CN109857798B - Double-library collaborative data mining system and processing method for logistics data - Google Patents
Double-library collaborative data mining system and processing method for logistics data Download PDFInfo
- Publication number
- CN109857798B CN109857798B CN201910077416.6A CN201910077416A CN109857798B CN 109857798 B CN109857798 B CN 109857798B CN 201910077416 A CN201910077416 A CN 201910077416A CN 109857798 B CN109857798 B CN 109857798B
- Authority
- CN
- China
- Prior art keywords
- data
- logistics
- library
- double
- collaborative
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Abstract
The invention is used for the double-base collaborative data mining system of the logistics data, builds an internal connection channel between a logistics client database and a basic knowledge base by utilizing a double-base collaborative mechanism, restricts and drives the mining process of logistics data knowledge discovery by utilizing the basic knowledge base, changes the inherent operation mechanism of data knowledge discovery, and enables the basic knowledge base to be continuously expanded, thereby forming a knowledge base subsystem with dynamic expansion characteristics; the system comprises a maintenance type coordination system and a heuristic coordination system; after focusing a large amount of data in a real database to generate a hypothesis rule, the maintenance coordination system enables the data mining process to generate an interrupt; under the database construction principle based on attributes, the heuristic coordination system searches and discovers shortage to generate an 'thinking intention', and discharges the priority of directional excavation according to the association strength to generate a directional excavation process.
Description
Technical Field
The invention relates to an intelligent control technology, in particular to a double-library collaborative data mining system for logistics data and a processing method.
Background
With the development of social economy, logistics transportation is also continuously developed, and logistics refers to a process of organically combining functions of transportation, storage, loading and unloading, carrying, packaging, circulation processing, distribution, information processing and the like according to actual needs in the process of enabling objects to flow from a supply place to a receiving place.
The logistics at the present stage comprises logistics management, wherein the logistics management specifically comprises planning, organizing, commanding, coordinating, controlling and supervising the logistics activities according to the basic principle and scientific method of the physical material entity flow, so that the optimal coordination and coordination of all the logistics activities are realized;
however, in the current logistics data management, detection is needed manually, and human resources are seriously wasted.
Therefore, there is a need to provide a dual library collaborative data mining system and processing method for logistics data to solve the above-mentioned problems.
Disclosure of Invention
The invention aims to provide a double-library collaborative data mining system for logistics data.
The technical proposal is as follows:
a double-library collaborative data mining system for logistics data utilizes a double-library collaborative mechanism to construct an internal connection channel of a logistics client database and a basic knowledge base, utilizes the basic knowledge base to restrict and drive the mining process of logistics data knowledge discovery, changes the inherent operation mechanism of data knowledge discovery, and enables the basic knowledge base to be expanded continuously, so that a knowledge base subsystem with dynamic expansion characteristics is formed;
the system comprises a maintenance type coordination system and a heuristic coordination system;
after focusing in a large amount of data of a real database to generate an assumption rule (decision basis), the maintenance coordination system enables the data mining process to generate an interrupt, and whether the generation rule is repeated, redundant and contradictory exists in the original database or not is directionally searched;
under the database construction principle based on attributes, the heuristic coordination system searches and discovers shortage to generate an 'creative intention', discharges the priority of directional mining according to the association strength, and inspires and activates the corresponding data sub-structure in the real database to generate a directional mining process.
Further, if there is repetition and redundancy, the generation rule is canceled and the "beginning" of the data mining is returned; if the contradiction exists, under the intervention of a field system expert, the contradiction rule is canceled according to the credibility and the rule strength or the contradiction is eliminated by using methods such as expansion precondition and the like.
Further, if there is no redundancy or contradiction, the knowledge discovery process is continued.
The second purpose of the invention is to provide a double-library collaborative data processing method for logistics data.
The technical proposal is as follows:
a double-library cooperation data processing method for logistics data comprises the following steps:
1) Creating a logistics data set;
2) Data cleaning and pre-processing of the logistics data set:
2-1) removing erroneous data;
2-2) collecting necessary information modeling or responsible error data;
2-3) determining a strategy to handle missing data and responsible for the chronological order and known changes of the information;
3) Data compression and projection of the logistic dataset: finding useful feature presentation data according to the purpose of the task;
4) The logistics data knowledge discovery system adopting double-library cooperation is adopted to match the process targets:
5) Searching a specific expression form or a group of characterized interest modes, selecting a maintenance type coordination system or a heuristic coordination system, and searching data.
Further, the logistic data set at least comprises customer information, route information and order information.
Further, by dimension reduction methods or transformations, the number of variables considered to be valid may be reduced or representations of invariant data may be found.
Further, in step 5), the specific expression forms include classification rules or trees, regression and clustering.
Compared with the prior art, the invention utilizes a double-base collaboration mechanism to construct an internal connection channel between the mining database and the basic knowledge base, thereby restricting and driving the mining process of logistics data by using the basic database, changing the original inherent operation mechanism of data mining, and leading the original basic database which takes experience and knowledge as a direct data source to be continuously expanded, thereby forming the logistics data mining system with dynamic expansion characteristics.
Detailed Description
Example 1:
the embodiment shows a double-library collaborative data mining system for logistics data, wherein an internal connection channel between a logistics client database and a basic knowledge base is constructed by utilizing a double-library collaborative mechanism, the basic knowledge base is used for restricting and driving the discovery process of logistics data knowledge, and the inherent operation mechanism of data knowledge discovery is changed, so that the basic knowledge base is continuously expanded, and a knowledge base subsystem with dynamic expansion characteristics is formed;
the system comprises a maintenance type coordination system and a heuristic coordination system;
after focusing in a large amount of data of a real database to generate an assumption rule (decision basis), the maintenance coordination system enables the data mining process to generate an interrupt, and whether the generation rule is repeated, redundant and contradictory exists in the original database or not is directionally searched;
under the database construction principle based on attributes, the heuristic coordination system searches and discovers shortage to generate an 'creative intention', discharges the priority of directional mining according to the association strength, and inspires and activates the corresponding data sub-structure in the real database to generate a directional mining process.
If repetition and redundancy exist, canceling the generation rule and returning to the beginning of data mining; if the contradiction exists, under the intervention of a field system expert, the contradiction rule is canceled according to the credibility and the rule strength or the contradiction is eliminated by using methods such as expansion precondition and the like.
If there is no redundancy and contradiction, the knowledge discovery process is continued.
Example 2:
the embodiment shows a data processing method for processing logistics data by using a double-library collaborative data mining system for logistics data.
The method comprises the following steps:
1) Creating a logistics data set;
2) Data cleaning and pre-processing of the logistics data set:
2-1) removing erroneous data;
2-2) collecting necessary information modeling or responsible error data;
2-3) determining a strategy to handle missing data and responsible for the chronological order and known changes of the information;
3) Data compression and projection of the logistic dataset: finding useful feature presentation data according to the purpose of the task;
4) The logistics data knowledge discovery system adopting double-library cooperation is adopted to match the process targets:
5) Searching a specific expression form or a group of characterized interest modes, selecting a maintenance type coordination system or a heuristic coordination system, and searching data.
The logistic data set at least comprises customer information, route information and order information.
By means of dimension reduction methods or transformations, the number of variables considered to be valid may be reduced or representations of invariant data may be found.
In step 5), specific manifestations, including classification rules or trees, regression and clustering.
Compared with the prior art, the technical schemes shown in the embodiments 1 and 2 construct an internal connection channel between the mining database and the basic knowledge base by using a double-base collaboration mechanism, so that the basic database is used for restricting and driving the mining process of logistics data, the original operation mechanism of data mining is changed, the original basic database which takes experience and knowledge as direct data sources is continuously expanded, and a logistics data mining system with dynamic expansion characteristics is formed.
What has been described above is merely some embodiments of the present invention. It will be apparent to those skilled in the art that various modifications and improvements can be made without departing from the spirit of the invention.
Claims (7)
1. A double-library collaborative data mining system for logistics data is characterized in that: an internal connection channel between a logistics client database and a basic knowledge base is constructed by utilizing a double-base collaboration mechanism, the basic knowledge base is used for restricting and driving the discovery process of logistics data knowledge discovery, the inherent operation mechanism of data knowledge discovery is changed, the basic knowledge base is expanded continuously, and a knowledge base subsystem with dynamic expansion characteristics is formed;
the system comprises a maintenance type coordination system and a heuristic coordination system;
after focusing in a large amount of data of a real database to generate a hypothesis rule, the maintenance coordination system enables the data mining process to generate an interrupt, and the original database is subjected to directional searching to determine whether the generation rule is repeated, redundant and contradictory;
under the database construction principle based on attributes, the heuristic coordination system searches and discovers shortage to generate an 'creative intention', discharges the priority of directional mining according to the association strength, and inspires and activates the corresponding data sub-structure in the real database to generate a directional mining process.
2. A dual library collaborative data mining system for logistic data according to claim 1, wherein: if repetition and redundancy exist, canceling the generation rule and returning to the beginning of data mining; if the contradiction exists, under the intervention of a field system expert, the contradiction rule is canceled according to the credibility and the rule strength or the contradiction is eliminated by using methods such as expansion precondition and the like.
3. A dual library collaborative data mining system for logistic data according to claim 2, wherein: if there is no redundancy and contradiction, the knowledge discovery process is continued.
4. A double-library cooperation data processing method for logistics data is characterized by comprising the following steps of:
based on the dual library collaborative data mining system for logistics data of claim 3, the steps are as follows:
1) Creating a logistics data set;
2) Data cleaning and pre-processing of the logistics data set:
2-1) removing erroneous data;
2-2) collecting necessary information modeling or responsible error data;
2-3) determining a strategy to handle missing data and responsible for the chronological order and known changes of the information;
3) Data compression and projection of the logistic dataset: finding useful feature presentation data according to the purpose of the task;
4) The logistics data knowledge discovery system adopting double-library cooperation is adopted to match the process targets:
5) Searching a specific expression form or a group of characterized interest modes, selecting a maintenance type coordination system or a heuristic coordination system, and searching data.
5. The method for processing the double-library collaborative data for logistics data according to claim 4, wherein the method comprises the following steps: the logistic data set at least comprises customer information, route information and order information.
6. The method for processing the double-library collaborative data for logistics data according to claim 5, wherein the method comprises the steps of: by means of dimension reduction methods or transformations, the number of variables considered to be valid may be reduced or representations of invariant data may be found.
7. The method for processing the double-library collaborative data for logistics data according to claim 5 or 6, wherein the method comprises the steps of: in step 5), specific manifestations, including classification rules or trees, regression and clustering.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910077416.6A CN109857798B (en) | 2019-01-28 | 2019-01-28 | Double-library collaborative data mining system and processing method for logistics data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910077416.6A CN109857798B (en) | 2019-01-28 | 2019-01-28 | Double-library collaborative data mining system and processing method for logistics data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109857798A CN109857798A (en) | 2019-06-07 |
| CN109857798B true CN109857798B (en) | 2023-05-12 |
Family
ID=66896321
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910077416.6A Active CN109857798B (en) | 2019-01-28 | 2019-01-28 | Double-library collaborative data mining system and processing method for logistics data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109857798B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1428696A (en) * | 2001-12-29 | 2003-07-09 | 杨炳儒 | KDD* system based on double-library synergistic mechanism |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| AUPR464601A0 (en) * | 2001-04-30 | 2001-05-24 | Commonwealth Of Australia, The | Shapes vector |
-
2019
- 2019-01-28 CN CN201910077416.6A patent/CN109857798B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1428696A (en) * | 2001-12-29 | 2003-07-09 | 杨炳儒 | KDD* system based on double-library synergistic mechanism |
Non-Patent Citations (1)
| Title |
|---|
| 一类基于认知心理特征的知识发现新模型;杨炳儒等;《高技术通讯》;20090425(第04期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109857798A (en) | 2019-06-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Meng et al. | MILP models for energy-aware flexible job shop scheduling problem | |
| Wang et al. | Case based reasoning method for computer aided welding fixture design | |
| Puchinger et al. | Combining metaheuristics and exact algorithms in combinatorial optimization: A survey and classification | |
| Miller et al. | Optimizing Murty's ranked assignment method | |
| Andersson et al. | The maritime pickup and delivery problem with time windows and split loads | |
| Givehchi et al. | Generic machining process sequencing through a revised enriched machining feature concept | |
| Yin et al. | A Pareto-discrete hummingbird algorithm for partial sequence-dependent disassembly line balancing problem considering tool requirements | |
| Xie et al. | A new algorithm for complex product flexible scheduling with constraint between jobs | |
| Rico-Garcia et al. | Parallel implementation of metaheuristics for optimizing tool path computation on CNC machining | |
| CN101573729A (en) | Method and apparatus for multi-level ray tracing | |
| Márquez et al. | Shop scheduling in manufacturing environments: a review | |
| Liu et al. | A multi-MILP model collaborative optimization method for integrated process planning and scheduling problem | |
| CN109857798B (en) | Double-library collaborative data mining system and processing method for logistics data | |
| Laadhar et al. | Partitioning and local matching learning of large biomedical ontologies | |
| Cheng et al. | An efficient genetic algorithm for multi AGV scheduling problem about intelligent warehouse | |
| Cuellar‐Usaquén et al. | Modeling and solving the endpoint cutting problem | |
| David et al. | Towards a taxonomy of digital twin evolution for technical sustainability | |
| US10191973B1 (en) | Patent analytics using mapreduce clustering | |
| Sharma et al. | Indexer++ workload-aware online index tuning with transformers and reinforcement learning | |
| Simon et al. | Finding and exploiting LTL trajectory constraints in heuristic search | |
| Ehmke et al. | Position Paper: Explainable Search of Multimodal Itineraries. | |
| Buyukozdemir et al. | A Review of Heuristic Approaches to Vehicle Routing Problems | |
| Lee et al. | A real-time intelligent speed optimization planner using reinforcement learning | |
| Huang et al. | An effective numerical control machining process optimization approach of part with complex pockets for numerical control process reuse | |
| US8818987B2 (en) | Converting union commands to union all commands |
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 |