CN113379187A - Traffic meteorological disaster assessment method and device and computer readable storage medium - Google Patents

Traffic meteorological disaster assessment method and device and computer readable storage medium Download PDF

Info

Publication number
CN113379187A
CN113379187A CN202110473219.3A CN202110473219A CN113379187A CN 113379187 A CN113379187 A CN 113379187A CN 202110473219 A CN202110473219 A CN 202110473219A CN 113379187 A CN113379187 A CN 113379187A
Authority
CN
China
Prior art keywords
information
output
traffic
gate
traffic accident
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
Application number
CN202110473219.3A
Other languages
Chinese (zh)
Other versions
CN113379187B (en
Inventor
褚端峰
孙森
陆丽萍
吴超仲
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Wuhan University of Technology WUT
Original Assignee
Wuhan University of Technology WUT
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Wuhan University of Technology WUT filed Critical Wuhan University of Technology WUT
Priority to CN202110473219.3A priority Critical patent/CN113379187B/en
Publication of CN113379187A publication Critical patent/CN113379187A/en
Application granted granted Critical
Publication of CN113379187B publication Critical patent/CN113379187B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/26—Government or public services
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/40—Business processes related to the transportation industry
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computing arrangements using knowledge-based models
    • G06N5/04—Inference or reasoning models

Landscapes

  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Engineering & Computer Science (AREA)
  • Tourism & Hospitality (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Physics & Mathematics (AREA)
  • Educational Administration (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Development Economics (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Quality & Reliability (AREA)
  • Operations Research (AREA)
  • Game Theory and Decision Science (AREA)
  • Traffic Control Systems (AREA)

Abstract

The invention relates to a traffic meteorological disaster assessment method, a device and a computer readable storage medium, wherein the method comprises the following steps: acquiring historical meteorological information and historical traffic accident data information; establishing a traffic meteorological disaster prediction model according to the historical meteorological information and the historical traffic accident data information, and training the traffic meteorological disaster prediction model to obtain a trained traffic meteorological disaster prediction model; and re-acquiring historical meteorological information and historical traffic accident data information, inputting the historical meteorological information and the historical traffic accident data information into a trained traffic meteorological disaster prediction model to obtain a traffic accident state vector, and evaluating the traffic meteorological disasters according to the traffic accident state vector. The traffic meteorological disaster assessment method provided by the invention realizes the assessment of the traffic meteorological disaster.

Description

Traffic meteorological disaster assessment method and device and computer readable storage medium
Technical Field
The invention relates to the technical field of meteorological disasters, in particular to a traffic meteorological disaster assessment method and device and a computer readable storage medium.
Background
At present, the early warning problem of meteorological disasters and emergencies is one of the important subjects in the traffic safety field, and attracts people's attention all the time. Due to the variable external environment of traffic, the current communication control means is difficult to accurately grasp the sudden change of weather and a series of emergency events in the traffic environment. Therefore, some indexes which cannot be originally measured are predicted through reinforcement learning, and more comprehensive current state analysis and future trend prediction are achieved. The assessment of the meteorological disasters of the road traffic has great significance and value for reducing the traffic accident rate caused by the meteorological disasters. How to avoid traffic accidents caused by severe weather and how to make accurate and effective assessment and reasonable and safe planning of vehicle speed and lane in advance is an important challenge in the field of road traffic early warning. The prior art can not evaluate the traffic meteorological disasters.
Disclosure of Invention
In view of the above, it is desirable to provide a method, an apparatus and a computer readable storage medium for evaluating a traffic weather disaster, which can solve the problem that the prior art cannot evaluate the traffic weather disaster.
The invention provides a traffic meteorological disaster assessment method, which comprises the following steps:
acquiring historical meteorological information and historical traffic accident data information;
establishing a traffic meteorological disaster prediction model according to the historical meteorological information and the historical traffic accident data information, and training the traffic meteorological disaster prediction model to obtain a trained traffic meteorological disaster prediction model;
and re-acquiring historical meteorological information and historical traffic accident data information, inputting the historical meteorological information and the historical traffic accident data information into a trained traffic meteorological disaster prediction model to obtain a traffic accident state vector, and evaluating the traffic meteorological disasters according to the traffic accident state vector.
Further, according to the historical weather information and the historical traffic accident data information, a prediction model of the traffic weather disaster is established, and the method specifically comprises the following steps:
and establishing a traffic accident state vector according to the historical meteorological information and the historical traffic accident data information, establishing a recurrent neural network, taking the traffic accident state vector at the previous moment and the meteorological information at the current moment as the input of the recurrent neural network, and taking the current traffic accident state vector as the output of the recurrent neural network to establish a prediction model of the traffic meteorological disasters.
Further, the method for establishing the prediction model of the traffic meteorological disaster by using the traffic accident state vector at the previous moment and the meteorological information at the current moment as the input of the recurrent neural network and using the current traffic accident state vector as the output of the recurrent neural network specifically comprises the following steps:
and respectively determining the output information of a forgetting gate, the output information of an input gate and the output information of an output gate in the LSTM memory unit structure according to the traffic accident state vector at the previous moment and the meteorological information at the current moment, and determining the current traffic accident state vector according to the output information of the forgetting gate, the output information of the input gate and the output information of the output gate so as to establish a traffic meteorological disaster prediction model.
Further, determining the output information of the forgotten door in the LSTM memory unit structure according to the traffic accident state vector at the previous time and the weather information at the current time, specifically comprising:
determining the output information of a forgetting gate in an LSTM memory unit structure according to the traffic accident state vector at the previous moment, the weather information at the current moment and an output expression of the forgetting gate, wherein the output expression of the forgetting gate is
Figure BDA0003046172200000021
Wherein f istFor output information of a forgetting gate, σ is an activation function, WfWeight matrix for forgetting gate, bfIn order to forget the biased item of the door,
Figure BDA0003046172200000022
for traffic accidents at the last momentState vector, YtAnd the weather information is the weather information at the current moment.
Further, determining the output information of the input gate in the LSTM memory unit structure according to the traffic accident state vector at the previous time and the weather information at the current time, specifically comprising:
determining the output information of an input gate in the LSTM memory unit structure according to the traffic accident state vector at the previous moment, the meteorological information at the current moment and an output expression of the input gate, wherein the output expression of the output gate is
Figure BDA0003046172200000031
Wherein, the itFor inputting output information of the gate, WiAs a weight matrix of the input gates, biTo input their paranoia.
Further, determining the output information of the output gate in the LSTM memory unit structure according to the traffic accident state vector at the previous time and the weather information at the current time, specifically comprising:
determining the output information of an output gate in the LSTM memory unit structure according to the traffic accident state vector at the previous moment, the meteorological information at the current moment and an output gate output expression, wherein the output gate output expression is
Figure BDA0003046172200000032
Wherein o istFor outputting the output information of the gate, WoAs a weight matrix of output gates, boIs the biased item of the output gate.
Further, determining the current traffic accident state vector according to the output information of the forgotten gate, the output information of the input gate and the output information of the output gate, specifically comprising:
and determining the memory state of the current moment according to the output information of the forgetting gate, the output information of the input gate and the output information of the output gate, acquiring the state unit of the current moment according to the memory state of the current moment, and acquiring the state vector of the current traffic accident according to the state unit of the current moment and the output information of the output gate.
Further, acquiring a state unit of the current moment according to the memory state of the current moment, and acquiring a current traffic accident state vector according to the state unit of the current moment and the output information of the output door, specifically comprising:
acquiring a state unit at the current moment according to the memory state and the state unit expression at the current moment, and acquiring a current traffic accident state vector according to the state unit at the current moment, the output information of an output gate and the state vector expression at the current moment; the state unit expression is
Figure BDA0003046172200000033
The state vector expression is
Figure BDA0003046172200000041
Wherein the content of the first and second substances,
Figure BDA0003046172200000042
for the current memory state, CtAs a status unit of the current time, ftFor output information of forgetting gate, itFor inputting output information of the gate, otIs the output information of the output gate.
The invention also provides a traffic weather disaster assessment device, which comprises a processor and a memory, wherein the memory is stored with a computer program, and when the computer program is executed by the processor, the traffic weather disaster assessment method of any technical scheme is realized.
The invention also provides a computer readable storage medium, on which a computer program is stored, wherein the computer program, when executed by a processor, implements the traffic weather hazard assessment method according to any one of the above technical solutions.
Compared with the prior art, the invention has the beneficial effects that: historical meteorological information and historical traffic accident data information are obtained; establishing a traffic meteorological disaster prediction model according to the historical meteorological information and the historical traffic accident data information, and training the traffic meteorological disaster prediction model to obtain a trained traffic meteorological disaster prediction model; re-acquiring historical meteorological information and historical traffic accident data information, inputting the historical meteorological information and the historical traffic accident data information into a trained traffic meteorological disaster prediction model to obtain a traffic accident state vector, and evaluating the traffic meteorological disaster according to the traffic accident state vector; the assessment of the traffic meteorological disasters is realized.
Drawings
FIG. 1 is a schematic flow chart illustrating an embodiment of a traffic weather disaster assessment method according to the present invention;
FIG. 2 shows the structure of the memory cell of the LSTM provided by the present invention.
Detailed Description
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate preferred embodiments of the invention and together with the description, serve to explain the principles of the invention and not to limit the scope of the invention.
The invention provides a traffic meteorological disaster assessment method, wherein the flow schematic diagram of one embodiment is shown in figure 1, and the method comprises the following steps:
s1, acquiring historical meteorological information and historical traffic accident data information;
s2, establishing a traffic meteorological disaster prediction model according to the historical meteorological information and the historical traffic accident data information, and training the traffic meteorological disaster prediction model to obtain a trained traffic meteorological disaster prediction model;
and S3, reacquiring historical weather information and historical traffic accident data information, inputting the historical weather information and the historical traffic accident data information into a trained traffic weather disaster prediction model to obtain a traffic accident state vector, and evaluating the traffic weather disaster according to the traffic accident state vector.
In a specific embodiment, historical weather information and historical traffic accident data information are obtained, a data twin is constructed by using a data twin technology, and a virtual environment which is mapped to a physical world is constructed.
As a preferred embodiment, establishing a prediction model of the traffic weather disaster according to the historical weather information and the historical traffic accident data information specifically includes:
and establishing a traffic accident state vector according to the historical meteorological information and the historical traffic accident data information, establishing a recurrent neural network, taking the traffic accident state vector at the previous moment and the meteorological information at the current moment as the input of the recurrent neural network, and taking the current traffic accident state vector as the output of the recurrent neural network to establish a prediction model of the traffic meteorological disasters.
In one embodiment, historical weather information of a past period of time is input into a prediction model of the traffic weather disaster, wherein the historical weather information comprises T continuous moments (1, 2.. multidot.T.) in the history and a weather observation value corresponding to the T continuous moments as Yt＝(y1,y2,...,yT) Wherein, the weather information data corresponding to a certain time t includes k weather index values, which can be expressed as
Figure BDA0003046172200000051
Then, historical traffic accident data information of a past period of time is input, and S is (S)1,s2,...,sT) (ii) a Establishing the influence relationship between the meteorological traffic conditions and the traffic accidents,
Figure BDA0003046172200000052
wherein the content of the first and second substances,
Figure BDA0003046172200000061
the traffic accident state vector is obtained after the influence of meteorological conditions on traffic safety is considered.
As a preferred embodiment, the method for establishing a prediction model of a traffic meteorological disaster by using a traffic accident state vector at a previous moment and meteorological information at a current moment as inputs of a recurrent neural network and using a current traffic accident state vector as an output of the recurrent neural network specifically includes:
and respectively determining the output information of a forgetting gate, the output information of an input gate and the output information of an output gate in the LSTM memory unit structure according to the traffic accident state vector at the previous moment and the meteorological information at the current moment, and determining the current traffic accident state vector according to the output information of the forgetting gate, the output information of the input gate and the output information of the output gate so as to establish a traffic meteorological disaster prediction model.
In one embodiment, an LSTM algorithm in a recurrent neural network is used for establishing a prediction model of the traffic meteorological disaster; in a recurrent neural network, the input to the neural network in the recurrent body has two parts, one being the state vector at the upper time instant under consideration of the influence of meteorological conditions on the traffic accident
Figure BDA0003046172200000062
The other part is the input meteorological sample Y at the current momentt(ii) a After splicing the two, outputting a new state vector through tanh operation
Figure BDA0003046172200000063
As a preferred embodiment, determining the output information of the forgotten gate in the LSTM memory unit structure according to the traffic accident state vector at the previous time and the weather information at the current time specifically includes:
determining the output information of a forgetting gate in an LSTM memory unit structure according to the traffic accident state vector at the previous moment, the weather information at the current moment and an output expression of the forgetting gate, wherein the output expression of the forgetting gate is
Figure BDA0003046172200000064
Wherein f istFor output information of a forgetting gate, σ is an activation function, WfWeight matrix for forgetting gate, bfIn order to forget the biased item of the door,
Figure BDA0003046172200000065
is the traffic accident state vector at the previous moment, YtAnd the weather information is the weather information at the current moment.
In one embodiment, the memory cell structure of LSTM, as shown in FIG. 2, the forgetting gate output expression is
Figure BDA0003046172200000066
ftA status unit C for the output information of the forgetting gate, the forgetting gate determining the last timet-1How many state cells can be retained to the current state, the activation function, typically a sigmoid function,
Figure BDA0003046172200000071
means to concatenate two vectors into one longer vector;
as a preferred embodiment, determining the output information of the input gate in the LSTM memory unit structure according to the traffic accident status vector at the previous time and the weather information at the current time specifically includes:
determining the output information of an input gate in the LSTM memory unit structure according to the traffic accident state vector at the previous moment, the meteorological information at the current moment and an output expression of the input gate, wherein the output expression of the output gate is
Figure BDA0003046172200000072
Wherein, the itFor inputting output information of the gate, WiAs a weight matrix of the input gates, biTo input their paranoia.
The output information of the gate is input, and the gate determines Y of the network at the present timetHow much to save to cell state CtIt is possible to prevent the currently insignificant contents from entering the memory.
As a preferred embodiment, determining the output information of the output gate in the LSTM memory unit structure according to the traffic accident state vector at the previous time and the weather information at the current time specifically includes:
determining the output information of an output gate in the LSTM memory unit structure according to the traffic accident state vector at the previous moment, the meteorological information at the current moment and an output gate output expression, wherein the output gate output expression is
Figure BDA0003046172200000073
Wherein o istFor outputting the output information of the gate, WoAs a weight matrix of output gates, boIs the biased item of the output gate.
It should be noted that the output information of the output gate indicates how much of the state of the output gate control unit is output to the current output value of the LSTM, that is, the influence of the control long-term memory on the current output.
As a preferred embodiment, determining the current traffic accident state vector according to the output information of the forgotten gate, the output information of the input gate, and the output information of the output gate specifically includes:
and determining the memory state of the current moment according to the output information of the forgetting gate, the output information of the input gate and the output information of the output gate, acquiring the state unit of the current moment according to the memory state of the current moment, and acquiring the state vector of the current traffic accident according to the state unit of the current moment and the output information of the output gate.
As a preferred embodiment, the method for acquiring a state unit at the current time according to a memory state at the current time and acquiring a current traffic accident state vector according to the state unit at the current time and output information of an output gate includes:
acquiring a state unit at the current moment according to the memory state and the state unit expression at the current moment, and acquiring a current traffic accident state vector according to the state unit at the current moment, the output information of an output gate and the state vector expression at the current moment; the state unit expression is
Figure BDA0003046172200000081
The state vector expression is
Figure BDA0003046172200000082
Wherein the content of the first and second substances,
Figure BDA0003046172200000083
for the current memory state, CtAs a status unit of the current time, ftFor output information of forgetting gate, itFor inputting output information of the gate, otIs the output information of the output gate.
In one embodiment, the current memory state
Figure BDA0003046172200000084
Figure BDA0003046172200000085
Obtaining the current memory state through state adjustment
Figure BDA0003046172200000086
The final output part transforms the memory value into a value between-1 and +1 by using an activation function tanh (), and a positive interval represents reasonable output. After the traffic accident state vector is obtained, the traffic meteorological disasters are evaluated, the traffic meteorological disasters are larger when the numerical value is larger, real-time state monitoring and dynamic state evaluation of the target object can be realized by utilizing a VR presentation technology, and a feedback and early warning report is given back to a physical entity.
The invention also provides a traffic weather disaster assessment device, which comprises a processor and a memory, wherein the memory is stored with a computer program, and the computer program is executed by the processor to realize all the above mentioned traffic weather disaster assessment methods. It can be understood that, in the present embodiment, the traffic weather disaster assessment apparatus can achieve the same functions as the above method, and has the same technical effects, which are not described herein again.
Embodiments of the present invention provide a computer-readable storage medium on which a computer program is stored, which, when executed by a processor, implements all of the above-mentioned traffic weather hazard assessment methods. It can be understood that, in the present embodiment, the traffic weather disaster assessment apparatus can achieve the same functions as the above method, and has the same technical effects, which are not described herein again.
In summary, the invention discloses a traffic weather disaster assessment method, a device and a computer readable storage medium, which are used for obtaining historical weather information and historical traffic accident data information; establishing a traffic meteorological disaster prediction model according to the historical meteorological information and the historical traffic accident data information, and training the traffic meteorological disaster prediction model to obtain a trained traffic meteorological disaster prediction model; re-acquiring historical meteorological information and historical traffic accident data information, inputting the historical meteorological information and the historical traffic accident data information into a trained traffic meteorological disaster prediction model to obtain a traffic accident state vector, and evaluating the traffic meteorological disaster according to the traffic accident state vector; the assessment of the traffic meteorological disasters is realized. The technical scheme of the invention combines a prediction model with a digital twin, simulates a prediction result in a virtual model, realizes real-time state monitoring and dynamic state evaluation of a target object by utilizing a VR presentation technology, and feeds back and early warning reports to a physical entity.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention.

Claims (10)

1. A traffic meteorological disaster assessment method is characterized by comprising the following steps:
acquiring historical meteorological information and historical traffic accident data information;
establishing a traffic meteorological disaster prediction model according to the historical meteorological information and the historical traffic accident data information, and training the traffic meteorological disaster prediction model to obtain a trained traffic meteorological disaster prediction model;
and re-acquiring historical meteorological information and historical traffic accident data information, inputting the historical meteorological information and the historical traffic accident data information into a trained traffic meteorological disaster prediction model to obtain a traffic accident state vector, and evaluating the traffic meteorological disasters according to the traffic accident state vector.
2. The method for assessing traffic weather disasters according to claim 1, wherein the building of a predictive model of traffic weather disasters based on the historical weather information and the historical traffic accident data information specifically comprises:
and establishing a traffic accident state vector according to the historical meteorological information and the historical traffic accident data information, establishing a recurrent neural network, taking the traffic accident state vector at the previous moment and the meteorological information at the current moment as the input of the recurrent neural network, and taking the current traffic accident state vector as the output of the recurrent neural network to establish a prediction model of the traffic meteorological disasters.
3. The method for assessing traffic meteorological disasters according to claim 2, wherein the step of establishing a prediction model of the traffic meteorological disasters by using the traffic accident state vector at the previous moment and the meteorological information at the current moment as inputs of the recurrent neural network and using the current traffic accident state vector as an output of the recurrent neural network comprises the steps of:
and respectively determining the output information of a forgetting gate, the output information of an input gate and the output information of an output gate in the LSTM memory unit structure according to the traffic accident state vector at the previous moment and the meteorological information at the current moment, and determining the current traffic accident state vector according to the output information of the forgetting gate, the output information of the input gate and the output information of the output gate so as to establish a traffic meteorological disaster prediction model.
4. The method for assessing traffic weather disasters according to claim 3, wherein determining the output information of a forgotten door in the LSTM memory unit structure according to the traffic accident state vector at the previous time and the weather information at the current time comprises:
determining the output information of a forgetting gate in an LSTM memory unit structure according to the traffic accident state vector at the previous moment, the weather information at the current moment and an output expression of the forgetting gate, wherein the output expression of the forgetting gate is
Figure FDA0003046172190000021
Wherein f istFor output information of a forgetting gate, σ is an activation function, WfWeight matrix for forgetting gate, bfIn order to forget the biased item of the door,
Figure FDA0003046172190000022
is the traffic accident state vector at the previous moment, YtAnd the weather information is the weather information at the current moment.
5. The method for assessing traffic weather disasters according to claim 4, wherein determining the output information of the input gates in the LSTM memory unit structure according to the traffic accident state vector at the previous time and the weather information at the current time comprises:
determining the output information of an input gate in the LSTM memory unit structure according to the traffic accident state vector at the previous moment, the meteorological information at the current moment and an output expression of the input gate, wherein the output expression of the output gate is
Figure FDA0003046172190000023
Wherein, the itFor inputting output information of the gate, WiAs a weight matrix of the input gates, biTo input their paranoia.
6. The method for assessing traffic weather disasters according to claim 5, wherein determining the output information of the output gate in the LSTM memory unit structure according to the traffic accident state vector at the previous time and the weather information at the current time comprises:
determining the output information of an output gate in the LSTM memory unit structure according to the traffic accident state vector at the previous moment, the meteorological information at the current moment and an output gate output expression, wherein the output gate output expression is
Figure FDA0003046172190000024
Wherein o istFor outputting the output information of the gate, WoAs a weight matrix of output gates, boIs the biased item of the output gate.
7. The method for assessing traffic weather disasters according to claim 3, wherein determining a current traffic accident state vector according to the output information of the forgotten gate, the output information of the input gate, and the output information of the output gate specifically comprises:
and determining the memory state of the current moment according to the output information of the forgetting gate, the output information of the input gate and the output information of the output gate, acquiring the state unit of the current moment according to the memory state of the current moment, and acquiring the state vector of the current traffic accident according to the state unit of the current moment and the output information of the output gate.
8. The method for assessing traffic weather disasters according to claim 1, wherein the obtaining of the state unit of the current time according to the memory state of the current time and the obtaining of the state vector of the current traffic accident according to the state unit of the current time and the output information of the output gate comprise:
acquiring a state unit at the current moment according to the memory state and the state unit expression at the current moment, and acquiring a current traffic accident state vector according to the state unit at the current moment, the output information of an output gate and the state vector expression at the current moment; the state unit expression is
Figure FDA0003046172190000031
The state vector expression is
Figure FDA0003046172190000032
Wherein the content of the first and second substances,
Figure FDA0003046172190000033
for the current memory state, CtAs a status unit of the current time, ftFor output information of forgetting gate, itFor inputting output information of the gate, otIs the output information of the output gate.
9. A traffic weather hazard assessment apparatus comprising a processor and a memory, the memory having stored thereon a computer program which, when executed by the processor, carries out the traffic weather hazard assessment method according to any one of claims 1 to 8.
10. A computer-readable storage medium having stored thereon a computer program, wherein the computer program, when executed by a processor, implements a traffic weather hazard assessment method according to any one of claims 1 to 8.
CN202110473219.3A 2021-04-29 2021-04-29 Traffic meteorological disaster assessment method and device and computer readable storage medium Active CN113379187B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110473219.3A CN113379187B (en) 2021-04-29 2021-04-29 Traffic meteorological disaster assessment method and device and computer readable storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110473219.3A CN113379187B (en) 2021-04-29 2021-04-29 Traffic meteorological disaster assessment method and device and computer readable storage medium

Publications (2)

Publication Number Publication Date
CN113379187A true CN113379187A (en) 2021-09-10
CN113379187B CN113379187B (en) 2023-01-10

Family

ID=77570345

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110473219.3A Active CN113379187B (en) 2021-04-29 2021-04-29 Traffic meteorological disaster assessment method and device and computer readable storage medium

Country Status (1)

Country Link
CN (1) CN113379187B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114781696A (en) * 2022-03-30 2022-07-22 西安电子科技大学 City road network-oriented model-free accident influence range prediction method
CN115469291A (en) * 2022-11-01 2022-12-13 湖南赛能环测科技有限公司 Method and system for forecasting meteorological radar based on digital twin technology

Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2001143109A (en) * 1999-11-17 2001-05-25 Hitachi Ltd Device for estimating traffic lane operation of pay road and method for operating traffic lane
CN104732075A (en) * 2015-03-06 2015-06-24 中山大学 Real-time prediction method for urban road traffic accident risk
CN107978149A (en) * 2017-11-17 2018-05-01 嘉兴四维智城信息科技有限公司 Typhoon weather urban traffic accident probabilistic forecasting processing unit and its method
CN109117987A (en) * 2018-07-18 2019-01-01 厦门大学 Personalized street accidents risks based on deep learning predict recommended method
CN110264711A (en) * 2019-05-29 2019-09-20 北京世纪高通科技有限公司 A kind of traffic accident method of determining probability and device
CN110415544A (en) * 2019-08-20 2019-11-05 深圳疆程技术有限公司 A kind of hazard weather method for early warning and automobile AR-HUD system
US20190354838A1 (en) * 2018-05-21 2019-11-21 Uber Technologies, Inc. Automobile Accident Detection Using Machine Learned Model
CN111461413A (en) * 2020-03-20 2020-07-28 淮阴工学院 Highway road surface performance detecting system
CN111489577A (en) * 2020-06-03 2020-08-04 刘胜楠 Highway disaster weather self-adaptation intelligent early warning real-time speed limiting system
CN111798662A (en) * 2020-07-31 2020-10-20 公安部交通管理科学研究所 Urban traffic accident early warning method based on space-time gridding data
CN111882869A (en) * 2020-07-13 2020-11-03 大连理工大学 Deep learning traffic flow prediction method considering adverse weather

Patent Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2001143109A (en) * 1999-11-17 2001-05-25 Hitachi Ltd Device for estimating traffic lane operation of pay road and method for operating traffic lane
CN104732075A (en) * 2015-03-06 2015-06-24 中山大学 Real-time prediction method for urban road traffic accident risk
CN107978149A (en) * 2017-11-17 2018-05-01 嘉兴四维智城信息科技有限公司 Typhoon weather urban traffic accident probabilistic forecasting processing unit and its method
US20190354838A1 (en) * 2018-05-21 2019-11-21 Uber Technologies, Inc. Automobile Accident Detection Using Machine Learned Model
CN109117987A (en) * 2018-07-18 2019-01-01 厦门大学 Personalized street accidents risks based on deep learning predict recommended method
CN110264711A (en) * 2019-05-29 2019-09-20 北京世纪高通科技有限公司 A kind of traffic accident method of determining probability and device
CN110415544A (en) * 2019-08-20 2019-11-05 深圳疆程技术有限公司 A kind of hazard weather method for early warning and automobile AR-HUD system
CN111461413A (en) * 2020-03-20 2020-07-28 淮阴工学院 Highway road surface performance detecting system
CN111489577A (en) * 2020-06-03 2020-08-04 刘胜楠 Highway disaster weather self-adaptation intelligent early warning real-time speed limiting system
CN111882869A (en) * 2020-07-13 2020-11-03 大连理工大学 Deep learning traffic flow prediction method considering adverse weather
CN111798662A (en) * 2020-07-31 2020-10-20 公安部交通管理科学研究所 Urban traffic accident early warning method based on space-time gridding data

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
LE YU 等: "Traffic Accident Prediction Based on Deep Spatio-Temporal Analysis", 《2019 IEEE SMARTWORLD, UBIQUITOUS INTELLIGENCE & COMPUTING, ADVANCED & TRUSTED COMPUTING, SCALABLE COMPUTING & COMMUNICATIONS, CLOUD & BIG DATA COMPUTING, INTERNET OF PEOPLE AND SMART CITY INNOVATION》 *
邹涛涛: "气象因素对道路交通安全的影响分析与预测系统", 《中国优秀硕士学位论文全文数据库 (工程科技Ⅰ辑)》 *

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114781696A (en) * 2022-03-30 2022-07-22 西安电子科技大学 City road network-oriented model-free accident influence range prediction method
CN114781696B (en) * 2022-03-30 2024-04-16 西安电子科技大学 Model-free accident influence range prediction method for urban road network
CN115469291A (en) * 2022-11-01 2022-12-13 湖南赛能环测科技有限公司 Method and system for forecasting meteorological radar based on digital twin technology

Also Published As

Publication number Publication date
CN113379187B (en) 2023-01-10

Similar Documents

Publication Publication Date Title
CN113379187B (en) Traffic meteorological disaster assessment method and device and computer readable storage medium
CN110298501B (en) Electrical load prediction method based on long-time and short-time memory neural network
CN111274737A (en) Method and system for predicting remaining service life of mechanical equipment
CN112529275B (en) Wind power climbing event prediction method based on feature extraction and deep learning
KR102172925B1 (en) Operating method of deep learning based climate change prediction system
CN112639495A (en) Battery detection method and device
CN112036075A (en) Abnormal data judgment method based on environmental monitoring data association relation
CN112183886A (en) Short-time approaching rainfall prediction method based on convolutional network and attention mechanism
Bohan et al. Traffic flow prediction based on BRNN
CN114154619A (en) Ship track prediction method based on CNN and BILSTM
CN115220133B (en) Rainfall prediction method, device and equipment for multiple meteorological elements and storage medium
Abdullahi et al. Flood disaster warning system on the go
CN113671421A (en) Transformer state evaluation and fault early warning method
CN114662791A (en) Long time sequence pm2.5 prediction method and system based on space-time attention
CN116028315A (en) Operation early warning method, device, medium and electronic equipment
CN116597642A (en) Traffic jam condition prediction method and system
Zhai et al. Optimization of Traffic Congestion Management in Smart Cities under Bidirectional Long and Short‐Term Memory Model
CN113378582A (en) Landslide displacement prediction model and method based on semantic information driving
CN111369078A (en) Water supply quality prediction method based on long-term and short-term memory neural network
CN114862062B (en) Early warning method and device for environmental bearing capacity, electronic equipment and readable storage medium
CN116523298A (en) Method for evaluating and tracing risk of preservation environment of cultural relics in collection of cultural relics
CN116720098A (en) Abnormal behavior sensitive student behavior time sequence modeling and academic early warning method
CN114444872A (en) Method and system for analyzing driving behavior of driver by adopting artificial intelligence algorithm
CN114037159A (en) Short-time passenger flow prediction method and system based on multi-source data fusion input
Qu et al. Research on the Academic Early Warning Model of Distance Education based on Student Behavior Data in the Context of COVID-19

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