CN110442657A - A kind of intelligent management platform based on big data - Google Patents
A kind of intelligent management platform based on big data Download PDFInfo
- Publication number
- CN110442657A CN110442657A CN201910718511.XA CN201910718511A CN110442657A CN 110442657 A CN110442657 A CN 110442657A CN 201910718511 A CN201910718511 A CN 201910718511A CN 110442657 A CN110442657 A CN 110442657A
- Authority
- CN
- China
- Prior art keywords
- time series
- data sequence
- series data
- sequence
- data
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
- G06F16/285—Clustering or classification
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/38—Services specially adapted for particular environments, situations or purposes for collecting sensor information
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Arrangements For Transmission Of Measured Signals (AREA)
Abstract
The present invention provides a kind of intelligent management platforms based on big data, including data acquisition subsystem, it is wirelessly transferred subsystem, data process subsystem and data administration subsystem, the data acquisition subsystem acquires time series data sequence using sensor, the wireless transmission subsystem is used to the time series data sequence of acquisition being transmitted to data process subsystem, the data process subsystem is for receiving the time series data sequence and classifying to the time series data sequence, the data administration subsystem is based on time series data sequence classification results and carries out Classification Management to the time series data sequence.The present invention is based on sensors to be acquired a large amount of time series data sequence, sends data to data process subsystem based on telecommunication technique and classifies, and realizes the Classification Management of Various types of data, and can provide guiding opinion for subsequent decision data.
Description
Technical field
The present invention relates to big data technical fields, and in particular to a kind of intelligent management platform based on big data.
Background technique
With the progress of human society and the development of science and technology, the data volume occurred in production and life is increasing,
If by manually handling data, not only treatment effeciency is slow, but also bigger by the subjective impact of people, computer logarithm
According to processing only rest on the simple process of data again, effective information can not be read from data rapidly, cannot achieve to data
Effective Classification Management.
Summary of the invention
In view of the above-mentioned problems, the present invention is intended to provide a kind of intelligent management platform based on big data.
The purpose of the present invention is realized using following technical scheme:
Provide a kind of intelligent management platform based on big data, including data acquisition subsystem, wireless transmission subsystem,
Data process subsystem and data administration subsystem, the data acquisition subsystem acquire time series data sequence using sensor,
The wireless transmission subsystem is used to for the time series data sequence of acquisition being transmitted to data process subsystem, data processing
System is for receiving the time series data sequence and classifying to the time series data sequence, the data administration subsystem base
Classification Management is carried out to the time series data sequence in time series data sequence classification results.
The present invention is based on sensors to be acquired a large amount of time series data sequence, is passed data based on telecommunication technique
It transports to data process subsystem to classify, realizes the Classification Management of Various types of data, and can provide for subsequent decision data
Guiding opinion.
Optionally, the wireless transmission subsystem is based on one or more of mobile 2G, 3G, 4G network and carries out data biography
It is defeated.
Optionally, the data process subsystem includes database module, data metric module and data categorization module, institute
The standard time sequence data sequence that database module is stored with each tag along sort is stated, the data metric module is used for measurement sensor
The similitude of the standard time sequence data sequence of the time series data sequence and each tag along sort of acquisition, the data categorization module are based on
Similarity measurement result determines the tag along sort of the time series data sequence of sensor acquisition.
Optionally, the data metric module includes first similarity measurement submodule, second similarity measurement submodule
Submodule is generated with measurement results, the first similarity measurement submodule is similar for first between calculating time series data sequence
The factor, the second similarity measurement submodule are used to calculate the second similar factors between time series data sequence, the measurement knot
Fruit generates submodule based on the first similarity factor and second similarity factor calculating time series data sequence between time series data sequence
Similarity between column.
Optionally, the first similarity measurement submodule is used to calculate the first similar factors between time series data sequence,
Specifically:
Intercept sensor acquisition time series data sequence, guarantee interception after sensor acquire time series data sequence with it is all kinds of
The standard time sequence data sequence of label includes that data number is identical;
Time series data sequence S is calculated using following formulai、SjThe first similar factors D1(Si, Sj):
In formula, D1(Si, Sj) indicate time series data sequence Si、SjThe first similar factors, Si=(si1, si2..., sin), sik
Indicate k-th of data in the time series data sequence of i-th of sensor acquisition, Sj=(sj1, sj2..., sjn), sjkIt indicates j-th
K-th of data in the standard time sequence data sequence of tag along sort, k=1,2 ..., n.
