Enterprise economic operation dispatching management method and system based on big data analysis

Abstract

The present invention relates to the field of electronic digital data processing technology, and specifically to a method and system for enterprise economic operation scheduling management based on big data analysis, the method comprising obtaining a multi-source data set; substituting the multi-source data set into an analysis scheduling model, so that according to the multi-source data set, it is judged whether the current scheduling management plan needs to be adjusted, and the optimal adjustment plan and the simulation results corresponding to the selected adjustment plan are selected and output; according to the decision opinions of multiple decision-makers on the selection of the optimal adjustment plan and the simulation results corresponding to the selected adjustment plan, the selected adjustment plan or the analysis scheduling model is selectively adjusted; according to the authority level of the personnel, the simulation results corresponding to the adjusted adjustment plan are selectively visualized. Timely and accurate economic operation scheduling is achieved, thereby optimizing the resource allocation of the enterprise and improving the economic benefits of the enterprise.

Description

Technical Field

[0001] The present invention relates to the technical field of electronic digital data processing, and in particular to the technical field of enterprise economic operation dispatching, and in particular to an enterprise economic operation dispatching management method and system based on big data analysis. Background Art

[0002] In economic activities, the production plan and decision-making scheme of an enterprise have a direct impact on the operating efficiency and profit of the enterprise. However, the management methods of production plan and decision-making scheme in the existing technology often lack real-time, dynamic and targeted, which easily leads to waste of production resources and reduced enterprise benefits.

[0003] Therefore, there is an urgent need to study an enterprise economic operation scheduling management method and system based on big data analysis that can provide enterprises with accurate and real-time business insights, thereby optimizing production and decision-making plans, enhancing enterprise competitiveness and ensuring information security. Summary of the invention

[0004] Based on this, the present invention proposes a method and system for enterprise economic operation scheduling management based on big data analysis, which solves the technical problems that the management methods of production plans and decision-making plans in the prior art often lack real-time, dynamic and targeted performance, and easily lead to waste of production resources and reduced enterprise benefits.

[0005] According to a first aspect of the present invention, there is provided a method for enterprise economic operation scheduling management based on big data analysis, the method comprising the following steps:

[0006] Acquire a multi-source data set, wherein the multi-source data set includes at least internal enterprise data, current policy data, and external data;

[0007] Substitute the multi-source data set into the analysis scheduling model, so that according to the multi-source data set, it is determined whether the current scheduling management plan needs to be adjusted, and the optimal adjustment plan and the simulation results corresponding to the selected adjustment plan are selected and output;

[0008] According to the decision opinions of multiple decision makers on selecting the best adjustment plan and the simulation results corresponding to the selected adjustment plan, selectively adjust the selected adjustment plan or the analysis and scheduling model;

[0009] According to the authority level of the personnel, the simulation results corresponding to the adjusted adjustment scheme are selectively visualized.

[0010] According to an embodiment of the present invention, before acquiring the multi-source data set, the method further includes:

[0011] Collecting enterprise internal data in real time, wherein the enterprise internal data at least includes enterprise inventory information, production information, economic distribution information and sales information;

[0012] Based on the collected internal enterprise data, determine whether it matches the current scheduling management plan:

[0013] If the judgment is no, it is determined that the enterprise economic operation scheduling needs to be executed, and the multi-source data set is obtained;

[0014] If the judgment is yes, then the current policy data is collected in real time, wherein the current policy data at least includes policy information and regulatory information;

[0015] Based on the collected current policy data, determine whether there are any changes:

[0016] If the answer is yes, it is determined that the enterprise economic operation scheduling needs to be executed, and the multi-source data set is obtained;

[0017] If the judgment is no, then collect external data in real time, wherein the external data at least includes market demand information and market supply information;

[0018] Based on the collected external data, the acquisition of multi-source datasets is selectively performed.

[0019] According to an embodiment of the present invention, before substituting the multi-source data set into the analysis scheduling model, the method further includes the following steps of training the analysis scheduling model:

[0020] Acquire multiple sets of multi-source training data sets, wherein each set of multi-source training data sets includes at least one obfuscated data;

[0021] Preprocessing multiple groups of multi-source training data sets to obtain training available data sets corresponding to each group of multi-source training data sets;

[0022] According to the available training data sets corresponding to each group of multi-source training data sets, it is judged whether the data processing training of the analysis scheduling model is successful:

[0023] If the judgment is no, the analysis and scheduling model is adjusted, and the adjusted analysis and scheduling model is retrained;

[0024] If the judgment is yes, then judging whether it is necessary to adjust the scheduling management plan for the time corresponding to each group of available training data sets according to each group of available training data sets;

[0025] According to the judgment result, it is judged whether the adjustment judgment training of the analysis scheduling model is successful:

[0026] If the judgment is yes, then according to each group of available training data sets and the scheduling management plan at the time corresponding to each group of available training data sets, a training adjustment plan for operating and scheduling the enterprise economy corresponding to the available training data sets is selectively generated;

[0027] and selectively adjusting the training adjustment scheme for operating and scheduling the enterprise economy corresponding to the training available data set, to generate a final training adjustment scheme corresponding to each set of training available data sets;

[0028] According to the final training adjustment plan corresponding to each set of training available data sets, judging whether the adjustment plan generation training of the analysis scheduling model is successful;

[0029] According to the training results of each training of the analysis and scheduling model, it is determined whether the analysis and scheduling model is successfully trained.

[0030] According to an embodiment of the present invention, a preset historical multi-source database is stored in the analysis and scheduling model, and the preset historical multi-source database stores several groups of original multi-source data sets of the enterprise at different times and the historical available data sets corresponding to each group of original multi-source data sets;

[0031] The obtaining of multiple sets of multi-source training data sets comprises:

[0032] According to the preset historical multi-source database, multiple groups of historical multi-source data sets are randomly obtained;

[0033] In multiple sets of historical multi-source data sets, a random number of labeled obfuscated data are randomly added to obtain multiple sets of historical multi-source data sets with obfuscated data;

[0034] Each set of historical multi-source data sets with obfuscated data is used as a multi-source training data set to obtain multiple sets of multi-source training data sets.

[0035] According to an embodiment of the present invention, the analytical scheduling model further stores a preset historical scheduling management solution database, wherein the preset historical scheduling management solution database stores historical scheduling management solutions at various moments and selectively existing historical adjustment solutions, wherein the historical scheduling management solutions include historical production plans and economic decision-making solutions;

[0036] The step of judging whether it is necessary to adjust the scheduling management scheme corresponding to each group of available training data sets according to each group of available training data sets includes:

[0037] Determine the historical scheduling management plan corresponding to each set of available training data sets according to each set of available training data sets and a preset historical scheduling management plan database;

[0038] Determine a matching combination score of each set of available training data sets and the historical scheduling management scheme corresponding to each set of available training data sets based on each set of available training data sets and the historical scheduling management scheme corresponding to each set of available training data sets;

[0039] According to each matching combination score, it is determined whether the scheduling management plan for the time corresponding to each group of training available data sets needs to be adjusted.

[0040] According to an embodiment of the present invention, the selectively generating a training adjustment plan for operating and scheduling the enterprise economy corresponding to each group of available training data sets and the scheduling management plan for the time corresponding to each group of available training data sets includes:

[0041] Generating a simulation training scheduling management plan that matches the available training data set according to the matching combination score;

[0042] Predict each set of available training data sets to obtain a predicted training multi-source data set corresponding to each set of available training data sets;

[0043] Determine a matching combination score of the predicted training multi-source data set and the training simulation scheduling management scheme corresponding to each group of training available data sets according to the predicted training multi-source data set and the simulation training scheduling management scheme corresponding to each group of training available data sets;

[0044] According to the matching combination scores of the predicted training multi-source data set and the training simulation scheduling management plan corresponding to each group of training available data sets, it is determined whether the historical scheduling management plan needs to be adjusted according to the training simulation scheduling management plan;

[0045] If the answer is yes, then a training adjustment plan for operating and scheduling the enterprise economy corresponding to the available training data set is generated according to the simulation training scheduling management plan, the predicted training multi-source data set and the available training data set.

[0046] According to an embodiment of the present invention, the selectively adjusting the training adjustment scheme for operating and scheduling the enterprise economy corresponding to the training available data set to generate the final training adjustment scheme corresponding to each set of training available data sets includes:

[0047] Simulating according to the available training data set and the training adjustment scheme for operating and scheduling the enterprise economy corresponding to the available training data set, to obtain simulation data corresponding to the training adjustment scheme;

[0048] According to the simulation data and the predicted training multi-source data set, it is determined whether the training adjustment scheme needs to be readjusted:

[0049] If the judgment is yes, then re-execute "selectively generate a training adjustment plan for operating and scheduling the enterprise economy corresponding to each group of available training data sets and the scheduling management plan for the time corresponding to each group of available training data sets";

[0050] If the judgment is no, the training adjustment scheme is used as the final training adjustment scheme corresponding to the available training data set.

[0051] According to an embodiment of the present invention, the multi-source data set is substituted into the analysis scheduling model, so that according to the multi-source data set, it is determined whether the current scheduling management plan needs to be adjusted, and the optimal adjustment plan and the simulation results corresponding to the selected adjustment plan are selected and output, including:

[0052] Preprocessing the multi-source data sets to obtain available data sets, wherein the available data sets include multiple types of available data;

[0053] Determine a matching combination score of the available data set and the current scheduling management plan according to the available data set and the current scheduling management plan, wherein the scheduling management plan includes a production plan and an economic decision plan;

[0054] Selectively generate an adjustment plan for operating and scheduling the enterprise economy according to the matching combination score;

[0055] Perform simulation according to the available data set and the adjustment plan to obtain simulation data corresponding to the adjustment plan;

[0056] According to the simulation data, it is determined whether the adjustment scheme needs to be readjusted:

[0057] If the judgment is yes, then re-execute "selectively generating an adjustment plan for operating and scheduling the enterprise economy according to the matching combination score";

[0058] If the judgment is no, the adjustment scheme is output and the simulation data is used as the simulation result of the adjustment scheme.

[0059] According to an embodiment of the present invention, selectively generating an adjustment plan for operating and scheduling the enterprise economy according to the matching combination score includes:

[0060] selectively generating a simulated scheduling management solution that matches the available data set according to the matching combination score;

[0061] Make predictions on available data sets to obtain predicted multi-source data sets;

[0062] Determine a matching combination score of the predicted multi-source data set and the simulated scheduling management solution according to the predicted multi-source data set and the simulated scheduling management solution;

[0063] Based on the predicted multi-source data set and the matching combination score of the simulated scheduling management plan, determine whether the current scheduling management plan needs to be adjusted according to the simulated scheduling management plan:

[0064] If the answer is yes, then an adjustment plan for operating and scheduling the enterprise economy is generated based on the simulated scheduling management plan, the predicted multi-source data set, and the available data set.

[0065] According to a second aspect of the present invention, there is provided an enterprise economic operation scheduling and management system, the system comprising a data acquisition device, an analysis and scheduling model and a control device, the data acquisition device interacts with different devices within the enterprise, the Internet and market contact devices to realize respective data collection for different devices within the enterprise, the Internet and market contact devices, the analysis and scheduling model stores a preset historical multi-source database and a preset historical scheduling management scheme database, the control device comprises a processor and a memory, the memory is suitable for storing multiple program codes, the program codes are suitable for being loaded and run by the processor to execute the enterprise economic operation scheduling and management method based on big data analysis as described in any one of the technical schemes of the above-mentioned technical schemes of the enterprise economic operation scheduling and management method based on big data analysis.

[0066] It can be seen from the above technical solutions that the enterprise economic operation scheduling management method and system based on big data analysis provided by the present invention have the following beneficial effects:

[0067] The enterprise economic operation scheduling management method and system based on big data analysis provided by the present invention substitutes the acquired multi-source data set into the analysis scheduling model, so that according to the multi-source data set, it is judged whether the current scheduling management plan needs to be adjusted, and the current scheduling situation of the enterprise is determined according to the multi-source data set, and whether the current scheduling management plan needs to be adjusted is independently judged, and the optimal adjustment plan and the simulation results corresponding to the selected adjustment plan are selected and output, so as to optimize the adjustment plan and ensure that the output adjustment plan is the optimal value. Then, according to the decision opinions of multiple decision makers on the adjustment plan and its simulation results, the adjustment plan is selectively adjusted, so as to obtain the subjective opinions of the decision makers of the enterprise on the adjustment plan. The matching degree between the adjustment plan and the enterprise is improved, making the adjustment plan more intelligent. According to the authority level of the personnel, the simulation results corresponding to the adjusted adjustment plan are selectively visualized to ensure that the data and decisions of the enterprise will not be leaked, and the personnel can understand the decision-making effect of the adjustment plan more intuitively, so as to find and correct errors in time, so that the personnel can better understand and accept the new decision-making plan, realize timely and accurate economic operation scheduling, and then optimize the resource allocation of the enterprise, improve the economic benefits of the enterprise, and avoid the technical problems that the management methods of production plans and decision-making plans in the existing technology often lack real-time, dynamic and targetedness, which easily lead to waste of production resources and reduced enterprise benefits. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] The disclosure of the present invention will become more easily understood with reference to the accompanying drawings. It is easy for those skilled in the art to understand that these drawings are only for illustrative purposes and are not intended to limit the scope of protection of the present invention. In addition, similar numbers in the figures are used to represent similar components, among which:

[0069] Figure 1 It is a flowchart of the main steps of a method for enterprise economic operation scheduling management based on big data analysis according to an embodiment of the present invention;

[0070] Figure 2 It is a flowchart of the main steps of a training analysis scheduling model of an enterprise economic operation scheduling management method based on big data analysis according to an embodiment of the present invention;

[0071] Figure 3 It is a schematic diagram of the main structural block diagram of an enterprise economic operation scheduling management system according to an embodiment of the present invention.

[0072] List of reference numerals:

[0073] 300: enterprise economic operation scheduling management system; 301: control device; 3011: processor; 3012: memory; 3013: program code; 302: analysis scheduling model; 3021: historical multi-source database; 3022: historical scheduling management solution database; 303: data acquisition device. DETAILED DESCRIPTION

[0074] Some embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0075] In the description of the present invention, "module" and "processor" may include hardware, software or a combination of the two. A module may include hardware circuits, various suitable sensors, communication ports, and memories, and may also include software parts, such as program codes, or a combination of software and hardware. The processor may be a central processing unit, a microprocessor, an image processor, a digital signal processor, or any other suitable processor. The processor has data and / or signal processing functions. The processor may be implemented in software, hardware, or a combination of the two. Non-temporary computer-readable storage media include any suitable medium that can store program codes, such as a magnetic disk, a hard disk, an optical disk, a flash memory, a read-only memory, a random access memory, and the like. The term "A and / or B" means all possible combinations of A and B, such as only A, only B, or A and B. The term "at least one A or B" or "at least one of A and B" has a similar meaning to "A and / or B", and may include only A, only B, or A and B. The singular terms "one" and "the" may also include plural forms.

[0076] See attached Figure 1 , Figure 1 1 is a flow chart of the main steps of a method for enterprise economic operation scheduling management based on big data analysis according to an embodiment of the present invention. Figure 1 As shown, a method for enterprise economic operation scheduling management based on big data analysis in an embodiment of the present invention mainly includes the following steps S101-S104.

[0077] Step S101: Acquire a multi-source data set, wherein the multi-source data set at least includes internal enterprise data, current policy data, and external data;

[0078] Furthermore, before acquiring the multi-source data set, the method further includes:

[0079] Collecting enterprise internal data in real time, wherein the enterprise internal data at least includes enterprise inventory information, production information, economic distribution information and sales information;

[0080] Based on the collected internal enterprise data, determine whether it matches the current scheduling management plan:

[0081] If the judgment is no, it is determined that the enterprise economic operation scheduling needs to be executed, and the multi-source data set is obtained;

[0082] If the judgment is yes, then the current policy data is collected in real time, wherein the current policy data at least includes policy information and regulatory information;

[0083] Based on the collected current policy data, determine whether there are any changes:

[0084] If the answer is yes, it is determined that the enterprise economic operation scheduling needs to be executed, and the multi-source data set is obtained;

[0085] If the judgment is no, then collect external data in real time, wherein the external data at least includes market demand information and market supply information;

[0086] Based on the collected external data, the acquisition of multi-source datasets is selectively performed.

[0087] Specifically, based on the collected external data, determine whether it is consistent with the current scheduling management plan:

[0088] If the answer is yes, continue to execute "Real-time collection of internal enterprise data" and subsequent steps;

[0089] If the judgment is no, it is determined that the enterprise economic operation scheduling needs to be executed, and the multi-source data set is obtained.

[0090] Step S102: Substituting the multi-source data set into the analysis scheduling model, so as to determine whether the current scheduling management plan needs to be adjusted according to the multi-source data set, and selecting the optimal adjustment plan and the simulation results corresponding to the selected adjustment plan and outputting them;

[0091] Furthermore, before substituting the multi-source data set into the analysis and scheduling model, the method further includes the following steps to train the analysis and scheduling model:

[0092] Acquire multiple sets of multi-source training data sets, wherein each set of multi-source training data sets includes at least one obfuscated data;

[0093] Preprocessing multiple groups of multi-source training data sets to obtain training available data sets corresponding to each group of multi-source training data sets;

[0094] According to the available training data sets corresponding to each group of multi-source training data sets, it is judged whether the data processing training of the analysis scheduling model is successful:

[0095] If the judgment is no, the analysis and scheduling model is adjusted, and the adjusted analysis and scheduling model is retrained;

[0096] If the judgment is yes, then judging whether it is necessary to adjust the scheduling management plan for the time corresponding to each group of available training data sets according to each group of available training data sets;

[0097] According to the judgment result, it is judged whether the adjustment judgment training of the analysis scheduling model is successful:

[0098] If the judgment is yes, then according to each group of available training data sets and the scheduling management plan at the time corresponding to each group of available training data sets, a training adjustment plan for operating and scheduling the enterprise economy corresponding to the available training data sets is selectively generated;

[0099] and selectively adjusting the training adjustment scheme for operating and scheduling the enterprise economy corresponding to the training available data set, to generate a final training adjustment scheme corresponding to each set of training available data sets;

[0100] According to the final training adjustment plan corresponding to each set of training available data sets, judging whether the adjustment plan generation training of the analysis scheduling model is successful;

[0101] According to the training results of each training of the analysis and scheduling model, it is determined whether the analysis and scheduling model is successfully trained.

[0102] Specifically, the analysis and scheduling model stores a preset historical multi-source database, which stores several groups of original multi-source data sets of the enterprise at different times and the historical available data sets corresponding to each group of original multi-source data sets;

[0103] The obtaining of multiple sets of multi-source training data sets comprises:

[0104] According to the preset historical multi-source database, multiple groups of historical multi-source data sets are randomly obtained;

[0105] In multiple sets of historical multi-source data sets, a random number of labeled obfuscated data are randomly added to obtain multiple sets of historical multi-source data sets with obfuscated data;

[0106] Each set of historical multi-source data sets with obfuscated data is used as a multi-source training data set to obtain multiple sets of multi-source training data sets.

[0107] Specifically, the data preprocessing method for preprocessing multiple groups of multi-source training data sets includes data processing and data screening. The data processing method can adopt the data processing method in the prior art, or it can adopt the data processing method of data cleaning, data deduplication, elimination of erroneous or inconsistent data, and data standardization processing in sequence. The screening method of the data screening can adopt a trained neural network model or a trained machine learning model. The selection of the data processing method and the data screening method here is only an exemplary description. In actual testing, technical personnel in this field can make a selection according to actual needs. As long as it is possible to perform data processing on multiple groups of multi-source training data sets to obtain multi-source training data sets in a unified format, and then perform data set screening on the multi-source training data sets in a unified format, and then obtain the training available data set corresponding to each group of multi-source training data sets, it will not be repeated here.

[0108] Specifically, judging whether the data processing training of the analysis scheduling model is successful according to the available training data set corresponding to each group of multi-source training data sets includes:

[0109] Determine, according to each group of multi-source training data sets and a preset historical multi-source database, a historical available data set corresponding to each group of multi-source training data sets;

[0110] According to the available training data sets corresponding to each set of multi-source training data sets, determine whether there is obfuscated data in each available training data set:

[0111] If there is obfuscated data in the training available data set, determining that the training result corresponding to the multi-source training data set is a training failure;

[0112] Otherwise, determining the training result corresponding to the multi-source training data set according to the training available data set corresponding to the multi-source training data set and the historical available data set corresponding to the multi-source training data set;

[0113] Determining the success rate of data processing training of the analysis scheduling model according to the training results corresponding to each group of multi-source training data sets;

[0114] Whether the data processing training of the analysis and scheduling model is successful is judged according to the success rate of the data processing training of the analysis and scheduling model.

[0115] Specifically, determining the training result corresponding to the multi-source training data set according to the training available data set corresponding to the multi-source training data set and the historical available data set corresponding to the multi-source training data set includes:

[0116] If the error value between the training available data set corresponding to the multi-source training data set and the historical available data set corresponding to the multi-source training data set is lower than a preset error value threshold, then the training result corresponding to the multi-source training data set is determined to be training successful;

[0117] Otherwise, it is determined that the training result corresponding to the multi-source training data set is a training failure.

[0118] Specifically, the preset error value threshold may be 1% or 3%. The setting of the preset error value threshold here is only an exemplary description. In actual testing, those skilled in the art may set it according to actual needs, which will not be elaborated here.

[0119] Specifically, judging whether the data processing training of the analysis scheduling model is successful according to the success rate of the data processing training of the analysis scheduling model includes:

[0120] If the success rate of the data processing training of the analysis scheduling model exceeds a preset success rate threshold, determining that the training result of the data processing training of the analysis scheduling model is successful;

[0121] Otherwise, it is determined that the training result of the data processing training of the analysis and scheduling model is training failure.

[0122] Specifically, the preset success rate threshold may be 98% or 95%. The setting of the preset success rate threshold here is only an exemplary description. In actual testing, those skilled in the art may set it according to actual needs, which will not be elaborated here.

[0123] Specifically, the adjustment method for adjusting the analysis and scheduling model can adopt a trained neural network model or a trained machine learning model. The choice of adjustment method here is only an exemplary explanation. In actual testing, technical personnel in this field can make a choice according to actual needs. As long as the analysis and scheduling model can be adjusted and the training results of the adjusted analysis and scheduling model are better than the analysis and scheduling model before the adjustment, it will not be repeated here.

[0124] Specifically, the analytical scheduling model also stores a preset historical scheduling management solution database, which stores historical scheduling management solutions at various moments and selectively existing historical adjustment solutions, wherein the historical scheduling management solutions include historical production plans and economic decision-making solutions;

[0125] The step of judging whether it is necessary to adjust the scheduling management scheme corresponding to each group of available training data sets according to each group of available training data sets includes:

[0126] Determine the historical scheduling management plan corresponding to each set of available training data sets according to each set of available training data sets and a preset historical scheduling management plan database;

[0127] Determine a matching combination score of each set of available training data sets and the historical scheduling management scheme corresponding to each set of available training data sets based on each set of available training data sets and the historical scheduling management scheme corresponding to each set of available training data sets;

[0128] According to each matching combination score, it is determined whether the scheduling management plan for the time corresponding to each group of training available data sets needs to be adjusted.

[0129] Specifically, judging whether it is necessary to adjust the scheduling management scheme corresponding to each group of available training data sets according to each matching combination score includes:

[0130] If the matching combination score is lower than a preset matching combination score threshold, it is determined that the scheduling management plan for the time corresponding to each group of training available data sets needs to be adjusted;

[0131] Otherwise, it is determined that there is no need to adjust the scheduling management scheme for the time corresponding to each group of available training data sets.

[0132] Specifically, judging whether the adjustment determination training of the analysis scheduling model is successful according to the judgment result includes:

[0133] If the judgment result is no, and there is no historical adjustment plan matching the training available data set in the preset historical scheduling management plan database, it is judged that the training result of the adjustment determination training of the analysis scheduling model is successful;

[0134] or,

[0135] If the judgment result is yes, and there is a historical adjustment plan matching the training available data set in the preset historical scheduling management plan database, it is judged that the training result of the adjustment determination training of the analysis scheduling model is successful;

[0136] Otherwise, it is determined that the training result of the adjustment determination training of the analysis and scheduling model is training failure.

[0137] Specifically, the selectively generating a training adjustment plan for operating and scheduling the enterprise economy corresponding to each set of available training data sets and the scheduling management plan at the time corresponding to each set of available training data sets includes:

[0138] Generating a simulation training scheduling management plan that matches the available training data set according to the matching combination score;

[0139] Predict each set of available training data sets to obtain a predicted training multi-source data set corresponding to each set of available training data sets;

[0140] Determine a matching combination score of the predicted training multi-source data set and the training simulation scheduling management scheme corresponding to each group of training available data sets according to the predicted training multi-source data set and the simulation training scheduling management scheme corresponding to each group of training available data sets;

[0141] According to the matching combination scores of the predicted training multi-source data set and the training simulation scheduling management plan corresponding to each group of training available data sets, it is determined whether the historical scheduling management plan needs to be adjusted according to the training simulation scheduling management plan;

[0142] If the judgment is yes, then generating a training adjustment plan for operating and scheduling the enterprise economy corresponding to the available training data set according to the simulation training scheduling management plan, the predicted training multi-source data set and the available training data set;

[0143] If the judgment is no, re-execute "generating a simulation training scheduling management plan matching the available training data set according to the matching combination score" and subsequent steps, and record the number of repetitions;

[0144] If the number of repetitions reaches a preset repetition threshold, it is determined that there is no need to generate a simulation training scheduling management plan that matches the training available data set, and the generation method of the simulation training scheduling management plan is adjusted.

[0145] Specifically, the preset repetition number threshold may be 3 times or 5 times. The setting of the preset repetition number threshold here is only an exemplary description. In actual testing, those skilled in the art may set it according to actual needs, which will not be elaborated here.

[0146] Specifically, the generation method and adjustment method of the simulation training scheduling management plan that matches the available training data set can both adopt a trained neural network model, or can be a trained machine learning model and a neural network model respectively. The selection of the generation method and the adjustment method here is only an exemplary description. In actual testing, technical personnel in this field can make a selection according to actual needs. As long as the generation of the simulation training scheduling management plan that matches the available training data set can be adjusted, and the adjusted simulation training scheduling management plan is better than the simulation training scheduling management plan before the adjustment, and the simulation training scheduling management plan that matches the available training data set can be generated according to the matching combination score, it will not be repeated here.

[0147] Specifically, the selectively adjusting the training adjustment scheme for operating and scheduling the enterprise economy corresponding to the training available data set to generate the final training adjustment scheme corresponding to each set of training available data sets includes:

[0148] Simulating according to the available training data set and the training adjustment scheme for operating and scheduling the enterprise economy corresponding to the available training data set, to obtain simulation data corresponding to the training adjustment scheme;

[0149] According to the simulation data and the predicted training multi-source data set, it is determined whether the training adjustment scheme needs to be readjusted:

[0150] If the judgment is yes, then re-execute "selectively generate a training adjustment plan for operating and scheduling the enterprise economy corresponding to each group of available training data sets and the scheduling management plan for the time corresponding to each group of available training data sets" and subsequent steps;

[0151] If the judgment is no, the training adjustment scheme is used as the final training adjustment scheme corresponding to the available training data set.

[0152] Specifically, the simulation method for simulating the training adjustment plan for operating the enterprise economy according to the training available data set and the training adjustment plan corresponding to the training available data set can adopt the simulation technology in the prior art. The selection of the simulation method here is only an exemplary description. In actual testing, technical personnel in this field can choose according to actual needs. As long as it is possible to simulate the training adjustment plan for operating the enterprise economy according to the training available data set and the training available data set corresponding to the training available data set, and obtain the simulation data corresponding to the training adjustment plan, it will not be repeated here.

[0153] Specifically, judging whether the adjustment scheme generation training of the analysis scheduling model is successful according to the final training adjustment scheme corresponding to each group of available training data sets includes:

[0154] Simulating the historical adjustment scheme that matches the available training data set to obtain simulation data of the historical adjustment scheme that matches the available training data set;

[0155] According to the simulation data of the training adjustment scheme matching the available training data set and the simulation data of the historical adjustment scheme, respectively obtaining a simulation score of the training adjustment scheme matching the available training data set and a simulation score of the historical adjustment scheme;

[0156] If the difference between the simulation score of the training adjustment scheme that matches the training available data set and the simulation score of the historical adjustment scheme reaches a preset difference threshold, it is determined that the training result of the adjustment scheme generation training of the analysis scheduling model is successful;

[0157] Otherwise, it is determined that the training result of the adjustment scheme generation training of the analysis and scheduling model is a training failure.

[0158] Specifically, the method for obtaining the simulation score of the training adjustment scheme that matches the available training data set and the simulation score of the historical adjustment scheme can be to determine the score corresponding to each data value based on each type of data value in the simulation data, and then calculate the sum of all types of data values ​​to obtain it. The choice of the method for obtaining the simulation score here is only an exemplary explanation. In actual testing, technical personnel in this field can make a choice according to actual needs, as long as it can be achieved based on the simulation data of the training adjustment scheme that matches the available training data set and the simulation data of the historical adjustment scheme, the simulation score of the training adjustment scheme that matches the available training data set and the simulation score of the historical adjustment scheme can be obtained respectively, and the method for obtaining the two simulation scores is consistent, which will not be repeated here.

[0159] Specifically, the preset difference threshold may be 5 or 10. The setting of the preset difference threshold here is only an exemplary description. In actual testing, those skilled in the art may set it according to actual needs, which will not be described in detail here.

[0160] Specifically, judging whether the analysis scheduling model is successfully trained according to the training results of each training of the analysis scheduling model includes:

[0161] If the training results of the data processing training, the adjustment determination training, and the adjustment scheme generation training corresponding to the available training data set are all successful training, then the comprehensive training result corresponding to the available training data set is determined to be successful training;

[0162] Otherwise, it is determined that the comprehensive training result corresponding to the training available data set is a training failure;

[0163] Determine the comprehensive training success rate corresponding to all available training data sets according to the comprehensive training results corresponding to each available training data set;

[0164] If the comprehensive training success rate corresponding to all training available data sets exceeds a preset comprehensive training success rate threshold, the training result of the analysis and scheduling model is determined to be training success;

[0165] Otherwise, it is determined that the training result of the analysis and scheduling model is a training failure.

[0166] Specifically, the preset comprehensive training success rate threshold can be 90% or 92%. The setting of the preset comprehensive training success rate threshold here is only an exemplary description. In actual testing, those skilled in the art can set it according to actual needs, which will not be repeated here.

[0167] In the above embodiment, in the model training, by obtaining multiple groups of multi-source training data sets, and each group of multi-source training data sets contains at least one obfuscated data, the generalization ability and robustness of the analysis and scheduling model are improved, and by preprocessing the multiple groups of multi-source training data sets, a training available data set is obtained, and the data preprocessing ability of the analysis and scheduling model is trained, thereby improving the stability and convergence of the analysis and scheduling model, and judging whether the data processing training of the analysis and scheduling model is successful based on the training available data set, and selectively performing retraining based on the judgment result, thereby realizing automatic judgment of the data processing training of the analysis and scheduling model, avoiding waste of training resources, and avoiding excessive In order to solve the phenomenon of fitting and overfitting, a corresponding training adjustment plan is selectively generated according to each group of available training data sets and their corresponding scheduling management plans, and the training adjustment plan is selectively adjusted to generate a final training adjustment plan, thereby optimizing the training adjustment plan and obtaining the final training adjustment plan that best suits the multi-source training data set. Based on the final training adjustment plan, it is determined whether the training of the adjustment plan is successful, thereby automatically verifying the training of the adjustment plan. Based on the training results of each training, it is determined whether the analysis scheduling model is successfully trained, thereby automatically verifying the training results of the analysis scheduling model and improving the accuracy and reliability of the analysis scheduling model.

[0168] Specifically, the multi-source data set is substituted into the analysis scheduling model, so that according to the multi-source data set, it is determined whether the current scheduling management plan needs to be adjusted, and the optimal adjustment plan and the simulation results corresponding to the selected adjustment plan are selected and output including:

[0169] Preprocessing the multi-source data set to obtain a usable data set, wherein the usable data set includes multiple types of available data, wherein the multiple types include internal data of the enterprise, current policies, and external data;

[0170] Determine a matching combination score of the available data set and the current scheduling management plan according to the available data set and the current scheduling management plan, wherein the scheduling management plan includes a production plan and an economic decision plan;

[0171] Selectively generate an adjustment plan for operating and scheduling the enterprise economy according to the matching combination score;

[0172] Perform simulation according to the available data set and the adjustment plan to obtain simulation data corresponding to the adjustment plan;

[0173] According to the simulation data, it is determined whether the adjustment scheme needs to be readjusted:

[0174] If the judgment is yes, then re-execute "selectively generate an adjustment plan for operating and scheduling the enterprise economy according to the matching combination score" and subsequent steps;

[0175] If the judgment is no, the adjustment scheme is output and the simulation data is used as the simulation result of the adjustment scheme.

[0176] Specifically, selectively generating an adjustment plan for operating and scheduling the enterprise economy according to the matching combination score includes:

[0177] selectively generating a simulated scheduling management solution that matches the available data set according to the matching combination score;

[0178] Make predictions on available data sets to obtain predicted multi-source data sets;

[0179] Determine a matching combination score of the predicted multi-source data set and the simulated scheduling management solution according to the predicted multi-source data set and the simulated scheduling management solution;

[0180] Based on the predicted multi-source data set and the matching combination score of the simulated scheduling management plan, determine whether the current scheduling management plan needs to be adjusted according to the simulated scheduling management plan:

[0181] If the judgment is yes, then generating an adjustment plan for operating and scheduling the enterprise economy according to the simulated scheduling management plan, the predicted multi-source data set and the available data set;

[0182] If the judgment is no, then the output does not need to adjust the current scheduling management plan, and the predicted multi-source data set is output as the simulation result of the current scheduling management plan.

[0183] In the above embodiment, in the model processing, the multi-source data set is preprocessed to obtain an available data set, thereby purifying and screening the multi-source data set to obtain useful data. According to the available data set and the current scheduling management plan, the matching combination score of the two is determined, and the matching degree between the current scheduling management plan and the available data set is measured by the matching combination score, that is, the higher the score, the closer the current scheduling management plan is to the ideal state, and vice versa, so that the pros and cons of the current scheduling management plan can be intuitively known. Then, according to the matching combination score, an adjustment plan is selectively generated, and the automatic generation of the scheduling plan is realized. Then, the available data set and the adjustment plan are simulated, and according to the simulation data, it is determined whether to readjust the adjustment plan, thereby realizing the automatic judgment and acquisition of the optimal value of the adjustment plan, thereby realizing real-time adjustment of the scheduling management plan of the enterprise to achieve the best economic benefits, thereby making the operation of the enterprise more efficient and economical.

[0184] Step S103: selectively adjusting the selected adjustment scheme or the analysis scheduling model according to the decision opinions of multiple decision makers on selecting the optimal adjustment scheme and the simulation results corresponding to the selected adjustment scheme;

[0185] Specifically, after the analysis and scheduling model outputs the optimal adjustment scheme and the simulation results corresponding to the selected adjustment scheme, the method further includes:

[0186] Obtaining decision opinions of multiple decision makers in the enterprise on selecting the optimal adjustment plan and the simulation results corresponding to the selected adjustment plan, wherein the decision opinions include at least one of three types of decision opinions: agreeing to the adjustment, opposing the adjustment and the object of opposition, and abstention, wherein the object of opposition is the adjustment plan or the simulation result;

[0187] According to the decision opinions of multiple decision makers on selecting the best adjustment plan and the simulation results corresponding to the selected adjustment plan, the selected adjustment plan or the analysis and scheduling model is selectively adjusted.

[0188] Specifically, selectively adjusting the selected adjustment scheme or the analysis scheduling model according to the decision opinions of multiple decision makers on selecting the optimal adjustment scheme and the simulation results corresponding to the selected adjustment scheme includes:

[0189] If the number of decision-makers who agree to adjust the selected optimal adjustment plan and the simulation results corresponding to the selected adjustment plan reaches a preset threshold of the number of agreed adjustments, the selected adjustment plan will not be adjusted;

[0190] If the number of objections to the selection of the optimal adjustment plan and the simulation results corresponding to the selected adjustment plan among the decision-makers reaches a preset threshold of objections, the selected adjustment plan or the analysis and scheduling model is selectively adjusted based on the proportion of objections corresponding to the objections to the adjustment.

[0191] Specifically, selectively adjusting the selected adjustment plan or analysis scheduling model according to the proportion of the opposed objects corresponding to the opposed adjustment includes:

[0192] If the proportion of adjustment plans among the opposed objects corresponding to the opposed adjustment reaches the preset opposition proportion threshold, the selected adjustment plan is adjusted;

[0193] If the proportion of simulation results among the objections corresponding to the objection adjustment reaches a preset objection proportion threshold, the analysis and scheduling model is adjusted.

[0194] Specifically, the preset agreement number threshold and / or the preset objection number threshold can both be 80% of the total number of decision makers, or can be 70% and 50% respectively. The selection of the preset agreement number threshold and the preset objection number threshold is only an exemplary description. In actual testing, those skilled in the art can make a selection according to actual needs, which will not be elaborated here.

[0195] Specifically, the preset opposition ratio threshold may be 60% or 66%. The selection of the preset opposition ratio threshold here is only an exemplary description. In actual testing, those skilled in the art may make a selection according to actual needs, which will not be elaborated here.

[0196] Step S104: selectively visually displaying the simulation results corresponding to the adjusted adjustment scheme according to the authority level of the personnel.

[0197] Specifically, before selectively visually displaying the simulation results corresponding to the adjusted adjustment scheme according to the authority level of the personnel, the method further includes:

[0198] The simulation results corresponding to the adjustment scheme are divided into levels and regions, and each divided region corresponds to a different management type, and each level region corresponds to a different authority level.

[0199] Specifically, the selectively visualizing the simulation results corresponding to the adjusted adjustment scheme according to the authority level of the personnel includes:

[0200] According to the authority level of the personnel and at least one management type corresponding to the personnel, the divided areas and level areas are visualized accordingly.

[0201] Based on the above steps S101 to S104, by substituting the acquired multi-source data set into the analysis and scheduling model, it is determined whether the current scheduling management plan needs to be adjusted according to the multi-source data set, and the current scheduling situation of the enterprise is determined according to the multi-source data set, and the current scheduling management plan needs to be adjusted. The optimal adjustment plan and the simulation results corresponding to the selected adjustment plan are selected and output, and the adjustment plan is optimized to ensure that the output adjustment plan is the optimal value. Then, according to the decision opinions of multiple decision makers on the adjustment plan and its simulation results, the adjustment plan is selectively adjusted, and the subjective opinions of the decision makers of the enterprise on the adjustment plan are obtained, thereby improving It improves the matching degree between the adjustment plan and the enterprise, makes the adjustment plan more intelligent, and selectively visualizes the simulation results corresponding to the adjusted adjustment plan according to the personnel's authority level to ensure that the enterprise's data and decisions will not be leaked, and allows personnel to more intuitively understand the decision-making effect of the adjustment plan, so as to timely discover and correct errors, so that personnel can better understand and accept new decision-making plans, realize timely and accurate economic operation scheduling, and then optimize the enterprise's resource allocation, improve the enterprise's economic benefits, and avoid the technical problems that the management methods of production plans and decision-making plans in the existing technology often lack real-time, dynamic and targetedness, which easily lead to waste of production resources and reduced enterprise benefits.

[0202] It should be pointed out that although the various steps in the above embodiments are described in a specific order, those skilled in the art can understand that in order to achieve the effects of the present invention, different steps do not have to be performed in such an order, and they can be performed simultaneously (in parallel) or in other orders. These changes are within the scope of protection of the present invention.

[0203] Furthermore, the present invention also provides an enterprise economic operation scheduling and management system.

[0204] See attached Figure 3 , Figure 3 1 is a main structural block diagram of an enterprise economic operation scheduling management system according to an embodiment of the present invention. Figure 3As shown, an enterprise economic operation scheduling management system 300 in the embodiment of the present invention mainly includes a data acquisition device 303, an analysis scheduling model 302 and a control device 301. The data acquisition device 303 interacts with different devices, the Internet and market contact devices within the enterprise to realize the respective data acquisition of different devices, the Internet and market contact devices within the enterprise. The analysis scheduling model 302 stores a preset historical multi-source database 3021 and a preset historical scheduling management solution database 3022. The control device 301 includes a processor 3011 and a memory 3012. The memory 3012 can be configured to store a program code 3013 for executing the enterprise economic operation scheduling management method based on big data analysis of the above method embodiment. The processor 3011 can be configured to execute the program code 3013 in the memory 3012, which includes but is not limited to executing the program code 3013 for the enterprise economic operation scheduling management method based on big data analysis of the above method embodiment. For the convenience of explanation, only the part related to the embodiment of the present invention is shown. For specific technical details not disclosed, please refer to the method part of the embodiment of the present invention. The control device 301 may be a control device including various electronic devices.

[0205] Specifically, the data acquisition device 303 can be various communication devices or data acquisition devices of different communication types. The selection of the data acquisition device 303 here is only an exemplary description. In actual testing, technical personnel in this field can make a selection according to actual needs, as long as information interaction can be achieved between the data acquisition device 303 and different devices within the enterprise, the Internet, and market contact equipment. It will not be repeated here.

[0206] Specifically, the preset historical multi-source database 3021 stores several groups of original multi-source data sets of the enterprise at different times and the historical available data sets corresponding to each group of original multi-source data sets;

[0207] The preset historical scheduling management plan database 3022 stores historical scheduling management plans at various moments and selective historical adjustment plans, wherein the historical scheduling management plans include historical production plans and economic decision-making plans.

[0208] In one implementation, the description of the specific implementation functions may refer to steps S101 to S104.

[0209] The above-mentioned enterprise economic operation scheduling management system 300 is used to execute Figure 1The embodiment of the enterprise economic operation scheduling management method based on big data analysis shown in the figure is similar in technical principles, technical problems solved and technical effects produced. Technical personnel in this technical field can clearly understand that for the convenience and conciseness of description, the specific working process and related instructions of the enterprise economic operation scheduling management system 300 can refer to the contents described in the embodiment of the enterprise economic operation scheduling management method based on big data analysis, which will not be repeated here.

[0210] It is understood by those skilled in the art that the present invention implements all or part of the processes in the method of the above embodiment, and can also be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium, and when the computer program is executed by the processor 3011, the steps of each of the above method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable storage medium may include: any entity or device, medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory, random access memory, electric carrier signal, telecommunication signal and software distribution medium that can carry the computer program code. It should be noted that the content contained in the computer-readable storage medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable storage medium does not include electric carrier signal and telecommunication signal.

[0211] Further, the enterprise economic operation scheduling management system 300 of the present invention also includes a computer-readable storage medium. In a computer-readable storage medium embodiment according to the present invention, the computer-readable storage medium can be configured to store a program code 3013 for executing the enterprise economic operation scheduling management method based on big data analysis of the above-mentioned method embodiment, and the program code 3013 can be loaded and run by the processor 3011 to implement the above-mentioned enterprise economic operation scheduling management method based on big data analysis. For ease of explanation, only the parts related to the embodiment of the present invention are shown. For specific technical details not disclosed, please refer to the method part of the embodiment of the present invention. The computer-readable storage medium can be a memory device formed by various electronic devices. Optionally, the computer-readable storage medium in the embodiment of the present invention is a non-temporary computer-readable storage medium.

[0212] Further, it should be understood that since the setting of each module is only for illustrating the functional units of the device of the present invention, the physical devices corresponding to these modules may be the processor 3011 itself, or a part of the software, a part of the hardware, or a part of the combination of software and hardware in the processor 3011. Therefore, the number of each module in the figure is only schematic.

[0213] Those skilled in the art will appreciate that the modules in the device can be adaptively split or merged. Such splitting or merging of specific modules will not cause the technical solution to deviate from the principle of the present invention, and therefore, the technical solutions after splitting or merging will fall within the protection scope of the present invention.

[0214] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

Claims

1. A method for enterprise economic operation scheduling management based on big data analysis, characterized in that: The method comprises the following steps: Acquire a multi-source data set, wherein the multi-source data set includes at least internal enterprise data, current policy data, and external data; Substitute the multi-source data set into the analysis scheduling model, so that according to the multi-source data set, it is determined whether the current scheduling management plan needs to be adjusted, and the optimal adjustment plan and the simulation results corresponding to the selected adjustment plan are selected and output; According to the decision opinions of multiple decision makers on selecting the best adjustment plan and the simulation results corresponding to the selected adjustment plan, selectively adjust the selected adjustment plan or the analysis and scheduling model; Selectively visualize the simulation results corresponding to the adjusted adjustment scheme according to the personnel's authority level; Before acquiring the multi-source data set, the method further includes: Collecting enterprise internal data in real time, wherein the enterprise internal data at least includes enterprise inventory information, production information, economic distribution information and sales information; Based on the collected internal enterprise data, determine whether it matches the current scheduling management plan: If the judgment is no, it is determined that the enterprise economic operation scheduling needs to be executed, and the multi-source data set is obtained; If the judgment is yes, then the current policy data is collected in real time, wherein the current policy data at least includes policy information and regulatory information; Based on the collected current policy data, determine whether there are any changes: If the answer is yes, it is determined that the enterprise economic operation scheduling needs to be executed, and the multi-source data set is obtained; If the judgment is no, then collect external data in real time, wherein the external data at least includes market demand information and market supply information; Selectively acquire multi-source data sets based on the collected external data; Before substituting the multi-source data set into the analysis scheduling model, the method further includes the following steps of training the analysis scheduling model: Acquire multiple sets of multi-source training data sets, wherein each set of multi-source training data sets includes at least one obfuscated data; Preprocessing multiple groups of multi-source training data sets to obtain training available data sets corresponding to each group of multi-source training data sets; According to the available training data sets corresponding to each group of multi-source training data sets, it is judged whether the data processing training of the analysis scheduling model is successful: If the judgment is no, the analysis and scheduling model is adjusted, and the adjusted analysis and scheduling model is retrained; If the judgment is yes, then judging whether it is necessary to adjust the scheduling management plan for the time corresponding to each group of available training data sets according to each group of available training data sets; According to the judgment result, it is judged whether the adjustment judgment training of the analysis scheduling model is successful: If the judgment is yes, then according to each group of available training data sets and the scheduling management plan at the time corresponding to each group of available training data sets, a training adjustment plan for operating and scheduling the enterprise economy corresponding to the available training data sets is selectively generated; and selectively adjusting the training adjustment scheme for operating and scheduling the enterprise economy corresponding to the training available data set, to generate a final training adjustment scheme corresponding to each set of training available data sets; According to the final training adjustment plan corresponding to each set of training available data sets, judging whether the adjustment plan generation training of the analysis scheduling model is successful; According to the training results of each training of the analysis and scheduling model, it is determined whether the analysis and scheduling model is successfully trained.

2. According to the enterprise economic operation scheduling management method based on big data analysis according to claim 1, it is characterized in that: The analysis and scheduling model stores a preset historical multi-source database, which stores several groups of original multi-source data sets of the enterprise at different times and the historical available data sets corresponding to each group of original multi-source data sets; The obtaining of multiple sets of multi-source training data sets comprises: According to the preset historical multi-source database, multiple groups of historical multi-source data sets are randomly obtained; In multiple sets of historical multi-source data sets, a random number of labeled obfuscated data are randomly added to obtain multiple sets of historical multi-source data sets with obfuscated data; Each group of historical multi-source data sets with obfuscated data is used as a multi-source training data set to obtain multiple groups of multi-source training data sets.

3. The enterprise economic operation scheduling management method based on big data analysis according to claim 2 is characterized in that: The analytical scheduling model also stores a preset historical scheduling management solution database, which stores historical scheduling management solutions at various times and selectively existing historical adjustment solutions, wherein the historical scheduling management solutions include historical production plans and economic decision-making solutions; The step of judging whether it is necessary to adjust the scheduling management scheme corresponding to each group of available training data sets according to each group of available training data sets includes: Determine the historical scheduling management plan corresponding to each set of available training data sets according to each set of available training data sets and a preset historical scheduling management plan database; Determine a matching combination score of each set of available training data sets and the historical scheduling management scheme corresponding to each set of available training data sets based on each set of available training data sets and the historical scheduling management scheme corresponding to each set of available training data sets; According to each matching combination score, it is determined whether the scheduling management plan for the time corresponding to each group of training available data sets needs to be adjusted.

4. The enterprise economic operation scheduling management method based on big data analysis according to claim 3 is characterized in that: The selectively generating a training adjustment plan for operating and scheduling the enterprise economy corresponding to each set of available training data sets according to each set of available training data sets and the scheduling management plan at the time corresponding to each set of available training data sets includes: Generating a simulation training scheduling management plan that matches the available training data set according to the matching combination score; Predict each set of available training data sets to obtain a predicted training multi-source data set corresponding to each set of available training data sets; Determine a matching combination score of the predicted training multi-source data set and the training simulation scheduling management scheme corresponding to each group of training available data sets according to the predicted training multi-source data set and the simulation training scheduling management scheme corresponding to each group of training available data sets; According to the matching combination scores of the predicted training multi-source data set and the training simulation scheduling management plan corresponding to each group of training available data sets, it is determined whether the historical scheduling management plan needs to be adjusted according to the training simulation scheduling management plan; If the answer is yes, then a training adjustment plan for operating and scheduling the enterprise economy corresponding to the available training data set is generated according to the simulation training scheduling management plan, the predicted training multi-source data set and the available training data set.

5. The enterprise economic operation scheduling management method based on big data analysis according to claim 4 is characterized in that: The selectively adjusting the training adjustment scheme for operating and scheduling the enterprise economy corresponding to the training available data set to generate the final training adjustment scheme corresponding to each set of training available data sets includes: Simulating according to the available training data set and the training adjustment scheme for operating and scheduling the enterprise economy corresponding to the available training data set, to obtain simulation data corresponding to the training adjustment scheme; According to the simulation data and the predicted training multi-source data set, it is determined whether the training adjustment scheme needs to be readjusted: If the judgment is yes, then re-execute "selectively generate a training adjustment plan for operating and scheduling the enterprise economy corresponding to each group of available training data sets and the scheduling management plan for the time corresponding to each group of available training data sets"; If the judgment is no, the training adjustment scheme is used as the final training adjustment scheme corresponding to the available training data set.

6. The enterprise economic operation scheduling management method based on big data analysis according to claim 5 is characterized in that: Substituting the multi-source data set into the analysis scheduling model, judging whether the current scheduling management plan needs to be adjusted according to the multi-source data set, and selecting the optimal adjustment plan and the simulation results corresponding to the selected adjustment plan and outputting them include: Preprocessing the multi-source data sets to obtain available data sets, wherein the available data sets include multiple types of available data; Determine a matching combination score of the available data set and the current scheduling management plan according to the available data set and the current scheduling management plan, wherein the scheduling management plan includes a production plan and an economic decision plan; Selectively generate an adjustment plan for operating and scheduling the enterprise economy according to the matching combination score; Perform simulation according to the available data set and the adjustment plan to obtain simulation data corresponding to the adjustment plan; According to the simulation data, it is determined whether the adjustment scheme needs to be readjusted: If the judgment is yes, then re-execute "selectively generating an adjustment plan for operating and scheduling the enterprise economy according to the matching combination score"; If the judgment is no, the adjustment scheme is output and the simulation data is used as the simulation result of the adjustment scheme.

7. The enterprise economic operation scheduling management method based on big data analysis according to claim 6 is characterized in that: The selectively generating an adjustment plan for operating and scheduling the enterprise economy according to the matching combination score includes: selectively generating a simulated scheduling management solution that matches the available data set according to the matching combination score; Make predictions on available data sets to obtain predicted multi-source data sets; Determine a matching combination score of the predicted multi-source data set and the simulated scheduling management solution according to the predicted multi-source data set and the simulated scheduling management solution; Based on the predicted multi-source data set and the matching combination score of the simulated scheduling management plan, determine whether the current scheduling management plan needs to be adjusted according to the simulated scheduling management plan: If the answer is yes, then an adjustment plan for operating and scheduling the enterprise economy is generated based on the simulated scheduling management plan, the predicted multi-source data set, and the available data set.

8. An enterprise economic operation dispatching and management system, characterized in that: The system includes a data acquisition device, an analysis and scheduling model, and a control device. The data acquisition device interacts with different devices within the enterprise, the Internet, and market contact devices to realize respective data acquisition of different devices within the enterprise, the Internet, and market contact devices. The analysis and scheduling model stores a preset historical multi-source database and a preset historical scheduling management solution database. The control device includes a processor and a memory. The memory is suitable for storing multiple program codes. The program code is suitable for being loaded and run by the processor to execute a method for enterprise economic operation scheduling management based on big data analysis as described in any one of claims 1 to 7.

Images