by the features with weak correlation.
The invention provides a flow chart similarity method based on a topological structure, which comprises the following steps:
s1: converting the flow chart into a graph model;
s2: constructing a minimum Breadth First (BFS) coding tree for the graph model;
s3: and according to the hierarchical relationship of the minimum BFS coding tree, giving a weight to the node, and measuring the similarity of the flow chart model.
The method for similarity of flowcharts based on topological structures, wherein the step S1 of converting the flowcharts into the graph model, is performed according to the following steps:
and identifying elements such as rectangles, diamonds, straight lines and arrows of the flow chart, and recording the logical relationship of each element in the flow chart.
The above flowchart similarity method based on the topology structure, wherein the constructing a minimum Breadth First (BFS) coding tree in step S2 is performed according to the following steps:
s2.1: constructing a BFS subscript for the flow chart model;
carrying out breadth-first search on the flow chart model G to generate a breadth-first search tree T, forming a linear sequence according to the traversal sequence of the vertexes of the tree T, and when i is<j, then indicates the vertex ViAt VjIs previously traversed, records this linear sequence using subscripts, and forms a subscript graph GT。
S2.2: establishing BFS codes for the breadth-first search tree of the flow chart model;
for a breadth-first search (BFS) tree of a given graph G, the corresponding BFS encoded BFSCode (G, T) for that breadth-first search tree is represented as a subscripted graph GTOrder of edges eiI-0, …, | E | -1, wherein the sequence EiSatisfy the partial order relation <BTThe conditions of (1): 1) if μ1<ν1And v1<μ2Then e1<BT e2(ii) a 2) If μ1=μ2And v1<ν2Then e1<BT e2(ii) a 3) If e1<BT e2And e2<BT e3Then e1<BT e3。
S2.3: determining a minimum BFS coding tree according to the lexicography order;
for the encoding set S of the flowchart model G ═ { BFSCode (G, T) | T is the BFS tree of the graph G }, if two elements a of the set S ═ BFSCode (G)A,TA)=(a0,a1,…,am) And B ═ BFSCode (G)B,TB)=(b0,b1,…,bn) And if the BFS lexicography order meets the condition: there is r, 0. ltoreq. r.ltoreq.min (m, n), ar=brWhen r is<k is, ak<bk(ii) a The minimum BFS encoding minBFSCode (G) is then represented as the smallest element in the set S (G) according to the BFS lexicography order.
In the above flowchart similarity method based on a topological structure, step S3 is to assign a weight to a node according to the hierarchical relationship of the minimum BFS coding tree, and measure the similarity of the flowchart model, and the method is performed according to the following steps:
s3.1: for matching flow chart FdFinding the node N with the minimum number of layersd;
S3.2: for the flow chart F to be searchedsCalculating all nodes N of the current active layersNode similarity Sim ofnode(Ns,Nd) And weighted similarity Simw(Ns,Nd);
For node Ns∈FsAnd Nd∈FdThe similarity of the nodes is
Wherein, T (N)s) And T (N)d) Representing text in a node, | T (N)s) I and I T (N)d) I represents the length of the text string in the node, d (T (N)s),T(Nd) ) represents the edit distance of the two strings.
The weighted similarity of the sum nodes is
Simw(Ns,Nd)=Wi·Simnode(Ns,Nd)
Wherein,the weight of the ith layer of the flow chart model.
S3.3: selecting weighted similarity Simw(Ns,Nd) The optimal node is used as the optimal matching node;
s3.4: deleting current node NdAnd updating the effective node layer and re-executing Step1 until FdAll nodes in the node are matched;
s3.5: calculate the two flowcharts FsAnd FdSimilarity of each layer of (a);
for the flow chart model FsThe similarity of the ith layer is expressed as
Wherein, | MathchedNode | is the number of matched node pairs.
S3.6: calculate the two flowcharts FsAnd FdThe similarity of (c).
