CN109460396A - Model treatment method and device, storage medium and electronic equipment - Google Patents
Model treatment method and device, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN109460396A CN109460396A CN201811191482.8A CN201811191482A CN109460396A CN 109460396 A CN109460396 A CN 109460396A CN 201811191482 A CN201811191482 A CN 201811191482A CN 109460396 A CN109460396 A CN 109460396A
- Authority
- CN
- China
- Prior art keywords
- model
- training
- treatment method
- configuration information
- module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 60
- 238000012549 training Methods 0.000 claims abstract description 116
- 238000004458 analytical method Methods 0.000 claims abstract description 42
- 230000002159 abnormal effect Effects 0.000 claims description 10
- 230000008569 process Effects 0.000 claims description 10
- 238000012986 modification Methods 0.000 claims description 6
- 230000004048 modification Effects 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 abstract description 4
- 238000012545 processing Methods 0.000 description 18
- 238000010586 diagram Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 7
- 238000012360 testing method Methods 0.000 description 6
- 238000012795 verification Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 238000003066 decision tree Methods 0.000 description 2
- 230000005291 magnetic effect Effects 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 210000004027 cell Anatomy 0.000 description 1
- 239000000470 constituent Substances 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000003014 reinforcing effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 210000000352 storage cell Anatomy 0.000 description 1
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of model treatment method and device, storage medium and electronic equipments, apply under stand-alone environment, are related to field of computer technology.The model treatment device includes: that configuration obtains module, for obtaining the configuration file of model；Information analysis module, for being parsed to the configuration file, to obtain configuration information；Model training module for constructing model according to the model parameter in the configuration information, and obtains training set according to the training set path in the configuration information to be trained to model；Database, for storing the training result of the configuration information and model.The disclosure can preferably realize the management to model under stand-alone environment.
Description
Technical field
This disclosure relates to field of computer technology, in particular to a kind of model treatment method, model treatment device,
Storage medium and electronic equipment.
Background technique
With the development of computer technology, every profession and trade can use model data are analyzed and solve it is various prediction ask
Topic.The establishment of model thought substantially increases the efficiency of processing problem and reduces the cost manually participated in repeatedly.
The foundation of model and the process for analyzing data often carry out under on line state.Currently, under stand-alone environment, still
There are not unified model parameter and version management.On the one hand, when model when something goes wrong, it is difficult to model is recalled；It is another
Aspect, due to not preferable administrative mechanism, therefore, it is impossible to expeditiously realize "current" model using historical models parameter
Building；In another aspect, user can not clearly check without intuitive control methods between the modelling effect of different model versions
To the comparing result of forecast result of model.
It should be noted that information is only used for reinforcing the reason to the background of the disclosure disclosed in above-mentioned background technology part
Solution, therefore may include the information not constituted to the prior art known to persons of ordinary skill in the art.
Summary of the invention
The disclosure is designed to provide a kind of model treatment method, model treatment device, storage medium and electronic equipment,
And then the model management under stand-alone environment is realized at least to a certain extent, and implementation model backtracking and model comparison.
According to one aspect of the disclosure, a kind of model treatment device is provided, is applied under stand-alone environment, comprising: configuration
Module is obtained, for obtaining the configuration file of model；Information analysis module, for being parsed to the configuration file, with
To configuration information；Model training module for constructing model according to the model parameter in the configuration information, and is matched according to described
Training set path in confidence breath obtains training set to be trained to model；Database, for store the configuration information and
The training result of model.
In a kind of exemplary embodiment of the disclosure, the model treatment device further include: information checking module is used for
The configuration information is verified；Wherein, the model training module is used for when the configuration information verifies successfully, according to
Model parameter in the configuration information constructs model, and according to the training set path in the configuration information obtain training set with
Model is trained.
In a kind of exemplary embodiment of the disclosure, the model treatment device further include: data prediction module is used for
Data to be predicted are obtained, the data to be predicted are predicted using the model after training, and prediction result is stored to institute
State database.
In a kind of exemplary embodiment of the disclosure, the model treatment device further include: exception processing module is used for
Whether judgment models are abnormal in the process in training and/or prediction, and when abnormal, execute initialization model, re-start training
And/or prediction, issue one of warning information or a variety of operations.
In a kind of exemplary embodiment of the disclosure, the model treatment device further include: analysis contrast module is used for
One or more model predictions are obtained from the database as a result, one or more of model prediction results are fed back to use
Family end carries out analysis comparison so as to user, and according to the results modification model parameter of analysis comparison.
In a kind of exemplary embodiment of the disclosure, the model treatment device further include: time control module is used for
The operation of building model, training pattern and/or data prediction is executed in the predetermined time.
In a kind of exemplary embodiment of the disclosure, configuration obtains configuration file of the module for obtaining model and includes:
Configuration obtains module and is used to obtain configuration file and training script that user is packaged upload；Wherein, model training module, for ringing
Model is constructed according to the model parameter in the configuration information using the training instruction at family, and according to the instruction in the configuration information
The path Lian Ji obtains training set, using the training set and executes the training script to be trained to model.
According to one aspect of the disclosure, a kind of model treatment method is provided, is applied under stand-alone environment, comprising: is obtained
The configuration file of model；The configuration file is parsed, to obtain configuration information；According to the model in the configuration information
Parameter constructs model, and obtains training set according to the training set path in the configuration information to be trained to model；By institute
The training result for stating configuration information and model is stored to database.
In a kind of exemplary embodiment of the disclosure, model treatment method further include: configuration information is verified；?
When verifying successfully, model is constructed according to the model parameter in configuration information.
In a kind of exemplary embodiment of the disclosure, model treatment method further include: data to be predicted are obtained, using instruction
Model after white silk predicts the data to be predicted, and prediction result is stored to database.
In a kind of exemplary embodiment of the disclosure, model treatment method further include: judgment models are trained and/or pre-
Whether survey is abnormal in the process, and when abnormal, executes initialization model, re-starts training and/or prediction, sending warning information
One of or a variety of operations.
In a kind of exemplary embodiment of the disclosure, model treatment method further include: from database obtain one or
Multiple model predictions as a result, one or more model prediction results are fed back to user terminal so that user carries out analysis comparison, and
According to the results modification model parameter of analysis comparison.
In a kind of exemplary embodiment of the disclosure, model treatment method further include: execute building mould in the predetermined time
The operation of type, training pattern and/or data prediction.
In a kind of exemplary embodiment of the disclosure, the configuration file for obtaining model includes obtaining user to be packaged upload
Configuration file and training script；Wherein it is possible to which the training instruction for responding user constructs mould according to the model parameter in configuration information
Type, and according in configuration information training set path obtain training set, using training set and execute training script with to model into
Row training.
According to one aspect of the disclosure, a kind of storage medium is provided, computer program, the computer are stored thereon with
Model treatment method described in above-mentioned any one is realized when program is executed by processor.
According to one aspect of the disclosure, a kind of electronic equipment is provided, comprising: processor；And memory, for storing
The executable instruction of the processor；Wherein, the processor is configured to above-mentioned to execute via the executable instruction is executed
Model treatment method described in any one.
In the technical solution provided by some embodiments of the present disclosure, obtained by the configuration constructed under stand-alone environment
Module, information analysis module, model training module and database, on the one hand, the disclosure preferably realizes under stand-alone environment
Management to model, can be by the configuration information and model training that store in database as a result, the backtracking of implementation model；It is another
Aspect can modify the configuration information stored in database, to fast implement the building of new model, save the time.
It should be understood that above general description and following detailed description be only it is exemplary and explanatory, not
The disclosure can be limited.
Detailed description of the invention
The drawings herein are incorporated into the specification and forms part of this specification, and shows the implementation for meeting the disclosure
Example, and together with specification for explaining the principles of this disclosure.It should be evident that the accompanying drawings in the following description is only the disclosure
Some embodiments for those of ordinary skill in the art without creative efforts, can also basis
These attached drawings obtain other attached drawings.In the accompanying drawings:
Fig. 1 diagrammatically illustrates the block diagram of the model treatment device of the first illustrative embodiments according to the disclosure；
Fig. 2 diagrammatically illustrates the block diagram of the model treatment device of the second illustrative embodiments according to the disclosure；
Fig. 3 diagrammatically illustrates the block diagram of the model treatment device of the third illustrative embodiments according to the disclosure；
Fig. 4 diagrammatically illustrates the block diagram of the model treatment device of the 4th illustrative embodiments according to the disclosure；
Fig. 5 diagrammatically illustrates the block diagram of the model treatment device of the 5th illustrative embodiments according to the disclosure；
Fig. 6 diagrammatically illustrates the block diagram of the model treatment device of the 6th illustrative embodiments according to the disclosure；
Fig. 7 diagrammatically illustrates the flow chart of model treatment method according to an exemplary embodiment of the present disclosure；
Fig. 8 shows the schematic diagram of storage medium according to an exemplary embodiment of the present disclosure；And
Fig. 9 diagrammatically illustrates the block diagram of electronic equipment according to an exemplary embodiment of the present disclosure.
Specific embodiment
Example embodiment is described more fully with reference to the drawings.However, example embodiment can be with a variety of shapes
Formula is implemented, and is not understood as limited to example set forth herein；On the contrary, thesing embodiments are provided so that the disclosure will more
Fully and completely, and by the design of example embodiment comprehensively it is communicated to those skilled in the art.Described feature, knot
Structure or characteristic can be incorporated in any suitable manner in one or more embodiments.In the following description, it provides perhaps
More details fully understand embodiment of the present disclosure to provide.It will be appreciated, however, by one skilled in the art that can
It is omitted with technical solution of the disclosure one or more in the specific detail, or others side can be used
Method, constituent element, device, step etc..In other cases, be not shown in detail or describe known solution to avoid a presumptuous guest usurps the role of the host and
So that all aspects of this disclosure thicken.
In addition, attached drawing is only the schematic illustrations of the disclosure, it is not necessarily drawn to scale.Identical attached drawing mark in figure
Note indicates same or similar part, thus will omit repetition thereof.Some block diagrams shown in the drawings are function
Energy entity, not necessarily must be corresponding with physically or logically independent entity.These function can be realized using software form
Energy entity, or these functional entitys are realized in one or more hardware modules or integrated circuit, or at heterogeneous networks and/or place
These functional entitys are realized in reason device device and/or microcontroller device.
Flow chart shown in the drawings is merely illustrative, it is not necessary to including all steps.For example, the step of having
It can also decompose, and the step of having can merge or part merges, therefore the sequence actually executed is possible to according to the actual situation
Change.
The model treatment device of the disclosure is applied under stand-alone environment.Fig. 1 diagrammatically illustrates first according to the disclosure
The block diagram of the model treatment device of illustrative embodiments.With reference to Fig. 1, model treatment device 1 may include that configuration obtains mould
Block 11, information analysis module 12, model training module 13 and database 19, in which:
Configuration obtains module 11, can be used for obtaining the configuration file of model；
Information analysis module 12 can be used for parsing configuration file, to obtain configuration information；
Model training module 13 can be used for constructing model according to the model parameter in configuration information, and according to confidence
Training set path in breath obtains training set to be trained to model；
Database 19 can be used for storing the training result of the configuration information and model.
In the model treatment device 1 of the exemplary embodiment of the disclosure, obtained by the configuration constructed under stand-alone environment
Modulus block, information analysis module, model training module and database, on the one hand, the disclosure is preferably realized under stand-alone environment
Management to model, can be by the configuration information and model training that store in database as a result, the backtracking of implementation model；Separately
On the one hand, the configuration information stored in database can be modified, to fast implement the building of new model, has saved the time.
Each component part of the model treatment device 1 to the disclosure is illustrated below.
In the illustrative embodiments of the disclosure, configuration obtains module 11 and can connect with user terminal, and user can lead to
Parameter information needed for crossing front-end interface (for example, Webpage) input model of user terminal, these parameter informations can with
Family end is configured as a configuration file, and the format of the configuration file can be, for example, json format.If by configuration file
It is denoted as conf, then configuration file can include but is not limited to following information:
Specifically, configuration file may include information relevant to model configuration permission, for example, username and password；With
The relevant information of model parameter, for example, algorithm used by model, can include but is not limited to SVM (Support Vector
Machine, support vector machines), logistic regression algorithm, (Gradient Boosting Decision Tree, gradient mention GBDT
Rise decision tree) etc.；Information relevant to data used in model, for example, the path of training set, the path of test set, number to be predicted
According to path etc..In addition, configuration file can also include the other information of above-mentioned such as " method of operation ", model id.
It is to be understood, however, that being merely exemplary above to the description of configuration file, the disclosure is to configuration file
Format and content does not do specifically limited.
After user's input model configuration information, the configuration file of generation can be sent to by model treatment by user terminal
The configuration of device obtains module 11.
In addition, user can real-time input model configuration information.However, configuration information can also be pre-stored in by user
In user terminal, and when scheduled event occurs, configuration information is sent to configuration and obtains module 11 by user terminal, wherein predetermined thing
Part may include the predetermined time of user's sets itself, in the unit free for constructing model, etc..
Configuration obtains module 11 after getting the configuration file of model, which can be sent to information solution
Analyse module 12.Information analysis module 12 can parse configuration file, to obtain above-mentioned specific configuration information.For example,
Information analysis module 12 can match json format by means of the tool equipped with the tool for parsing json file
File is set to be parsed.Specifically, the tool can be existing analytical tool, it is also possible to developer according to practical business
Demand independently developed tool does not do particular determination to this in this illustrative embodiment.
After information analysis module 12 parses configuration file, configured after the available parsing of model training module 13
Model parameter in information.Specifically, after information analysis module 12 obtains configuration information, information analysis module 12 can will be complete
Portion's configuration information is transmitted directly to model training module 13, however, information analysis module 12 can also only will be in configuration information
Model parameter is sent to model training module.
Model training module 13 can construct model according to model parameter, by taking neural network model as an example, model parameter tool
Body can also include the information such as size, dimension of convolution kernel of each convolutional layer in neural network.
After model construction completion, model training module 13 can also be obtained from the training set path in configuration information and be instructed
Practice collection, wherein the process for obtaining training set path is similar with the process of above-mentioned acquisition model parameter, and details are not described herein.It connects down
Come, the training set that model training module 13 can use acquisition is trained the model of building.In addition, so it is easy to understand that
Model training module 13 can also obtain the path of test set from configuration information, and the test of model is obtained according to the path
Collection, to test the model after training.
It should be noted that business is different, the path of training set and test set is also different.The disclosure is to training set and test
The specific storage location of collection is not done specifically limited.
With reference to Fig. 1, surveyed carrying out above-mentioned acquisition configuration file, the parsing of configuration file, model construction and/or model training
During examination, wherein each module can be received, be generated, the data of transmitting are stored in database 19.Specifically, database
19 can store configuration information and model training module 13 obtained from information analysis module 12 parses configuration file
Training result after being trained to the model of building.In addition, the time that database 19 can be constructed with storage model, directly deposits
Store up configuration file etc..
In addition, in view of database 19 need to meet easy to use, scalability is strong, it is easy to maintain etc. require, the number of the disclosure
According to library 19 using mongodb database.However, database 19 can also be other kinds of database.
In the model treatment device of the second illustrative embodiments of the disclosure, with reference to Fig. 2, model treatment device 2 is removed
It may include that configuration obtains outside module 11, information analysis module 12, model training module 13 and database 19, can also include letter
Cease correction verification module 14.
After information analysis module 12 obtains configuration information, configuration information can be sent to information checking module 14.Letter
Breath correction verification module 14 can verify configuration information, specifically, can verify to the permission of user.For example, can be with
Judge whether user is in preconfigured white list, if user in white list, illustrate user meet modeling and it is right
The permission that model is managed.The white list can be preset, and for the ease of verification, which can be for example stored in
In information checking module 14.In addition, information checking module 14 whether model id can also be met call format, whether with it is existing
Model repeat etc. information verified.Particular determination is not done in this illustrative embodiment to this.
If configuration information verifies successfully, model training module 13 can execute above-mentioned process performed by it.In addition,
Configuration information can be sent to model training module 13 by information checking module 14.However, configuration information can also be by information solution
Analysis module 12 is sent to model training module 13, and in this case, information checking module 14 only plays the function of verification, and does not have
The function of thering is information to transmit.
If configuration information verification failure, information checking module 14 can directly send a warning message to user terminal, to mention
Show that configuration information is wrong, and then prompting user reconfigures the upload of file.
In the model treatment device of the third illustrative embodiments of the disclosure, with reference to Fig. 3, model treatment device 3 is removed
It may include that configuration obtains outside module 11, information analysis module 12, model training module 13 and database 19, can also include mould
Type prediction module 15.
The available data to be predicted of model prediction module 15.Wherein, data to be predicted can be what user uploaded in real time
Data, in addition, including the path of prediction data in configuration file, model prediction module can obtain number to be predicted according to the path
According to.
Model prediction module 15 can be obtained from model training module 13 or database 11 it is trained after model, and adopt
Prediction data is treated with the model to be predicted.After prediction, model prediction module 15 prediction result can be stored to
Database 19.
In the model treatment device of the 4th illustrative embodiments of the disclosure, with reference to Fig. 4, model treatment device 4 is removed
It may include that configuration obtains module 11, information analysis module 12, model training module 13, database 19 and model prediction module 15
It outside, can also include exception processing module 16.
Exception processing module 16 may determine that whether model is abnormal in the process in training and/or prediction, which can wrap
It includes program run-time error and exits.When exception processing module 16 judges abnormal, initialization model can be executed, re-started
Training and/or prediction, issue one of warning information or a variety of operations.Wherein, initialization model may refer to Controlling model
Training module 13 re-uses model parameter and is modeled；Re-starting training may refer to Controlling model training module 13 again
It is trained using training the set pair analysis model；It re-starts prediction and may refer to Controlling model prediction module 15 and treat prediction data weight
Newly predicted；Issuing warning information may refer to the letter that treatment process exception is directly transmitted to user terminal and/or developer
Breath, to remind user and/or developer to carry out the operation of investigation mistake.
In addition, exception processing module 16 can store the information for generating mistake into database 19.
In the model treatment device of the 5th illustrative embodiments of the disclosure, with reference to Fig. 5, model treatment device 5 is removed
It may include that configuration obtains module 11, information analysis module 12, model training module 13, database 19 and model prediction module 15
It outside, can also include analysis contrast module 17.
Analysis contrast module 17 can obtain one or more model prediction results from database 19, wherein model is pre-
It surveys result and database 19 is sent to by model prediction module 15.Next, analysis contrast module 17 can be by model prediction result
It is sent to user terminal, user terminal can carry out analysis ratio to model prediction result using software or the means of user's manual analysis
It is right, and analysis comparing result is sent to analysis contrast module 17, point that analysis contrast module 17 can be sent according to user terminal
Analysis comparing result modifies to model parameter.
Still by taking neural network model as an example, when user has found that model prediction result is larger with the gap of anticipation, Ke Yizeng
The dimension of big convolution kernel, and the parameter information for increasing convolution kernel dimension is sent to model treatment device, analyze contrast module 17
The parameter information can be sent to model training module 13, model training module 13 can re-start training to model, into
And model prediction module 15 can again predict data.In addition, analysis contrast module 17 can also be directly by the parameter
Information is sent to model prediction module 15, after modifying model parameter so as to model prediction module 15, is directly predicted.
In the model treatment device of the 6th illustrative embodiments of the disclosure, with reference to Fig. 6, model treatment device 6 is removed
It may include that configuration obtains module 11, information analysis module 12, model training module 13, database 19 and model prediction module 15
It outside, can also include time control module 18.
Time control module 18 can execute the operation that building model, training pattern and/or data are predicted in the predetermined time.
Specifically, the predetermined time can be by developer's sets itself, and the time quantum of predetermined time can be minute, small
When, day, week, the moon etc..For example, may be set in the training that daily 2:00 AM starts model, to avoid the resource of the system of occupancy.
According to other embodiment, configuration obtain module 11 can be used for obtaining user be packaged the configuration file uploaded and
Training script.Thus, it is possible to avoid the loss of data in transmission process.
In this case, model training module 13 can respond the training instruction of user, according to the mould in configuration information
Shape parameter construct model, and according in configuration information training set path obtain training set, execute training script with to model into
Row training.
In addition, the disclosure can also rebuild new model including the use of the historical models information in database 19.?
In this case, may only need to modify some parameters can construct model faster, and the time is greatly saved.
The model treatment device within the scope of the disclosure is illustrated in an exemplary fashion above.It should be understood that
It is, although information checking module 14 is described in model treatment device 2, however, information checking module 14 may be included in
Model treatment device 3 is into model treatment device 6, similarly, exception processing module 16, analysis contrast module 17, time control
Module 18 may be included in other model treatment devices.
Further, a kind of model treatment method is additionally provided in this example embodiment.
Fig. 7 diagrammatically illustrates the flow chart of model treatment method according to an exemplary embodiment of the present disclosure.With reference to
The model treatment method of Fig. 7, the illustrative embodiments of the disclosure may include:
S72. the configuration file of model is obtained；
S74. the configuration file is parsed, to obtain configuration information；
S76. model is constructed according to the model parameter in the configuration information, and according to the training set in the configuration information
Path obtains training set to be trained to model；
S78. the training result of the configuration information and model is stored to database.
In the model treatment method provided by some embodiments of the present disclosure, on the one hand, the disclosure is preferably in single machine
The management to model is realized under environment, it can be by the configuration information and model training that are stored in database as a result, realizing mould
The backtracking of type；On the other hand, the configuration information stored in database can be modified, to fast implement the building of new model, is saved
Time.
According to an exemplary embodiment of the present disclosure, model treatment method further include: configuration information is verified；It is verifying
When success, model is constructed according to the model parameter in configuration information.
According to an exemplary embodiment of the present disclosure, model treatment method further include: data to be predicted are obtained, after training
Model the data to be predicted are predicted, and prediction result is stored to database.
According to an exemplary embodiment of the present disclosure, model treatment method further include: judgment models are in training and/or predict
It is whether abnormal in journey, and when abnormal, initialization model is executed, training re-started and/or predicts, issue in warning information
One or more operations.
According to an exemplary embodiment of the present disclosure, model treatment method further include: obtained from database one or more
Model prediction as a result, one or more model prediction results are fed back to user terminal so that user carries out analysis comparison, and according to
Analyze the results modification model parameter of comparison.
According to an exemplary embodiment of the present disclosure, model treatment method further include: execute building model, instruction in the predetermined time
Practice the operation of model and/or data prediction.
According to an exemplary embodiment of the present disclosure, the configuration file for obtaining model includes obtaining user to be packaged the configuration uploaded
File and training script；Wherein it is possible to the training instruction for responding user constructs model according to the model parameter in configuration information, and
Training set is obtained according to the training set path in configuration information, using training set and executes training script to instruct to model
Practice.
It is retouched since the detailed process of the model treatment method of embodiment of the present invention is corresponding with above-mentioned model treatment device
State identical, therefore details are not described herein.
In an exemplary embodiment of the disclosure, a kind of computer readable storage medium is additionally provided, energy is stored thereon with
Enough realize the program product of this specification above method.In some possible embodiments, various aspects of the invention may be used also
In the form of being embodied as a kind of program product comprising program code, when described program product is run on the terminal device, institute
Program code is stated for executing the terminal device described in above-mentioned " illustrative methods " part of this specification according to this hair
The step of bright various illustrative embodiments.
Refering to what is shown in Fig. 8, describing the program product for realizing the above method of embodiment according to the present invention
800, can using portable compact disc read only memory (CD-ROM) and including program code, and can in terminal device,
Such as it is run on PC.However, program product of the invention is without being limited thereto, in this document, readable storage medium storing program for executing can be with
To be any include or the tangible medium of storage program, the program can be commanded execution system, device or device use or
It is in connection.
Described program product can be using any combination of one or more readable mediums.Readable medium can be readable letter
Number medium or readable storage medium storing program for executing.Readable storage medium storing program for executing for example can be but be not limited to electricity, magnetic, optical, electromagnetic, infrared ray or
System, device or the device of semiconductor, or any above combination.The more specific example of readable storage medium storing program for executing is (non exhaustive
List) include: electrical connection with one or more conducting wires, portable disc, hard disk, random access memory (RAM), read-only
Memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read only memory
(CD-ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.
Computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal,
In carry readable program code.The data-signal of this propagation can take various forms, including but not limited to electromagnetic signal,
Optical signal or above-mentioned any appropriate combination.Readable signal medium can also be any readable Jie other than readable storage medium storing program for executing
Matter, the readable medium can send, propagate or transmit for by instruction execution system, device or device use or and its
The program of combined use.
The program code for including on readable medium can transmit with any suitable medium, including but not limited to wirelessly, have
Line, optical cable, RF etc. or above-mentioned any appropriate combination.
The program for executing operation of the present invention can be write with any combination of one or more programming languages
Code, described program design language include object oriented program language-Java, C++ etc., further include conventional
Procedural programming language-such as " C " language or similar programming language.Program code can be fully in user
It calculates and executes in equipment, partly executes on a user device, being executed as an independent software package, partially in user's calculating
Upper side point is executed on a remote computing or is executed in remote computing device or server completely.It is being related to far
Journey calculates in the situation of equipment, and remote computing device can pass through the network of any kind, including local area network (LAN) or wide area network
(WAN), it is connected to user calculating equipment, or, it may be connected to external computing device (such as utilize ISP
To be connected by internet).
In an exemplary embodiment of the disclosure, a kind of electronic equipment that can be realized the above method is additionally provided.
Person of ordinary skill in the field it is understood that various aspects of the invention can be implemented as system, method or
Program product.Therefore, various aspects of the invention can be embodied in the following forms, it may be assumed that complete hardware embodiment, complete
The embodiment combined in terms of full Software Implementation (including firmware, microcode etc.) or hardware and software, can unite here
Referred to as circuit, " module " or " system ".
The electronic equipment 900 of this embodiment according to the present invention is described referring to Fig. 9.The electronics that Fig. 9 is shown
Equipment 900 is only an example, should not function to the embodiment of the present invention and use scope bring any restrictions.
As shown in figure 9, electronic equipment 900 is showed in the form of universal computing device.The component of electronic equipment 900 can wrap
It includes but is not limited to: at least one above-mentioned processing unit 910, at least one above-mentioned storage unit 920, the different system components of connection
The bus 930 of (including storage unit 920 and processing unit 910), display unit 940.
Wherein, the storage unit is stored with program code, and said program code can be held by the processing unit 910
Row, so that various according to the present invention described in the execution of the processing unit 910 above-mentioned " illustrative methods " part of this specification
The step of illustrative embodiments.For example, the processing unit 910 can execute step S72 as shown in Figure 7 to step
S78。
Storage unit 920 may include the readable medium of volatile memory cell form, such as Random Access Storage Unit
(RAM) 9201 and/or cache memory unit 9202, it can further include read-only memory unit (ROM) 9203.
Storage unit 920 can also include program/utility with one group of (at least one) program module 9205
9204, such program module 9205 includes but is not limited to: operating system, one or more application program, other program moulds
It may include the realization of network environment in block and program data, each of these examples or certain combination.
Bus 930 can be to indicate one of a few class bus structures or a variety of, including storage unit bus or storage
Cell controller, peripheral bus, graphics acceleration port, processing unit use any bus structures in a variety of bus structures
Local bus.
Electronic equipment 900 can also be with one or more external equipments 1000 (such as keyboard, sensing equipment, bluetooth equipment
Deng) communication, can also be enabled a user to one or more equipment interact with the electronic equipment 900 communicate, and/or with make
Any equipment (such as the router, modulation /demodulation that the electronic equipment 900 can be communicated with one or more of the other calculating equipment
Device etc.) communication.This communication can be carried out by input/output (I/O) interface 950.Also, electronic equipment 900 can be with
By network adapter 960 and one or more network (such as local area network (LAN), wide area network (WAN) and/or public network,
Such as internet) communication.As shown, network adapter 960 is communicated by bus 930 with other modules of electronic equipment 900.
It should be understood that although not shown in the drawings, other hardware and/or software module can not used in conjunction with electronic equipment 900, including but not
Be limited to: microcode, device driver, redundant processing unit, external disk drive array, RAID system, tape drive and
Data backup storage system etc..
Through the above description of the embodiments, those skilled in the art is it can be readily appreciated that example described herein is implemented
Mode can also be realized by software realization in such a way that software is in conjunction with necessary hardware.Therefore, according to the disclosure
The technical solution of embodiment can be embodied in the form of software products, which can store non-volatile at one
Property storage medium (can be CD-ROM, USB flash disk, mobile hard disk etc.) in or network on, including some instructions are so that a calculating
Equipment (can be personal computer, server, terminal installation or network equipment etc.) is executed according to disclosure embodiment
Method.
In addition, above-mentioned attached drawing is only the schematic theory of processing included by method according to an exemplary embodiment of the present invention
It is bright, rather than limit purpose.It can be readily appreciated that the time that above-mentioned processing shown in the drawings did not indicated or limited these processing is suitable
Sequence.In addition, be also easy to understand, these processing, which can be, for example either synchronously or asynchronously to be executed in multiple modules.
It should be noted that although being referred to several modules or list for acting the equipment executed in the above detailed description
Member, but this division is not enforceable.In fact, according to embodiment of the present disclosure, it is above-described two or more
Module or the feature and function of unit can embody in a module or unit.Conversely, an above-described mould
The feature and function of block or unit can be to be embodied by multiple modules or unit with further division.
Those skilled in the art after considering the specification and implementing the invention disclosed here, will readily occur to its of the disclosure
His embodiment.This application is intended to cover any variations, uses, or adaptations of the disclosure, these modifications, purposes or
Adaptive change follow the general principles of this disclosure and including the undocumented common knowledge in the art of the disclosure or
Conventional techniques.The description and examples are only to be considered as illustrative, and the true scope and spirit of the disclosure are by claim
It points out.
It should be understood that the present disclosure is not limited to the precise structures that have been described above and shown in the drawings, and
And various modifications and changes may be made without departing from the scope thereof.The scope of the present disclosure is only limited by the attached claims.
Claims (10)
1. a kind of model treatment method, is applied under stand-alone environment characterized by comprising
Obtain the configuration file of model；
The configuration file is parsed, to obtain configuration information；
Model is constructed according to the model parameter in the configuration information, and is obtained according to the training set path in the configuration information
Training set is to be trained model；
The training result of the configuration information and model is stored to database.
2. model treatment method according to claim 1, which is characterized in that the model treatment method further include:
The configuration information is verified；
Wherein, when verifying successfully, model is constructed according to the model parameter in the configuration information.
3. model treatment method according to claim 1, which is characterized in that the model treatment method further include:
Data to be predicted are obtained, the data to be predicted are predicted using the model after training, and prediction result is stored
To the database.
4. model treatment method according to claim 3, which is characterized in that the model treatment method further include:
Whether judgment models are abnormal in the process in training and/or prediction, and when abnormal, execute initialization model, re-start
Training and/or one of prediction, sending warning information or a variety of operations.
5. model treatment method according to claim 3, which is characterized in that the model treatment method further include:
One or more model predictions are obtained from the database as a result, one or more of model prediction results are fed back
To user terminal so that user carries out analysis comparison, and according to the results modification model parameter of analysis comparison.
6. model treatment method according to claim 3, which is characterized in that the model treatment method further include:
The operation of building model, training pattern and/or data prediction is executed in the predetermined time.
7. model treatment method according to claim 1, which is characterized in that the configuration file for obtaining model includes:
It obtains user and is packaged the configuration file and training script uploaded；
Wherein, the training instruction for responding user constructs model according to the model parameter in the configuration information, and is matched according to described
Training set path in confidence breath obtains training set, using the training set and executes the training script to instruct to model
Practice.
8. a kind of model treatment device, is applied under stand-alone environment characterized by comprising
Configuration obtains module, for obtaining the configuration file of model；
Information analysis module, for being parsed to the configuration file, to obtain configuration information；
Model training module, for constructing model according to the model parameter in the configuration information, and according to the configuration information
In training set path obtain training set to be trained to model；
Database, for storing the training result of the configuration information and model.
9. a kind of storage medium, is stored thereon with computer program, which is characterized in that the computer program is executed by processor
Model treatment method described in Shi Shixian any one of claims 1 to 7.
10. a kind of electronic equipment characterized by comprising
Processor；And
Memory, for storing the executable instruction of the processor；
Wherein, the processor is configured to come described in any one of perform claim requirement 1 to 7 via the execution executable instruction
Model treatment method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811191482.8A CN109460396B (en) | 2018-10-12 | 2018-10-12 | Model processing method and device, storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811191482.8A CN109460396B (en) | 2018-10-12 | 2018-10-12 | Model processing method and device, storage medium and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109460396A true CN109460396A (en) | 2019-03-12 |
| CN109460396B CN109460396B (en) | 2024-06-04 |
Family
ID=65607600
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811191482.8A Active CN109460396B (en) | 2018-10-12 | 2018-10-12 | Model processing method and device, storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109460396B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109992258A (en) * | 2019-04-02 | 2019-07-09 | 北京市天元网络技术股份有限公司 | A kind of flexible implementation model configuration method and device |
| CN111367891A (en) * | 2020-03-30 | 2020-07-03 | 中国建设银行股份有限公司 | Method, device and equipment for calling modeling intermediate data and readable storage medium |
| CN111949514A (en) * | 2020-07-13 | 2020-11-17 | 深圳地平线机器人科技有限公司 | Model prediction method, device and storage medium |
| CN113011138A (en) * | 2019-12-19 | 2021-06-22 | 北京懿医云科技有限公司 | Information processing method, information processing device, electronic equipment and storage medium |
| CN113806180A (en) * | 2021-09-23 | 2021-12-17 | 腾云悦智科技(深圳)有限责任公司 | Unsupervised intelligent noise reduction processing method |
| CN114722025A (en) * | 2022-03-10 | 2022-07-08 | 平安科技（深圳）有限公司 | Data prediction method, device and equipment based on prediction model and storage medium |
| CN114816506A (en) * | 2022-04-21 | 2022-07-29 | 北京金堤科技有限公司 | Model feature rapid processing method and device, storage medium and electronic equipment |
| WO2022206567A1 (en) * | 2021-03-30 | 2022-10-06 | 华为技术有限公司 | Method and apparatus for training management and control model, and system |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004287094A (en) * | 2003-03-20 | 2004-10-14 | Fujitsu Ltd | Method and program for presenting operation procedure in on-line learning system |
| JP2013245927A (en) * | 2012-05-29 | 2013-12-09 | Japan Radio Co Ltd | Training support system |
| US8775341B1 (en) * | 2010-10-26 | 2014-07-08 | Michael Lamport Commons | Intelligent control with hierarchical stacked neural networks |
| CN106548675A (en) * | 2016-11-08 | 2017-03-29 | 湖南拓视觉信息技术有限公司 | Virtual military training method and device |
| US20170213156A1 (en) * | 2016-01-27 | 2017-07-27 | Bonsai AI, Inc. | Artificial intelligence engine having multiple independent processes on a cloud based platform configured to scale |
| WO2017193769A1 (en) * | 2016-05-11 | 2017-11-16 | 星环信息科技（上海）有限公司 | Method and apparatus for conversion between machine learning models |
| CN107678951A (en) * | 2017-09-21 | 2018-02-09 | 平安科技（深圳）有限公司 | Test exemple automation management method, device, equipment and storage medium |
| CN108509453A (en) * | 2017-02-27 | 2018-09-07 | 华为技术有限公司 | A kind of information processing method and device |
-
2018
- 2018-10-12 CN CN201811191482.8A patent/CN109460396B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004287094A (en) * | 2003-03-20 | 2004-10-14 | Fujitsu Ltd | Method and program for presenting operation procedure in on-line learning system |
| US8775341B1 (en) * | 2010-10-26 | 2014-07-08 | Michael Lamport Commons | Intelligent control with hierarchical stacked neural networks |
| JP2013245927A (en) * | 2012-05-29 | 2013-12-09 | Japan Radio Co Ltd | Training support system |
| US20170213156A1 (en) * | 2016-01-27 | 2017-07-27 | Bonsai AI, Inc. | Artificial intelligence engine having multiple independent processes on a cloud based platform configured to scale |
| WO2017193769A1 (en) * | 2016-05-11 | 2017-11-16 | 星环信息科技（上海）有限公司 | Method and apparatus for conversion between machine learning models |
| CN106548675A (en) * | 2016-11-08 | 2017-03-29 | 湖南拓视觉信息技术有限公司 | Virtual military training method and device |
| CN108509453A (en) * | 2017-02-27 | 2018-09-07 | 华为技术有限公司 | A kind of information processing method and device |
| CN107678951A (en) * | 2017-09-21 | 2018-02-09 | 平安科技（深圳）有限公司 | Test exemple automation management method, device, equipment and storage medium |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109992258A (en) * | 2019-04-02 | 2019-07-09 | 北京市天元网络技术股份有限公司 | A kind of flexible implementation model configuration method and device |
| CN113011138A (en) * | 2019-12-19 | 2021-06-22 | 北京懿医云科技有限公司 | Information processing method, information processing device, electronic equipment and storage medium |
| CN113011138B (en) * | 2019-12-19 | 2023-09-15 | 北京懿医云科技有限公司 | Information processing method, information processing device, electronic equipment and storage medium |
| CN111367891A (en) * | 2020-03-30 | 2020-07-03 | 中国建设银行股份有限公司 | Method, device and equipment for calling modeling intermediate data and readable storage medium |
| CN111949514A (en) * | 2020-07-13 | 2020-11-17 | 深圳地平线机器人科技有限公司 | Model prediction method, device and storage medium |
| WO2022206567A1 (en) * | 2021-03-30 | 2022-10-06 | 华为技术有限公司 | Method and apparatus for training management and control model, and system |
| CN113806180A (en) * | 2021-09-23 | 2021-12-17 | 腾云悦智科技(深圳)有限责任公司 | Unsupervised intelligent noise reduction processing method |
| CN114722025A (en) * | 2022-03-10 | 2022-07-08 | 平安科技（深圳）有限公司 | Data prediction method, device and equipment based on prediction model and storage medium |
| CN114816506A (en) * | 2022-04-21 | 2022-07-29 | 北京金堤科技有限公司 | Model feature rapid processing method and device, storage medium and electronic equipment |
| CN114816506B (en) * | 2022-04-21 | 2024-08-09 | 北京金堤科技有限公司 | Quick processing method and device for model features, storage medium and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109460396B (en) | 2024-06-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109460396A (en) | Model treatment method and device, storage medium and electronic equipment | |
| US11822906B2 (en) | Industrial programming development with a converted industrial control program | |
| CN112631555B (en) | System and method for developing industrial applications | |
| US20210294734A1 (en) | Testing framework for automation objects | |
| US10234853B2 (en) | Systems and methods for managing industrial assets | |
| US20210405975A1 (en) | Maintenance and commissioning | |
| US11947943B2 (en) | Industrial automation smart object inheritance | |
| US10977076B2 (en) | Method and apparatus for processing a heterogeneous cluster-oriented task | |
| CN109739478A (en) | Front end project automated construction method, device, storage medium and electronic equipment | |
| CN109961151A (en) | For the system for calculating service of machine learning and for the method for machine learning | |
| CN112639794A (en) | Quantum circuit design | |
| JP2019536185A (en) | System and method for monitoring and analyzing computer and network activity | |
| CN109685089A (en) | The system and method for assessment models performance | |
| US20230305813A1 (en) | Continuous integration and development of code in a secure environment | |
| CN110166276A (en) | A kind of localization method, device, terminal device and the medium of frame synchronization exception | |
| CN112417938B (en) | Generating conceptual images of human gestures using machine learning models | |
| CN106951248A (en) | Add method, device and the readable storage medium storing program for executing of code | |
| CN110515944A (en) | Date storage method, storage medium and electronic equipment based on distributed data base | |
| CN109284126A (en) | Class libraries automatic update method, device, electronic equipment, storage medium | |
| US20180189039A1 (en) | Automatic generation of manual coding suggestions for conversion of application programs to off-line environment | |
| CN110480633A (en) | A kind of method, apparatus and storage medium controlling equipment | |
| US20180189038A1 (en) | Automatic conversion of application program code listing segments for off-line environment | |
| US20200380530A1 (en) | Automatic internet of things enabled contract compliance monitoring | |
| US11074090B2 (en) | Virtual action-based troubleshooter | |
| CN109522355A (en) | Control method, device, medium and the electronic equipment of data handling procedure |
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 |