CN114819410A - Dragging type traffic field-oriented data prediction system - Google Patents
Dragging type traffic field-oriented data prediction system Download PDFInfo
- Publication number
- CN114819410A CN114819410A CN202210707677.3A CN202210707677A CN114819410A CN 114819410 A CN114819410 A CN 114819410A CN 202210707677 A CN202210707677 A CN 202210707677A CN 114819410 A CN114819410 A CN 114819410A
- Authority
- CN
- China
- Prior art keywords
- data
- algorithm
- prediction
- predicted
- traffic
- 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
- 238000007781 pre-processing Methods 0.000 claims abstract description 57
- 238000013135 deep learning Methods 0.000 claims abstract description 12
- 238000012545 processing Methods 0.000 claims description 24
- 238000000034 method Methods 0.000 claims description 19
- 238000012795 verification Methods 0.000 claims description 13
- 239000010410 layer Substances 0.000 description 77
- 230000006870 function Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000013507 mapping Methods 0.000 description 5
- 206010063385 Intellectualisation Diseases 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 239000012792 core layer Substances 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000000007 visual effect Effects 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
- G06F3/0484—Interaction techniques based on graphical user interfaces [GUI] for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range
- G06F3/0486—Drag-and-drop
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- General Engineering & Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a dragging type data prediction system facing to the traffic field, which relates to the traffic data prediction field and comprises the following steps: the view layer is used for selecting one traffic scene from a plurality of set traffic scenes as a traffic scene to be predicted; the system is also used for selecting a data preprocessing algorithm and a data prediction algorithm based on the traffic scene to be predicted; the device is also used for selecting one from a plurality of data source addresses as a data source address to be predicted; the device is also used for displaying the prediction result; the data prediction algorithm is a deep learning algorithm; the central layer is used for receiving data to be predicted, inputting the data to be predicted into a selected data prediction algorithm to obtain a prediction result, and feeding the prediction result back to the view layer; the access layer is connected with the central layer and used for acquiring data source data according to a data source address to be predicted, preprocessing the data source data by adopting a selected data preprocessing algorithm to acquire the data to be predicted and sending the data to be predicted to the central layer. The invention improves the data prediction efficiency in the traffic field.
Description
Technical Field
The invention relates to the technical field of traffic data prediction, in particular to a dragging type data prediction system facing the traffic field.
Background
With the continuous deep optimization of deep learning technology in research and application, the traffic industry is developing towards intellectualization and intellectualization. However, a general deep learning platform has a high learning threshold and a complex operation flow, and practitioners with zero basis are easy to feel difficult to use, so that the wide application of deep learning in the traffic field is hindered.
Disclosure of Invention
The invention aims to provide a dragging type traffic field-oriented data prediction system, which improves the data prediction efficiency of the traffic field.
In order to achieve the purpose, the invention provides the following scheme:
a drag-and-drop traffic-domain oriented data prediction system, comprising:
the view layer is used for selecting one traffic scene from a plurality of set traffic scenes as a traffic scene to be predicted; the system is also used for selecting a data preprocessing algorithm and a data prediction algorithm based on the traffic scene to be predicted to obtain a selected data preprocessing algorithm and a selected data prediction algorithm; the device is also used for selecting one from a plurality of data source addresses as a data source address to be predicted; the device is also used for displaying the prediction result; the data prediction algorithm is a deep learning algorithm; the view layer selects a traffic scene, a data preprocessing algorithm, a data prediction algorithm and a data source address in a dragging mode;
the central layer is connected with the view layer, receives data to be predicted, inputs the data to be predicted into the selected data prediction algorithm to obtain a prediction result, and feeds the prediction result back to the view layer;
and the access layer is connected with the central layer and is used for acquiring data source data according to the source address of the data to be predicted, preprocessing the data source data by adopting the selected data preprocessing algorithm to acquire the data to be predicted and sending the data to be predicted to the central layer.
Optionally, the traffic scene comprises a vehicle flow speed and flow prediction scene and a toll gate congestion duration prediction scene of a set part of road sections.
Optionally, the central layer is configured to perform flow verification according to the selected data preprocessing algorithm, the selected data prediction algorithm, and the source address of the data to be predicted, where the flow verification includes verifying whether a quantity type of the data source data conforms to a data type input by the selected data prediction model, and the flow verification further includes verifying whether a combination of the selected data preprocessing algorithm and the selected data prediction algorithm is a combination in a preset combination library; the central layer is also used for feeding back a process verification result to the view layer;
and when the quantity type of the data source data accords with the data type input by the selected data prediction model and the combination of the selected data preprocessing algorithm and the selected data prediction algorithm is a combination in a preset combination library, the central layer inputs the data to be predicted into the selected data prediction algorithm to obtain a prediction result.
Optionally, the view layer is further configured to set parameters for the selected data preprocessing algorithm and the selected data prediction algorithm, respectively.
Optionally, the access layer includes a data access unit, a data preprocessing unit, and a data caching unit;
the data access unit is used for accessing real-time streaming data into data source data according to the source address of the data to be predicted;
the data preprocessing unit is used for preprocessing the data source data according to the selected data preprocessing algorithm to obtain data to be predicted;
and the data caching unit is used for caching the data to be predicted output by the data preprocessing unit.
Optionally, the data prediction algorithm comprises YOLOv3, fast RCNN and RetinaNet.
Optionally, the data processing in the data preprocessing algorithm includes data noise processing or data missing value padding processing.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects:
the invention discloses a dragging type traffic-field-oriented data prediction system, which selects a traffic scene, a data preprocessing algorithm, a data prediction algorithm and a data source address through a view layer, verifies whether the selected data preprocessing algorithm, the selected data prediction algorithm and the data source address to be predicted are matched through a center layer, predicts data to be predicted acquired by an access layer according to the data source address to be predicted by adopting the selected data prediction algorithm after the verification is passed, obtains a prediction result, reduces the difficulty degree of application of a deep learning algorithm, and improves the data prediction efficiency in the traffic field.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise.
FIG. 1 is a schematic structural diagram of a drag-type traffic-domain-oriented data prediction system according to the present invention;
FIG. 2 is a detailed structural diagram of a dragging type traffic-domain-oriented data prediction system according to the present invention;
FIG. 3 is a schematic view of a viewing layer process of the present invention;
FIG. 4 is a schematic diagram of the core layer process of the present invention;
fig. 5 is a schematic view of the access stratum operation flow of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention aims to provide a dragging type traffic field-oriented data prediction system, which improves the data prediction efficiency of the traffic field.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
Fig. 1 is a schematic structural diagram of a dragged traffic-domain-oriented data prediction system of the present invention, and fig. 2 is a detailed structural diagram of a dragged traffic-domain-oriented data prediction system of the present invention, as shown in fig. 1-2, a dragged traffic-domain-oriented data prediction system includes:
the view layer is used for selecting one traffic scene from a plurality of set traffic scenes as a traffic scene to be predicted; the system is also used for selecting a data preprocessing algorithm and a data prediction algorithm based on the traffic scene to be predicted to obtain the selected data preprocessing algorithm and the selected data prediction algorithm; the device is also used for selecting one from a plurality of data source addresses as a data source address to be predicted; the device is also used for displaying the prediction result; the data prediction algorithm is a deep learning algorithm.
And the viewing layer selects a traffic scene, a data preprocessing algorithm, a data prediction algorithm and a data source address in a dragging mode. The view layer is also used for setting parameters for the selected data preprocessing algorithm and the selected data prediction algorithm respectively.
The traffic scene comprises a vehicle flow speed and flow prediction scene of a set part of road sections and a toll station congestion duration prediction scene.
Data prediction algorithms include YOLOv3, fast RCNN, and RetinaNet. The data prediction algorithm is a trained data prediction algorithm.
The data processing in the data preprocessing algorithm includes data noise processing or data missing value padding processing.
The data source address includes a URL address.
The view layer is a user operation interface and is mainly used for selecting a traffic scene, a dragging selection algorithm (a data preprocessing algorithm and a data prediction algorithm), setting parameters, selecting data (a data source address to be predicted) and displaying operation information. The operation information displayed by the view layer comprises a verification result and a prediction result. For example, when the traffic scene to be predicted is a vehicle flow speed and flow prediction scene of a set part of road sections, the prediction result is the vehicle flow speed and the vehicle flow of the part of road sections corresponding to the data source address to be predicted, and when the traffic scene to be predicted is a congestion duration prediction scene of the toll gate, the prediction result is the congestion duration of the toll gate corresponding to the data source address to be predicted. The view layer is also used for viewing the current state information of the system.
The view layer is beneficial to clear problem division through scene selection, provides an algorithm under a corresponding scene and uses a data modularization dragging function, and a user can drag the modularization algorithm and the data to a corresponding scene flow chart to construct a complete processing process of the selected scene problem, and meanwhile, the processing process includes but is not limited to transmitting various corresponding parameters to the central layer in an Http or Http request mode and starting execution of the flow chart.
As shown in fig. 3, the user drags the selected scene, the data source, the data preprocessing algorithm, the data processing algorithm, the setting algorithm parameters, and the like using the front-end interface (the viewing layer).
In fig. 3, the view layer workflow includes: 1. the general user needs to select a scenario at the front end, which is defined as the actual problem to be solved, including but not limited to as shown in fig. 3: toll station congestion prediction, holiday flow rate prediction, ETC long-time prediction (prediction of high-speed vehicle flow rate), and the like. By selecting a scene, the system automatically updates a data preprocessing algorithm and an AI algorithm (data prediction algorithm) which can be used for displaying the current scene; 2. on the basis of determining a problem to be solved by a selected scene, real-time data for solving the problem needs to be set, and the step is completed by filling an address in a front end, wherein the address form comprises but is not limited to URL; 3. in the step, a data preprocessing algorithm to be used for data accessed by the filling address is selected, such as data noise processing, data missing value filling and the like; 4. setting a deep learning AI algorithm required for solving the scene problem, wherein the algorithm works on the preprocessed data; 5. in the step, specific pop-up explanations and prompts are provided for the selected algorithm setting parameters, the functions of the parameters and the range of the set values; 6. the steps 1-5 form a complete data processing flow chart, the validity of the generated flow chart is verified, if the generated flow chart is passed, a detailed problem prompt is displayed, and a user is guided to correct the generated flow chart; 7. clicking to start executing the scene flow chart and waiting for an execution result.
The core key points of the viewing layer are as follows: 1. establishing a flow chart through dragging type flow chart step prompts, and simultaneously performing popup prompt on details in each step; 2. the result of the dragging can be displayed to the user in the process and result style of the complete flow chart, and the system gives errors possibly existing in the flow chart and carries out verification on the integrity of the flow chart. The execution and display of the viewing layer greatly reduce the understanding of operators on the deep learning algorithm, and only needs to drag according to requirements. The matching between the algorithm and the data is automatically selected and listed by the system, and the core parameter setting of the algorithm comprises detailed function description and default value setting.
As shown in fig. 4, the central layer receives the execution request from the front end, executes the flowchart, and feeds back the execution result in real time. In fig. 4, the central layer starts from an execution command issued by the view layer to be received, and the work flow is as follows: 1. after receiving a scene flow chart execution command issued by a view layer, a central layer checks the scene flow chart, including but not limited to setting parameters, algorithm matching and the like, if the check is passed, the central layer executes the scene flow chart, and if the check is not passed, error information is fed back to a front end view layer; 2. on the basis that the verification of the step 1 is passed, the mapping relation between the flow chart and the scene is put into a back-end database so as to search the data address, the scene and the algorithm used by the flow chart; 3. after the step 2 is stored in the database, the mapping relation stored in the database is scheduled, such as used data addresses, used algorithms, set parameters and the like, and codes are automatically organized to be matched to be operated; 4. the central layer informs the data access layer to start accessing data according to requirements, puts the data in a cache, and simultaneously starts an algorithm thread to start executing front-end requirements; 5. and the central layer retrieves the data from the cache, executes the data and feeds the result back to the front-end view layer in real time.
The core key point of the central layer is two, which are respectively: 1. the central layer automatically constructs a mapping relation according to the scene task flow chart and stores the mapping relation in a database, and all running codes are automatically organized and constructed through mapping. 2. The data access and result processing are real-time, the platform supports streaming data access, real data accessed in real time are processed immediately instead of pre-storing the data in advance, and meanwhile, the platform adopts a mode of processing and feedback at the same time, so that the front end can see the real-time processing result.
And the central layer is used for connecting with the view layer, receiving the data to be predicted, inputting the data to be predicted into a selected data prediction algorithm to obtain a prediction result, and feeding the prediction result back to the view layer.
The central layer is used for carrying out flow verification according to the selected data preprocessing algorithm, the selected data prediction algorithm and the source address of the data to be predicted, the flow verification comprises the steps of verifying whether the quantity type of the data source data accords with the data type input by the selected data prediction model or not, and the flow verification also comprises the steps of verifying whether the combination of the selected data preprocessing algorithm and the selected data prediction algorithm is the combination in a preset combination library or not; the central layer is also used for feeding back the process verification result to the view layer.
The preset composition library specifies a combination relationship between a plurality of data preprocessing algorithms and a plurality of data prediction algorithms, that is, specifies which data prediction algorithm and which data preprocessing algorithm can be combined.
And when the quantity type of the data source data accords with the data type input by the selected data prediction model and the combination of the selected data preprocessing algorithm and the selected data prediction algorithm is a combination in a preset combination library, the central layer inputs the data to be predicted into the selected data prediction algorithm to obtain a prediction result.
The central layer provides data processing services to the view layer and the data access layer. The central layer comprises a request distribution module, a data processing module, a back-end database management module and an algorithm control module.
The request distribution module receives an execution request from the view layer, wherein the request can simultaneously contain various parameters for starting the execution of the flow chart and appoint a corresponding process to respond; and the request distribution module also returns the processing result to the view layer for displaying.
The data processing module and the back-end database management module are matched to access and acquire third-party streaming data, and the corresponding data is submitted to the algorithm control module after being preprocessed and standardized.
And the algorithm control module automatically constructs algorithm service according to the flow chart submitted by the view layer and the real-time data accessed by the data processing module, and returns the execution result to the request distribution module again.
And the access layer is connected with the central layer and used for acquiring data source data according to the source address of the data to be predicted, preprocessing the data source data by adopting a selected data preprocessing algorithm to acquire the data to be predicted and sending the data to be predicted to the central layer.
The access layer comprises a data access unit, a data preprocessing unit and a data caching unit. The data access unit is used for accessing the real-time streaming data into the data source data according to the source address of the data to be predicted. And the data preprocessing unit is used for preprocessing the data source data according to the selected data preprocessing algorithm to obtain the data to be predicted.
And the data caching unit is used for caching the data to be predicted output by the data preprocessing unit. The data cache unit includes but is not limited to functional components using redis and the like.
As shown in fig. 5, the access layer has a real-time streaming data access and cache function, and the work flow of the access layer includes: the access layer uses the data access command waiting for the central layer to issue as a starting point, and firstly checks the data access command of the central layer, such as whether the address is legal or not, whether the format is correct or not, and the like. If the test is not passed, the error information is fed back to the central layer; and if the current data passes the access, starting to use the set address to perform streaming data access, and in the access process, according to a data preprocessing algorithm set by the front end, preprocessing the data, such as data noise, data format adjustment, missing value filling and the like, and meanwhile, putting the processed data into a cache to wait for the central layer to retrieve the real-time data.
The invention adopts a three-layer structure design, the bottom layer is an access layer which is responsible for accessing and caching the online streaming data, and the streaming data access method comprises but is not limited to using a POST request and the like; the second layer is a central layer and is mainly responsible for processing the front-end service logic of the platform, the back-end service logic of the platform and the interaction with the algorithm service process, and the second layer mainly comprises the functions of request distribution, data processing, database management and data prediction algorithm control; the top layer of the third layer is a view layer, a browser-side dragging operation interface is provided for a user, and the main functions comprise scene selection, dragging data and algorithm, request distribution and data display. According to the method, complete codes are automatically constructed according to the algorithm and data dragged and selected by the user, and the prediction result is obtained by operation, so that the full-automatic customizable deep learning prediction method is realized.
The invention provides a dragging type traffic field-oriented data prediction system, wherein a one-stop AI algorithm model construction platform is provided, so that the dragging strong operability is used for providing convenient and visual user operation experience, typical deep learning application scenes in the traffic industry are selected and solved, and an instant and easy-to-use traffic industry data prediction method is provided for users by combining traffic real-time big data.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.
The principles and embodiments of the present invention have been described herein using specific examples, which are provided only to help understand the method and the core concept of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed. In view of the above, the present disclosure should not be construed as limiting the invention.
Claims (7)
1. A drag-and-drop traffic-domain oriented data prediction system, comprising:
the view layer is used for selecting one traffic scene from a plurality of set traffic scenes as a traffic scene to be predicted; the system is also used for selecting a data preprocessing algorithm and a data prediction algorithm based on the traffic scene to be predicted to obtain a selected data preprocessing algorithm and a selected data prediction algorithm; the device is also used for selecting one from a plurality of data source addresses as a data source address to be predicted; the device is also used for displaying the prediction result; the data prediction algorithm is a deep learning algorithm; the view layer selects a traffic scene, a data preprocessing algorithm, a data prediction algorithm and a data source address in a dragging mode;
the central layer is used for being connected with the view layer, receiving data to be predicted, inputting the data to be predicted into the selected data prediction algorithm to obtain a prediction result, and feeding the prediction result back to the view layer;
and the access layer is connected with the central layer and is used for acquiring data source data according to the source address of the data to be predicted, preprocessing the data source data by adopting the selected data preprocessing algorithm to acquire the data to be predicted and sending the data to be predicted to the central layer.
2. The towed traffic-domain-oriented data prediction system of claim 1, wherein the traffic scenarios include a vehicle flow velocity and flow prediction scenario and a toll gate congestion duration prediction scenario for a set portion of road segments.
3. The towed traffic-domain-oriented data prediction system according to claim 1, wherein the central layer is configured to perform a process check according to the selected data preprocessing algorithm, the selected data prediction algorithm, and the source address of the data to be predicted, the process check includes checking whether a quantity type of the data source data matches a data type input by the selected data prediction model, and the process check further includes checking whether a combination of the selected data preprocessing algorithm and the selected data prediction algorithm is a combination in a preset combination library; the central layer is also used for feeding back a process verification result to the view layer;
and when the quantity type of the data source data accords with the data type input by the selected data prediction model and the combination of the selected data preprocessing algorithm and the selected data prediction algorithm is a combination in a preset combination library, the central layer inputs the data to be predicted into the selected data prediction algorithm to obtain a prediction result.
4. The towed traffic-domain oriented data prediction system of claim 1, wherein said view layer is further configured to set parameters for a selected data preprocessing algorithm and a selected data prediction algorithm, respectively.
5. The towed traffic-domain oriented data prediction system of claim 1, wherein the access layer comprises a data access unit and a data caching unit;
the data access unit is used for accessing data source data according to the data source address to be predicted in a real-time streaming manner;
the data preprocessing unit is used for preprocessing the data source data according to the selected data preprocessing algorithm to obtain data to be predicted;
and the data caching unit is used for caching the data to be predicted output by the data preprocessing unit.
6. The towed, traffic-domain oriented data prediction system of claim 1, wherein said data prediction algorithms include YOLOv3, fast RCNN, and RetinaNet.
7. The towed traffic-domain oriented data prediction system of claim 1, wherein the data processing in the data pre-processing algorithm comprises data noise processing or data missing value padding processing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210707677.3A CN114819410B (en) | 2022-06-22 | 2022-06-22 | Dragging type traffic field-oriented data prediction system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210707677.3A CN114819410B (en) | 2022-06-22 | 2022-06-22 | Dragging type traffic field-oriented data prediction system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114819410A true CN114819410A (en) | 2022-07-29 |
| CN114819410B CN114819410B (en) | 2022-10-11 |
Family
ID=82521718
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210707677.3A Active CN114819410B (en) | 2022-06-22 | 2022-06-22 | Dragging type traffic field-oriented data prediction system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114819410B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107704608A (en) * | 2017-10-17 | 2018-02-16 | 北京览群智数据科技有限责任公司 | A kind of OLAP multidimensional analyses and data digging system |
| CN111047190A (en) * | 2019-12-12 | 2020-04-21 | 广西电网有限责任公司 | Diversified business modeling framework system based on interactive learning technology |
| WO2020245639A1 (en) * | 2019-06-07 | 2020-12-10 | Telefonaktiebolaget Lm Ericsson (Publ) | Fault prediction using adaptive model selection |
| CN113128781A (en) * | 2021-04-30 | 2021-07-16 | 大连理工大学 | Distributed industrial energy operation optimization platform for automatically constructing intelligent model and algorithm |
| CN114066172A (en) * | 2021-10-26 | 2022-02-18 | 恒银金融科技股份有限公司 | Banking data studying, judging and analyzing system based on big data technology |
-
2022
- 2022-06-22 CN CN202210707677.3A patent/CN114819410B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107704608A (en) * | 2017-10-17 | 2018-02-16 | 北京览群智数据科技有限责任公司 | A kind of OLAP multidimensional analyses and data digging system |
| WO2020245639A1 (en) * | 2019-06-07 | 2020-12-10 | Telefonaktiebolaget Lm Ericsson (Publ) | Fault prediction using adaptive model selection |
| CN111047190A (en) * | 2019-12-12 | 2020-04-21 | 广西电网有限责任公司 | Diversified business modeling framework system based on interactive learning technology |
| CN113128781A (en) * | 2021-04-30 | 2021-07-16 | 大连理工大学 | Distributed industrial energy operation optimization platform for automatically constructing intelligent model and algorithm |
| CN114066172A (en) * | 2021-10-26 | 2022-02-18 | 恒银金融科技股份有限公司 | Banking data studying, judging and analyzing system based on big data technology |
Non-Patent Citations (2)
| Title |
|---|
| 吴小刚等: "基于大数据的智能交通资源中心体系建设研究", 《智能城市》 * |
| 武兆伟: "高速公路综合指挥调度系统设计", 《科技信息》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114819410B (en) | 2022-10-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110232162B (en) | HTML 5-based flow definition method and system | |
| US11733978B2 (en) | AI facilitated collection of data | |
| CN107832468B (en) | Demand recognition methods and device | |
| CN110727587A (en) | Test data acquisition method and device, storage medium and computer equipment | |
| US20150106723A1 (en) | Tools for locating, curating, editing, and using content of an online library | |
| CN103098051A (en) | Search engine optmization assistant | |
| US20160349978A1 (en) | Knowledge base studio | |
| CN111694561A (en) | Interface management method, device, equipment and storage medium | |
| CN109902251A (en) | Scheme Choice method, apparatus, terminal and readable storage medium storing program for executing based on decision tree | |
| CN112395027A (en) | Widget interface generation method and device, storage medium and electronic equipment | |
| CN114036439A (en) | Website building method, device, medium and electronic equipment | |
| CN114819410B (en) | Dragging type traffic field-oriented data prediction system | |
| CN111459820B (en) | Model application method and device and data analysis processing system | |
| CN111476373B (en) | Artificial intelligence data service system | |
| CN110268400A (en) | Improve the interaction with electronics chat interface | |
| CN109101429B (en) | Method and device for debugging browser page of set top box | |
| CN113722577B (en) | Feedback information processing method, device, equipment and storage medium | |
| CN114625344A (en) | Application service generation system and service process configuration method | |
| CN115269285A (en) | Test method and device, equipment and computer readable storage medium | |
| CN114707961A (en) | Pending task execution method, device, equipment, medium and program product based on approval flow configuration | |
| CN114095360A (en) | Communication service opening method and device | |
| CN111160817A (en) | Goods acceptance method and system, computer system and computer readable storage medium | |
| CN113849418B (en) | Code quality debugging method, server, user equipment and storage medium | |
| CN110659191A (en) | Buried point data analysis method and device, computer equipment and storage medium | |
| CN104834756B (en) | The querying method and device of information in engineering management |
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 |