CN107180070A - A kind of risk information is classified, recognized and method for early warning and system automatically - Google Patents
A kind of risk information is classified, recognized and method for early warning and system automatically Download PDFInfo
- Publication number
- CN107180070A CN107180070A CN201710197952.0A CN201710197952A CN107180070A CN 107180070 A CN107180070 A CN 107180070A CN 201710197952 A CN201710197952 A CN 201710197952A CN 107180070 A CN107180070 A CN 107180070A
- Authority
- CN
- China
- Prior art keywords
- risk
- information
- classified
- carried out
- early warning
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
- G06F16/358—Browsing; Visualisation therefor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
- G06F16/353—Clustering; Classification into predefined classes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Databases & Information Systems (AREA)
- Strategic Management (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention relates to risk identification and early warning field, classify automatically more particularly, to a kind of risk information, recognize and method for early warning and system.Method includes：S1. the information of user's transmission is received and as risk target；S2. risk information classification is carried out to the information and identifying processing obtains the kind of risk of user's local environment；S3. corresponding pre-warning signal is exported according to kind of risk；S4. Emergency decision scheme is provided according to pre-warning signal.The information that the method for the present invention is first sent to user carries out risk information classification processing, then corresponding pre-warning signal is exported according to classification situation, corresponding Emergency decision scheme is provided according to pre-warning signal, this method set risk identification, classification and warning function, the information that can be sent according to user provide the user counter-measure in time.
Description
Technical field
The present invention relates to risk identification and early warning field, classify automatically more particularly, to a kind of risk information, recognize with
Method for early warning and system.
Background technology
At present, probably there is following centralized system to information classification in the prior art：Step-by-step classifier differentiates, successive Discrimination point
Analysis, successively classification stepwise evaluation, greedy coaching method, successively progressive method.
Wherein, successive Discrimination is all tested using having into there is the algorithm that to each step.One discriminating power is most strong
Variable introduce discriminate, while some variables to being introduced into discriminate, if its original difference ability is with variable thereafter
Introducing and change, substituted, then in time reject it from discriminate by the effect of some variables, protect final discriminate
Stay discriminating power most strong variable.Stepwise Discriminatory Analysis algorithm is concretely comprised the following steps：1st step：Select variable（Data prepare, choosing
Enter and reject variable）；2nd step：Discriminant function is set up using being selected into and rejecting variable；3rd step：Sample to be discriminated is made to differentiate
Analysis.
Stepwise evaluation method of classifying is on the basis of expert estimation, using the improvement based on cloud model scale judgment matrix
Analytic hierarchy process (AHP), successively carries out weight calculation, it is determined that each specific targets and Urban Integrated Transport Hub are evaluated between combined index
Relation, then carry out classification stepwise evaluation.
Successively the main thought of greedy coaching method is：In deep neural network, one layer in each training network, i.e.,
A network containing only a hidden layer is trained first, and only just starting training one after the training of this layer network terminates there are two
The network of hidden layer, by that analogy.In each step, the preceding k-1 layers of fixation trained, then increase kth layer, also
It is that the preceding k-1 that will have been trained output is used as input.Each layer of training can have supervision（For example, by each step
Error in classification be used as object function）, but more generally use unsupervised approaches.
Successively progressive method is called layer and enters formula, it and block form（Parallel combinations method）, through-beam Series, total and fractional together form view
Four kinds of patterns of paper argument structure.Successively in progressive method, each point of argument show from one to the other, from the superficial to the deep, by phenomenon to
Essence, from simple to complex, progressive relationship ascending, from outward appearance to inner essence.But this 5 concepts are that step-by-step classifier differentiates, progressively
Discriminant analysis, classification stepwise evaluation, successively greedy coaching method, successively progressive method all not yet found on the net accordingly in Chinese periodical
Research Literature.
In terms of disaggregated model and algorithm research, West（2000）Establish five kinds of different neutral net credit classification moulds
Type and its respective algorithms：Multilayer perceptron（MLP）, expert's heterological system（mixture-of-experts）, Radial Basis Function Network
Network（RBF）, learning vector quantization device（learning vector quantization）With fuzzy self-adaption resonance（fuzzy
adaptive resonance）, for studying the accuracy of business bank's credit appraisal.Pang Sulin（2005）Establish 10 kinds of letters
With disaggregated model and its respective algorithms：1. 5 kinds of neutral net Credit Evaluation Models of：Multilayer perceptron（MLP）, BP algorithm net
Network, radial primary function network（RBF）, probabilistic neural network（PNN）And Self-organizing Neural Networks（SOCN）；2. Logistic are returned
Return model；3. two kinds of linear discriminant analysis models of：One kind is to carry out discriminant analysis to data sample using SPSS statistical softwares
（Referred to as LDA-SPSS methods）, one kind is to derive to set up linear discriminant analysis model using initial data, then according to model meter
Obtained result carries out discriminant analysis to data sample（Referred to as LDA methods）；4. employs 2 kinds of supporting vector based methods：
One kind is that, by the use of polynomial function as kernel function, one kind is by the use of RBF as kernel function, for studying in China
The accuracy that company credit of city evaluates.All fixed member（2009）Extensive calamity emergency rescue plan is real in the Wenchuan earthquake provided
Example, provides the application of the emergent sorting algorithm of big data processing.Anjum（2011）Oil storage is simulated on the basis of GIS technology
Tank explosion scene, passes through scene analysis and the method city risk bypassing method of mathematical modeling.Pang Sulin（2015）Catastrophe risk
Emergent classification, decomposition and the sorting algorithm of big data processing, give corresponding algorithm principle and realize step.
In terms of big data contingency management and Network Warning Mechanism Study, Gong etc.（2013）By setting up Optimized model,
Study the network optimization problem of disaster big data in supply chain.Horse runs quickly and Mao Qingduo（2015）Respectively with regard to accident in advance,
Thing is neutralized afterwards, have studied application of the big data in contingency management, contingency management three stage base of the framework based on big data
This frame diagram, it is proposed that the condition of a disaster data of magnanimity are changed into straightforward with big data visualization technique in the event response stage
Decision-making assistant information；Duan Huaming et al.（2016）Propose the Disaster Assessment pattern based on big data, it is indicated that big data technology
The condition of a disaster is optimized to collect and visualization process.Pang Sulin and Cai Mufu（2017）By catastrophe the condition of a disaster big data be categorized as structuring with
Unstructured data, the characteristics of analysis catastrophe the condition of a disaster big data has dispersiveness, poor legibility, dynamic, and based on WEBGIS
Catastrophe the condition of a disaster, provide big data visualization system analysis with design.
In terms of knowledge for coping with emergencies management study, Qiu Jiangnan etc.（2009）To accident and event chain Research Characteristics, use
The system engineering theory, establishes accident and its chain relationship Knowledge Representation Model.The model is from accident mechanism
The knowledge requirement of contingency management process is described, accident development, the behavior pattern developed and accident chain are not only disclosed
Formula relation formation mechenism, also provides theoretical foundation for Emergency decision, finally provides the application example of model, realizes event evolution
Automatically generate and contingency procedure in knowledge support.
In terms of GIS-Geographic Information System and early warning mechanism research, Gunes et al.（2010）Construct answering based on GIS technology
Anxious management decision system, this system enables contingency management decision-maker in the Kansas State grasping the flood calamity of more devastateds
Decision-making is carried out on the premise of feelings spatial information；Wang（2011）Then devise the emergent pipe based on GIS technology and computer science
Information system is managed, contingency tasks are subject to integrated and visualization, assist contingency management mechanism to reduce emergency by this system
Occur；Pollino et al.（2011）Geographical information technology is applied into the early warning system in fire or earthquake, and demonstrates it
Effect in Disaster Assessment and emergency response；Zhao Ke et al.（2004）Caused using geographical space technology evaluation flood
Loss, more scientific emergency information decision support is provided for flood contingency management；Li Weiquan（2013）Study government emergency management
Middle network public opinion audient antagonistic psychology model, gives corresponding early warning mechanism and emergency management method.
Although prior art has correlative study to fields such as big data analysis, information early warnings, still lack at present
Risk identification, classification, early warning are carried out Study on Integration and the scheme of decision-making by a kind of combination.
The content of the invention
The present invention is to overcome at least one defect described in above-mentioned prior art（It is not enough）Being capable of Integrated Risk there is provided one kind
Identification, classification, the risk information of warning function are classified, recognized and method for early warning automatically.
The present invention also provides a kind of risk information and classifies automatically, recognizes and early warning system.
In order to solve the above technical problems, technical scheme is as follows：
A kind of risk information classifies, recognizes and method for early warning automatically, including：
S1. the information of user's transmission is received and as risk target；
S2. the kind of risk that risk information classification processing obtains user's local environment is carried out to the information；
S3. risk class is identified and measured according to kind of risk, export corresponding Risk-warning signal；
S4. Emergency decision scheme is provided according to pre-warning signal.
The information that the method for the present invention is first sent to user carries out risk information classification processing, then according to classification situation pair
Risk class is identified and measured, then exports corresponding Risk-warning signal, provides corresponding emergent according to pre-warning signal
Decision scheme, this method set risk classification and recognition measurement and warning function, the information that can be sent according to user is in time
User provides counter-measure.
In such scheme, S2's concretely comprises the following steps：
S21. assume that the information that user sends is designated as S；
S22. judge whether S contains risk information, step S23 is then performed in this way, otherwise S is classified as not containing to the class of risk information
Not；
S23. judge whether S risk can recognize that, step S24 is then performed in this way, otherwise S is classified as not can recognize that to the class of risk
Not；
S24. judge that the risk in S whether there is, step S25 is then performed in this way, otherwise S is classified as to the classification of devoid of risk；
S25. risk class identification is carried out to S, is some grade risk informations by S points.
The method proposition of the present invention carries out classification of risks with step-by-step classifier algorithm to the information that user sends, and it is according to interior
Contain the classification obtained by disjoint attribute is divided, it is ensured that the information each handled can be divided into corresponding class
In not, so as to provide the user pre-warning signal and corresponding Emergency decision scheme exactly.
In such scheme, S2 is further concretely comprised the following steps：
Assuming that S is the character string of a word, literal expression logical base, the word for risk information classification are pre-established
Content repository（Scene descriptive text content for storing various risk cases in daily life）And vulnerability database（For
Store the risk point and corresponding risk class of various risks event）；
Characters matching processing is carried out to S in word content knowledge base, S is made whether containing risk information according to matching result
Judgement；
To being judged as that the S of risky information carries out semantic logic processing in literal expression logical base, according to logical process result
The judgement whether risk can recognize that is carried out to S；
To being judged as that the recognizable S of risk carries out keyword match in word content knowledge base, according to keyword match result
The judgement for having devoid of risk is carried out to S；
Information matches are carried out to the keyword in S in vulnerability database, risk class identification is carried out to S according to matching result.
The method of the present invention is that the information sent using risk identification information matches algorithm to user carries out risk knowledge automatically
Other and measurement, this method is also combined with step-by-step classifier algorithm, realizes the automatic classification, identification and measurement of risk.
In such scheme, the risk class is divided into level Four：Low-risk, risk, excessive risk and extreme risk.
In such scheme, the pre-warning signal is distinguished by color, and different classes of and risk class is pre- with different colors
It is alert.
A kind of risk information classifies, recognizes and early warning system automatically, including：
Receiving module, for receiving the information of user's transmission and as risk target；
Kind of risk identification module, for carrying out the risk class that risk information classification processing obtains user's local environment to the information
Not；
Pre-warning signal output module, for exporting corresponding pre-warning signal according to kind of risk；
Emergency decision module, for providing Emergency decision scheme according to pre-warning signal.
In the system of the present invention, the information first sent using kind of risk identification module to user carries out risk information classification
And identifying processing, then pre-warning signal output module is according to the corresponding pre-warning signal of classification situation output, Emergency decision module
According to pre-warning signal provide corresponding Emergency decision scheme, the system set risk identification, classification and warning function, Neng Gougen
The information sent according to user provides the user counter-measure in time.
In such scheme, in addition to：
Risk large database concept, the received risk information sent by user for storing, information is designated as S, it is assumed that S is
The character string of one word；
Whether literal expression logical base, for storing semantic logic sample, carry out risk information to S according to semantic logic sample and may be used
The judgement of identification；
Word content knowledge base, the scene descriptive text content for storing various risk cases in daily life, according to being deposited
The information of storage is made whether the judgement that whether can recognize that containing risk information, risk information, have devoid of risk to match to S；
Vulnerability database, risk point and corresponding risk class for storing various risks event, passes through send user
Risk information carries out matching treatment with the risk point and risk class in storehouse, and then S is carried out further according to the keyword matched
Risk class is recognized.
In such scheme, kind of risk identification module specifically for：
Characters matching processing is carried out to S using word content knowledge base, S is made whether containing risk information according to matching result
Judgement, as S to be classified as not containing to the classification of risk information without if；
Using literal expression logical base to being judged as that the S of risky information carries out semantic logic processing, according to logical process result
The judgement whether risk can recognize that is carried out to S, otherwise S such as is classified as not can recognize that to the classification of risk；
Using word content knowledge base to being judged as that the recognizable S of risk carries out keyword match, according to keyword match result
The judgement for having devoid of risk, the classification as S to be classified as to devoid of risk without if are carried out to S；
Information matches are carried out to the keyword in S using vulnerability database, risk class identification is carried out to S according to matching result.
In such scheme, the risk class is divided into level Four：Low-risk, risk, excessive risk and extreme risk.
In such scheme, the pre-warning signal is distinguished by color, and different classes of and risk class is pre- with different colors
It is alert.
Compared with prior art, the beneficial effect of technical solution of the present invention is：
The present invention proposes step-by-step classifier algorithm and risk identification information matches algorithm, both algorithms is combined user is sent out
The risk information of cloth carries out risk step-by-step classifier, automatic identification and measurement, and carries out Risk-warning according to kind of risk, helps to use
Family carries out Emergency decision.During implementing, by the step of designing step-by-step classifier algorithm idea and realize, being believed
Matched rule design is ceased, and further provides risk identification information matches algorithm, step-by-step classifier algorithm and risk is then utilized
The thought that identification information matching algorithm is combined, is progressively divided into seven major classes to the environmental risk residing for user：" extreme risk ",
" excessive risk ", " risk ", " low-risk ", " devoid of risk ", " not can recognize that risk " and " not containing risk information ", provide risk
Automatic identification, measurement, the scheme of early warning and Emergency decision.
Brief description of the drawings
Fig. 1 is the schematic diagram of kind of risk and corresponding pre-warning signal.
Fig. 2 is kind of risk, pre-warning signal, the one-to-one schematic diagram of decision-making.
Fig. 3 be a kind of risk information of the invention classify automatically, recognize and method for early warning specific embodiment flow chart.
Fig. 4 be a kind of risk information of the invention classify automatically, recognize and early warning system specific embodiment Organization Chart.
Embodiment
Accompanying drawing being given for example only property explanation, it is impossible to be interpreted as the limitation to this patent；
In order to more preferably illustrate the present embodiment, some parts of accompanying drawing have omission, zoomed in or out, and do not represent the chi of actual product
It is very little；
To those skilled in the art, some known features and its explanation may be omitted and will be understood by accompanying drawing.
In the description of the invention, it is to be understood that in addition, term " first ", " second " are only used for describing purpose, and
It is not intended that indicating or implying relative importance or imply the quantity of indicated technical characteristic.Thus, " first " of restriction,
One or more this feature can be expressed or be implicitly included to the feature of " second ".In the description of the invention, unless separately
It is described, " multiple " are meant that two or more.
In the description of the invention, it is necessary to illustrate, unless otherwise clearly defined and limited, term " installation ", " company
Connect " it should be interpreted broadly, for example, it may be being fixedly connected or being detachably connected, or it is integrally connected；It can be machine
Tool is connected or electrically connected；It can be joined directly together or be indirectly connected with by intermediary, it may be said that two
The connection of element internal.For the ordinary skill in the art, with concrete condition above-mentioned term can be understood in the present invention
Concrete meaning.