For a given two flow charts FsAnd FdAnd their similarity is the weighted sum of the similarities of the layers, the similarity of the flow chart is represented
Compared with the prior art, the technical scheme of the invention has the following advantages:
(1) the invention divides the hierarchical structure of the flow chart model by using the minimum BFS coding tree method, so that the hierarchy of the flow chart nodes is more obvious, and the measurement of the importance degree of the nodes is facilitated;
(2) according to the method, the weight is given to each layer of nodes according to the influence degree of the nodes on the flow chart similarity measurement, so that the negative influence of the nodes with low correlation degree on the similarity measurement effect is effectively avoided, and the precision of the flow chart similarity measurement method is improved;
(3) simulation experiments show that compared with the existing flow chart similarity method, the method has higher precision and better retrieval efficiency.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flowchart of a topology-based flowchart similarity method in an embodiment of the present invention;
FIG. 2 is a diagram of the results of a comparison experiment of the similarity method A Star algorithm, the exhaustion method and the heuristic method of the present invention with the existing flow chart.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, the flowchart similarity method based on the topology of the present technical solution includes the following steps:
step 1: converting the flow chart into a graph model;
and identifying elements such as rectangles, diamonds, straight lines and arrows of the flow chart, and recording the logical relationship of each element in the flow chart.
Step 2: constructing a minimum Breadth First (BFS) coding tree for the graph model;
(1) constructing a BFS subscript for the flow chart model;
carrying out breadth-first search on the flow chart model G to generate a breadth-first search tree T, forming a linear sequence according to the traversal sequence of the vertexes of the tree T, and when i is<j, then indicates the vertex ViAt VjIs previously traversed, records this linear sequence using subscripts, and forms a subscript graph GT。
(2) Establishing BFS codes for the breadth-first search tree of the flow chart model;
for a breadth-first search (BFS) tree of a given graph G, the corresponding BFS encoded BFSCode (G, T) for that breadth-first search tree is represented as a subscripted graph GTOrder of edges eiI-0, …, | E | -1, wherein the sequence EiSatisfy the partial order relation <BTThe conditions of (1): 1) if μ1<ν1And v1<μ2Then e1<BT e2(ii) a 2) If μ1=μ2And v1<ν2Then e1<BT e2(ii) a 3) If e1<BT e2And e2<BT e3Then e1<BT e3。
(3) Determining a minimum BFS coding tree according to the lexicography order;
for the encoding set S of the flowchart model G ═ { BFSCode (G, T) | T is the BFS tree of the graph G }, if two elements a of the set S ═ BFSCode (G)A,TA)=(a0,a1,…,am) And B ═ BFSCode (G)B,TB)=(b0,b1,…,bn) And if the BFS lexicography order meets the condition: exists r, 0 is less than or equal tor≤min(m,n),ar=brWhen r is<k is, ak<bk(ii) a The minimum BFS encoding minBFSCode (G) is then represented as the smallest element in the set S (G) according to the BFS lexicography order.
And step 3: and according to the hierarchical relationship of the minimum BFS coding tree, giving a weight to the node, and measuring the similarity of the flow chart model.
(1) For matching flow chart FdFinding the node N with the minimum number of layersd;
(2) For the flow chart F to be searchedsCalculating all nodes N of the current active layersNode similarity Sim ofnode(Ns,Nd) And weighted similarity Simw(Ns,Nd);
For node Ns∈FsAnd Nd∈FdThe similarity of the nodes is
Wherein, T (N)s) And T (N)d) Representing text in a node, | T (N)s) I and I T (N)d) I represents the length of the text string in the node, d (T (N)s),T(Nd) ) represents the edit distance of the two strings.
The weighted similarity of the sum nodes is
Simw(Ns,Nd)=Wi·Simnode(Ns,Nd)
Wherein,the weight of the ith layer of the flow chart model.
(3) Selecting weighted similarity Simw(Ns,Nd) The optimal node is used as the optimal matching node;
(4) deleting current node NdAnd updating the effective node layer and re-executing Step1 until FdAll nodes in the node are matched;
(5) calculate the two flowcharts FsAnd FdSimilarity of each layer of (a);
for the flow chart model FsThe similarity of the ith layer is expressed as
Wherein, | MathchedNode | is the number of matched node pairs.
(5) Calculate the two flowcharts FsAnd FdThe similarity of (c).
