CN109634854B - Method for detecting configuration abnormity of software engineering algorithm - Google Patents
Method for detecting configuration abnormity of software engineering algorithm Download PDFInfo
- Publication number
- CN109634854B CN109634854B CN201811473776.XA CN201811473776A CN109634854B CN 109634854 B CN109634854 B CN 109634854B CN 201811473776 A CN201811473776 A CN 201811473776A CN 109634854 B CN109634854 B CN 109634854B
- Authority
- CN
- China
- Prior art keywords
- algorithm
- configuration
- abnormal
- weight
- total number
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/36—Preventing errors by testing or debugging software
- G06F11/3604—Software analysis for verifying properties of programs
- G06F11/3608—Software analysis for verifying properties of programs using formal methods, e.g. model checking, abstract interpretation
Abstract
The invention relates to a method for detecting configuration abnormity of a software engineering algorithm, belongs to the technical field of software, and solves the problem that the calculation of the occurrence rate of the configuration abnormity in the prior art is inaccurate and unreasonable. The method comprises the following steps: classifying and detecting the software engineering algorithm configuration to obtain the total algorithm configuration number contained in each class in the classification detection result; identifying the number of algorithm configurations of the inconsistency between the configuration diagram contained in each class of the classification detection result and the functional diagram, and analyzing to obtain severity level weights corresponding to the inconsistency; and obtaining the comprehensive configuration abnormal occurrence rate according to the total algorithm configuration number contained in each category in the classification detection result, the number of the algorithm configurations with inconsistent configuration diagrams and function diagrams, and the severity level weight corresponding to the inconsistency. According to the method, the configuration diagram elements are split, the effect of quantizing the configuration logic is achieved, and the calculation method of the abnormal configuration rate is updated.
Description
Technical Field
The invention relates to the technical field of software, in particular to a method for detecting abnormal configuration of a software engineering algorithm.
Background
And the software V & V comprises concept V & V, requirement V & V, design V & V and realization V & V. The design V & V is used for verifying whether the software design meets the actual requirement, and verification contents comprise documents such as algorithm configuration, interfaces and the like of the software.
The existing engineering configuration software is special software for data acquisition and process control, can use a flexible configuration mode, provides a monitoring function for quickly constructing an industrial automatic control system for a user, and provides a basic design platform for engineering configuration research.
The software engineering algorithm configuration verification is to verify the correctness of the configuration by comparing the consistency of the functional diagram and the configuration diagram of the engineering. At present, the method for calculating the occurrence rate of configuration exception is the occurrence rate of configuration exception, i.e. the number of configuration exceptions/the number of pages of the configuration map. In the actual engineering, each configuration diagram has different logic complexity and different logic quantity, so that the calculation of dividing the configuration abnormal quantity by the configuration page number is not reasonable, the result is not accurate, and meanwhile, the calculation method does not consider the influence of the severity grade of the abnormality and does not meet the actual use requirement.
Disclosure of Invention
In view of the foregoing analysis, the embodiments of the present invention provide a method for detecting a configuration anomaly of a software engineering algorithm, so as to solve the problem of inaccurate and unreasonable calculation of the occurrence rate of the configuration anomaly in the prior art.
In one aspect, an embodiment of the present invention provides a method for detecting a configuration exception of a software engineering algorithm, including the following steps:
classifying and detecting the software engineering algorithm configuration to obtain the total algorithm configuration number contained in each class in the classification detection result;
identifying the number of algorithm configurations of the inconsistency between the configuration diagram contained in each class of the classification detection result and the functional diagram, and analyzing to obtain severity level weights corresponding to the inconsistency;
and obtaining the comprehensive configuration abnormal occurrence rate according to the total algorithm configuration number contained in each category in the classification detection result, the number of the algorithm configurations with inconsistent configuration diagrams and function diagrams, and the severity level weight corresponding to the inconsistency.
The beneficial effects of the above technical scheme are as follows: aiming at the problem that the existing configuration abnormity incidence rate is inaccurate and unreasonable to calculate, the configuration elements are classified by researching the characteristics of the engineering V & V software configuration diagram, the incidence rates of different configuration types are respectively calculated, and then the comprehensive configuration abnormity incidence rate is calculated. According to the method, the configuration diagram elements are split, the effect of classifying and quantifying the configuration logic is achieved, the calculation method of the abnormal configuration rate is updated, and the programming implementation is facilitated. A large number of tests prove that the result is effective and accurate.
