CN113344085A - Balanced-bias multi-source data collaborative optimization and fusion method and device - Google Patents
Balanced-bias multi-source data collaborative optimization and fusion method and device Download PDFInfo
- Publication number
- CN113344085A CN113344085A CN202110667243.0A CN202110667243A CN113344085A CN 113344085 A CN113344085 A CN 113344085A CN 202110667243 A CN202110667243 A CN 202110667243A CN 113344085 A CN113344085 A CN 113344085A
- Authority
- CN
- China
- Prior art keywords
- data
- fusion
- information
- module
- storage module
- 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.)
- Granted
Links
- 238000005457 optimization Methods 0.000 title claims abstract description 30
- 238000007500 overflow downdraw method Methods 0.000 title claims abstract description 23
- 238000003860 storage Methods 0.000 claims abstract description 49
- 230000004927 fusion Effects 0.000 claims abstract description 42
- 238000000034 method Methods 0.000 claims abstract description 11
- 239000013598 vector Substances 0.000 claims description 5
- 238000007499 fusion processing Methods 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 238000013528 artificial neural network Methods 0.000 claims description 2
- 230000001174 ascending effect Effects 0.000 claims description 2
- 238000010801 machine learning Methods 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 5
- 238000007405 data analysis Methods 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000007418 data mining Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a balanced biased multi-source data collaborative optimization and fusion method and a device, wherein the method comprises the following steps: (1) collecting data s for each data provideriAnd the data type information contained therein, and data siCost information b ofi(ii) a (2) Adopting a multi-attribute combined truth value discovery algorithm for the collected data; (3) according to data siThe difference of the included data kind information to all data siGrouping the belonged to S; (4) determining a selected data set using a data-optimized BPMG-M algorithm
(5) Data S to be selectedwAnd inputting the data into a data fusion module for data fusion. The device comprises a master control scheduling module, a data information storage module, a data fusion parameter storage module and the like. The invention provides a balanced biased multi-source data collaborative optimization and fusion method and a data collaboration by utilizing a combinatorial optimization and machine learning methodAnd the optimization and fusion device realizes the optimization target of the balance bias data and the data fusion of the multi-source high-quality data.
Description
Technical Field
The invention belongs to the field of data mining, and particularly relates to a data optimization and fusion method, in particular to a multi-source data collaborative optimization and fusion method and device capable of balancing bias.
Background
In recent years, data mining has attracted great attention in the information industry, mainly because of the large amount of data generated in the real world, the wide spread use of the data, and the urgent need to convert the data into useful information and knowledge. The information and knowledge obtained can be used in a wide variety of applications including business management, production control, market analysis, engineering and scientific exploration, among others. In today's data analysis scenario, the following two key issues are still faced:
on one hand, with the continuous development of social environment, data has more and more complexity and diversity, and especially data sources and data information types have diversity as well. For example, in a city perception environment, different environmental information such as temperature, humidity, illumination and the like can be collected in the same area; meanwhile, different data providers (data sources) can simultaneously acquire different types of data information due to the range of activities and the diversity of devices used. In order to reduce the deviation caused by using a single type of data in the data analysis process, a data analyzer needs to select diversified representative data information (for example, balance the selection quantity of different types of data information).
On the other hand, the data fusion can adopt a fusion method for multi-source data so as to further improve the accuracy of data analysis. Information fusion is a multi-level and multi-aspect process that detects, combines, correlates, estimates, and combines multi-source data to achieve accurate state estimation. After the preferred multi-source data is obtained, a data fusion method capable of fully utilizing the characteristics of the multi-source data is urgently required.
Based on the problems, a data service platform is urgently required to design a multi-source data collaborative optimization and fusion method and device capable of balancing bias.
Disclosure of Invention
The technical problem to be solved by the invention is to provide a balanced biased multi-source data collaborative optimization and fusion method, which is designed while considering factors such as data information diversity, data source and data cost difference, budget limitation and the like, and can optimize the minimum value of the data information selection ratio corresponding to each data type and perform data fusion on the optimized multi-source data.
In order to solve the technical problem, the invention provides a balanced biased multi-source data collaborative optimization and fusion method, which comprises the following steps:
(1) collecting data si which can be provided by each data provider and data type information contained in the data si, and if the data si contains j (j is more than or equal to 1 and less than or equal to m) type data, GjE.g. G put into set
And requires holding data siProvide cost information b of the datai；
(2) The accuracy of the collected data is improved by adopting a multi-attribute combined truth value discovery algorithm;
(3) according to data siThe difference of the included data kind information to all data siE, grouping by S: assuming that there are m data in total, if data siContaining j type data, put it into j data group and put it into set GjBelongs to G;
(4) decision of selected data set using data-optimized BPMG-M algorithm with balanced bias
(5) Data S to be selectedwInputting the data into a data fusion module for data fusion;
wherein S ═ { S ═ S1,s2,s3,…,snThe current data set; gjIs a data group containing j (1 is not less than j not more than m) type data; g ═ G1,G2,G3,…,GnThe data groups are all collected;
as data siA data group set corresponding to the contained data type; swIs the final selected data set.
The BPMG-M algorithm used in the step (4) is specifically as follows:
a) ordering all data costs from low to high first, e.g. b1≤b2≤…≤bnWith the simultaneous data sequence being(s)1,s2,…,sn). By using
Indicating the selection ratio of the j-class data. Then, an integer programming method is proposed, which is able to perform on a given set of data
In the case of (2), the minimum value of the selection ratio of each set of data, i.e., maxmin, is maximized1≤j≤mrj. Then modeling the planning problem into a maximum flow network (Max-Flownetworks) model, solving the integer planning in polynomial time by adopting a maximum flow algorithm (Max-FlowAlgorithm), and using Xm(sh) Represents the sum of the solution results rm(sh) Representing the minimum selection ratio among different data groups and calculating the total data amount to be selected at the time
b) A candidate data set is then determined, for any subset of data
According to the step a) calculatingFm(si) Find data skSatisfies bk·Fm(sk) B and B are not more thank+1·Fm(sk+1)>B. If the data subset is present
Is selected at a ratio rm(sk) Less than a target value r*Then, the current budget is increased to B' ═ 1+ α) B, and the satisfaction of B is calculated againk·Fm(sk) B' and B are not more thank+1·Fm(sk+1)>Data s of B' conditionkThis operation is performed until the target selection ratio is reached. If rm(sk) Reaches the target value r*Then determine the current data subset
Is a set of alternative data.
c) Determining the final selected data set by first determining each piece of data siA unique weight value, and then collecting the candidate data
In (3), selecting the subset with the smallest sum of weights
So as to satisfy the condition that the number of data selected from each group of data is at least
The fusion method in the step (5) specifically comprises the following steps: data S to be selectedwSeparately input Embedded representation network NwExtracting features, normalizing the extracted feature vectors, and fusing the network N by using parametersFAnd performing feature fusion, and finally outputting the fused data features.
In addition, the invention also provides a balanced biased multi-source data collaborative optimization and fusion device, which is used for the balanced biased multi-source data collaborative optimization and fusion method, and comprises a main control scheduling module, an input module, an output module and a plurality of storage modules, wherein the input module, the output module and the plurality of storage modules are all connected with the main control scheduling module, and the device is characterized in that: the plurality of storage modules comprise a data information storage module and a data fusion parameter storage module, wherein the data information storage module needs to acquire cost information of all data and data type information contained in each piece of data; and the main control module is used for sequencing the cost information of all the data in an ascending order, grouping the data according to different data types, storing the grouped structure in the data information storage module, and calling the data information and other storage modules by the BPMG-M algorithm in the step (4). The data fusion parameter storage module is used for storing parameter setting information in the data fusion process.
As a further improvement of the present invention, the data cooperation, optimization and fusion device further includes an alternative data set storage module and a data selection storage module, where the alternative data set storage module is used to store the alternative data set obtained by calculation in step (4); and the data selection storage module is used for storing the data set finally selected in the step (4).
The invention has the beneficial effects that: in a data analysis scene facing multi-source data, factors such as data information diversity, data source and data cost difference, budget limitation and the like are considered, a balanced biased multi-source data collaborative optimization and fusion method and a data collaborative optimization and fusion device are invented, and the goal of optimizing the minimum value of data selection ratio among different data groups and the fusion of multi-source optimized data are achieved.
Drawings
Fig. 1 is a schematic structural diagram of a data collaboration optimization and fusion system proposed by the present invention.
FIG. 2 is a schematic diagram of a balanced biased multi-source data collaborative optimization and fusion method provided by the present invention.
Fig. 3 is a schematic diagram of a data fusion module according to the present invention.
Fig. 4 is a schematic diagram of a data cooperation optimization and fusion device according to the present invention.
Detailed Description
The present invention will be further illustrated with reference to the accompanying drawings and specific embodiments, which are to be understood as merely illustrative of the invention and not as limiting the scope of the invention.
Fig. 1 is a schematic diagram of a data collaboration optimization and fusion system according to the present invention, wherein a data service platform has a plurality of data providers for providing raw data information. The raw data provided by each data provider may contain different types of data information. For example, in an urban sensing environment, different mobile devices may be equipped with different sensors, such as a temperature sensor, a humidity sensor, and a light sensor, and can simultaneously sense different types of data information in the environment. The data service platform firstly collects the data cost of all data providers and the original data information thereof, then inputs all the information to the designed balanced biased multi-source data collaborative optimization and fusion device, and outputs the selected data and the fused data.
As shown in fig. 2, the present invention provides a balanced biased multi-source data collaborative optimization and fusion method, which includes the following steps:
(1) collecting data s that each data provider can provideiAnd the data type information contained therein, if the data siIncluding j (j is more than or equal to 1 and less than or equal to m) class data, then G is addedjE.g. G put into set
And requires holding data siProvide cost information b of the datai；
(2) The accuracy of the collected data is improved by adopting a multi-attribute combined truth value discovery algorithm;
(3) according to data siThe difference of the included data kind information to all data siE, grouping by S: assuming that there are m data in total, if data siContaining j type data, put it into j data group and put it into set GjBelongs to G;
(4) decision of selected data set using data-optimized BPMG-M algorithm with balanced bias
(5) Data S to be selectedwInputting the data into a data fusion module for data fusion;
wherein S ═ { S ═ S1,s2,s3,…,snThe current data set; gjIs a data group containing j (1 is not less than j not more than m) type data; g ═ G1,G2,G3,…,GnThe data groups are all collected;
as data siA data group set corresponding to the contained data type; swIs the final selected data set.
First, data s that each data provider can provide is requirediAnd the data type information contained therein, if the data siIncluding j (j is more than or equal to 1 and less than or equal to m) class data, then G is addedjE.g. G put into set
And requires holding data siProvide cost information b of the datai。
Then, a multi-attribute combined true value discovery algorithm is adopted for the collected data, the algorithm is used for fitting abnormal data by adopting a local linear regression method, and a strategy of missing value interpolation is used for repairing abnormal values, so that the robustness of the data is further improved;
then according to the data siThe difference of the included data kind information to all data siE, grouping by S: assuming that there are m data in total, if data siContaining j type data, put it into j data group and put it into set GjBelongs to G; at the same time have a radical G1∪G2∪…∪Gm＝S。
And then using BPMG-M algorithm to decide selectionData collection
The BPMG-M algorithm has the main function of selecting data information of different data types in a balanced manner on the premise of considering the diversity of data sources so as to reduce the model deviation caused by the simplification of the data types during data fusion.
The BPMG-M algorithm comprises the following specific steps: a) ordering all data costs from low to high first, e.g. b1≤b2≤…≤bnWith the simultaneous data sequence being(s)1,s2,…,sn). By xiE {0,1} represents data siWhether or not to be selected, simultaneously
Indicating the selection ratio of the j-class data. The method then proposes an integer programming method which enables to define a given set of data
In the case of (2), the minimum value of the selection ratio of each set of data, i.e., maxmin, is maximized1≤j≤mrj. The specific plan is expressed as follows:
wherein n isjIndicating the amount of j-type data that all data providers are able to provide. Then modeling the planning problem into a maximum flow network (Max-Flownetworks) model, and solving the problem in polynomial time by adopting a maximum flow algorithm (Max-FlowAlgorithm)Solving the above integer program by Xm(sh) Represents the sum of the solution results rm(sh) Representing the minimum selection ratio between different data sets, i.e.
xi∈Xm(sh). Based on the selection ratio rm(sh) Calculating the total amount of data to be selected at that time
b) An alternative data set is then determined. For arbitrary subsets of data
Calculating F according to step a)m(si) Find data skSatisfies bk·Fm(sk) B and B are not more thank+1·Fm(sk+1)>B. If the data subset is present
Is selected at a ratio rm(sk) Less than a target value r*Then, the current budget is increased to B' ═ 1+ α) B, and the satisfaction of B is calculated againk·Fm(sk) B' and B are not more thank+1·Fm(sk+1)>Data s of B' conditionkThis operation is performed until the target selection ratio is reached. If rm(sk) Reaches the target value r*Then determine the current data subset
Is a set of alternative data.
c) Second, the final selected data set is determined. First of all given to each data siA weight value
Wherein z isi∈N+Is any positive integer, fullData of any two footiAnd si′With different weights, i.e.