For a given two flow charts FsAnd FdAnd their similarity is the weighted sum of the similarities of the layers, the similarity of the flow chart is represented
The effectiveness and the practicability of the method are verified through simulation experiments.
Simulation content: three representative flow chart similarity methods are selected to test on the same flow chart set in a comparative experiment mode to verify the effectiveness of the invention. Specifically selected is the A Star method proposed by B.Messmer et al, references specifically "B.Messmer, effective Graphmatching Algorithms for preprocessing Model Graphs, PhD thesis, Switzerland, University of Bern, 1995", exhaustive and heuristic methods proposed by Remco M.Dijkman and Marlon Dumas, references specifically "Graph matching Algorithms for business processing similarity search, Proceedings of the 7th International Conference Business Process Management,2009, 48-63"
Experiment: the flow chart data set used in the experiment is from an image database (PubMed Central) in the fields of biomedicine and life science provided by the United states national library of medicine, and comprises 10 types of flow chart models, each type comprises 10 flow charts, the experiment respectively carries out experiment precision comparison on an A Star method, an exhaustion method, a heuristic method and the method of the invention, the classification result is shown in figure 2, and the simulation result shows that: the method of the invention is higher than the A Star method, the exhaustion method and the heuristic method in precision ratio, recall ratio and time efficiency.
The experimental result shows that the method of the invention is higher than the prior flow chart similarity method in precision ratio, recall ratio and time efficiency.
The method for similarity of flowcharts based on topological structures provided by the embodiment of the present invention is described in detail above, and the principle and the implementation of the present invention are explained in detail herein by applying specific examples, and the description of the above embodiments is only used to help understanding the method and the core idea of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (10)
1. A flow chart similarity method based on a topological structure is characterized by comprising the following steps:
s1: converting the flow chart into a graph model;
s2: constructing a minimum Breadth First (BFS) coding tree for the graph model;
s3: and according to the hierarchical relationship of the minimum BFS coding tree, giving a weight to the node, and measuring the similarity of the flow chart model.
2. The topology based flow chart similarity method according to claim 1, wherein the step S1 of converting the flow chart into the graph model comprises:
and identifying elements such as rectangles, diamonds, straight lines and arrows of the flow chart, and recording the logical relationship of each element in the flow chart.
3. The topology based flow chart similarity method according to claim 1, wherein said step S2, constructing a minimum Breadth First (BFS) coding tree comprises:
s2.1: constructing a BFS subscript for the flow chart model;
s2.2: establishing BFS codes for the breadth-first search tree of the flow chart model;
s2.3: and determining the minimum BFS coding tree according to the lexicographical order.
4. The topology-based flowchart similarity method according to claim 3, wherein the step S2.1 of constructing BFS subscripts for the flowchart model specifically comprises:
carrying out breadth-first search on the flow chart model G to generate a breadth-first search tree T, forming a linear sequence according to the traversal sequence of the vertexes of the tree T, and when i is<j, then indicates the vertex ViAt VjIs previously traversed, records this linear sequence using subscripts, and forms a subscript graph GT。
5. The topology-based flowchart similarity method according to claim 3, wherein the step S2.2 of establishing BFS coding for the breadth-first search tree of the flowchart model further comprises:
for a breadth-first search (BFS) tree of a given graph G, the corresponding BFS encoded BFSCode (G, T) for that breadth-first search tree is represented as a subscripted graph GTOrder of edges eiI-0, …, | E | -1, wherein the sequence EiThe condition that the partial order relation is less than BT is satisfied: 1) if μ1<ν1And v1<μ2Then e1<BT e2(ii) a 2) If μ1=μ2And v1<ν2Then e1<BT e2(ii) a 3) If e1<BT e2And e2<BT e3E is then1<BT e3。
6. The topology-based flow chart similarity method according to claim 3, wherein the step S2.3 of determining the minimum BFS coding tree according to the lexicographical order specifically comprises:
for the encoding set S of the flowchart model G ═ { BFSCode (G, T) | T is the BFS tree of the graph G }, if two elements a of the set S ═ BFSCode (G)A,TA)=(a0,a1,…,am) And B ═ BFSCode (G)B,TB)=(b0,b1,…,bn) And if the BFS lexicography order meets the condition: there is r, 0. ltoreq. r.ltoreq.min (m, n), ar=brWhen r is<k is, ak<bk(ii) a The minimum BFS encoding minBFSCode (G) is then represented as the smallest element in the set S (G) according to the BFS lexicography order.
