CN113485697A - Model construction operation service method and system under artificial intelligence framework - Google Patents
Model construction operation service method and system under artificial intelligence framework Download PDFInfo
- Publication number
- CN113485697A CN113485697A CN202110630083.2A CN202110630083A CN113485697A CN 113485697 A CN113485697 A CN 113485697A CN 202110630083 A CN202110630083 A CN 202110630083A CN 113485697 A CN113485697 A CN 113485697A
- Authority
- CN
- China
- Prior art keywords
- model
- service system
- operation service
- artificial intelligence
- deployment
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 32
- 238000010276 construction Methods 0.000 title claims abstract description 22
- 238000012549 training Methods 0.000 claims abstract description 29
- 230000007423 decrease Effects 0.000 claims abstract description 18
- 238000005457 optimization Methods 0.000 claims abstract description 14
- 238000012795 verification Methods 0.000 claims abstract description 14
- 239000008280 blood Substances 0.000 claims description 11
- 210000004369 blood Anatomy 0.000 claims description 11
- 230000000694 effects Effects 0.000 claims description 6
- 230000002159 abnormal effect Effects 0.000 claims description 4
- 238000001514 detection method Methods 0.000 claims description 3
- 238000010200 validation analysis Methods 0.000 claims 1
- 238000012544 monitoring process Methods 0.000 description 8
- 238000003860 storage Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 7
- 230000000007 visual effect Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000004590 computer program Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 235000019800 disodium phosphate Nutrition 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F8/00—Arrangements for software engineering
- G06F8/30—Creation or generation of source code
- G06F8/35—Creation or generation of source code model driven
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F8/00—Arrangements for software engineering
- G06F8/60—Software deployment
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a model construction operation service method and a system under an artificial intelligence framework, wherein the method comprises the following steps: acquiring a trained model, and registering in a model operation service system according to relevant parameters of the model; uploading the training codes of the model to a GIT library in the model operation service system; a model deployment module in the model operation service system acquires a model code and deploys the model through the model code; carrying out model gray scale verification on the deployed model, and formally uploading the successfully verified model; obtaining model operation data in real time, comparing the operation data with preset data, and judging whether the model has a decline phenomenon; if so, performing iterative optimization on the model; if not, the model continues to run. The method greatly simplifies the model deployment online process, improves the model deployment efficiency, reduces manual operation and reduces the model operation cost.
Description
Technical Field
The invention relates to the technical field of information, in particular to a method and a system for model construction and operation service under an artificial intelligence framework.
Background
With the coming of the global artificial intelligence era, artificial intelligence technologies such as big data, machine learning, deep learning and the like are widely applied to various industry fields, more models are applied to business scenes such as risk prevention and control, anti-fraud and the like, and a set of model construction and operation system is gradually formed in the process. Modeling personnel in each industry perform model training development work on a modeling platform according to actual business scenes, after model training is completed, the model is deployed on line, the model is put into production environment application in a batch pre-estimation or real-time pre-estimation mode, meanwhile, after the model is deployed on line, the modeling personnel can continuously count the operation condition and effect index of the model through corresponding tools, after model performance is declined, the model is iteratively optimized, the model is retrained, and the trained model is re-deployed on line after the model performance index meets the requirement to replace the original model.
The existing model construction and operation system has defects which are mainly reflected in the following points: 1. the model deployment process usually needs more manual intervention, the automation degree is low, for the model with repeated iterative optimization, the deployment operation needs to be carried out for multiple times, and the human resource consumption is high; 2. model information, model input and output blood relationship, model performance indexes and the like after the model is deployed on line cannot form unified visual monitoring management, and the off-line operation cost is high.
Disclosure of Invention
In order to solve the technical problems, the invention provides a model construction operation service method and a system under an artificial intelligence framework, which reduce the model operation cost by carrying out unified visual monitoring management on model information, model input/output relationship, model performance indexes and the like after online model deployment, and realize a robust deployment function of the model by matching with an independent model deployment API service, realize the automatic model deployment and improve the model deployment efficiency.
The first aspect of the present invention provides a method for model construction and operation service under an artificial intelligence framework, comprising:
acquiring a trained model, and registering in a model operation service system according to relevant parameters of the model;
uploading the training codes of the model to a GIT library in the model operation service system;
a model deployment module in the model operation service system acquires a model code and deploys the model through the model code;
and carrying out model gray scale verification on the deployed model, and formally uploading the successfully verified model.
Further, after the successfully verified model is formally online, the method further includes:
obtaining model operation data in real time, comparing the operation data with preset data, and judging whether the model has a decline phenomenon; if so, performing iterative optimization on the model; if not, the model continues to run.
Further, after the successfully verified model is formally online, the method further includes:
obtaining model operation data in real time, comparing the operation data with preset data, and judging whether the model has a decline phenomenon; if so, performing iterative optimization on the model; if not, the model continues to run.
Further, the iteratively optimizing the model includes:
re-establishing a training model according to the actual scene to obtain a new model;
and after the decline model is offline, uploading the new model to a model operation service system.
Further, the performing model grayscale verification on the deployed model includes:
and verifying the model information, the input and output blood relationship of the model and the performance index of the model.
The second party of the invention, man, provides a model construction and operation service system under an artificial intelligence framework, comprising:
the registration module is used for acquiring the trained model and registering in the model operation service system according to the relevant parameters of the model;
the code uploading module is used for uploading the training codes of the model to a GIT library in the model operation service system;
the model deployment module is used for acquiring a model code by the model deployment module in the model operation service system and deploying the model through the model code;
and the model verification module is used for carrying out model gray scale verification on the deployed model, and formally uploading the successfully verified model.
Further, the model construction and operation service system under the artificial intelligence framework further includes:
the model iteration module is used for acquiring model operation data in real time, comparing the operation data with preset data and judging whether the model has a decline phenomenon or not; if so, performing iterative optimization on the model; if not, the model continues to run.
Further, the model iteration module is further configured to:
re-establishing a training model according to the actual scene to obtain a new model;
and after the decline model is offline, uploading the new model to a model operation service system.
Further, the model deployment module is further configured to:
and verifying the model information, the input and output blood relationship of the model and the performance index of the model.
A third aspect of the present invention provides a model operation service system, including:
the model registration unit is used for registering model information which needs to be deployed on line after model training is finished;
the model deployment unit is used for deploying the registered model;
the model Git library unit is used for storing the training codes of the models;
and the model performance detection unit is used for checking the performance index operation data of the online model, and taking corresponding measures when the model is degenerated or the model operation state is abnormal, so that the stable operation and the optimal effect of the model are ensured.
Further, the model operation service system further includes:
the model information query unit is used for querying parameter information of the online model;
the model deployment API service unit is used for acquiring a model code from the model Git library unit after receiving a model deployment request;
and the model input and output unit is used for checking the input data and the output data of the online model.
Compared with the prior art, the embodiment of the invention has the beneficial effects that:
the invention provides a model construction operation service method and a system under an artificial intelligence framework, wherein the method comprises the following steps: acquiring a trained model, and registering in a model operation service system according to relevant parameters of the model; uploading the training codes of the model to a GIT library in the model operation service system; a model deployment module in the model operation service system acquires a model code and deploys the model through the model code; carrying out model gray scale verification on the deployed model, and formally uploading the successfully verified model; obtaining model operation data in real time, comparing the operation data with preset data, and judging whether the model has a decline phenomenon; if so, performing iterative optimization on the model; if not, the model continues to run. The method realizes the one-key deployment function of the model after the model training is finished, greatly simplifies the online process of model deployment, and improves the model deployment efficiency in the process of repeated iterative optimization of the model; unified visual monitoring management reduces manual operation, reduces the model operation cost.
Drawings
In order to more clearly illustrate the technical solution of the present invention, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a flowchart of a method for model building and operation service under an artificial intelligence framework according to an embodiment of the present invention;
FIG. 2 is a flowchart of a method for model building and operation service under an artificial intelligence framework according to another embodiment of the present invention;
fig. 3 is a structural diagram of a model building operation service system under an artificial intelligence framework according to an embodiment of the present invention;
FIG. 4 is a flowchart of a method for model building and operation service under an artificial intelligence framework according to another embodiment of the present invention;
fig. 5 is a diagram of an apparatus of a model building operation service system under an artificial intelligence framework according to an embodiment of the present invention;
FIG. 6 is a diagram of an apparatus for a model building operation service system under an artificial intelligence framework according to another embodiment of the present invention;
fig. 7 is a block diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be understood that the step numbers used herein are for convenience of description only and are not intended as limitations on the order in which the steps are performed.
It is to be understood that the terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the specification of the present invention and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
The terms "comprises" and "comprising" indicate the presence of the described features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
The term "and/or" refers to and includes any and all possible combinations of one or more of the associated listed items.
A first aspect.
Referring to fig. 1-2, an embodiment of the present invention provides a method for model building and operation service under an artificial intelligence framework, including:
and S10, acquiring the trained model, and registering in the model operation service system according to the relevant parameters of the model.
And S20, uploading the training codes of the model to a GIT library in the model operation service system.
S30, the model deployment module in the model operation service system obtains the model code, and deploys the model through the model code.
And S40, carrying out model gray scale verification on the deployed model, and formally putting the successfully verified model on line.
In a specific embodiment, the performing model grayscale verification on the deployed model includes:
and verifying the model information, the input and output blood relationship of the model and the performance index of the model.
In a specific embodiment, after step S40, the method further includes:
s50, obtaining model operation data in real time, comparing the operation data with preset data, and judging whether the model has a decline phenomenon; if so, performing iterative optimization on the model; if not, the model continues to run.
In a specific embodiment, the iteratively optimizing the model includes:
re-establishing a training model according to the actual scene to obtain a new model;
and after the decline model is offline, uploading the new model to a model operation service system.
In an embodiment, referring to fig. 3, the present invention provides a model building operation service system under an artificial intelligence framework, including:
1) model registration: the module registers model information which needs to be deployed online after model training is completed by a modeling person on a modeling platform, and the model information can be displayed on a model construction operation service system after the registration is completed;
2) model deployment: the module realizes a key deployment function of the model on the modeling platform by clicking a corresponding menu by a modeling worker;
3) and (3) inputting and outputting a model: the module is used for checking input and output data of the online model, inputting table data used for training the finger model, and outputting result data after the finger model completes estimation, and management of the input and output blood relationship of the model can be realized through the module;
4) monitoring model performance indexes: the module is used for checking performance index data of the online model, and can find and take corresponding measures in time under the condition that the model effect is degraded or the model operation state is abnormal, so as to ensure the stable operation and the optimal effect of the model, wherein the model performance indexes mainly comprise operation indexes, technical indexes and operation indexes;
5) inquiring model information; the module is used for checking and managing various basic information of the online model, and mainly comprises information such as a model name, modeling personnel, a modeling platform, a model GIT library address, a model scene and the like;
6) model deployment API services: after receiving a model deployment request, the module pulls a corresponding code from the model GIT library to a modeling platform to create a project, and completes the deployment operation of the model;
7) model GIT library: the module is used for storing the model codes uploaded to the model construction operation service system and realizing the unified management of the model versions.
Referring to fig. 4, the basic process of the present system includes:
1) after a modeling person trains a model on a modeling platform, the system is used for registering the trained model, the registration content comprises model basic information, model performance indexes, model input and output data and the like, and the registration process is completed by importing excel forms on a system interface;
2) after the model registration is completed, uploading the trained model codes on a system interface, and storing the model codes into a model GIT library;
3) after the model codes are uploaded to the GIT library, a model deployment menu button corresponding to the model is found on a system interface, and after clicking, the system model deployment API service pulls the corresponding model codes from the model GIT library to a modeling platform to create a project;
4) after the gray level verification of the model passes, the model is formally online, and then unified visual monitoring management can be carried out on model information, model input and output blood relationship, model performance indexes and the like on the system;
5) comparing the monitored model performance index data with a preset normal target value to judge whether the model has a decline phenomenon, if the model has the decline phenomenon, performing iterative optimization on the model, if the model does not have the decline phenomenon, continuing the operation of the model, in the model optimization process, training the model on a modeling platform again according to an actual scene, after the model training is completed, firstly putting off the old model, then uploading the newly trained model code to a system model GIT library, and deploying the model on line according to the previous process, thereby circulating.
The invention has the beneficial effects that:
1. the model one-key deployment function of the model after model training is completed can be realized by using the model construction operation service system, the model deployment online process is greatly simplified, and the model deployment efficiency is improved in the process of repeated iterative optimization of the model;
2. the model construction operation service system can be used for realizing unified visual monitoring management of model information, model input and output blood relationship and model performance indexes, manual operation is reduced, and model operation cost is reduced.
The invention mainly aims at the field of artificial intelligence, and mainly comprises the module functions of model one-key deployment, model information management, model input and output blood relationship management, model performance evaluation index monitoring and the like of a model construction operation service system under an artificial intelligence framework:
the points of protection are mainly:
1. a key deployment function module of the model construction operation service system is applied to the model deployment online after the model training is finished;
2. the module functions of model information management, model input and output relationship management, model performance evaluation index monitoring and the like of the model construction operation service system are applied to model operation management after model deployment is on line.
A second aspect.
Referring to fig. 5-6, the present invention provides a model building operation service system under an artificial intelligence framework, comprising:
and the registration module 10 is configured to obtain the trained model, and register in the model operation service system according to the relevant parameters of the model.
And the code uploading module 20 is used for uploading the training codes of the model to a GIT library in the model operation service system.
And the model deployment module 30 is used for acquiring a model code by the model deployment module in the model operation service system and deploying the model through the model code.
In a specific embodiment, the model deployment module 30 is further configured to:
and verifying the model information, the input and output blood relationship of the model and the performance index of the model.
And the model verification module 40 is used for performing model gray scale verification on the deployed model, and formally uploading the successfully verified model.
In a specific embodiment, the method further comprises:
the model iteration module 50 is used for acquiring model operation data in real time, comparing the operation data with preset data and judging whether the model has a decline phenomenon or not; if so, performing iterative optimization on the model; if not, the model continues to run.
In a specific embodiment, the model iterating module 50 is further configured to:
re-establishing a training model according to the actual scene to obtain a new model;
and after the decline model is offline, uploading the new model to a model operation service system.
In a third aspect.
One embodiment of the present invention provides a model operation service system, including:
the model registration unit is used for registering model information which needs to be deployed on line after model training is finished;
the model deployment unit is used for deploying the registered model;
the model Git library unit is used for storing the training codes of the models;
and the model performance detection unit is used for checking the performance index operation data of the online model, and taking corresponding measures when the model is degenerated or the model operation state is abnormal, so that the stable operation and the optimal effect of the model are ensured.
In a specific embodiment, the method further comprises:
the model information query unit is used for querying parameter information of the online model;
the model deployment API service unit is used for acquiring a model code from the model Git library unit after receiving a model deployment request;
and the model input and output unit is used for checking the input data and the output data of the online model.
A fourth aspect.
The present invention provides an electronic device, including:
a processor, a memory, and a bus;
the bus is used for connecting the processor and the memory;
the memory is used for storing operation instructions;
the processor is configured to invoke the operation instruction, and the executable instruction enables the processor to execute an operation corresponding to the model construction operation service method under the artificial intelligence framework shown in the first aspect of the present application.
In an alternative embodiment, an electronic device is provided, as shown in fig. 7, the electronic device 5000 shown in fig. 7 includes: a processor 5001 and a memory 5003. The processor 5001 and the memory 5003 are coupled, such as via a bus 5002. Optionally, the electronic device 5000 may also include a transceiver 5004. It should be noted that the transceiver 5004 is not limited to one in practical application, and the structure of the electronic device 5000 is not limited to the embodiment of the present application.
The processor 5001 may be a CPU, general purpose processor, DSP, ASIC, FPGA or other programmable logic device, transistor logic device, hardware component, or any combination thereof. Which may implement or perform the various illustrative logical blocks, modules, and circuits described in connection with the disclosure. The processor 5001 may also be a combination of processors implementing computing functionality, e.g., a combination comprising one or more microprocessors, a combination of DSPs and microprocessors, or the like.
The memory 5003 may be, but is not limited to, a ROM or other type of static storage device that can store static information and instructions, a RAM or other type of dynamic storage device that can store information and instructions, an EEPROM, a CD-ROM or other optical disk storage, optical disk storage (including compact disk, laser disk, optical disk, digital versatile disk, blu-ray disk, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer.
The memory 5003 is used for storing application program codes for executing the present solution, and the execution is controlled by the processor 5001. The processor 5001 is configured to execute application program code stored in the memory 5003 to implement the teachings of any of the foregoing method embodiments.
Among them, electronic devices include but are not limited to: mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and the like, and fixed terminals such as digital TVs, desktop computers, and the like.
A fifth aspect.
The present invention provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements a method for model building and operation service under an artificial intelligence framework as shown in the first aspect of the present application.
Yet another embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored, which, when run on a computer, enables the computer to perform the corresponding content in the aforementioned method embodiments.
Claims (10)
1. A model construction operation service method under an artificial intelligence framework is characterized by comprising the following steps:
acquiring a trained model, and registering in a model operation service system according to relevant parameters of the model;
uploading the training codes of the model to a GIT library in the model operation service system;
a model deployment module in the model operation service system acquires a model code and deploys the model through the model code;
and carrying out model gray scale verification on the deployed model, and formally uploading the successfully verified model.
2. The method for model building and operation service under artificial intelligence framework according to claim 1, wherein after the successfully verified model is formally brought online, the method further comprises:
obtaining model operation data in real time, comparing the operation data with preset data, and judging whether the model has a decline phenomenon; if so, performing iterative optimization on the model; if not, the model continues to run.
3. The method for model building and operation service under artificial intelligence framework according to claim 2, wherein said iteratively optimizing said model comprises:
re-establishing a training model according to the actual scene to obtain a new model;
and after the decline model is offline, uploading the new model to a model operation service system.
4. The method for model construction and operation service under artificial intelligence framework according to claim 1, wherein said performing model gray scale validation on the deployed model comprises:
and verifying the model information, the input and output blood relationship of the model and the performance index of the model.
5. A model construction operation service system under an artificial intelligence framework, comprising:
the registration module is used for acquiring the trained model and registering in the model operation service system according to the relevant parameters of the model;
the code uploading module is used for uploading the training codes of the model to a GIT library in the model operation service system;
the model deployment module is used for acquiring a model code by the model deployment module in the model operation service system and deploying the model through the model code;
and the model verification module is used for carrying out model gray scale verification on the deployed model, and formally uploading the successfully verified model.
6. The model building and operation service system under artificial intelligence framework of claim 5, further comprising:
the model iteration module is used for acquiring model operation data in real time, comparing the operation data with preset data and judging whether the model has a decline phenomenon or not; if so, performing iterative optimization on the model; if not, the model continues to run.
7. The model building operation service system under artificial intelligence framework of claim 6, wherein the model iteration module is further configured to:
re-establishing a training model according to the actual scene to obtain a new model;
and after the decline model is offline, uploading the new model to a model operation service system.
8. The model building operation service system under artificial intelligence framework of claim 6, wherein the model deployment module is further configured to:
and verifying the model information, the input and output blood relationship of the model and the performance index of the model.
9. A model operations service system, comprising:
the model registration unit is used for registering model information which needs to be deployed on line after model training is finished;
the model deployment unit is used for deploying the registered model;
the model Git library unit is used for storing the training codes of the models;
and the model performance detection unit is used for checking the performance index operation data of the online model, and taking corresponding measures when the model is degenerated or the model operation state is abnormal, so that the stable operation and the optimal effect of the model are ensured.
10. The model operations service system of claim 9, further comprising:
the model information query unit is used for querying parameter information of the online model;
the model deployment API service unit is used for acquiring a model code from the model Git library unit after receiving a model deployment request;
and the model input and output unit is used for checking the input data and the output data of the online model.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110630083.2A CN113485697A (en) | 2021-06-07 | 2021-06-07 | Model construction operation service method and system under artificial intelligence framework |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110630083.2A CN113485697A (en) | 2021-06-07 | 2021-06-07 | Model construction operation service method and system under artificial intelligence framework |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113485697A true CN113485697A (en) | 2021-10-08 |
Family
ID=77934261
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110630083.2A Pending CN113485697A (en) | 2021-06-07 | 2021-06-07 | Model construction operation service method and system under artificial intelligence framework |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113485697A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114707654A (en) * | 2022-06-06 | 2022-07-05 | 浙江大学 | Algorithm training reasoning performance visualization method and device based on artificial intelligence framework |
CN117056238A (en) * | 2023-10-11 | 2023-11-14 | 深圳鲲云信息科技有限公司 | Method and computing device for verifying correctness of model conversion under deployment framework |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109492749A (en) * | 2018-10-12 | 2019-03-19 | 平安科技(深圳)有限公司 | The method and device of neural network model online service is realized in a local network |
-
2021
- 2021-06-07 CN CN202110630083.2A patent/CN113485697A/en active Pending
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109492749A (en) * | 2018-10-12 | 2019-03-19 | 平安科技(深圳)有限公司 | The method and device of neural network model online service is realized in a local network |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114707654A (en) * | 2022-06-06 | 2022-07-05 | 浙江大学 | Algorithm training reasoning performance visualization method and device based on artificial intelligence framework |
CN114707654B (en) * | 2022-06-06 | 2022-08-23 | 浙江大学 | Algorithm training reasoning performance visualization method and device based on artificial intelligence framework |
CN117056238A (en) * | 2023-10-11 | 2023-11-14 | 深圳鲲云信息科技有限公司 | Method and computing device for verifying correctness of model conversion under deployment framework |
CN117056238B (en) * | 2023-10-11 | 2024-01-30 | 深圳鲲云信息科技有限公司 | Method and computing device for verifying correctness of model conversion under deployment framework |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113485697A (en) | Model construction operation service method and system under artificial intelligence framework | |
CN110674047B (en) | Software testing method and device and electronic equipment | |
CN107807841B (en) | Server simulation method, device, equipment and readable storage medium | |
CN113268336B (en) | Service acquisition method, device, equipment and readable medium | |
CN112905459B (en) | Service interface testing method and device, electronic equipment and storage medium | |
CN108111364B (en) | Service system testing method and device | |
CN110955715A (en) | ERP system, data conversion method and device of target platform and electronic equipment | |
CN112800063A (en) | Automatic label passing method and device based on data structure | |
CN116011955A (en) | Robot flow automation demand realization method, device, equipment and storage medium | |
CN115983191A (en) | Test point verification method and related device | |
CN111949510A (en) | Test processing method and device, electronic equipment and readable storage medium | |
CN113434938B (en) | BIM model checking method, BIM model checking device, computer equipment and storage medium | |
CN114817707A (en) | Method and device for creating node and problem, electronic equipment and storage medium | |
CN114185805A (en) | Embedded point verification method, device, equipment and storage medium | |
CN110515653B (en) | Document generation method and device, electronic equipment and computer readable storage medium | |
CN112395575A (en) | Authority management method, device, equipment and storage medium | |
CN112328473A (en) | Code automation integration test method and device and electronic equipment | |
CN112181825A (en) | Test case library construction method and device, electronic equipment and medium | |
CN111679924A (en) | Component software system reliability simulation method and device and electronic equipment | |
CN112650679B (en) | Test verification method, device and computer system | |
US20120005055A1 (en) | Dynamic computation of roi for test automation | |
CN112597717B (en) | IP verification method and device and electronic equipment | |
CN108628750B (en) | Test code processing method and device | |
CN111857679B (en) | Method and device for generating script program and script program processing system | |
CN117971679A (en) | Intelligent contract test data generation method, device, equipment and storage medium |
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 |