CN111126726A - Intelligent decision multi-target analysis method based on heterogeneous fusion data - Google Patents
Intelligent decision multi-target analysis method based on heterogeneous fusion data Download PDFInfo
- Publication number
- CN111126726A CN111126726A CN201811274544.1A CN201811274544A CN111126726A CN 111126726 A CN111126726 A CN 111126726A CN 201811274544 A CN201811274544 A CN 201811274544A CN 111126726 A CN111126726 A CN 111126726A
- Authority
- CN
- China
- Prior art keywords
- target
- analysis
- scheme
- data
- setting
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 75
- 230000004927 fusion Effects 0.000 title claims abstract description 20
- 238000004364 calculation method Methods 0.000 claims abstract description 28
- 238000005259 measurement Methods 0.000 claims abstract description 26
- 238000000034 method Methods 0.000 claims abstract description 24
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 20
- 238000011161 development Methods 0.000 claims abstract description 20
- 238000011156 evaluation Methods 0.000 claims abstract description 20
- 230000003993 interaction Effects 0.000 claims abstract description 6
- 230000001133 acceleration Effects 0.000 claims description 17
- 239000011159 matrix material Substances 0.000 claims description 9
- 238000012986 modification Methods 0.000 claims description 6
- 230000004048 modification Effects 0.000 claims description 6
- 238000012544 monitoring process Methods 0.000 claims description 6
- 238000013473 artificial intelligence Methods 0.000 claims description 4
- 238000004422 calculation algorithm Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 abstract description 4
- 230000008569 process Effects 0.000 description 7
- 230000006870 function Effects 0.000 description 5
- 238000007405 data analysis Methods 0.000 description 2
- 238000005553 drilling Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012854 evaluation process Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000005065 mining Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 229920001872 Spider silk Polymers 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 238000004883 computer application Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
Abstract
An intelligent decision multi-target analysis method based on heterogeneous fusion data relates to the technical field of multi-target decision. The method comprises the following steps: 1) selecting indexes: the method is divided into two parts, wherein one part is the setting of an analysis index; the other is the setting of interaction conditions. 2) Target measurement and calculation: and acquiring corresponding historical data from the heterogeneous fusion database, analyzing the current latest data and the development speed, and setting corresponding target values for the group of indexes. 3) Target evaluation: and calculating the difference between each comparison scheme and the reference scheme to determine an optimal scheme. 4) Target decomposition: and decomposing the target according to the lower administrative division, calculating the target required to be completed in each lower region to be achieved, and landing the target scheme practically. Compared with the prior art, the method considers the mutual influence and mutual restriction relationship among multiple targets, carries out cooperative processing on the multiple targets as a whole, and provides a more reasonable solution.
Description
Technical Field
The invention relates to the technical field of multi-target decision making, in particular to an intelligent decision multi-target analysis method based on heterogeneous fusion data.
Background
The decision support is to collect all relevant data and information and process the data and the information to provide information for a decision maker and provide basis for the decision maker. The computer decision support system is a computer application system for assisting a decision maker in making decisions in a man-machine interaction mode, and is used for assisting the decision maker in analyzing problems and assisting in decision making.
Currently, there are popular data analysis and decision support applications on the market. The method mainly comprises the following functions:
1. and (6) visualizing the data. And visual elements and graphs are built in, and rich visual effects are realized through data relation definition. The visualization graph comprises conventional graphs such as a line graph, a pie graph, a histogram and the like, and helps a user to understand data.
2. And (6) data conversion. And functions of drilling, linkage and the like are supported in the data viewing process. The user is helped to intuitively master the information overall and obtain the data value.
3. And (6) analyzing the data. The data trend and relevance are discovered and predicted by a user through conventional calculation and definition of mining calculation. Through statistics, drilling, analysis and mining of data, spider-silk trails of the data are mined, and leader decision is assisted.
The analysis and decision support application is mainly characterized in that data is displayed and converted and walked in the data, the granularity of decision support is slightly low, a leader needs to decompose a target by himself, searches for the data according to a specific target, and tries to find a problem and guess the problem from the data. Mainly suitable for single-target decision making. Single objective decision is the decision of a single objective problem that is classified by the number of decision objectives. The method is characterized in that the target is definite and single, and the standard for selecting various feasible schemes is also definite and single. Since the decision-making target and criteria are all single, the comparison and selection of the schemes is easy. For profit decision, the goal is to maximize profit, and the preference can be objectively decided according to the profit value expected by each scheme.
The problems of the existing data analysis and decision making technology are as follows: the analysis and decision is not a function designed for target analysis, and is more biased to put out data, and the data triggers deep thinking of a decision maker, and does not support multi-target measurement and calculation, target decomposition, target evaluation and the like. The prior art is only suitable for the situations of definite target and single target decision, and is not suitable for the situation of balancing common decision of a plurality of targets. In reality, no matter government reform, smart city construction, company development, personal/family life and consumption problems are all multi-target selection and multi-target decision, and are not single targets. The prior art thus still suffers from significant drawbacks.
Disclosure of Invention
In view of the above problems in the prior art, the present invention is to provide an intelligent decision-making multi-objective analysis method based on heterogeneous fusion data. The method considers the mutual influence and mutual restriction relation among multiple targets, carries out cooperative processing on the multiple targets as a whole, and provides a more reasonable solution.
In order to achieve the above object, the technical solution of the present invention is implemented as follows:
an intelligent decision multi-target analysis method based on heterogeneous fusion data comprises the following steps:
1) selecting indexes:
the index selection is divided into two parts, one is the setting of analysis indexes: the method comprises the steps of adding, deleting, modifying and adjusting the indexes; the other is the setting of interaction conditions: including selecting a region directory, setting a default region, and setting whether to display all indicators by default.
2) Target measurement and calculation:
and acquiring corresponding historical data from the heterogeneous fusion database, analyzing the current latest data and the development speed, and setting corresponding target values for the group of indexes.
3) Target evaluation:
each analysis and measurement is temporarily stored as an analysis scheme, one or more analysis schemes are selected during evaluation, one scheme is designated as a reference scheme, and the rest are designated as comparison schemes. Calculating the difference between each comparison scheme and the reference scheme; and determining an optimal scheme according to the gap size.
4) Target decomposition:
after the optimal scheme is determined, the target is decomposed according to lower administrative divisions, the set target to be achieved and the target to be completed in each lower region are calculated, and the target scheme is actually landed.
In the above intelligent decision-making multi-target analysis method, the modification in the analysis index setting includes a display name, whether to prioritize an index.
In the intelligent decision multi-target analysis method, the set target value in the target measurement and calculation adopts the utilization of historical data to establish a time sequence model, a group of targets are measured and calculated according to an artificial intelligence algorithm model and target time, meanwhile, the system automatically calculates the increment of the group of targets and the current latest data and the development speed required by completing the group of targets, and the analysis is stored as an analysis scheme for subsequent evaluation and selection. Setting the target value also adopts starting from the development speed, selecting a group of acceleration rates, calculating the latest speed by the system, and predicting the target which can be realized for a long time. Or switching other acceleration rates, or locally adjusting the acceleration rates, and developing target analysis to form a corresponding analysis scheme.
In the above intelligent decision-making multi-target analysis method, after the target value is set, the system automatically calculates the increment of the set of targets and the current latest data and the development speed required for completing the set of targets by locally adjusting the targets.
In the intelligent decision multi-target analysis method, the target measurement and calculation support sets constraints on target values, increment and development speed according to conditions, a constraint formula is generated in a click mode, common four arithmetic operation symbols and logic operation symbols are supported, and in addition, the constraint formula for acceleration also supports comparison with business acceleration. After the constraint condition is set, when the system carries out target measurement and calculation again, the system firstly detects whether the specified item meets the constraint, and when the specified matrix does not completely meet the constraint, a prompt box pops up to remind modification; when the constraint is satisfied, the system automatically calculates other two matrix values and the satisfied condition of each matrix pair constraint.
In the intelligent decision multi-target analysis method, the target decomposition decomposes the target according to the latest data occupation ratio of each lower region, and simultaneously calculates the development speed required by each region to finish the target, so as to obtain the latest data occupation ratio. Or adjusting the decomposition scheme to locally adjust the ratio, decomposing the target again, storing the decomposition result as the monitoring target of each region, and performing subsequent monitoring evaluation.
As the method is adopted, compared with the prior art, the method has the following advantages that: a plurality of sets of schemes can be generated through multi-objective analysis, the system provides a scheme comparison function, differences between the reference scheme and other schemes are checked through comparison, and the optimal solution is selected from the plurality of sets of schemes by combining the achievement effect of the main objective and the importance degree of influence of other aspects.
The invention is further described with reference to the following figures and detailed description.