Technical scheme is described further with reference to the accompanying drawings and examples.
Embodiment 1
（One）Step-by-step classifier algorithm idea can be described as：To a certain object being classified, some standard or premise are first according to,
Under the maximum extension of its described concept, divided according to the disjoint attribute of its intension, the result of division obtain according to
The current criteria for classifying or under the premise of several classes；Then in all classifications currently divided, and according to some standard
Or premise（It can be premise or standard just now, may not be）, under the maximum extension of its described concept, according in it
Contain disjoint attribute to be divided, the result of division get back according to the current criteria for classifying or under the premise of several classes；Such as
This proceeds down, and the classification of each step is all under the classification results of back, according to some standard or premise（Can be with
It is the premise or standard of previous step, may not be）, it is non-intersect according to its intension under the maximum extension of its described concept
Attribute divided obtained by classification, being performed until need not be resorted to as stopping.
When user releases news on platform, APP emergency systems as risk target, adjust the information that user is sent
Step-by-step classifier algorithm is used, user's input risk information is classified.APP emergency systems preset classification of risks rule with being
System realizes that target is as follows：
Rule 1：Whether issue content contains risk information
System realizes target：It is, it is no；
1st grade of classification：" containing risk information " and " not containing risk information "（Two classes）
Rule 2：Whether the risk can recognize that（Under the conditions of containing risk information）
System realizes target：Recognizable risk, not can recognize that risk；
2nd grade of classification：" recognizable " and " not can recognize that "（Two classes）
Rule 3：The risk whether there is（Under recognizable risk conditions）
System realizes target：It is risky, devoid of risk；
3rd level is classified：" risky " and " devoid of risk "（Two classes）
Rule 4：Risk class is divided（Under risk existence condition）
System realizes target：Extreme risk, excessive risk, risk, low-risk；
4th grade of classification：" extreme risk ", " excessive risk ", " risk " and " low-risk "（Four classes）
According to risk hierarchical classification algorithm principle, the risk environment residing for user is divided into seven grades by one：" without risky
Information ", " not can recognize that risk ", " devoid of risk ", " low-risk ", " risk ", " excessive risk " and " extreme risk ".
Rule 5：Risk-warning（Divided for the risk class under risk existence condition）
System realizes target：White, grey, green, yellow are orange, light red, peony；
Rule 6：Risk resolution method（Emergency decision）
Sets target：Maintain the original state, risk is studied and judged again, Environmental security is saved oneself, save oneself with mutually rescuing, SOS is with saving oneself mutually
Rescue, distress call.
As shown in figure 1, being schematic diagram of the kind of risk with corresponding pre-warning signal.
Wherein, the risk environment grade residing for user is divided into：" extreme risk ", " excessive risk ", " risk " and " low wind
The grade of danger " four, with risk value as shown in table 1, wherein risk value is environmental risk for the description of degrees of risk at different levels
The possibility of generation.
The risk class of table 1 and description
| Risk classifications | Degree of risk is described | Risk value（Risk possibility occurrence） |
| Extreme risk | There is extreme exception or extreme obstacle in environment, definitely risky | 95-100% |
| Excessive risk | There is Height Anomalies or height barrier in environment, risky | 80-94% |
| Risk | There is moderate exception or moderate obstacle in environment, there is a certain degree of risk, but dangerous little | 50-79% |
| Low-risk | There is low abnormal or low obstacle in environment, and risk is small | 1-49% |
As shown in Fig. 2 being kind of risk, pre-warning signal, the one-to-one schematic diagram of decision-making.
As shown in figure 3, classifying automatically for a kind of risk information of the invention, recognizing and the flow of method for early warning specific embodiment
Figure.Referring to Fig. 3, a kind of risk information of this specific embodiment classifies, recognizes that the specific steps with method for early warning include automatically：
S1. the information of user's transmission is received and as risk target；It is whole by intelligent movable that usual user, which releases news,
End or other electronic equipments are sent, and APP emergency systems are received after the information that user sends, and are possessed according to APP emergency systems
Function risk classification and recognition, measurement and early warning are carried out to the information of user.In specific implementation process, receive what user sent
It is deposited into after information in risk large database concept.
S2. the kind of risk that risk information classification processing obtains user's local environment is carried out to the information；
S3. risk class is identified and measured according to kind of risk, export corresponding Risk-warning signal；
S4. Emergency decision scheme is provided according to pre-warning signal.
In specific implementation process, S2's concretely comprises the following steps：
S21. assume that the information that user sends is designated as S, it is assumed that S is the character string of a word, and pre-establishes for risk information
Literal expression logical base, word content knowledge base and the vulnerability database of classification, S literal expression semanteme ownership word
Express logic library management, S information content ownership word content knowledge base management.
S22. judge whether S contains risk information, step S23 is then performed in this way, is otherwise classified as S not containing risk information
Classification；This step is to carry out characters matching processing to S using word content knowledge base, and S is made whether according to matching result
Judgement containing risk information；
S23. judge whether S risk can recognize that, step S24 is then performed in this way, otherwise S is classified as not can recognize that to the class of risk
Not；The step is, further according to S description, semantic logic matching to be carried out in literal expression logical base, if S language is retouched
It is clear to state, and the word content of expression has logicality, then judges S for " recognizable risk ", is otherwise " not can recognize that risk ", such as
This, the judgement whether risk can recognize that is carried out to S according to logical process result；
S24. judge that the risk in S whether there is, step S25 is then performed in this way, otherwise S is classified as to the classification of devoid of risk；This step
Suddenly it is, further according to S description, text information matching to be carried out in word content knowledge base, if had in S description and wind
The related keyword in danger, then judge S for " risky ", S otherwise judged for " devoid of risk ", in this way, according to keyword match result
The judgement for having devoid of risk is carried out to S；
S25. risk class identification is carried out to S, is some grade risk informations by S points.In this step, system retouching according to S
State the word description progress information matches that " risk " keyword is carried out in vulnerability database, the result matched according to risk information
The identification of " low-risk ", " risk ", " excessive risk " and " extreme risk " is carried out to risk, so S is entered according to matching result
Row risk class is recognized.
By step S2 processing, to one be categorized as in 7 results of S：" not containing risk information ", " it can not know
Other risk ", " devoid of risk ", " low-risk ", " risk ", " excessive risk " and " extreme risk ".APP emergency systems are directed to this in advance
7 results are assigned with 7 kinds of Risk-warning signals：White, grey, green, yellow are orange, light red and peony.
In step s3, corresponding Risk-warning signal will accordingly be exported according to S classification results.
APP emergency systems are also assigned with 7 kinds of corresponding Emergency decision schemes previously according to 7 kinds of Risk-warning signals：Keep
Original state, risk are studied and judged again, Environmental security, save oneself, save oneself and mutually rescue, SOS and self and mutual medical aid and distress call.In step
In rapid S4, corresponding Emergency decision scheme is provided according to S Risk-warning signal, so as to provide the user the emergent of practicality
Decision scheme.
Embodiment 2
On the basis of embodiment 1, classify automatically present invention also offers a kind of risk information, recognize and early warning system.Such as Fig. 4
Shown, a kind of risk information of the present embodiment classifies automatically, recognizes and is specifically included with early warning system：
Receiving module 201, for receiving the information of user's transmission and as risk target；
Kind of risk identification module 202, for obtaining ring residing for user to information progress risk information classification and identifying processing
The kind of risk in border；
Pre-warning signal output module 203, for exporting corresponding pre-warning signal according to kind of risk；
Emergency decision module 204, for providing Emergency decision scheme according to pre-warning signal.
Receiving module 201 is received after the information that user sends, and the function of being possessed according to system is carried out to the information of user
Risk identification and early warning.
In specific implementation process, system also includes：
Risk large database concept 205, for storing the information sent by user received by receiving module 201, information note
For S, it is assumed that S is the character string of a word；
Literal expression logical base 206, for storing semantic logic sample, carrying out risk information to S according to semantic logic sample is
No recognizable judgement；S literal expression semanteme ownership literal expression logic library management.
Word content knowledge base 207, the scene descriptive text content for storing various risk cases in daily life, root
It is made whether whether can recognize that to S containing risk information, risk information according to the information stored, has what devoid of risk matched to sentence
It is disconnected；S information content ownership word content knowledge base management.
Vulnerability database 208, risk point and corresponding risk class for storing various risks event, by by user
Risk point and risk class in the risk information and storehouse of transmission carry out matching treatment, then further according to the keyword pair matched
S carries out risk class identification.
In specific implementation process, kind of risk identification module 202 specifically for：
Characters matching processing is carried out to S using word content knowledge base 207, S is made whether containing risky according to matching result
The judgement of information, the classification as S to be classified as not containing to risk information without if.
Semantic logic processing is carried out using 206 couples of S for being judged as risky information of literal expression logical base, at logic
Reason result carries out the judgement whether risk can recognize that to S, and otherwise S such as is classified as not can recognize that to the classification of risk；During this, such as
Fruit S language description is clear, and the word content of expression has logicality, then judges S for " recognizable risk ", otherwise for " can not
Recognize risk ".
Using word content knowledge base, 207 pairs are judged as that the recognizable S of risk carries out keyword match, according to keyword
The judgement for having devoid of risk, the classification as S to be classified as to devoid of risk without if are carried out to S with result；During this, existed according to S description
Text information matching is carried out in word content knowledge base, if there is the keyword related to risk in S description, judges that S is
" risky ", otherwise judges S for " devoid of risk ".
Information matches are carried out to the keyword in S using vulnerability database 208, risk etc. is carried out to S according to matching result
Level identification.During this, the word description for carrying out " risk " keyword in vulnerability database according to S description enters row information
Match somebody with somebody, the result matched according to risk information carries out the knowledge of " low-risk ", " risk ", " excessive risk " and " extreme risk " to risk
Not, risk class identification is so carried out to S according to matching result.
Any S can be classified using kind of risk identification module 202, one be categorized as in 7 results of S：
" not containing risk information ", " not can recognize that risk ", " devoid of risk ", " low-risk ", " risk ", " excessive risk " and " extreme wind
Danger ".Pre-warning signal output module 203 is assigned with 7 kinds of Risk-warning signals for this 7 results in advance：White, grey, green,
Yellow, orange, light red and peony, pre-warning signal output module 203 will accordingly export corresponding wind according to S classification results
Dangerous pre-warning signal.
Emergency decision module 204 is assigned with 7 kinds of corresponding Emergency decision schemes previously according to 7 kinds of Risk-warning signals：Protect
Hold original state, risk study and judge again, Environmental security, save oneself, save oneself and mutually rescue, SOS and self and mutual medical aid and distress call.Should
Anxious decision-making module 204 provides corresponding Emergency decision scheme according to S Risk-warning signal, so as to provide the user practicality
Emergency decision scheme.
The same or analogous part of same or analogous label correspondence；
Position relationship is used for being given for example only property explanation described in accompanying drawing, it is impossible to be interpreted as the limitation to this patent；
Obviously, the above embodiment of the present invention is only intended to clearly illustrate example of the present invention, and is not to this hair
The restriction of bright embodiment.For those of ordinary skill in the field, it can also do on the basis of the above description
Go out other various forms of changes or variation.There is no necessity and possibility to exhaust all the enbodiments.It is all in the present invention
Spirit and principle within any modifications, equivalent substitutions and improvements for being made etc., should be included in the guarantor of the claims in the present invention
Within the scope of shield.
Claims (10)
1. a kind of risk information is classified, recognized and method for early warning automatically, it is characterised in that including：
S1. the information of user's transmission is received and as risk target；
S2. risk information classification is carried out to the information and identifying processing obtains the kind of risk of user's local environment；
S3. corresponding pre-warning signal is exported according to kind of risk；
S4. Emergency decision scheme is provided according to pre-warning signal.
2. risk automatic identification according to claim 1 and method for early warning, it is characterised in that S2's concretely comprises the following steps：
S21. assume that the information that user sends is designated as S；
S22. judge whether S contains risk information, step S23 is then performed in this way, otherwise S is classified as not containing to the class of risk information
Not；
S23. judge whether S risk can recognize that, step S24 is then performed in this way, otherwise S is classified as not can recognize that to the class of risk
Not；
S24. judge that the risk in S whether there is, step S25 is then performed in this way, otherwise S is classified as to the classification of devoid of risk；
S25. risk class identification is carried out to S, is some grade risk informations by S points.
3. risk automatic identification according to claim 2 and method for early warning, it is characterised in that the further specific steps of S2
For：
Assuming that S is the character string of a word, literal expression logical base, the word for risk information classification are pre-established
Content repository（The scene description of various risk cases i.e. in daily life）And vulnerability database（Refer to the wind of various risks event
Dangerous point）；
Characters matching processing is carried out to S in word content knowledge base, S is made whether containing risk information according to matching result
Judgement；
To being judged as that the S of risky information carries out semantic logic processing in literal expression logical base, according to logical process result
The judgement whether risk can recognize that is carried out to S；
To being judged as that the recognizable S of risk carries out keyword match in word content knowledge base, according to keyword match result
The judgement for having devoid of risk is carried out to S；
Information matches are carried out to the keyword in S in vulnerability database, risk class identification is carried out to S according to matching result.
4. risk automatic identification and method for early warning according to Claims 2 or 3, it is characterised in that the risk class point
For level Four：Low-risk, risk, excessive risk and extreme risk.
5. risk automatic identification according to claim 4 and method for early warning, it is characterised in that the pre-warning signal passes through face
Color is distinguished, and different classes of and risk class is with different color early warning.
6. a kind of risk information is classified, recognized and early warning system automatically, it is characterised in that including：
Receiving module, for receiving the information of user's transmission and as risk target；
Kind of risk identification module, for carrying out the risk class that risk information classification processing obtains user's local environment to the information
Not；
Pre-warning signal output module, for exporting corresponding pre-warning signal according to kind of risk；
Emergency decision module, for providing Emergency decision scheme according to pre-warning signal.
7. risk information according to claim 6 is classified, recognized and early warning system automatically, it is characterised in that also include：
Risk large database concept, for storing the received risk information sent by user, the risk information is designated as S, false
If S is the character string of a word；
Whether literal expression logical base, for storing semantic logic sample, carry out risk information to S according to semantic logic sample and may be used
The judgement of identification；
Word content knowledge base, the scene descriptive text content for storing various risk cases in daily life, according to being deposited
The information of storage is made whether the judgement that whether can recognize that containing risk information, risk information, have devoid of risk to match to S；
Vulnerability database, risk point and corresponding risk class for storing various risks event, passes through send user
Risk information carries out matching treatment with the risk point and risk class in storehouse, and then S is carried out further according to the keyword matched
Risk class is recognized.
8. risk information according to claim 7 is classified, recognized and early warning system automatically, it is characterised in that kind of risk
Identification module specifically for：
Characters matching processing is carried out to S using word content knowledge base, S is made whether containing risk information according to matching result
Judgement, as S to be classified as not containing to the classification of risk information without if；
Using literal expression logical base to being judged as that the S of risky information carries out semantic logic processing, according to logical process result
The judgement whether risk can recognize that is carried out to S, otherwise S such as is classified as not can recognize that to the classification of risk；
Using word content knowledge base to being judged as that the recognizable S of risk carries out keyword match, according to keyword match result
The judgement for having devoid of risk, the classification as S to be classified as to devoid of risk without if are carried out to S；
Information matches are carried out to the keyword in S using vulnerability database, risk class identification is carried out to S according to matching result.
9. the risk information according to claim any one of 6-8 is classified, recognized and early warning system automatically, it is characterised in that
The risk class is divided into level Four：Low-risk, risk, excessive risk and extreme risk.
10. the risk information according to claim any one of 6-8 is classified, recognized and early warning system automatically, it is characterised in that
The pre-warning signal is distinguished by color, and different classes of and risk class is with different color early warning.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710197952.0A CN107180070B (en) | 2017-03-29 | 2017-03-29 | Automatic risk information classification, identification and early warning method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710197952.0A CN107180070B (en) | 2017-03-29 | 2017-03-29 | Automatic risk information classification, identification and early warning method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107180070A true CN107180070A (en) | 2017-09-19 |
| CN107180070B CN107180070B (en) | 2020-10-30 |
Family
ID=59829806
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710197952.0A Active CN107180070B (en) | 2017-03-29 | 2017-03-29 | Automatic risk information classification, identification and early warning method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107180070B (en) |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108445489A (en) * | 2018-02-07 | 2018-08-24 | 海南云保遥感科技有限公司 | The method for determining tropical agriculture loss based on satellite remote sensing and unmanned aerial vehicle remote sensing |
| CN109409659A (en) * | 2018-09-18 | 2019-03-01 | 平安科技（深圳）有限公司 | Method for prewarning risk, device, computer equipment and storage medium |
| WO2019104867A1 (en) * | 2017-11-30 | 2019-06-06 | 平安科技（深圳）有限公司 | Early warning level determining method, apparatus, and device, and readable storage medium |
| CN110121053A (en) * | 2018-02-07 | 2019-08-13 | 中国石油化工股份有限公司 | A kind of video monitoring method of situ of drilling well risk stratification early warning |
| CN110177147A (en) * | 2019-05-28 | 2019-08-27 | 西安邮电大学 | A kind of multiple terminals resource joint system based on Internet of Things |
| CN110503563A (en) * | 2019-07-05 | 2019-11-26 | 中国平安人寿保险股份有限公司 | Risk control method and system |
| CN110516836A (en) * | 2019-07-05 | 2019-11-29 | 中国平安财产保险股份有限公司 | Intelligent early-warning method, apparatus, equipment and storage medium based on big data |
| CN111583067A (en) * | 2020-03-31 | 2020-08-25 | 西南交通大学 | Urban underground large space construction safety early warning and emergency decision-making method and system |
| CN111613034A (en) * | 2020-04-25 | 2020-09-01 | 国泰瑞安股份有限公司 | Fire-fighting monitoring control method and system |
| CN112348675A (en) * | 2020-10-21 | 2021-02-09 | 上海淇玥信息技术有限公司 | Intelligent risk assessment method and device for providing standardized comments and electronic equipment |
| CN112731889A (en) * | 2021-01-18 | 2021-04-30 | 太原理工大学 | Intelligent air regulation management system and regulation and control method thereof |
| CN112862322A (en) * | 2021-02-10 | 2021-05-28 | 支付宝(杭州)信息技术有限公司 | Universal interactive wind control method and device |
| CN113051573A (en) * | 2021-02-19 | 2021-06-29 | 广州银汉科技有限公司 | Host safety real-time monitoring alarm system based on big data |
| CN113673826A (en) * | 2021-07-20 | 2021-11-19 | 中国科学技术大学先进技术研究院 | Driving risk assessment method and system based on individual factors of driver |
| CN113688169A (en) * | 2021-08-11 | 2021-11-23 | 北京科技大学 | Mine potential safety hazard identification and early warning system based on big data analysis |
| CN113902533A (en) * | 2021-10-11 | 2022-01-07 | 税安科技(杭州)有限公司 | Application suitable for index customization and automatic operation in finance and tax field |
| CN114022207A (en) * | 2021-11-08 | 2022-02-08 | 广东电网有限责任公司广州供电局 | Power grid marketing risk management and control method and device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102074956A (en) * | 2011-02-11 | 2011-05-25 | 华北电网有限公司 | Power grid risk management method and system |
| CN103002425A (en) * | 2011-09-16 | 2013-03-27 | 三星电子（中国）研发中心 | Method and system for automatically triggering emergency calls and mobile terminal |
| CN105427196A (en) * | 2015-12-23 | 2016-03-23 | 国网山东省电力公司聊城供电公司 | Credit risk management and control system of electric power consumer |
| CN106530127A (en) * | 2016-11-09 | 2017-03-22 | 国网江苏省电力公司南京供电公司 | Complaint early warning and monitoring analysis system based on text mining |
-
2017
- 2017-03-29 CN CN201710197952.0A patent/CN107180070B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102074956A (en) * | 2011-02-11 | 2011-05-25 | 华北电网有限公司 | Power grid risk management method and system |
| CN103002425A (en) * | 2011-09-16 | 2013-03-27 | 三星电子（中国）研发中心 | Method and system for automatically triggering emergency calls and mobile terminal |
| CN105427196A (en) * | 2015-12-23 | 2016-03-23 | 国网山东省电力公司聊城供电公司 | Credit risk management and control system of electric power consumer |
| CN106530127A (en) * | 2016-11-09 | 2017-03-22 | 国网江苏省电力公司南京供电公司 | Complaint early warning and monitoring analysis system based on text mining |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019104867A1 (en) * | 2017-11-30 | 2019-06-06 | 平安科技（深圳）有限公司 | Early warning level determining method, apparatus, and device, and readable storage medium |
| CN110121053B (en) * | 2018-02-07 | 2021-07-20 | 中国石油化工股份有限公司 | Video monitoring method for drilling site risk grading early warning |
| CN110121053A (en) * | 2018-02-07 | 2019-08-13 | 中国石油化工股份有限公司 | A kind of video monitoring method of situ of drilling well risk stratification early warning |
| CN108445489A (en) * | 2018-02-07 | 2018-08-24 | 海南云保遥感科技有限公司 | The method for determining tropical agriculture loss based on satellite remote sensing and unmanned aerial vehicle remote sensing |
| CN109409659A (en) * | 2018-09-18 | 2019-03-01 | 平安科技（深圳）有限公司 | Method for prewarning risk, device, computer equipment and storage medium |
| CN110177147A (en) * | 2019-05-28 | 2019-08-27 | 西安邮电大学 | A kind of multiple terminals resource joint system based on Internet of Things |
| CN110503563A (en) * | 2019-07-05 | 2019-11-26 | 中国平安人寿保险股份有限公司 | Risk control method and system |
| CN110516836A (en) * | 2019-07-05 | 2019-11-29 | 中国平安财产保险股份有限公司 | Intelligent early-warning method, apparatus, equipment and storage medium based on big data |
| CN110503563B (en) * | 2019-07-05 | 2023-07-21 | 中国平安人寿保险股份有限公司 | Risk control method and system |
| CN111583067A (en) * | 2020-03-31 | 2020-08-25 | 西南交通大学 | Urban underground large space construction safety early warning and emergency decision-making method and system |
| CN111613034A (en) * | 2020-04-25 | 2020-09-01 | 国泰瑞安股份有限公司 | Fire-fighting monitoring control method and system |
| CN112348675A (en) * | 2020-10-21 | 2021-02-09 | 上海淇玥信息技术有限公司 | Intelligent risk assessment method and device for providing standardized comments and electronic equipment |
| CN112731889A (en) * | 2021-01-18 | 2021-04-30 | 太原理工大学 | Intelligent air regulation management system and regulation and control method thereof |
| CN112862322A (en) * | 2021-02-10 | 2021-05-28 | 支付宝(杭州)信息技术有限公司 | Universal interactive wind control method and device |
| CN113051573A (en) * | 2021-02-19 | 2021-06-29 | 广州银汉科技有限公司 | Host safety real-time monitoring alarm system based on big data |
| CN113673826A (en) * | 2021-07-20 | 2021-11-19 | 中国科学技术大学先进技术研究院 | Driving risk assessment method and system based on individual factors of driver |
| CN113673826B (en) * | 2021-07-20 | 2023-06-02 | 中国科学技术大学先进技术研究院 | Driving risk assessment method and system based on individual factors of driver |
| CN113688169A (en) * | 2021-08-11 | 2021-11-23 | 北京科技大学 | Mine potential safety hazard identification and early warning system based on big data analysis |
| CN113688169B (en) * | 2021-08-11 | 2023-08-08 | 北京科技大学 | Mine potential safety hazard identification and early warning system based on big data analysis |
| CN113902533A (en) * | 2021-10-11 | 2022-01-07 | 税安科技(杭州)有限公司 | Application suitable for index customization and automatic operation in finance and tax field |
| CN113902533B (en) * | 2021-10-11 | 2023-08-25 | 税安科技(杭州)有限公司 | Application method suitable for finance and tax field index self-definition and automatic operation |
| CN114022207A (en) * | 2021-11-08 | 2022-02-08 | 广东电网有限责任公司广州供电局 | Power grid marketing risk management and control method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107180070B (en) | 2020-10-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107180070A (en) | A kind of risk information is classified, recognized and method for early warning and system automatically | |
| Kumeda et al. | Classification of road traffic accident data using machine learning algorithms | |
| CN107886073A (en) | A kind of more attribute recognition approaches of fine granularity vehicle based on convolutional neural networks | |
| Johansson et al. | Detection of vessel anomalies-a Bayesian network approach | |
| CN108091111B (en) | A kind of oil truck oil and gas leakage intelligent early-warning system | |
| CN104636449A (en) | Distributed type big data system risk recognition method based on LSA-GCC | |
| CN110837523A (en) | High-confidence reconstruction quality and false-transient-reduction quantitative evaluation method based on cascade neural network | |
| CN113688169B (en) | Mine potential safety hazard identification and early warning system based on big data analysis | |
| CN109711547A (en) | A kind of pollution sources disorder data recognition method based on deep learning algorithm | |
| CN108009690A (en) | A kind of routine bus system optimized based on modularity steals group's automatic testing method | |
| CN107976934A (en) | A kind of oil truck oil and gas leakage speed intelligent early-warning system based on wireless sensor network | |
| Yang et al. | An intelligent singular value diagnostic method for concrete dam deformation monitoring | |
| Zhao et al. | A driving risk prediction algorithm based on PCA-BP neural network in vehicular communication | |
| CN116976318A (en) | Intelligent auditing system for switching operation ticket of power grid based on deep learning and model reasoning | |
| Hui | Construction of information security risk assessment model in smart city | |
| CN117275202A (en) | Omnibearing real-time intelligent early warning method and system for dangerous sources in important areas of cultural relics | |
| CN111080005B (en) | Support vector machine-based public security risk early warning method and system | |
| CN110618980A (en) | System and method based on legal text accurate matching and contradiction detection | |
| CN108874767A (en) | A kind of four dimension module intelligence Compare Systems and method for public security system | |
| Gosavi et al. | A survey on crime occurrence detection and prediction techniques | |
| Hui et al. | Predictive analysis of impact hazard level of coal rock mass based on fuzzy inference network | |
| CN113919544A (en) | Crime early warning method and device, computer equipment and storage medium | |
| TWI524724B (en) | Telecommunication network alarm correlation analysis method | |
| CN113449966A (en) | Gypsum board equipment inspection method and system | |
| Noor et al. | Visualization of crime data using self-organizing map (som) and improvement in som: A review and available tools |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |