CN108256685B - Hospital logistics transportation time prediction method based on multiple linear regression model - Google Patents
Hospital logistics transportation time prediction method based on multiple linear regression model Download PDFInfo
- Publication number
- CN108256685B CN108256685B CN201810057082.1A CN201810057082A CN108256685B CN 108256685 B CN108256685 B CN 108256685B CN 201810057082 A CN201810057082 A CN 201810057082A CN 108256685 B CN108256685 B CN 108256685B
- Authority
- CN
- China
- Prior art keywords
- task
- data
- hospital
- time
- linear regression
- 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
- 238000012417 linear regression Methods 0.000 title claims abstract description 33
- 238000000034 method Methods 0.000 title claims abstract description 24
- 238000004458 analytical method Methods 0.000 claims abstract description 9
- 230000008520 organization Effects 0.000 claims description 8
- 230000001419 dependent effect Effects 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 2
- 238000005303 weighing Methods 0.000 claims 2
- 230000010354 integration Effects 0.000 claims 1
- 238000011835 investigation Methods 0.000 abstract description 2
- 239000000284 extract Substances 0.000 abstract 1
- 238000013139 quantization Methods 0.000 abstract 1
- 238000007418 data mining Methods 0.000 description 2
- 238000012886 linear function Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/083—Shipping
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Quality & Reliability (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Medical Treatment And Welfare Office Work (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
A hospital logistics delivery time prediction method based on a multiple linear regression model extracts index factors influencing delivery time, such as execution tools of delivery tasks, distances among buildings, the number of layers of buildings spanned, the difference of codes of departments at intervals and other indexes, and conducts multiple linear regression analysis through analysis of hospital logistics data and investigation of field actual conditions. And a time interval busy degree index obtained by quantizing the previous transportation task data set is added to be used as an independent variable to be added to the function for fitting, so that the prediction precision can be further improved. The method comprises the following steps: and establishing a prediction model by means of a linear regression method according to a time interval busy degree index obtained by quantization of the past data set. According to the invention, the transportation task time of the logistics staff can be accurately predicted by analyzing index factors such as the transportation execution tool, the distance between the buildings spanned, the number of the floors spanned, the difference between the numbers of the departments in the department and the like and quantitatively obtaining the busy degree index of the hospital in the time period.
Description
Technical Field
The invention relates to the field of data mining and hospital logistics systems, in particular to a hospital logistics transportation time prediction method based on a multiple linear regression model.
Background
With the intensive use of intelligent medical systems in the hospital industry, the overall management structure of hospitals has also undergone a significant revolution over the world. The hospital logistics department as one of the important components of the hospital has great span under the wave of the Internet of things, so that the analysis of the logistics transportation condition of the hospital by the transportation historical task data in the hospital database is very valuable.
The multiple linear regression model is one of the more important models in the field of data mining. Linear regression model of yi＝β0+β1xi1+β2xi2+……+βpxip+εi. Wherein, beta0Called the regression constant, beta1，……，βpReferred to as regression coefficients. y is called dependent variable, and X1,X2,……，XpIs p general variables which can be accurately measured and controlled, and is called independent variable. From n sets of observations (y)i，xi1，xi2，……，xip) Determining a parameter beta according to a least squares method0，β1，……，βpEstimated value b of0,b1，……，bpEstablishing a multiple linear regression equation
Conventional temporal prediction models only consider spatially dependent factors such as distance and the like. The length of the task execution time depends to some extent on the length of the distance between the start point and the end point of the task. However, in the hospital logistics transportation system, the factors affecting the transportation time include not only the distance but also important factors such as transportation implementation tools, whether the transportation implementation tools cross buildings, and whether the transportation implementation tools cross floors.
Disclosure of Invention
In order to accurately predict the hospital logistics transportation time and make up the deficiency of the prediction precision of the traditional space-time linear regression model, in consideration of the special background of the hospital logistics transportation, the invention adds an execution tool of a transportation task, important factor indexes of whether a building is crossed and whether a floor is crossed, and adds a quantized time interval busy degree index, and provides a hospital logistics transportation time prediction method based on a multiple linear regression model, and carries out linear regression equation modeling on the hospital logistics transportation time, thereby providing a model for prediction for the time management of the hospital logistics transportation.
The technical scheme adopted by the invention for solving the technical problems is as follows:
a hospital logistics transportation time prediction method based on a multiple linear regression model comprises the following steps:
s1: extracting the transport data and the infrastructure data of the hospital from a hospital logistics database, wherein the used data contents comprise a transport history task table, a hospital organization table, a building distance information table and a floor information table;
s2: integrating the data of the hospital organization table, the building distance information table and the floor information table into a transport history task table to obtain a dependent variable Y and a series of independent variables X1,X2,……，Xp；
S3: analyzing and processing the stable transportation task data with the repeated execution times larger than the set number;
s4: in the aspect of processing the same task, the median value of the same task data is taken as the standard of the data for conveying the task to form a data set Y, X to be subjected to multivariate linear fitting1,X2,……，Xp；
S5: and calculating a time interval busy degree index. And taking original conveying task data, and counting the conveying task number in different time periods. Calculating the ratio of the number of different tasks to the total number of tasks
i is 0, 1, … …, M;
s6: taking the time interval busy degree U as an independent variable Xp+1Adding the indexes into a data set to be subjected to multivariate linear fitting;
s7: performing multiple regression linear fitting on the transportation task data set added with the busy degree index to obtain a multiple linear function yi＝β0+β1xi1+β2xi2+……+βp+1xip+1+εiAnd then predicting the subsequent logistics delivery time.
The technical conception of the invention is as follows: multiple linear regression has multiple independent variables or regression elements. Aiming at the time prediction problem of hospital logistics transportation, a period busy degree index can be obtained by utilizing the conventional transportation task data set and added into a row and column of known independent variables, and the prediction precision of the medical logistics transportation time can be improved compared with a general time-space model.
In the multiple linear regression model after adding the time interval busy degree index, a statistical diagnosis is carried out on the model, and generally, residual values (residuals), R-squares (R-squared) and Standard estimation errors (Standard error) are used for representing the prediction accuracy and the reasonable degree of the model. When the multiple linear regression is used for calculation, numerical data is needed, nominal data is converted into binary data, and nominal weight of the task tool is needed to be converted into numerical data.
In a prediction model of the hospital logistics transportation time, the more index factors are considered, the higher the prediction precision is. According to the investigation of the actual condition of the hospital. Knowing the conveying execution tool, the distance between the crossed buildings, the number of the crossed buildings and the number difference of the inter-department rooms have certain influence on the task execution time, and according to the busy degree index of the time period calculated according to the previous data, the subjective environment for executing the task can be depicted to a certain degree, so that the execution time of the conveying task is influenced. Therefore, the model of the patent not only models the objective space-time model of the hospital, but also can depict the subjective environment to a certain degree, and after the busy degree index of the time period is added, the prediction precision of the logistics transportation time can be further improved.
The invention has the following beneficial effects: by using the independent variable as a conveying execution tool, the distance between the crossed buildings, the number of the crossed buildings, the difference between the department numbers and the dependent variable as a multiple linear regression model of the task execution time, after a busy degree index of a time period is added, the prediction precision can be further improved, and the increase of the R-side index and the reduction of the error of standard estimation can be visually expressed.
Drawings
FIG. 1 is a flow chart of the modeling steps of a hospital logistics transportation time prediction method based on a multiple linear regression model;
FIG. 2 is a summary of various evaluations of a multiple regression model built with busy indicators;
FIG. 3 shows the predicted values and residuals of the model.
FIG. 4 shows the parameter coefficients of a multiple regression function established by adding a busy level indicator;
FIG. 5 is a regression-normalized residual histogram;
FIG. 6 is a plot of the normalized P-P of regression-normalized residuals;
Detailed Description
The invention is further described below with reference to the accompanying drawings.
Referring to fig. 1 to 6, a hospital logistics transportation time prediction method based on a multiple linear regression model takes the study of logistics transportation data in a hospital as an example, the raw data records the execution time and other information of each task within a certain period of time, and modeling analysis of transportation time prediction is performed by corresponding index factors.
The following embodiments describe the present invention in detail with reference to the accompanying drawings, as shown in fig. 1, the present invention includes the following steps:
s1: extracting the transport data and the infrastructure data of the hospital from a hospital logistics database, wherein the used data contents comprise a transport history task table, a hospital organization table, a building distance information table, a floor information table and the like;
s2: integrating data of a hospital organization table, a building distance information table and a floor information table into a transport history task table, wherein the data comprises information such as floor and building distance and the like, so that the data structure is more complete; containing the independent variable X1,X2,X3,X4,X5Respectively representing the number of the task spanning floors, the difference between the numbers of departments, the linear distance between buildings, the actual distance between buildings and the type of an execution tool of the task; the dependent variable Y represents the transit time.
The type of the execution tool of the task in the S2 is a nominal weight, numerical data are needed when the multiple linear regression is used for calculation, the nominal data need to be converted into binary data, and the nominal weight of the task tool is converted into the numerical data;
s3: extracting single conveying task data with large data volume, wherein the conveying task with small data volume has overlarge contingency and can cause great error influence on a fitting function, and through preliminary analysis, the model only analyzes and processes stable conveying task data with the repeated execution times of more than 40 times;
s4: in order to avoid the influence of the outlier data on the transport task to be analyzed, the median value of the same task data is taken as the standard of the transport task data to form a data set Y, X to be fitted1,X2,……，X8Wherein X5 is a nominal variable, and ONE variable is converted into 4 binary variables after the ONE-HOT coding is adopted;
s5: calculating the busy degree index of the time period, taking the original transportation task data, counting the transportation task number in different time periods, and calculating the ratio of the different task numbers to the total task number
i is 0, 1 … … 23, wherein i represents each time period after 24 times of day division;
s6: taking the time interval busy degree U as a new independent variable index X9Adding a data set to be subjected to multivariate linear fitting;
s7: carrying out multivariate linear fitting on the transportation task data set added with the time interval busy degree index to obtain the coefficient beta of each variable0，β1，……，β9Obtaining the final multiple linear function y ═ beta0+β1x1+β2x2+……+β9x9+ ε; and calculating the residual value of the fitting function, the R square and the error of the standard estimation, and representing the prediction precision and the reasonable degree of the model.
In step S1, in the logistics system of the hospital, every time the delivery employee completes one piece of information, the information is in the database; the information comprises a task tool type, task content, a starting place number, a destination number, task starting time and task ending time; the hospital database also contains some basic data of the hospital, including a hospital organization table, a building distance information table, a floor information table and the like, which are in one-to-one correspondence with the numbers in the transportation task data.
The step S2 is to extract the index of the logistics transportation task data, obtain the execution time of the task according to the difference between the start time of the task and the end time of the task, obtain distance information and data of crossing floors according to the departure place number and the destination number of the task and some basic data, determine some index factors affecting the execution time according to the actual research on the site, and integrate the newly obtained data of the secondary data into the transportation history task table, so as to make the data structure more complete.
When integrating data, certain cleaning and processing are required to be performed on the original data so as to facilitate subsequent operations. Obtaining independent variable X after treatment1,X2,X3,X4,X5The task cross floor number, the difference between department numbers, the linear distance between buildings, the actual distance between buildings and the type of the task execution tool are represented respectively.
Wherein the execution tool type X of the task in S25For the nominal amount, numerical data is required for the calculation by multiple linear regression, and the nominal data is converted into binary data. And converting the task tool standard weight into numerical data. The conversion mode adopted by the method is an One-Hot Encoding method, and four tool types for carrying execution are converted into four-bit binary data.
In step S3, labels of many tasks in the database are completely consistent, and we define them as the same task, if a certain task is executed less times, the matching function will be affected by a large error due to the fact that the delivery task is too occasional. Through preliminary analysis, the model only analyzes and processes stable transportation task data with the repeated execution times more than 40.
In step S4, the median of the processed same task data is used as the index standard of the transport task data to form a data set Y, X to be subjected to multivariate linear fitting1,X2,……，X8。
In step S5, the ratio of the number of different tasks to the total number of tasks is calculated
i is taken as 0, 1 … … 23 is obtained to obtain the time interval busy degree index U.
In the step S6, the time interval busy degree index U is combined as an independent variable index X9Add to the dataset to be fitted.
In step S7, the transportation task data set with the busyness indicator is subjected to multiple linear regression analysis by using SPSS mathematical analysis software to obtain multiple linear regression function y ═ β0+β1x1+β2x2+……+β9x9+ epsilon (the function coefficients are shown in figure 4 of the model coefficients of the drawings of the specification). And calculating to obtain the residual value of the fitting function, the R square and the error of the standard estimation, and representing the prediction precision and the reasonable degree of the model. (the inspection amount is shown in the attached figure 2 of the specification, and the error of the standard estimation is shown in the attached figure 3 of the specification).
As described above, according to the embodiment of the hospital logistics transportation time prediction method based on the multiple linear regression model in the medical logistics data, the invention selects the logistics transportation data provided by the hospital logistics database and the basic information data of the hospital, and adopts the multiple linear regression model after adding the busyness degree index, so that the final prediction result has high precision, and the requirement of actual use is met. The present invention is to be considered as illustrative and not restrictive. It will be understood by those skilled in the art that various changes, modifications and equivalents may be made therein without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (5)
1. A hospital logistics transportation time prediction method based on a multiple linear regression model is characterized by comprising the following steps:
s1: extracting transport task data and basic data of a hospital from a hospital logistics database, wherein the used data contents comprise a transport history task table, a hospital organization table, a building distance information table and a floor information table;
s2: the numbers of the hospital organization table, the building distance information table and the floor information tableAccording to the integration into the delivery history task table, the dependent variable Y and a series of independent variables X are obtained1,X2,X3,X4,X5；
When integrating data, the original data needs to be cleaned and processed to obtain independent variable X1,X2,X3,X4,X5Respectively representing the number of the task spanning floors, the difference of the numbers of departments, the linear distance between buildings, the actual distance between buildings and the type of a task tool; task tool type X5The method comprises the steps that numerical data are needed for standard weighing when multivariate linear regression calculation is used, the nominal data need to be converted into binary data, task tool standard weighing is converted into the numerical data, the conversion method is an One-Hot Encoding method, and four tool types for carrying out conveying are converted into four-bit binary data;
s3: analyzing and processing the stable transportation task data with the repeated execution times larger than the set number;
s4: in the aspect of processing the same task, the median of the same task data is taken as the standard of the transport task data, the median of the processed same task data is taken as the index standard of the transport task data, and a data set Y and X to be subjected to multivariate linear fitting is formed1,X2,......，X8；
S5: calculating the busy degree index of the time period, taking the original transportation task data, counting the transportation task number in different time periods, and calculating the ratio of the different task numbers to the total task number
i, taking 0, 1, a.
S6: taking a time interval busy degree index U as an independent variable X9Adding the indexes into a data set to be subjected to multivariate linear fitting;
s7: carrying out multiple linear regression analysis on the transportation task data set added with the busyness index by using SPSS mathematical analysis software to obtain multiple linear regression function y ═ beta [ beta ] with congestion consciousness0+β1x1+β2x2+......+β9x9And + epsilon, calculating to obtain a fitting function residual value, an R square and an error of standard estimation, and further predicting subsequent logistics transportation time.
2. The hospital logistics transportation time prediction method based on multiple linear regression model as claimed in claim 1, wherein: in step S1, in the logistics system of the hospital, each time the delivery staff completes one piece of information, the information includes a task tool type, task content, a departure location number, a destination number, a task start time, and a task end time, the hospital database further includes basic data of the hospital, the basic data includes a hospital organization table, a building distance information table, and a floor information table, and the basic data corresponds to the numbers in the delivery task data one to one.
3. The hospital logistics transportation time prediction method based on multiple linear regression model as claimed in claim 2, wherein: in step S2, the execution time of the task is obtained from the difference between the start time of the task and the end time of the task, the distance information and the data of the floor crossing can be obtained from the departure point number and the destination number of the task and the basic data, and the secondary data is integrated into the delivery history task table.
4. The hospital logistics transportation time prediction method based on the multiple linear regression model as claimed in claim 1 or 2, characterized in that: in step S3, the analysis process is performed on the stable transportation task data whose number of times of execution is more than 40.
5. The hospital logistics transportation time prediction method based on multiple linear regression model as claimed in claim 1, wherein: in the step S5, the ratio of the number of different tasks to the total number of tasks is calculated
i is taken to be 01.. 23 obtains a time period busy degree index U, where i represents each time period after 24 times of dividing one day.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810057082.1A CN108256685B (en) | 2018-01-22 | 2018-01-22 | Hospital logistics transportation time prediction method based on multiple linear regression model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810057082.1A CN108256685B (en) | 2018-01-22 | 2018-01-22 | Hospital logistics transportation time prediction method based on multiple linear regression model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108256685A CN108256685A (en) | 2018-07-06 |
| CN108256685B true CN108256685B (en) | 2021-02-26 |
Family
ID=62741667
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810057082.1A Active CN108256685B (en) | 2018-01-22 | 2018-01-22 | Hospital logistics transportation time prediction method based on multiple linear regression model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108256685B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109524125B (en) * | 2019-01-24 | 2021-03-02 | 易保互联医疗信息科技（北京）有限公司 | Medicine inventory analysis method based on medical big data, storage medium and equipment |
| CN110163453B (en) * | 2019-06-20 | 2021-08-13 | 跑哪儿科技（北京）有限公司 | Method, device and system for predicting replenishment resource allocation strategy and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2381396A1 (en) * | 2010-04-20 | 2011-10-26 | Deutsche Post AG | Delivery system for objects |
| CN103794053A (en) * | 2014-03-05 | 2014-05-14 | 中商商业发展规划院有限公司 | Vague predicting method and system for city short-distance logistics simple target delivering time |
| CN104050512A (en) * | 2013-03-15 | 2014-09-17 | Sap股份公司 | Transport time estimation based on multi-granular map |
| CN104915819A (en) * | 2015-06-04 | 2015-09-16 | 江苏辉源供应链管理有限公司 | Production planning-based vehicle allocation method |
| CN105938585A (en) * | 2016-04-12 | 2016-09-14 | 湖南卓跃生物技术开发有限公司 | Cloud-technology-based fresh milk distribution system |
| CN107449428A (en) * | 2017-08-11 | 2017-12-08 | 深圳市腾讯计算机***有限公司 | A kind of missing air navigation aid, device, server and terminal device |
-
2018
- 2018-01-22 CN CN201810057082.1A patent/CN108256685B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2381396A1 (en) * | 2010-04-20 | 2011-10-26 | Deutsche Post AG | Delivery system for objects |
| CN104050512A (en) * | 2013-03-15 | 2014-09-17 | Sap股份公司 | Transport time estimation based on multi-granular map |
| CN103794053A (en) * | 2014-03-05 | 2014-05-14 | 中商商业发展规划院有限公司 | Vague predicting method and system for city short-distance logistics simple target delivering time |
| CN104915819A (en) * | 2015-06-04 | 2015-09-16 | 江苏辉源供应链管理有限公司 | Production planning-based vehicle allocation method |
| CN105938585A (en) * | 2016-04-12 | 2016-09-14 | 湖南卓跃生物技术开发有限公司 | Cloud-technology-based fresh milk distribution system |
| CN107449428A (en) * | 2017-08-11 | 2017-12-08 | 深圳市腾讯计算机***有限公司 | A kind of missing air navigation aid, device, server and terminal device |
Non-Patent Citations (1)
| Title |
|---|
| 基于MLR的公交车行程时间预测模型;汪磊 等;《大连交通大学学报》;20150430;第1-5页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108256685A (en) | 2018-07-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109376953B (en) | Medium-and-long-term electric quantity prediction method and system | |
| US20200083902A1 (en) | Method for handling multidimensional data | |
| CN116757546B (en) | Production monitoring and early warning system based on industrial Internet | |
| CN108256685B (en) | Hospital logistics transportation time prediction method based on multiple linear regression model | |
| US20100057533A1 (en) | Multidimensional method and computer system for patent and technology portfolio rating and related database | |
| Alharbi et al. | A seasonal autoregressive integrated moving average with exogenous factors (SARIMAX) forecasting model-based time series approach | |
| CA2937919A1 (en) | Evaluating data quality of clinical trials | |
| CN108461150A (en) | A kind of occupational health forecasting research method | |
| Sánchez-Garrido et al. | An adaptive ANP & ELECTRE IS-based MCDM model using quantitative variables | |
| US7813893B2 (en) | Method of process trend matching for identification of process variable | |
| CN117435997B (en) | Elevator early warning and on-demand maintenance method based on transducer and time sequence compression mechanism | |
| Krajčovič et al. | System of parametric modelling and assessing the production staff utilisation as a basis for aggregate production planning | |
| CN113723541B (en) | Slope displacement prediction method based on hybrid intelligent algorithm | |
| Ramírez et al. | A methodology for discriminant time series analysis applied to microclimate monitoring of fresco paintings | |
| CN114154716A (en) | Enterprise energy consumption prediction method and device based on graph neural network | |
| CN114021808A (en) | Power resource allocation method based on emergency influence grade identification | |
| CN111915100B (en) | High-precision freight prediction method and freight prediction system | |
| CN113673842A (en) | Production efficiency diagnosis method, device, equipment and storage medium based on big data | |
| Hassan et al. | Condition Prediction for Existing Educational Facilities Using Artificial Neural Networks and Regression Analysis | |
| CN116383645A (en) | Intelligent system health degree monitoring and evaluating method based on anomaly detection | |
| Han et al. | Implementation of construction performance database prototype for curtain wall operation in high-rise building construction | |
| CN111105148B (en) | Off-job probability evaluation method, apparatus and computer readable storage medium | |
| Carnero | Asymmetries in the Maintenance Performance of Spanish Industries before and after the Recession | |
| Aichouni et al. | On the use of Johnson’s distribution in quality and process improvement | |
| CN107220252B (en) | Atmospheric tower normal line flash point prediction method for atmospheric and vacuum device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |