CN109450567A - Frequency range degree Tendency Prediction method and apparatus - Google Patents
Frequency range degree Tendency Prediction method and apparatus Download PDFInfo
- Publication number
- CN109450567A CN109450567A CN201811295194.7A CN201811295194A CN109450567A CN 109450567 A CN109450567 A CN 109450567A CN 201811295194 A CN201811295194 A CN 201811295194A CN 109450567 A CN109450567 A CN 109450567A
- Authority
- CN
- China
- Prior art keywords
- frequency range
- range degree
- situation
- degree
- tendency prediction
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B17/00—Monitoring; Testing
- H04B17/30—Monitoring; Testing of propagation channels
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B17/00—Monitoring; Testing
- H04B17/30—Monitoring; Testing of propagation channels
- H04B17/373—Predicting channel quality or other radio frequency [RF] parameters
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B17/00—Monitoring; Testing
- H04B17/30—Monitoring; Testing of propagation channels
- H04B17/391—Modelling the propagation channel
- H04B17/3913—Predictive models, e.g. based on neural network models
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Electromagnetism (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Quality & Reliability (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The present invention provides a kind of frequency range degree Tendency Prediction method and apparatus, are related to radio communication field.Decompose by the frequency range degree to the continuous time point first and generates the corresponding frequency range degree of multiple current slots；Then the situation feature of the corresponding frequency range degree of the multiple current slot is extracted；It is last that according to currently extracting, the situation feature of the corresponding frequency range degree of multiple current slots, the corresponding frequency range degree situation of the situation feature training sample of the non-linear Tendency Prediction model of training, the situation feature training sample of pre-stored multiple history frequency range degree and each history frequency range degree generates the corresponding multiple future time section frequency range degree situation of multiple current slots in advance；The corresponding multiple future time section frequency range degree situation of multiple current slots are synthetically generated frequency range degree Tendency Prediction as a result, to realize prediction to frequency range degree further trend, and prediction result is accurate, high reliablity.
Description
Technical field
The present invention relates to radio communication fields, in particular to a kind of frequency range degree Tendency Prediction method and dress
It sets.
Background technique
Radio refers in the electromagnetic wave that all free spaces (including air and vacuum) is propagated, and is that one of those is limited
Frequency band, upper limiting frequency common are 3kHz in various Radio Specification books compared with disunity in 300GHz (girz), lower frequency limit
~300GHz, 9kHz~300GHz, 10kHz~300GHz.It is responsible for the monitoring of radio, monitors in radio guard；Radio
Equipment detection；Measurement of electromagnetic environment；The interference lookup of radio and related work.Radio monitoring is the technology of radio control
Means and mode, the different business including the different frequency range to radio have carried out tendentious monitoring and monitoring.Radio prison
Survey mainly include shortwave, ultrashort wave and satellite band monitoring, in traditional technology, usually progress real-time monitoring.Wireless communication
Used in frequency range be small part in electromagnetic wave frequency range, define the frequency range of radio wave.What tradition used
In technology, radio control department can not grasp the situation in frequency spectrum resource future, and the situation Added Management decision according to future,
Radio Spectrum Resource can not efficiently be utilized.
Summary of the invention
In view of this, the embodiment of the present invention is designed to provide a kind of frequency range degree Tendency Prediction method and apparatus,
To improve above-mentioned problem.
In a first aspect, the embodiment of the invention provides a kind of frequency range degree Tendency Prediction method, the frequency range degree
Tendency Prediction method includes:
Receive the frequency range degree in continuous time point that intelligent terminal is sent；
The frequency range degree of the continuous time point decompose and generates the corresponding frequency range occupancy of multiple current slots
Degree；
Extract the situation feature of the corresponding frequency range degree of the multiple current slot；
According to currently extracting, the situation feature of the corresponding frequency range degree of multiple current slots, training is non-thread in advance
Condition gesture prediction model, the situation feature training sample of pre-stored multiple history frequency range degree and each history frequency range account for
When the multiple current slots of the corresponding frequency range degree situation generation of the situation feature training sample of expenditure are corresponding multiple following
Between section frequency range degree situation；
The corresponding multiple future time section frequency range degree situation of multiple current slots are synthetically generated frequency range degree
Tendency Prediction result.
Second aspect, the embodiment of the invention provides a kind of frequency range degree Tendency Prediction device, the frequency range degree
Tendency Prediction device includes:
Information receiving unit, for receiving the frequency range degree in continuous time point of intelligent terminal transmission；
Signal decomposition unit carries out decomposing the multiple current times of generation for the frequency range degree to the continuous time point
The corresponding frequency range degree of section；
Feature extraction unit, for extracting the situation feature of the corresponding frequency range degree of the multiple current slot；
Predicting unit, for according to currently extract the corresponding frequency range degree of multiple current slots situation feature,
In advance training non-linear Tendency Prediction model, pre-stored multiple history frequency range degree situation feature training sample and
The corresponding frequency range degree situation of the situation feature training sample of each history frequency range degree generates multiple current slots pair
The multiple future time section frequency range degree situation answered；
As a result generation unit, for closing the corresponding multiple future time section frequency range degree situation of multiple current slots
At generation frequency range degree Tendency Prediction result.
Compared with prior art, frequency range degree Tendency Prediction method and apparatus provided by the invention, first by institute
The frequency range degree for stating continuous time point, which decompose, generates the corresponding frequency range degree of multiple current slots；Then institute is extracted
State the situation feature of the corresponding frequency range degree of multiple current slots；Last foundation currently extracts multiple current slots pair
The situation feature for the frequency range degree answered, the non-linear Tendency Prediction model of training, pre-stored multiple history frequency ranges account in advance
The situation feature training sample of expenditure and the corresponding frequency range of the situation feature training sample of each history frequency range degree occupy
It spends situation and generates the corresponding multiple future time section frequency range degree situation of multiple current slots；By multiple current slots pair
The multiple future time section frequency range degree situation answered are synthetically generated frequency range degree Tendency Prediction as a result, to realize to frequency
The prediction of section degree further trend, and prediction result is accurate, high reliablity, so that radio control department can grasp frequency
The situation in spectrum resource future, and work as frequency range according to following situation Added Management decision efficiently to utilize Radio Spectrum Resource
It when larger difference occurs for degree predicted value and actual monitoring value, regards as being abnormal, and to anomaly classification processing, facilitates
Radio interference discovery, electromagnetic environment anomaly etc..
To enable the above objects, features and advantages of the present invention to be clearer and more comprehensible, preferred embodiment is cited below particularly, and cooperate
Appended attached drawing, is described in detail below.
Detailed description of the invention
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.The present invention being usually described and illustrated herein in the accompanying drawings is implemented
The component of example can be arranged and be designed with a variety of different configurations.Therefore, below to the reality of the invention provided in the accompanying drawings
The detailed description for applying example is not intended to limit the range of claimed invention, but is merely representative of selected implementation of the invention
Example.Based on the embodiments of the present invention, obtained by those of ordinary skill in the art without making creative efforts
Every other embodiment, shall fall within the protection scope of the present invention.
Fig. 1 is the interaction schematic diagram of server provided in an embodiment of the present invention and intelligent terminal；
Fig. 2 is the structural block diagram of server provided in an embodiment of the present invention；
Fig. 3 is the flow chart of frequency range degree Tendency Prediction method provided in an embodiment of the present invention；
Fig. 4 is the functional block diagram of frequency range degree Tendency Prediction device provided in an embodiment of the present invention.
Icon: 100- server；200- intelligent terminal；300- frequency range degree Tendency Prediction device；101- processor；
102- memory；103- storage control；104- Peripheral Interface；401- information receiving unit；402- signal decomposition unit；403-
Feature extraction unit；404- predicting unit；405- result generation unit；406- information transmitting unit.
Specific embodiment
Below in conjunction with attached drawing in the embodiment of the present invention, technical solution in the embodiment of the present invention carries out clear, complete
Ground description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.Usually exist
The component of the embodiment of the present invention described and illustrated in attached drawing can be arranged and be designed with a variety of different configurations herein.Cause
This, is not intended to limit claimed invention to the detailed description of the embodiment of the present invention provided in the accompanying drawings below
Range, but it is merely representative of selected embodiment of the invention.Based on the embodiment of the present invention, those skilled in the art are not doing
Every other embodiment obtained under the premise of creative work out, shall fall within the protection scope of the present invention.
Frequency range degree Tendency Prediction method and apparatus provided by present pre-ferred embodiments can be applied to server
100, which is applied to frequency range degree Tendency Prediction system.As shown in Figure 1, frequency range degree Tendency Prediction system
Comprising server 100 and intelligent terminal 200, communication connection is established between server 100 and intelligent terminal 200.The server 100
It may be, but not limited to, network server, database server, cloud server etc..Fig. 2 shows one kind can be applied to
The structural block diagram of server 100 in the embodiment of the present invention.Wherein, server 100 includes frequency range degree Tendency Prediction device
200, Peripheral Interface 104, memory 102, storage control 103 and processor 101.
Peripheral Interface 104, the memory 102, storage control 103 and processor 101, each element are direct between each other
Or be electrically connected indirectly, to realize the transmission or interaction of data.For example, these elements can pass through one or more between each other
Communication bus or signal wire, which are realized, to be electrically connected.The frequency range degree Tendency Prediction device 200 includes at least one can be soft
The form of part or firmware (firmware) is stored in the memory 102 or solidifies software function module in the server.
The processor 101 is for executing the executable module stored in memory 102, for example, the frequency range degree Tendency Prediction
The software function module or computer program that device 200 includes.
Wherein, memory 102 may be, but not limited to, random access memory (Random Access Memory,
RAM), read-only memory 102Read Only Memory, ROM), programmable read only memory (Programmable Read-
Only Memory, PROM), erasable read-only memory (Erasable Programmable Read-Only Memory,
EPROM), electricallyerasable ROM (EEROM) (Electric Erasable Programmable Read-Only Memory,
EEPROM) etc..Wherein, memory 102 is for storing program, and the processor 101 is after receiving and executing instruction, described in execution
Program, method performed by the server-side that the stream process that aforementioned any embodiment of the embodiment of the present invention discloses defines can be applied to
In processor 101, or realized by processor 101.
Processor 101 may be a kind of IC chip, the processing capacity with signal.Above-mentioned processor 101 can
To be general processor, including central processing unit (Central Processing Unit, abbreviation CPU), network processing unit
(Network Processor, abbreviation NP) etc.；Can also be digital signal processor (DSP), specific integrated circuit (ASIC),
Ready-made programmable gate array (FPGA) either other programmable logic device, discrete gate or transistor logic, discrete hard
Part component.It may be implemented or execute disclosed each method, step and the logic diagram in the embodiment of the present invention.General processor
It can be microprocessor or the processor 101 be also possible to any conventional processor 101 etc..
Various input/output devices are couple processor 101 and memory 102 by Peripheral Interface 104.In some implementations
In example, Peripheral Interface 104, processor 101 and storage control 103 can be realized in one single chip.In some other reality
In example, they can be realized by independent chip respectively.
Referring to Fig. 3, the embodiment of the invention provides a kind of frequency range degree Tendency Prediction method, frequency range degree situation
Prediction technique includes:
Step S301: the frequency range degree in continuous time point that intelligent terminal 200 is sent is received.
Specifically, tranmitting frequency, the power, transmitted bandwidth of signal detection apparatus monitoring wireless electricity can be used, and is transmitted
To intelligent terminal 200, intelligent terminal 200 can be accounted for according to the generation of the feature of the radio listened in the frequency range of continuous time point
Expenditure, and it is transmitted to server 100.
Step S302: the frequency range degree of continuous time point is carried out to decompose the corresponding frequency range of the multiple current slots of generation
Degree.
Specifically, can use small echo signal decomposition method to the frequency range degree of continuous time point carry out decompose generate it is more
The corresponding frequency range degree of a current slot.It is in a presetting detection cycle in the frequency range degree of continuous time point
Frequency range degree, wherein presetting detection cycle can be one day or half a day or one hour etc., do not limit herein
It is fixed.The frequency range degree of continuous time point is decomposed, the feature of the corresponding frequency range degree of extraction time section is more advantageous to.
Step S303: the situation feature of the corresponding frequency range degree of multiple current slots is extracted.
Wherein, multiple time serieses of the corresponding frequency range degree, that is, frequency range degree of multiple current slots, in difference
The frequency range degree of period have different situation features.
Step S304: according to currently extract the corresponding frequency range degree of multiple current slots situation feature, in advance
The situation feature training sample of trained non-linear Tendency Prediction model, pre-stored multiple history frequency range degree and each
It is corresponding that the corresponding frequency range degree situation of the situation feature training sample of history frequency range degree generates multiple current slots
Multiple future time section frequency range degree situation.
Wherein, the non-linear Tendency Prediction model of training is to be instructed using the situation feature of multiple history frequency range degree in advance
Practice the corresponding frequency range degree situation of the situation feature training sample training in advance of sample and each history frequency range degree
Time recurrent neural network algorithm model or decision Tree algorithms model or algorithm of support vector machine model.Wherein, decision Tree algorithms
Model is that decision Tree algorithms are a kind of methods for approaching discrete function value.It is a kind of typical classification method, first to data
It is handled, readable rule and decision tree is generated using inductive algorithm, then new data is analyzed using decision.Essence
Upper decision tree is the process classified by series of rules to data.Decision tree construction can be carried out in two steps, the first step,
The generation of decision tree: the process of decision tree is generated by training sample set.Under normal circumstances, training sample data collection is according to reality
Need it is historied, have certain degree of integration, the data set for Data Analysis Services.Second step, the beta pruning of decision tree: certainly
The beta pruning of plan tree is the process under the decision tree generated on last stage is tested, corrects and repaired, mainly with new sample
The preliminary rule generated in data check Decision Tree Construction in data set (referred to as test data set) influences those pre-
The branch of weighing apparatus accuracy is wiped out.Neural network algorithm model has adaptively and self organization ability, utilizes given sample canonical
Classified or imitated, is carrying out changing synaptic weight value in study or training process according to training sample, to adapt to ring around
The requirement in border.Algorithm of support vector machine model is supervised learning model related to relevant learning algorithm, can analyze data,
Recognition mode gives one group of training sample for classification and regression analysis, and each label is two classes, a SVM training calculation
Method establishes a model, distributes new example as a kind of or other classes, becomes non-probability binary linearity classification.
In addition, the corresponding multiple future time section frequency range degree situation of multiple current slots it is to be understood that for example,
Multiple current slots include first time period, second time period and third period according to time point sequencing, multiple
Future time section includes the 4th period, the 5th period and the 6th period according to time point sequencing, wherein first
Period corresponds to the 5th period, second time period corresponding 6th period, third period corresponding 7th period.
Step S305: the corresponding multiple future time section frequency range degree situation of multiple current slots are synthetically generated frequency
Section degree Tendency Prediction result.
Signal synthetic method be can use by the corresponding multiple future time section frequency range degree situation of multiple current slots
It is synthetically generated frequency range degree Tendency Prediction result.It can be advised according to the variation of component in different time periods by above-mentioned mode
The drawbacks of rule is learnt and predicted respectively, excessively macroscopic viewization is integrally predicted so as to avoid initial data, prediction result and reality
The deviation of border result is smaller, and prediction result is very accurate.
Step S306: frequency range degree Tendency Prediction result is sent to intelligent terminal 200.
To which staff directly can observe frequency range degree Tendency Prediction in intelligent terminal 200200 as a result, convenient
Fast.
Referring to Fig. 4, needing to illustrate the embodiment of the invention provides a kind of frequency range degree Tendency Prediction device 300
Frequency range degree Tendency Prediction device 300 provided by the embodiment of the present invention, the technical effect of basic principle and generation and
Above-described embodiment is identical, and to briefly describe, the present embodiment part does not refer to place, can refer in corresponding in the above embodiments
Hold.Frequency range degree Tendency Prediction device include information receiving unit 401, signal decomposition unit 402, feature extraction unit 403,
Predicting unit 404, result generation unit 405 and information transmitting unit 406.
Information receiving unit 401 is used to receive the frequency range degree in continuous time point of the transmission of intelligent terminal 200.
Signal decomposition unit 402, which is used to carry out decomposing to the frequency range degree of continuous time point, generates multiple current slots
Corresponding frequency range degree.
Wherein, radio is preferably the frequency range in a presetting detection cycle in the frequency range degree of continuous time point
Degree.
Signal decomposition unit 402 be specifically used for using small echo signal decomposition apparatus to the frequency range degree of continuous time point into
Row, which decomposes, generates the corresponding frequency range degree of multiple current slots.
Feature extraction unit 403 is used to extract the situation feature of the corresponding frequency range degree of multiple current slots.
Predicting unit 404 is used for special according to the situation for currently extracting the corresponding frequency range degree of multiple current slots
The situation feature training sample of sign, the in advance non-linear Tendency Prediction model of training, pre-stored multiple history frequency range degree
And the corresponding frequency range degree situation of situation feature training sample of each history frequency range degree generates multiple current times
The corresponding multiple future time section frequency range degree situation of section.
The non-linear Tendency Prediction model of training is the situation feature training sample using multiple history frequency range degree in advance
The time that the corresponding frequency range degree situation of situation feature training sample of this and each history frequency range degree is trained in advance
Recurrent neural network algorithm model or decision Tree algorithms model or algorithm of support vector machine model.
As a result generation unit 405 is used for the corresponding multiple future time section frequency range degree situation of multiple current slots
It is synthetically generated frequency range degree Tendency Prediction result.
Information transmitting unit 406 is used to frequency range degree Tendency Prediction result being sent to intelligent terminal 200.
In conclusion frequency range degree Tendency Prediction method and apparatus provided by the invention, first by described continuous
The frequency range degree at time point, which decompose, generates the corresponding frequency range degree of multiple current slots；Then it extracts the multiple
The situation feature of the corresponding frequency range degree of current slot；Last foundation currently extracts the corresponding frequency of multiple current slots
The situation feature of section degree, the in advance non-linear Tendency Prediction model of training, pre-stored multiple history frequency range degree
The corresponding frequency range degree situation of the situation feature training sample of situation feature training sample and each history frequency range degree
Generate the corresponding multiple future time section frequency range degree situation of multiple current slots；Multiple current slots are corresponding more
A future time section frequency range degree situation is synthetically generated frequency range degree Tendency Prediction as a result, occupying to realize to frequency range
The prediction of further trend is spent, and prediction result is accurate, high reliablity, so that radio control department can grasp frequency spectrum resource
Following situation, and according to following situation Added Management decision, efficiently to utilize Radio Spectrum Resource, when frequency range degree
It when larger difference occurs for predicted value and actual monitoring value, regards as being abnormal, and to anomaly classification processing, facilitates radio
Interfere discovery, electromagnetic environment anomaly etc..
In several embodiments provided herein, it should be understood that disclosed device and method can also pass through
Other modes are realized.The apparatus embodiments described above are merely exemplary, for example, flow chart and block diagram in attached drawing
Show the device of multiple embodiments according to the present invention, the architectural framework in the cards of method and computer program product,
Function and operation.In this regard, each box in flowchart or block diagram can represent the one of a module, section or code
Part, a part of the module, section or code, which includes that one or more is for implementing the specified logical function, to be held
Row instruction.It should also be noted that function marked in the box can also be to be different from some implementations as replacement
The sequence marked in attached drawing occurs.For example, two continuous boxes can actually be basically executed in parallel, they are sometimes
It can execute in the opposite order, this depends on the function involved.It is also noted that every in block diagram and or flow chart
The combination of box in a box and block diagram and or flow chart can use the dedicated base for executing defined function or movement
It realizes, or can realize using a combination of dedicated hardware and computer instructions in the system of hardware.
In addition, each functional module in each embodiment of the present invention can integrate one independent portion of formation together
Point, it is also possible to modules individualism, an independent part can also be integrated to form with two or more modules.
It, can be with if the function is realized and when sold or used as an independent product in the form of software function module
It is stored in a computer readable storage medium.Based on this understanding, technical solution of the present invention is substantially in other words
The part of the part that contributes to existing technology or the technical solution can be embodied in the form of software products, the meter
Calculation machine software product is stored in a storage medium, including some instructions are used so that a computer equipment (can be a
People's computer, server or network equipment etc.) it performs all or part of the steps of the method described in the various embodiments of the present invention.
And storage medium above-mentioned includes: that USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), arbitrary access are deposited
The various media that can store program code such as reservoir (RAM, Random Access Memory), magnetic or disk.It needs
Illustrate, herein, relational terms such as first and second and the like be used merely to by an entity or operation with
Another entity or operation distinguish, and without necessarily requiring or implying between these entities or operation, there are any this realities
The relationship or sequence on border.Moreover, the terms "include", "comprise" or its any other variant are intended to the packet of nonexcludability
Contain, so that the process, method, article or equipment for including a series of elements not only includes those elements, but also including
Other elements that are not explicitly listed, or further include for elements inherent to such a process, method, article, or device.
In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including the element
Process, method, article or equipment in there is also other identical elements.
The foregoing is only a preferred embodiment of the present invention, is not intended to restrict the invention, for the skill of this field
For art personnel, the invention may be variously modified and varied.All within the spirits and principles of the present invention, made any to repair
Change, equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.It should also be noted that similar label and letter exist
Similar terms are indicated in following attached drawing, therefore, once being defined in a certain Xiang Yi attached drawing, are then not required in subsequent attached drawing
It is further defined and explained.
Claims (10)
1. a kind of frequency range degree Tendency Prediction method, which is characterized in that the frequency range degree Tendency Prediction method includes:
Receive the frequency range degree in continuous time point that intelligent terminal is sent；
The frequency range degree of the continuous time point decompose and generates the corresponding frequency range degree of multiple current slots；
Extract the situation feature of the corresponding frequency range degree of the multiple current slot；
Foundation currently extracts the situation feature of the corresponding frequency range degree of multiple current slots, the non-thread condition of training in advance
Gesture prediction model, the situation feature training sample of pre-stored multiple history frequency range degree and each history frequency range degree
The corresponding frequency range degree situation of situation feature training sample generate the corresponding multiple future time sections of multiple current slots
Frequency range degree situation；
The corresponding multiple future time section frequency range degree situation of multiple current slots are synthetically generated frequency range degree situation
Prediction result.
2. frequency range degree Tendency Prediction method according to claim 1, which is characterized in that it is described in advance training it is non-thread
Condition gesture prediction model is to be occupied using the situation feature training sample of multiple history frequency range degree and each history frequency range
Time recurrent neural network algorithm model that the corresponding frequency range degree situation of situation feature training sample of degree is trained in advance or
Decision Tree algorithms model or algorithm of support vector machine model.
3. frequency range degree Tendency Prediction method according to claim 1, which is characterized in that described to the continuous time
The frequency range degree of point decompose the step of generating multiple current slots corresponding frequency range degree and includes:
Decompose using frequency range degree of the small echo signal decomposition method to the continuous time point and generates multiple current times
The corresponding frequency range degree of section.
4. frequency range degree Tendency Prediction method according to claim 1, which is characterized in that described in continuous time point
Frequency range degree is the frequency range degree in a presetting detection cycle.
5. frequency range degree Tendency Prediction method according to claim 1, which is characterized in that the frequency range degree situation
Prediction technique further include:
Frequency range degree Tendency Prediction result is sent to the intelligent terminal.
6. a kind of frequency range degree Tendency Prediction device, which is characterized in that the frequency range degree Tendency Prediction device includes:
Information receiving unit, for receiving the frequency range degree in continuous time point of intelligent terminal transmission；
Signal decomposition unit carries out decomposing the multiple current slots pair of generation for the frequency range degree to the continuous time point
The frequency range degree answered；
Feature extraction unit, for extracting the situation feature of the corresponding frequency range degree of the multiple current slot；
Predicting unit, for according to the situation feature, in advance for currently extracting the corresponding frequency range degree of multiple current slots
The situation feature training sample of trained non-linear Tendency Prediction model, pre-stored multiple history frequency range degree and each
It is corresponding that the corresponding frequency range degree situation of the situation feature training sample of history frequency range degree generates multiple current slots
Multiple future time section frequency range degree situation；
As a result generation unit, for giving birth to the corresponding multiple future time section frequency range degree situation synthesis of multiple current slots
At frequency range degree Tendency Prediction result.
7. frequency range degree Tendency Prediction device according to claim 6, which is characterized in that it is described in advance training it is non-thread
Condition gesture prediction model is to be occupied using the situation feature training sample of multiple history frequency range degree and each history frequency range
Time recurrent neural network algorithm model that the corresponding frequency range degree situation of situation feature training sample of degree is trained in advance or
Decision Tree algorithms model or algorithm of support vector machine model.
8. frequency range degree Tendency Prediction device according to claim 6, which is characterized in that the signal decomposition unit tool
When body is used to carry out decomposition using frequency range degree of the small echo signal decomposition apparatus to the continuous time point to generate multiple current
Between the corresponding frequency range degree of section.
9. frequency range degree Tendency Prediction device according to claim 6, which is characterized in that described in continuous time point
Frequency range degree is the frequency range degree in a presetting detection cycle.
10. frequency range degree Tendency Prediction device according to claim 6, which is characterized in that the frequency range degree state
Gesture prediction meanss further include:
Information transmitting unit, for frequency range degree Tendency Prediction result to be sent to the intelligent terminal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811295194.7A CN109450567A (en) | 2018-11-01 | 2018-11-01 | Frequency range degree Tendency Prediction method and apparatus |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811295194.7A CN109450567A (en) | 2018-11-01 | 2018-11-01 | Frequency range degree Tendency Prediction method and apparatus |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109450567A true CN109450567A (en) | 2019-03-08 |
Family
ID=65550616
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811295194.7A Pending CN109450567A (en) | 2018-11-01 | 2018-11-01 | Frequency range degree Tendency Prediction method and apparatus |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109450567A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021080670A1 (en) * | 2019-10-22 | 2021-04-29 | Raytheon Company | Closed-loop control of rf test environment |
| EP3989626A1 (en) * | 2020-10-23 | 2022-04-27 | Vestel Elektronik Sanayi ve Ticaret A.S. | Learning-based spectrum occupancy prediction exploiting multi-dimensional correlation |
-
2018
- 2018-11-01 CN CN201811295194.7A patent/CN109450567A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021080670A1 (en) * | 2019-10-22 | 2021-04-29 | Raytheon Company | Closed-loop control of rf test environment |
| EP3989626A1 (en) * | 2020-10-23 | 2022-04-27 | Vestel Elektronik Sanayi ve Ticaret A.S. | Learning-based spectrum occupancy prediction exploiting multi-dimensional correlation |
| WO2022084096A1 (en) * | 2020-10-23 | 2022-04-28 | Vestel Elektronik Sanayi ve Ticaret A. S. | Learning-based spectrum occupancy prediction exploiting multi-dimensional correlation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ford et al. | Smart grid energy fraud detection using artificial neural networks | |
| Sirojan et al. | Sustainable deep learning at grid edge for real-time high impedance fault detection | |
| CN107809331A (en) | The method and apparatus for identifying abnormal flow | |
| CN109543992A (en) | Intelligent polling method, device, intelligent terminal and server | |
| CN106056879B (en) | A kind of ammeter remote monitoring system based on intelligent recognition | |
| CN103076547A (en) | Method for identifying GIS (Gas Insulated Switchgear) local discharge fault type mode based on support vector machines | |
| CN110232499A (en) | A kind of power distribution network information physical side method for prewarning risk and system | |
| Guo et al. | Traffic forecasting via dilated temporal convolution with peak-sensitive loss | |
| CN112750051B (en) | Random forest algorithm-based phase sequence identification method and device for transformer area and terminal equipment | |
| Jiao | Application and prospect of artificial intelligence in smart grid | |
| CN109450567A (en) | Frequency range degree Tendency Prediction method and apparatus | |
| CN114358106A (en) | System anomaly detection method and device, computer program product and electronic equipment | |
| CN113313280A (en) | Cloud platform inspection method, electronic equipment and nonvolatile storage medium | |
| CN107045475A (en) | Method of testing and device | |
| CN109685344A (en) | A kind of power equipment O&M strategy determines method, apparatus and storage medium | |
| CN106443380A (en) | Distribution cable partial discharge signal identifying method and apparatus | |
| CN107819745A (en) | The defence method and device of abnormal flow | |
| CN113887626A (en) | Method and device for generating portrait of power equipment | |
| Cabral et al. | Fraud detection system for high and low voltage electricity consumers based on data mining | |
| CN109542867A (en) | Distribution type data collection method and device | |
| Elseidi | A hybrid Facebook Prophet-ARIMA framework for forecasting high-frequency temperature data | |
| CN109412855A (en) | Signal degree Tendency Prediction method and apparatus | |
| CN109412854A (en) | Signal life cycle Tendency Prediction method and apparatus | |
| CN116308679A (en) | Supply chain abnormal order processing method, device, equipment and storage medium | |
| Rosenlund et al. | Clustering and dimensionality-reduction techniques applied on power quality measurement data |
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 |