Industrial production task resource demand analysis method based on big data

Abstract

The invention discloses an industrial production task resource demand analysis method based on big data, and relates to the technical field of industrial production task management. The resource demand data distribution capability is effectively improved; by setting a time chain, multi-dimensional time sequence production data of a time period corresponding to the time chain is collected; performing standardization processing on the multi-dimensional time sequence production data to construct a multi-dimensional production data feature data set; setting a resource demand data feature matrix, and constructing a resource feature correlation coefficient model corresponding to the multi-dimensional production data feature data set; constructing a time prediction model corresponding to the time period; setting a prediction time period corresponding to the production task, and obtaining a prediction time period resource demand data prediction table corresponding to the prediction time period according to the time prediction model; and setting resource constraint data, and optimizing the prediction time period resource demand data prediction table to obtain an optimal prediction time period resource demand data prediction table.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial production task management, and in particular to a method for analyzing resource demand of industrial production tasks based on big data. Background Art

[0002] The resource requirements for industrial production tasks mainly include natural resources, labor, main materials and turnover materials, etc. Natural resources are the basis of industrial production, including land, water, minerals, forests, etc.; in addition, industrial production also requires resources such as labor, main materials and turnover materials; In industrial production, resource demand analysis is a key link to ensure production efficiency and cost control. In the prior art, resource demand analysis mostly relies on manual experience or static models, lacks real-time adaptability to dynamic production tasks, and cannot allocate resource demand data in advance. For example, traditional methods are difficult to strictly control multivariate resource demand data (such as equipment status fluctuations, raw material supply delays, order priority changes, etc.), lack of strict allocation capabilities, resulting in waste of resource demand data, or insufficient resource demand data causing delays, which in turn leads to problems such as inefficient resource allocation, inventory backlogs or shortages. To this end, the present invention proposes a resource demand analysis method for industrial production tasks based on big data, which realizes intelligent analysis and optimization of resource demand by dynamically collecting multi-dimensional production data and building a prediction model. Summary of the invention

[0003] In order to solve the above technical problems, the present invention provides an industrial production task resource demand analysis method based on big data; The purpose of the present invention can be achieved by the following technical solution: a method for analyzing resource requirements of industrial production tasks based on big data, the method comprising the following steps: Step S1: Setting a time chain, and collecting multi-dimensional time series production data of a time period corresponding to the time chain based on big data; Step S2: Standardize the multi-dimensional time series production data to construct a multi-dimensional production data feature data set; Step S3: setting a resource demand data feature matrix, and constructing a resource feature correlation coefficient model corresponding to a multi-dimensional production data feature data set according to the resource demand data feature matrix; Step S4: constructing a time prediction model corresponding to the time period according to the resource feature correlation coefficient model; Step S5: setting a forecast time period corresponding to the production task, and obtaining a forecast time period resource demand data forecast table corresponding to the forecast time period according to the time forecast model; Step S6: setting resource constraint data, and optimizing the prediction time period resource demand data prediction table according to the resource constraint data to obtain the optimal prediction time period resource demand data prediction table.

[0004] Further, the process of setting up the time chain includes: Based on big data collection, the collection time periods of the maximum and minimum resource demand data corresponding to the production tasks are marked as maximum demand time periods and minimum demand time periods, and collection time period segments are generated with the maximum demand time periods and minimum demand time periods as boundaries; historical collection cycles are set, and several time periods corresponding to the collection time period segments are obtained according to the historical collection cycles, and the time periods are connected to generate a time chain.

[0005] Furthermore, the process of generating multi-dimensional time series production data includes: Based on big data, resource demand data corresponding to each time period on the time chain are collected, and resource demand data types corresponding to each resource demand data are collected and connected to generate a resource demand data chain, and each resource demand data chain is connected to generate a resource demand data network; The industrial production task types corresponding to the marked resource demand data network are connected to generate industrial multi-dimensional production data, and then connected with the corresponding time period to generate multi-dimensional time series production data. At the same time, the resource demand data corresponding to the multi-dimensional time series production data is marked as ; Among them, k represents the industrial production task type; j represents the resource demand data type.

[0006] Furthermore, the process of standardizing the multi-dimensional time series production data includes: Set the standard resource demand value of each resource demand data type corresponding to the resource demand data of the industrial production task type, and generate a standard resource demand model of the production task type with several standard resource demand values, marked as , and greater than 0; In the resource requirement standard model of the production task type, the absolute value of the fluctuation level ratio is set, marked as ; Set the fluctuation level range, the fluctuation level range includes , as well as ; Obtain multi-dimensional time series production data corresponding to the same industrial production task type in the time chain, integrate them to generate a multi-dimensional time series production data set, and send the resource demand data chain corresponding to the multi-dimensional time series production data set to the production task type resource demand standard model corresponding to the industrial production task type in sequence according to the time period sequence; map the resource demand data to the corresponding standard resource demand value according to the resource demand data type; obtain the corresponding absolute value of the fluctuation level ratio, and compare it with the fluctuation level range; like or , it means that the corresponding resource demand data is high-volatility resource demand data, marked as ; like , it means that the corresponding resource demand data is stable resource demand data.

[0007] Furthermore, the process of constructing a multi-dimensional production data feature dataset includes: Correct the resource demand data corresponding to the high-volatility resource demand data to the corresponding standard resource demand value for standardization correction, marked as , and then integrated with the stable resource demand data to generate a multi-dimensional production data feature data set corresponding to each time period.

[0008] Furthermore, the process of constructing a resource feature correlation coefficient model corresponding to the multi-dimensional production data feature data set includes: Generate a resource demand data feature matrix from the multi-dimensional production data feature data set corresponding to each industrial production task type; The resource demand data feature matrix is ​​numbered, denoted as k=1, 2, ..., h, and h is a positive integer; the horizontal and vertical columns of the resource demand data feature matrix are numbered, denoted as j=1, 2, ..., i, and i is a positive integer; t is numbered as n, denoted as n=1, 2, ..., m, and m is a positive integer; Based on big data technology, the resource demand data feature matrix is ​​analyzed to build a resource feature correlation coefficient model, which is recorded as ; The specific formula is: ; in, It is expressed as the average value of the resource demand data type corresponding to the vertical direction of the resource demand data feature matrix; It is expressed as the average value of the horizontal time period corresponding to the resource demand data feature matrix.

[0009] Furthermore, the process of constructing a time prediction model corresponding to a time period according to the resource feature correlation coefficient model includes: Set the external environment variable model corresponding to the time period, marked as ; Set the weight coefficient, and obtain the time prediction model corresponding to the time period according to the weight coefficient, marked as ; The specific formula is: ; Among them, w1 and w2 represent the corresponding weight coefficients respectively.

[0010] Further, the process of obtaining the forecast time period resource demand data forecast table corresponding to the time period includes: Obtain the resource demand type corresponding to the predicted time period and send it to the resource feature correlation coefficient model to obtain the resource feature correlation coefficient corresponding to the resource demand type; then send the resource feature correlation coefficient and the predicted time period to the time prediction model to obtain the predicted resource demand data corresponding to the resource demand data type; The predicted resource demand data corresponding to each resource demand data type in the predicted time period are connected to generate a predicted time period resource demand data prediction table.

[0011] Furthermore, the process of obtaining the optimal prediction time period resource demand data prediction table includes: Set the upper limit of resource demand data corresponding to each resource demand data type in the forecast table of resource demand data for the forecast time period, marked as MAXR j , and generate an upper limit resource demand data table; Set the corresponding resource constraint data according to the resource requirement data type, marked as U j ;According to the resource constraint data, obtain the resource demand data range corresponding to the resource demand data type, marked as , and generate a resource constraint data table; Compare the resource constraint data table with the forecast time period resource demand data forecast table; If the predicted resource demand data corresponding to the resource demand data type is less than the minimum value of the resource demand data range, the corresponding predicted resource demand data will be automatically modified to MAXR j -U j ; If the predicted resource demand data corresponding to the resource demand data type is greater than the maximum value of the resource demand data range, the corresponding predicted resource demand data will be automatically modified to MAXR j +U j ; Otherwise, no processing is done; The modified forecast time period resource demand data forecast table is generated and optimized to obtain the optimal forecast time period resource demand data forecast table.

[0012] Compared with the prior art, the beneficial effects of the present invention are: by setting a time chain, a number of multi-dimensional time series production data corresponding to the time chain are collected; the multi-dimensional time series production data are standardized to construct a multi-dimensional production data feature data set; a resource demand data feature matrix is ​​set, and a resource feature correlation coefficient model corresponding to the multi-dimensional production data feature data set is constructed according to the resource demand data feature matrix; a time prediction model corresponding to the time period is constructed according to the resource feature correlation coefficient model; a prediction time period corresponding to the production task is set, and a prediction time period resource demand data prediction table corresponding to the prediction time period is obtained according to the time prediction model; resource constraint data is set, and the prediction time period resource demand data prediction table is optimized according to the resource constraint data to obtain the optimal prediction time period resource demand data prediction table; the resource demand data allocation capability is effectively improved; waste of resource demand data is prevented, or delays caused by insufficient resource demand data are prevented; and problems such as inefficient resource allocation, inventory backlog or shortage are caused. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0014] Figure 1 It is a schematic diagram of the present invention. DETAILED DESCRIPTION

[0015] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0016] like Figure 1 As shown, a method for analyzing resource requirements of industrial production tasks based on big data comprises the following steps: Step S1: Setting a time chain, and collecting multi-dimensional time series production data of a time period corresponding to the time chain based on big data; Step S2: Standardize the multi-dimensional time series production data to construct a multi-dimensional production data feature data set; Step S3: setting a resource demand data feature matrix, and constructing a resource feature correlation coefficient model corresponding to a multi-dimensional production data feature data set according to the resource demand data feature matrix; Step S4: constructing a time prediction model corresponding to the time period according to the resource feature correlation coefficient model; Step S5: setting a forecast time period corresponding to the production task, and obtaining a forecast time period resource demand data forecast table corresponding to the forecast time period according to the time forecast model; Step S6: setting resource constraint data, and optimizing the prediction time period resource demand data prediction table according to the resource constraint data to obtain the optimal prediction time period resource demand data prediction table.

[0017] For step S1, setting a time chain, collecting industrial multi-dimensional production data of production tasks corresponding to the time chain based on big data, and generating multi-dimensional time series production data need to be further defined: Based on the big data collection, the collection time period of the maximum and minimum resource demand data corresponding to the production task is marked as the maximum demand time period and the minimum demand time period, and the collection time period is generated with the maximum demand time period and the minimum demand time period as the boundary; set the historical collection cycle, obtain several time periods corresponding to the collection time period according to the historical collection cycle, and connect the time periods to generate a time chain; In the above embodiment, it needs to be further explained that the resource demand data includes but is not limited to multi-dimensional information such as equipment load rate, raw material consumption, order information, production progress, and man-hours; the corresponding resource demand data types include but are not limited to equipment, raw materials, orders, production progress, man-hours, etc.; the maximum resource demand value and the minimum resource demand value are respectively used to express the maximum and minimum values ​​of the sum of resource demands; the time period is but not limited to one hour, one day, one month, etc.

[0018] Based on big data, resource demand data corresponding to each time period on the time chain are collected, and resource demand data types corresponding to each resource demand data are collected and connected to generate a resource demand data chain, and each resource demand data chain is connected to generate a resource demand data network; The industrial production task types corresponding to the marked resource demand data network are connected to generate industrial multi-dimensional production data, and then connected with the corresponding time period to generate multi-dimensional time series production data. At the same time, the resource demand data corresponding to the multi-dimensional time series production data is marked as ; Where k represents the industrial production task type; j represents the resource demand data type; In the above embodiment, it needs to be further explained that different industrial production task types have different resource demand data, and multi-dimensional time series production data corresponding to different time periods of the time chain are collected based on big data; the multi-dimensional resource demand data corresponding to different production task types are better analyzed and associated.

[0019] For step S2, standardizing the multi-dimensional time series production data to construct a multi-dimensional production data feature dataset requires further definition: Set the standard resource demand value of each resource demand data type corresponding to the resource demand data of the industrial production task type, and generate a standard resource demand model of the production task type with several standard resource demand values, marked as , and greater than 0; In the resource requirement standard model of the production task type, the absolute value of the fluctuation level ratio is set, marked as ; Set the fluctuation level range, the fluctuation level range includes , as well as ; The multi-dimensional time series production data corresponding to the same industrial production task type in the time chain are obtained and integrated to generate a multi-dimensional time series production data set, and the resource demand data chain corresponding to the multi-dimensional time series production data set is sent to the production task type resource demand standard model corresponding to the industrial production task type in sequence according to the time period sequence; the resource demand data is mapped to the corresponding standard resource demand value according to the resource demand data type; marked as ; Get the corresponding absolute value of the fluctuation level ratio and compare it with the fluctuation level range; like or , it means that the corresponding resource demand data is high-volatility resource demand data, marked as ; like , it means that the corresponding resource demand data is stable resource demand data; Correct the resource demand data corresponding to the high-volatility resource demand data to the corresponding standard resource demand value for standardization correction, marked as , and then integrated with the stable resource demand data to generate a multi-dimensional production data feature data set corresponding to each time period.

[0020] In the above embodiment, it needs to be further explained that by constructing a standard model of resource requirements of production task types to obtain the fluctuation level range of each time period corresponding to each industrial production task type, the high-volatility resource demand data is corrected to high-volatility resource demand data to improve the accuracy of the data.

[0021] For step S3, setting a resource demand data feature matrix and constructing a resource feature correlation coefficient model corresponding to a multi-dimensional production data feature data set based on the resource demand data feature matrix needs to be further defined: The multi-dimensional production data feature data set corresponding to each industrial production task type generates a resource demand data feature matrix, marked as ; Wherein, t represents the time period and is the vertical axis of the resource demand data feature matrix; j represents the horizontal axis of the resource demand data feature matrix; The resource demand data feature matrix is ​​numbered, denoted as k=1, 2, ..., h, and h is a positive integer; the horizontal and vertical columns of the resource demand data feature matrix are numbered, denoted as j=1, 2, ..., i, and i is a positive integer; t is numbered as n, denoted as n=1, 2, ..., m, and m is a positive integer; Based on big data technology, the resource demand data feature matrix is ​​analyzed to build a resource feature correlation coefficient model, which is recorded as ; The specific formula is: ; in, It is expressed as the average value of the resource demand data type corresponding to the vertical direction of the resource demand data feature matrix; It is expressed as the average value of the horizontal time period corresponding to the resource demand data feature matrix.

[0022] In the above embodiment, it needs to be further explained that by generating a resource demand data feature matrix based on the multi-dimensional production data feature data set according to the industrial production task type, and processing and analyzing all industrial production task types, the resource demand in complex production scenarios can be accurately predicted.

[0023] For step S4, the time prediction model corresponding to the time period constructed according to the resource feature correlation coefficient model needs to be further defined: Set the external environment variable model corresponding to the time period, marked as ; Set the weight coefficient, and obtain the time prediction model corresponding to the time period according to the weight coefficient, marked as ; The specific formula is: ; Among them, w1 and w2 represent the corresponding weight coefficients respectively.

[0024] In the above embodiment, it needs to be further explained that the resource feature correlation coefficients corresponding to different resource demand data types in different time periods are known, and the resource demand data corresponding to the time period and the resource demand data type are obtained according to the linear relationship.

[0025] For step S5, the forecast time period corresponding to the production task is set, and the forecast time period resource demand data forecast table corresponding to the forecast time period is obtained according to the time forecast model, which needs to be further defined: Obtain the resource demand type corresponding to the predicted time period and send it to the resource feature correlation coefficient model to obtain the resource feature correlation coefficient corresponding to the resource demand type; then send the resource feature correlation coefficient and the predicted time period to the time prediction model to obtain the predicted resource demand data corresponding to the resource demand data type; Connect the predicted resource demand data corresponding to each resource demand data type in the predicted time period to generate a predicted resource demand data prediction table for the predicted time period; In the above embodiment, it needs to be further explained that obtaining a number of predicted resource demand data for a predicted time period and merging the predicted resource demand data to generate a predicted time period resource demand data forecast table can better lay a foundation for later industrial production tasks and prevent waste of resource demand data.

[0026] For step S6: setting resource constraint data, optimizing the forecast time period resource demand data forecast table according to the resource constraint data to obtain the optimal forecast time period resource demand data forecast table needs to be further defined: Set the upper limit of resource demand data corresponding to each resource demand data type in the forecast time period resource demand data forecast table, mark it as MAXRj, and generate an upper limit resource demand data table; According to the resource demand data type, the corresponding resource constraint data is set, marked as Uj; then, according to the resource constraint data, the resource demand data range corresponding to the resource demand data type corresponding to the upper limit resource demand data table is obtained, marked as , and generate a resource constraint data table; Compare the resource constraint data table with the forecast time period resource demand data forecast table; If the predicted resource demand data corresponding to the resource demand data type is less than the minimum value of the resource demand data range, the corresponding predicted resource demand data will be automatically modified to MAXR j -U j ; If the predicted resource demand data corresponding to the resource demand data type is greater than the maximum value of the resource demand data range, the corresponding predicted resource demand data will be automatically modified to MAXR j +U j ; Otherwise, no processing is done; The modified forecast time period resource demand data forecast table is generated and optimized to obtain the optimal forecast time period resource demand data forecast table.

[0027] In the above embodiment, it needs to be further explained that re-correcting the forecast time period resource demand data forecast table to obtain the optimal forecast time period resource demand data forecast table can better control the resource demand data and prevent resource waste.

[0028] The features and exemplary embodiments of various aspects of the present application are described in detail above. In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is further described in detail in combination with the drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application rather than to limit the present application. For those skilled in the art, the present application can be implemented without some of these specific details. The above description of the embodiments is merely to provide a better understanding of the present application by showing examples of the present application.

[0029] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A method for analyzing resource requirements of industrial production tasks based on big data, characterized in that: The method comprises the following steps: Step S1: Setting a time chain, and collecting multi-dimensional time series production data of a time period corresponding to the time chain based on big data; Step S2: Standardize the multi-dimensional time series production data to construct a multi-dimensional production data feature data set; Step S3: setting a resource demand data feature matrix, and constructing a resource feature correlation coefficient model corresponding to a multi-dimensional production data feature data set according to the resource demand data feature matrix; Step S4: constructing a time prediction model corresponding to the time period according to the resource feature correlation coefficient model; Step S5: setting a forecast time period corresponding to the production task, and obtaining a forecast time period resource demand data forecast table corresponding to the forecast time period according to the time forecast model; Step S6: setting resource constraint data, and optimizing the prediction time period resource demand data prediction table according to the resource constraint data to obtain the optimal prediction time period resource demand data prediction table.

2. According to the big data-based industrial production task resource demand analysis method of claim 1, it is characterized in that: The process of setting up a timeline includes: Based on big data collection, the collection time periods of the maximum and minimum resource demand data corresponding to the production tasks are marked as maximum demand time periods and minimum demand time periods, and collection time period segments are generated with the maximum demand time periods and minimum demand time periods as boundaries; historical collection cycles are set, and several time periods corresponding to the collection time period segments are obtained according to the historical collection cycles, and the time periods are connected to generate a time chain.

3. The method for analyzing industrial production task resource requirements based on big data according to claim 2 is characterized in that: The process of generating multi-dimensional time series production data includes: Based on big data, resource demand data corresponding to each time period on the time chain are collected, and resource demand data types corresponding to each resource demand data are collected and connected to generate a resource demand data chain, and each resource demand data chain is connected to generate a resource demand data network; The industrial production task types corresponding to the marked resource demand data network are connected to generate industrial multi-dimensional production data, and then connected with the corresponding time period to generate multi-dimensional time series production data. At the same time, the resource demand data corresponding to the multi-dimensional time series production data is marked as ; Among them, k represents the industrial production task type; j represents the resource demand data type.

4. The method for analyzing industrial production task resource requirements based on big data according to claim 3 is characterized in that: The process of standardizing multi-dimensional time series production data includes: Set the standard resource demand value of each resource demand data type corresponding to the resource demand data of the industrial production task type, and generate a standard resource demand model of the production task type with several standard resource demand values, marked as , and greater than 0; In the resource requirement standard model of the production task type, the absolute value of the fluctuation level ratio is set, marked as ; Set the fluctuation level range, the fluctuation level range includes , as well as ; Obtain multi-dimensional time series production data corresponding to the same industrial production task type in the time chain, integrate them to generate a multi-dimensional time series production data set, and send the resource demand data chain corresponding to the multi-dimensional time series production data set to the production task type resource demand standard model corresponding to the industrial production task type in sequence according to the time period sequence; map the resource demand data to the corresponding standard resource demand value according to the resource demand data type; obtain the corresponding absolute value of the fluctuation level ratio, and compare it with the fluctuation level range; like or , it means that the corresponding resource demand data is high-volatility resource demand data, marked as ; like , it means that the corresponding resource demand data is stable resource demand data.

5. The method for analyzing industrial production task resource requirements based on big data according to claim 4 is characterized in that: The process of building a multi-dimensional production data feature dataset includes: Correct the resource demand data corresponding to the high-volatility resource demand data to the corresponding standard resource demand value for standardization correction, marked as , and then integrated with the stable resource demand data to generate a multi-dimensional production data feature data set corresponding to each time period.

6. The method for analyzing industrial production task resource requirements based on big data according to claim 5 is characterized in that: The process of constructing a resource feature correlation coefficient model corresponding to a multi-dimensional production data feature dataset includes: Generate a resource demand data feature matrix from the multi-dimensional production data feature data set corresponding to each industrial production task type; The resource demand data feature matrix is ​​numbered, denoted as k=1, 2, ..., h, and h is a positive integer; the horizontal and vertical columns of the resource demand data feature matrix are numbered, denoted as j=1, 2, ..., i, and i is a positive integer; t is numbered as n, denoted as n=1, 2, ..., m, and m is a positive integer; Based on big data technology, the resource demand data feature matrix is ​​analyzed to build a resource feature correlation coefficient model, which is recorded as ; The specific formula is: The specific formula is: ； in, It is expressed as the average value of the resource demand data type corresponding to the vertical direction of the resource demand data feature matrix; It is expressed as the average value of the horizontal time period corresponding to the resource demand data feature matrix.

7. The method for analyzing industrial production task resource requirements based on big data according to claim 6 is characterized in that: The process of constructing a time prediction model corresponding to a time period based on the resource feature correlation coefficient model includes: Set the external environment variable model corresponding to the time period, marked as ; Set the weight coefficient, and obtain the time prediction model corresponding to the time period according to the weight coefficient, marked as ; The specific formula is: ； Among them, w1 and w2 represent the corresponding weight coefficients respectively.

8. The method for analyzing industrial production task resource requirements based on big data according to claim 7 is characterized in that: The process of obtaining the forecast time period resource demand data forecast table corresponding to the time period includes: Obtain the resource demand type corresponding to the predicted time period and send it to the resource feature correlation coefficient model to obtain the resource feature correlation coefficient corresponding to the resource demand type; then send the resource feature correlation coefficient and the predicted time period to the time prediction model to obtain the predicted resource demand data corresponding to the resource demand data type; The predicted resource demand data corresponding to each resource demand data type in the predicted time period are connected to generate a predicted time period resource demand data prediction table.

9. The method for analyzing industrial production task resource requirements based on big data according to claim 8 is characterized in that: The process of obtaining the optimal forecast time period resource demand data forecast table includes: Set the upper limit of resource demand data corresponding to each resource demand data type in the forecast table of resource demand data for the forecast time period, marked as MAXR j , and generate an upper limit resource demand data table; Set the corresponding resource constraint data according to the resource requirement data type, marked as U j ;According to the resource constraint data, obtain the resource demand data range corresponding to the resource demand data type, marked as , and generate a resource constraint data table; Compare the resource constraint data table with the forecast time period resource demand data forecast table; If the predicted resource demand data corresponding to the resource demand data type is less than the minimum value of the resource demand data range, the corresponding predicted resource demand data is automatically modified to MAXRj-Uj; If the predicted resource demand data corresponding to the resource demand data type is greater than the maximum value of the resource demand data range, the corresponding predicted resource demand data is automatically modified to MAXRj+Uj; Otherwise, no processing is done; The modified forecast time period resource demand data forecast table is generated and optimized to obtain the optimal forecast time period resource demand data forecast table.

Images