In another embodiment based on the above method, the classification detection includes a connection detection, an algorithm block detection, and a roll call detection.
The beneficial effects of the above technical scheme are: the classification detection method of the software engineering algorithm configuration is limited, namely classification is carried out according to configuration diagram elements, and the classification is divided into connection line detection, algorithm block detection and roll call detection, so that subsequent quantization and programming are conveniently realized.
Further, the classifying and detecting the software engineering algorithm configuration to obtain the total number of algorithm configurations included in each class in the classifying and detecting result includes the following steps:
drawing a configuration diagram corresponding to a software engineering algorithm;
performing connection detection, algorithm block detection and roll call detection on the software engineering algorithm configuration through the configuration diagram;
and counting the total number of connecting lines, the total number of algorithm blocks and the total number of roll names in the software engineering algorithm configuration through the classification detection result.
The beneficial effects of the further scheme are as follows: the configuration map elements are quantized.
Further, the step of identifying the number of the algorithm configurations in which the configuration diagram included in each of the classification detection results is inconsistent with the function diagram, and analyzing to obtain the severity level weight corresponding to the inconsistency includes the following steps:
drawing a functional diagram corresponding to a software engineering algorithm;
comparing and analyzing a function diagram and a configuration diagram corresponding to the software engineering algorithm, identifying the number of algorithm configurations of which the configuration diagram contained in each class is inconsistent with the function diagram in the classification detection result, and obtaining the number of abnormal algorithm blocks, the number of abnormal connecting lines and the number of abnormal roll calling;
and obtaining the severity grade weight corresponding to each class in the classification detection result by an expert evaluation method.
The beneficial effects of the further scheme are as follows: and counting the configuration diagram abnormity, specifically, counting the number of the elements of the configuration diagram with abnormity.
Further, the severity level weight comprises an algorithm block abnormal weight, a connection abnormal weight and a roll call abnormal weight;
the severity level includes general and severe.
The beneficial effects of the further scheme are as follows: and the severity grade of the algorithm configuration abnormity is classified and evaluated, so that accurate distinguishing and programming realization are facilitated.
Further, the severity level corresponding to the algorithm block abnormality is severe, and the severity levels of the link abnormality and the name abnormality are general.
The beneficial effects of the further scheme are as follows: and evaluating the severity levels of the algorithm block abnormality, the connecting line abnormality and the point name abnormality, so that the accurate distinguishing and programming realization are facilitated.
Further, the step of obtaining the comprehensive configuration abnormality occurrence rate according to the algorithm configuration total number contained in each category of the classification detection result, the algorithm configuration number of the inconsistency between the configuration diagram and the function diagram, and the severity level weight corresponding to the inconsistency includes the following steps:
acquiring the abnormal occurrence rate of the algorithm blocks according to the abnormal number of the algorithm blocks and the total number of the algorithm blocks;
obtaining the occurrence rate of the abnormal connecting lines according to the number of the abnormal connecting lines and the total number of the connecting lines;
acquiring the roll call abnormal occurrence rate according to the roll call abnormal number and the roll call total number;
and obtaining the comprehensive configuration abnormal incidence according to the algorithm block abnormal incidence, the connecting line abnormal incidence and the roll call abnormal incidence by combining the algorithm block abnormal weight, the connecting line abnormal weight and the roll call abnormal weight.
The beneficial effects of the further scheme are as follows: and limiting the method for obtaining the comprehensive configuration abnormity incidence, and obtaining parameters such as the number and the total number of the abnormal configurations of each algorithm through statistics so as to obtain the comprehensive configuration abnormity incidence.
Further, the algorithm block anomaly occurrence rate x1Is composed of
x1＝d/a
In the formula, d represents the number of abnormal algorithm blocks, and a represents the total number of algorithm blocks.
The incidence rate x of connection anomaly2Is composed of
x2＝e/b
In the formula, e represents the number of abnormal connecting lines, and b represents the total number of the connecting lines.
The roll call anomaly incidence rate x3Is composed of
x3＝f/c
In the formula, f represents the number of roll names abnormal, and c represents the total number of roll names.
The beneficial effects of the further scheme are as follows: and the algorithm of the abnormal occurrence rate of the configuration of each algorithm is limited, and the method is simple and easy to program.
Further, the comprehensive configuration abnormality occurrence rate y is
y＝x1·m+x2·n+x3·p
In the formula, m represents the abnormal weight of the algorithm block, n represents the abnormal weight of the connecting line, and p represents the abnormal weight of the roll call.
The beneficial effects of the further scheme are as follows: and limiting an algorithm of the comprehensive configuration abnormity incidence, specifically, calculating the comprehensive configuration abnormity incidence of the configuration diagram through weighting.
Further, the weight of the algorithm block exception is 40%, and the weight of the connection exception and the point name exception is 30%.
The beneficial effects of the further scheme are as follows: reference weights are provided for the weighting calculations.
In the invention, the technical schemes can be combined with each other to realize more preferable combination schemes. Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
Drawings
The drawings are only for purposes of illustrating particular embodiments and are not to be construed as limiting the invention, wherein like reference numerals are used to designate like parts throughout.
FIG. 1 is a schematic diagram illustrating steps of a method for detecting an abnormal configuration of a software engineering algorithm according to embodiment 1 of the present invention;
fig. 2 is a schematic diagram of the steps of performing classification detection on software engineering algorithm configurations and obtaining the total number of algorithm configurations included in each class in the classification detection result in embodiment 2 of the present invention;
fig. 3 is a schematic diagram illustrating steps of identifying the number of algorithm configurations in which a configuration diagram included in each of the classification detection results is inconsistent with a function diagram, and analyzing to obtain severity level weights corresponding to the inconsistency according to embodiment 2 of the present invention;
fig. 4 is a schematic diagram of a step of obtaining an abnormal occurrence rate of a comprehensive configuration according to the total number of algorithm configurations included in each class in the classification detection result, the number of algorithm configurations in which the configuration diagram is inconsistent with the function diagram, and severity level weights corresponding to the inconsistency in the embodiment 2 of the present invention;
fig. 5 is an example of a configuration diagram according to embodiment 2 of the present invention;
fig. 6 is a functional diagram example of embodiment 2 of the present invention.
Reference numerals:
firstly, connecting lines; algorithm block; ③ roll calling;
Detailed Description
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate preferred embodiments of the invention and together with the description, serve to explain the principles of the invention and not to limit the scope of the invention.
Example 1
One embodiment of the present invention, as shown in fig. 1, discloses a method for detecting software engineering algorithm configuration abnormality, comprising the following steps:
s1, carrying out classification detection on the software engineering algorithm configuration to obtain the total number of algorithm configurations contained in each class in a classification detection result.
And S2, identifying the number of algorithm configurations with inconsistent configuration diagrams and function diagrams contained in each class in the classification detection result, and analyzing to obtain severity level weights corresponding to the inconsistency.
And S3, obtaining the comprehensive configuration abnormal occurrence rate according to the algorithm configuration total number contained in each class in the classification detection result, the algorithm configuration number of the inconsistency of the configuration diagram and the function diagram, and the severity level weight corresponding to the inconsistency.
Compared with the prior art, the method for detecting the configuration abnormality of the software engineering algorithm, provided by the embodiment, aims at the problem that the existing configuration abnormality occurrence rate is inaccurate and unreasonable in calculation, classifies the configuration elements by researching the characteristics of the engineering V & V software configuration diagram, respectively calculates the occurrence rates of different configuration types, and then calculates the comprehensive configuration abnormality occurrence rate. According to the method, the configuration diagram elements are split, the effect of classifying and quantifying the configuration logic is achieved, the calculation method of the abnormal configuration rate is updated, and the programming implementation is facilitated. A large number of tests prove that the result is effective and accurate.
Example 2
And optimizing on the basis of the embodiment 1, wherein the classified detection comprises connection detection, algorithm block detection and roll call detection.
Preferably, as shown in fig. 2, step S1 can be further refined into the following steps:
and S11, drawing a configuration diagram corresponding to the software engineering algorithm, for example, the configuration diagram shown in FIG. 5.
S12, performing connection detection (I), algorithm block detection (II) and roll call detection (III) on the software engineering algorithm configuration through the configuration diagram. Wherein, the connecting line is defined as the connecting line between the two algorithm blocks, and the roll call is defined as the important node concerned by the designer.
And S13, counting the total number of connecting lines, the total number of algorithm blocks and the total number of roll names in the software engineering algorithm configuration through the classification detection result.
Preferably, as shown in fig. 3, the step S2 can be further refined into the following steps:
and S21, drawing a functional diagram corresponding to the software engineering algorithm, for example, the functional diagram shown in FIG. 6.
And S22, comparing and analyzing the function diagrams and the configuration diagrams corresponding to the software engineering algorithm, identifying the number of algorithm configuration numbers with different configuration diagrams from the function diagrams contained in each class in the classification detection result, and obtaining the number of abnormal algorithm blocks, the number of abnormal connection lines and the number of abnormal roll calls. The number of the abnormal algorithm blocks is the number of the inconsistent algorithm blocks in the configuration diagram and the function diagram, the number of the abnormal connecting lines is the number of the inconsistent connecting lines in the configuration diagram and the function diagram, and the number of the abnormal roll calling is the number of the inconsistent roll calling in the configuration diagram and the function diagram. The identification method can be realized by adopting a manual method or computer programming.
And S23, obtaining severity grade weight corresponding to each class in the classification detection result by an expert evaluation method.
Preferably, in step S23, the severity level weights include an algorithm block abnormality weight, a link abnormality weight, and a point name abnormality weight. Severity levels include general and severe.
Preferably, the severity level corresponding to the abnormal algorithm block is set to be severe and corresponds to one weight value, and the severity levels of the abnormal connection and the abnormal name are set to be general and correspond to another weight value.
Preferably, as shown in fig. 4, the step S3 can be further refined into the following steps:
s31, acquiring the abnormal occurrence rate of the algorithm blocks according to the abnormal number of the algorithm blocks and the total number of the algorithm blocks;
s32, obtaining the occurrence rate of the abnormal connecting lines according to the number of the abnormal connecting lines and the total number of the connecting lines;
s33, obtaining the roll call abnormal occurrence rate according to the roll call abnormal number and the roll call total number;
and S34, obtaining the comprehensive configuration abnormity incidence according to the abnormity incidence of the algorithm block, the abnormity incidence of the connecting line and the abnormity incidence of the roll call by combining the abnormity weight of the algorithm block, the abnormity weight of the connecting line and the abnormity weight of the roll call.
Preferably, in step S31, the algorithm block is abnormalIncidence x1Is composed of
x1＝d/a
In the formula, d represents the number of abnormal algorithm blocks, and a represents the total number of algorithm blocks.
In step S32, the occurrence rate x of abnormal connection2Is composed of
x2＝e/b
In the formula, e represents the number of abnormal connecting lines, and b represents the total number of the connecting lines.
In step S33, the roll call abnormality occurrence rate x3Is composed of
x3＝f/c
In the formula, f represents the number of roll names abnormal, and c represents the total number of roll names.
Preferably, in step S34, the comprehensive configuration abnormality occurrence rate y is
y＝x1·m+x2·n+x3·p
In the formula, m represents the abnormal weight of the algorithm block, n represents the abnormal weight of the connecting line, and p represents the abnormal weight of the roll call.
Preferably, the algorithm block exception weight is 40%, and the join exception and point name exception weight is 30%.
Compared with the embodiment 1, the method provided by the embodiment achieves the effect of classifying and quantizing the configuration logic by splitting the configuration diagram elements, increases the configuration exception weight (namely the algorithm block exception weight, the connection exception weight and the roll call exception weight), updates the calculation method of the comprehensive configuration exception occurrence rate, and facilitates the programming realization.
Those skilled in the art will appreciate that all or part of the flow of the method implementing the above embodiments may be implemented by a computer program, which is stored in a computer readable storage medium, to instruct related hardware. The computer readable storage medium is a magnetic disk, an optical disk, a read-only memory or a random access memory.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention 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 invention are included in the scope of the present invention.
Claims (8)
1. A method for detecting software engineering algorithm configuration abnormity is characterized by comprising the following steps:
the method for classifying and detecting the software engineering algorithm configuration to obtain the total number of the algorithm configurations contained in each class in the classification detection result comprises the following steps:
drawing a configuration diagram corresponding to a software engineering algorithm;
the classified detection comprises connection detection, algorithm block detection and roll call detection;
performing connection detection, algorithm block detection and roll call detection on the software engineering algorithm configuration through the configuration diagram;
counting the total number of connecting lines, the total number of algorithm blocks and the total number of roll names in the software engineering algorithm configuration through the classification detection result;
identifying the number of algorithm configurations of the inconsistency between the configuration diagram contained in each class of the classification detection result and the functional diagram, and analyzing to obtain severity level weights corresponding to the inconsistency;
and obtaining the comprehensive configuration abnormal occurrence rate according to the total algorithm configuration number contained in each category in the classification detection result, the number of the algorithm configurations with inconsistent configuration diagrams and function diagrams, and the severity level weight corresponding to the inconsistency.
2. The method of claim 1, wherein the step of identifying the number of algorithm configurations in which the configuration diagram included in each of the classification detection results is inconsistent with the function diagram, and analyzing the identified number to obtain the severity level weight corresponding to the inconsistency includes the steps of:
drawing a functional diagram corresponding to a software engineering algorithm;
comparing and analyzing a function diagram and a configuration diagram corresponding to the software engineering algorithm, identifying the number of algorithm configurations of which the configuration diagram contained in each class is inconsistent with the function diagram in the classification detection result, and obtaining the number of abnormal algorithm blocks, the number of abnormal connecting lines and the number of abnormal roll calling;
and obtaining the severity grade weight corresponding to each class in the classification detection result by an expert evaluation method.
3. The method of claim 2, wherein the severity level weights comprise an algorithm block exception weight, a link exception weight, and a roll call exception weight;
the severity level includes general and severe.
4. The method of claim 3, wherein the severity level of the algorithm block abnormality is severe, and the severity levels of the tie-line abnormality and the point name abnormality are general.
5. The method according to claim 2, wherein the step of obtaining the comprehensive abnormal configuration rate according to the algorithm configuration total number, the algorithm configuration number of the inconsistency between the configuration diagram and the function diagram, and the severity level weight of the inconsistency included in each of the classification detection results comprises the steps of:
acquiring the abnormal occurrence rate of the algorithm blocks according to the abnormal number of the algorithm blocks and the total number of the algorithm blocks;
obtaining the occurrence rate of the abnormal connecting lines according to the number of the abnormal connecting lines and the total number of the connecting lines;
acquiring the roll call abnormal occurrence rate according to the roll call abnormal number and the roll call total number;
and obtaining the comprehensive configuration abnormal incidence according to the algorithm block abnormal incidence, the connecting line abnormal incidence and the roll call abnormal incidence by combining the algorithm block abnormal weight, the connecting line abnormal weight and the roll call abnormal weight.
6. The method of claim 5, wherein the algorithm block anomaly occurrence rate x is1Is composed of
x1＝d/a
In the formula, d represents the abnormal number of the algorithm blocks, and a represents the total number of the algorithm blocks;
the incidence rate x of connection anomaly2Is composed of
x2＝e/b
In the formula, e represents the number of abnormal connecting lines, and b represents the total number of the connecting lines;
the roll call anomaly incidence rate x3Is composed of
x3＝f/c
In the formula, f represents the number of roll names abnormal, and c represents the total number of roll names.
7. The method according to claim 6, wherein the comprehensive configuration abnormality occurrence rate y is
y＝x1·m+x2·n+x3·p
In the formula, m represents the abnormal weight of the algorithm block, n represents the abnormal weight of the connecting line, and p represents the abnormal weight of the roll call.
8. The method of claim 7, wherein the weight of the algorithm block exception is 40%, and the weight of the link exception and the point name exception is 30%.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811473776.XA CN109634854B (en) | 2018-12-04 | 2018-12-04 | Method for detecting configuration abnormity of software engineering algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811473776.XA CN109634854B (en) | 2018-12-04 | 2018-12-04 | Method for detecting configuration abnormity of software engineering algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109634854A CN109634854A (en) | 2019-04-16 |
| CN109634854B true CN109634854B (en) | 2022-03-15 |
Family
ID=66071001
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811473776.XA Active CN109634854B (en) | 2018-12-04 | 2018-12-04 | Method for detecting configuration abnormity of software engineering algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109634854B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111401028B (en) * | 2020-03-19 | 2023-12-26 | 北京广利核系统工程有限公司 | Automatic comparison method and device for RPS software versions of nuclear power station |
| CN111830918B (en) * | 2020-07-20 | 2021-08-03 | 北京广利核系统工程有限公司 | EPLAN platform-based nuclear power DCS control cabinet complete drawing upgrading method and system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1244208A1 (en) * | 2001-03-21 | 2002-09-25 | Pioneer Corporation | Power amplifying device |
| CN1403999A (en) * | 2001-09-10 | 2003-03-19 | 英业达股份有限公司 | Inspection method of product allocation to be delivered |
| CN102360335A (en) * | 2011-10-19 | 2012-02-22 | 北京广利核系统工程有限公司 | Method for quantitatively evaluating value of security level DCS (Data Communication System) application software defect for nuclear power plant |
-
2018
- 2018-12-04 CN CN201811473776.XA patent/CN109634854B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1244208A1 (en) * | 2001-03-21 | 2002-09-25 | Pioneer Corporation | Power amplifying device |
| CN1403999A (en) * | 2001-09-10 | 2003-03-19 | 英业达股份有限公司 | Inspection method of product allocation to be delivered |
| CN102360335A (en) * | 2011-10-19 | 2012-02-22 | 北京广利核系统工程有限公司 | Method for quantitatively evaluating value of security level DCS (Data Communication System) application software defect for nuclear power plant |
Non-Patent Citations (1)
| Title |
|---|
| 一种在Auto CAD下的组态工具软件的设计方法;中国自动化网;《https://m.e-works.net.cn/articles/article34433.htm》;20051212;第1-4页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109634854A (en) | 2019-04-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108520357B (en) | Method and device for judging line loss abnormality reason and server | |
| US10482093B2 (en) | Data mining method | |
| CN106951984B (en) | Dynamic analysis and prediction method and device for system health degree | |
| US7243049B1 (en) | Method for modeling system performance | |
| CN109949290A (en) | Pavement crack detection method, device, equipment and storage medium | |
| Grbac et al. | A second replicated quantitative analysis of fault distributions in complex software systems | |
| CN109634854B (en) | Method for detecting configuration abnormity of software engineering algorithm | |
| CN109711707B (en) | Comprehensive state evaluation method for ship power device | |
| CN110930248A (en) | Credit risk prediction model construction method and system, storage medium and electronic equipment | |
| CN110634060A (en) | User credit risk assessment method, system, device and storage medium | |
| CN110703743A (en) | Equipment failure prediction and detection system and method | |
| CN111627199A (en) | Hydropower station dam safety monitoring system and monitoring method | |
| CN115952081A (en) | Software testing method, device, storage medium and equipment | |
| CN116882804A (en) | Intelligent power monitoring method and system | |
| CN115719283A (en) | Intelligent accounting management system | |
| CN111612019A (en) | Method for identifying and analyzing fault abnormality of intelligent electric meter based on big data model | |
| CN111612149A (en) | Main network line state detection method, system and medium based on decision tree | |
| CN107862599B (en) | Bank risk data processing method and device, computer equipment and storage medium | |
| CN112598326A (en) | Model iteration method and device, electronic equipment and storage medium | |
| CN105469141A (en) | Neural-network-based prediction method and system | |
| CN105227410A (en) | Based on the method and system that the server load of adaptive neural network detects | |
| CN114219245A (en) | Village power index evaluation method and device based on big data and storage medium | |
| CN113902457A (en) | Method and device for evaluating reliability of house source information, electronic equipment and storage medium | |
| CN112712194A (en) | Electric quantity prediction method and device for power consumption cost intelligent optimization analysis | |
| CN113627585A (en) | Single well index prediction method and system based on long-time and short-time memory neural network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |