CN108733777A - A kind of internet public feelings analysis method based on probability statistics - Google Patents
A kind of internet public feelings analysis method based on probability statistics Download PDFInfo
- Publication number
- CN108733777A CN108733777A CN201810415496.7A CN201810415496A CN108733777A CN 108733777 A CN108733777 A CN 108733777A CN 201810415496 A CN201810415496 A CN 201810415496A CN 108733777 A CN108733777 A CN 108733777A
- Authority
- CN
- China
- Prior art keywords
- module
- internet
- probability
- signal
- statistics
- 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
Abstract
The invention belongs to internet public feelings analysis method technical fields, disclose a kind of internet public feelings analysis method based on probability statistics.It is provided with:The total end module in internet is responsible for collecting all relevant informations herein;Retrieving module includes:Key search module and Internal retrieval module, it includes internet information amount statistical module, relevant information quantity statistics module to be sent out after data collection is got well into statistical module, statistical module;Probability evaluation entity is recently entered, probability evaluation entity finally connects end results display module.The present invention analyzes internet public opinion situation, is first retrieved, is then counted, then classified, finally according to classification situation by computerized algorithm, situations such as calculating probability, analyze public opinion temperature;And in statistical module the moon metering module, all metering modules, three kinds of classification metering modules of day metering module, whether the temperature situation for intuitively calculating public opinion can be changed with time change.
Description
Technical field
The invention belongs to internet public feelings analysis method technical field more particularly to a kind of internets based on probability statistics
The analysis of public opinion method.
Background technology
Public sentiment is the abbreviation of " public opinion situation ", refers to surrounding the hair of intermediary social event in certain social space
Raw, development and variation, society people at different levels are to this understanding and attitude and words situation, and modern society, internet development is rapid,
Many public opinion situations are all embodied in network, various search platforms or are the public opinions such as microblogging space, on the internet, people
Deliver the opinion of oneself wantonly, many social events are even more because the public opinion of people becomes temperature upgrading.Want to know about carriage
It is more effective to carry out statistics ability by internet, more efficiently obtains oneself desired information for feelings.
In conclusion problem of the existing technology is:Public sentiment is wanted to know about, is just more had to be counted by internet
Effect more efficiently obtains oneself desired information.
Invention content
In view of the problems of the existing technology, the present invention provides a kind of internet public feelings analysis side based on probability statistics
Method.
The invention is realized in this way a kind of internet public feelings analysis method based on probability statistics is provided with:Internet
Total end module is responsible for collecting all relevant informations herein;
Retrieving module includes:Key search module and Internal retrieval module, send out after data collection is got well into statistics
Module, statistical module include internet information amount statistical module, relevant information quantity statistics module, and above-mentioned module recently enters
Probability evaluation entity, probability evaluation entity finally connect end results display module.
The total end module data acquisition module in internet is right within the independent sampling period using integrated awareness apparatus
Echo signal x (t) is acquired, and A/D modes is used in combination to carry out digital quantization to signal;Then, to the signal x (i) after quantization into
Row dimensionality reduction;Finally, the signal after dimensionality reduction is reconstructed;Wherein t is sampling instant, and i is the signal sequence after quantization;To quantization
Signal afterwards carries out dimensionality reduction, the difference equation for specifically passing through finite impulse response filter to the signal after quantizationI=1 ..., M, wherein h (0) ..., h (L-1) are filter coefficient, design the compression based on filtering
Perceptual signal acquires frame, constructs following Teoplitz calculation matrix:
Then observeI=1 ..., M, wherein b1,…,bLRegard filter coefficient as;Submatrix ΦFT
Singular value be gram matrix G (ΦF, T) and=Φ 'FTΦFTThe arithmetic root of characteristic value, all eigenvalue λs of verification G (Φ F, T)
i∈(1-δK,1+δK), i=1 ..., T, then ΦFMeet RIP, and passes through solutionOptimization problem weighs
Structure original signal;Original signal, that is, BP algorithm are reconstructed by linear programming method;For the acquisition of actual compression picture signal,
Then change ΦFFor following form:
If signal has sparsity on transformation basic matrix Ψ, pass through solution
Optimization problem, Accurate Reconstruction go out original signal:Wherein Φ is uncorrelated to Ψ, and Ξ is known as CS matrixes;
The key search module obtains the unbiased estimator of each node measurement data by iteration, seeks each biography
Euclidean distance between the measured data values and estimated value of sensor node, melts using normalized Euclidean distance as adaptive weighted
The weights of sum;Number centered on the average value of the maxima and minima of the collected data of sensor node in selection cluster
According to;There is a sensor node in some cluster, with dimensional vector D=(d1,d2,…,dn) indicate respective nodes measured value, pass through
The Euclidean distance for calculating each node data and centre data reacts deviation size between different node datas and centre data,
Wherein liCalculation formula be:
According to the corresponding weights size of Euclidean distance adaptive setting, the bigger weights of distance are smaller, got over apart from smaller weights
Greatly;
WhereinwiFor corresponding weights;
The display module noise model parameters estimation judgment method be:
JudgeError requirements are such as unsatisfactory for, are enabled:
L=l+1;
And it will be revisedWith corresponding power spectrum measurement dataIt substitutes into canonical systems to be solved, obtain each
The correction value of parameterβ=0, Isosorbide-5-Nitrae rejudgeUntil errorMeet measurement request or reaches setting
Iterations.
Further, retrieval module uses big data search modes, can search for knot together in major search platform of internet
Fruit.
Further, computerized algorithm program is used inside probability evaluation entity, is designed with various probabilistic algorithm programs.
Further, statistical module includes three kinds of moon metering module, all metering modules, day metering module classification metering modules.
Advantages of the present invention and good effect are:This internet public feelings analysis method based on probability statistics is by internet carriage
It is analyzed by situation, is first retrieved, then counted, then classified, finally according to classification situation by calculating
Situations such as machine algorithm calculates probability, analyzes public opinion temperature;And in statistical module the moon metering module, all metering modules, day meter
Three kinds of module classification metering modules are measured, whether the temperature situation for intuitively calculating public opinion can be changed with time change.
This internet public feelings analysis method based on probability statistics can effectively according to correlation circumstance network retrieval amount
And always retrieval amount analyzes public opinion situation for internet, calculates quick, visual result.
Description of the drawings
Fig. 1 is the internet public feelings analysis method modules exhibit figure provided in an embodiment of the present invention based on probability statistics.
In figure:1, the total end module in internet;2, module is retrieved;3, key search module;4, Internal retrieval module;5,
Statistical module;6, internet information amount statistical module;7, relevant information quantity statistics module;8, moon metering module;9, Zhou Jiliang
Module;10, day metering module;11, probability evaluation entity;12, end results display module.
Specific implementation mode
In order to further understand the content, features and effects of the present invention, the following examples are hereby given, and coordinate attached drawing
1 detailed description are as follows.
The structure of the present invention is explained in detail below in conjunction with the accompanying drawings.
As shown in Fig. 1, internet public feelings analysis method of the invention based on probability statistics includes:The total end module in internet
1, retrieve module 2, key search module 3, Internal retrieval module 4, statistical module 5, internet information amount statistical module 6,
Relevant information quantity statistics module 7, moon metering module 8, all metering modules 9, day metering module 10, probability evaluation entity 11, end
Hold result display module 12.
The total end module 1 in internet is responsible for collecting all relevant informations herein;Retrieving module 2 includes:Key search mould
Block 3 and Internal retrieval module 4, it includes internet information amount to be sent out after data collection is got well into statistical module 5, statistical module 5
Statistical module 6, relevant information quantity statistics module 7, above-mentioned module recently enters probability evaluation entity 11, probability evaluation entity
11 last connection end results display modules 12.
Further, retrieval module 2 uses big data search modes, can search for knot together in major search platform of internet
Fruit.
Further, 11 inside of probability evaluation entity uses computerized algorithm program, is designed with various probabilistic algorithm programs.
Further, statistical module includes 10 3 kinds of moon metering module 8, all metering modules 9, day metering module classification metering moulds
Block.
The total end module data acquisition module in internet is right within the independent sampling period using integrated awareness apparatus
Echo signal x (t) is acquired, and A/D modes is used in combination to carry out digital quantization to signal;Then, to the signal x (i) after quantization into
Row dimensionality reduction;Finally, the signal after dimensionality reduction is reconstructed;Wherein t is sampling instant, and i is the signal sequence after quantization;To quantization
Signal afterwards carries out dimensionality reduction, the difference equation for specifically passing through finite impulse response filter to the signal after quantizationI=1 ..., M, wherein h (0) ..., h (L-1) are filter coefficient, design the compression based on filtering
Perceptual signal acquires frame, constructs following Teoplitz calculation matrix:
Then observeI=1 ..., M, wherein b1,…,bLRegard filter coefficient as;Submatrix ΦFT
Singular value be gram matrix G (ΦF, T) and=Φ 'FTΦFTThe arithmetic root of characteristic value, all eigenvalue λs of verification G (Φ F, T)
i∈(1-δK,1+δK), i=1 ..., T, then ΦFMeet RIP, and passes through solutionOptimization problem weighs
Structure original signal;Original signal, that is, BP algorithm are reconstructed by linear programming method;For the acquisition of actual compression picture signal,
Then change ΦFFor following form:
If signal has sparsity on transformation basic matrix Ψ, pass through solution
Optimization problem, Accurate Reconstruction go out original signal:Wherein Φ is uncorrelated to Ψ, and Ξ is known as CS matrixes;
The key search module obtains the unbiased estimator of each node measurement data by iteration, seeks each biography
Euclidean distance between the measured data values and estimated value of sensor node, melts using normalized Euclidean distance as adaptive weighted
The weights of sum;Number centered on the average value of the maxima and minima of the collected data of sensor node in selection cluster
According to;There is a sensor node in some cluster, with dimensional vector D=(d1,d2,…,dn) indicate respective nodes measured value, pass through
The Euclidean distance for calculating each node data and centre data reacts deviation size between different node datas and centre data,
Wherein liCalculation formula be:
According to the corresponding weights size of Euclidean distance adaptive setting, the bigger weights of distance are smaller, got over apart from smaller weights
Greatly;
WhereinwiFor corresponding weights;
The display module noise model parameters estimation judgment method be:
JudgeError requirements are such as unsatisfactory for, are enabled:
L=l+1;
And it will be revisedWith corresponding power spectrum measurement dataIt substitutes into canonical systems to be solved, obtain each
The correction value of parameterβ=0, Isosorbide-5-Nitrae rejudgeUntil errorMeet measurement request or reaches setting
Iterations.
The operation principle of the present invention:This internet public feelings analysis method based on probability statistics is with the total end module in internet 1
Based on, the key search module 3 and Internal retrieval module 4 in module 2 are retrieved, to dependent event and all societies
Event is retrieved, and the internet information amount statistical module 6, relevant information quantity statistics module 7 in subsequent statistical module 5 carry out
ASSOCIATE STATISTICS, and classified with day, week, the moon, posterior probability computing module 11 is responsible for calculating public sentiment probability of occurrence, finally,
As a result it is shown in end results display module 12.
This internet public feelings analysis method based on probability statistics analyzes internet public opinion situation, first carries out
Retrieval, is then counted, is then classified, and finally calculates probability, analysis public opinion heat by computerized algorithm according to classification situation
Situations such as spending;And in statistical module the moon metering module 8, all metering modules 9,10 3 kinds of classification metering moulds of day metering module
Whether block can change with time change the temperature situation for intuitively calculating public opinion.
This internet public feelings analysis method based on probability statistics can effectively according to correlation circumstance network retrieval amount
And always retrieval amount analyzes public opinion situation for internet, calculates quick, visual result.
The above is only the preferred embodiments of the present invention, and is not intended to limit the present invention in any form,
Every any simple modification made to the above embodiment according to the technical essence of the invention, equivalent variations and modification, belong to
In the range of technical solution of the present invention.
Claims (5)
1. a kind of internet public feelings analysis system based on probability statistics, which is characterized in that the interconnection based on probability statistics
Net the analysis of public opinion system is provided with:
The total end module in internet, for collecting all relevant informations herein;
Retrieving module includes:Key search module and Internal retrieval module, sent out after data collection is got well into statistical module,
Statistical module includes internet information amount statistical module, relevant information quantity statistics module, and above-mentioned module recently enters probability
Computing module, probability evaluation entity finally connect end results display module;
The total end module data acquisition module in internet is using integrated awareness apparatus to target within the independent sampling period
Signal x (t) is acquired, and A/D modes is used in combination to carry out digital quantization to signal;Then, the signal x (i) after quantization is dropped
Dimension;Finally, the signal after dimensionality reduction is reconstructed;Wherein t is sampling instant, and i is the signal sequence after quantization;After quantization
Signal carries out dimensionality reduction, the difference equation for specifically passing through finite impulse response filter to the signal after quantizationWherein h (0) ..., h (L-1) are filter coefficient, design the pressure based on filtering
Contracting perceptual signal acquires frame, constructs following Teoplitz calculation matrix:
Then observeWherein b1,…,bLRegard filter coefficient as;Submatrix ΦFT's
Singular value is gram matrix G (ΦF, T) and=Φ 'FTΦFTThe arithmetic root of characteristic value, all eigenvalue λ i of verification G (Φ F, T)
∈(1-δK,1+δK), i=1 ..., T, then ΦFMeet RIP, and passes through solutionOptimization problem reconstructs
Original signal;Original signal, that is, BP algorithm are reconstructed by linear programming method;For the acquisition of actual compression picture signal, then
Change ΦFFor following form:
If signal has sparsity on transformation basic matrix Ψ, pass through solution
Optimization problem, Accurate Reconstruction go out original signal:Wherein Φ is uncorrelated to Ψ, and Ξ is known as CS matrixes;
The key search module obtains the unbiased estimator of each node measurement data by iteration, seeks each sensor
Euclidean distance between the measured data values and estimated value of node, using normalized Euclidean distance as adaptive weighted warm
Weights;Data centered on the average value of the maxima and minima of the collected data of sensor node in selection cluster;Certain
There is a sensor node in a cluster, with dimensional vector D=(d1,d2,…,dn) measured value that indicates respective nodes, it is each by calculating
The Euclidean distance of a node data and centre data reacts the deviation size between different node datas and centre data, wherein li
Calculation formula be:
According to the corresponding weights size of Euclidean distance adaptive setting, the bigger weights of distance are smaller, bigger apart from smaller weights;
WhereinwiFor corresponding weights;
The display module noise model parameters estimation judgment method be:
JudgeError requirements are such as unsatisfactory for, are enabled:
L=l+1;
And it will be revisedWith corresponding power spectrum measurement dataIt substitutes into canonical systems to be solved, obtains each parameter
Correction valueIt rejudgesUntil errorMeet measurement request or reaches the iteration time of setting
Number.
2. the internet public feelings analysis system based on probability statistics as described in claim 1, which is characterized in that the retrieval module
Using big data search modes, major search platform search result together in internet.
3. the internet public feelings analysis system based on probability statistics as described in claim 1, which is characterized in that the probability calculation
Inside modules use computerized algorithm program, are designed with various probabilistic algorithm programs.
4. the internet public feelings analysis system based on probability statistics as described in claim 1, which is characterized in that the statistical module
Including three kinds of moon metering module, all metering modules, day metering module classification metering modules.
5. a kind of interconnection based on probability statistics of the internet public feelings analysis system based on probability statistics as described in claim 1
Net the analysis of public opinion method, which is characterized in that the internet public feelings analysis method based on probability statistics always holds mould with internet
Based on block, retrieval mould key search module in the block and Internal retrieval module, to dependent event and all societies
Event is retrieved, and the internet information amount statistical module, relevant information quantity statistics module in subsequent statistical module carry out phase
Statistics is closed, and is classified with day, week, the moon, posterior probability computing module is responsible for calculating public sentiment probability of occurrence;Finally, as a result
It is shown in end results display module.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810415496.7A CN108733777A (en) | 2018-05-03 | 2018-05-03 | A kind of internet public feelings analysis method based on probability statistics |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810415496.7A CN108733777A (en) | 2018-05-03 | 2018-05-03 | A kind of internet public feelings analysis method based on probability statistics |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108733777A true CN108733777A (en) | 2018-11-02 |
Family
ID=63937952
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810415496.7A Pending CN108733777A (en) | 2018-05-03 | 2018-05-03 | A kind of internet public feelings analysis method based on probability statistics |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108733777A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109799420A (en) * | 2019-02-13 | 2019-05-24 | 临沂大学 | A kind of the internet of things functional detection system and detection method of internet of things home appliance |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101826090A (en) * | 2009-09-15 | 2010-09-08 | 电子科技大学 | WEB public opinion trend forecasting method based on optimal model |
CN101975939A (en) * | 2010-09-28 | 2011-02-16 | 北京航空航天大学 | Compressive sensing theory-based Doppler ambiguity-resolution processing method |
CN103036573A (en) * | 2012-12-03 | 2013-04-10 | 南京工业大学 | Compressed sensing signal collection method based on filtering |
CN104618997A (en) * | 2015-01-28 | 2015-05-13 | 西安电子科技大学 | Data aggregation method based on non-uniform grids |
CN105512431A (en) * | 2016-01-04 | 2016-04-20 | 西安电子科技大学 | Phase noise measuring method based on phase noise mathematical model |
US20160335276A1 (en) * | 2015-05-13 | 2016-11-17 | International Business Machines Corporation | Dynamic modeling of geospatial words in social media |
CN107071858A (en) * | 2017-03-16 | 2017-08-18 | 许昌学院 | A kind of subdivision remote sensing image method for parallel processing under Hadoop |
-
2018
- 2018-05-03 CN CN201810415496.7A patent/CN108733777A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101826090A (en) * | 2009-09-15 | 2010-09-08 | 电子科技大学 | WEB public opinion trend forecasting method based on optimal model |
CN101975939A (en) * | 2010-09-28 | 2011-02-16 | 北京航空航天大学 | Compressive sensing theory-based Doppler ambiguity-resolution processing method |
CN103036573A (en) * | 2012-12-03 | 2013-04-10 | 南京工业大学 | Compressed sensing signal collection method based on filtering |
CN104618997A (en) * | 2015-01-28 | 2015-05-13 | 西安电子科技大学 | Data aggregation method based on non-uniform grids |
US20160335276A1 (en) * | 2015-05-13 | 2016-11-17 | International Business Machines Corporation | Dynamic modeling of geospatial words in social media |
CN105512431A (en) * | 2016-01-04 | 2016-04-20 | 西安电子科技大学 | Phase noise measuring method based on phase noise mathematical model |
CN107071858A (en) * | 2017-03-16 | 2017-08-18 | 许昌学院 | A kind of subdivision remote sensing image method for parallel processing under Hadoop |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109799420A (en) * | 2019-02-13 | 2019-05-24 | 临沂大学 | A kind of the internet of things functional detection system and detection method of internet of things home appliance |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110427654B (en) | Landslide prediction model construction method and system based on sensitive state | |
US8200813B2 (en) | Monitoring device and a server | |
CN103714084B (en) | The method and apparatus of recommendation information | |
WO2022111327A1 (en) | Risk level data processing method and apparatus, and storage medium and electronic device | |
CN105593864B (en) | Analytical device degradation for maintenance device | |
CN115013298B (en) | Real-time performance online monitoring system and monitoring method of sewage pump | |
CN106030612B (en) | Photo thermal map is provided | |
CN111415752A (en) | Hand-foot-and-mouth disease prediction method integrating meteorological factors and search indexes | |
CN106096047A (en) | User partition preference computational methods based on Information Entropy and system | |
CN109558544A (en) | Sort method and device, server and storage medium | |
CN102880603A (en) | Method and equipment for filtering ranking list data | |
CN108733777A (en) | A kind of internet public feelings analysis method based on probability statistics | |
CN108664605B (en) | Model evaluation method and system | |
CN108154380A (en) | The method for carrying out the online real-time recommendation of commodity to user based on extensive score data | |
CN110910201B (en) | Information recommendation control method and device, computer equipment and storage medium | |
CN112070559A (en) | State acquisition method and device, electronic equipment and storage medium | |
CN106708880B (en) | Topic associated word acquisition method and device | |
CN115016040B (en) | Sea fog prediction method, device, equipment and medium based on multi-model intelligent selection | |
CN112784160B (en) | Interest point recommendation method based on tensor decomposition and considering context semantic information | |
Candy | Estimation of natural mortality using catch-at-age and aged mark-recapture data: a multi-cohort simulation study comparing estimation for a model based on the Baranov equations versus a new mortality equation | |
CN104331836B (en) | Crops decision support method and device | |
JP7024663B2 (en) | Evaluation updater, method, and program | |
WO2020045106A1 (en) | Evaluation device, method, and program | |
AU2020335019A1 (en) | Evaluation method based on mobile news client and system thereof | |
CN113946836B (en) | Method, system, equipment and medium for evaluating toughness of information system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181102 |
|
RJ01 | Rejection of invention patent application after publication |