7. The method according to claim 1, wherein the step S3 of assigning weights to the nodes according to the hierarchical relationship of the minimum BFS coding tree, and measuring the similarity of the flow graph model comprises:
s3.1: for matching flow chart FdFinding the node N with the minimum number of layersd;
S3.2: for the flow chart F to be searchedsCalculating all nodes N of the current active layersNode similarity Sim ofnode(Ns,Nd) And weighted similarity Simw(Ns,Nd);
S3.3: selecting weighted similarity Simw(Ns,Nd) The optimal node is used as the optimal matching node;
s3.4: deleting current node NdAnd updating the valid node level, andstep1 is newly executed until FdAll nodes in the node are matched;
s3.5: calculate the two flowcharts FsAnd FdSimilarity of each layer of (a);
s3.6: calculate the two flowcharts FsAnd FdThe similarity of (c).
8. The topology based flow chart similarity method according to claim 7, wherein said step S3.2, calculating node similarity and weighted similarity comprises:
for node Ns∈FsAnd Nd∈FdThe similarity of the nodes is
Wherein, T (N)s) And T (N)d) Representing text in a node, | T (N)s) I and I T (N)d) I represents the length of the text string in the node, d (T (N)s),T(Nd) ) represents the edit distance of the two strings.
The weighted similarity of the sum nodes is
Simw(Ns,Nd)=Wi·Simnode(Ns,Nd)
Wherein,the weight of the ith layer of the flow chart model.
9. The topology based flow chart similarity method according to claim 7, wherein said step S3.5, calculating the similarity of each layer in the flow chart, comprises:
for the flow chart model FsThe similarity of the ith layer is expressed as
Wherein, | MathchedNode | is the number of matched node pairs.
10. The topology based flow chart similarity method according to claim 7, wherein said step S3.5, calculating the similarity of two flow charts, comprises:
for a given two flow charts FsAnd FdAnd their similarity is the weighted sum of the similarities of the layers, the similarity of the flow chart is represented
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410768419.1A CN104462414A (en) | 2014-12-12 | 2014-12-12 | Topological structure based flow chart similarity method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410768419.1A CN104462414A (en) | 2014-12-12 | 2014-12-12 | Topological structure based flow chart similarity method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN104462414A true CN104462414A (en) | 2015-03-25 |
Family
ID=52908449
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410768419.1A Pending CN104462414A (en) | 2014-12-12 | 2014-12-12 | Topological structure based flow chart similarity method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104462414A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109165669A (en) * | 2018-07-09 | 2019-01-08 | 浙江大学 | Three-dimensional dough sheet model file similarity detection method based on model identification code |
CN109344280A (en) * | 2018-10-13 | 2019-02-15 | 中山大学 | A kind of flow chart search method and system based on graph model |
CN109766940A (en) * | 2018-12-29 | 2019-05-17 | 北京天诚同创电气有限公司 | The method and apparatus for assessing the similarity between multiple sewage disposal systems |
CN110334758A (en) * | 2019-06-28 | 2019-10-15 | 西安理工大学 | The similarity calculating method of graph topological structure based on topological characteristic |
CN116227907A (en) * | 2023-05-06 | 2023-06-06 | 安徽思高智能科技有限公司 | Multi-dimensional RPA flow similarity calculation method based on alignment |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101114291A (en) * | 2007-08-24 | 2008-01-30 | 西安交通大学 | XML document approximate enquiring method based on diversity |
US20140040262A1 (en) * | 2012-08-03 | 2014-02-06 | Adobe Systems Incorporated | Techniques for cloud-based similarity searches |
CN103927613A (en) * | 2014-03-13 | 2014-07-16 | 浙江大学 | Process retrieval system and method |
-
2014
- 2014-12-12 CN CN201410768419.1A patent/CN104462414A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101114291A (en) * | 2007-08-24 | 2008-01-30 | 西安交通大学 | XML document approximate enquiring method based on diversity |
US20140040262A1 (en) * | 2012-08-03 | 2014-02-06 | Adobe Systems Incorporated | Techniques for cloud-based similarity searches |
CN103927613A (en) * | 2014-03-13 | 2014-07-16 | 浙江大学 | Process retrieval system and method |
Non-Patent Citations (1)
Title |
---|
张杰等: "基于BFS树的XML文档图结构相似性计算", 《计算机工程与设计》 * |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109165669A (en) * | 2018-07-09 | 2019-01-08 | 浙江大学 | Three-dimensional dough sheet model file similarity detection method based on model identification code |
CN109344280A (en) * | 2018-10-13 | 2019-02-15 | 中山大学 | A kind of flow chart search method and system based on graph model |
CN109344280B (en) * | 2018-10-13 | 2021-09-17 | 中山大学 | Method and system for retrieving flow chart based on graph model |
CN109766940A (en) * | 2018-12-29 | 2019-05-17 | 北京天诚同创电气有限公司 | The method and apparatus for assessing the similarity between multiple sewage disposal systems |
CN109766940B (en) * | 2018-12-29 | 2024-02-02 | 北京天诚同创电气有限公司 | Method and apparatus for evaluating similarity between multiple sewage treatment systems |
CN110334758A (en) * | 2019-06-28 | 2019-10-15 | 西安理工大学 | The similarity calculating method of graph topological structure based on topological characteristic |
CN116227907A (en) * | 2023-05-06 | 2023-06-06 | 安徽思高智能科技有限公司 | Multi-dimensional RPA flow similarity calculation method based on alignment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
TWI846942B (en) | Machine learning system and method to generate structure for target property | |
Du et al. | Inversecsg: Automatic conversion of 3d models to csg trees | |
CN108388651B (en) | Text classification method based on graph kernel and convolutional neural network | |
Para et al. | Sketchgen: Generating constrained cad sketches | |
WO2023124204A1 (en) | Anti-fraud risk assessment method and apparatus, training method and apparatus, and readable storage medium | |
CN104462414A (en) | Topological structure based flow chart similarity method | |
CN110929951B (en) | Correlation analysis and prediction method for power grid alarm signal | |
WO2023155508A1 (en) | Graph convolutional neural network and knowledge base-based paper correlation analysis method | |
CN109633748B (en) | Seismic attribute optimization method based on improved genetic algorithm | |
CN117131449A (en) | Data management-oriented anomaly identification method and system with propagation learning capability | |
CN108920446A (en) | A kind of processing method of Engineering document | |
CN112860904A (en) | External knowledge-integrated biomedical relation extraction method | |
CN114742208A (en) | Graph pre-training learning method based on contrast learning and counterlearning | |
CN110019796A (en) | A kind of user version information analysis method and device | |
CN117972111A (en) | Knowledge graph-oriented knowledge reasoning method based on-line graph processing technology | |
Patel et al. | Smart adaptive mesh refinement with NEMoSys | |
CN113743453A (en) | Population quantity prediction method based on random forest | |
He et al. | Parallel outlier detection using kd-tree based on mapreduce | |
CN113051408A (en) | Sparse knowledge graph reasoning method based on information enhancement | |
CN117236374A (en) | Layering interpretation method based on fully developed material graph neural network | |
WO2024011979A1 (en) | Pre-trained deep neural network based superconducting material prediction method and apparatus | |
CN111259106A (en) | Relation extraction method combining neural network and feature calculation | |
CN105162648B (en) | Corporations' detection method based on backbone network extension | |
Schwenke et al. | Identifying Informative Nodes in Attributed Spatial Sensor Networks Using Attention for Symbolic Abstraction in a GNN-based Modeling Approach | |
CN116108127A (en) | Document level event extraction method based on heterogeneous graph interaction and mask multi-head attention mechanism |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20150325 |
|
WD01 | Invention patent application deemed withdrawn after publication |