CN111260134A - Debugging assistance apparatus, product debugging apparatus, computer readable medium - Google Patents

Debugging assistance apparatus, product debugging apparatus, computer readable medium Download PDF

Info

Publication number
CN111260134A
CN111260134A CN202010053435.8A CN202010053435A CN111260134A CN 111260134 A CN111260134 A CN 111260134A CN 202010053435 A CN202010053435 A CN 202010053435A CN 111260134 A CN111260134 A CN 111260134A
Authority
CN
China
Prior art keywords
debugging
product
model
parameters
data
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
Application number
CN202010053435.8A
Other languages
Chinese (zh)
Inventor
刘洁
陈志熙
石佳
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Nanjing Starfire Technology Co ltd
Original Assignee
Nanjing Starfire Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Nanjing Starfire Technology Co ltd filed Critical Nanjing Starfire Technology Co ltd
Priority to CN202010053435.8A priority Critical patent/CN111260134A/en
Publication of CN111260134A publication Critical patent/CN111260134A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06395—Quality analysis or management
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/04—Manufacturing
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30—Computing systems specially adapted for manufacturing

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • General Physics & Mathematics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Development Economics (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Educational Administration (AREA)
  • Marketing (AREA)
  • General Health & Medical Sciences (AREA)
  • Game Theory and Decision Science (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Health & Medical Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • Biophysics (AREA)
  • Software Systems (AREA)
  • Mathematical Physics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Computing Systems (AREA)
  • Molecular Biology (AREA)
  • Evolutionary Computation (AREA)
  • Computational Linguistics (AREA)
  • Artificial Intelligence (AREA)
  • Biomedical Technology (AREA)
  • Manufacturing & Machinery (AREA)
  • Primary Health Care (AREA)
  • Debugging And Monitoring (AREA)

Abstract

The application discloses a debugging auxiliary device, an apparatus, a product debugging device and a computer readable medium. The auxiliary device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the following steps when executing the computer program: evaluating product debugging according to the received product debugging data and a preset performance index, wherein the product debugging data is obtained by debugging a product by product debugging equipment; if the product debugging data is consistent with the performance index, sending a product debugging completion instruction to product debugging equipment; or if the product debugging data is inconsistent with the performance index, adjusting the debugging parameters of the product based on the product debugging model to obtain optimized debugging parameters, sending out a product debugging instruction, executing the product debugging instruction by product debugging equipment, and completing product debugging according to the optimized debugging parameters.

Description

Debugging assistance apparatus, product debugging apparatus, computer readable medium
Technical Field
The present application relates to the field of artificial intelligence technologies, and in particular, to a debugging assistance device, an apparatus, a product debugging device, and a computer readable medium.
Background
Because the product is in the design, processing and the in-process of assembly, inevitable can have the deviation, cause the performance of product to probably deviate from the design original intention, consequently just need debug the product, make the performance of product satisfy the requirement of performance index.
In the existing product debugging equipment, the debugging process is mechanical and rigid, and the product cannot be debugged to the best effect, for example, in the debugging process of the cavity filter, only a tuning screw is mechanically screwed to a fixed coordinate position, and the debugging effect cannot be guaranteed; or, in the product debugging process, a debugging person is relied on to perform continuous adjustment attempts on the product through the debugging equipment to find a state meeting the performance index requirement. Therefore, how to ensure the product debugging effect, shorten the product debugging time, and improve the product debugging efficiency has become a problem that needs to be solved urgently.
Disclosure of Invention
In view of the above, the present application provides a debugging aid, an apparatus, a product debugging device and a computer readable medium for adjusting or alleviating the above-mentioned problems in the prior art.
The embodiment of the application discloses the following technical scheme:
the application provides a debugging auxiliary assembly, includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the processor implementing the following steps when executing the computer program: evaluating product debugging according to received product debugging data and a preset performance index, wherein the product debugging data is obtained by debugging the product by product debugging equipment; if the product debugging data is consistent with the performance index, sending a product debugging completion instruction to the product debugging equipment; or if the product debugging data is inconsistent with the performance index, adjusting the debugging parameters of the product based on a product debugging model to obtain optimized debugging parameters, sending a product debugging instruction, executing the product debugging instruction by the product debugging equipment, and completing the product debugging according to the optimized debugging parameters.
Optionally, in any embodiment of the application, in the step implemented when the processor executes the computer program, if the product debugging data is inconsistent with the performance index, the debugging parameter is adjusted based on a product debugging model to obtain an optimized debugging parameter, and a product debugging instruction is issued, where the product debugging apparatus executes the product debugging instruction, and the product debugging is completed according to the optimized debugging parameter, including: if the product debugging data is inconsistent with the performance index, adjusting the debugging parameters according to the product debugging data based on the product debugging model, and sending out a model debugging instruction; executing the model debugging instruction based on a performance prediction model, debugging a product model according to the adjusted debugging parameters, and generating model debugging data, wherein the product model corresponds to the product; generating a model debugging evaluation result according to the model debugging data and the performance index, wherein the model debugging evaluation result is used for evaluating the debugging of the product model; and obtaining the optimized debugging parameters according to the model debugging evaluation result, sending the product debugging instruction, executing the product debugging instruction by the product debugging equipment, and completing the product debugging according to the optimized debugging parameters.
Optionally, in any embodiment of the application, in the step implemented when the processor executes the computer program, obtaining the optimized debugging parameter according to the model debugging evaluation result, sending the product debugging instruction, executing the product debugging instruction by the product debugging device, and completing the product debugging according to the optimized debugging parameter, the method includes: and if the model debugging data is consistent with the performance index, outputting the adjusted debugging parameters as the optimized debugging parameters, sending out the product debugging instructions, executing the product debugging instructions by the product debugging equipment, and completing the product debugging according to the optimized debugging parameters. Or if the model debugging data is inconsistent with the performance index, adjusting the adjusted debugging parameters according to the model debugging data based on the product debugging model to generate optimized debugging parameters, sending the product debugging instructions, executing the product debugging instructions by the product debugging equipment, and completing the product debugging according to the optimized debugging parameters.
Optionally, in any embodiment of the application, in the step implemented when the processor executes the computer program, if the model debugging data is inconsistent with the performance index, adjusting the adjusted debugging parameter according to the model debugging data based on the product debugging model to generate the optimized debugging parameter, and issuing the product debugging instruction, where the product debugging apparatus executes the product debugging instruction, and the product debugging is completed according to the optimized debugging parameter, the method includes: if the model debugging data is inconsistent with the performance index, adjusting the adjusted debugging parameters according to the model debugging data based on the product debugging model, and sending out the model debugging instruction; executing the model debugging instruction based on the performance prediction model, debugging the product model according to the adjusted debugging parameters, and generating new model debugging data; generating a new model debugging evaluation result according to the new model debugging data and the performance index; and obtaining the optimized debugging parameters according to the new model debugging evaluation result, sending the product debugging instruction, executing the product debugging instruction by the product debugging equipment, and completing the product debugging according to the optimized debugging parameters.
Optionally, in any embodiment of the application, in the step implemented when the processor executes the computer program, obtaining the optimized debugging parameter according to the new model debugging evaluation result, issuing the product debugging instruction, executing the product debugging instruction by the product debugging device, and completing the product debugging according to the optimized debugging parameter, the method includes: and if the new model debugging data is inconsistent with the performance index and the adjusting times of the debugging parameters reach a preset threshold value, outputting the final debugging parameters as the optimized debugging parameters, sending the product debugging instructions, executing the product debugging instructions by the product debugging equipment, and completing the product debugging according to the optimized debugging parameters.
Optionally, in any embodiment of the present application, the product commissioning model is a machine learning model.
Optionally, in any embodiment of the present application, the machine learning model is a deep neural network model.
The embodiment of the application further provides product debugging equipment, and the product debugging equipment is used for debugging the product, generating product debugging data and sending the product debugging data to any one of the debugging auxiliary equipment.
An embodiment of the present application further provides a debugging auxiliary device, including: the performance evaluation unit is configured to evaluate the product debugging according to the received product debugging data and a preset performance index, wherein the product debugging data is obtained by debugging the product by product debugging equipment; the debugging output unit is configured to send a product debugging completion instruction to the product debugging equipment if the product debugging data is consistent with the performance index; or if the product debugging data is inconsistent with the performance index, adjusting the debugging parameters of the product based on a product debugging model to obtain optimized debugging parameters, sending a product debugging instruction, executing the product debugging instruction by the product debugging equipment, and completing the product debugging according to the optimized debugging parameters.
Optionally, in any embodiment of the present application, the debug output unit includes: the parameter adjusting subunit is configured to adjust the debugging parameters according to the product debugging data and the product debugging data based on the product debugging model and send out a model debugging instruction if the product debugging data is inconsistent with the performance index; the model debugging subunit is configured to execute the model debugging instruction based on a performance prediction model, debug a product model according to the adjusted debugging parameters, and generate model debugging data, wherein the product model corresponds to the product; the debugging evaluation subunit is configured to generate a model debugging evaluation result according to the model debugging data and the performance index, and the model debugging evaluation result is used for evaluating the debugging of the product model; and the parameter output subunit is configured to obtain the optimized debugging parameters according to the model debugging evaluation result, send the product debugging instruction, execute the product debugging instruction by the product debugging equipment, and complete the product debugging according to the optimized debugging parameters.
Optionally, in any embodiment of the present application, the parameter output subunit is further configured to, if the model debugging data is consistent with the performance index, output the adjusted debugging parameter as the optimized debugging parameter, and issue the product debugging instruction, where the product debugging device executes the product debugging instruction, and the product debugging is completed according to the optimized debugging parameter; or if the model debugging data is inconsistent with the performance index, adjusting the adjusted debugging parameters again according to the model debugging data based on the product debugging model to generate optimized debugging parameters, sending the product debugging instructions, executing the product debugging instructions by the product debugging equipment, and completing the product debugging according to the optimized debugging parameters.
The embodiment of the application further provides product debugging equipment, and the product debugging equipment is used for debugging the product, generating product debugging data and sending the product debugging data to any one of the debugging auxiliary equipment.
An embodiment of the present application further provides a computer-readable medium, where a computer program is stored in the debugging auxiliary device described in any one of the foregoing descriptions.
In the technical scheme of the embodiment of the application, when executing a computer program stored in a computer readable medium, a processor evaluates product debugging according to received product debugging data and a preset performance index, wherein the product debugging data is obtained by debugging a product by product debugging equipment; if the product debugging data is consistent with the performance index, sending a product debugging completion instruction to the product debugging equipment; or if the product debugging data is inconsistent with the performance index, adjusting the debugging parameters of the product based on a product debugging model to obtain optimized debugging parameters, sending a product debugging instruction, executing the product debugging instruction by the product debugging equipment, and completing the product debugging according to the optimized debugging parameters. Through the technology of the embodiment of the application, the process of repeatedly debugging the product can be finished by the processor through executing the computer program stored in the computer readable medium, the debugging parameters are optimized through continuously adjusting the debugging parameters of the product model by the product debugging model, the optimized debugging parameters meeting performance indexes are finally output, product debugging is finished by product debugging equipment, the product debugging time is greatly shortened, the product debugging efficiency is improved, and the energy spent in product debugging is saved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without inventive exercise.
FIG. 1 is a schematic diagram of an architecture of a product debugging system according to a first embodiment of the present application;
FIG. 2A is a flowchart illustrating a product debugging method implemented by a computer program executed by a processor of a debugging assistance device according to a second embodiment of the present application;
fig. 2B is a schematic flowchart of step S202 in a product debugging method implemented by a processor of a debugging assistance device executing a computer program according to a second embodiment of the present application;
FIG. 3A is a flowchart illustrating a product debugging model training method implemented by a computer program executed by a processor of a debugging assistance device according to a third embodiment of the present application;
fig. 3B is a schematic flowchart of step S302 in the method for training a product debugging model implemented by executing a computer program by a processor of a debugging auxiliary device according to the third embodiment of the present application;
FIG. 4A is a schematic structural diagram of a debugging aid according to a fourth embodiment of the present application;
FIG. 4B is a diagram illustrating a debug output unit in a debug assistance apparatus according to a fourth embodiment of the present application;
fig. 5A is a schematic structural diagram of a product debugging model training system in a debugging aid according to a fifth embodiment of the present application;
fig. 5B is a schematic structural diagram of a model adjustment unit in a debugging assistant device according to a fifth embodiment of the present application;
fig. 6 is a schematic structural diagram of a debugging aid according to a fifth embodiment of the present application;
fig. 7 is a hardware configuration of a debugging assistance apparatus according to a seventh embodiment of the present application.
Detailed Description
It is not necessary for any particular embodiment of the invention to achieve all of the above advantages at the same time.
In order to make the technical solutions of the present invention better understood, 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.
First embodiment
FIG. 1 is a schematic diagram of an architecture of a product debugging system according to a first embodiment of the present application; as shown in fig. 1, the system architecture includes: a product debugging device 101, a performance testing device 102, and a debugging auxiliary device 103;
the product debugging device 101 and the performance testing device 102 are deployed locally, the debugging auxiliary device 103 may be a local debugging auxiliary device or a cloud debugging auxiliary device, and the product debugging device 101, the performance testing device 102 and the debugging auxiliary device 103 may communicate with each other through a network;
the product debugging device 101 is configured to debug a product, and the performance testing device 102 is configured to test the product debugged by the product debugging device 101 to obtain product debugging data, and upload the product debugging data to the debugging auxiliary device 103 through the network;
the commissioning assistance device 103 comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor; the processor, when executing the computer program, implements the following flow:
evaluating the received product debugging data according to a preset performance index through a comparison function deployed in the debugging auxiliary equipment 103;
and realizing product debugging through the interaction of the product debugging model and the performance prediction model in the computer program. If the product debugging data is consistent with the performance index, sending a product debugging completion instruction to the product debugging equipment 101;
if the product debugging data is inconsistent with the performance index, the product debugging model adjusts debugging parameters of the product according to the product debugging data, sends out a model debugging instruction and interacts with the performance prediction model;
the performance prediction model is used for executing a model debugging instruction, debugging a product model according to the adjusted debugging parameters and generating model debugging data, wherein the product model corresponds to the product; the performance prediction model feeds back the model debugging data to the comparison function, and the comparison function evaluates the model debugging data according to the performance index;
if the model debugging data is consistent with the performance index, outputting the adjusted debugging parameters as the optimized debugging parameters, sending out product debugging instructions, sending the product debugging instructions to the product debugging equipment 101 through the network, executing the product debugging instructions by the product debugging equipment 101, debugging the product according to the optimized debugging parameters, and completing product debugging;
if the model debugging data is inconsistent with the performance index, the product debugging model adjusts the debugging parameters again according to the model debugging data, sends out a model debugging instruction and interacts with the performance prediction model;
if the adjustment times of the debugging parameters by the product debugging model reach a preset threshold value, outputting the final debugging parameters as the optimized debugging parameters, sending out product debugging instructions, sending the product debugging instructions to the product debugging equipment 101 through the network, executing the product debugging instructions by the product debugging equipment 101, debugging the product according to the optimized debugging parameters, and completing the product debugging.
Second embodiment
FIG. 2A is a flowchart illustrating a product debugging method implemented by a computer program executed by a processor of a debugging assistance device according to a second embodiment of the present application; as shown in fig. 2A, the product debugging method includes:
step S201, evaluating product debugging according to received product debugging data and preset performance indexes, wherein the product debugging data is obtained by debugging a product by product debugging equipment;
in this embodiment, the product debugging data may be generated in advance, the product to be debugged is debugged by the product debugging device, and then the debugged product is tested and generated by the performance testing device. The performance index corresponds to a product to be debugged, and can be a national standard, an industrial standard and an enterprise standard corresponding to the product, or a custom standard meeting use requirements according to actual application occasions of the product, and the like. The performance standard may be set by a debugger, and may be adjusted in real time according to the actual application of the product.
In this step, the product debugging data and the preset performance index can be compared through the comparison function so as to evaluate the action of product debugging, and the comparison result is used for representing the quality degree of product debugging. In addition, the product debugging data and the preset performance index can be compared through the comparator, and the comparison mode of the product debugging data and the preset performance index is not limited.
Step S202, if the product debugging data is consistent with the performance index, a product debugging completion instruction is sent to the product debugging equipment; or if the product debugging data is inconsistent with the performance index, adjusting the debugging parameters of the product based on a product debugging model to obtain optimized debugging parameters, sending out a product debugging instruction, executing the debugging instruction by the product debugging equipment, and completing the product debugging according to the optimized debugging parameters.
By comparing the product debugging data with the performance index, whether the product debugging meets the requirements can be clearly known. If the product debugging data is consistent with the performance index, the current product debugging meets the requirements, the product is not required to be debugged any more, and the product debugging is finished. If the product debugging data is inconsistent with the performance indexes, the current product debugging does not meet the requirements, and the product needs to be continuously debugged to meet the performance indexes to the maximum extent.
The product debugging model and the performance prediction model can be machine learning models. Such as a deep neural network model, a decision tree model, a logistic regression model, etc. And adjusting debugging parameters of the product based on the product debugging model, sending the adjusted debugging parameters serving as optimized debugging parameters to product debugging equipment, and debugging the product by the product debugging equipment according to the optimized debugging parameters.
Here, it should be noted that the product debugging model may be a deep neural network model capable of learning a first mapping relationship, where the first mapping relationship is a relationship between product debugging data (or model debugging data) and guidance for product debugging. Inputting product debugging data (or model debugging data) into a deep neural network model, analyzing the product debugging data (or model debugging data) by the deep neural network model, and outputting debugging parameters (including a part to be debugged and a specific value for adjustment) of a product to be debugged.
The performance prediction model can be a graph neural network model, the work topological structure of the product and the attribute (type, size, structure, material, conductivity, permeability, dielectric constant and the like) information contained in the product are converted into data containing nodes and edge structures and used as the input of the graph neural network, the performance index of the product is used as a target value, the work topological structure of the product, the contained attribute and the performance index are mapped with each other through learning, the function of simulating traditional modeling simulation software is achieved, the product model is debugged instead of the traditional modeling simulation software, and model debugging data of the product model are generated, so that the problems that the traditional modeling simulation software consumes time and occupies large computing resources can be solved. The detailed process is not described herein.
Here, it should be noted that the performance prediction model may be a neural network model that learns a second mapping relationship between the product model and the product debugging data (or the model debugging data). And inputting relevant information (such as the topological structure, the size and the like of the product model) of the product model into the deep neural network model, analyzing the relevant information of the product model by the deep neural network model, and outputting model debugging data of the product model.
Fig. 2B is a schematic flowchart of step S202 in a product debugging method implemented by a processor of a debugging assistance device executing a computer program according to a second embodiment of the present application; as shown in fig. 2B, step S202 includes:
step S212, if the product debugging data is inconsistent with the performance index, adjusting the debugging parameters according to the product debugging data based on the product debugging model, and sending out a model debugging instruction;
and comparing the product debugging data with the performance index, finding out the difference between the product debugging data and the performance index if the product debugging data is inconsistent with the performance index, adjusting the debugging parameters according to the product debugging data by using the product debugging model as a target according to the performance index, and sending out a model debugging instruction, so that the product debugging data closer to the performance index can be obtained when the product is debugged according to the adjusted debugging parameters.
Step S222, executing the model debugging instruction based on a performance prediction model, debugging a product model according to the adjusted debugging parameters, and generating model debugging data, wherein the product model corresponds to the product;
in the step, the performance prediction model executes the model debugging instruction to debug the product model so as to simulate the product debugging equipment to debug the product. The product model corresponds to the product, and the attribute information such as the type, size, structure, material, conductivity, permeability, dielectric constant and the like of the product model is completely the same as the attribute information of the product, so that the product debugging can be simulated better through the product model debugging. And under the condition that debugging parameters are the same, debugging the product model through the performance prediction model, and generating model debugging data which are completely the same as the product debugging data generated by debugging the product through product debugging equipment. Therefore, the debugging effect of the product model can be directly reflected, the product debugging time is greatly shortened, the product debugging efficiency is improved, and the energy spent in product debugging is saved.
Step S232, generating a model debugging evaluation result according to the model debugging data and the performance index, wherein the model debugging evaluation result is used for evaluating the debugging of the product model;
and after the model debugging data is obtained, in order to measure whether the adjustment of the product debugging model to the debugging parameters meets the requirements or not, the debugging action of the product model is evaluated by using the model debugging evaluation result. Specifically, model debugging data and performance indexes are compared, and the difference between the model debugging data and the performance indexes is found out, so that a model debugging evaluation result can be obtained. Specifically, the comparison between the model debugging data and the performance index may be implemented by a comparison function or a comparator, and the details are not repeated here.
And step S242, obtaining the optimized debugging parameters according to the model debugging evaluation result, sending a product debugging instruction, executing the product debugging instruction by the product debugging equipment, and completing product debugging according to the optimized debugging parameters.
According to the model debugging evaluation result, whether the model debugging data of the product model meet the performance index or not can be clearly known, if the model debugging data meet the performance index, the product is debugged through the debugging parameters corresponding to the model debugging data, the performance index can also be met, the debugging parameters corresponding to the model debugging data can be output as optimized debugging parameters, a product debugging instruction is sent, the product debugging instruction is executed by product debugging equipment, and the product is debugged according to the optimized debugging parameters. If the model debugging data does not meet the performance index, the product is debugged through the debugging parameters corresponding to the model debugging data, the performance index cannot be met, the debugging parameters of the product model need to be adjusted continuously until the product model is debugged according to the adjusted debugging parameters, the obtained model debugging data is consistent with the performance index, the debugging parameters corresponding to the model debugging data are used as optimized debugging parameters, a product debugging instruction is sent, the product debugging instruction is executed by product debugging equipment, and the product is debugged according to the optimized debugging parameters.
Specifically, step S242 includes: if the model debugging data is consistent with the performance index, outputting the adjusted debugging parameters as the optimized debugging parameters, sending out the product debugging instructions, executing the product debugging instructions by the product debugging equipment, and completing the product debugging according to the optimized debugging parameters; or if the model debugging data is inconsistent with the performance index, adjusting the adjusted debugging parameters according to the model debugging data based on the product debugging model to generate optimized debugging parameters, sending the product debugging instructions, executing the product debugging instructions by the product debugging equipment, and completing the product debugging according to the optimized debugging parameters.
Further, if the model debugging data is inconsistent with the performance index, adjusting the adjusted debugging parameters according to the model debugging data based on the product debugging model; generating the optimized debugging parameters, sending the model debugging instructions, executing the model debugging instructions by the product debugging equipment, and completing the product debugging according to the optimized debugging parameters comprises the following steps: if the model debugging data is inconsistent with the performance index, adjusting the adjusted debugging parameters according to the model debugging data based on the product debugging model, and sending out the product debugging instruction; executing the product debugging instruction based on the performance prediction model, debugging the product model according to the adjusted debugging parameters, and generating new model debugging data; generating a new model debugging evaluation result according to the new model debugging data and the performance index; and obtaining the optimized debugging parameters according to the new model debugging evaluation result, sending the product debugging instruction, executing the product debugging instruction by the product debugging equipment, and completing the product debugging according to the optimized debugging parameters.
Through the continuous adjustment of the product debugging model to the debugging parameters, the performance prediction model debugs the product model, and the generated model debugging data is closer to the performance index. And when the model debugging data is consistent with the performance index, the debugging parameters can be stopped from being adjusted, and at the moment, the debugging parameters corresponding to the model debugging parameters consistent with the performance index are the optimized debugging parameters, the optimized debugging parameters are output, and a product debugging instruction is sent to product debugging equipment to complete product debugging.
It should be noted that the number of times of adjustment of the debug parameters is not as large as possible. When the product debugging model aims at the performance index and continuously adjusts the debugging parameters, a large amount of computing resources are inevitably occupied. In order to coordinate the relationship between the computing resources occupied by the product debugging model and the debugging efficiency, in this embodiment, the product debugging model is limited by setting the maximum adjustment times of the debugging parameters, so that the computing resources occupied by the product debugging model and the debugging efficiency are relatively balanced. Specifically, the obtaining the optimized debugging parameters according to the new model debugging evaluation result, issuing a product debugging instruction, executing the product debugging instruction by the product debugging device, and completing the product debugging according to the optimized debugging parameters includes: and if the new model debugging data is inconsistent with the performance index and the adjusting times of the debugging parameters reach a preset threshold value, outputting the final debugging parameters as the optimized debugging parameters, sending a product debugging instruction, executing the product debugging instruction by the product debugging equipment, and completing the product debugging according to the optimized debugging parameters. The preset threshold value may be set according to the actual condition of product debugging and the resource configuration when the product debugging model adjusts the parameters, and is not specifically limited.
The product debugging method of the embodiment can finish the process of repeatedly debugging the product by debugging auxiliary equipment, the debugging parameters are optimized by continuously adjusting the debugging parameters of the product model by the product debugging model, the optimized debugging parameters meeting performance indexes are finally output, and the product debugging is finished by the product debugging equipment, so that the product debugging time is greatly shortened, the product debugging efficiency is improved, and the energy spent in product debugging is saved.
Next, the product tuning method of the present embodiment will be described by taking an example of tuning a product using a ceramic dielectric filter for a 5G base station.
The ceramic dielectric filter for 5G base station is composed of a ceramic substrate and a surface metal layer, and the material of the surface metal layer is usually silver and is fixed on the ceramic by sintering. In the process of debugging the ceramic dielectric filter, the electric grinding head destroys the ceramic substrate or the silver layer sintered on the surface, so that the electromagnetic field in the ceramic dielectric filter can be adjusted, and the debugging of the ceramic dielectric filter is realized.
By using the product debugging method of the embodiment, first, the ceramic dielectric filter is placed on the electromechanical device (i.e., the product debugging device) to debug the ceramic dielectric filter, and the electromechanical device is connected with the vector network analyzer (i.e., the performance testing device), so that an S-parameter curve (i.e., product debugging data) of the ceramic dielectric filter after debugging can be obtained, and the S-parameter curve obtained by the vector network analyzer is uploaded to the server.
And then, comparing the S parameter curve according to the preset performance index of the ceramic dielectric filter, and if the S parameter curve is consistent with the performance index, indicating that the debugging of the electromechanical equipment on the ceramic dielectric filter achieves the target and meets the requirement. If the S parameter curve is inconsistent with the performance index, adjusting debugging parameters through a product debugging model arranged at the server according to the input S parameter curve, sending a model debugging instruction, executing the model debugging instruction by the performance prediction model, debugging the ceramic dielectric filter model (namely the product model) according to the adjusted debugging parameters, and generating model debugging data. Here, the ceramic dielectric filter model is a model created from a ceramic dielectric filter.
And after the performance prediction model generates model debugging data, the model debugging data is delivered to the product debugging model for evaluation, and the model debugging data is compared with the performance index to see whether the model debugging data meets the requirements or not. And if the model debugging data is inconsistent with the performance index, continuously adjusting the debugging parameters of the ceramic dielectric filter model, interacting with the performance prediction model until the model debugging data is consistent with the performance index, outputting the debugging parameters corresponding to the model debugging data consistent with the performance index to the electromechanical equipment, sending a product debugging instruction, and executing the product debugging instruction by the electromechanical equipment to finish the debugging of the ceramic dielectric filter.
Here, it should be noted that, comparing the product debugging data with the performance index may be performed by a product debugging model (adding a comparison function to the product debugging model), or may be performed by separately setting a comparison model (such as a comparator). In the embodiment of debugging the ceramic dielectric filter, a product debugging model is adopted to finish the comparison of product debugging data and performance indexes.
The product to be debugged may be a microwave rf device, a filter for communication equipment, a sound meter filter, a rf filter, an if filter, a frequency discriminator, a medium/antenna/transceiver duplexer, a medium band pass filter, a ceramic capacitor, a positive/negative temperature coefficient thermistor, a high-precision adjustable potentiometer, a high-voltage resistance chip inductor, a noise suppressor/electromagnetic interference noise suppressor (EMIFIL), a chip magnetic bead, a magnetic bead bank, a common mode choke coil for DC/AC, a coincidence noise filter for military use, a ceramic oscillator (Resonators), a high-frequency device (Micro wave Modules) PLL device, a rf switch, a microwave oscillator VCO, a Bluetooth module, a Power supply (Power Supplies), a sensor device (Sensors), or the like.
Third embodiment
In the product debugging process, the product debugging model for adjusting the debugging parameters can be trained in advance, and can also be trained along with the product debugging. The product debugging model in this embodiment is a deep neural network model. The deep neural network model is based on a deep reinforcement learning framework, an AC network (behavior network and value network) framework, wherein the AC network framework can be A3C (Asynchronous Advantage Acitiation-Critic), A2C (adaptive Acientage-Critic), PPO (rapid Policy optimization), DDPG (deep decision Policy gradient) and the like.
At this time, the product debugging model training method comprises the following steps: training the product debugging model according to sampling data, wherein the sampling data comprises: the product debugging model is used for adjusting the debugging parameters, and the performance prediction model is used for debugging the product model.
The sampling data may be obtained by sampling through interaction between a product debugging model and an environment, where the environment may be a performance prediction model, or may also be a product debugging device, or may be other simulation software capable of calculating performance of the product model, and the like, and is not limited herein. In this embodiment, the product debugging model is trained through interaction between the performance prediction model and the product debugging model, and the interaction between the product debugging model and the performance prediction model is sampled to obtain sampling data in the process of adjusting debugging parameters by the product debugging model and debugging the product model by the performance prediction model.
FIG. 3A is a flowchart illustrating a product debugging model training method implemented by a computer program executed by a processor of a debugging assistance device according to a third embodiment of the present application; as shown in fig. 3A, the training the product debugging model according to the sampling data includes:
s301, evaluating the action of adjusting the debugging parameters of the product debugging model through a value function according to the sampling data to generate an adjustment action evaluation result;
in the process of interacting the product debugging model and the performance prediction model, the product debugging model takes the performance index as a target, and the product debugging model evaluates the state of the product model after debugging, namely, the debugging parameters are adjusted according to the model debugging data, and new debugging parameters in the product model to be debugged are given.
In this embodiment, the action of the product debugging model is evaluated by the cost function, and an adjustment action evaluation result is generated, where the adjustment action evaluation result is used to guide the product debugging model to adjust the next debugging parameter.
Specifically, step S301 includes:
if the model debugging data is consistent with the performance index, the adjusting action evaluation result is zero; and if the model debugging data is inconsistent with the performance index, the adjustment action evaluation result is an accumulated return approximate value of the model debugging data obtained through the value function according to the sampling data.
In this embodiment, Q represents the adjustment action evaluation result, and V represents the cumulative return approximation value, that is, when the model debug data is consistent with the performance index, the adjustment action evaluation result Q (s, t) is 0; model debugging data and performance indexWhen the two are consistent, adjusting the action evaluation result Q (s, t) to V(s)tω). Wherein t is a natural number and represents that the product debugging model adjusts debugging parameters for the second time; stRepresenting the debugging state of the product model after the debugging parameters are adjusted for the t time, wherein s represents model debugging data of the last time sequence; ω is a parameter of the cost function.
The accumulated return approximation represents the target of the product debugging model, i.e. the optimal neural network model parameters are found, so that the expectation of accumulated return is maximum. Specifically, iterative computation may be performed through a state cost function. Such as: calculating an adjustment action evaluation result of the product debugging model for adjusting the debugging parameters for the last time through the value function; and calculating the adjustment action evaluation result of the adjustment of the debugging parameters in the previous time according to the adjustment action evaluation result of the adjustment of the debugging parameters in the next time. Specifically, the calculation can be performed according to the following formula (1).
Q(s，i)＝ri+γ*Q(s，i+1)............(1)
Wherein, i belongs to (t-1, 1), and represents that the ith debugging parameter of the product debugging model is adjusted; q (s, i +1) represents an adjustment action evaluation result of the debugging state of the product model after the debugging parameters are adjusted for the (i +1) th time; q (s, i) represents an adjustment action evaluation result of the predicted debugging state of the product model after the debugging parameters are adjusted for the ith time;
rirepresenting instant rewards for adjusting debugging parameters of the product model for the ith time, wherein the instant rewards are used for evaluating the quality of the current adjusting action; gamma belongs to (0,1) and represents the discount rate, and the value of gamma influences the training of a product debugging model and optimizes the result of debugging parameters. When gamma is close to 0, the optimized debugging parameters output by the trained product debugging model are probably locally optimal; when gamma is close to 1, the optimized debugging parameters output by the trained product debugging model can be globally optimal. Since the product debugging model may not converge when γ is 1, the value of γ should be determined according to the actual condition of product debugging, and it is not better to be larger.
Step S302, according to the adjustment action evaluation result, parameters of the product debugging model and parameters of the cost function are respectively adjusted, so that the product debugging model and the cost function are converged, and training of the product debugging model is completed.
If the difference between the model debugging data and the performance index is reduced through the adjustment of the product debugging model on the debugging parameters, the evaluation of the product debugging model adjusting action by the value function is positive and positive, namely the result of the evaluation of the adjusting action is positive and positive. At this time, the parameter adjustment of the product debugging model and the parameter adjustment of the cost function refer to the adjustment of the debugging parameters, and the parameters of the product debugging model and the parameters of the cost function are adjusted along the adjustment direction of the debugging parameters, so that the product debugging model and the cost function are converged finally.
Fig. 3B is a schematic flowchart of step S302 in the method for training a product debugging model implemented by executing a computer program by a processor of a debugging auxiliary device according to the third embodiment of the present application; as shown in fig. 3B, step S302 includes:
step S312, calculating the thread gradient updating of the parameters of the product debugging model and the thread gradient updating of the parameters of the value function according to the adjustment action evaluation result;
the thread gradient updating of the parameters of the product debugging model is completed by the following formula (2).
Figure BDA0002372008600000171
Theta is a parameter of the product debugging model, theta' represents a thread parameter of the product debugging model, and d theta represents an accumulated gradient of the parameter of the product debugging model; pi represents the adjustment strategy of the product debugging model to debugging parameters; piθ'Representing a debugging strategy when the parameter of the thread product debugging model is theta'; piθ'(si,ai) Is shown in state siDo the following action aiThe probability of (d); q (s, i) -V(s)iω') represents the merit function;
Figure BDA0002372008600000172
representing a calculated gradient;
h is entropy, c is an entropy coefficient, and the entropy representing the adjusting action pi is added into the value function to encourage and explore the adjusting action of the product debugging model so as to prevent the product debugging model from falling into local optimum when the adjusting action is performed. In the embodiment, the exploratory property and the robustness of the product debugging model when the product debugging model performs the adjusting action are enhanced by adding the random noise into the product debugging model. When the adjustment action is made through a product debugging model, part of randomly selected actions are added, and random noise is added; the debugging action of the product debugging model can be limited by using entropy regulation, and random noise is added to prevent the product debugging model from fast convergence; noise disturbance can also be added through the action of the product debugging model, and random noise is added. The noise adding modes directly act on the output end of the product debugging model and act on the value function in the product debugging model. It should be noted that the manner of adding noise in the product debugging model is not limited, and other manners may also be adopted, for example, noise is added in parameters of the product debugging model, and details are not described here.
This thread gradient update of the parameters of the cost function is done by the following equation (3):
Figure BDA0002372008600000173
where ω represents a parameter of the cost function and d ω represents a gradient of the parameter of the cost function; omega' represents the parameter of the thread cost function; v(s)iω') the state s at time i when the parameter characterizing the cost function of the thread is ωiA value estimate of (d);
step S322, adjusting the parameters of the product debugging model according to the gradient update of the thread of the parameters of the product debugging model; and adjusting the parameters of the value function according to the gradient update of the thread of the parameters of the value function, so that the product debugging model and the value function are converged, and the training of the product debugging model is completed.
After the gradient update of the thread of the parameters of the product debugging model is completed, the parameters of the product debugging model can be adjusted through the following formula (4):
θ＝θ-αdθ............(4)；
α, the step size of the parameter adjustment of the product debugging model can be a fixed value at the beginning and is reduced with the time, if the training is not improved, we will change the step size of each iteration according to some loop functions.
After the present thread gradient update of the parameters of the cost function, the parameters of the cost function can be adjusted by the following formula (5):
ω＝ω-βdω............(5)；
β the adjustment step size for the parameter adjustment of the cost function may be initially a fixed value and decrease over time, and if the training does not improve, we will change the step size for each iteration according to some round-robin function.
By adjusting the parameters of the product debugging model and the parameters of the value function, the training of the product debugging model is completed when the product debugging model and the value function are both converged.
Fourth embodiment
FIG. 4A is a schematic structural diagram of a debugging aid according to a fourth embodiment of the present application; as shown in fig. 4A, the debug assistance apparatus includes: the performance evaluation unit 401 is configured to evaluate product debugging according to received product debugging data and a preset performance index, wherein the product debugging data is obtained by debugging a product by product debugging equipment; a debugging output unit 402 configured to send a product debugging completion instruction to the product debugging device if the product debugging data is consistent with the performance index; or if the product debugging data is inconsistent with the performance index, adjusting the debugging parameters of the product based on a product debugging model to obtain optimized debugging parameters, sending a product debugging instruction, executing the product debugging instruction by the product debugging equipment, and completing the product debugging according to the optimized debugging parameters.
FIG. 4B is a diagram illustrating a debug output unit in a debug assistance apparatus according to a fourth embodiment of the present application; as shown in fig. 4B, the debug output unit 402 includes: a parameter adjusting subunit 412, configured to, if the product debugging data is inconsistent with the performance index, adjust the debugging parameter according to the product debugging data based on the product debugging model, and send a model debugging instruction; a model debugging subunit 422 configured to execute the model debugging instruction based on the performance prediction model, debug the product model according to the adjusted debugging parameters, and generate model debugging data, where the product model corresponds to the product; a debugging evaluation subunit 432, configured to generate a model debugging evaluation result according to the model debugging data and the performance index, where the model debugging evaluation result is used to evaluate debugging of the product model; a parameter output subunit 442, configured to obtain the optimized debugging parameter according to the model debugging evaluation result, and issue the product debugging instruction, where the product debugging device executes the product debugging instruction, and the product debugging is completed according to the optimized debugging parameter.
Further, the parameter output subunit 442 is further configured to, if the model debugging data is consistent with the performance index, output the adjusted debugging parameter as the optimized debugging parameter, and issue the product debugging instruction, where the product debugging apparatus executes the product debugging instruction, and complete product debugging according to the optimized debugging parameter; or if the model debugging data is inconsistent with the performance index, adjusting the adjusted debugging parameters again according to the model debugging data based on the product debugging model to generate optimized debugging parameters, sending the product debugging instructions, executing the product debugging instructions by the product debugging equipment, and completing the product debugging according to the optimized debugging parameters.
It should be noted that, the operation flow of the debugging assisting apparatus in the embodiment of the present application may refer to the operation flow of the product debugging method in the second embodiment, and details are not repeated here.
Fifth embodiment
Fig. 5A is a schematic structural diagram of a product debugging model training system in a debugging aid according to a fifth embodiment of the present application; as shown in fig. 5A, the training system includes: the action evaluation unit 501 is configured to evaluate the action of the product debugging model for adjusting the debugging parameters through a cost function according to the sampling data, and generate an adjustment action evaluation result; the model adjusting unit 502 is configured to adjust parameters of the product debugging model and parameters of the cost function respectively according to the adjustment action evaluation result, so that the product debugging model and the cost function are both converged, and training of the product debugging model is completed.
Specifically, the action evaluation unit 501 is further configured to determine that the adjustment action evaluation result is zero if the model debugging data is consistent with the performance index; and if the model debugging data is inconsistent with the performance index, the adjustment action evaluation result is an accumulated return approximate value of the model debugging data obtained through the value function according to the sampling data.
Fig. 5B is a schematic structural diagram of a model adjustment unit in a debugging assistance device according to a fifth embodiment of the present application; as shown in fig. 5B, the model adjusting unit 502 includes: a gradient update subunit 512, configured to calculate a present thread gradient update of the parameter of the product debugging model and a present thread gradient update of the parameter of the cost function according to the adjustment action evaluation result; a parameter adjusting subunit 522 configured to adjust the parameters of the product debugging model according to the thread gradient update of the parameters of the product debugging model; and adjusting the parameters of the value function according to the gradient update of the thread of the parameters of the value function, so that the product debugging model and the value function are converged, and the training of the product debugging model is completed.
It should be noted that, the operation flow of the product debugging model training system according to the embodiment of the present application may refer to the operation flow of the product debugging model training method according to the third embodiment, and details are not repeated here.
Sixth embodiment
Fig. 6 is a schematic structural diagram of a debugging aid according to a fifth embodiment of the present application; the commissioning assistance apparatus may comprise:
one or more processors 601;
a memory 602, the memory 602 being a computer-readable medium that may be configured to store one or more programs,
the one or more programs, when executed by the one or more processors 601, cause the one or more processors 601 to implement a method of product debugging as described in any of the embodiments above.
Seventh embodiment
Fig. 7 is a hardware configuration of a debugging aid according to a seventh embodiment of the present application; as shown in fig. 7, the hardware structure of the apparatus may include: a processor 701 and a computer-readable medium 703;
optionally, the method further includes: a communication interface 702, wherein the communication interface 702 may be an interface of a communication module, such as an interface of a GSM module;
the processor 701, the communication interface 702, and the computer-readable medium 703 are configured to perform communication with each other through a communication bus 704;
the processor 701 may be specifically configured to: evaluating product debugging according to received product debugging data and a preset performance index, wherein the product debugging data is obtained by debugging the product by product debugging equipment; if the product debugging data is consistent with the performance index, sending a product debugging completion instruction to the product debugging equipment; or if the product debugging data is inconsistent with the performance index, adjusting debugging parameters of product debugging based on a product debugging model to obtain optimized debugging parameters, sending a product debugging instruction, executing the product debugging instruction by the product debugging equipment, and completing the product debugging according to the optimized debugging parameters.
The processor 701 may be a general-purpose processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; but may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components. The various methods, steps, and logic blocks disclosed in the embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The electronic device of the embodiments of the present application exists in various forms, including but not limited to:
(1) mobile communication devices, which are characterized by mobile communication capabilities and are primarily targeted at providing voice and data communications. Such terminals include smart phones (e.g., iphones), multimedia phones, functional phones, and low-end phones, among others.
(2) The ultra-mobile personal computer equipment belongs to the category of personal computers, has calculation and processing functions and generally has the characteristic of mobile internet access. Such terminals include PDA, MID, and UMPC devices, such as ipads.
(3) Portable entertainment devices such devices may display and play multimedia content. Such devices include audio and video players (e.g., ipods), handheld game consoles, electronic books, as well as smart toys and portable car navigation devices.
(4) The server is similar to a general computer architecture, but has higher requirements on processing capability, stability, reliability, safety, expandability, manageability and the like because of the need of providing highly reliable services.
(5) And other electronic devices with data interaction functions.
It should be noted that, in the present specification, all the embodiments are described in a progressive manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the apparatus and system embodiments, since they are substantially similar to the method embodiments, they are described in a relatively simple manner, and reference may be made to some of the descriptions of the method embodiments for related points. The above-described embodiments of the apparatus and system are merely illustrative, and the units described as separate parts may or may not be physically separate, and the parts suggested as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
The above description is only one specific embodiment of the present application, but the scope of the present application is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present application should be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims (12)

1. A commissioning assistance apparatus, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the processor implementing the following steps when executing the computer program:
evaluating product debugging according to received product debugging data and a preset performance index, wherein the product debugging data is obtained by debugging the product by product debugging equipment;
if the product debugging data is consistent with the performance index, sending a product debugging completion instruction to the product debugging equipment;
or the like, or, alternatively,
and if the product debugging data is inconsistent with the performance index, adjusting the debugging parameters of the product based on a product debugging model to obtain optimized debugging parameters, sending a product debugging instruction, executing the product debugging instruction by the product debugging equipment, and completing the product debugging according to the optimized debugging parameters.
2. The debugging assistance device of claim 1, wherein in the step implemented when the processor executes the computer program, if the product debugging data is inconsistent with the performance index, the debugging parameters are adjusted based on a product debugging model to obtain optimized debugging parameters, and a product debugging instruction is issued, and the product debugging device executes the product debugging instruction to complete the product debugging according to the optimized debugging parameters, the debugging assistance device comprising:
if the product debugging data is inconsistent with the performance index, adjusting the debugging parameters according to the product debugging data based on the product debugging model, and sending out a model debugging instruction;
executing the model debugging instruction based on a performance prediction model, debugging a product model according to the adjusted debugging parameters, and generating model debugging data, wherein the product model corresponds to the product;
generating a model debugging evaluation result according to the model debugging data and the performance index, wherein the model debugging evaluation result is used for evaluating the debugging of the product model;
and obtaining the optimized debugging parameters according to the model debugging evaluation result, sending the product debugging instruction, executing the product debugging instruction by the product debugging equipment, and completing the product debugging according to the optimized debugging parameters.
3. The debugging assistance device of claim 2, wherein the steps implemented when the processor executes the computer program include obtaining the optimized debugging parameters according to the model debugging evaluation result, issuing the product debugging command, executing the product debugging command by the product debugging device, and completing the product debugging according to the optimized debugging parameters, and the steps include:
if the model debugging data is consistent with the performance index, outputting the adjusted debugging parameters as the optimized debugging parameters, sending out the product debugging instructions, executing the product debugging instructions by the product debugging equipment, and completing the product debugging according to the optimized debugging parameters;
or the like, or, alternatively,
and if the model debugging data is inconsistent with the performance index, adjusting the adjusted debugging parameters according to the model debugging data based on the product debugging model to generate optimized debugging parameters, sending out the product debugging instruction, executing the product debugging instruction by the product debugging equipment, and completing the product debugging according to the optimized debugging parameters.
4. The debugging assistance device of claim 3, wherein in the step implemented when the processor executes the computer program, if the model debugging data is inconsistent with the performance index, the processor adjusts the adjusted debugging parameters according to the model debugging data based on the product debugging model to generate the optimized debugging parameters, and issues the product debugging command, and the product debugging device executes the product debugging command to complete the product debugging according to the optimized debugging parameters, including:
if the model debugging data is inconsistent with the performance index, adjusting the adjusted debugging parameters according to the model debugging data based on the product debugging model, and sending out the model debugging instruction;
executing the model debugging instruction based on the performance prediction model, debugging the product model according to the adjusted debugging parameters, and generating new model debugging data;
generating a new model debugging evaluation result according to the new model debugging data and the performance index;
and obtaining the optimized debugging parameters according to the new model debugging evaluation result, sending the product debugging instruction, executing the product debugging instruction by the product debugging equipment, and completing the product debugging according to the optimized debugging parameters.
5. The debugging assistance device according to claim 4, wherein the steps implemented when the processor executes the computer program include obtaining the optimized debugging parameters according to the new model debugging evaluation result, issuing the product debugging command, executing the product debugging command by the product debugging device, and completing the product debugging according to the optimized debugging parameters, and the steps include: and if the new model debugging data is inconsistent with the performance index and the adjusting times of the debugging parameters reach a preset threshold value, outputting the final debugging parameters as the optimized debugging parameters, sending the product debugging instructions, executing the product debugging instructions by the product debugging equipment, and completing the product debugging according to the optimized debugging parameters.
6. The commissioning assistance device of any one of claims 1 to 5, wherein the product commissioning model is a machine learning model.
7. The debugging assistance apparatus of claim 6 wherein the machine learning model is a deep neural network model.
8. A debugging assistance apparatus, comprising:
the performance evaluation unit is configured to evaluate the product debugging according to the received product debugging data and a preset performance index, wherein the product debugging data is obtained by debugging the product by product debugging equipment;
the debugging output unit is configured to send a product debugging completion instruction to the product debugging equipment if the product debugging data is consistent with the performance index; or if the product debugging data is inconsistent with the performance index, adjusting the debugging parameters of the product based on a product debugging model to obtain optimized debugging parameters, and sending a product debugging instruction, wherein the product debugging equipment completes product debugging according to the optimized debugging parameters by executing the product debugging instruction.
9. The debug assistance apparatus according to claim 7, wherein said debug output unit comprises:
the parameter adjusting subunit is configured to adjust the debugging parameters according to the product debugging data and the product debugging data based on the product debugging model and send out a model debugging instruction if the product debugging data is inconsistent with the performance index;
the model debugging subunit is configured to execute the model debugging instruction based on a performance prediction model, debug a product model according to the adjusted debugging parameters, and generate model debugging data, wherein the product model corresponds to the product;
the debugging evaluation subunit is configured to generate a model debugging evaluation result according to the model debugging data and the performance index, and the model debugging evaluation result is used for evaluating the debugging of the product model;
and the parameter output subunit is configured to obtain the optimized debugging parameters according to the model debugging evaluation result, send the product debugging instruction, execute the product debugging instruction by the product debugging equipment, and complete the product debugging according to the optimized debugging parameters.
10. The debugging assistance apparatus according to claim 8, wherein the parameter output subunit is further configured to,
if the model debugging data is consistent with the performance index, outputting the adjusted debugging parameters as the optimized debugging parameters, sending out the product debugging instructions, executing the product debugging instructions by the product debugging equipment, and completing the product debugging according to the optimized debugging parameters;
or the like, or, alternatively,
and if the model debugging data is inconsistent with the performance index, based on the product debugging model, adjusting the adjusted debugging parameters again according to the model debugging data to generate optimized debugging parameters, sending out the product debugging instruction, executing the product debugging instruction by the product debugging equipment, and completing the product debugging according to the optimized debugging parameters.
11. A product commissioning device, wherein the product commissioning device is configured to commission the product, generate product commissioning data, and send the product commissioning data to the commissioning assistance device of any one of claims 1-7.
12. A computer-readable medium, in which a computer program is stored, characterized in that the computer program is stored in a debugging assistance device according to any of claims 1 to 7.
CN202010053435.8A 2020-01-17 2020-01-17 Debugging assistance apparatus, product debugging apparatus, computer readable medium Pending CN111260134A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010053435.8A CN111260134A (en) 2020-01-17 2020-01-17 Debugging assistance apparatus, product debugging apparatus, computer readable medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010053435.8A CN111260134A (en) 2020-01-17 2020-01-17 Debugging assistance apparatus, product debugging apparatus, computer readable medium

Publications (1)

Publication Number Publication Date
CN111260134A true CN111260134A (en) 2020-06-09

Family

ID=70952262

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010053435.8A Pending CN111260134A (en) 2020-01-17 2020-01-17 Debugging assistance apparatus, product debugging apparatus, computer readable medium

Country Status (1)

Country Link
CN (1) CN111260134A (en)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111639812A (en) * 2020-06-01 2020-09-08 南京星火技术有限公司 Performance debugging method and device of electronic product and related product
CN111880982A (en) * 2020-07-30 2020-11-03 南京星火技术有限公司 Performance debugging method and device of radio frequency piezoelectric device and related product
CN113344281A (en) * 2021-06-22 2021-09-03 太仓比泰科自动化设备有限公司 Probe performance prediction method, system, device and storage medium
US11469975B2 (en) 2020-06-30 2022-10-11 Beijing Baidu Netcom Science & Technology Co., Ltd Filter debugging method, device, electronic apparatus and readable storage medium
CN116661317A (en) * 2023-06-01 2023-08-29 六和电子（江西）有限公司 Stepped temperature, time and pressure hot-pressing method for thin film capacitor
CN117472474A (en) * 2023-12-27 2024-01-30 苏州元脑智能科技有限公司 Configuration space debugging method, system, electronic equipment and storage medium

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108805134A (en) * 2018-06-25 2018-11-13 慧影医疗科技（北京）有限公司 A kind of construction method of dissection of aorta parted pattern and application
CN109960616A (en) * 2017-12-22 2019-07-02 龙芯中科技术有限公司 The adjustment method and system of processor-based memory parameters
CN110187647A (en) * 2018-02-23 2019-08-30 北京京东尚科信息技术有限公司 Model training method and system
CN110210654A (en) * 2019-05-20 2019-09-06 南京星火技术有限公司 Product model designing system and method
CN110211119A (en) * 2019-06-04 2019-09-06 厦门美图之家科技有限公司 Image quality measure method, apparatus, electronic equipment and readable storage medium storing program for executing
CN110378419A (en) * 2019-07-19 2019-10-25 广东浪潮大数据研究有限公司 A kind of image set extending method, device, equipment and readable storage medium storing program for executing

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109960616A (en) * 2017-12-22 2019-07-02 龙芯中科技术有限公司 The adjustment method and system of processor-based memory parameters
CN110187647A (en) * 2018-02-23 2019-08-30 北京京东尚科信息技术有限公司 Model training method and system
CN108805134A (en) * 2018-06-25 2018-11-13 慧影医疗科技（北京）有限公司 A kind of construction method of dissection of aorta parted pattern and application
CN110210654A (en) * 2019-05-20 2019-09-06 南京星火技术有限公司 Product model designing system and method
CN110211119A (en) * 2019-06-04 2019-09-06 厦门美图之家科技有限公司 Image quality measure method, apparatus, electronic equipment and readable storage medium storing program for executing
CN110378419A (en) * 2019-07-19 2019-10-25 广东浪潮大数据研究有限公司 A kind of image set extending method, device, equipment and readable storage medium storing program for executing

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
张天泽: "基于强化学习的四旋翼无人机路径规划方法研究", 《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》, pages 15 - 16 *

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111639812A (en) * 2020-06-01 2020-09-08 南京星火技术有限公司 Performance debugging method and device of electronic product and related product
US11469975B2 (en) 2020-06-30 2022-10-11 Beijing Baidu Netcom Science & Technology Co., Ltd Filter debugging method, device, electronic apparatus and readable storage medium
CN111880982A (en) * 2020-07-30 2020-11-03 南京星火技术有限公司 Performance debugging method and device of radio frequency piezoelectric device and related product
CN111880982B (en) * 2020-07-30 2023-08-08 南京星火技术有限公司 Performance debugging method and device of radio frequency piezoelectric device and related products
CN113344281A (en) * 2021-06-22 2021-09-03 太仓比泰科自动化设备有限公司 Probe performance prediction method, system, device and storage medium
CN113344281B (en) * 2021-06-22 2022-02-11 太仓比泰科自动化设备有限公司 Probe performance prediction method, system, device and storage medium
CN116661317A (en) * 2023-06-01 2023-08-29 六和电子（江西）有限公司 Stepped temperature, time and pressure hot-pressing method for thin film capacitor
CN116661317B (en) * 2023-06-01 2024-04-12 六和电子（江西）有限公司 Stepped temperature, time and pressure hot-pressing method for thin film capacitor
CN117472474A (en) * 2023-12-27 2024-01-30 苏州元脑智能科技有限公司 Configuration space debugging method, system, electronic equipment and storage medium
CN117472474B (en) * 2023-12-27 2024-03-15 苏州元脑智能科技有限公司 Configuration space debugging method, system, electronic equipment and storage medium

Similar Documents

Publication Publication Date Title
CN111260134A (en) Debugging assistance apparatus, product debugging apparatus, computer readable medium
Yelten et al. Demystifying surrogate modeling for circuits and systems
KR102615957B1 (en) Point cloud data processing method, apparatus, electronic device and computer readable storage medium
CN108304388A (en) Machine translation method and device
CN111260079B (en) Electronic equipment and intelligent body self-training device
TWI670617B (en) Simulation system and method
CN105787558A (en) Knowledge-based neural network micro-strip filter design method based on ADS
WO2023207487A1 (en) Circuit wiring determination method and related device
CN117787426B (en) Method and device for acquiring ground state of quantum system, storage medium and electronic equipment
CN115510795A (en) Data processing method and related device
CN107909141A (en) A kind of data analysing method and device based on grey wolf optimization algorithm
CN110874635B (en) Deep neural network model compression method and device
CN115329974A (en) Simulation method, device, equipment and storage medium
CN111274727B (en) Electronic device, microwave product model design apparatus, and computer-readable medium
CN107870862B (en) Construction method, traversal testing method and computing device of new control prediction model
CN113127019B (en) Verification method and related equipment
WO2023179379A1 (en) Simulation method and system for nonlinear delay circuit system, and medium
CN116665219A (en) Data processing method and device
CN110059326A (en) Simulation method and simulation system for debugging microwave device
Sallem et al. Simulation-based optimization of CCIIs' performances in weak inversion
CN111340217B (en) Electronic device, neural network training apparatus, and computer-readable medium
CN114862000A (en) Trajectory prediction method, apparatus, device and storage medium
CN114996487A (en) Media resource recommendation method and device, electronic equipment and storage medium
US9507894B1 (en) Automatic harmonic number identification for harmonic balance analysis
Kundu et al. Single factor transformation priors for density regression

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