CN110990573A - Genetic algorithm intelligent volume assembling method and device based on segmented real number coding and readable storage medium - Google Patents
Genetic algorithm intelligent volume assembling method and device based on segmented real number coding and readable storage medium Download PDFInfo
- Publication number
- CN110990573A CN110990573A CN201911293627.XA CN201911293627A CN110990573A CN 110990573 A CN110990573 A CN 110990573A CN 201911293627 A CN201911293627 A CN 201911293627A CN 110990573 A CN110990573 A CN 110990573A
- Authority
- CN
- China
- Prior art keywords
- test
- individual
- genetic algorithm
- real number
- fitness
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Biophysics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Biomedical Technology (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Genetics & Genomics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Physiology (AREA)
- Databases & Information Systems (AREA)
- Electrically Operated Instructional Devices (AREA)
Abstract
The invention provides a genetic algorithm intelligent paper-composing method, equipment and a readable storage medium based on segmented real number coding, which comprises the steps of 1, coding test papers, mapping each set of test paper into an independent chromosome in the genetic algorithm, mapping the test papers into genes, and completing the gene value under the support of a coding mechanism; step 2, generating an initial population, and generating N sets of test paper, namely the initial population, in a random extraction mode; and 3, calculating the individual fitness, calculating and initializing to obtain the fitness values of all the individuals in the initial population, and evaluating the quality. Step 4, selecting operators, eliminating inferior individuals according to the fitness value, and reserving superior individuals in the population; step 5, generating a new operator by adopting a gene crossing and mutation mode; and 6, setting a termination condition, searching the test questions matched with the characteristic parameters in the test question library according to a given constraint condition, thereby extracting an optimal test question combination and selecting an individual with the highest fitness value as a final test paper.
Description
Technical Field
The invention relates to the field of genetic algorithms, in particular to a genetic algorithm intelligent volume assembling method based on segmented real number coding, equipment and a readable storage medium.
Background
With the popularization of computer use, paperless and automatic examinations gradually become a trend, and one of the key steps for realizing paperless examinations is intelligent examination paper composition. The intelligent test paper is a high-quality test paper which is automatically formed by extracting test questions from a question bank according to the requirements of a question maker and meets multiple constraint conditions.
Currently, the commonly used group volume policy includes three types: a random volume-grouping algorithm, a backtracking volume-grouping algorithm and a genetic algorithm. Random paper grouping is the most common strategy, and randomly screens test questions and adds the test questions into the test paper according to the control indexes of the state space, and the process is repeated continuously until the paper grouping is finished or the test questions meeting the conditions cannot be screened; the backtracking algorithm is characterized in that each state generated by the random algorithm is recorded on the basis of the random algorithm, backtracking is carried out when search fails, the last recorded state is released, then a new state type probe is generated according to a rule, and the backtracking algorithm has better paper grouping efficiency for a paper grouping model with few constraint conditions but has large memory occupation, relatively complex program structure and long paper grouping time and is difficult to meet the real-time paper grouping requirement of a user through continuous backtracking probes until the test paper generation is finished or the initial state is backtracked; compared with the former two methods, the genetic algorithm has incomparable advantages in the group rolling speed and the group rolling quality, and is concerned in the field of intelligent group rolling.
Disclosure of Invention
In order to overcome the defects in the prior art, the invention carries out optimization design on the aspects of a test question coding method, an optimized adaptability value, an improved selection strategy and the like on the basis of the traditional genetic algorithm, can rapidly and successfully group the test paper, and improves the test paper grouping efficiency.
The method comprises the following steps:
step 1, encoding test questions, namely mapping each set of test paper into an independent chromosome in a genetic algorithm, mapping the test questions in the test paper into genes, and completing the gene values under the support of an encoding mechanism;
step 2, generating an initial population, and generating N sets of test paper, namely the initial population, in a random extraction mode;
step 3, calculating the individual fitness, calculating and initializing the fitness values of all the individuals in the initial population, and evaluating the quality;
step 4, selecting an operator, eliminating inferior individuals according to the fitness value, and reserving superior individuals in the population;
step 5, generating a new operator, and generating the new operator by adopting a gene crossing and mutation mode;
and 6, setting a termination condition, searching test questions matched with the characteristic parameters in the test question library according to a given constraint condition, and extracting an optimal test question combination.
The invention also provides a device for realizing the genetic algorithm intelligent volume assembling method based on the segmented real number coding, which comprises the following steps:
the memory is used for storing a computer program and a genetic algorithm intelligent volume assembling method based on the segmented real number coding;
and the processor is used for executing the computer program and the genetic algorithm intelligent volume assembling method based on the segmented real number codes so as to realize the steps of the genetic algorithm intelligent volume assembling method based on the segmented real number codes.
The invention also provides a readable storage medium with the genetic algorithm intelligent volume organizing method based on the segmented real number coding, and a computer program is stored on the readable storage medium and is executed by a processor to realize the steps of the genetic algorithm intelligent volume organizing method based on the segmented real number coding.
According to the technical scheme, the invention has the following advantages:
the invention adopts a real number segmented coding mode, is convenient for the segmented operation of the genetic algorithm, has better searching capability and can relatively shorten the solving time.
The selection is carried out by adopting a mode of combining an elite selection strategy and roulette, excellent individuals can be simultaneously reserved, the diversity of the population is maintained, and the local optimal solution is prevented from being generated too early.
And the importance degree of the constraint condition is assigned by adopting a classification constraint method, so that the success rate of volume combination is improved.
Drawings
In order to more clearly illustrate the technical solution of the present invention, the drawings used in the description will be briefly introduced, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained based on these drawings without creative efforts.
FIG. 1 is a flow chart of a genetic algorithm intelligent volume generation method based on segmented real number coding;
FIG. 2 is a flow chart of an embodiment of a genetic algorithm intelligent volume assembling method based on segmented real number coding.
Fig. 3 is a diagram of a real number segment encoding format.
Detailed Description
Those of ordinary skill in the art will appreciate that the elements and algorithm steps of the examples described in connection with the embodiments disclosed herein may be embodied in electronic hardware, computer software, or combinations of both, and that the components and steps of the examples have been described in a functional general in the foregoing description for the purpose of illustrating clearly the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The block diagrams shown in the figures are functional entities only and do not necessarily correspond to physically separate entities. I.e. these functional entities may be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor means and/or microcontroller means.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may also be an electric, mechanical or other form of connection.
The invention provides a genetic algorithm intelligent volume assembling method based on segmented real number coding, which comprises the following steps of:
step 1, encoding test questions, namely mapping each set of test paper into an independent chromosome in a genetic algorithm, mapping the test questions in the test paper into genes, and completing the gene values under the support of an encoding mechanism;
step 1, independently designing real number codes according to different question types by adopting a real number segmented coding mode;
step 1, a mapping mode that one chromosome corresponds to one test paper is adopted, a special number of each question is used as a gene, the gene value is a numerical value of the question number, the question numbers of different question types are placed in a classification mode, and segmentation is realized based on the question types. Taking a test paper of information technology academic proficiency level test as an example, 5 channels are required to be singly selected, 5 channels are required to be selected more, 8 channels are judged, 4 channels are filled in, 2 channels are asked for questions and answers, and the corresponding chromosome codes are as follows:
(2、22、97、43、105|4、21、38、19、7|52、16、57、13、35、48、77、91|71、25、47、39|12、55)
description of the drawings: (single selection | multiple selection | judgment | space filling | question and answer).
Step 2, generating an initial population, and generating N sets of test paper, namely the initial population, in a random extraction mode;
generating an initial population in step 2. First, the population size needs to be confirmed, and usually, an initial value is set according to a manual standard, a multiple of 50 or 100 is selected, and the initial population size is determined to be 1000 by the invention. According to a segmented real number coding mode, the question types are used as basic units and are randomly generated, the genetic algorithm process is simplified, and the volume forming speed is improved.
Step 3, calculating the individual fitness, calculating and initializing the fitness values of all the individuals in the initial population, and evaluating the quality;
the fitness value obtaining formula in step 3 is as follows:
the fitness value is: f (x) ═ 1-F (x), (o < F < 1)
The objective function is:
githe closer the gap between the ith constraint and the user requirement is, the closer the constraint g isiThe smaller;
wi(wi＞0,w1+w2+…+wn1) is a weight given to the ith constraint.
Step 4, selecting an operator, eliminating inferior individuals according to the fitness value, and reserving superior individuals in the population;
the main goal of selection is to have more chance for "good" individuals in the current population to propagate offspring in order to deliver the "good" gene. Meanwhile, the selection rule should also ensure that the population always has a certain diversity, i.e. a part of relatively poor individuals are reserved with a certain probability, and the algorithm is prevented from being premature and converging to a suboptimal solution. The invention adopts a mode of combining an elite selection strategy and roulette, namely, excellent individuals in a population are directly inherited to the next generation, and the rest individuals adopt a random roulette method to judge whether each individual is inherited to the next generation or not by judging the probability that each individual is possibly selected. The selectivity can be calculated by the ratio C of the fitness of a single individual to the sum of the fitness values of each individual in the populationiTo be determined. Finally in [0, 1]]Randomly generating a series of arrays if the value in the random array is greater than the probability value C of the individual being selectediThen the individual is selected to enter the next generationOtherwise, the individual is directly discarded. Assuming that there are n individuals in the population and the fitness is f (x), the probability of selecting it is:
the interval definition process is as follows:
1) calculating the proportion of the fitness value of each individual to the total fitness of the population, namely the selection probability P(x)；
2) Each individual forms a carousel zone, the size of which is determined by the fitness size of the individual, denoted by [ P ' (x-1), P ' (x) ], where P ' (0) is 0, P ' (x) is P (x) plus P ' (x-1), x is 1, 2 …, 1000;
3) generating a random number r, wherein r belongs to (0, 1 ];
4) if r is less than or equal to C' (1), selecting an individual 1; otherwise, if C '(j-1) < r ≦ C' (j), selecting the individual j.
Step 5, generating a new operator, and generating the new operator by adopting a gene crossing and mutation mode;
step 5 includes both crossover and mutation modes. The invention uses a segmented real number coding mode, the crossing needs to be carried out in a single-point crossing mode according to a question type segmentation mode, and a set of test paper presents multi-point crossing. And (3) a crossing process: and performing pairwise pairing operation on all the test papers in the group, randomly selecting a cross point in each question type, exchanging questions before and after the cross points of the two sets of test papers, and generating two sets of new test papers. Repeated question numbers may appear on the new test paper after the crossing, and the repeated question numbers are replaced by new unrepeated question numbers to generate a set of new test paper.
The invention adopts basic bit variation, namely one or more genes are randomly assigned to an individual (test question type) coding string, a new test question number is generated by adopting a random extraction mode, and the original test question number is replaced to generate a set of new test paper.
And 6, setting a termination condition, searching test questions matched with the characteristic parameters in the test question library according to a given constraint condition, and extracting an optimal test question combination.
The invention adopts the given iteration times as a termination mode, and can terminate the algorithm when the given iteration times are reached.
To further illustrate the above method, a specific embodiment is described below, as shown in fig. 2, taking a "information technology academic proficiency level test" as an example, the paper-making process takes question types, general scores, difficulty, knowledge points, test questions and the requirement of the ability of examinees as constraints. Each test question is composed of the above 5 indexes, forming a matrix of m × 5, m represents the number of test questions, each column in the S matrix represents an attribute of the test question, each row represents all the attributes of one test question, and the matrix is as follows:
step (1): the test paper comprises 5 question types of single-choice questions (5), multiple-choice questions (5), judgment questions (8), blank filling questions (4) and question and answer questions (2), and is coded according to the question types in a real number segmented coding mode, and the detailed coding is shown in figure 3.
Step (2): initializing the population, and forming 1000 sets of test paper by adopting a mode of dividing the topic type and randomly drawing.
And (3): and calculating and sorting the fitness value. In order to improve the success rate of volume grouping, a classification constraint method is adopted in the research to assign the importance degree of constraint conditions: strong constraint (question type, total score and knowledge point) and sub-constraint (difficulty and question requirements on examinee capacity), based on which, the proportion of the constraint conditions is respectively 20%, 20%, 20%, 10% and 10%, and the fitness value is calculated for 1000 generated test papers and sorted according to the fitness value.
And (4): and selecting an operator, and extracting 10% of individuals before the fitness value according to an elite selection strategy to directly transmit to the next generation. In addition, of the remaining individuals, 10% (100 sets of test papers) were drawn using the roulette option.
The roulette selection method has the following operation flow:
1) calculating the proportion of the fitness value of each individual to the total fitness of the population, namely the selection probability P(x)；
2) Each individual forms a carousel zone, the size of which is determined by the fitness size of the individual, denoted by [ P ' (x-1), P ' (x) ], where P ' (0) is 0, P ' (x) is P (x) plus P ' (x-1), x is 1, 2 …, 1000;
3) generating a random number r, wherein r belongs to (0, 1 ];
4) if r is less than or equal to C' (1, selecting the individual 1; otherwise, if C '(j-1) < r ≦ C' (j), selecting the individual j;
and repeating the step 3) and the step 4), and finally selecting 200 test paper sets to be inherited to the next generation.
And (5) crossing and mutating to generate a new operator.
Step (5.1) cross operator: and performing single-point crossing according to a question type segmentation mode, wherein one set of test paper presents multi-point crossing. And (3) a crossing process: and randomly pairing all the test papers in the group, randomly setting a cross point in each question type, performing cross, and if the same question appears, replacing the repeated question number with a new unrepeated question number to generate a set of new test papers.
Step (5.2) performing operator mutation: randomly selecting a variation point from different topic segments for variation, if variation exists in the segment, reselecting the variation point for variation, otherwise, directly replacing the original value with the value after variation.
And (6) terminating conditions. The given iteration number is used as a termination mode, and the termination number is set to be 100.
Although the embodiments of the present invention have been described with reference to the accompanying drawings, it is not intended to limit the scope of the present invention, and it should be understood by those skilled in the art that various modifications and variations can be made without inventive efforts by those skilled in the art based on the technical solution of the present invention.
Based on the method, the invention also provides equipment for realizing the genetic algorithm intelligent volume assembling method based on the segmented real number coding, which comprises the following steps: the memory is used for storing a computer program and a genetic algorithm intelligent volume assembling method based on the segmented real number coding; and the processor is used for executing the computer program and the genetic algorithm intelligent volume assembling method based on the segmented real number codes so as to realize the steps of the genetic algorithm intelligent volume assembling method based on the segmented real number codes.
Based on the method, the invention also provides a readable storage medium with the genetic algorithm intelligent volume organizing method based on the segmented real number coding, and the readable storage medium stores a computer program which is executed by a processor to realize the steps of the genetic algorithm intelligent volume organizing method based on the segmented real number coding.
The apparatus implementing the segmented real number encoding based genetic algorithm intelligent volume organizing method is the elements and algorithm steps of the examples described in connection with the embodiments disclosed herein, and can be implemented in electronic hardware, computer software, or a combination of both, and the components and steps of the examples have been generally described in terms of functionality in the foregoing description for clarity of illustration of interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
Through the above description of the embodiments, those skilled in the art will readily understand that the apparatus for implementing the intelligent volume-organizing method based on a segmented real number encoding genetic algorithm described herein can be implemented by software, and can also be implemented by software in combination with necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (which may be a CD-ROM, a usb disk, a removable hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which may be a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the indexing method according to the embodiments of the present disclosure.
Claims (9)
1. A genetic algorithm intelligent volume assembling method based on segmented real number coding is characterized by comprising the following steps:
step 1, encoding test questions, namely mapping each set of test paper into an independent chromosome in a genetic algorithm, mapping the test questions in the test paper into genes, and completing the gene values under the support of an encoding mechanism;
step 2, generating an initial population, and generating N sets of test paper, namely the initial population, in a random extraction mode;
step 3, calculating the individual fitness, calculating and initializing the fitness values of all the individuals in the initial population, and evaluating the quality;
step 4, selecting an operator, eliminating inferior individuals according to the fitness value, and reserving superior individuals in the population;
step 5, generating a new operator, and generating the new operator by adopting a gene crossing and mutation mode;
and 6, setting a termination condition, searching test questions matched with the characteristic parameters in the test question library according to a given constraint condition, and extracting an optimal test question combination.
2. The method of claim 1,
step 1, a real number segmented coding mode is adopted, and real number coding is independently designed according to different question types.
3. The method of claim 1,
in step 2, the method for generating the initial population comprises the following steps:
confirming the size of the population, setting an initial value according to an artificial standard, and selecting a multiple of 50 or 100;
according to a segmented real number coding mode, the question types are used as basic units and are randomly generated, the genetic algorithm process is simplified, and the volume forming speed is improved.
4. The method of claim 1,
the fitness value obtaining formula in step 3 is as follows:
the fitness value is: f (x) ═ 1-F (x), (o < F < 1)
The objective function is:
githe closer the gap between the ith constraint and the user requirement is, the closer the constraint g isiThe smaller;
wi(wi＞0,w1+w2+…+wn1) is a weight given to the ith constraint.
5. The method of claim 1,
step 4 also includes:
adopting a mode of combining an elite selection strategy and roulette, namely directly inheriting excellent individuals in a population to the next generation, and judging whether the excellent individuals are inherited to the next generation by judging the probability that each individual is possibly selected by adopting a random roulette method;
the selectivity is calculated by the ratio C of the fitness of a single individual to the sum of the fitness values of each individual in the populationiTo determine;
in [0, 1]]Randomly generating a series of arrays if the value in the random array is greater than the probability value C of the individual being selectediIf not, directly discarding the individual;
assuming that there are n individuals in the population and the fitness is f (x), the probability of selecting it is:
the interval definition process is as follows:
1) calculating the proportion of the fitness value of each individual to the total fitness of the population, namely the selection probability P(x)；
2) Each individual forms a carousel zone, the size of which is determined by the fitness size of the individual, denoted by [ P ' (x-1), P ' (x) ], where P ' (0) is 0, P ' (x) is P (x) plus P ' (x-1), x is 1, 2 …, 1000;
3) generating a random number r, wherein r belongs to (0, 1 ];
4) if r is less than or equal to C' (1), selecting an individual 1; otherwise, if C '(j-1) < r ≦ C' (j), selecting the individual j.
6. The method of claim 1,
step 5 comprises two modes of crossing and mutation;
and (3) a crossing process: pairing all the test papers in the group, randomly selecting a cross point in each question type, exchanging questions before and after the cross points of the two sets of test papers to generate two sets of new test papers; the new cross test paper has repeated question numbers, and the repeated question numbers are replaced by new unrepeated question numbers to generate a set of new test paper;
and (3) adopting basic bit variation to randomly assign one or more genes to the individual coding strings, adopting a random extraction mode to generate a new test question number, replacing the original test question number, and generating a set of new test paper.
7. The method of claim 1,
and 6, adopting the given iteration times as a termination mode, and terminating the algorithm when the given iteration times are reached.
8. An apparatus for implementing a genetic algorithm intelligent volume organizing method based on segmented real number coding, comprising:
the memory is used for storing a computer program and a genetic algorithm intelligent volume assembling method based on the segmented real number coding;
a processor for executing the computer program and the intelligent grouping method based on the segmented real number coding genetic algorithm to realize the steps of the intelligent grouping method based on the segmented real number coding genetic algorithm according to any one of claims 1 to 7.
9. A readable storage medium having a segmented real number coding based genetic algorithm intelligent volume organizing method, wherein the readable storage medium has a computer program stored thereon, and the computer program is executed by a processor to implement the steps of the segmented real number coding based genetic algorithm intelligent volume organizing method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911293627.XA CN110990573A (en) | 2019-12-16 | 2019-12-16 | Genetic algorithm intelligent volume assembling method and device based on segmented real number coding and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911293627.XA CN110990573A (en) | 2019-12-16 | 2019-12-16 | Genetic algorithm intelligent volume assembling method and device based on segmented real number coding and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110990573A true CN110990573A (en) | 2020-04-10 |
Family
ID=70094058
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911293627.XA Pending CN110990573A (en) | 2019-12-16 | 2019-12-16 | Genetic algorithm intelligent volume assembling method and device based on segmented real number coding and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110990573A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112182172A (en) * | 2020-09-23 | 2021-01-05 | 华南师范大学 | Volume forming method, system, device and medium based on particle swarm genetic algorithm |
| CN113255913A (en) * | 2021-06-08 | 2021-08-13 | 上海对外经贸大学 | Evolution method for fusion block chain technology |
| CN114745310A (en) * | 2022-03-31 | 2022-07-12 | 工银科技有限公司 | Method and device for determining flow threshold based on genetic algorithm |
| CN117131104A (en) * | 2023-08-28 | 2023-11-28 | 河北望岳信息科技有限公司 | Intelligent question-drawing and winding method and device, electronic equipment and storage medium |
| CN112182172B (en) * | 2020-09-23 | 2024-05-31 | 华南师范大学 | Group-rolling method, system, device and medium based on particle swarm genetic algorithm |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104299053A (en) * | 2014-10-13 | 2015-01-21 | 国家电网公司 | Method for selecting optimal path of power distribution and utilization communication network based on genetic algorithm |
| CN104504627A (en) * | 2014-12-03 | 2015-04-08 | 中建材国际贸易有限公司 | Test paper automatic composing method utilizing genetic algorithm |
-
2019
- 2019-12-16 CN CN201911293627.XA patent/CN110990573A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104299053A (en) * | 2014-10-13 | 2015-01-21 | 国家电网公司 | Method for selecting optimal path of power distribution and utilization communication network based on genetic algorithm |
| CN104504627A (en) * | 2014-12-03 | 2015-04-08 | 中建材国际贸易有限公司 | Test paper automatic composing method utilizing genetic algorithm |
Non-Patent Citations (4)
| Title |
|---|
| ARTWL: "《https://www.cnblogs.com/artwl/archive/2011/05/19/2051556.html》", 19 May 2011 * |
| 徐新华: "《基于分段的自然数编码的遗传算法在自动组卷问题中的应用》", 《廊坊师范学院学报（自然科学版）》 * |
| 方党生: "《基于.NET的学校考试管理系统的研究与实现》", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 朱会霞: "《二进制遗传算法的改进研究》", 31 March 2018, 《东北大学出版社》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112182172A (en) * | 2020-09-23 | 2021-01-05 | 华南师范大学 | Volume forming method, system, device and medium based on particle swarm genetic algorithm |
| CN112182172B (en) * | 2020-09-23 | 2024-05-31 | 华南师范大学 | Group-rolling method, system, device and medium based on particle swarm genetic algorithm |
| CN113255913A (en) * | 2021-06-08 | 2021-08-13 | 上海对外经贸大学 | Evolution method for fusion block chain technology |
| CN114745310A (en) * | 2022-03-31 | 2022-07-12 | 工银科技有限公司 | Method and device for determining flow threshold based on genetic algorithm |
| CN114745310B (en) * | 2022-03-31 | 2024-01-12 | 工银科技有限公司 | Flow threshold determining method and device based on genetic algorithm |
| CN117131104A (en) * | 2023-08-28 | 2023-11-28 | 河北望岳信息科技有限公司 | Intelligent question-drawing and winding method and device, electronic equipment and storage medium |
| CN117131104B (en) * | 2023-08-28 | 2024-02-27 | 河北望岳信息科技有限公司 | Intelligent question-drawing and winding method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110990573A (en) | Genetic algorithm intelligent volume assembling method and device based on segmented real number coding and readable storage medium | |
| CN108734202A (en) | A kind of Fault Diagnosis for HV Circuit Breakers method based on improved BP | |
| US5245696A (en) | Evolution and learning in neural networks: the number and distribution of learning trials affect the rate of evolution | |
| CN110781406B (en) | Social network user multi-attribute inference method based on variational automatic encoder | |
| CN108573399A (en) | Method and its system are recommended by trade company based on transition probability network | |
| CN107197006B (en) | Multi-constraint service selection method and device based on global QoS decomposition | |
| CN107294775B (en) | Communication network optimization method based on analytic hierarchy process and genetic algorithm | |
| CN107577924A (en) | A kind of long-chain non-coding RNA subcellular location prediction algorithm based on deep learning | |
| CN111312334A (en) | Method for analyzing receptor-ligand system influencing intercellular communication | |
| CN115881238A (en) | Model training method, transformer fault diagnosis method and related device | |
| CN110222838A (en) | Deep neural network and its training method, device, electronic equipment and storage medium | |
| CN115131183A (en) | Method and system for improving physical education teaching effect | |
| CN115659807A (en) | Method for predicting talent performance based on Bayesian optimization model fusion algorithm | |
| CN113870634A (en) | Intelligent volume combination method and system combined with virtual teaching | |
| CN109635869A (en) | On-line study interfering system | |
| CN110471854A (en) | A kind of defect report assigning method based on high dimensional data mixing reduction | |
| CN105407060A (en) | Multiple-access multi-unit distributed resource distribution method based on heterogeneous wireless network | |
| CN116011787A (en) | Intelligent course arrangement method and device, electronic equipment and computer readable storage medium | |
| Liu et al. | A hybrid genetic based clustering algorithm | |
| Salcedo-Sanz et al. | Teaching advanced features of evolutionary algorithms using Japanese puzzles | |
| CN114219605A (en) | Wind control method, device and storage medium | |
| CN110046667B (en) | Teaching evaluation method based on deep neural network learning scoring data pair | |
| CN113398593A (en) | Multi-agent hierarchical control method and device, storage medium and electronic equipment | |
| Eiben et al. | Evolutionary algorithms | |
| CN112597357A (en) | Volume assembling method used as intelligent volume assembling system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200410 |