CN116502768B - Civil aviation information post load early warning method, system and storage medium - Google Patents
Civil aviation information post load early warning method, system and storage medium Download PDFInfo
- Publication number
- CN116502768B CN116502768B CN202310590254.2A CN202310590254A CN116502768B CN 116502768 B CN116502768 B CN 116502768B CN 202310590254 A CN202310590254 A CN 202310590254A CN 116502768 B CN116502768 B CN 116502768B
- Authority
- CN
- China
- Prior art keywords
- post
- data
- sample data
- predicted
- day
- 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
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000003066 decision tree Methods 0.000 claims abstract description 38
- 238000012549 training Methods 0.000 claims abstract description 35
- 238000012216 screening Methods 0.000 claims abstract description 34
- 238000012545 processing Methods 0.000 claims abstract description 32
- 238000012805 post-processing Methods 0.000 claims abstract description 31
- 238000004458 analytical method Methods 0.000 claims abstract description 7
- 238000011156 evaluation Methods 0.000 claims description 61
- 238000004590 computer program Methods 0.000 claims description 22
- 230000010365 information processing Effects 0.000 claims description 18
- 230000002068 genetic effect Effects 0.000 claims description 8
- 238000010606 normalization Methods 0.000 claims description 7
- 238000012360 testing method Methods 0.000 claims description 6
- 238000012097 association analysis method Methods 0.000 claims description 5
- 238000012098 association analyses Methods 0.000 claims description 4
- 238000005070 sampling Methods 0.000 claims description 4
- 238000000926 separation method Methods 0.000 claims description 4
- 230000006872 improvement Effects 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000010219 correlation analysis Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 230000000295 complement effect Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000001502 supplementing effect Effects 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000036772 blood pressure Effects 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000007499 fusion processing Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000029058 respiratory gaseous exchange Effects 0.000 description 1
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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- 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
-
- 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
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06313—Resource planning in a project environment
-
- 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
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06314—Calendaring for a resource
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- Development Economics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- General Business, Economics & Management (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Evolutionary Biology (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Data Mining & Analysis (AREA)
- Biophysics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Physiology (AREA)
- Biodiversity & Conservation Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Genetics & Genomics (AREA)
- Biomedical Technology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a civil aviation information post load early warning method, a system and a storage medium, wherein the method comprises the following steps: according to post history processing records of a pre-collected civil aviation information post on duty background, a history sample set is constructed; collecting post processing data of a day to be predicted in real time; the method comprises the steps of screening historical sample data meeting preset relevancy screening conditions as similar day sample data by performing relevancy analysis on post processing data of a day to be predicted and historical sample data in a historical sample set; training the CART decision tree by adopting sample data of similar days to obtain a post load prediction model; according to the post processing data, carrying out post load prediction by adopting a post load prediction model to obtain a post load index; when the post load index exceeds a preset condition, carrying out workload early warning; according to the invention, the workload prediction can be performed according to the background data of the civil aviation information duty system, and the accuracy of workload prediction and early warning is improved.
Description
Technical Field
The invention relates to the technical field of flight dispatch and operation monitoring, in particular to a civil aviation information post load early warning method, a system and a storage medium.
Background
The information collection and analysis work of civil aviation is an indispensable part for guaranteeing the flight assignment release and operation control of airlines, and the effective management of the information posts of the civil aviation is a powerful measure for guaranteeing the uploading and the downloading of various information completely and timely. This is in close relation to the working status of the on-Shift staff, and the size of the workload clearly directly influences the working status of the staff. With the rapid development of civil aviation industry, the information quantity is rapidly increased, and the information types and sources are also continuously enriched. The workload faced by the civil aviation information department is also increased continuously, and the accurate evaluation and prediction of the workload of the civil aviation information post are beneficial to improving the service quality and guaranteeing the flight safety.
Analysis on the workload of civil aviation operators is concentrated on three dimensions of subjective scales, working time and physiological indexes in the past, wherein the subjective scales fill out questionnaires through the experience evaluation of the testees in a questionnaire mode, coefficients are determined according to a set mode method, the workload condition of the testees is obtained, and NASA-TLX is a common method in the industry; counting the working time mainly by using DORATASK evaluation method, dividing the work into visible, invisible and recovery time, subdividing the work content into detailed work processes, classifying the detailed work processes into specific work parts, and evaluating the total workload; the physiological index measures the workload of the subject by measuring indexes such as heart rate, blood pressure, respiration severity, and the like. The evaluation result based on the subjective scale is greatly influenced by individual variability and lacks universality; the statistics of the working time length lacks a unified mode method with high acceptance, and the statistical result is difficult to reflect the authenticity of the working load; the physiological index can only indirectly infer the size of the workload, and the functional relation between the physiological index and the workload can not be obtained.
Therefore, in order to solve the problems in the prior art, research on an accurate civil aviation information post load prediction and early warning method while carrying out organization management on management services becomes a technical problem to be solved in the field.
Disclosure of Invention
The embodiment of the invention provides a method, a system and a storage medium for pre-warning the load of a civil aviation information post, which can predict the workload according to background data of a system on duty of the civil aviation information post, effectively shorten the workload assessment period and improve the accuracy of the workload prediction and pre-warning.
In a first aspect, an embodiment of the present invention provides a method for early warning load of civil aviation information post, including:
According to post history processing records of a pre-collected civil aviation information post on duty background, a history sample set is constructed;
Collecting post processing data of a day to be predicted in real time;
Through carrying out association analysis on the post processing data of the day to be predicted and the historical sample data in the historical sample set, screening out the historical sample data meeting the preset association screening condition, and taking the historical sample data as similar day sample data;
training a pre-constructed CART decision tree by adopting the sample data of similar days to obtain a post load prediction model;
according to the post processing data, carrying out post load prediction by adopting the post load prediction model to obtain a post load index;
and when the post load index exceeds a preset condition, carrying out workload early warning.
As an improvement of the above solution, the post history processing record includes: the civil aviation information type of the processed information, the information processing quantity in unit time and the information receiving quantity in unit time;
The post history processing record of the post on duty background according to the pre-collected civil aviation information is used for constructing a history sample set, and the post history processing record comprises:
counting the civil aviation information types of the processed information in different time periods to obtain the working complexity evaluation index of the corresponding time period;
Calculating the ratio of the information processing quantity to the information receiving quantity in unit time of different time periods to obtain the workload evaluation index of the corresponding time period;
according to the work complexity evaluation indexes and the work load evaluation indexes of different time periods, a history sample set is constructed; wherein one of the history sample data in the history sample set includes: a work complexity evaluation index for a time period and a work load evaluation index for a corresponding time period.
As an improvement of the above solution, the screening the historical sample data meeting the preset relevancy screening condition by performing relevancy analysis on the post processing data of the day to be predicted and the historical sample data in the historical sample set, as the similar day sample data, includes:
constructing a comparison data sequence of corresponding historical sample data according to the working complexity evaluation index in each historical sample data;
constructing a predicted data sequence according to the work complexity evaluation index in the post processing data of the day to be predicted;
calculating the association degree between the predicted data sequence and each comparison data sequence by adopting a gray association analysis method;
And screening historical sample data corresponding to the comparison data sequence with the association degree meeting the association degree screening condition from the historical sample set, and taking the historical sample data as similar day sample data.
As an improvement of the above scheme, the calculating the association degree between the predicted data sequence and each comparison data sequence by using the gray association analysis method includes:
calculating a correlation coefficient between the predicted data sequence and each of the comparison data sequences by adopting a formula (1);
Calculating the association degree between the predicted data sequence and each contrast data sequence by adopting a formula (2) according to the association degree coefficient between the predicted data sequence and each contrast data sequence; :
Wherein X 0i＝x0(k)-xi(k),Xi represents a comparison data sequence, X i＝{xi(1),xi(2),…,xi(n)},X0 represents a predicted data sequence, and X 0＝{x0(1),x0(2),…,x0(n)};x0 (k) represents an evaluation index of the working complexity of k points in the predicted data sequence; x i (k) represents an evaluation index of the working complexity of the k point in the comparison data sequence; representing the minimum absolute difference between k points x 0 (k) and x i (k); /(I) Representing the maximum absolute difference between k points x 0 (k) and x i (k); ρ represents a resolution coefficient, and between [0,1], n represents the number of the work complexity evaluation indexes.
As an improvement of the scheme, the association degree screening condition is that the association degree is greater than or equal to a preset association degree threshold value;
the step of screening the historical sample data corresponding to the comparison data sequence with the association degree meeting the association degree screening condition from the historical sample set, as similar day sample data, comprises the following steps:
screening historical sample data corresponding to a comparison data sequence with the association degree larger than or equal to a preset association degree threshold value from the historical sample set, and taking the historical sample data as candidate historical sample data;
Counting the number of samples of the candidate historical sample data, sorting the candidate historical sample data according to a time sequence when the number of samples is larger than a preset number threshold, and selecting a plurality of candidate historical sample data adjacent to the day to be predicted;
And performing de-duplication processing on the selected plurality of candidate historical sample data adjacent to the day to be predicted to obtain sample data of similar days.
As an improvement of the scheme, training the pre-constructed CART decision tree by adopting the similar daily sample data, and before obtaining the post load prediction model, the method further comprises the following steps:
Carrying out normalization processing on the sample data of the similar days;
And carrying out data separation and mixing on the sample data of similar days after normalization processing, and then carrying out random sampling to obtain a sample training set and a sample testing set.
As an improvement of the above scheme, training a pre-constructed CART decision tree by using the similar day sample data to obtain a post load prediction model, including:
Initializing sample weight distribution of the sample data of the similar days;
Training the CART decision tree by adopting the sample data of similar days, and introducing a genetic algorithm to optimize the CART decision tree and the sample weight distribution so as to obtain a CART decision tree prediction model;
Inputting the sample data of the similar days and the optimized sample weight distribution thereof into the CART decision tree prediction model for training to obtain a current base learner;
Calculating a prediction error of the current base learner, and calculating a weight coefficient of the current base learner according to the prediction error of the current base learner;
according to the weight coefficient of the current base learner, adjusting the sample weight distribution;
inputting the sample data of the similar days and the sample weight distribution after adjustment into the CART decision tree prediction model for training to obtain a next base learner, and repeatedly iterating until a preset termination condition is met to obtain a plurality of base learners;
and combining a plurality of the base learners according to the weight coefficient of each base learner to obtain a post load prediction model.
As an improvement of the above solution, the step load prediction is performed by using the step load prediction model according to the step processing data to obtain a step load index, including:
counting the post processing data to obtain a working complexity evaluation index of a day to be predicted;
calculating the ratio of the information processing quantity to the information receiving quantity in unit time in the post processing data to obtain a workload evaluation index of a day to be predicted;
constructing a data sequence to be tested according to the work complexity evaluation index and the work load evaluation index of the day to be predicted;
And inputting the data sequence to be detected into the post load prediction model to predict, so as to obtain a post load index.
In a second aspect, an embodiment of the present invention provides a civil aviation information post load early warning system, including: a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, the processor implementing the civil aviation information post load warning method of any one of the first aspects when the computer program is executed.
In a third aspect, an embodiment of the present invention provides a computer readable storage medium, where the computer readable storage medium stores a computer program, where when the computer program runs, controls a device where the computer readable storage medium is located to execute the civil aviation information post load early warning method according to any one of the first aspects.
Compared with the prior art, the beneficial effects of the embodiment of the scheme are as follows: according to post history processing records of a pre-collected civil aviation information post on duty background, a history sample set is constructed; collecting post processing data of a day to be predicted in real time; through carrying out association analysis on the post processing data of the day to be predicted and the historical sample data in the historical sample set, screening out the historical sample data meeting the preset association screening condition, and taking the historical sample data as similar day sample data; training a pre-constructed CART decision tree by adopting the sample data of similar days to obtain a post load prediction model; according to the post processing data, carrying out post load prediction by adopting the post load prediction model to obtain a post load index; and when the post load index exceeds a preset condition, carrying out workload early warning. According to the embodiment of the invention, the workload prediction can be carried out according to the background data of the civil aviation information post on duty system, the workload assessment period is effectively shortened, the risk gateway can be moved forward, the warning can be successfully carried out before overload work of the staff, and the accuracy of the workload prediction and early warning is improved.
Drawings
In order to more clearly illustrate the technical solutions of the present invention, the drawings that will be used in the embodiments will be briefly described below, and it will be apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a civil aviation information post load early warning method provided by an embodiment of the invention;
fig. 2 is a schematic diagram of a process for extracting sample data of similar days according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a post load prediction model construction flow provided by an embodiment of the present invention;
FIG. 4 is a schematic diagram of a workload prediction flow provided by an embodiment of the present invention;
FIG. 5 is a schematic diagram of a civil aviation information post load warning system provided by an embodiment of the invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1
Please refer to fig. 1, which is a flowchart of a load early warning method for civil aviation information post according to an embodiment of the present invention. The civil aviation information post load early warning method comprises the following steps:
s1: according to post history processing records of a pre-collected civil aviation information post on duty background, a history sample set is constructed;
wherein, the post history processing record includes: the civil aviation information type of the processed information, the information processing quantity in unit time and the information receiving quantity in unit time;
Further, according to a post history processing record of a pre-collected civil aviation information post on duty background, a history sample set is constructed, including:
counting the civil aviation information types of the processed information in different time periods to obtain the working complexity evaluation index of the corresponding time period;
Calculating the ratio of the information processing quantity to the information receiving quantity in unit time of different time periods to obtain the workload evaluation index of the corresponding time period;
according to the work complexity evaluation indexes and the work load evaluation indexes of different time periods, a history sample set is constructed; wherein one of the history sample data in the history sample set includes: a work complexity evaluation index for a time period and a work load evaluation index for a corresponding time period.
The information processing of the civil aviation information post is embodied in the number and the type of the information processing, and the timely processing and the notification of the civil aviation information are the basic working requirements of the civil aviation information post, so that the overall workload of the civil aviation information post is mainly embodied in whether to timely process the received notification in unit time or not. Therefore, the embodiment of the invention takes the ratio of the processing quantity of the civil aviation information to the receiving quantity of the civil aviation information in unit time as the evaluation index of the working load of the civil aviation information post. By way of example, the 1-hour period is 1, and the ratio of the civil aviation information type, the information processing quantity in unit time and the information receiving quantity in 1 hour is counted to obtain the working complexity evaluation index and the working load evaluation index of the hour as one historical sample data.
S2: collecting post processing data of a day to be predicted in real time;
S3: through carrying out association analysis on the post processing data of the day to be predicted and the historical sample data in the historical sample set, screening out the historical sample data meeting the preset association screening condition, and taking the historical sample data as similar day sample data;
The similar day refers to a historical day of which the type and the number of civil aviation information (including the information processing number and the information receiving number) in the historical sample set are similar to each other. That is, the sample data of similar days can reflect the workload performance under the condition of receiving and transmitting information of specific civil aviation information type and quantity.
S4: training a pre-constructed CART decision tree by adopting the sample data of similar days to obtain a post load prediction model;
S5: according to the post processing data, carrying out post load prediction by adopting the post load prediction model to obtain a post load index;
S6: and when the post load index exceeds a preset condition, carrying out workload early warning.
And when the post load index does not exceed the preset condition, no workload early warning is carried out.
In the embodiment of the invention, the ratio of the information processing quantity to the information receiving quantity in unit time is used as an index for evaluating the post workload, the type of the civil aviation information processed is collected and used as an evaluation index for evaluating the post workload complexity, the historical sample data similar to the type and quantity of the civil aviation information on the day to be predicted is selected based on the correlation analysis and used as the sample data on the similar day, the CART decision tree constructed in advance is trained by adopting the sample data on the similar day to obtain a post workload prediction model, and finally the post workload prediction model is used for predicting the post workload degree of the daily movement to be predicted, so that the prediction and alarm of the workload state of the civil aviation information post can be realized.
In an optional embodiment, the screening the historical sample data meeting the preset relevancy screening condition by performing relevancy analysis on the post processing data of the day to be predicted and the historical sample data in the historical sample set, as the similar day sample data, includes:
constructing a comparison data sequence of corresponding historical sample data according to the working complexity evaluation index in each historical sample data;
constructing a predicted data sequence according to the work complexity evaluation index in the post processing data of the day to be predicted;
Exemplary, the voyage annunciation work that stands out in the civil aviation industry is: different types of civil aviation information influence the processing difficulty, workload and flexibility degree of the processing process, so that the navigation notification type and the receiving report condition are used as the working complexity evaluation indexes for evaluating the navigation notification when the workload of the navigation notification post is analyzed, and the selected indexes are shown in the table 1:
table 1: the evaluation index of the working complexity of navigation announcement;
The fluctuation and irregularity of the report types and amounts are important reasons for influencing the prediction accuracy of the workload, so that finding the relation between the day to be predicted and the historical data is important for improving the prediction accuracy. The embodiment of the invention selects gray correlation analysis as an acquisition method of a historical sample data set. The gray correlation analysis is used for analyzing the navigation notification complexity, and the similarity degree among the influence factors is reflected through gray correlation degree based on the data sequence.
Illustratively, constructing a comparison data sequence X i＝{xi(1),xi(2),…,xi(n)},xi (k) from the associated operational complexity assessment indicators of the historical sample data represents operational complexity assessment indicators for k points in the comparison data sequence, such as X (1) -X (14) described above; and constructing a predicted data sequence X 0＝{x0(1),x0(2),…,x0(n)},x0 (k) to represent the work complexity evaluation index of k points in the predicted data sequence according to the related work complexity evaluation index of the day to be predicted.
Calculating the association degree between the predicted data sequence and each comparison data sequence by adopting a gray association analysis method;
Specifically, calculating a correlation coefficient between the predicted data sequence and each of the comparison data sequences by adopting a formula (1);
Calculating the association degree between the predicted data sequence and each contrast data sequence by adopting a formula (2) according to the association degree coefficient between the predicted data sequence and each contrast data sequence; :
Wherein X 0i＝x0(k)-xi(k),Xi represents a comparison data sequence, X i＝{xi(1),xi(2),…,xi(n)},X0 represents a predicted data sequence, and X 0＝{x0(1),x0(2),…,x0(n)};x0 (k) represents an evaluation index of the working complexity of k points in the predicted data sequence; x i (k) represents an evaluation index of the working complexity of the k point in the comparison data sequence; representing the minimum absolute difference between k points x 0 (k) and x i (k); /(I) Representing the maximum absolute difference between k points x 0 (k) and x i (k); ρ represents a resolution coefficient, and between [0,1], n represents the number of the work complexity evaluation indexes.
And screening historical sample data corresponding to the comparison data sequence with the association degree meeting the association degree screening condition from the historical sample set, and taking the historical sample data as similar day sample data.
The relevancy screening condition is that the relevancy is greater than or equal to a preset relevancy threshold value;
further, screening historical sample data corresponding to the comparison data sequence with the association degree meeting the association degree screening condition from the historical sample set, wherein the historical sample data is used as similar day sample data and comprises the following steps:
screening historical sample data corresponding to a comparison data sequence with the association degree larger than or equal to a preset association degree threshold value from the historical sample set, and taking the historical sample data as candidate historical sample data;
Counting the number of samples of the candidate historical sample data, sorting the candidate historical sample data according to a time sequence when the number of samples is larger than a preset number threshold, and selecting a plurality of candidate historical sample data adjacent to the day to be predicted;
And performing de-duplication processing on the selected plurality of candidate historical sample data adjacent to the day to be predicted to obtain sample data of similar days.
For example, the correlation threshold is 0.9, that is, historical sample data corresponding to a comparison data sequence with the correlation degree not less than 0.9 is screened out from the historical sample set and used as candidate historical sample data. As shown in fig. 2, when the number of candidate historical sample data is greater than the number threshold, indicating that the sample data of similar days is too much, selecting date data similar to the day to be predicted based on the time "near-far-small" principle; the selected data is further subjected to repeated daily number removal to form effective similar daily sample data. It should be noted that, in the embodiment of the present invention, the numerical value of the numerical threshold is not specifically limited, and a user may customize the setting according to the needs. Because the time span between partial data in the historical sample set and the day to be predicted is longer, external changes (such as changes in aviation seasons, large-scale military exercises, changes in special areas and the like) may cause external performances reflected by information to be different, so that the actual conditions of the sample data of similar days and the day to be predicted are greatly different. The time span between the adjacent days and the forecast days is short, and besides the information types and the quantity are different, other conditions are basically consistent, so that the defect that the forecast is carried out by taking the information types and the quantity as the basis is overcome. Therefore, the embodiment of the invention adopts the time principle of 'near big and far small', and the data of the similar day is selected, then the data of the adjacent day is selected in one step, and the reasonable use of the similar day and the adjacent day can play the roles of supplementing the long-term and complement each other, so that the finally obtained sample data of the similar day is ensured to be similar to the information type and quantity of the predicted day, and the time span is short, thereby ensuring that the sample data of the similar day is basically identical to the actual condition of the predicted day.
In an optional embodiment, before training the pre-constructed CART decision tree by using the sample data of similar days to obtain the post load prediction model, the method further includes:
Carrying out normalization processing on the sample data of the similar days;
And carrying out data separation and mixing on the sample data of similar days after normalization processing, and then carrying out random sampling to obtain a sample training set and a sample testing set.
In order to further improve the reliability of data, after data separation and mixing are carried out on the screened similar daily sample data, a sample training set for training a CART decision tree and a sample testing set for testing a post load prediction model obtained after training are constructed through random sampling. In the embodiment of the invention, the sample ratio of the sample training set to the sample testing set is kept at 2:1 to 4:1, the data processing procedure is as described in fig. 2.
In an optional embodiment, training a pre-constructed CART decision tree by using the sample data of similar days to obtain a post load prediction model includes:
Initializing sample weight distribution of the sample data of the similar days;
Training the CART decision tree by adopting the sample data of similar days, and introducing a genetic algorithm to optimize the CART decision tree and the sample weight distribution so as to obtain a CART decision tree prediction model;
Inputting the sample data of the similar days and the optimized sample weight distribution thereof into the CART decision tree prediction model for training to obtain a current base learner;
Calculating a prediction error of the current base learner, and calculating a weight coefficient of the current base learner according to the prediction error of the current base learner;
according to the weight coefficient of the current base learner, adjusting the sample weight distribution;
inputting the sample data of the similar days and the sample weight distribution after adjustment into the CART decision tree prediction model for training to obtain a next base learner, and repeatedly iterating until a preset termination condition is met to obtain a plurality of base learners;
and combining a plurality of the base learners according to the weight coefficient of each base learner to obtain a post load prediction model.
In the embodiment of the invention, the CART decision tree can be trained by adopting the sample data of similar days in the sample training set, the training process is shown in fig. 3, and the sample weight distribution, CART decision tree and genetic algorithm (GA, genetic Algorithms) of the sample data of related similar days are initialized before training. Exemplary, the initialized sample weight distribution may beWhere m is the sample size, and w 1i represents the weight of the sample data on the i-th similar day.
Compared with the CART decision tree which is easy to fall into local optimum by adopting a traditional dichotomy, the CART decision tree in the embodiment of the invention adopts a genetic algorithm to replace the traditional dichotomy, and the genetic algorithm is utilized to divide data, so that a global split optimum solution can be obtained, thereby improving the overall classification and prediction effects of the CART decision tree, and the following description is carried out on the training flow of the CART decision tree by taking sample data of similar days as an individual:
(1) Setting the codes of the individuals in a real number coding mode, and initializing the population;
(2) Calculating an individual fitness value by taking the classification precision as a fitness evaluation index;
(3) Selecting individuals according to the individual fitness of the problem domain in each generation, and carrying out combination crossover and mutation on genetic operators according to concepts in genetics to generate a group representing a new solution set; the population is subjected to iterative optimization according to the characteristics of the first layer decision tree, and an optimal individual and an optimal adaptation value are output after the iteration is completed, so that an optimal splitting point of the first layer decision tree is obtained;
(4) And decoding the optimal individuals of the final population in a progressive search mode to obtain a preliminary CART decision tree prediction model and optimized sample weight distribution.
An AdaBoost base learner was then built. The construction flow of the base learner is described below with reference to fig. 3:
(1) When training T decision trees by using similar daily sample data with sample weight distribution of D k, obtaining a base learner G k (x) and calculating a prediction error e ki;
Where m is the number of similar day sample data in the sample training set. G k(xi) represents the predicted post load index output by the kth base learner, and y i represents the post load index label of the corresponding similar day sample data.
(2) And calculating the weight coefficient of the base learner and updating the sample weight distribution. Calculating a regression error rate e k of the kth base learner and a weight coefficient alpha k thereof according to the prediction error e ki, and updating the weight distribution of the next sample according to the weight D k of the kth base learner;
wherein Z k represents a normalization factor,
(3) And constructing a final strong learner and forming a GA-CART-AdaBoost post load prediction model based on similar days. Training the set number of the base learners and the corresponding weight coefficient alpha k according to the steps, and obtaining a final strong learner according to a corresponding combination strategy:
Wherein, Is all/>The median value of (2) is multiplied by the base learner corresponding to the corresponding sequence number k *.
In an alternative embodiment, the step of predicting the step load according to the step processing data by using the step load prediction model to obtain a step load index includes:
counting the post processing data to obtain a working complexity evaluation index of a day to be predicted;
calculating the ratio of the information processing quantity to the information receiving quantity in unit time in the post processing data to obtain a workload evaluation index of a day to be predicted;
constructing a data sequence to be tested according to the work complexity evaluation index and the work load evaluation index of the day to be predicted;
And inputting the data sequence to be detected into the post load prediction model to predict, so as to obtain a post load index.
In the embodiment of the invention, a background of a civil aviation information post on-duty system is accessed to collect and report the original post processing data in real time, the original post processing data is subjected to the characteristic extraction and fusion process which is the same as that of the historical post processing data, the predicted data to be input is obtained, a post load prediction model trained through the optimization is called on line to predict the post real-time work load, if the post load index exceeds a preset condition, for example, the post load index exceeds a preset index threshold, a warning is responded, otherwise, the warning is not responded, as shown in fig. 4. It should be noted that, in the embodiment of the present invention, the preset index threshold is not limited specifically, and the user may set the preset index threshold according to actual needs, for example, the preset index threshold is set to a value ranging from 0.8 to 0.9.
Compared with the prior art, the embodiment of the invention has the beneficial effects that:
(1) According to the embodiment of the invention, the ratio of the information processing quantity to the information receiving quantity in unit time is used as a post workload evaluation index, the type of the processed civil aviation information is collected as a post work complexity evaluation index, a machine learning model based on an AdaBoost composite algorithm is constructed, the constructed model is used for post workload degree prediction, prediction and warning of the load state of the civil aviation information post worker can be realized, and unlike a load research method of past analysis, the risk gateway can be moved forward and successfully warned before overload work of workers can be performed.
(2) The embodiment of the invention selects the data of similar days similar to the types and the quantity of the civil aviation information in the historical sample set, and can reflect the performance of the workload under the condition of receiving and transmitting information of specific types and quantity. Meanwhile, the time principle of 'near big and far small' is adopted to further select date data similar to the predicted date, the time span is short, and the defect that prediction is carried out by taking the type and the quantity of information as the basis can be overcome; the few embodiments of the invention can take the effects of supplementing the advantages and complement each other through reasonable use of the similar days and the adjacent days, ensure that the finally obtained similar day sample data is similar to the information types and the quantity of the predicted days, and have short time span, thereby ensuring that the similar day sample data is basically identical to the actual condition of the predicted days.
(3) The information processing of the civil aviation information post is embodied in the number and the type of the information processing, and the timely processing and the notification of the civil aviation information are the basic working requirements of the civil aviation information post, so that the overall workload of the civil aviation information post is mainly embodied in whether to timely process the received notification in unit time or not. According to the embodiment of the invention, the ratio of the civil aviation information processing quantity to the civil aviation information receiving quantity in unit time is used as the workload evaluation index of the civil aviation information post, the 'near-large-far-small' time principle is adopted to screen out similar daily sample data, and the training set characterized by the workload has more similarity and time continuity.
Example two
Referring to fig. 5, a schematic diagram of a civil aviation information post load early warning device provided by an embodiment of the invention is shown. The civil aviation information post load early warning device of this embodiment includes: a processor 100, a memory 200 and a computer program stored in said memory 200 and executable on said processor 100, such as a civil aviation information post load warning program. The steps of the above embodiments of the method for pre-warning load of civil aviation information post are implemented by the processor 100 when executing the computer program, for example, steps S1-S3 shown in fig. 1.
The computer program may be divided into one or more modules/units, which are stored in the memory and executed by the processor to accomplish the present invention, for example. The one or more modules/units may be a series of computer program instruction segments capable of performing a specific function describing the execution of the computer program in the civil aviation information post load warning device.
The civil aviation information post load warning device can comprise, but is not limited to, a processor and a memory. It will be appreciated by those skilled in the art that the schematic diagram is merely an example of a civil aviation information post load warning device, and is not meant to be limiting, and may include more or fewer components than shown, or may combine certain components, or different components, e.g., the civil aviation information post load warning device may further include an input-output device, a network access device, a bus, etc.
The Processor may be a central processing unit (Central Processing Unit, CPU), but may also be other general purpose processors, digital signal processors (DIGITAL SIGNAL Processor, DSP), application SPECIFIC INTEGRATED Circuit (ASIC), off-the-shelf Programmable gate array (Field-Programmable GATE ARRAY, FPGA) or other Programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. The general processor can be a microprocessor or any conventional processor, and the like, and the processor is a control center of the civil aviation information post load early warning device and is connected with various parts of the whole civil aviation information post load early warning device by various interfaces and lines.
The memory can be used for storing the computer program and/or the module, and the processor can realize various functions of the civil aviation information post load early warning device by running or executing the computer program and/or the module stored in the memory and calling the data stored in the memory. The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program (such as a sound playing function, an image playing function, etc.) required for at least one function, and the like; the storage data area may store data (such as audio data, phonebook, etc.) created according to the use of the handset, etc. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as a hard disk, memory, plug-in hard disk, smart memory card (SMART MEDIA CARD, SMC), secure Digital (SD) card, flash memory card (FLASH CARD), at least one disk storage device, flash memory device, or other volatile solid-state storage device.
The module/unit integrated by the civil aviation information post load early warning device can be stored in a computer readable storage medium if the module/unit is realized in the form of a software functional unit and sold or used as an independent product. Based on such understanding, the present invention may implement all or part of the flow of the method of the above embodiment, or may be implemented by a computer program to instruct related hardware, where the computer program may be stored in a computer readable storage medium, and when the computer program is executed by a processor, the computer program may implement the steps of each of the method embodiments described above. Wherein the computer program comprises computer program code which may be in source code form, object code form, executable file or some intermediate form etc. The computer readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), an electrical carrier signal, a telecommunications signal, a software distribution medium, and so forth.
It should be noted that the above-described apparatus embodiments are merely illustrative, and the units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over 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 this embodiment. In addition, in the drawings of the embodiment of the device provided by the invention, the connection relation between the modules represents that the modules have communication connection, and can be specifically implemented as one or more communication buses or signal lines. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
While the foregoing is directed to the preferred embodiments of the present invention, it will be appreciated by those skilled in the art that many modifications and variations may be made without departing from the spirit of the invention, and it is intended that such modifications and variations be considered as a departure from the scope of the invention.
Claims (5)
1. A civil aviation information post load early warning method is characterized by comprising the following steps:
according to post history processing records of a pre-collected civil aviation information post on duty background, a history sample set is constructed; the post history processing record comprises: the civil aviation information type of the processed information, the information processing quantity in unit time and the information receiving quantity in unit time;
Collecting post processing data of a day to be predicted in real time;
Through carrying out association analysis on the post processing data of the day to be predicted and the historical sample data in the historical sample set, screening out the historical sample data meeting the preset association screening condition, and taking the historical sample data as similar day sample data; the relevancy screening condition is that the relevancy is greater than or equal to a preset relevancy threshold value; the similar day sample data refers to the historical sample data which is similar in type and quantity of civil aviation information in the historical sample set and is adjacent in time and selected based on the principle of near-time, big-time and far-time;
training a pre-constructed CART decision tree by adopting the sample data of similar days to obtain a post load prediction model;
according to the post processing data, carrying out post load prediction by adopting the post load prediction model to obtain a post load index;
When the post load index exceeds a preset condition, carrying out workload early warning;
The post history processing record of the post on duty background according to the pre-collected civil aviation information is used for constructing a history sample set, and the post history processing record comprises:
counting the civil aviation information types of the processed information in different time periods to obtain the working complexity evaluation index of the corresponding time period;
Calculating the ratio of the information processing quantity to the information receiving quantity in unit time of different time periods to obtain the workload evaluation index of the corresponding time period;
According to the work complexity evaluation indexes and the work load evaluation indexes of different time periods, a history sample set is constructed; wherein one of the history sample data in the history sample set includes: a work complexity evaluation index of a time period and a work load evaluation index of a corresponding time period;
The step of screening out the historical sample data meeting the preset relevancy screening condition as the similar day sample data by performing relevancy analysis on the post processing data of the day to be predicted and the historical sample data in the historical sample set comprises the following steps:
constructing a comparison data sequence of corresponding historical sample data according to the working complexity evaluation index in each historical sample data;
constructing a predicted data sequence according to the work complexity evaluation index in the post processing data of the day to be predicted;
calculating the association degree between the predicted data sequence and each comparison data sequence by adopting a gray association analysis method;
screening historical sample data corresponding to a comparison data sequence with the association degree meeting the association degree screening condition from the historical sample set, and taking the historical sample data as similar day sample data;
the method for calculating the association degree between the predicted data sequence and each comparison data sequence by adopting the gray association analysis method comprises the following steps:
calculating a correlation coefficient between the predicted data sequence and each of the comparison data sequences by adopting a formula (1);
Calculating the association degree between the predicted data sequence and each contrast data sequence according to the association degree coefficient between the predicted data sequence and each contrast data sequence by adopting a formula (2):
Wherein X 0i＝x0(k)-xi(k),Xi represents a comparison data sequence, X i＝{xi(1),xi(2),…,xi(n)},X0 represents a predicted data sequence, and X 0＝{x0(1),x0(2),…,x0(n)};x0 (k) represents an evaluation index of the working complexity of k points in the predicted data sequence; x i (k) represents an evaluation index of the working complexity of the k point in the comparison data sequence; representing the minimum absolute difference between k points x 0 (k) and x i (k); /(I) Representing the maximum absolute difference between k points x 0 (k) and x i (k); ρ represents a resolution coefficient, between [0,1], and n represents the number of the work complexity evaluation indexes;
Training a pre-constructed CART decision tree by adopting the similar day sample data to obtain a post load prediction model, wherein the post load prediction model comprises the following steps:
Initializing sample weight distribution of the sample data of the similar days;
Training the CART decision tree by adopting the sample data of similar days, and introducing a genetic algorithm to optimize the CART decision tree and the sample weight distribution so as to obtain a CART decision tree prediction model;
Inputting the sample data of the similar days and the optimized sample weight distribution thereof into the CART decision tree prediction model for training to obtain a current base learner;
Calculating a prediction error of the current base learner, and calculating a weight coefficient of the current base learner according to the prediction error of the current base learner;
according to the weight coefficient of the current base learner, adjusting the sample weight distribution;
inputting the sample data of the similar days and the sample weight distribution after adjustment into the CART decision tree prediction model for training to obtain a next base learner, and repeatedly iterating until a preset termination condition is met to obtain a plurality of base learners;
combining a plurality of base learners according to the weight coefficient of each base learner to obtain a post load prediction model;
And according to the post processing data, carrying out post load prediction by adopting the post load prediction model to obtain a post load index, wherein the post load index comprises the following components:
counting the post processing data to obtain a working complexity evaluation index of a day to be predicted;
calculating the ratio of the information processing quantity to the information receiving quantity in unit time in the post processing data to obtain a workload evaluation index of a day to be predicted;
constructing a data sequence to be tested according to the work complexity evaluation index and the work load evaluation index of the day to be predicted;
And inputting the data sequence to be detected into the post load prediction model to predict, so as to obtain a post load index.
2. The method for pre-warning the load of civil aviation information post according to claim 1, wherein the step of screening the historical sample data corresponding to the comparison data sequence with the association degree meeting the association degree screening condition from the historical sample set as the similar day sample data comprises the following steps:
screening historical sample data corresponding to a comparison data sequence with the association degree larger than or equal to a preset association degree threshold value from the historical sample set, and taking the historical sample data as candidate historical sample data;
Counting the number of samples of the candidate historical sample data, sorting the candidate historical sample data according to a time sequence when the number of samples is larger than a preset number threshold, and selecting a plurality of candidate historical sample data adjacent to the day to be predicted;
And performing de-duplication processing on the selected plurality of candidate historical sample data adjacent to the day to be predicted to obtain sample data of similar days.
3. The method for pre-warning the load of civil aviation information post according to claim 1, wherein the training of the pre-constructed CART decision tree by using the sample data of similar days further comprises, before obtaining the post load prediction model:
Carrying out normalization processing on the sample data of the similar days;
And carrying out data separation and mixing on the sample data of similar days after normalization processing, and then carrying out random sampling to obtain a sample training set and a sample testing set.
4. The utility model provides a civil aviation information post load early warning system which characterized in that includes: a processor, a memory and a computer program stored in the memory and configured to be executed by the processor, the processor implementing the civil aviation information post load warning method of any one of claims 1 to 3 when the computer program is executed.
5. A computer readable storage medium, wherein the computer readable storage medium stores a computer program, and wherein the computer program when executed controls a device in which the computer readable storage medium is located to perform the civil aviation information post load warning method according to any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310590254.2A CN116502768B (en) | 2023-05-23 | 2023-05-23 | Civil aviation information post load early warning method, system and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310590254.2A CN116502768B (en) | 2023-05-23 | 2023-05-23 | Civil aviation information post load early warning method, system and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116502768A CN116502768A (en) | 2023-07-28 |
| CN116502768B true CN116502768B (en) | 2024-06-07 |
Family
ID=87316549
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310590254.2A Active CN116502768B (en) | 2023-05-23 | 2023-05-23 | Civil aviation information post load early warning method, system and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116502768B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104881706A (en) * | 2014-12-31 | 2015-09-02 | 天津弘源慧能科技有限公司 | Electrical power system short-term load forecasting method based on big data technology |
| CN111028100A (en) * | 2019-11-29 | 2020-04-17 | 南方电网能源发展研究院有限责任公司 | Refined short-term load prediction method, device and medium considering meteorological factors |
| AU2020104000A4 (en) * | 2020-12-10 | 2021-02-18 | Guangxi University | Short-term Load Forecasting Method Based on TCN and IPSO-LSSVM Combined Model |
| CN113361785A (en) * | 2021-06-10 | 2021-09-07 | 国网河北省电力有限公司经济技术研究院 | Power distribution network short-term load prediction method and device, terminal and storage medium |
| CN114530059A (en) * | 2022-01-14 | 2022-05-24 | 南京航空航天大学 | Dynamic configuration method and system for multi-sector monitoring seat |
-
2023
- 2023-05-23 CN CN202310590254.2A patent/CN116502768B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104881706A (en) * | 2014-12-31 | 2015-09-02 | 天津弘源慧能科技有限公司 | Electrical power system short-term load forecasting method based on big data technology |
| CN111028100A (en) * | 2019-11-29 | 2020-04-17 | 南方电网能源发展研究院有限责任公司 | Refined short-term load prediction method, device and medium considering meteorological factors |
| AU2020104000A4 (en) * | 2020-12-10 | 2021-02-18 | Guangxi University | Short-term Load Forecasting Method Based on TCN and IPSO-LSSVM Combined Model |
| CN113361785A (en) * | 2021-06-10 | 2021-09-07 | 国网河北省电力有限公司经济技术研究院 | Power distribution network short-term load prediction method and device, terminal and storage medium |
| CN114530059A (en) * | 2022-01-14 | 2022-05-24 | 南京航空航天大学 | Dynamic configuration method and system for multi-sector monitoring seat |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116502768A (en) | 2023-07-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106909933B (en) | A kind of stealing classification Forecasting Methodology of three stages various visual angles Fusion Features | |
| CN111724211A (en) | Offline store commodity sales prediction method, device and equipment | |
| CN108733631A (en) | A kind of data assessment method, apparatus, terminal device and storage medium | |
| Kell et al. | Evaluation of the prediction skill of stock assessment using hindcasting | |
| CN106154209A (en) | Electrical energy meter fault Forecasting Methodology based on decision Tree algorithms | |
| CN106127242A (en) | Year of based on integrated study Extreme Precipitation prognoses system and Forecasting Methodology thereof | |
| CN110348490A (en) | A kind of soil quality prediction technique and device based on algorithm of support vector machine | |
| CN111695747A (en) | Intelligent dispatching method and device and computer readable storage medium | |
| CN110570097A (en) | business personnel risk identification method and device based on big data and storage medium | |
| CN116109195A (en) | Performance evaluation method and system based on graph convolution neural network | |
| CN111931992A (en) | Power load prediction index selection method and device | |
| CN116739317B (en) | Mining winch automatic management and dispatching platform, method, equipment and medium | |
| CN113177644A (en) | Automatic modeling system based on word embedding and depth time sequence model | |
| US20230386665A1 (en) | Method and device for constructing autism spectrum disorder (asd) risk prediction model | |
| CN116502768B (en) | Civil aviation information post load early warning method, system and storage medium | |
| CN111882113A (en) | Enterprise mobile banking user prediction method and device | |
| CN117254587A (en) | Monitoring method and device for power distribution network, electronic equipment and storage medium | |
| CN116843395A (en) | Alarm classification method, device, equipment and storage medium of service system | |
| CN113393169B (en) | Financial industry transaction system performance index analysis method based on big data technology | |
| CN115376692A (en) | Health data processing method and device, electronic equipment and storage medium | |
| CN113888318A (en) | Risk detection method and system | |
| CN115204501A (en) | Enterprise evaluation method and device, computer equipment and storage medium | |
| CN112418652B (en) | Risk identification method and related device | |
| CN113449923A (en) | Multi-model object market quotation prediction method and device | |
| CN113934894A (en) | Data display method based on index tree and terminal equipment |
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 |