Optionally, the second similarity measurement submodule is used to calculate the second similar factors between time series data sequence,
Specifically:
Intercept sensor acquisition time series data sequence, guarantee interception after sensor acquire time series data sequence with it is all kinds of
The standard time sequence data sequence of label includes that data number is identical;
Time series data sequence S is calculated using following formulai、SjThe second similar factors D2(Si, Sj):
In formula, D2(Si, Sj) indicate time series data sequence Si、SjThe second similar factors, Si=(si1, si2..., sin), sik
Indicate k-th of data in the time series data sequence of i-th of sensor acquisition, Sj=(sj1, sj2..., sjn), sjkIt indicates j-th
K-th of data in the standard time sequence data sequence of tag along sort, k=1,2 ..., n.
Optionally, the measurement results generate submodule based on the first similarity factor and second between time series data sequence
Similarity factor calculates the similarity between time series data sequence, specifically:
Time series data sequence S is calculated using following formulai、SjSimilarity:
D(Si, Sj)=b1D1(Si, Sj)+b2D2(Si, Sj)
In formula, D (Si, Sj) indicate time series data sequence Si、SjSimilarity, b1、b2Respectively indicate the first similar factors
With the weight of the second similar factors, b1+b2=1;The time series data sequence Si、SjSimilarity it is bigger, indicate time series data
Sequence Si、SjSimilarity degree it is higher.
Optionally, the data categorization module determines the time series data sequence of sensor acquisition based on similarity measurement result
Tag along sort, specifically:
The similarity of the time series data sequence of sensor acquisition and the standard time sequence data sequence of each tag along sort is calculated,
The classification for the time series data sequence that the tag along sort of the maximum standard time sequence data sequence of similarity is acquired as sensor
Label realizes the classification to sensor time series data sequence.
Detailed description of the invention
The present invention will be further described with reference to the accompanying drawings, but the embodiment in attached drawing is not constituted to any limit of the invention
System, for those of ordinary skill in the art, without creative efforts, can also obtain according to the following drawings
Other attached drawings.
Fig. 1 is structural schematic diagram of the invention;
Fig. 2 is the structural schematic diagram of data process subsystem of the present invention.
Appended drawing reference:
Data acquisition subsystem 1, wireless transmission subsystem 2, data process subsystem 3, data administration subsystem 4, data
Library module 5, data metric module 6, data categorization module 7.
Specific embodiment
The invention will be further described with the following Examples.
Referring to Fig. 1, Fig. 2, a kind of intelligent management platform based on big data, including data acquisition are present embodiments provided
System 1, wireless transmission subsystem 2, data process subsystem 3 and data administration subsystem 4,1 benefit of data acquisition subsystem
Time series data sequence is acquired with sensor, the wireless transmission subsystem 2 is used to the time series data sequence of acquisition being transmitted to number
According to processing subsystem 3, the data process subsystem 3 is for receiving the time series data sequence and to the time series data sequence
Classify, the data administration subsystem 4 is based on time series data sequence classification results and divides the time series data sequence
Class management.
Purpose based on intelligent management, which carries out data acquisition using different sensors, according to biography
The time series data sequence of the difference of sensor type, acquisition is different, data process subsystem 3 be based on sensor type to it is corresponding when
Sequence data sequence is classified, to achieve the purpose that obtain time series data sequence classification information, is mentioned for subsequent information decision
For good basis.
The present embodiment is based on sensor and is acquired to a large amount of time series data sequence, is based on telecommunication technique for data
It is transmitted to data process subsystem to classify, realizes the Classification Management of Various types of data, and can mention for subsequent decision data
For guiding opinion.
Preferably, the wireless transmission subsystem 2 is based on one or more of mobile 2G, 3G, 4G network and carries out data
Transmission.
In the arduouser remote districts of condition, which can be used 2G network and 3G network carries out data
Transmission, in the relatively advanced city of 4G network, is carried out data transmission using 4G network, when 4G network signal is bad,
It can be carried out data transmission using 2G network and 3G network.
This preferred embodiment realizes the data transmission of different regions, even if also can guarantee in the area of no 4G network
Sensing data carries out timely and effective transmission, to improve the application range of the intelligent management platform.
Preferably, the data process subsystem 3 includes database module 5, data metric module 6 and data categorization module
7, the database module 5 is stored with the standard time sequence data sequence of each tag along sort, and the data metric module 6 is for measuring
The similitude of the standard time sequence data sequence of the time series data sequence and each tag along sort of sensor acquisition, the data classification mould
Block 7 determines the tag along sort of the time series data sequence of sensor acquisition based on similarity measurement result.
Specifically, the database module 5 is stored with the standard time sequence data sequence of each tag along sort, according to intelligent management
The concrete application of platform is different, and corresponding sensor type is different, and the time series data sequence of acquisition is different, database module 5 with
Internet connection, is stored with the standard time sequence data sequence of each tag along sort under different application field;When sensor is temperature
Sensor is acquired the status temperature in a certain area, then database module 5 store tag along sort be high temperature, it is medium temperature, low
The standard time sequence data sequence of temperature, cold lower corresponding temperature, by the time series data sequence of temperature sensor acquisition respectively with high temperature,
The standard time sequence data sequence of the lower corresponding temperature of medium temperature, low temperature, cold carries out similarity measurement, realizes and acquires to current sensor
Temperature classification, for next step sunstroke prevention resisting cold be ready.
When sensor be current sensor, certain power equipment electric current is acquired, then database module 5 store contingency table
Label are normal, overcurrent, the standard time sequence data sequence of the relatively low lower corresponding current of electric current, the time series data that current sensor is acquired
Sequence carries out similarity measurement, realization pair with normal, overcurrent, the standard time sequence data sequence of the relatively low lower corresponding current of electric current respectively
The classification of the electric current of current sensor acquisition provides valid data for device diagnostic maintenance.
When sensor be blood pressure sensor, the blood pressure of human body is acquired, then database module 5 store tag along sort be
Normally, the standard time sequence data sequence that blood pressure is corresponded under hypertension, low blood pressure, the time series data sequence that blood pressure sensor is acquired
Similarity measurement is carried out with the standard time sequence data sequence for corresponding to blood pressure under normal, hypertension, low blood pressure respectively, is realized to current
The classification of the blood pressure of sensor acquisition, provides effective suggestion for medical diagnosis.
This preferred embodiment lists the data processing and application of intelligent management platform under three kinds of situations, realizes day respectively
Gas forecast, electric equipment diagnosis and distance medical diagnosis.
Certainly, the intelligent management platform be not limited to processing single-sensor situation under data classification administrative decision, into
When row weather forecasting, multidimensional data can be carried out using temperature sensor, humidity sensor, wind direction sensor simultaneously and adopted
Collection will be in various kinds of sensors data and database module 5 since database module 5 stores largely existing normal data
Standard time sequence data are compared, and can be realized the comprehensive forecast of weather.Similarly, clinical thermometer, cardiotachometer, blood pressure can be used
The multiple sensors such as sensor carry out comprehensive diagnos to health.
Preferably, the data metric module 6 includes first similarity measurement submodule, second similarity measurement submodule
Submodule is generated with measurement results, the first similarity measurement submodule is similar for first between calculating time series data sequence
The factor, the second similarity measurement submodule are used to calculate the second similar factors between time series data sequence, the measurement knot
Fruit generates submodule based on the first similarity factor and second similarity factor calculating time series data sequence between time series data sequence
Similarity between column.
This preferred embodiment provides a kind of new method of similarity measurement, establishes similarity measurement new model, passes through
The first similar factors of resume and the second similar factors calculate the similitude of time series data sequence, it is accurate to improve similarity measurement
Property.
Preferably, the first similarity measurement submodule is used to calculate the first similar factors between time series data sequence,
Specifically:
Intercept sensor acquisition time series data sequence, guarantee interception after sensor acquire time series data sequence with it is all kinds of
The standard time sequence data sequence of label includes that data number is identical;
Time series data sequence S is calculated using following formulai、SjThe first similar factors D1(Si, Sj):
In formula, D1(Si, Sj) indicate time series data sequence Si、SjThe first similar factors, Si=(si1, si2..., sin), sik
Indicate k-th of data in the time series data sequence of i-th of sensor acquisition, Sj=(sj1, sj2..., sjn), sjkIt indicates j-th
K-th of data in the standard time sequence data sequence of tag along sort, k=1,2 ..., n.
This preferred embodiment by the time series data sequence truncation of acquisition length identical with standard time sequence ordered series of numbers, is convenient for first
Similarity measurement is carried out, the first similar factors consider the numerical characteristics of time series data sequence, in metrics process, overcome list
One the drawbacks of being measured by time series data sequence overall trend.
Preferably, the second similarity measurement submodule is used to calculate the second similar factors between time series data sequence,
Specifically:
Intercept sensor acquisition time series data sequence, guarantee interception after sensor acquire time series data sequence with it is all kinds of
The standard time sequence data sequence of label includes that data number is identical;
Time series data sequence S is calculated using following formulai、SjThe second similar factors D2(Si, Sj):
In formula, D2(Si, Sj) indicate time series data sequence Si、SjThe second similar factors, Si=(si1, si2..., sin), sik
Indicate k-th of data in the time series data sequence of i-th of sensor acquisition, Sj=(sj1, sj2..., sjn), sjkIt indicates j-th
K-th of data in the standard time sequence data sequence of tag along sort, k=1,2 ..., n.
This preferred embodiment by the time series data sequence truncation of acquisition length identical with standard time sequence ordered series of numbers, is convenient for first
Similarity measurement is carried out, the second similar factors consider the trend feature of time series data sequence, in metrics process, overcome list
One the drawbacks of being measured by time series data sequential digit values.
Preferably, the measurement results generate submodule based on the first similarity factor and second between time series data sequence
Similarity factor calculates the similarity between time series data sequence, specifically:
Time series data sequence S is calculated using following formulai、SjSimilarity:
D(Si, Sj)=b1D1(Si, Sj)+b2D2(Si, Sj)
In formula, D (Si, Sj) indicate time series data sequence Si、SjSimilarity, b1、b2Respectively indicate the first similar factors
With the weight of the second similar factors, b1+b2=1;The time series data sequence Si、SjSimilarity it is bigger, indicate time series data
Sequence Si、SjSimilarity degree it is higher.
In the specific application process, b1、b2Weight can be adjusted according to practical application, if in similarity measurement
The variation tendency of time series data sequence occupies main status in the process, at this point, should suitably increase b2Value, if in similitude
In metrics process, more focus on the difference of numerical value itself, at this point, should suitably increase b1Value.
This preferential implementation considers two spies of numerical value and trend in time series data sequence simultaneously during similarity measurement
Sign, obtained classification results are more accurate, and the application of the intelligent management platform is more extensive.
Preferably, the data categorization module 7 determines the time series data sequence of sensor acquisition based on similarity measurement result
The tag along sort of column, specifically:
The similarity of the time series data sequence of sensor acquisition and the standard time sequence data sequence of each tag along sort is calculated,
The classification for the time series data sequence that the tag along sort of the maximum standard time sequence data sequence of similarity is acquired as sensor
Label realizes the classification to sensor time series data sequence.
Through the above description of the embodiments, those skilled in the art can be understood that it should be appreciated that can
To realize the embodiments described herein with hardware, software, firmware, middleware, code or its any appropriate combination.For hardware
It realizes, processor can be realized in one or more the following units: specific integrated circuit (ASIC), digital signal processor
(DSP), digital signal processing appts (DSPD), programmable logic device (PLD), field programmable gate array (FPGA), processing
Device, controller, microcontroller, microprocessor, other electronic units designed for realizing functions described herein or combinations thereof.
For software implementations, some or all of embodiment process can instruct relevant hardware to complete by computer program.
When realization, above procedure can be stored in computer-readable medium or as the one or more on computer-readable medium
Instruction or code are transmitted.Computer-readable medium includes computer storage media and communication media, wherein communication media packet
It includes convenient for from a place to any medium of another place transmission computer program.Storage medium can be computer can
Any usable medium of access.Computer-readable medium can include but is not limited to RAM, ROM, EEPROM, CD-ROM or other
Optical disc storage, magnetic disk storage medium or other magnetic storage apparatus or can be used in carry or store have instruction or data
The desired program code of structure type simultaneously can be by any other medium of computer access.
Finally it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than the present invention is protected
The limitation for protecting range, although being explained in detail referring to preferred embodiment to the present invention, the ordinary skill destination of this field
It should be appreciated that can be with modification or equivalent replacement of the technical solution of the present invention are made, without departing from technical solution of the present invention
Spirit and scope.
Claims (8)
1. a kind of intelligent management platform based on big data, which is characterized in that including data acquisition subsystem, wireless transmission subsystem
System, data process subsystem and data administration subsystem, the data acquisition subsystem acquire time series data sequence using sensor
Column, the wireless transmission subsystem is for being transmitted to data process subsystem for the time series data sequence of acquisition, at the data
Reason subsystem is for receiving the time series data sequence and classifying to the time series data sequence, the data management subsystem
System carries out Classification Management to the time series data sequence based on time series data sequence classification results.
2. the intelligent management platform according to claim 1 based on big data, which is characterized in that the wireless transmission subsystem
System is carried out data transmission based on one or more of mobile 2G, 3G, 4G network.
3. the intelligent management platform according to claim 1 based on big data, which is characterized in that the data processing subsystem
System includes database module, data metric module and data categorization module, and the database module is stored with each tag along sort
Standard time sequence data sequence, time series data sequence and each tag along sort of the data metric module for measurement sensor acquisition
Standard time sequence data sequence similitude, the data categorization module based on similarity measurement result determine sensor acquisition
The tag along sort of time series data sequence.
4. the intelligent management platform according to claim 3 based on big data, which is characterized in that the data metric module
Submodule, first phase are generated including first similarity measurement submodule, second similarity measurement submodule and measurement results
It is used to calculate the first similar factors between time series data sequence like property measurement submodule, the second similarity measurement submodule is used
The second similar factors between calculating time series data sequence, the measurement results generate submodule based between time series data sequence
The first similarity factor and the second similarity factor calculate the similarity between time series data sequence.
5. the intelligent management platform according to claim 4 based on big data, which is characterized in that the first similarity degree
Quantum module is used to calculate the first similar factors between time series data sequence, specifically:
The time series data sequence of sensor acquisition is intercepted, guarantees sensor acquires after intercepting time series data sequence and all kinds of labels
Standard time sequence data sequence include data number it is identical;
Time series data sequence S is calculated using following formulai、SjThe first similar factors D1(Si, Sj):
In formula, D1(Si, Sj) indicate time series data sequence Si、SjThe first similar factors, Si=(si1, si2..., sin), sikIt indicates
K-th of data in the time series data sequence of i-th of sensor acquisition, Sj=(sj1, sj2..., sjn), sjkIndicate j-th of classification
K-th of data in the standard time sequence data sequence of label, k=1,2 ..., n.
6. the intelligent management platform according to claim 5 based on big data, which is characterized in that the second similarity degree
Quantum module is used to calculate the second similar factors between time series data sequence, specifically:
The time series data sequence of sensor acquisition is intercepted, guarantees sensor acquires after intercepting time series data sequence and all kinds of labels
Standard time sequence data sequence include data number it is identical;
Time series data sequence S is calculated using following formulai、SjThe second similar factors D2(Si, Sj):
In formula, D2(Si, Sj) indicate time series data sequence Si、SjThe second similar factors, Si=(si1, si2..., sin), sikIt indicates
K-th of data in the time series data sequence of i-th of sensor acquisition, Sj=(sj1, sj2..., sjn), sjkIndicate j-th of classification
K-th of data in the standard time sequence data sequence of label, k=1,2 ..., n.
7. the intelligent management platform according to claim 6 based on big data, which is characterized in that the measurement results generate
Submodule is calculated based on the first similarity factor between time series data sequence and the second similarity factor between time series data sequence
Similarity, specifically:
Time series data sequence S is calculated using following formulai、SjSimilarity:
D(Si, Sj)=b1D1(Si, Sj)+b2D2(Si, Sj)
In formula, D (Si, Sj) indicate time series data sequence Si、SjSimilarity, b1、b2Respectively indicate the first similar factors and
The weight of two similar factors, b1+b2=1;The time series data sequence Si、SjSimilarity it is bigger, indicate time series data sequence
Si、SjSimilarity degree it is higher.
8. the intelligent management platform according to claim 7 based on big data, which is characterized in that the data categorization module
The tag along sort of the time series data sequence of sensor acquisition is determined based on similarity measurement result, specifically:
The similarity for calculating the time series data sequence of sensor acquisition and the standard time sequence data sequence of each tag along sort, by phase
Like the tag along sort for the time series data sequence that the tag along sort that property is worth maximum standard time sequence data sequence is acquired as sensor,
Realize the classification to sensor time series data sequence.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910718511.XA CN110442657A (en) | 2019-08-05 | 2019-08-05 | A kind of intelligent management platform based on big data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910718511.XA CN110442657A (en) | 2019-08-05 | 2019-08-05 | A kind of intelligent management platform based on big data |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110442657A true CN110442657A (en) | 2019-11-12 |
Family
ID=68433241
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910718511.XA Pending CN110442657A (en) | 2019-08-05 | 2019-08-05 | A kind of intelligent management platform based on big data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110442657A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112487045A (en) * | 2020-10-20 | 2021-03-12 | 广西盛源行大数据科技有限公司 | Management platform based on big data |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106127150A (en) * | 2016-06-23 | 2016-11-16 | 华中科技大学 | A kind of measure of Time Series Similarity |
CN106779505A (en) * | 2017-02-28 | 2017-05-31 | 中国南方电网有限责任公司 | A kind of transmission line malfunction method for early warning driven based on big data and system |
CN108090241A (en) * | 2016-11-23 | 2018-05-29 | 财团法人工业技术研究院 | trend variable identification method and system of continuous process |
CN108981781A (en) * | 2017-05-30 | 2018-12-11 | 迪尔公司 | For analyzing and detecting the hypothesis analysis system and method for machine sensor fault |
CN110032670A (en) * | 2019-04-17 | 2019-07-19 | 腾讯科技(深圳)有限公司 | Method for detecting abnormality, device, equipment and the storage medium of time series data |
-
2019
- 2019-08-05 CN CN201910718511.XA patent/CN110442657A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106127150A (en) * | 2016-06-23 | 2016-11-16 | 华中科技大学 | A kind of measure of Time Series Similarity |
CN108090241A (en) * | 2016-11-23 | 2018-05-29 | 财团法人工业技术研究院 | trend variable identification method and system of continuous process |
CN106779505A (en) * | 2017-02-28 | 2017-05-31 | 中国南方电网有限责任公司 | A kind of transmission line malfunction method for early warning driven based on big data and system |
CN108981781A (en) * | 2017-05-30 | 2018-12-11 | 迪尔公司 | For analyzing and detecting the hypothesis analysis system and method for machine sensor fault |
CN110032670A (en) * | 2019-04-17 | 2019-07-19 | 腾讯科技(深圳)有限公司 | Method for detecting abnormality, device, equipment and the storage medium of time series data |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112487045A (en) * | 2020-10-20 | 2021-03-12 | 广西盛源行大数据科技有限公司 | Management platform based on big data |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107742127A (en) | A kind of improved anti-electricity-theft intelligent early-warning system and method | |
CN109450956A (en) | Internet security appraisal procedure, system, medium and calculating equipment | |
CN109257383A (en) | A kind of BGP method for detecting abnormality and system | |
CN107958395A (en) | A kind of recognition methods of electric system abnormal user | |
CN107679089A (en) | A kind of cleaning method for electric power sensing data, device and system | |
Hou et al. | Damage probability assessment of transmission line-tower system under typhoon disaster, based on model-driven and data-driven views | |
CN111081379A (en) | Disease probability decision method and system | |
CN110442657A (en) | A kind of intelligent management platform based on big data | |
CN108281177A (en) | A kind of Internet of Things intensive care monitoring system | |
CN104274164A (en) | Blood pressure predicting method and mobile phone based on facial image | |
CN115329904A (en) | Outlier detection method, system and storage medium for distinguishing population data | |
CN113707323B (en) | Disease prediction method, device, equipment and medium based on machine learning | |
Assaf et al. | Assessing the Vulnerability of Communities Exposed to Climate Change-Related Challenges Caused by the Urban Heat Island Effect Using Machine Learning | |
CN206251240U (en) | A kind of active wisdom endowment system based on motion perception analysis | |
CN107729206A (en) | Real-time analysis method, system and the computer-processing equipment of alarm log | |
CN106971361A (en) | A kind of professional ability remote test system and professional ability remote test method | |
JP2024031759A (en) | Ventilation control system, ventilation control device, and ventilation control program | |
CN110223788A (en) | User health management system based on portable equipment | |
CN116957585A (en) | Data processing method, device, equipment and storage medium | |
CN110020746A (en) | A kind of risk prevention system method, apparatus, processing equipment and system | |
CN115034839A (en) | Office area state detection method and device, storage medium and electronic equipment | |
Zhang et al. | Prediction of traffic accident impact range based on CatBoost ensemble algorithm | |
CN110277834A (en) | A kind of grid responsive building interior load monitoring method, system and storage medium | |
CN206611451U (en) | Community data shares Transmission system | |
Xiong et al. | State Evaluation of Self-Powered Wireless Sensors Based on a Fuzzy Comprehensive Evaluation Model |
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 |