And then from the alternative data set
In (3), selecting the subset with the smallest sum of weights
So as to satisfy the condition that the number of data selected from each group of data is at least
Can be planned with the following integers
Represents:
by using
Representing the solution of the integer program described above. For data siIf, if
Then the data is readsiJoin selected data set Sw。
Finally the selected data SwAnd carrying out data fusion. The specific method comprises the following steps: inputting the preferred data in the data group into the embedded representation network NwExtracting features, normalizing the extracted feature vectors, and fusing the network N by using parametersFAnd performing feature fusion, and finally outputting the fused data features.
As shown in fig. 3, the present invention further provides a data cooperation optimizing and merging device, which is used for the data cooperation optimizing and merging method described above, and includes a master control scheduling module, an input module, an output module, and a plurality of storage modules, where the input module, the output module, and the plurality of storage modules are all connected to the master control scheduling module. The storage module comprises a data information storage module, an alternative data set storage module, a data selection storage module and a data fusion parameter storage module.
The input module is used for receiving data from outside the device, and the received data comprises cost and data type information of all data providers. The input module may be an input device formed by various existing input interfaces, such as a keyboard or the like for providing user input, or a transmission port for obtaining data from another device.
The main control module is used for firstly sequencing the data cost information of all data providers according to the information received by the input module, storing the result and all input information into the data information storage module and transmitting the final result to the output module. The main control module can be realized by various computing elements with digital computing capability, such as a CPU, a DSP and the like. The specific operation of the main control module will be described in detail below.
The output module is used for receiving the scheduling result from the main control module and outputting the scheduling result to the outside of the device. The output module can be various data input devices, such as a display device, an external data storage device and the like.
The data information storage module is used for storing data cost and data type information of a data provider.
The data fusion parameter storage module is used for storing neural network parameters adopted in the data fusion process. The parameters are also input and stored through the input module under the control of the main control module.
The alternative data set storage module is used for storing alternative data sets. This set determines from which data the data that is ultimately input into the fusion algorithm is determined.
The data selection storage module is used for storing a data provider set of the selected data.
The main control module is a core module of the invention and is a key step for executing the data cooperation optimization and fusion method of the invention. First, after the input device receives all data information, the main control module performs the step (1) of the method to collect data that each data provider can provide, data category information included therein, and cost information of the data, and stores the information in the data information storage module. Then, the main control module executes the step (2) of the invention, and a multi-attribute combined truth value discovery algorithm is adopted for the collected data to improve the accuracy of the data; then, the main control module executes the step (3) of the invention, groups all the data according to the difference that the data provided by the data provider contains data information types, and simultaneously stores the grouping result in the data information storage module. Then according to step (4) of the present invention, a data-preferred BPMG-M algorithm is performed: firstly, sorting the cost information of the data from low to high, and storing the sorting result in a data information storage module; computing a set of devices for a target device from data information and ranking information
The optimum selection ratio of (a); a candidate data set that satisfies the condition is then calculated
And storing the data into an alternative data set storage module; calculating a data set with a final selection input into the fusion algorithm by using a formula (4) from the alternative data set, and storing the data set into a data selection storageAnd (5) modules. Finally, according to step (5) of the invention, the selected data S are processedwSeparately input Embedded representation network NwExtracting features, normalizing the extracted feature vectors, and fusing the network N by using parametersFAnd performing feature fusion, and finally outputting the fused data features.
Claims (5)
1. A balanced biased multi-source data collaborative optimization and fusion method is characterized by comprising the following steps:
(1) collecting data s that each data provider can provideiAnd the data type information contained therein, if the data siIncluding j (j is more than or equal to 1 and less than or equal to m) class data, then G is addedjE.g. G put into set
And requires holding data siProvide cost information b of the datai；
(2) The robustness of the data is further improved by adopting a multi-attribute combined truth value discovery algorithm for the collected data;
(3) according to data siThe difference of the included data kind information to all data siE, grouping by S: assuming that there are m data in total, if data siContaining j type data, put it into j data group and put it into set GjBelongs to G;
(4) decision of selected data set using data-optimized BPMG-M algorithm with balanced bias
(5) Data S to be selectedwInputting the data into a data fusion module for data fusion;
wherein S ═ { S ═ S1,s2,s3,...,snThe current data set; gjIs a data group containing j (1 is not less than j not more than m) type data; g ═ G1,G2,G3,...,GnThe data groups are all collected;
as data siA data group set corresponding to the contained data type; swIs the final selected data set.
2. The balanced-biased multi-source data collaborative optimization and fusion method according to claim 1, characterized in that: the BPMG-M algorithm used in the step (4) is specifically as follows:
a) ordering all data costs from low to high first, b1≤b2≤…≤bnWith the simultaneous data sequence being(s)1,s2,…,sn) By using
Expressing the selection ratio of the j-class data, and then proposing an integer programming method capable of providing a given data set
In the case of (2), the minimum value of the selection ratio of each set of data, i.e., maxmin, is maximized1≤j≤mrj. Then modeling the planning problem into a maximum flow network model, solving the integer planning in polynomial time by adopting a maximum flow algorithm, and using Xm(sh) Represents the sum of the solution results rm(sh) Representing the minimum selection ratio among different data groups and calculating the total data amount to be selected at the time
b) A candidate data set is then determined, for any subset of data
Calculating F according to step a)m(si) Find data skSatisfies bk·Fm(sk) B and B are not more thank+1·Fm(sk+1)>B. If the data subset is present
Is selected at a ratio rm(sk) Less than a target value r*Then, the current budget is increased to B' ═ 1+ α) B, and the satisfaction of B is calculated againk·Fm(sk) B' and B are not more thank+1·Fm(sk+1)>Data s of B' conditionkThis operation is performed until the target selection ratio is reached. If rm(sk) Reaches the target value r*Then determine the current data subset
Is an alternative data set;
c) determining the final selected data set by first determining each piece of data siA unique weight value, and then collecting the candidate data
In (3), selecting the subset with the smallest sum of weights
So as to satisfy the condition that the number of data selected from each group of data is at least
3. The balanced-biased multi-source data collaborative optimization and fusion method according to claim 1, characterized in that: the fusion method in the step (5) specifically comprises the following steps: data S to be selectedwSeparately input Embedded representation network NwExtracting features, normalizing the extracted feature vectors, and fusing the network N by using parametersFAnd performing feature fusion, and finally outputting the fused data features.
4. A balanced biased multi-source data collaborative optimization and fusion device for executing the balanced biased multi-source data collaborative optimization and fusion method of any one of claims 1 to 3, comprising a master control scheduling module, an input module, an output module and a plurality of storage modules, wherein the input module, the output module and the plurality of storage modules are all connected with the master control scheduling module, and characterized in that: the plurality of storage modules comprise a data information storage module and a data fusion parameter storage module, wherein,
the data information storage module is used for storing data cost and data type information of a data provider;
the main control module is used for sequencing the cost of all data in an ascending order, grouping the data according to the data types, storing the grouped structure in the data information storage module, and calling the data information and other storage modules by the BPMG-M algorithm in the step (4);
the data fusion parameter storage module is used for storing neural network parameters adopted in the data fusion process, and the parameters are also input and stored through the input module under the control of the main control module.
5. The balanced biased multi-source data collaborative preference and fusion apparatus of claim 4, wherein: also comprises an alternative data set storage module and a data selection storage module, wherein,
the alternative data set storage module is used for storing an alternative data set, and the alternative data set determines data which is finally input into the fusion algorithm from which data is determined;
the data selection storage module is used for storing a data provider set of selected data;
the main control module is a core module and is a key step for executing a data collaborative optimization and fusion method, and specifically comprises the following steps: firstly, after the input device receives all data information, the main control module executes the method in step (1) to collect the data that each data provider can provide, the data type information contained in the data and the cost information of the data, and stores the informationThe data information is stored in the data information storage module; then, the main control module executes the step (2) of the invention, and a multi-attribute combined truth value discovery algorithm is adopted for the collected data to improve the accuracy of the data; then, the main control module executes the step (3) of the invention, groups all data according to the difference that the data provided by the data provider contains data information types, and simultaneously stores the grouping result in the data information storage module; then according to step (4) of the present invention, a data-preferred BPMG-M algorithm is performed: firstly, sorting the cost information of the data from low to high, and storing the sorting result in a data information storage module; computing a set of devices for a target device from data information and ranking information
The optimum selection ratio of (a); a set of candidate data that can meet the budget constraint is then computed
The set satisfies bk·Fm(sk) B and B are not more thank+1·Fm(sk+1)>B, storing the data into an alternative data set storage module; calculating a data set finally selected and input into the fusion algorithm by using a formula (4) from the alternative data set, and storing the data set in a data selection storage module; finally, according to step (5) of the invention, the selected data S are processedwSeparately input Embedded representation network NwExtracting features, normalizing the extracted feature vectors, and fusing the network N by using parametersFAnd performing feature fusion, and finally outputting the fused data features.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110667243.0A CN113344085B (en) | 2021-06-16 | 2021-06-16 | Balance bias multi-source data collaborative optimization and fusion method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110667243.0A CN113344085B (en) | 2021-06-16 | 2021-06-16 | Balance bias multi-source data collaborative optimization and fusion method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113344085A true CN113344085A (en) | 2021-09-03 |
| CN113344085B CN113344085B (en) | 2024-04-26 |
Family
ID=77476036
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110667243.0A Active CN113344085B (en) | 2021-06-16 | 2021-06-16 | Balance bias multi-source data collaborative optimization and fusion method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113344085B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108804715A (en) * | 2018-07-09 | 2018-11-13 | 北京邮电大学 | Merge multitask coordinated recognition methods and the system of audiovisual perception |
| CN111178639A (en) * | 2019-12-31 | 2020-05-19 | 北京明略软件系统有限公司 | Method and device for realizing prediction based on multi-model fusion |
| CN111504676A (en) * | 2020-04-23 | 2020-08-07 | 中国石油大学(北京) | Equipment fault diagnosis method, device and system based on multi-source monitoring data fusion |
-
2021
- 2021-06-16 CN CN202110667243.0A patent/CN113344085B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108804715A (en) * | 2018-07-09 | 2018-11-13 | 北京邮电大学 | Merge multitask coordinated recognition methods and the system of audiovisual perception |
| CN111178639A (en) * | 2019-12-31 | 2020-05-19 | 北京明略软件系统有限公司 | Method and device for realizing prediction based on multi-model fusion |
| CN111504676A (en) * | 2020-04-23 | 2020-08-07 | 中国石油大学(北京) | Equipment fault diagnosis method, device and system based on multi-source monitoring data fusion |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113344085B (en) | 2024-04-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109214719B (en) | Marketing inspection analysis system and method based on artificial intelligence | |
| Zhang et al. | An efficient multiobjective genetic algorithm for mixed-model assembly line balancing problem considering demand ratio-based cycle time | |
| Sun et al. | Heterogeneous multigranulation fuzzy rough set-based multiple attribute group decision making with heterogeneous preference information | |
| CN103761254B (en) | Method for matching and recommending service themes in various fields | |
| CN101556464A (en) | Auto recommending method of urban power load forecasting module based on associative rules | |
| CN105786860A (en) | Data processing method and device in data modeling | |
| Chen et al. | Identification of λ-fuzzy measures using sampling design and genetic algorithms | |
| CN109919356A (en) | One kind being based on BP neural network section water demand prediction method | |
| Xiao et al. | Dynamic multi-attribute evaluation of digital economy development in China: A perspective from interaction effect | |
| CN105701562A (en) | Training method, suitable method of predicating generated power and respective systems | |
| CN112990587A (en) | Method, system, equipment and medium for accurately predicting power consumption of transformer area | |
| CN114995964A (en) | Combination service reconstruction method, device, equipment and computer readable medium | |
| Gao et al. | An efficient evolutionary algorithm based on deep reinforcement learning for large-scale sparse multiobjective optimization | |
| CN114330090A (en) | Defect detection method and device, computer equipment and storage medium | |
| CN118037000A (en) | Urban resource dynamic scheduling method and system based on digital economy | |
| Shen et al. | Heterogeneous multi-project multi-task allocation in mobile crowdsensing using an ensemble fireworks algorithm | |
| Liu et al. | Optimization of construction program schedule plans based on multi-objective optimization theory | |
| Aghamohagheghi et al. | A new decision approach to the sustainable transport investment selection based on the generalized entropy and knowledge measure under an interval-valued Pythagorean fuzzy environment | |
| Kasperski et al. | Possibilistic minmax regret sequencing problems with fuzzy parameters | |
| CN113344085A (en) | Balanced-bias multi-source data collaborative optimization and fusion method and device | |
| CN117436029A (en) | Method and system for serial collaborative fusion of multiple large models | |
| CN107180286A (en) | Manufacturing service supply chain optimization method and system based on modified pollen algorithm | |
| WO2023082788A1 (en) | Method and apparatus for predicting oxygen content in flue gas and load, method and apparatus for selecting prediction model, and method and apparatus for predicting flue gas emission | |
| CN114493172B (en) | Emergency capacity allocation plan deduction method and system | |
| CN113034033B (en) | Method for determining variety of newly-researched equipment spare parts |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |