CN116433799B - Flow chart generation method and device based on semantic similarity and sub-graph matching - Google Patents
Flow chart generation method and device based on semantic similarity and sub-graph matching Download PDFInfo
- Publication number
- CN116433799B CN116433799B CN202310698508.2A CN202310698508A CN116433799B CN 116433799 B CN116433799 B CN 116433799B CN 202310698508 A CN202310698508 A CN 202310698508A CN 116433799 B CN116433799 B CN 116433799B
- Authority
- CN
- China
- Prior art keywords
- document
- word
- graph
- sub
- flow chart
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 30
- 239000013598 vector Substances 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 7
- 230000011218 segmentation Effects 0.000 claims description 6
- 238000013507 mapping Methods 0.000 claims description 2
- 230000009977 dual effect Effects 0.000 abstract 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 9
- BQCADISMDOOEFD-UHFFFAOYSA-N Silver Chemical compound [Ag] BQCADISMDOOEFD-UHFFFAOYSA-N 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 229910052709 silver Inorganic materials 0.000 description 2
- 239000004332 silver Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000004801 process automation Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
Classifications
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F8/00—Arrangements for software engineering
- G06F8/10—Requirements analysis; Specification techniques
-
- 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
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The invention discloses a flow chart generation method based on semantic similarity and sub-graph matching, which comprises the following steps: acquiring a user demand document and an RPA project asset library document; calculating the semantic similarity of the user demand document and the RPA project asset library document, and obtaining a top-k sub-graph to be matched according to the semantic similarity from high to low; constructing a query knowledge graph according to a user demand document, and setting a starting node; searching and matching the subgraphs to be matched in the query knowledge graph to obtain a final optimal matching graph, and returning to the corresponding flow chart. The technical scheme of the invention reduces the time of sub-graph matching search traversal, and more accurately generates the flow chart of the current user requirement from dual constraint of semantics and structure.
Description
Technical Field
The invention belongs to the technical field of data processing, and particularly relates to a flow chart generation method and device based on semantic similarity and sub-graph matching.
Background
For execution of business processes, employees currently spend a great deal of time processing Enterprise Resource Planning (ERP), customer Relationship Management (CRM), spreadsheets, and legacy systems, performing manually repeatable tasks such as entering, copying, pasting, extracting, merging, and moving data of large volumes of data from one system to another. It is contemplated that some of these highly structured, routine, and manual tasks may be handled by robots, so that knowledge workers have more time to handle value-added tasks. Robotic Process Automation (RPA) emerges as a software-based solution for automating rule-based business processes that involve routine tasks, structured data, and deterministic results. The flow chart is an important ring in the RPA technology, the flow chart is drawn according to the requirement of a user, and then the execution code is generated according to the flow chart to complete the appointed operation. The flow chart is helpful in determining how things are going and deciding how the process should be improved. And the manual drawing of the flow chart requires longer time and consumes more manpower resources. How to automatically generate a flow chart for the current user demands by utilizing the existing flow charts in the RPA implementation library can save manpower and material resources, greatly improves the efficiency of RPA implementation, and is the direction of current research.
Disclosure of Invention
In view of this, the invention proposes a flow chart generating method based on semantic similarity and sub-graph matching, comprising the following steps:
s1, acquiring a user demand document and an RPA project asset library document;
s2, calculating semantic similarity of the user demand document and the RPA project asset library document, and obtaining a top-k sub-graph to be matched according to the semantic similarity from high to low;
s3, constructing a query knowledge graph according to the user demand document, and setting a starting node;
and S4, searching and matching the subgraphs to be matched in the query knowledge graph to obtain a final optimal matching graph, and returning to the corresponding flow chart.
The invention also provides a flow chart generating device based on semantic similarity and sub-graph matching, which comprises the following steps:
a processor;
a memory having stored thereon a computer program executable on the processor;
the method comprises the steps of generating a flow chart based on semantic similarity and sub-graph matching, wherein the computer program is executed by the processor.
The technical scheme provided by the invention has the beneficial effects that:
according to the technical scheme provided by the invention, the items similar to the current demands in the project library are screened out through semantic similarity by using the demand documents of the users, meanwhile, the demand documents of the users are constructed into small demand graphs, and the small demand graphs are matched with the RPA project asset knowledge graph by using a fuzzy sub-graph matching method, so that the items similar to the current user demand flow structure are found. First, semantic is used for preliminary screening, and then sub-graph matching is used for searching traversal. On one hand, the time for sub-graph matching search traversal is reduced, and on the other hand, the flow chart of the current user requirement is generated more accurately by double constraint from semantics and structure. The flow chart is automatically generated according to the user requirement by using the generation technology, so that the user can directly use or fine tune conveniently, the process of drawing the flow chart is simplified, the manual intervention is greatly reduced, and the RPA efficiency is improved.
Drawings
FIG. 1 is a flow chart of a flow chart generation method based on semantic similarity and sub-graph matching according to an embodiment of the present invention;
FIG. 2 is a knowledge graph of the agricultural online silver flow water downloading user requirements constructed in an embodiment of the invention;
fig. 3 is a diagram of the network silver flow water downloading knowledge of RPA asset library project B company constructed in an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention will be further described with reference to the accompanying drawings.
The invention provides a flow chart generation method based on semantic similarity and sub-graph matching, referring to fig. 1, fig. 1 is a flow chart of a flow chart generation method based on semantic similarity and sub-graph matching, comprising the following steps:
s1, acquiring a user demand document and an RPA project asset library document.
In a further embodiment, the user's demand is a farm bank running water download.
And S2, calculating the semantic similarity of the user demand document and the RPA project asset library document, and obtaining a top-k sub-graph to be matched according to the semantic similarity from high to low.
The method comprises the following steps:
s21, need for userSolving document Q and RPA project asset library user documentAnd performing word segmentation and removing stop words.
In the embodiment, a word segmentation component jieba is used for a user requirement document Q and an RPA project asset library user documentAnd performing word segmentation.
S22, describing the document by using the frequency of word occurrence in the text, and enabling the user' S requirement document Q and RPA project asset library user documentRepresented as a one-dimensional vector.
In this embodiment, the method of normalizing the bag of words model of BOW is used to represent Q and Q, respectively。
S23, learning each word of the user demand document Q and the RPA project asset library user document according to the one-dimensional vector obtained in S22Is a term of similarity, in this vector space, the distance between semantically similar terms is similar.
In this embodiment, each word of the user requirement document Q and the RPA project asset library user document are learned by using a word2vec methodIs a term for each word.
S24, calculating user requirement document Q and RPA project asset library user document by using WMD algorithmThe text similarity between the two documents, the WMD algorithm models the document distance into the combination of the semantic distances of words in the two documents, and word vectors corresponding to any two words in the two documentsThe euclidean distance is found and then summed again. The WMD algorithm is an algorithm that measures the similarity of texts by calculating the distance of words between texts based on word2 vec.
S241, document Q and documentThe number of times of word occurrence in the document Q is normalized, and word frequency +.>Document->The word frequency of the jth word in the list is +.>：
Wherein m and n are respectively the document Q and the document D s The number of words in the medium-sized word,、/>respectively represent document Q and document D s The number of occurrences of the ith word and the jth word;
s242, calculating word i from document Q and word D from document D s The Euclidean distance between two words of word j of (a) is：
wherein , and />The embedded vectors learned for words i and j;
s243, solving the document Q and the RPA project asset library D by using a dynamic programming algorithm s WMD distance of each document:
wherein ,representing the mapping of word i in document Q to document D s Weights of word j in +.>Representing word i and document D in document Q s Distance between words j in (a); notably, the ith word of document Q corresponds to D s The sum of the weight values of all words in a document is equal to +.>Similarly, D s The sum of the weight values of all words of the j-th word of the document mapped to document Q is equal to +.>Wherein the smaller the f-number, the more similar the two documents.
S244, calculating document Q and document D s Similarity of (3):
s245, setting a similarity thresholdAccording to document Q and document D s The similarity of (2) is less than the threshold +.>And (3) the k RPA project asset documents and the knowledge maps and flowcharts corresponding to the k projects.
In a further embodiment, referring to fig. 2 and fig. 3, fig. 2 is a rural online banking water downloading user demand knowledge graph constructed in the embodiment of the present invention, and fig. 3 is an RPA asset library project B company online banking water downloading knowledge graph constructed in the embodiment of the present invention. The user's demand documents include farm bank running water, etc., and project documents that can be matched to similar completions in the RPA asset library, such as company B running water, including construction bank running water and industry bank running water downloads.
S3, constructing a query knowledge graph according to the user demand document, and setting a starting node. As shown in fig. 2, the user's demand is a rural internet banking serial download, and includes the substeps of a rural internet banking U-shield login, a rural internet banking serial export, and a rural internet banking serial data conversion.
And S4, searching and matching the subgraphs to be matched in the query knowledge graph to obtain a final optimal matching graph, and returning to the corresponding flow chart.
S41, searching the best possible matching result of the query knowledge graph in the sub-graph to be matched by using a TALE approximate large graph matching tool.
S42, if the best matching result is searched in the step S41, returning the matched candidate subgraph and the flow chart corresponding to the matched candidate subgraph, and if the best matching result is not searched, executing the step S43.
S43, dividing the graph according to the attribute of the edge of the current starting node as the inclusion relation to obtain a sub-graph set, and repeatedly executing the step S41 and the step S42, wherein the starting node is updated as the tail entity of the current node until the best matching result is obtained or the sub-graph set is empty.
The invention also provides a flow chart generating device based on semantic similarity and sub-graph matching, which comprises the following steps:
a processor;
a memory having stored thereon a computer program executable on the processor;
the method comprises the steps of generating a flow chart based on semantic similarity and sub-graph matching, wherein the flow chart is generated by the computer program when the computer program is executed by the processor.
According to the technical scheme provided by the invention, the similarity between the user demand document and the RPA project asset library document is measured by using a WMD algorithm, and the project similar to the current user demand is found, so that the scope of further searching by using sub-graph matching is reduced, and the efficiency is improved.
The method of matching the graph division with the subgraph is combined, and the optimal matching subgraph is searched iteratively. Searching the best matching subgraph from the RPA project asset knowledge graph by using a fuzzy subgraph matching method, allowing certain nodes to be unmatched and certain edges to be missed by fuzzy subgraph matching, recommending a related flow chart, and manually participating in correcting the flow chart. When the searching is not completed, the concept of edge division of graph division is utilized, the characteristics of the knowledge graph required by the user are considered at the same time, the relationship edge is limited to be 'containing' relationship, sub-graph division is carried out, and then the best matching sub-graph is searched.
The method for matching the semantic similarity and the subgraph is utilized to jointly generate a flow chart: firstly, searching for the first round by using semantic similarity to obtain a history item which is more similar to the user demand, and simultaneously reducing the matching search space of the second wheel diagram; and secondly, carrying out a second round of search by using fuzzy subgraph matching, finding a history item which is similar to the user demand semanteme and structure as an optimal matching item, and finding a corresponding flow chart.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (5)
1. The flow chart generation method based on semantic similarity and sub-graph matching is characterized by comprising the following steps of:
s1, acquiring a user demand document and an RPA project asset library document;
s2, calculating semantic similarity of the user demand document and the RPA project asset library document, and obtaining a top-k sub-graph to be matched according to the semantic similarity from high to low;
the method comprises the following steps:
s21, a requirement document Q of a user and an RPA project asset library user documentPerforming word segmentation and removing stop words;
s22, describing the document by using the frequency of word occurrence in the text, and enabling the user' S requirement document Q and RPA project asset library user documentRepresented as a one-dimensional vector;
s23, learning each word of the user demand document Q and the RPA project asset library user document according to the one-dimensional vector obtained in S22Is a term for each word;
s24, calculating user requirement document Q and RPA project asset library user document by using WMD algorithmText similarity between;
s241, document Q and documentThe number of times of word occurrence in the document Q is normalized, and word frequency +.>Document->The word frequency of the jth word in the list is +.>：
Wherein m and n are the vocabulary numbers in the document Q and the document Ds respectively,、/>the times of occurrence of the ith word and the jth word in the document Q and the document Ds are respectively represented;
s242, calculating the Euclidean distance between the two words of the word i from the document Q and the word j from the document Ds as：
wherein , and />The embedded vectors learned for words i and j;
s243, solving the WMD distance between the document Q and the document Ds by using a dynamic programming algorithm:
where f is the WMD distance between the document Q and the document Ds,weights representing the mapping of word i in document Q to word j in document Ds,/>Representing the distance between word i in document Q and word j in document Ds; notably, the sum of the weight values of all words in a document in which the ith word of the document Q corresponds to Ds is equal to +.>Similarly, the sum of the weight values of all words of the document Q mapped to the jth word of the document in Ds is equal to +.>；
S244, calculating the similarity of the document Q and the document Ds:
s245, setting a similarity thresholdBased on the similarity between the document Q and the document Ds, the result is less than the threshold +.>The knowledge graph and the flow chart corresponding to k RPA project asset documents and k projects;
s3, constructing a query knowledge graph according to the user demand document, and setting a starting node;
s4, searching and matching the subgraphs to be matched in the query knowledge graph to obtain a final optimal matching graph, and returning to the corresponding flow chart;
the method comprises the following steps:
s41, searching the best possible matching result of the query knowledge graph in the sub-graph to be matched by using a TALE approximate large graph matching tool;
s42, if the best matching result is searched, returning the matched candidate subgraph and the flow chart corresponding to the matched candidate subgraph in the step S41, and if the best matching result is not searched, executing the step S43;
s43, dividing the graph according to the attribute of the edge of the current starting node as the inclusion relation to obtain a sub-graph set, and repeatedly executing the step S41 and the step S42, wherein the starting node is updated as the tail entity of the current node until the best matching result is obtained or the sub-graph set is empty.
2. The method for generating a flow chart based on semantic similarity and sub-graph matching according to claim 1, wherein in step S21, the word segmentation component jieba is used for the user' S requirement document Q and RPA project asset library user documentAnd performing word segmentation.
3. The method for generating a flow chart based on semantic similarity and sub-graph matching according to claim 1, wherein in step S22, Q and Q are represented by using a normalized BOW bag-of-word model method, respectively。
4. The flow chart generating method based on semantic similarity and sub-graph matching according to claim 1, wherein in step S23, each word of the user requirement document Q and RPA project asset library user document are learned using word2vec methodIs a term for each word.
5. A flow chart generation apparatus based on semantic similarity and sub-graph matching, the apparatus comprising:
a processor;
a memory having stored thereon a computer program executable on the processor;
wherein the computer program when executed by the processor implements a method of generating a flow chart based on semantic similarity and sub-graph matching as claimed in any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310698508.2A CN116433799B (en) | 2023-06-14 | 2023-06-14 | Flow chart generation method and device based on semantic similarity and sub-graph matching |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310698508.2A CN116433799B (en) | 2023-06-14 | 2023-06-14 | Flow chart generation method and device based on semantic similarity and sub-graph matching |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116433799A CN116433799A (en) | 2023-07-14 |
| CN116433799B true CN116433799B (en) | 2023-08-25 |
Family
ID=87083684
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310698508.2A Active CN116433799B (en) | 2023-06-14 | 2023-06-14 | Flow chart generation method and device based on semantic similarity and sub-graph matching |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116433799B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116628228B (en) * | 2023-07-19 | 2023-09-19 | 安徽思高智能科技有限公司 | RPA flow recommendation method and computer readable storage medium |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110704574A (en) * | 2019-09-03 | 2020-01-17 | 福建省农村信用社联合社 | Method and system for managing bank business demand assets |
| CN111666740A (en) * | 2020-06-22 | 2020-09-15 | 深圳壹账通智能科技有限公司 | Flow chart generation method and device, computer equipment and storage medium |
| CN112836029A (en) * | 2021-01-27 | 2021-05-25 | 润联软件系统(深圳)有限公司 | Graph-based document retrieval method, system and related components thereof |
| WO2021164171A1 (en) * | 2020-02-17 | 2021-08-26 | 平安科技（深圳）有限公司 | Method and apparatus for processing data in knowledge base, and computer device and storage medium |
| CN113641833A (en) * | 2021-08-17 | 2021-11-12 | 同济大学 | Service requirement matching method and device |
| CN114298022A (en) * | 2021-12-03 | 2022-04-08 | 天津大学 | Subgraph matching method for large-scale complex semantic network |
| WO2022088409A1 (en) * | 2020-10-28 | 2022-05-05 | 中国商用飞机有限责任公司北京民用飞机技术研究中心 | Interactive retrieval method and apparatus, and computer device and storage medium |
| CN114780746A (en) * | 2022-04-22 | 2022-07-22 | 润联软件系统(深圳)有限公司 | Knowledge graph-based document retrieval method and related equipment thereof |
| CN115496830A (en) * | 2022-09-29 | 2022-12-20 | 中国银行股份有限公司 | Method and device for generating product demand flow chart |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10162892B2 (en) * | 2011-02-28 | 2018-12-25 | International Business Machines Corporation | Identifying information assets within an enterprise using a semantic graph created using feedback re-enforced search and navigation |
| US8887076B2 (en) * | 2011-11-01 | 2014-11-11 | Aver Informatics Inc. | Software user interface allowing logical expression to be expressed as a flowchart |
| CN109740143B (en) * | 2018-11-28 | 2022-08-23 | 平安科技（深圳）有限公司 | Sentence distance mapping method and device based on machine learning and computer equipment |
| US11593592B2 (en) * | 2020-06-02 | 2023-02-28 | Accenture Global Solutions Limited | Intelligent payment processing platform system and method |
| WO2022087497A1 (en) * | 2020-10-22 | 2022-04-28 | Assent Compliance, Inc. | Multi-dimensional product information analysis, management, and application systems and methods |
-
2023
- 2023-06-14 CN CN202310698508.2A patent/CN116433799B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110704574A (en) * | 2019-09-03 | 2020-01-17 | 福建省农村信用社联合社 | Method and system for managing bank business demand assets |
| WO2021164171A1 (en) * | 2020-02-17 | 2021-08-26 | 平安科技（深圳）有限公司 | Method and apparatus for processing data in knowledge base, and computer device and storage medium |
| CN111666740A (en) * | 2020-06-22 | 2020-09-15 | 深圳壹账通智能科技有限公司 | Flow chart generation method and device, computer equipment and storage medium |
| WO2022088409A1 (en) * | 2020-10-28 | 2022-05-05 | 中国商用飞机有限责任公司北京民用飞机技术研究中心 | Interactive retrieval method and apparatus, and computer device and storage medium |
| CN112836029A (en) * | 2021-01-27 | 2021-05-25 | 润联软件系统(深圳)有限公司 | Graph-based document retrieval method, system and related components thereof |
| CN113641833A (en) * | 2021-08-17 | 2021-11-12 | 同济大学 | Service requirement matching method and device |
| CN114298022A (en) * | 2021-12-03 | 2022-04-08 | 天津大学 | Subgraph matching method for large-scale complex semantic network |
| CN114780746A (en) * | 2022-04-22 | 2022-07-22 | 润联软件系统(深圳)有限公司 | Knowledge graph-based document retrieval method and related equipment thereof |
| CN115496830A (en) * | 2022-09-29 | 2022-12-20 | 中国银行股份有限公司 | Method and device for generating product demand flow chart |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116433799A (en) | 2023-07-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20210019341A1 (en) | Implementing a software action based on machine interpretation of a language input | |
| Miao et al. | Towards unified data and lifecycle management for deep learning | |
| Das et al. | A group incremental feature selection for classification using rough set theory based genetic algorithm | |
| EP3475884B1 (en) | System and method for automated mapping of data types for use with dataflow environments | |
| US11714831B2 (en) | Data processing and classification | |
| Escalante | Automated machine learning—a brief review at the end of the early years | |
| CN116433799B (en) | Flow chart generation method and device based on semantic similarity and sub-graph matching | |
| US20190244094A1 (en) | Machine learning driven data management | |
| Miao et al. | Modelhub: Towards unified data and lifecycle management for deep learning | |
| CN114119058A (en) | User portrait model construction method and device and storage medium | |
| US20220121823A1 (en) | System and method for artificial intelligence driven document analysis, including searching, indexing, comparing or associating datasets based on learned representations | |
| US11599666B2 (en) | Smart document migration and entity detection | |
| US20220405701A1 (en) | Matching past post-approved transactions with past pre-approved transactions using machine learning systems | |
| Panahi et al. | Towards Interactive Debugging of Rule-based Entity Matching. | |
| Anderson et al. | Sample, estimate, tune: Scaling bayesian auto-tuning of data science pipelines | |
| CN116628228B (en) | RPA flow recommendation method and computer readable storage medium | |
| CN113807809A (en) | Method for constructing audit user portrait based on machine learning technology | |
| WO2012174632A1 (en) | Method and apparatus for preference guided data exploration | |
| CN116400910A (en) | Code performance optimization method based on API substitution | |
| CN115309995A (en) | Scientific and technological resource pushing method and device based on demand text | |
| US20220284023A1 (en) | Estimating computational cost for database queries | |
| CN112988699B (en) | Model training method, and data label generation method and device | |
| Hsu et al. | Similarity search over personal process description graph | |
| Eidoon et al. | A vector based method of ontology matching | |
| Lin et al. | An efficient modified Hyperband and trust-region-based mode-pursuing sampling hybrid method for hyperparameter optimization |
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 |