CN107392374A - A kind of task parcel optimization method, system, equipment - Google Patents
A kind of task parcel optimization method, system, equipment Download PDFInfo
- Publication number
- CN107392374A CN107392374A CN201710600029.7A CN201710600029A CN107392374A CN 107392374 A CN107392374 A CN 107392374A CN 201710600029 A CN201710600029 A CN 201710600029A CN 107392374 A CN107392374 A CN 107392374A
- Authority
- CN
- China
- Prior art keywords
- parcel
- vector
- attribute information
- msub
- mrow
- 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
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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
- G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- 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
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/083—Shipping
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Tourism & Hospitality (AREA)
- Life Sciences & Earth Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Game Theory and Decision Science (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention relates to a kind of task parcel optimization method, system, equipment.The task wraps up optimization method, including：S1, the attribute information for obtaining multiple parcels；S2, the multi-C vector according to the foundation of parcel attribute information corresponding thereto；S3, multi-C vector is inputted into k means clustering algorithms parcel is classified, wherein, the parcel of same category group carries out path planning as an entirety input large neighborhood search algorithm.Package quantity level can be compressed to original 10% 20%, search space is not only greatly reduced, and the computing capability of later stage algorithm is required to reduce, the parcel handled through k means clustering algorithms meet extensive neighborhood search it is accurate, stably, the requirement of quick path planning, without extra cost input.
Description
Technical field
The present invention relates to path planning, more particularly to a kind of task parcel optimization method, system, equipment.
Background technology
With the fast development of logistic industry, the competition between logistics also constantly aggravates.Logistics cost and the contracting in cycle
It is short to be concentrated mainly in the optimization in path.Select optimal path and have become loglstics enterprise demand the most urgent.On a large scale
Neighborhood-region-search algorithm is one of method for solving problems.
In the algorithm in path planning field, the directly incoming algorithm model of magnanimity package data is typically subjected to path rule
Draw, but if mass data is passed into algorithm model, that is, when problematic amount level is excessive, it is meant that search space
It is huge, it may result in the quality extreme difference of solution.It is also possible to because incoming quality level is excessive, the computing capability of algorithm is limited, causes nothing
Method finds the destruction formula problem of feasible solution.
The content of the invention
In order to solve the above-mentioned technical problem, optimization method, system wrapped up it is an object of the invention to provide a kind of task, set
It is standby.
According to an aspect of the invention, there is provided a kind of task parcel optimization method, including：
S1, the attribute information for obtaining multiple parcels；
S2, the multi-C vector according to the foundation of parcel attribute information corresponding thereto；
S3, by multi-C vector input k-means clustering algorithms to parcel classify, wherein, the parcel of same category group
Path planning is carried out as an entirety input large neighborhood search algorithm.
Further, the attribute information of parcel includes address flow direction, packing requires and time window.
Wherein, address flow direction is the starting of parcel, termination address, and packing is required as wrapped up whether needing positive placement, when
Between window be that client posts and the part time and requires delivery time.
Further, include address flow direction with the corresponding multi-C vector of parcel attribute information, packing requires, time window to
Amount.
Further, multi-C vector input k-means clustering algorithms are carried out into classification to parcel includes：
S31, K vector is taken at random from multiple multi-C vectors, as the respective center of K cluster；
S32, remaining vector is calculated respectively to the distinctiveness ratio at K cluster center, incorporate these vectors into distinctiveness ratio respectively
Minimum cluster；
S33, according to cluster result, recalculate the respective center of K cluster；
S34, by all vector clusters according to new center again in above-mentioned multiple multi-C vectors；
S35, repeat step S34, until cluster result no longer changes；
S36, the result output that parcel will be classified.
Further, in S32, S34, S35, non-cluster center vector is assigned to phase according to vector distance d (X, Y) minimum principle
The minimum cluster of different degree, clustering processing is carried out,
Wherein,
X is the center of a cluster,
X={ x1,x2,...,xn,
Y is non-cluster center,
Y={ y1,y2,...yn}。
Further, the selection quantity K=a at cluster center × parcel sum, wherein, 0 ＜ a≤1, a specific value and bag
The region characteristic wrapped up in is relevant.
According to another aspect of the present invention, there is provided a kind of task wraps up optimization system, including：
Obtain the collecting unit of the attribute information of multiple parcels；
The multi-C vector that multi-C vector corresponding thereto is established according to parcel attribute information establishes unit；
Multi-C vector is inputted into k-means clustering algorithms to wrapping up the data-optimized pretreatment unit classified.
Further, the parcel of same category group carries out path rule as an entirety input large neighborhood search algorithm
Draw.
The system is the system that optimization method is wrapped up based on any of the above-described task, therefore attribute information, the multi-C vector wrapped up
Foundation, by k-means clustering algorithms classify etc. step as described in task wraps up optimization method part to parcel.
According to another aspect of the present invention, there is provided a kind of task parcel optimization equipment, it is characterized in that, including be stored with
The computer-readable medium of computer program, described program are run for performing：
S1, the attribute information for obtaining multiple parcels；
S2, the multi-C vector according to the foundation of parcel attribute information corresponding thereto；
S3, by multi-C vector input k-means clustering algorithms to parcel classify, wherein, the parcel of same category group
Path planning is carried out as an entirety input large neighborhood search algorithm.
The equipment is the equipment that optimization method is wrapped up based on any of the above-described task, therefore attribute information, the multi-C vector wrapped up
Foundation, by k-means clustering algorithms classify etc. step as described in task wraps up optimization method part to parcel.
Compared with prior art, the invention has the advantages that：
1st, the task parcel optimization method of example of the present invention, according to parcel attribute information establish multidimensional corresponding thereto to
Amount；Multi-C vector is inputted into k-means clustering algorithms to classify to parcel, wherein, the parcel of same category group is as one
Overall input large neighborhood search algorithm carries out path planning, and package quantity level can be compressed to original 10%-20%, no
But search space is greatly reduced, and the computing capability of later stage algorithm is required to reduce, is handled through k-means clustering algorithms
Parcel meet extensive neighborhood search it is accurate, stably, the requirement of quick path planning, put into without extra cost.
2nd, the task parcel optimization system of example of the present invention, the attribute information of multiple parcels is obtained by collecting unit；It is logical
Cross multi-C vector and establish the multi-C vector of unit according to the foundation of parcel attribute information corresponding thereto；Pass through data-optimized pretreatment
Unit is classified multi-C vector input k-means clustering algorithms to parcel, compressed data.The system architecture is simple, passes through
The mutual cooperation of unit, package quantity level is set to be compressed to original 10%-20%, it is ensured that extensive neighborhood search essence
Really, stably, quick path planning.
3rd, the task parcel optimization equipment of example of the present invention, stores, is run for performing following programs：Pass through k-
Means clustering algorithms are compressed to package quantity level, reduce search space, reduce the meter to route in later period planning algorithm
The requirement of calculation ability, it is ensured that extensive neighborhood search is accurate, stably, quick path planning, and put into without extra cost, should
Equipment is worthy to be popularized.
Brief description of the drawings
Fig. 1 is the exemplary process diagram that the task of embodiments of the invention one wraps up optimization method；
Fig. 2 is the block diagram that the task of embodiments of the invention one wraps up optimization system.
Embodiment
In order to be better understood by technical scheme, the present invention is made furtherly with reference to specific embodiment
It is bright.
Embodiment one：
A kind of task parcel optimization method is present embodiments provided, including：
S1, the attribute information for obtaining multiple parcels, the attribute information is address flow direction, packing requires and time window, wherein,
Address flow direction is the starting of parcel, termination address, and packing requires whether need positive placement as wrapped up, and time window is that client posts part
Time and require delivery time；
S2, the multi-C vector according to the foundation of parcel attribute information corresponding thereto, the multi-C vector are address flow direction, packing
It is required that and time window；
S3, by multi-C vector input k-means clustering algorithms to parcel classify, wherein, the parcel of same category group
Path planning is carried out as an entirety input large neighborhood search algorithm,
Concretely comprise the following steps：
S31, K vectorial (i.e. element) is taken at random from multiple multi-C vectors, as the respective center of K cluster；
S32, calculate the distinctiveness ratio that remaining vectorial (i.e. element) arrives K cluster center respectively, non-cluster center vector according to
Span is assigned to the minimum cluster of distinctiveness ratio from d (X, Y) minimum principle,
Wherein,
X is the center of a cluster,
X={ x1,x2,...,xn,
Y is non-cluster center,
Y={ y1,y2,...yn}；
S33, according to cluster result, recalculate the respective center of K cluster；
S34, by all vector clusters according to new center again in above-mentioned multiple multi-C vectors, clustering method is with reference to step
S32；
S35, repeat step S34, until cluster result no longer changes；
S36, the result output that parcel will be classified.
K is obtained by above-mentioned computing to cluster, the high similarity of parcel vector in cluster, the parcel vector between cluster is low
Similarity.
The selection quantity K=0.5 at cluster center × parcel sum.
After pre-processing packing parcel via k-means clustering algorithms, the parcel in the range of certain time, one can be integrated into
The parcel of individual set time, if customer requirement delivery time is 10:00-10:10 parcel, delivery time is packaged as 10:00
Parcel it is overall.When package quantity magnanimity, this pretreatment just becomes particularly important, experiment statisticses, is clustered via k-means
Algorithm is pretreated, and package quantity level can be compressed to original 10%-20%.
A kind of task parcel optimization system is present embodiments provided, including：
Obtain the collecting unit of the attribute information of multiple parcels；
The multi-C vector that multi-C vector corresponding thereto is established according to parcel attribute information establishes unit；
Multi-C vector is inputted into k-means clustering algorithms to wrapping up the data-optimized pretreatment unit classified.
Wherein, the parcel of same category group carries out path planning as an entirety input large neighborhood search algorithm.
A kind of task parcel optimization equipment is present embodiments provided, including is stored with computer-readable Jie of computer program
Matter, described program are run for performing：
S1, the attribute information for obtaining multiple parcels；
S2, the multi-C vector according to the foundation of parcel attribute information corresponding thereto；
S3, by multi-C vector input k-means clustering algorithms to parcel classify, wherein, the parcel of same category group
Path planning is carried out as an entirety input large neighborhood search algorithm.
The computer-readable recording medium can be that computer-readable included in device described in above-described embodiment is deposited
Storage media；Can also be individualism, without the computer-readable recording medium in supplying equipment.Computer-readable recording medium
One or more than one program are stored with, described program is used for performing by one or more than one processor.
Embodiment two：
The present embodiment repeats no more with the identical feature of embodiment one, and the present embodiment feature different from embodiment one exists
In：
In the task parcel optimization method of the present embodiment,
In step S1, attribute information is address flow direction, packing requires and time window, wherein, address flow direction rises for parcel
Begin, termination address, packing requires such as to paste frangible explanation, and time window is that client posts the part time and requires delivery time；
Step S2, multi-C vector corresponding thereto is established according to parcel attribute information, the multi-C vector be address flow direction,
Packing requires and time window.
The selection quantity K=0.1 at cluster center × parcel sum.
Embodiment three：
The present embodiment repeats no more with the identical feature of embodiment one, and the present embodiment feature different from embodiment one exists
In：
In the task parcel optimization method of the present embodiment,
In step S1, attribute information is address flow direction, packing requires and time window, wherein, address flow direction rises for parcel
Begin, termination address, it is outer that packing requires that item price label such as is attached to parcel, when time window is that client posts the part time and requirement is sent to
Between；
Step S2, multi-C vector corresponding thereto is established according to parcel attribute information, the multi-C vector be address flow direction,
Packing requires and time window.
The selection quantity K=0.8 at cluster center × parcel sum.
Example IV：
The present embodiment repeats no more with the identical feature of embodiment one, and the present embodiment feature different from embodiment one exists
In：
In the task parcel optimization method of the present embodiment,
The selection quantity K=0.9 at cluster center × parcel sum.
Embodiment five：
The present embodiment repeats no more with the identical feature of embodiment one, and the present embodiment feature different from embodiment one exists
In：
In the task parcel optimization method of the present embodiment,
The selection quantity K=1 at cluster center × parcel sum.
Above description is only the preferred embodiment of the application and the explanation to institute's application technology principle.People in the art
Member should be appreciated that invention scope involved in the application, however it is not limited to the technology that the particular combination of above-mentioned technical characteristic forms
Scheme, while should also cover in the case where not departing from the inventive concept, carried out by above-mentioned technical characteristic or its equivalent feature
The other technical schemes for being combined and being formed.Such as features described above has similar work(with (but not limited to) disclosed herein
Energy.
Claims (9)
1. a kind of task wraps up optimization method, it is characterized in that, including：
S1, the attribute information for obtaining multiple parcels；
S2, the multi-C vector according to the foundation of parcel attribute information corresponding thereto；
S3, by multi-C vector input k-means clustering algorithms to parcel classify, wherein, the parcel conduct of same category group
One entirety input large neighborhood search algorithm carries out path planning.
2. task according to claim 1 wraps up optimization method, it is characterized in that, the attribute information of parcel includes address stream
To, packing require and time window.
3. task according to claim 2 wraps up optimization method, it is characterized in that, the multidimensional corresponding with parcel attribute information
Vector includes address flow direction, packing requires, time window vector.
4. task according to claim 1 wraps up optimization method, it is characterized in that, by multi-C vector input k-means clusters
Algorithm carries out classification to parcel to be included：
S31, K vector is taken at random from multiple multi-C vectors, as the respective center of K cluster；
S32, remaining vector is calculated respectively to the distinctiveness ratio at K cluster center, it is minimum to incorporate these vectors into distinctiveness ratio respectively
Cluster；
S33, according to cluster result, recalculate the respective center of K cluster；
S34, by all vector clusters according to new center again in above-mentioned multiple multi-C vectors；
S35, repeat step S34, until cluster result no longer changes；
S36, the result output that parcel will be classified.
5. task according to claim 4 wraps up optimization method, it is characterized in that, in S32, S34, S35, non-cluster center vector
The minimum cluster of distinctiveness ratio is assigned to according to vector distance d (X, Y) minimum principle, carries out clustering processing,
Wherein,
<mrow>
<mi>d</mi>
<mrow>
<mo>(</mo>
<mi>X</mi>
<mo>,</mo>
<mi>Y</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<msqrt>
<mrow>
<msup>
<mrow>
<mo>(</mo>
<msub>
<mi>x</mi>
<mn>1</mn>
</msub>
<mo>-</mo>
<msub>
<mi>y</mi>
<mn>1</mn>
</msub>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
<mo>+</mo>
<msup>
<mrow>
<mo>(</mo>
<msub>
<mi>x</mi>
<mn>2</mn>
</msub>
<mo>-</mo>
<msub>
<mi>y</mi>
<mn>2</mn>
</msub>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
<mo>+</mo>
<mn>...</mn>
<mo>+</mo>
<msup>
<mrow>
<mo>(</mo>
<msub>
<mi>x</mi>
<mi>n</mi>
</msub>
<mo>-</mo>
<msub>
<mi>y</mi>
<mi>n</mi>
</msub>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
</mrow>
</msqrt>
</mrow>
X is the center of a cluster,
X={ x1,x2,...,xn,
Y is non-cluster center,
Y={ y1,y2,...yn}。
6. task according to claim 4 wraps up optimization method, it is characterized in that,
The selection quantity K=a at cluster center × parcel sum,
Wherein, 0 ＜ a≤1.
7. a kind of task wraps up optimization system, it is characterized in that, including：
Obtain the collecting unit of the attribute information of multiple parcels；
The multi-C vector that multi-C vector corresponding thereto is established according to parcel attribute information establishes unit；
Multi-C vector is inputted into k-means clustering algorithms to wrapping up the data-optimized pretreatment unit classified.
8. task according to claim 7 wraps up optimization system, it is characterized in that, the parcel of same category group is whole as one
Body input large neighborhood search algorithm carries out path planning.
9. a kind of task parcel optimization equipment, it is characterized in that, including the computer-readable medium of computer program is stored with, it is described
Program is run for performing：
S1, the attribute information for obtaining multiple parcels；
S2, the multi-C vector according to the foundation of parcel attribute information corresponding thereto；
S3, by multi-C vector input k-means clustering algorithms to parcel classify, wherein, the parcel conduct of same category group
One entirety input large neighborhood search algorithm carries out path planning.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710600029.7A CN107392374A (en) | 2017-07-21 | 2017-07-21 | A kind of task parcel optimization method, system, equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710600029.7A CN107392374A (en) | 2017-07-21 | 2017-07-21 | A kind of task parcel optimization method, system, equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107392374A true CN107392374A (en) | 2017-11-24 |
Family
ID=60337632
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710600029.7A Pending CN107392374A (en) | 2017-07-21 | 2017-07-21 | A kind of task parcel optimization method, system, equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107392374A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109919530A (en) * | 2017-12-12 | 2019-06-21 | 顺丰科技有限公司 | A kind of Distribution path destroys method for reconstructing, device, storage medium and equipment |
| CN109919348A (en) * | 2017-12-12 | 2019-06-21 | 顺丰科技有限公司 | A kind of method for optimizing route, device, equipment, storage medium |
| CN110322106A (en) * | 2019-04-12 | 2019-10-11 | 成都服务生科技有限公司 | A kind of multi-destination, multiple means of transports luggage fetch and deliver dispatching method |
| CN115271354A (en) * | 2022-06-24 | 2022-11-01 | 湖南湘邮科技股份有限公司 | Service electronic fence dynamic planning method and system based on delivery unit |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103440566A (en) * | 2013-08-27 | 2013-12-11 | 北京京东尚科信息技术有限公司 | Method and device for generating order picking collection lists and method for optimizing order picking route |
| CN103489108A (en) * | 2013-08-22 | 2014-01-01 | 浙江工商大学 | Large-scale order form matching method in community commerce cloud |
-
2017
- 2017-07-21 CN CN201710600029.7A patent/CN107392374A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103489108A (en) * | 2013-08-22 | 2014-01-01 | 浙江工商大学 | Large-scale order form matching method in community commerce cloud |
| CN103440566A (en) * | 2013-08-27 | 2013-12-11 | 北京京东尚科信息技术有限公司 | Method and device for generating order picking collection lists and method for optimizing order picking route |
Non-Patent Citations (3)
| Title |
|---|
| 任丽: "基于时空聚类的车辆路径分析与优化", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
| 刘小兰等: "有时间窗的车辆路径问题的近似算法研究", 《计算机集成制造系统》 * |
| 胡继雪: "基于大规模车辆路径问题的配送分区优化研究", <中国优秀硕士学位论文全文数据库 信息科技辑> * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109919530A (en) * | 2017-12-12 | 2019-06-21 | 顺丰科技有限公司 | A kind of Distribution path destroys method for reconstructing, device, storage medium and equipment |
| CN109919348A (en) * | 2017-12-12 | 2019-06-21 | 顺丰科技有限公司 | A kind of method for optimizing route, device, equipment, storage medium |
| CN110322106A (en) * | 2019-04-12 | 2019-10-11 | 成都服务生科技有限公司 | A kind of multi-destination, multiple means of transports luggage fetch and deliver dispatching method |
| CN115271354A (en) * | 2022-06-24 | 2022-11-01 | 湖南湘邮科技股份有限公司 | Service electronic fence dynamic planning method and system based on delivery unit |
| CN115271354B (en) * | 2022-06-24 | 2023-08-25 | 湖南湘邮科技股份有限公司 | Service electronic fence dynamic planning method and system based on delivery unit |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107392374A (en) | A kind of task parcel optimization method, system, equipment | |
| US10963692B1 (en) | Deep learning based document image embeddings for layout classification and retrieval | |
| CN109272115A (en) | A kind of neural network training method and device, equipment, medium | |
| CN108334513A (en) | A kind of identification processing method of Similar Text, apparatus and system | |
| US10599985B2 (en) | Systems and methods for expediting rule-based data processing | |
| CN107180064A (en) | A kind of logistics information processing method, device and logistic information systems | |
| CN107679856A (en) | Service control method and device based on transaction | |
| US20160275446A1 (en) | Apparatus and method for determining hs code | |
| Azman et al. | Artificial intelligence in automated bookkeeping: a value-added function for small and medium enterprises | |
| US20200380524A1 (en) | Transaction feature generation | |
| CN104021125A (en) | Search engine sorting method and system and search engine | |
| Sihombing et al. | Fake review detection on yelp dataset using classification techniques in machine learning | |
| TW201636877A (en) | Filtering data objects | |
| CN107169061A (en) | A kind of text multi-tag sorting technique for merging double information sources | |
| TW202305654A (en) | Business data origanizing system, method and computer program product | |
| CN111143678B (en) | Recommendation system and recommendation method | |
| CN101661510A (en) | Data matching method and device thereof | |
| US8505811B2 (en) | Anomalous billing event correlation engine | |
| WO2017095439A1 (en) | Incremental clustering of a data stream via an orthogonal transform based indexing | |
| US20230137639A1 (en) | Data processing system and method for operating an enterprise application | |
| CN103995831B (en) | Object processing method, system and device based on similarity among objects | |
| CN110032664A (en) | A method of quickly establishing the full node address index of bit coin block chain | |
| CN113656466B (en) | Policy data query method, device, equipment and storage medium | |
| CN104573101A (en) | System and method for real-time data stream classification on basis of rule routes | |
| Ilieva | Decision analysis for big data platform selection |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171124 |