Drawings
FIG. 1 is a flow chart of a method of an embodiment of the present invention;
FIG. 2 is a flowchart of target estimation according to an embodiment of the present invention;
FIG. 3 is a flowchart of setting a target in an incremental manner in target measurement and calculation according to an embodiment of the present invention;
FIG. 4 is a flowchart of setting a target in an acceleration manner in target measurement and calculation according to an embodiment of the present invention;
FIG. 5 is a flowchart illustrating a target setting process for setting a target value in target estimation according to an embodiment of the present invention;
FIG. 6 is a flow chart of target evaluation according to an embodiment of the present invention;
FIG. 7 is a target decomposition flow chart of an embodiment of the present invention.
Detailed Description
The invention relates to an intelligent decision multi-target analysis method based on heterogeneous fusion data, which comprises the following steps:
1) selecting indexes:
the index selection is divided into two parts, one is the setting of analysis indexes: the method comprises the steps of adding, deleting, modifying and adjusting the indexes, wherein the modification comprises the display name and whether the indexes are prioritized; the other is the setting of interaction conditions: including selecting a region directory, setting a default region, and setting whether to display all indicators by default.
2) Target measurement and calculation:
and acquiring corresponding historical data from the heterogeneous fusion database, analyzing the current latest data and the development speed, and setting corresponding target values for the group of indexes.
Setting a target value, establishing a time sequence model by using historical data, and measuring and calculating a group of targets according to an artificial intelligence algorithm model and target time. Meanwhile, the system automatically calculates the increment of the group of targets and the current latest data and the development speed required by finishing the group of targets, and stores the analysis as an analysis scheme for subsequent evaluation and selection. Setting the target value also adopts starting from the development speed, selecting a group of acceleration rates, calculating the latest speed by the system, and predicting the target which can be realized for a long time. Or switching other acceleration rates, or locally adjusting the acceleration rates, and developing target analysis to form a corresponding analysis scheme.
After the target value is set, the system automatically calculates the increment of the set of targets and the current latest data and the development speed required for finishing the set of targets by locally adjusting the targets.
The target measurement and calculation support sets constraints on a target value, increment and development speed according to conditions, a constraint formula is generated in a click mode, common four arithmetic symbols and logic arithmetic symbols are supported, and in addition, the constraint formula for acceleration also supports comparison with business acceleration. After the constraint condition is set, when the system carries out target measurement and calculation again, the system firstly detects whether the specified item meets the constraint, and when the specified matrix does not completely meet the constraint, a prompt box pops up to remind modification; when the constraint is satisfied, the system automatically calculates other two matrix values and the satisfied condition of each matrix pair constraint.
3) Target evaluation:
each analysis and measurement is temporarily stored as an analysis scheme, one or more analysis schemes are selected during evaluation, one scheme is designated as a reference scheme, and the rest are designated as comparison schemes. Calculating the difference between each comparison scheme and the reference scheme, and determining an optimal scheme according to the size of the difference.
4) Target decomposition:
after the optimal scheme is determined, the target is decomposed according to lower administrative divisions, the set target to be achieved and the target to be completed in each lower region are calculated, and the target scheme is actually landed.
Decomposing the target according to the latest data occupation ratio of each lower region, and calculating the development speed required by each region to finish the target to obtain the latest data occupation ratio; or adjusting the decomposition scheme to locally adjust the ratio, decomposing the target again, storing the decomposition result as the monitoring target of each region, and performing subsequent monitoring evaluation.
The multi-target analysis product adopting the method is used as a component of an intelligent decision product based on heterogeneous fusion data, and is established on the basis of data resources which are described by unified metadata and are in heterogeneous fusion. Under the support of a big data batch processing engine and a stream processing engine, the convergence and integration of multi-source and mass data are realized; by utilizing artificial intelligence technologies such as natural language processing and machine learning classification algorithms, metadata of data and deep fusion based on service metadata are realized, and finally data resources supporting upper-layer decision support analysis application are formed.
When the method is applied, a multi-target data set comprises four major factors: the system comprises a region, a plurality of target indexes, a target time and a target value of the region target index at the target time. As shown in fig. 1, a region where multi-target analysis is performed and an index list related to the multi-target are set, and a target time of the multi-target analysis is set. This is done in preparation before the specific analysis is performed using the multi-target analysis template, and also supports adjustments during use.
The next major task of the multi-target analysis product is target measurement and calculation, as shown in fig. 2, the target measurement and calculation provides three modes, namely absolute increment, relative acceleration and an absolute target value, and one of the three modes can be selected to complete automatic measurement and calculation of the other two modes. The determination of the measurement and calculation target value needs to be performed through target constraint, and corresponding constraint conditions are set according to the three modes of a single target index to complete the target measurement and calculation process.
Wherein the target value is calculated in an incremental manner, as shown in fig. 3. And in the input process, the system gives a recommended result according to the correlation of historical data among indexes. And (4) finishing primary target measurement and calculation when all the target incremental data are not null.
The target value is measured by the speed increasing method, and as shown in fig. 4, the ring ratio speed increase is used for the speed increase. In addition to incrementally similar import or input mode settings, a mode of referencing historical data or other regional data is supported. Referring to historical speed increase, several groups of speed increase expression modes of business are provided, such as average in the last year, the last three years, the best history, average history and the like, and customization of business speed increase is supported. The reference to other regions may give other regions that are closer in target index set than the current region, or may custom select regions. The centralized modes are mutually exclusive, namely only one mode can be selected to finish the speed increasing setting finally, and the speed increasing of all target indexes is ensured to be not null.
The target value is directly set as shown in fig. 5. Besides adopting an importing mode and an inputting mode, two modes of forecasting and referring to other regions according to historical data are provided. The idea of referring to other areas is similar to that of setting a target value through speed increase, and fine adjustment is performed on the basis of referring to other areas. The more accurate result is given on the basis of the prediction of a plurality of time series methods according to the historical data prediction, and the judgment condition is the difference between the predicted value and the actual value of the historical data. Likewise, it is also guaranteed that the target values of all target indicators are not empty.
After setting in the above ways, the final target value is measured and calculated by performing the measurement and calculation, and the matching condition with the constraint in the target value is given. The measurement and calculation results can be used as a multi-target analysis scheme.
For a variety of multi-target analysis schemes, as shown in FIG. 6. And giving an evaluation flow of the multi-target analysis scheme, and recommending an optimal scheme through the evaluation process. The evaluation process needs to define multi-target analysis schemes and set reference schemes, and through comparison of the multi-schemes on the dimension of an evaluation object, a scheme closest to the reference scheme is found out to be used as a final recommendation scheme, wherein the judgment standard is that the difference between each analysis scheme and the reference scheme is marked on the dimension of the evaluation object.
According to the current national management level, the selected optimal scheme is decomposed into lower regions to perform further multi-objective analysis, as shown in fig. 7. The disaggregation aperture currently only supports a per-region disaggregation. The decomposition idea is mainly to automatically distribute according to the composition proportion of historical data of each region, simultaneously support the fine adjustment of individual regions, automatically redistribute the fine adjustment of individual regions according to the relevance and the proportion condition of the rest regions in order to ensure that the overall target is reached, give a prompt for failing to meet the overall target after distribution, finally complete the decomposition scheme, distribute the decomposed target to subordinate users through the setting of a region user group, and serve as the initial target and the constraint for the subordinate users to execute multi-target analysis.
Therefore, multi-target measurement and calculation, multi-target scheme evaluation and multi-target scheme decomposition at the regional level are completed. The lower level region may further perform analysis, evaluation, and decomposition on the basis of the target given at the upper level, as needed.
The method aims to provide a universal multi-target scientific decision tool for a user to make targets, plan and implement application scenes of work, and a complex multi-target decision process is programmed and streamlined by setting multi-target conditions and constraints, measuring and calculating target values, recommending a multi-target analysis scheme and decomposing the flow of the multi-target analysis scheme in regional dimensions.
The multi-target analysis product is divided into two modules of configuration management and analysis example display. The configuration management mainly completes the setting of the personalized parameters of the analysis examples, the content of the analysis example display template and the analysis interaction according to the operation of the user.
The target measuring and calculating part mainly achieves the purpose of setting any two and calculating a third party based on the function relation among latest data (including historical data) of multiple indexes, targets or increment and speed increase. And checking and constraining the operation process and the operation result through a constraint formula. The target decomposition part utilizes the past data and is matched with the intelligence of a user to set a reasonable proportioning relation for the subordinate region. The system automatically completes the decomposition of the target and the calculation of the speed increase required by the lower-level region to reach the target.
In a word, as an important component of an intelligent decision support product system based on big data, the multi-target analysis product is characterized in that various complex operations and integrated mass statistics and machine learning algorithms are executed, in order to achieve a high-efficiency measuring and calculating effect, an R environment is selected as a measuring and calculating core of a multi-target analysis template and is used as a calculating brain of multi-target analysis, and powerful calculation support and powerful scientific basis are provided for multi-target decision of a user.
Claims (6)
1. An intelligent decision multi-target analysis method based on heterogeneous fusion data comprises the following steps:
1) selecting indexes:
the index selection is divided into two parts, one is the setting of analysis indexes: the method comprises the steps of adding, deleting, modifying and adjusting the indexes; the other is the setting of interaction conditions: selecting a region directory, setting a default region and setting whether to display all indexes by default;
2) target measurement and calculation:
acquiring corresponding historical data from the heterogeneous fusion database, analyzing the current latest data and development speed, and setting corresponding target values for the group of indexes;
3) target evaluation:
each time of analysis and measurement is temporarily stored as an analysis scheme, one or more analysis schemes are selected during evaluation, one scheme is designated as a reference scheme, the rest are designated as comparison schemes, and the difference between each comparison scheme and the reference scheme is calculated; determining an optimal scheme according to the difference;
4) target decomposition:
after the optimal scheme is determined, the target is decomposed according to lower administrative divisions, the set target to be achieved and the target to be completed in each lower region are calculated, and the target scheme is actually landed.
2. The intelligent decision-making multi-objective analysis method based on heterogeneous fusion data of claim 1, wherein the modification in the analysis index setting includes display name, priority index or not.
3. The intelligent decision multi-target analysis method based on heterogeneous fusion data as claimed in claim 1, wherein the set target value in the target calculation is calculated by using historical data to establish a time series model, a group of targets are calculated according to an artificial intelligence algorithm model and target time, meanwhile, the system automatically calculates the increment of the group of targets and the current latest data and the development speed required by completing the group of targets, and the analysis is stored as an analysis scheme for subsequent evaluation and selection; setting a target value by starting from the development speed, selecting a group of acceleration rates, calculating the latest speed by a system, and predicting the target which can be realized for a long time; or switching other acceleration rates, or locally adjusting the acceleration rates, and developing target analysis to form a corresponding analysis scheme.
4. The intelligent decision-making multi-target analysis method based on heterogeneous fusion data according to claim 1 or 3, wherein after the target value is set, the system automatically calculates the increment between the set of targets and the current latest data and the development speed required for completing the set of targets by locally adjusting the targets.
5. The intelligent decision multi-target analysis method based on heterogeneous fusion data as claimed in claim 4, wherein the target measurement and calculation support sets constraints on target values, increment and development speed according to conditions, a constraint formula is generated in a click mode, common four operation symbols and logic operation symbols are supported, and in addition, the constraint formula for acceleration also supports comparison with business acceleration; after the constraint condition is set, when the system carries out target measurement and calculation again, the system firstly detects whether the specified item meets the constraint, and when the specified matrix does not completely meet the constraint, a prompt box pops up to remind modification; when the constraint is satisfied, the system automatically calculates other two matrix values and the satisfied condition of each matrix pair constraint.
6. The intelligent decision multi-target analysis method based on heterogeneous fusion data as claimed in claim 1, wherein the target decomposition decomposes the target according to the latest data occupation ratio of each lower level region, and calculates the development speed required by each region to complete the target to obtain the latest data occupation ratio; or adjusting the decomposition scheme to locally adjust the ratio, decomposing the target again, storing the decomposition result as the monitoring target of each region, and performing subsequent monitoring evaluation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811274544.1A CN111126726A (en) | 2018-10-30 | 2018-10-30 | Intelligent decision multi-target analysis method based on heterogeneous fusion data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811274544.1A CN111126726A (en) | 2018-10-30 | 2018-10-30 | Intelligent decision multi-target analysis method based on heterogeneous fusion data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111126726A true CN111126726A (en) | 2020-05-08 |
Family
ID=70484144
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811274544.1A Pending CN111126726A (en) | 2018-10-30 | 2018-10-30 | Intelligent decision multi-target analysis method based on heterogeneous fusion data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111126726A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113792887A (en) * | 2021-09-16 | 2021-12-14 | 平安资产管理有限责任公司 | Component analysis method, device and equipment based on intelligent decision and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0602673A2 (en) * | 1992-12-18 | 1994-06-22 | Hughes Aircraft Company | System and method for allocating resources |
| US20030167265A1 (en) * | 2001-06-07 | 2003-09-04 | Corynen Guy Charles | Computer method and user interface for decision analysis and for global system optimization |
| CN103295079A (en) * | 2013-06-09 | 2013-09-11 | 国家电网公司 | Electric power multi-objective decision support method based on intelligent data mining model |
| CN103577942A (en) * | 2013-11-27 | 2014-02-12 | 中国水利水电科学研究院 | Decision support system and method for coordinated development of water resources and economy |
| CN103699940A (en) * | 2013-11-27 | 2014-04-02 | 中国科学院大学 | Spatial-division multi-objective optimized decision-making method based on scenarios |
| CN105447585A (en) * | 2014-08-23 | 2016-03-30 | 沈阳东大自动化有限公司 | Ore dressing production full-flow comprehensive production index optimization decision-making system |
| CN106570567A (en) * | 2016-10-26 | 2017-04-19 | 国家电网公司 | Main network maintenance multi-constraint multi-target evaluation expert system and optimization method |
-
2018
- 2018-10-30 CN CN201811274544.1A patent/CN111126726A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0602673A2 (en) * | 1992-12-18 | 1994-06-22 | Hughes Aircraft Company | System and method for allocating resources |
| US20030167265A1 (en) * | 2001-06-07 | 2003-09-04 | Corynen Guy Charles | Computer method and user interface for decision analysis and for global system optimization |
| CN103295079A (en) * | 2013-06-09 | 2013-09-11 | 国家电网公司 | Electric power multi-objective decision support method based on intelligent data mining model |
| CN103577942A (en) * | 2013-11-27 | 2014-02-12 | 中国水利水电科学研究院 | Decision support system and method for coordinated development of water resources and economy |
| CN103699940A (en) * | 2013-11-27 | 2014-04-02 | 中国科学院大学 | Spatial-division multi-objective optimized decision-making method based on scenarios |
| CN105447585A (en) * | 2014-08-23 | 2016-03-30 | 沈阳东大自动化有限公司 | Ore dressing production full-flow comprehensive production index optimization decision-making system |
| CN106570567A (en) * | 2016-10-26 | 2017-04-19 | 国家电网公司 | Main network maintenance multi-constraint multi-target evaluation expert system and optimization method |
Non-Patent Citations (1)
| Title |
|---|
| 刘洪波等, 天津大学出版社 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113792887A (en) * | 2021-09-16 | 2021-12-14 | 平安资产管理有限责任公司 | Component analysis method, device and equipment based on intelligent decision and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108846517B (en) | Integration method for predicating quantile probabilistic short-term power load | |
| Zhang et al. | A framework for passengers demand prediction and recommendation | |
| Singh et al. | Justification for the selection of a reconfigurable manufacturing system: a fuzzy analytical hierarchy based approach | |
| CN108764663A (en) | A kind of power customer portrait generates the method and system of management | |
| CN109711865A (en) | A method of prediction is refined based on the mobile radio communication flow that user behavior excavates | |
| CN107908606A (en) | Method and system based on different aforementioned sources automatic report generation | |
| CN109034469A (en) | A kind of tourist flow prediction technique based on machine learning | |
| CN111709613A (en) | Task automatic allocation method and device based on data statistics and computer equipment | |
| CN108536652A (en) | A kind of short-term vehicle usage amount prediction technique based on arma modeling | |
| CN112734284B (en) | Flow industrial energy consumption optimization decision system and method for improving accuracy of evaluation result | |
| CN111831704A (en) | Abnormal data determination method and device, storage medium and electronic equipment | |
| CN105677625B (en) | Processing method is made a report in the collaboration of multi-layer collect statistics report | |
| Jing et al. | An integrated product conceptual scheme decision approach based on Shapley value method and fuzzy logic for economic-technical objectives trade-off under uncertainty | |
| CN109816157A (en) | Project plan optimization method, device, computer equipment and storage medium | |
| CN114742481A (en) | Special steel performance evaluation method and system based on components | |
| CN113807004A (en) | Tool life prediction method, device and system based on data mining | |
| CN111126726A (en) | Intelligent decision multi-target analysis method based on heterogeneous fusion data | |
| Skvortsova et al. | Study of the possibility of applying intellectual methods in creating risk analysis decision support system in the socio-economic sphere | |
| CN113095680A (en) | Evaluation index system and construction method of electric power big data model | |
| CN111859787A (en) | Daily runoff forecasting method based on coupling of meteorological hydrological forecasting factor classification and deep learning model | |
| CN112148942A (en) | Business index data classification method and device based on data clustering | |
| Ervural et al. | A novel multiple attribute group decision making methodology based on intuitionistic fuzzy TOPSIS | |
| CN113034033B (en) | Method for determining variety of newly-researched equipment spare parts | |
| CN114519073A (en) | Product configuration recommendation method and system based on atlas relation mining | |
| WO2020225959A1 (en) | Design assistance system, design assistance method, and design assistance program |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20200508 |