CN106682280A - Method and system for universal modeling of optimization algorithm - Google Patents
Method and system for universal modeling of optimization algorithm Download PDFInfo
- Publication number
- CN106682280A CN106682280A CN201611123964.0A CN201611123964A CN106682280A CN 106682280 A CN106682280 A CN 106682280A CN 201611123964 A CN201611123964 A CN 201611123964A CN 106682280 A CN106682280 A CN 106682280A
- Authority
- CN
- China
- Prior art keywords
- model
- algorithm
- basic module
- objective optimization
- optimization algorithm
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/04—Constraint-based CAD
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/20—Configuration CAD, e.g. designing by assembling or positioning modules selected from libraries of predesigned modules
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a method and system for universal modeling of an optimization algorithm. The method comprises the steps of obtaining modeling information of a to-be-established target optimization algorithm model through a modeling tool, wherein the modeling information comprises an objective function, constraint conditions and a data source; saving the modeling information in a model file; obtaining a basic module of the target optimization algorithm model through the model file; integrating the basic module and a preset corresponding universal algorithm template, and establishing the target optimization algorithm model. A universal part of the algorithm irrelevant with the solving concrete optimization problems is set as the algorithm template, the modeling information of the to-be-established target optimization algorithm model is obtained through the modeling tool, the basic module of the target optimization algorithm model is obtained, the basic module and the universal algorithm template are integrated to establish the target optimization algorithm model, so that the modeling workload is reduced, and modeling efficiency is improved.
Description
Technical field
The present invention relates to field of computer technology, and in particular to a kind of universal modeling method and system of optimized algorithm.
Background technology
In engineering practice, often optimizing application algorithm solves complicated engineering problem.Optimized algorithm to be solved one
As be optimization problem, common optimized algorithm has ant group algorithm, particle cluster algorithm and genetic algorithm.Optimization problem is substantially
Inside a solution space, optimal solution is found, the combinatorial optimization problem for making target function value minimum.Typical optimization problem has：
Traveling salesman problem (Traveling Salesman Problem, TSP), Vehicle Routing Problems (Vehicle Routing
Problem, VRP), job shop problem (Job Shop Scheduling, JSS) and work pieces process problem (Flow Shop
Scheduling, FSS) etc..
Optimized algorithm model is generally made up of object function and one group of constraints.To arrange for specific optimization problem
Specific object function and constraints.In the existing method for setting up optimized algorithm model, to re-establish whole optimization and calculate
Method model, workload is big, efficiency is low.
How a kind of universal modeling method of optimized algorithm is provided to reduce the workload for setting up model, and model is set up in raising
Efficiency become problem demanding prompt solution.
The content of the invention
The embodiment of the present invention provides a kind of universal modeling method and system of optimized algorithm, for solving existing to set up excellent
Change the problem that workload is big, efficiency is low of algorithm model.
A kind of universal modeling method of optimized algorithm is embodiments provided, including：
The model for obtaining objective optimization algorithm model to be set up by modeling tool sets up information, and the model sets up letter
Breath includes object function, constraints and data source；
The model is set up into information to be stored in model file；
The basic module of the objective optimization algorithm model is obtained by the model file；
The basic module and the corresponding general-purpose algorithm template for pre-setting are carried out integrated, set up objective optimization algorithm
Model.
Alternatively, the model for obtaining objective optimization algorithm model to be set up by modeling tool sets up information, including：
Object function and constraints according to standard cell lib is with cumulative summation symbolic formulation.
Alternatively, the model file is XML file.
Alternatively, the basic module of the objective optimization algorithm model is obtained by the model file, including：
The model file is converted to into the basic module of the objective optimization algorithm model, the source journey of the basic module
The programming language of sequence is identical with the programming language of the general-purpose algorithm template.
Alternatively, the general-purpose algorithm template includes multiformity component and convergence component.
A kind of general modeling system of optimized algorithm is embodiments provided, including：
Model sets up information acquisition unit, for obtaining the mould of objective optimization algorithm model to be set up by modeling tool
Type sets up information, and the model sets up information including object function, constraints and data source；
Model sets up information holding unit, is stored in model file for the model to be set up into information；
Basic module acquiring unit, for obtaining basic group of the objective optimization algorithm model by the model file
Part；
Objective optimization algorithm model sets up unit, for by the basic module and the corresponding general-purpose algorithm for pre-setting
Template carries out integrated, sets up objective optimization algorithm model.
Alternatively, the model is set up information acquisition unit and is further used for：
Object function and constraints according to standard cell lib is with cumulative summation symbolic formulation.
Alternatively, the model file is XML file.
Alternatively, the basic module acquiring unit is further used for：
The model file is converted to into the basic module of the objective optimization algorithm model, the source journey of the basic module
The programming language of sequence is identical with the programming language of the general-purpose algorithm template.
Alternatively, the general-purpose algorithm template includes multiformity component and convergence component.
The universal modeling method and system of optimized algorithm provided in an embodiment of the present invention, is obtained by modeling tool and waits to set up
The model of objective optimization algorithm model set up information；The model is set up into information to be stored in model file；By described
Model file obtains the basic module of the objective optimization algorithm model；The basic module is corresponding logical with what is pre-set
Carried out with algorithm template integrated, set up objective optimization algorithm model.The embodiment of the present invention passes through will be with the specific optimization of solution
The versatility part of the unrelated algorithm of problem is arranged to algorithm template, and by modeling tool objective optimization algorithm to be set up is obtained
The model of model sets up information, obtains the basic module of objective optimization algorithm model, by basic module and general-purpose algorithm template set
Into objective optimization algorithm model is set up, the workload of model is set up in reduction, and the efficiency of model is set up in raising.
Description of the drawings
In order to be illustrated more clearly that the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
The accompanying drawing to be used needed for having technology description is briefly described, it should be apparent that, drawings in the following description are the present invention
Some embodiments, for those of ordinary skill in the art, on the premise of not paying creative work, can be with basis
These accompanying drawings obtain other accompanying drawings.
Fig. 1 is the schematic flow sheet of the universal modeling method of the optimized algorithm of one embodiment of the invention；
Fig. 2 is the principle schematic of the universal modeling method of the optimized algorithm of one embodiment of the invention；
Fig. 3 is the structural representation of the general modeling system of the optimized algorithm of one embodiment of the invention.
Specific embodiment
To make purpose, technical scheme and the advantage of the embodiment of the present invention clearer, below in conjunction with the embodiment of the present invention
In accompanying drawing, clear, complete description is carried out to the technical scheme in the embodiment of the present invention, it is clear that described embodiment is
The a part of embodiment of the present invention, rather than the embodiment of whole.Based on the embodiment in the present invention, those of ordinary skill in the art
The every other embodiment obtained under the premise of creative work is not made, belongs to the scope of protection of the invention.
Fig. 1 is the schematic flow sheet of the universal modeling method of the optimized algorithm of one embodiment of the invention.As shown in figure 1,
The method of the embodiment includes：
S11：The model for obtaining objective optimization algorithm model to be set up by modeling tool sets up information, and the model is built
Vertical information includes object function, constraints and data source；
It should be noted that objective optimization algorithm model is made up of object function and one group of constraints, set up for tool
The objective optimization algorithm model of body optimization problem, needs to obtain object function, constraints, and obtains data source.
S12：The model is set up into information to be stored in model file；
In actual applications, model is set up into information to be stored in XML file.
S13：The basic module of the objective optimization algorithm model is obtained by the model file；
S14：The basic module and the corresponding general-purpose algorithm template for pre-setting are carried out integrated, set up objective optimization
Algorithm model；
It should be noted that each optimized algorithm model is to solve certain concrete optimization problem, for different but similar
Problem optimized algorithm model can be set up by general-purpose algorithm template.General-purpose algorithm template is and the concrete optimization problem for being solved
Unrelated a certain algorithm abstraction versatility part out.According to the difference of optimized algorithm, general-purpose algorithm template can be divided into ant
Group's general-purpose algorithm template, population general-purpose algorithm template and hereditary general-purpose algorithm template.For the portion of concrete optimization problem process
Set up separately and put basic module.Basic module, by Interface integration, just realizes and objective optimization is calculated with corresponding general-purpose algorithm template
The foundation of method model.
The universal modeling method of optimized algorithm provided in an embodiment of the present invention, by modeling tool target to be set up is obtained
The model of optimized algorithm model sets up information；The model is set up into information to be stored in model file；By model text
Part obtains the basic module of the objective optimization algorithm model；By the basic module and the corresponding general-purpose algorithm for pre-setting
Template carries out integrated, sets up objective optimization algorithm model.The embodiment of the present invention by will with solve specific optimization problem without
The versatility part of the algorithm of pass is arranged to algorithm template, and by modeling tool objective optimization algorithm model to be set up is obtained
Model sets up information, obtains the basic module of objective optimization algorithm model, by basic module and the integrated foundation of general-purpose algorithm template
The workload of model is set up in objective optimization algorithm model, reduction, and the efficiency of model is set up in raising.
The embodiment of the present invention it is a kind of preferred embodiment in, similar with the method in Fig. 1, step S11 includes：
Object function and constraints according to standard cell lib is with cumulative summation symbolic formulation.
It should be noted that in optimized algorithm, constraints is usually transformed into penalty function and locates in the lump with object function
Reason.Object function and constraints can be expressed with the mathematical symbol of standard.
For example, the object function of objective optimization algorithm model to be set up is：
MAX(C1X1+C2X2+...+CiXi)
The constraint matrix of objective optimization algorithm model to be set up is：
A11X1+A12X2+...+A1iX1≥B1
A21X1+A22X2+...+A2iX2≤B2
......
......
Ai1X1+Ai2X2+...+AiiXi≤Bi
Master pattern unit in above-mentioned object function and constraint matrix standard cell lib can be represented, master pattern
Unit can not be less than number of dimensions with cumulative summation symbol definition, the cumulative number of master pattern unit.
The master pattern unit of 4 cumulative 4 dimensions is defined as follows：
The master pattern unit of 3 cumulative 3-dimensional degree is defined as follows：
The master pattern unit of 2 cumulative 2 dimensions is defined as follows：
The master pattern unit of 1 cumulative 3-dimensional degree is defined as follows：
The master pattern unit of 1 cumulative 2 dimensions is defined as follows：
The master pattern unit of 1 cumulative 1 dimension is defined as follows：
Further, step S13 includes：
The model file is converted to into the basic module of the objective optimization algorithm model, the source journey of the basic module
The programming language of sequence is identical with the programming language of the general-purpose algorithm template.
Further, the general-purpose algorithm template includes multiformity component and convergence component.
It will be appreciated that when complicated engineering problem is solved using optimized algorithm, various Sexual behavior mode is used to avoid being absorbed in
Local optimum, quickly laying in a coffin convergence of algorithm speed of then accelerate, therefore to be weighed between various Sexual behavior mode and Fast Convergent
Weighing apparatus.Even if different optimized algorithms, multiformity and the means for accelerating to lay in a coffin are also limited, can become logical with separate modular
With a part for algorithm template.
Fig. 2 is the principle schematic of the universal modeling method of the optimized algorithm of one embodiment of the invention.As shown in Fig. 2
The universal modeling method of the optimized algorithm of the embodiment of the present invention obtains objective optimization algorithm model to be set up by modeling tool
Object function, constraints and data source；Above- mentioned information is stored in model file；Institute is obtained by the model file
State the basic module of objective optimization algorithm model；The basic module is carried out with the corresponding general-purpose algorithm template for pre-setting
It is integrated, set up objective optimization algorithm model.The embodiment of the present invention is by by the algorithm unrelated with specific optimization problem is solved
Versatility part be arranged to algorithm template, by modeling tool obtain objective optimization algorithm model to be set up model set up
Information, obtains the basic module of objective optimization algorithm model, and basic module is set up into objective optimization with general-purpose algorithm template is integrated
The workload of model is set up in algorithm model, reduction, and the efficiency of model is set up in raising.
Fig. 3 is the structural representation of the general modeling system of the optimized algorithm of one embodiment of the invention.Such as Fig. 3 institutes
Show, the general modeling system of the optimized algorithm of the embodiment of the present invention sets up information acquisition unit 31, model and sets up letter including model
Breath storage unit 32, basic module acquiring unit 33 and objective optimization algorithm model set up unit 34, specifically：
Model sets up information acquisition unit 31, for obtaining objective optimization algorithm model to be set up by modeling tool
Model sets up information, and the model sets up information including object function, constraints and data source；
Model sets up information holding unit 32, is stored in model file for the model to be set up into information；
Basic module acquiring unit 33, for obtaining the basic of the objective optimization algorithm model by the model file
Component；
Objective optimization algorithm model sets up unit 34, for by the basic module and the corresponding general calculation for pre-setting
Method template carries out integrated, sets up objective optimization algorithm model.
Model is set up information acquisition unit 31 and is further used for：
Object function and constraints according to standard cell lib is with cumulative summation symbolic formulation.
Alternatively, the model file is XML file.
Basic module acquiring unit 33 is further used for：
The model file is converted to into the basic module of the objective optimization algorithm model, the source journey of the basic module
The programming language of sequence is identical with the programming language of the general-purpose algorithm template.
Alternatively, the general-purpose algorithm template includes multiformity component and convergence component.
The general modeling system of the optimized algorithm of the embodiment of the present invention can be used for performing said method embodiment, its principle
Similar with technique effect, here is omitted.
The universal modeling method and system of optimized algorithm provided in an embodiment of the present invention, is obtained by modeling tool and waits to set up
The model of objective optimization algorithm model set up information；The model is set up into information to be stored in model file；By described
Model file obtains the basic module of the objective optimization algorithm model；The basic module is corresponding logical with what is pre-set
Carried out with algorithm template integrated, set up objective optimization algorithm model.The embodiment of the present invention passes through will be with the specific optimization of solution
The versatility part of the unrelated algorithm of problem is arranged to algorithm template, and by modeling tool objective optimization algorithm to be set up is obtained
The model of model sets up information, obtains the basic module of objective optimization algorithm model, by basic module and general-purpose algorithm template set
Into objective optimization algorithm model is set up, the workload of model is set up in reduction, and the efficiency of model is set up in raising.
Those skilled in the art are it should be appreciated that embodiments of the invention can be provided as method, system or computer program
Product.Therefore, the present invention can be using complete hardware embodiment, complete software embodiment or with reference to the reality in terms of software and hardware
Apply the form of example.And, the present invention can be adopted and wherein include the computer of computer usable program code at one or more
The computer program implemented in usable storage medium (including but not limited to disk memory, CD-ROM, optical memory etc.) is produced
The form of product.
The present invention is the flow process with reference to method according to embodiments of the present invention, equipment (system) and computer program
Figure and/or block diagram are describing.It should be understood that can be by computer program instructions flowchart and/or each stream in block diagram
The combination of journey and/or square frame and flow chart and/or the flow process in block diagram and/or square frame.These computer programs can be provided
The processor of general purpose computer, special-purpose computer, Embedded Processor or other programmable data processing devices is instructed to produce
A raw machine so that produced for reality by the instruction of computer or the computing device of other programmable data processing devices
The device of the function of specifying in present one flow process of flow chart or one square frame of multiple flow processs and/or block diagram or multiple square frames.
It should be noted that term " including ", "comprising" or its any other variant are intended to the bag of nonexcludability
Contain, so that a series of process, method, article or equipment including key elements is not only including those key elements, but also including
Other key elements being not expressly set out, or also include the key element intrinsic for this process, method, article or equipment.
In the absence of more restrictions, the key element for being limited by sentence "including a ...", it is not excluded that including the key element
Process, method, article or equipment in also there is other identical element.
In the description of the present invention, a large amount of details are illustrated.Although it is understood that, embodiments of the invention can
To put into practice in the case of without these details.In some instances, known method, structure and skill is not been shown in detail
Art, so as not to obscure the understanding of this description.Similarly, it will be appreciated that disclose and help understand each to simplify the present invention
One or more in individual inventive aspect, above in the description of the exemplary embodiment of the present invention, each of the present invention is special
Levy and be grouped together into sometimes in single embodiment, figure or descriptions thereof.However, should not be by the method solution of the disclosure
Release in the following intention of reflection：The feature that i.e. the present invention for required protection requirement ratio is expressly recited in each claim is more
Many features.More precisely, as the following claims reflect, inventive aspect is less than single reality disclosed above
Apply all features of example.Therefore, it then follows thus claims of specific embodiment are expressly incorporated in the specific embodiment,
Wherein each claim itself is used as separate embodiments of the invention.
Above example is merely to illustrate technical scheme, rather than a limitation；Although with reference to the foregoing embodiments
The present invention has been described in detail, it will be understood by those within the art that：It still can be to aforementioned each enforcement
Technical scheme described in example is modified, or carries out equivalent to which part technical characteristic；And these are changed or replace
Change, do not make the spirit and scope of the essence disengaging various embodiments of the present invention technical scheme of appropriate technical solution.
Claims (10)
1. a kind of universal modeling method of optimized algorithm, it is characterised in that include:
The model for obtaining objective optimization algorithm model to be set up by modeling tool sets up information, and the model sets up packet
Include object function, constraints and data source；
The model is set up into information to be stored in model file；
The basic module of the objective optimization algorithm model is obtained by the model file；
The basic module and the corresponding general-purpose algorithm template for pre-setting are carried out integrated, set up objective optimization algorithm mould
Type.
2. the universal modeling method of optimized algorithm according to claim 1, it is characterised in that obtained by modeling tool and treated
The model of the objective optimization algorithm model of foundation sets up information, including：
Object function and constraints according to standard cell lib is with cumulative summation symbolic formulation.
3. the universal modeling method of optimized algorithm according to claim 1, it is characterised in that the model file is XML
File.
4. the universal modeling method of optimized algorithm according to claim 1, it is characterised in that obtained by the model file
The basic module of the objective optimization algorithm model is taken, including：
The model file is converted to into the basic module of the objective optimization algorithm model, the source program of the basic module
Programming language is identical with the programming language of the general-purpose algorithm template.
5. the universal modeling method of optimized algorithm according to claim 1, it is characterised in that the general-purpose algorithm template bag
Include multiformity component and convergence component.
6. the general modeling system of a kind of optimized algorithm, it is characterised in that include：
Model sets up information acquisition unit, and the model for being obtained objective optimization algorithm model to be set up by modeling tool is built
Vertical information, the model sets up information including object function, constraints and data source；
Model sets up information holding unit, is stored in model file for the model to be set up into information；
Basic module acquiring unit, for obtaining the basic module of the objective optimization algorithm model by the model file；
Objective optimization algorithm model sets up unit, for by the basic module and the corresponding general-purpose algorithm template for pre-setting
Carry out integrated, set up objective optimization algorithm model.
7. the general modeling system of optimized algorithm according to claim 6, it is characterised in that the model is set up information and obtained
Take unit to be further used for：
Object function and constraints according to standard cell lib is with cumulative summation symbolic formulation.
8. the general modeling system of optimized algorithm according to claim 6, it is characterised in that the model file is XML
File.
9. the general modeling system of optimized algorithm according to claim 6, it is characterised in that the basic module obtains single
Unit is further used for：
The model file is converted to into the basic module of the objective optimization algorithm model, the source program of the basic module
Programming language is identical with the programming language of the general-purpose algorithm template.
10. the general modeling system of optimized algorithm according to claim 6, it is characterised in that the general-purpose algorithm template
Including multiformity component and convergence component.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611123964.0A CN106682280A (en) | 2016-12-08 | 2016-12-08 | Method and system for universal modeling of optimization algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611123964.0A CN106682280A (en) | 2016-12-08 | 2016-12-08 | Method and system for universal modeling of optimization algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106682280A true CN106682280A (en) | 2017-05-17 |
Family
ID=58868456
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611123964.0A Pending CN106682280A (en) | 2016-12-08 | 2016-12-08 | Method and system for universal modeling of optimization algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106682280A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111260071A (en) * | 2018-11-30 | 2020-06-09 | 上海寒武纪信息科技有限公司 | Method, device and storage medium for analyzing universal machine learning model file |
| CN111260018A (en) * | 2018-11-30 | 2020-06-09 | 上海寒武纪信息科技有限公司 | Machine learning secondary model file generation method and device and storage medium |
| CN111258584A (en) * | 2018-11-30 | 2020-06-09 | 上海寒武纪信息科技有限公司 | General machine learning secondary model file analysis method and device and storage medium |
| CN111338630A (en) * | 2018-11-30 | 2020-06-26 | 上海寒武纪信息科技有限公司 | Method and device for generating universal machine learning model file and storage medium |
| CN113408807A (en) * | 2021-06-28 | 2021-09-17 | 内蒙古显鸿科技股份有限公司 | Air pollution prediction modeling algorithm based on full-connection and LSTM neural network |
| US11307836B2 (en) | 2018-06-08 | 2022-04-19 | Shanghai Cambricon Information Technology Co., Ltd. | General machine learning model, and model file generation and parsing method |
-
2016
- 2016-12-08 CN CN201611123964.0A patent/CN106682280A/en active Pending
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11307836B2 (en) | 2018-06-08 | 2022-04-19 | Shanghai Cambricon Information Technology Co., Ltd. | General machine learning model, and model file generation and parsing method |
| US11726754B2 (en) | 2018-06-08 | 2023-08-15 | Shanghai Cambricon Information Technology Co., Ltd. | General machine learning model, and model file generation and parsing method |
| US11403080B2 (en) | 2018-06-08 | 2022-08-02 | Shanghai Cambricon Information Technology Co., Ltd. | General machine learning model, and model file generation and parsing method |
| US11379199B2 (en) | 2018-06-08 | 2022-07-05 | Shanghai Cambricon Information Technology Co., Ltd. | General machine learning model, and model file generation and parsing method |
| US11334330B2 (en) | 2018-06-08 | 2022-05-17 | Shanghai Cambricon Information Technology Co., Ltd. | General machine learning model, and model file generation and parsing method |
| US11334329B2 (en) | 2018-06-08 | 2022-05-17 | Shanghai Cambricon Information Technology Co., Ltd. | General machine learning model, and model file generation and parsing method |
| CN111338630A (en) * | 2018-11-30 | 2020-06-26 | 上海寒武纪信息科技有限公司 | Method and device for generating universal machine learning model file and storage medium |
| CN111260018B (en) * | 2018-11-30 | 2022-03-22 | 上海寒武纪信息科技有限公司 | Machine learning secondary model file generation method and device and storage medium |
| CN111260071B (en) * | 2018-11-30 | 2022-04-08 | 上海寒武纪信息科技有限公司 | Method, device and storage medium for analyzing universal machine learning model file |
| CN111338630B (en) * | 2018-11-30 | 2022-02-08 | 上海寒武纪信息科技有限公司 | Method and device for generating universal machine learning model file and storage medium |
| CN111258584B (en) * | 2018-11-30 | 2022-02-08 | 上海寒武纪信息科技有限公司 | General machine learning secondary model file analysis method and device and storage medium |
| CN111260071A (en) * | 2018-11-30 | 2020-06-09 | 上海寒武纪信息科技有限公司 | Method, device and storage medium for analyzing universal machine learning model file |
| CN111258584A (en) * | 2018-11-30 | 2020-06-09 | 上海寒武纪信息科技有限公司 | General machine learning secondary model file analysis method and device and storage medium |
| CN111260018A (en) * | 2018-11-30 | 2020-06-09 | 上海寒武纪信息科技有限公司 | Machine learning secondary model file generation method and device and storage medium |
| CN113408807A (en) * | 2021-06-28 | 2021-09-17 | 内蒙古显鸿科技股份有限公司 | Air pollution prediction modeling algorithm based on full-connection and LSTM neural network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106682280A (en) | Method and system for universal modeling of optimization algorithm | |
| CN109993299A (en) | Data training method and device, storage medium, electronic device | |
| CN105718607B (en) | A kind of suspension hard spot optimization method based on K&C characteristic | |
| CN105045102B (en) | A kind of non-linear integrated control method of vehicle lateral stability | |
| CN104572201B (en) | A kind of spacecraft information altering system and variation based on threedimensional model | |
| CN104036068A (en) | Car crash safety simulation analysis and optimization design integrated system | |
| CN103699719A (en) | Interval optimum design method for vehicle powertrain mounting system | |
| CN106156406B (en) | A kind of method and system for 3D printing model Automatic Typesetting | |
| CN102521854A (en) | Parallel flow line placing method applicable to two-dimensional flow field | |
| CN104519072A (en) | Authority control method and device | |
| CN106293547A (en) | A kind of support automatic generation method printed for 3D | |
| CN118036165B (en) | Automatic generation method, device and storage medium for skirt house form of high-rise building | |
| CN104504227A (en) | Hydraulic forging press multi-dimensional virtual prototype collaborative simulation method and system | |
| CN103870681B (en) | Band sawing machine mixed type fail-safe analysis computational methods | |
| CN103065306B (en) | The disposal route of graph data and device | |
| Chen et al. | An automatic optimization method for minimizing supporting structures in additive manufacturing | |
| CN103793281A (en) | Load balancing method of compute-intensive simulation task | |
| CN107729057A (en) | Flow processing method being buffered a kind of data block under multi-core DSP more | |
| CN104156528B (en) | A kind of standard device ontology model fast modeling method based on Pro/E | |
| CN108021935B (en) | Dimension reduction method and device based on big data technology | |
| CN112925281B (en) | Generation method and system of entity manufacturing system deployment scheme based on digital twin | |
| CN114818414A (en) | Simulation method, device, equipment and medium of transverse stabilizer bar | |
| CN104658018A (en) | Method of decomposing loop polygon and drawing device | |
| CN108090655A (en) | For smart allocation process method, module and the system of garment production | |
| CN102253861A (en) | Method for executing stepwise plug-in computation |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170517 |
|
| RJ01 | Rejection of invention patent application after publication |