WO2021035588A1 - 生产建模方法、装置和系统 - Google Patents

生产建模方法、装置和系统 Download PDF

Info

Publication number
WO2021035588A1
WO2021035588A1 PCT/CN2019/103129 CN2019103129W WO2021035588A1 WO 2021035588 A1 WO2021035588 A1 WO 2021035588A1 CN 2019103129 W CN2019103129 W CN 2019103129W WO 2021035588 A1 WO2021035588 A1 WO 2021035588A1
Authority
WO
WIPO (PCT)
Prior art keywords
modeling
production
sub
user
graph
Prior art date
Application number
PCT/CN2019/103129
Other languages
English (en)
French (fr)
Inventor
陈雪
李明
Original Assignee
西门子股份公司
西门子（中国）有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 西门子股份公司, 西门子（中国）有限公司 filed Critical 西门子股份公司
Priority to CN201980099505.9A priority Critical patent/CN114258551A/zh
Priority to PCT/CN2019/103129 priority patent/WO2021035588A1/zh
Publication of WO2021035588A1 publication Critical patent/WO2021035588A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling

Definitions

  • the present invention relates to the field of digitalization, in particular to a production modeling method, device and system.
  • Modeling targets include stamping lines, welding lines, painting lines, final assembly lines, or warehouses.
  • the first aspect of the present invention provides a production modeling method, which includes the following steps: S1, converting an existing production model into a map, and extracting the same sub-graphs among multiple existing production model maps; S2, Analyze the modeling intention based on the user's input on the modeling software, capture modeling events to extract the event flow based on the modeling intention; S3, match the subgraph in the database based on the modeling intention event flow, and based on the subgraph
  • the graph recommends the production model related to the subgraph to the user to support the user in modeling.
  • step S1 also includes the following step before the step S1: classifying the existing production model according to the technical field, wherein the step S3 further includes the following step: based on the modeling intent event stream and the technical field Match the sub-pictures in the database.
  • step S2 further includes the following step: removing redundant information other than the event stream in the user's input on the modeling software.
  • the production modeling method further includes the following step: matching the sub-pictures in the database based on the user's selection.
  • step 1 is performed offline, and the steps S2 and S3 are performed online.
  • step 1 also includes the following step: extracting layout information of the production model, the layout information includes the target component and its attribute characteristics and the connection relationship between the target component, wherein the attribute characteristics include name, type, and parameter.
  • the second aspect of the present invention provides a production modeling device, which includes: a conversion device, which converts an existing production model into a map; a map extraction device, which extracts the same patterns among a plurality of existing production model maps Sub-graph; capture device, which analyzes modeling intent based on user input on modeling software, captures modeling events to extract the event flow based on modeling intent; sub-graph matching device, which matches the event flow based on the modeling intent The sub-graph in the database; a recommendation device, which recommends the production model related to the sub-graph to the user based on the sub-graph, so as to support the user in modeling.
  • the production modeling device further includes: a classification device, which classifies existing production models according to technical fields, wherein the graph matching device is also used for the event flow based on the modeling intent and its The technical field matches the subgraph in the database.
  • the production modeling device further includes: a cleaning device that removes redundant information other than the event stream from the user's input on the modeling software.
  • the matching device is further configured to match the sub-pictures in the database based on the user's selection.
  • the atlas extraction device is also used to extract layout information of the production model.
  • the layout information includes the target component and its attribute characteristics and the connection relationship between the target component, wherein the attribute characteristics include name, type, and parameter. .
  • a third aspect of the present invention provides a production modeling system, which includes: a processor; and a memory coupled with the processor, the memory having instructions stored therein, when the instructions are executed by the processor Make the electronic device perform actions, the actions include: S1, converting an existing production model into a map, and extracting the same sub-graphs among multiple existing production model maps; S2, based on the user's modeling software Analyze the modeling intent of the input, capture modeling events to extract the event flow based on the modeling intent; S3, match the sub-graph in the database based on the modeling intent event flow, and recommend the user to the sub-graph based on the sub-graph Figure-related production models to support users in modeling.
  • the action S1 further includes: classifying the existing production model according to the technical field, wherein the action S3 further includes the following step: based on the modeling intent event stream and the technical field matching method. Describe the sub-pictures in the database.
  • the action S2 further includes: removing redundant information other than the event stream in the input of the user on the modeling software.
  • the action matching the sub-pictures in the database based on the user's selection.
  • S1 is executed offline, and the actions S2 and S3 are executed online.
  • the action S1 further includes: extracting layout information of the production model, the layout information including the target component and its attribute characteristics and the connection relationship between the target component, wherein the attribute characteristics include name, type, and parameters.
  • the fourth aspect of the present invention provides a computer program product that is tangibly stored on a computer-readable medium and includes computer-executable instructions that, when executed, cause at least one processor to Perform the method according to the first aspect of the present invention.
  • the fifth aspect of the present invention provides a computer-readable medium on which computer-executable instructions are stored, and when executed, the computer-executable instructions cause at least one processor to perform the method according to the first aspect of the present invention.
  • the production modeling mechanism provided by the present invention can utilize existing production models, so that production models in the same or similar fields can share some common maps.
  • the production modeling mechanism provided by the present invention is more efficient.
  • Fig. 1 is a schematic structural diagram of a production modeling device according to a specific embodiment of the present invention
  • FIG. 2 is a schematic diagram of the map data structure for converting a production model into a map in production modeling according to a specific embodiment of the present invention
  • FIG. 3 is a schematic diagram of extracting the same sub-graphs between the atlases of different existing production models based on the atlas in the production modeling according to a specific embodiment of the present invention
  • FIG. 4 is a schematic diagram of recommending modeling components to users in production modeling according to a specific embodiment of the present invention.
  • Fig. 5 is a schematic diagram of extracting the same subgraphs between the atlases of different existing production models based on the atlas in the production modeling according to another specific embodiment of the present invention
  • Fig. 6 is a schematic diagram of sub-graph matching and recommended production models in production modeling according to a specific embodiment of the present invention.
  • the present invention provides a production-based modeling mechanism that can utilize existing production models to improve production modeling efficiency and avoid resource waste.
  • the production modeling mechanism provided by the present invention is based on modeling software and a graph database.
  • Fig. 1 is a schematic structural diagram of a production modeling device according to a specific embodiment of the present invention.
  • the production modeling device 100 includes a conversion device 110, a capture device 120, a matching device 130, a recommendation device 140, an atlas extraction device 150, a data cleaning device 160, an extraction device 170, a sub-picture matching device 180, and user selection
  • the device 190 and the database DB The device 190 and the database DB.
  • the conversion device 110, the capture device 120, the sub-picture matching device 180, and the matching device 130 are executed based on the application program interface or modeling language of the modeling software, and have information interaction with the modeling software, so they can be embedded in the modeling software in.
  • Other functional modules can be independent of modeling software and can be recognized by various programming software.
  • the above-mentioned functional modules are aimed at different application scenarios. Some perform their predetermined functions offline, and some need to perform online functions online. Among them, offline means that the user is not performing modeling at the same time, and online means that the user is performing modeling at the same time.
  • the user performs modeling based on a modeling software 200
  • the production modeling device 100 calls at least one existing production model according to user needs
  • the conversion device 110 converts the existing production model into a map
  • the capture device 120 captures the user’s Input actions in 200 and use the extraction device 170 to extract the modeling intent
  • the matching device 180 matches the subgraph based on the modeling intent and recommends the production model related to the subgraph in the recommendation device 140, and finally recommends the final model through the matching device 130 .
  • the database DB includes a first database DB 1 and a second database DB 2.
  • the first database DB 1 is used to store the graphs G 1 , G 2 ... G n
  • the second database DB 2 is used to store the sub graphs S 1 , S 2 —S n .
  • the first aspect of the present invention provides a production modeling method.
  • step 1 further includes the following step: extracting layout information of the production model, the layout information including the target component and its attribute characteristics and the connection relationship between the target component, wherein the attribute characteristics include name, type and parameters.
  • the existing production model refers to a production model that has been modeled, and all existing production models M 1 , M 2, ... M n .
  • the conversion device 110 calls at least one existing production model, and extracts the layout information of the production model, including the target component and its attribute characteristics, and the connection relationship between the components.
  • the attribute characteristics include name, type, parameters, and so on.
  • the layout information of these production models is saved in a .csv format for subsequent use.
  • the above table is a production model layout information list, where the layout information includes serial number, target name, target type, previous component, next component and material.
  • the target component with the target name "pipe” has the target type "*.Fluids.Pipe” (liquid pipe), the former component is “A_mixer” (mixer), and the latter component is “Pipe3" (pipe) ,
  • the material of the target component "pipe” is "A1”.
  • the target component with the target name "Line” has the target type "*.MaterialFlow.line” (conveyor belt), the former component is “Capping", and the latter component is “Pipe2".
  • the target The material of the component "Line” is "B1".
  • the target component with the target name "Connector” has the target type "*.MaterialFlow.connector” (material fluid connector), the former component is “Pipe4" (pipe), the latter component is "Tank” (buffer node), The material of the target component "Connector” is "C1".
  • the conversion device 110 is used to convert the layout information of the above-mentioned production model into a map.
  • Fig. 2 is a schematic diagram of a map data structure for converting a production model into a map in production modeling according to a specific embodiment of the present invention.
  • the "component type” is the target node, which represents the component.
  • "Name” and “Processing Time” are characteristic nodes, which represent the characteristic attributes of the component.
  • the value of one component type is "assembly", which has a name parameter whose value is “component m automatic assembly machine”, and the component type also has a processing time, and the value of the processing time parameter is "1 minute”.
  • the value of the other component type is a single-step process, which has a name parameter whose value is "initial test", and the component type also has a processing time, which has a value of "3 minutes”.
  • the relationship of the target node includes the connection relationship, which can also be described as a parameter. For example, the relationship between the two component types in Figure 2 is "has the previous component” and "has the next component”.
  • the existing production model is converted into a map and then stored in the first database DB1, where the first database DB1 is used to store the map of the production model, and multiple maps are stored, such as the first map G 1 , the first map G 2 ... ...The nth spectrum G n .
  • the map extraction device 150 extracts the same sub-maps among the multiple existing production model maps based on the map.
  • the map extraction device 150 has a subgraph map extraction algorithm pre-stored in the map extraction device 150 to find the same subgraph among multiple production model maps.
  • the first pattern G 1 is a first production model map M 1, having a node a, node B, node C, node d and node e.
  • the second graph G 2 is a graph of the second production model M 2 , which has a node a, a node b, a node c, a node d, and a node f.
  • G3 is the third pattern of the third pattern producing model M 3 having a node a, node B, node C, node d, the node e and the node f. Therefore, the same subgraph among the first graph G 1 , the second graph G 2 and the third graph G 3 is extracted by a subgraph pattern extraction algorithm pre-stored in the graph extraction device 150 as the sub graph S 1 .
  • the functions of the conversion device 110 and the map extraction device 150 are performed offline, so as to prepare the data required for the user to reproduce the modeling in peacetime, so as to further improve efficiency.
  • the factory model is composed of nodes, for example, a node represents a station.
  • a node represents a station.
  • the production lines are similar. Although there are bound to be differences, the differences are not big.
  • step S2 is executed, and the capturing device 120 analyzes the modeling intention based on the user's input on the modeling software 200, and captures the modeling event to extract the event stream based on the modeling intention.
  • the purpose of the capturing device 120 is to obtain the user's modeling information, including which components are required for the ongoing modeling operation, and how these components are connected.
  • the capture device 120 captures the input based on the modeling software on the personal computer, wherein the modeling information corresponding to the input includes an event and a screenshot of the modeling software interface when the event occurs, wherein the event is a response to a mouse action, a keyboard action, or a touch
  • the screen action issues a command to the personal computer to operate the modeling software.
  • the capture device 120 decomposes the modeling intention into multiple times according to the input of the personal computer on the modeling software according to the time combined with the positioning of the modeling software interface screenshot, and extracts and generates an event record table, and finally generates an event stream based on the modeling intent .
  • step S2 also includes the following steps: the cleaning device 160 removes redundant information other than the event stream from the user's input on the modeling software. Specifically, the cleaning device 160 will perform some data cleaning operations, such as deleting noise information. , Missing data or combining related data, etc. Then, the extraction device 170 uses a process extraction algorithm to extract the modeling intention of the engineer on the modeling software 200, that is, the model map on the interface of the modeling software 200 that the engineer is on.
  • step S3 is executed.
  • the sub-picture matching device 180 matches the sub-pictures in the database based on the modeling intent event stream, and the recommending device 140 recommends the production model related to the sub-picture to the user based on the sub-picture, so as to support the user to construct mold.
  • the input of the sub-graph matching device 180 is the modeling intent event flow and the sub-graph in the second database DB 2 , and compare the model atlas on the interface of the modeling software 200 that the engineer is working on with the sub-graph in the second database DB 2. and identify whether the sub pattern is modeled in FIG. 2 any second database DB.
  • the user drags two nodes a and b in the modeling software 200, since the same sub-graph is the sub-graph S 1 is extracted and stored in the second database DB 2 , it will be automatically After matching the subgraph S 1 , the recommending device 140 will recommend the node c and the node d on the user interface of the modeling software 200. Finally, if the user is satisfied with the recommended node c and d, the matching means 130 is automatically presented in modeling software interface 200 after the user has input profile subgraph nodes a, b, c and d S 1.
  • the step S1 also includes the following step before the step S1: classifying the existing production model according to the technical field
  • the step S3 also includes the following step: based on the modeling intent event flow and the technical field Match the sub-pictures in the database.
  • the production lines are similar to the same type of automobile factories.
  • the differences are not big. Therefore, they can be divided into one field, so that once the user is on the modeling software
  • the modeling intent of the event flow is to model one of the production lines of a soda filling plant, and then immediately match the subgraph recommendations of the same type, that is, the same type of production line in the soda filling workshop, in the database.
  • the layout information of the production model of the conversion device 110 is converted into a map.
  • one of the production models is transformed into a third graph G3, and the other production model is transformed into a graph G4.
  • the third graph G3 includes six FluidSource nodes, seven Tank nodes, one mixer node, two SingleProc nodes, three line nodes, one Portioner node, one Assembly node, and one Source node.
  • the fourth graph G4 includes two FluidSource nodes, two Tank nodes, one mixer node, one Portioner node, two SingleProc nodes, one Assembly node, and one Drain node.
  • the atlas extraction device 150 extracts the same sub-images between the two production models based on the third atlas G3 and the fourth atlas G4. As shown in FIG. 5, the same sub-images in the third atlas G3 and the fourth atlas G4 are the second sub-images.
  • S2 which includes two FluidSource nodes, two Tank nodes, a mixer node, a Portioner node, and an Assembly node. Among them, FluidSource and Tank are node types, FluidSource is the entrance, Tank is the buffer node area, Assembly is the assembly type, Portioner is the sub-assembly type, and the mixer is the mixing and mixing type.
  • the capturing device 120 analyzes the modeling intention based on the user's input on the modeling software 200 to obtain the user's modeling information, including which components are required for the ongoing modeling operation, and these components are connected.
  • the user's first input f1 on the modeling software 200 is a FliudSource node
  • the second input f1 is to continue to establish a Tank node on the FliudSource node
  • the third input f3 is to continue to establish another FliudSource.
  • the fourth input f4 continues to establish another Tank node on the FliudSource node.
  • the user’s sequential first input f1, second input f2, third input f3, and fourth input f4 on the modeling software 200 are sequentially sent to the matching device 180, and the matching device 180 sequentially inputs the first input f1, the second input f2, and
  • the third input f3 and the fourth input f4 perform recommendation value scoring, and as long as the matching recommendation value of a certain input and a certain subgraph is greater than the recommended value threshold, the subgraph will be pushed.
  • the second database DB2 has a second subgraph S2, a third subgraph S3, a fourth subgraph S4, and so on.
  • the user selection device 190 provides the user with a selection interface, and the matching device 180 matches the sub-pictures in the database based on the user's selection.
  • the step 1 is performed offline, and the steps S2 and S3 are performed online.
  • the second aspect of the present invention provides a production modeling device, which includes: a conversion device, which converts an existing production model into a map; a map extraction device, which extracts the same patterns among a plurality of existing production model maps Sub-graph; capture device, which analyzes modeling intent based on user input on modeling software, captures modeling events to extract the event flow based on modeling intent; sub-graph matching device, which matches the event flow based on the modeling intent The sub-graph in the database; a recommendation device, which recommends the production model related to the sub-graph to the user based on the sub-graph, so as to support the user in modeling.
  • the production modeling device further includes: a classification device, which classifies existing production models according to technical fields, wherein the graph matching device is also used for the event flow based on the modeling intent and its The technical field matches the subgraph in the database.
  • the production modeling device further includes: a cleaning device that removes redundant information other than the event stream from the user's input on the modeling software.
  • the matching device is further configured to match the sub-pictures in the database based on the user's selection.
  • the atlas extraction device is also used to extract layout information of the production model.
  • the layout information includes the target component and its attribute characteristics and the connection relationship between the target component, wherein the attribute characteristics include name, type, and parameter. .
  • a third aspect of the present invention provides a production modeling system, which includes: a processor; and a memory coupled with the processor, the memory having instructions stored therein, when the instructions are executed by the processor Make the electronic device perform actions, the actions include: S1, converting an existing production model into a map, and extracting the same sub-graphs among multiple existing production model maps; S2, based on the user's modeling software Analyze the modeling intent of the input, capture modeling events to extract the event flow based on the modeling intent; S3, match the sub-graph in the database based on the modeling intent event flow, and recommend the user to the sub-graph based on the sub-graph Figure-related production models to support users in modeling.
  • the action S1 further includes: classifying the existing production model according to the technical field, wherein the action S3 further includes the following step: based on the modeling intent event stream and the technical field matching method. Describe the sub-pictures in the database.
  • the action S2 further includes: removing redundant information other than the event stream in the input of the user on the modeling software.
  • the action matching the sub-pictures in the database based on the user's selection.
  • S1 is executed offline, and the actions S2 and S3 are executed online.
  • the action S1 further includes: extracting layout information of the production model, the layout information including the target component and its attribute characteristics and the connection relationship between the target component, wherein the attribute characteristics include name, type, and parameters.
  • the fourth aspect of the present invention provides a computer program product that is tangibly stored on a computer-readable medium and includes computer-executable instructions that, when executed, cause at least one processor to Perform the method according to the first aspect of the present invention.
  • the fifth aspect of the present invention provides a computer-readable medium on which computer-executable instructions are stored, and when executed, the computer-executable instructions cause at least one processor to perform the method according to the first aspect of the present invention
  • the help files and small examples provided by the modeling software can only help users to know the basic operations of the modeling software.
  • the modeling mechanism provided by the present invention can provide a model map of the target industry field, which is more effective, smoother and more convenient.
  • the production modeling mechanism provided by the present invention can utilize existing production models, so that production models in the same or similar fields can share some common maps.
  • the present invention provides a way to effectively extract the values in these models, and applies the extracted knowledge in the process of guiding the modeling.

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Educational Administration (AREA)
  • Game Theory and Decision Science (AREA)
  • Development Economics (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

一种生产建模方法、装置和系统，该方法包括如下步骤：S1，将现有的生产模型转化为图谱，提取多个现有的生产模型图谱之间相同的子图；S2，基于用户在建模软件上的输入分析建模意图，捕捉建模事件以提取基于建模意图的事件流；S3，基于所述建模意图事件流匹配数据库中的子图，并基于子图向用户推荐与该子图相关的生产模型，以支持用户进行建模。所提供的生产建模机制能够利用现有的生产模型，以使得相同或者相似领域的生产模型能够共享一些共同的图谱。所提供的生产建模机制效率更高。

Description

生产建模方法、装置和系统 技术领域
本发明涉及数字化领域，尤其涉及生产建模方法、装置和系统。
背景技术
工厂建立生产模型是实现生产数字化的关键步骤。为了建立生产模型，不仅需要学习建模软件的建模指令，还需要学习目标工业的领域知识，例如汽车工业、饮食业、离散制造行业，甚至包括目标生产阶段的领域知识，例如在汽车工业中，建模目标包括冲压线、焊装线、涂装线、总装线，或者仓库。
现有建模方案的问题在于知识资源的浪费。一方面已经存在一些特定领域的模型，要利用这些现存模型支持建模过程会大大减少工程师的学习时间，并提高建模效率。
发明内容
本发明第一方面提供了一种生产建模方法，其中，包括如下步骤：S1，将现有的生产模型转化为图谱，提取多个现有的生产模型图谱之间相同的子图；S2，基于用户在建模软件上的输入分析建模意图，捕捉建模事件以提取基于建模意图的事件流；S3，基于所述建模意图事件流匹配所述数据库中的子图，并基于子图向用户推荐与该子图相关的生产模型，以支持用户进行建模。
进一步地，所述步骤S1之前还包括如下步骤：对现有的生产模型按照技术领域进行分类，其中，所述步骤S3还包括如下步骤：基于所述建模意图事件流及其所述技术领域匹配所述数据库中的子图。
进一步地，所述步骤S2还包括如下步骤：去除用户在建模软件上的输入中除所述事件流以外的冗余信息。
进一步地，所述生产建模方法还包括如下步骤：基于用户的选择匹配所述所述数据库中的子图。
进一步地，所述步骤1是在线下执行的，所述步骤S2和步骤S3是线上执行的。
进一步地，所述步骤1还包括如下步骤：提取生产模型的布局信息，所述布局信息包括目标组件及其属性特征和目标组件之间的连接关系，其中，所述属性特征包括名称、类型和参数。
本发明第二方面提供了一种生产建模装置，其中，包括：转换装置，其将现有的生产模型转化为图谱；图谱提取装置，其提取多个现有的生产模型图谱之间相同的子图；捕捉装置，其基于用户在建模软件上的输入分析建模意图，捕捉建模事件以提取基于建模意图的事件流；子图匹配装置，其基于所述建模意图事件流匹配所述数据库中的子图；推荐装置，其基于子图向用户推荐与该子图相关的生产模型，以支持用户进行建模。
进一步地，所述生产建模装置还包括：分类装置，其对现有的生产模型按照技术领域进行分类，其中，所述图匹配装置还用于基于所述建模意图事件流及其所述技术领域匹配所述数据库中的子图。
进一步地，所述生产建模装置还包括：清理装置，其去除用户在建模软件上的输入中除所述事件流以外的冗余信息。
进一步地，所述匹配装置还用于基于用户的选择匹配所述所述数据库中的子图。
进一步地，所述图谱提取装置还用于提取生产模型的布局信息，所述布局信息包括目标组件及其属性特征和目标组件之间的连接关系，其中，所述属性特征包括名称、类型和参数。
本发明第三方面提供了一种生产建模系统，其中，包括：处理器；以及与所述处理器耦合的存储器，所述存储器具有存储于其中的指令，所述指令在被处理器执行时使所述电子设备执行动作，所述动作包括：S1，将现有的生产模型转化为图谱，提取多个现有的生产模型图谱之间相同的子图；S2，基于用户在建模软件上的输入分析建模意图，捕捉建模事件以提取基于建模意图的事件流；S3，基于所述建模意图事件流匹配所述数据库中的子图，并基于子图向用户推荐与该子图相关的生产模型，以支持用户进行建模。
进一步地，所述动作S1之前还包括：对现有的生产模型按照技术领 域进行分类，其中，所述动作S3还包括如下步骤：基于所述建模意图事件流及其所述技术领域匹配所述数据库中的子图。
进一步地，所述动作S2还包括：去除用户在建模软件上的输入中除所述事件流以外的冗余信息。
进一步地，所述动作：基于用户的选择匹配所述所述数据库中的子图。
进一步地，S1是在线下执行的，所述动作S2和动作S3是线上执行的。
进一步地，所述动作S1还包括：提取生产模型的布局信息，所述布局信息包括目标组件及其属性特征和目标组件之间的连接关系，其中，所述属性特征包括名称、类型和参数。
本发明第四方面提供了一种计算机程序产品，所述计算机程序产品被有形地存储在计算机可读介质上并且包括计算机可执行指令，所述计算机可执行指令在被执行时使至少一个处理器执行根据本发明第一方面所述的方法。
本发明第五方面提供了计算机可读介质，其上存储有计算机可执行指令，所述计算机可执行指令在被执行时使至少一个处理器执行根据本发明第一方面所述的方法。
本发明提供的生产建模机制能够利用现有的生产模型，以使得相同或者相似领域的生产模型能够共享一些共同的图谱。本发明提供的生产建模机制效率更高。
附图说明
图1是根据本发明一个具体实施例的生产建模装置的结构示意图；
图2是根据本发明一个具体实施例的生产建模中将生产模型转化为图谱的图谱数据结构示意图；
图3是根据本发明一个具体实施例的生产建模中基于所述图谱提取不同现有生产模型的图谱之间相同的子图的示意图；
图4是根据本发明一个具体实施例的生产建模中给用户推荐建模组件的示意图；
图5是根据本发明又一具体实施例的生产建模中基于所述图谱提 取不同现有生产模型的图谱之间相同的子图的示意图；
图6是根据本发明一个具体实施例的生产建模中子图匹配和推荐生产模型的示意图。
具体实施方式
以下结合附图，对本发明的具体实施方式进行说明。
本发明提供了一种能够利用现有生产模型进行基于生产的建模机制，以提高生产建模效率，并避免资源浪费。本发明提供的生产建模机制基于建模软件和图谱数据库。
图1是根据本发明一个具体实施例的生产建模装置的结构示意图。如图1所示，生产建模装置100包括转换装置110、捕捉装置120、匹配装置130、推荐装置140、图谱提取装置150、数据清理装置160、提取装置170、子图匹配装置180和用户选择装置190以及数据库DB。其中，转换装置110、捕捉装置120、子图匹配装置180和匹配装置130是基于建模软件的应用程序界面或者建模语言执行的，并且和建模软件有信息交互，因此可以嵌入建模软件中。其他功能模块可以独立于建模软件以外，并且能够被各种编程软件识别。上述功能模块针对不同的应用场景，有的在线下执行其既定功能，有的需要线上执行在线功能。其中，线下是指并没有在用户执行建模同时，线上是指用户执行建模同时。
用户基于一个建模软件200执行建模，生产建模装置100根据用户需求调用现有的至少一个生产模型，转换装置110将现有的生产模型转换为图谱，捕捉装置120捕捉用户在建模软件200中的输入动作并利用提取装置170提取建模意图，然后匹配装置180基于建模意图匹配子图并在推荐装置140中推荐与该子图相关的生产模型，最后通过匹配装置130推荐最终模型。其中，数据库DB包括第一数据库DB 1和第二数据库DB 2，第一数据库DB 1用于存储图谱G 1、G 2……G n，第二数据库DB 2用于存储子图S 1、S 2……S n。
本发明第一方面提供了一种生产建模方法。
首先执行S1，转换装置110将现有的生产模型转化为图谱，图谱提取装置150基于所述图谱提取不同现有生产模型之间相同的子图。所述步骤1还包括如下步骤：提取生产模型的布局信息，所述布局信息包括 目标组件及其属性特征和目标组件之间的连接关系，其中，所述属性特征包括名称、类型和参数。
具体地，现有的生产模型是指已经建模完成的生产模型，将所有现有的生产模型M 1、M 2……M n。转换装置110调用至少一个现有的生产模型，提取该生产模型的布局信息，包括目标组件及其属性特征、组件之间的连接关系。所述属性特征包括名称、类型、参数等。示例性地，这些生产模型的布局信息被保存为.csv格式以供后续使用。
表1生产模型布局信息列表
序号 目标名称 目标类型 前一组件 后一组件 材料
1 Pipe *.Fluids.Pipe A_mixer Pipe3 A1
2 Line *.MaterialFlow.line Capping Pipe2 B1
3 Connector *.MaterialFlow.connector Pipe4 Tank C1
上表为一个生产模型布局信息列表，其中布局信息包括序号、目标名称、目标类型、前一组件、后一组件和材料。具体地，目标名称为“pipe”的目标组件具有目标类型“*.Fluids.Pipe”(液体管)，其前一组件为“A_mixer”(混合器)，后一组件为“Pipe3”(管道)，所述目标组件“pipe”的材料为“A1”。目标名称为“Line”的目标组件具有目标类型“*.MaterialFlow.line”(传送带)，其前一组件为“Capping”(封盖)，后一组件为“Pipe2”(管道)，所述目标组件“Line”的材料为“B1”。目标名称为“Connector”的目标组件具有目标类型“*.MaterialFlow.connector”(材料流体连接件)，其前一组件为“Pipe4”(管道)，后一组件为“Tank”(缓冲节点)，所述目标组件“Connector”的材料为“C1”。
转换装置110用于将上述生产模型的布局信息转化为图谱。图2是根据本发明一个具体实施例的生产建模中将生产模型转化为图谱的图谱数据结构示意图。如图2所示，“组件类型”是目标节点，代表组件。“名称”和“处理时间”为特征节点，代表该组件的特征属性。其中一个组件类型的数值为“组装”，其具有名称参数，该名称参数的值为“部件m自动组装机”，组件类型还具有处理时间，该处理时间参数的值为“1分钟”。另一个组件类型的数值为单步工艺，其具有名称参数，该名称参数的值为“初始测试”，组件类型还具有处理时间，该处理时间参数的值为 “3分钟”。？此外，目标节点的关系包括连接关系，也可以被描述为参数。例如，图2中两个组件类型的关系就是“具有前一个组件”“具有后一个组件”。
现有的生产模型转化为图谱后被存储于第一数据库DB1，其中第一数据库DB1用于存储生产模型的图谱，其中存储有多个图谱，例如第一图谱G 1、第一图谱G 2……第n图谱G n。
然后图谱提取装置150基于所述图谱提取多个现有的生产模型图谱之间相同的子图。图谱提取装置150中预存有子图(subgraph)图谱提取算法寻找多个生产模型图谱之间相同的子图。如图3所示，第一图谱G 1为第一生产模型M 1的图谱，其具有节点a、节点b、节点c、节点d和节点e。第二图谱G 2为第二生产模型M 2的图谱，其具有节点a、节点b、节点c、节点d和节点f。第三图谱G3为第三生产模型M 3的图谱，其具有节点a、节点b、节点c、节点d、节点e和节点f。因此，经过图谱提取装置150中预存有子图(subgraph)图案提取算法提取得到第一图谱G 1、第二图谱G 2和第三图谱G 3之间相同的子图为子图S 1。
需要说明得是，多个现有的生产模型经过图谱提取装置150迭代提取相同的子图，获得了多个子图，并将每一次针对不同生产模型的图谱提取的子图存储于第二数据库DB 2。
根据本发明一个优选实施例，转换装置110和图谱提取装置150功能的执行是在线下的，以在平时就将用户需要重新生产建模所需的数据做好准备，以进一步提升效率。
此外，工厂模型都是由一个个节点组成，例如一个节点代表一个工位。比如不同的汽车工厂虽然有多条生产线，但是对相同类型的汽车工厂来说生产线大同小异，虽然必然有区别，但是区别不大。
然后执行步骤S2，捕捉装置120基于用户在建模软件200上的输入分析建模意图，捕捉建模事件以提取基于建模意图的事件流。捕捉装置120的目标是获取用户的建模信息，包括正在进行的建模操作需要哪些组件，这些组件之间是如何连接的。
具体地，捕捉装置120捕捉个人电脑上基于建模软件的输入，其中输入对应的建模信息包括事件以及事件发生时的建模软件界面截屏，其中所述事件为响应鼠标动作、键盘动作或者触屏动作对所述个人电脑发 出操作所述建模软件的命令。捕捉装置120将个人电脑在建模软件上的输入按照时间结合建模软件界面截屏的定位将建模意图分解为多个时间，并提取并生成事件记录表，最后生成基于建模意图的事件流。
由于现有的生产模型在人工建模的过程中必然包括很多重复操作或者来回修正操作，这些不必要的操作变成了噪声数据，噪声数据是冗余信息。因此需要对事件流的冗余信息执行去除操作。因此，步骤S2还包括如下步骤：清理装置160去除用户在建模软件上的输入中除所述事件流以外的冗余信息，具体地，清理装置160会执行一些数据清理操作，例如删除噪声信息、缺失数据或者结合相关数据等。然后，提取装置170利用过程提取算法提取工程师正在建模软件200上的建模意图，也就是工程师正在建模软件200界面上的模型图谱。
最后执行步骤S3，子图匹配装置180基于所述建模意图事件流匹配所述数据库中的子图，推荐装置140基于子图向用户推荐与该子图相关的生产模型，以支持用户进行建模。
具体地，子图匹配装置180的输入为建模意图事件流和第二数据库DB 2中的子图，比较工程师正在建模软件200界面上的模型图谱和第二数据库DB 2中的子图，并识别正在建模的图谱是否是任何第二数据库DB 2中的子图。如图4所示，如果用户在建模软件200中拖拽了两个节点a和b，由于相同的子图为子图S 1被提取并存储于第二数据库DB 2，此时就会自动匹配子图S 1，然后推荐装置140就会在建模软件200的用户界面上推荐节点c和节点d。最后，如果用户对于推荐的节点c和d很满意，匹配装置130则会在用户输入确认信息以后自动在建模软件200界面中呈现具有节点a、b、c和d的子图S 1。
特别地，所述步骤S1之前还包括如下步骤：对现有的生产模型按照技术领域进行分类，其中，所述步骤S3还包括如下步骤：基于所述建模意图事件流及其所述技术领域匹配所述数据库中的子图。例如，比如不同的汽车工厂虽然有多条生产线，但是对相同类型的汽车工厂来说生产线大同小异，虽然必然有区别，但是区别不大，因此可以分为一个领域，这样用户一旦在建模软件上的建模意图事件流执行的是针对一个汽水灌装工厂的其中一个生产线建模，则立刻在数据库中匹配相同类型即汽水灌装车间的同类生产线的子图推荐。
具体地，根据本发明的一个优选实施例，转换装置110生产模型的布局信息转化为图谱。如图5所示，其中一个生产模型转化为的图谱为第三图谱G3，另一个生产模型转化为的图谱为G4。其中，第三图谱G3包括六个FluidSource节点、七个Tank节点、一个mixer节点、两个SingleProc节点、三个line节点、一个Portioner节点、一个Assembly节点和一个Source节点。第四图谱G4包括两个FluidSource节点、两个Tank节点、一个mixer节点、一个Portioner节点、两个SingleProc节点、一个Assembly节点和一个Drain节点。虽然第三图谱G3和第四图谱G4有相同的节点，但是各个节点之间的连接关系虽然有相同的部分，但是不完全相同。图谱提取装置150基于第三图谱G3和第四图谱G4提取两个生产模型之间相同的子图，如图5所示，第三图谱G3和第四图谱G4相同的子图是第二子图S2，其包括两个FluidSource节点，两个Tank节点，一个mixer节点、一个Portioner节点和一个Assembly节点。其中，FluidSource和Tank都是节点类型，FluidSource是入口，Tank为缓冲节点区，Assembly是组装类，Portioner是分装类，mixer是混合搅拌。
捕捉装置120基于用户在建模软件200上的输入分析建模意图，以获取用户的建模信息，包括正在进行的建模操作需要哪些组件，这些组件之间是连接关系。如图6所示，用户在建模软件200上的第一输入f1为一个FliudSource节点，第二输入f1为在FliudSource节点上继续建立了一个Tank节点，第三输入f3为继续建立了另外一个FliudSource节点，第四输入f4 FliudSource节点上继续建立了另一个Tank节点。用户在建模软件200上的依次第一输入f1、第二输入f2、第三输入f3和第四输入f4依次送入匹配装置180，匹配装置180依次对第一输入f1、第二输入f2、第三输入f3和第四输入f4进行推荐值打分，只要某一输入和某一子图的匹配推荐值大于推荐值阈值则推送该子图。例如，针对第二子图S2，匹配装置180给第一输入f1推荐值d1＝0.077，匹配装置180给第二输入f2推荐值d2＝0.231，匹配装置180给第三输入f3推荐值d3＝0.308，匹配装置180给第四输入f4推荐值d4＝0.462，当匹配装置180得到推荐值d4＝0.462后判断d4大于子图S2的推荐阈值，则推送子图S2，并从第二数据库DB2中调取子图S2，最后推荐装置140中推荐与第二子图S2相关的生产模型给用户。其中，第二数据库DB2中具有第二子图S2，第 三子图S3，第四子图S4等。
进一步地，用户选择装置190给用户提供了选择界面，匹配装置180基于用户的选择匹配所述所述数据库中的子图。
优选地，所述步骤1是在线下执行的，所述步骤S2和步骤S3是线上执行的。
本发明第二方面提供了一种生产建模装置，其中，包括：转换装置，其将现有的生产模型转化为图谱；图谱提取装置，其提取多个现有的生产模型图谱之间相同的子图；捕捉装置，其基于用户在建模软件上的输入分析建模意图，捕捉建模事件以提取基于建模意图的事件流；子图匹配装置，其基于所述建模意图事件流匹配所述数据库中的子图；推荐装置，其基于子图向用户推荐与该子图相关的生产模型，以支持用户进行建模。
进一步地，所述生产建模装置还包括：分类装置，其对现有的生产模型按照技术领域进行分类，其中，所述图匹配装置还用于基于所述建模意图事件流及其所述技术领域匹配所述数据库中的子图。
进一步地，所述生产建模装置还包括：清理装置，其去除用户在建模软件上的输入中除所述事件流以外的冗余信息。
进一步地，所述匹配装置还用于基于用户的选择匹配所述所述数据库中的子图。
进一步地，所述图谱提取装置还用于提取生产模型的布局信息，所述布局信息包括目标组件及其属性特征和目标组件之间的连接关系，其中，所述属性特征包括名称、类型和参数。
本发明第三方面提供了一种生产建模系统，其中，包括：处理器；以及与所述处理器耦合的存储器，所述存储器具有存储于其中的指令，所述指令在被处理器执行时使所述电子设备执行动作，所述动作包括：S1，将现有的生产模型转化为图谱，提取多个现有的生产模型图谱之间相同的子图；S2，基于用户在建模软件上的输入分析建模意图，捕捉建模事件以提取基于建模意图的事件流；S3，基于所述建模意图事件流匹配所述数据库中的子图，并基于子图向用户推荐与该子图相关的生产模型，以支持用户进行建模。
进一步地，所述动作S1之前还包括：对现有的生产模型按照技术领 域进行分类，其中，所述动作S3还包括如下步骤：基于所述建模意图事件流及其所述技术领域匹配所述数据库中的子图。
进一步地，所述动作S2还包括：去除用户在建模软件上的输入中除所述事件流以外的冗余信息。
进一步地，所述动作：基于用户的选择匹配所述所述数据库中的子图。
进一步地，S1是在线下执行的，所述动作S2和动作S3是线上执行的。
进一步地，所述动作S1还包括：提取生产模型的布局信息，所述布局信息包括目标组件及其属性特征和目标组件之间的连接关系，其中，所述属性特征包括名称、类型和参数。
本发明第四方面提供了一种计算机程序产品，所述计算机程序产品被有形地存储在计算机可读介质上并且包括计算机可执行指令，所述计算机可执行指令在被执行时使至少一个处理器执行根据本发明第一方面所述的方法。
本发明第五方面提供了计算机可读介质，其上存储有计算机可执行指令，所述计算机可执行指令在被执行时使至少一个处理器执行根据本发明第一方面所述的方法
建模软件提供的帮助文件和小实例仅仅能够帮助用户知道建模软件的基本操作。为了建立一个更有效率的生产模型，用户需要知道许多目标产业的领域知识。本发明提供的建模机制能够提供目标产业领域的模型图谱，其更有效更顺利更便捷。
本发明提供的生产建模机制能够利用现有的生产模型，以使得相同或者相似领域的生产模型能够共享一些共同的图谱。本发明提供了有效提取这些模型中的数值的方式，在指导建模过程中应用了这些提取的知识。
尽管本发明的内容已经通过上述优选实施例作了详细介绍，但应当认识到上述的描述不应被认为是对本发明的限制。在本领域技术人员阅读了上述内容后，对于本发明的多种修改和替代都将是显而易见的。因此，本发明的保护范围应由所附的权利要求来限定。此外，不应将权利要求中的任何附图标记视为限制所涉及的权利要求；“包括”一词不排除 其它权利要求或说明书中未列出的装置或步骤；“第一”、“第二”等词语仅用来表示名称，而并不表示任何特定的顺序。

Claims (19)

  1. 生产建模方法，其中，包括如下步骤：
    S1，将现有的生产模型转化为图谱，提取多个现有的生产模型图谱之间相同的子图；
    S2，基于用户在建模软件上的输入分析建模意图，捕捉建模事件以提取基于建模意图的事件流；
    S3，基于所述建模意图事件流匹配所述数据库中的子图，并基于子图向用户推荐与该子图相关的生产模型，以支持用户进行建模。
  2. 根据权利要求1所述的生产建模方法，其特征在于，所述步骤S1之前还包括如下步骤：
    对现有的生产模型按照技术领域进行分类，
    其中，所述步骤S3还包括如下步骤：
    基于所述建模意图事件流及其所述技术领域匹配所述数据库中的子图。
  3. 根据权利要求1所述的生产建模方法，其特征在于，所述步骤S2还包括如下步骤：
    去除用户在建模软件上的输入中除所述事件流以外的冗余信息。
  4. 根据权利要求1所述的生产建模方法，其特征在于，所述生产建模方法还包括如下步骤：基于用户的选择匹配所述所述数据库中的子图。
  5. 根据权利要求1所述的生产建模方法，其特征在于，所述步骤1是在线下执行的，所述步骤S2和步骤S3是线上执行的。
  6. 根据权利要求1所述的生产建模方法，其特征在于，所述步骤1还包括如下步骤：
    提取生产模型的布局信息，所述布局信息包括目标组件及其属性特征和目标组件之间的连接关系，其中，所述属性特征包括名称、类型和参数。
  7. 生产建模装置，其中，包括：
    转换装置，其将现有的生产模型转化为图谱；
    图谱提取装置，其提取多个现有的生产模型图谱之间相同的子图；
    捕捉装置，其基于用户在建模软件上的输入分析建模意图，捕捉建 模事件以提取基于建模意图的事件流；
    子图匹配装置，其基于所述建模意图事件流匹配所述数据库中的子图；
    推荐装置，其基于子图向用户推荐与该子图相关的生产模型，以支持用户进行建模。
  8. 根据权利要求7所述的生产建模装置，其特征在于，所述生产建模装置还包括：
    分类装置，其对现有的生产模型按照技术领域进行分类，
    其中，所述图匹配装置还用于基于所述建模意图事件流及其所述技术领域匹配所述数据库中的子图。
  9. 根据权利要求7所述的生产建模装置，其特征在于，所述生产建模装置还包括：
    数据清理装置，其去除用户在建模软件上的输入中除所述事件流以外的冗余信息。
  10. 根据权利要求7所述的生产建模装置，其特征在于，所述匹配装置还用于基于用户的选择匹配所述所述数据库中的子图。
  11. 根据权利要求7所述的生产建模装置，其特征在于，所述图谱提取装置还用于提取生产模型的布局信息，所述布局信息包括目标组件及其属性特征和目标组件之间的连接关系，其中，所述属性特征包括名称、类型和参数。
  12. 生产建模系统，其中，包括：
    处理器；以及
    与所述处理器耦合的存储器，所述存储器具有存储于其中的指令，所述指令在被处理器执行时使所述电子设备执行动作，所述动作包括：
    S1，将现有的生产模型转化为图谱，提取多个现有的生产模型图谱之间相同的子图；
    S2，基于用户在建模软件上的输入分析建模意图，捕捉建模事件以提取基于建模意图的事件流；
    S3，基于所述建模意图事件流匹配所述数据库中的子图，并基于子图向用户推荐与该子图相关的生产模型，以支持用户进行建模。
  13. 根据权利要求12所述的生产建模系统，其特征在于，所述动作S1之前还包括：
    对现有的生产模型按照技术领域进行分类，
    其中，所述动作S3还包括如下步骤：
    基于所述建模意图事件流及其所述技术领域匹配所述数据库中的子图。
  14. 根据权利要求12所述的生产建模系统，其特征在于，所述动作S2还包括：
    去除用户在建模软件上的输入中除所述事件流以外的冗余信息。
  15. 根据权利要求12所述的生产建模系统，其特征在于，所述动作：基于用户的选择匹配所述所述数据库中的子图。
  16. 根据权利要求12所述的生产建模系统，其特征在于，所述动作S1是在线下执行的，所述动作S2和动作S3是线上执行的。
  17. 根据权利要求12所述的生产建模系统，其特征在于，所述动作S1还包括：
    提取生产模型的布局信息，所述布局信息包括目标组件及其属性特征和目标组件之间的连接关系，其中，所述属性特征包括名称、类型和参数。
  18. 计算机程序产品，所述计算机程序产品被有形地存储在计算机可读介质上并且包括计算机可执行指令，所述计算机可执行指令在被执行时使至少一个处理器执行根据权利要求1至6中任一项所述的方法。
  19. 计算机可读介质，其上存储有计算机可执行指令，所述计算机可执行指令在被执行时使至少一个处理器执行根据权利要求1至6中任一项所述的方法。
PCT/CN2019/103129 2019-08-28 2019-08-28 生产建模方法、装置和系统 WO2021035588A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN201980099505.9A CN114258551A (zh) 2019-08-28 2019-08-28 生产建模方法、装置和系统
PCT/CN2019/103129 WO2021035588A1 (zh) 2019-08-28 2019-08-28 生产建模方法、装置和系统

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2019/103129 WO2021035588A1 (zh) 2019-08-28 2019-08-28 生产建模方法、装置和系统

Publications (1)

Publication Number Publication Date
WO2021035588A1 true WO2021035588A1 (zh) 2021-03-04

Family

ID=74683314

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/103129 WO2021035588A1 (zh) 2019-08-28 2019-08-28 生产建模方法、装置和系统

Country Status (2)

Country Link
CN (1) CN114258551A (zh)
WO (1) WO2021035588A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116954587B (zh) * 2023-09-19 2023-12-19 中电科大数据研究院有限公司 前端智能拖拽引擎、建立数据处理流程的方法

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101493764A (zh) * 2008-01-22 2009-07-29 江苏省金思维信息技术有限公司 企业业务流程可视化动态建模与功能操作联动方法
CN102650995A (zh) * 2011-02-25 2012-08-29 中国银联股份有限公司 多维数据分析模型生成系统及方法
CN105718471A (zh) * 2014-12-03 2016-06-29 中国科学院声学研究所 用户偏好建模方法、系统及用户偏好评估方法、系统
CN107301166A (zh) * 2017-02-13 2017-10-27 上海大学 面向跨领域进行信息抽取的多层次特征模型和特征评价方法

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101493764A (zh) * 2008-01-22 2009-07-29 江苏省金思维信息技术有限公司 企业业务流程可视化动态建模与功能操作联动方法
CN102650995A (zh) * 2011-02-25 2012-08-29 中国银联股份有限公司 多维数据分析模型生成系统及方法
CN105718471A (zh) * 2014-12-03 2016-06-29 中国科学院声学研究所 用户偏好建模方法、系统及用户偏好评估方法、系统
CN107301166A (zh) * 2017-02-13 2017-10-27 上海大学 面向跨领域进行信息抽取的多层次特征模型和特征评价方法

Also Published As

Publication number Publication date
CN114258551A (zh) 2022-03-29

Similar Documents

Publication Publication Date Title
US11327935B2 (en) Intelligent data quality
CN105488185B (zh) 一种知识库的优化方法和装置
Matějka et al. Ontology of BIM in a construction project life cycle
CN107291716B (zh) 一种链路数据校验方法及装置
US11574237B2 (en) Quick path to train, score, and operationalize a machine learning project
CN108664241B (zh) 一种将SysML模型进行仿真验证的方法
CN103970872B (zh) 基于业务口径的多层级数据处理方法
CN102831167B (zh) 图结构的xml处理方法及装置
CN103942220A (zh) 一种适用于it运维系统的工单智能关联知识库知识的方法
US10295979B2 (en) Scheduling in manufacturing environments
CN105468371A (zh) 一种基于主题聚类的业务流程图合并方法
JP7098327B2 (ja) 情報処理システム、関数作成方法および関数作成プログラム
CN101013451A (zh) 一种自动生成设计bom的系统
CN103942138A (zh) 测试方法及装置
CN105512725A (zh) 一种神经网络的训练方法和设备
JP2021527292A (ja) 会話業務ツール
WO2021035588A1 (zh) 生产建模方法、装置和系统
JP4648386B2 (ja) 設計支援装置、設計支援方法、設計支援プログラム
CN106557881B (zh) 一种基于业务活动执行顺序的业务流程系统构建方法
CN109299473B (zh) 一种基于开发者画像的软件工程任务推荐方法
Babar et al. Systematic reviews in requirements engineering: A systematic review
EP3933653A1 (en) Method and system for generating a digital representation of one or more engineering diagrams in a computing environment
TWI781138B (zh) 多階層網路交互關係查找方法
US8510254B2 (en) Ontology model to accelerate engineering analysis in manufacturing
CN116186506A (zh) 基于bert预训练模型的可访问性问题报告的自动识别方法

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19942882

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19942882

Country of ref document: EP

Kind code of ref document: A1