CN112733874A - Suspicious vehicle discrimination method based on knowledge graph reasoning - Google Patents

Suspicious vehicle discrimination method based on knowledge graph reasoning Download PDF

Info

Publication number
CN112733874A
CN112733874A CN202011144715.6A CN202011144715A CN112733874A CN 112733874 A CN112733874 A CN 112733874A CN 202011144715 A CN202011144715 A CN 202011144715A CN 112733874 A CN112733874 A CN 112733874A
Authority
CN
China
Prior art keywords
entity
path
triple
relation
model
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
CN202011144715.6A
Other languages
Chinese (zh)
Other versions
CN112733874B (en
Inventor
俞山川
谢耀华
闫禹
周欣
周健
王少飞
涂耘
陈晓利
叶青
陈晨
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.)
China Merchants Chongqing Communications Research and Design Institute Co Ltd
Original Assignee
China Merchants Chongqing Communications Research and Design Institute Co Ltd
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 China Merchants Chongqing Communications Research and Design Institute Co Ltd filed Critical China Merchants Chongqing Communications Research and Design Institute Co Ltd
Priority to CN202011144715.6A priority Critical patent/CN112733874B/en
Publication of CN112733874A publication Critical patent/CN112733874A/en
Application granted granted Critical
Publication of CN112733874B publication Critical patent/CN112733874B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • 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
    • G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
    • G06F16/367—Ontology
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T10/00—Road transport of goods or passengers
    • Y02T10/10—Internal combustion engine [ICE] based vehicles
    • Y02T10/40—Engine management systems

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Computation (AREA)
  • Evolutionary Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Artificial Intelligence (AREA)
  • Animal Behavior & Ethology (AREA)
  • Computational Linguistics (AREA)
  • Databases & Information Systems (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Traffic Control Systems (AREA)

Abstract

The invention discloses a suspicious vehicle distinguishing method based on knowledge graph reasoning, which comprises the following steps: s1: the method comprises the steps of obtaining suspicious vehicle knowledge, representing the suspicious vehicle knowledge in a triple (h, r, t) mode based on a knowledge graph construction mode, and establishing a suspicious vehicle knowledge graph; wherein h represents a head entity, r represents a relationship, and t represents a tail entity; s2: embedding the triple suspicious vehicle knowledge graph into a vector space in a fusion manner to obtain a triple expression vector; s3: constructing a triple relation model, training the triple relation model, and determining the vector similarity between the relation r of the entity h and the tail entity t according to a relation score function; s4: and constructing a triple path model, training the triple path model, and determining the reliability between the relation r of the entity h and the tail entity t according to a path score function of the triple path model, wherein the path with the highest path score is an inference result.

Description

Suspicious vehicle discrimination method based on knowledge graph reasoning
Technical Field
The invention relates to a suspicious vehicle distinguishing method based on knowledge graph reasoning.
Background
With the establishment of an intelligent management system/platform of management departments such as an expressway and the like, managers can obviously improve the capacity and dimensionality in the aspects of automatic vehicle feature identification and automatic historical behavior recording, and the establishment of a large number of electronic files for vehicles becomes possible. However, the relevance between vehicles and potential traffic accidents of vehicles is lack of deep mining, and the management department is difficult to perform 'capture' and fine management on suspicious vehicles.
Disclosure of Invention
The invention aims to provide a suspicious vehicle distinguishing method based on knowledge graph reasoning, which aims to solve the problem that the suspicious vehicle is difficult to effectively identify at present.
In order to solve the technical problem, the invention provides a suspicious vehicle discrimination method based on knowledge graph reasoning, which comprises the following steps:
s1: the method comprises the steps of obtaining suspicious vehicle knowledge, representing the suspicious vehicle knowledge in the form of triples (h, r, t) based on a construction mode of a knowledge graph, and establishing the suspicious vehicle knowledge graph; wherein h represents a head entity, r represents a relation, and t represents a tail entity;
s2: embedding the triple suspicious vehicle knowledge graph into a vector space in a fusion manner to obtain a triple representing vector;
s3: constructing a triple relation model, training the triple relation model, and determining the vector similarity between the relation r of the entity h and the tail entity t according to a relation score function;
s4: and constructing a triple path model, training the triple path model, and determining the reliability between the relation r of the entity h and the tail entity t according to a path score function of the triple path model, wherein the path with the highest path score is an inference result.
Further, constructing the triple relationship model specifically includes:
and establishing one-to-one, one-to-many, many-to-one or many-to-many relationship between the entity h and the entity t through mapping of the entity space and the relationship space.
Further, a score function f is calculated according to the relationshipr(h, t) determining the vectorial similarity between the relation r of the entity h and the tail entity t, said relation scoring function fr(h, t) is calculated using formula (1):
Figure BDA0002739353840000021
wherein, wh、wt、wrMapping functions between entity/relationship representations; i is an identity matrix; each vector satisfies the following constraints:
||h||2≤1,||r||2≤1,||t||2≤1 (2)
Figure BDA0002739353840000022
further, the training target of the triplet relation model is a minimization loss function, and the minimization loss function is expressed as follows:
Figure BDA0002739353840000023
s.t.
Figure BDA0002739353840000024
wherein,
Figure BDA0002739353840000025
representing a set of triples;
Figure BDA0002739353840000026
a negative sample representing (h, r, t) is obtained by randomly replacing a head entity h or a tail entity t in the training process; and, if
Figure BDA0002739353840000027
Figure BDA0002739353840000028
Figure BDA0002739353840000029
Further, constructing the triplet path model specifically includes:
generating path representation according to the relation between the entities h and t, and according to the characteristic value function s of each pathh,p(e)Establishing a series of paths, wherein the path set is represented as:
p(h,t)＝{…,pi(h,t),…}
wherein p isi(h,t)＝(h,r1,e1,r2,e2,…,ek-1,rkT), k is the path length.
Further, a path score function f is usedp(h, t) to determine the reliability between the relation r of the entity h and the tail entity t, the path score function fp(h, t) is calculated by the formula (5):
Figure BDA0002739353840000031
probability of each sample being
Figure BDA0002739353840000032
Further, the training target of the triplet path model is a minimization loss function, and the minimization loss function is expressed as follows:
Figure BDA0002739353840000033
the invention has the beneficial effects that: the invention judges whether a certain vehicle running in a certain area is a suspicious vehicle or not based on knowledge map reasoning, and accordingly, the invention carries out early warning on relevant management departments such as an expressway and the like, and improves the capabilities of the management departments in capturing the suspicious vehicle and handling the accident in an emergency.
Detailed Description
A suspicious vehicle discrimination method based on knowledge graph reasoning,
s1: the method comprises the steps of obtaining suspicious vehicle knowledge, representing the suspicious vehicle knowledge in the form of triples (h, r, t) based on a construction mode of a knowledge graph, and establishing the suspicious vehicle knowledge graph; wherein h represents a head entity, r represents a relation, and t represents a tail entity;
wherein the suspicious vehicle knowledge comprises: within an area (e.g., a section of highway), vehicles meeting one of three conditions: firstly, the vehicle type, the license plate and the driver characteristics are not matched with the historical records of the database; (ii) has occurred in a historical accident site; thirdly, traffic violation such as overspeed and overload or dangerous driving behaviors such as lushikim lane change occur for many times; and fourthly, the vehicle which is determined to be suspicious often appears simultaneously, namely, the vehicle which is along with the suspicious vehicle.
S2: embedding the triple suspicious vehicle knowledge graph into a vector space in a fusion manner to obtain a triple representing vector;
by using
Figure BDA0002739353840000041
A collection of entities is represented as a set of entities,
Figure BDA0002739353840000042
representing a collection of relationships. Representing a pair of embedded relationships using a triplet (h, r, t), where
Figure BDA0002739353840000047
The header entity is represented as a header entity,
Figure BDA0002739353840000043
the relationship is represented by a relationship of,
Figure BDA0002739353840000044
representing the tail entity. Grouping of triplets
Figure BDA0002739353840000045
And (4) showing. Thus, each entity and relationship in the knowledge-graph is represented as a vector. Examples are as follows:
if r is the relationship of "car type", then (h, r, t) can be expressed as (Yu A00000, car type, car); if r is a "driver is" relationship, (h, r, t) can be represented as (Yu A00000, driver is, driver ID 1); if r is a "body characteristic is" relationship, (h, r, t) can be represented as (driver ID 1, body characteristic is, thin); if r is "occurred at the accident scene", then (h, r, t) can be expressed as (Yu A00000, occurred at the accident scene, accident ID 1); if r is "multiple traffic violations," then (h, r, t) can be expressed as (Yu A00000, multiple traffic violations, 0 or 1); if r is "present at location", then (h, r, t) can be expressed as (Yu A00000, present at location, K1+ 120); if r is "present at time", then (h, r, t) can be expressed as (Yu A00000, present at time, YYYY-MM-DDhh: MM: ss); and so on.
S3: constructing a triple relation model, training the triple relation model, and determining the vector similarity between the relation r of the entity h and the tail entity t according to a relation score function;
1. triple relationship model building
The ranD model establishes one-to-one, one-to-many, many-to-one or many-to-many relationships between h and t through mapping of the entity space and the relationship space. The vector similarity between the relations r is measured by a score function. Score function fr(h, t) is calculated by the formula (1):
Figure BDA0002739353840000046
wherein, wh、wt、wrMapping functions between entity/relationship representations; and I is an identity matrix. Each vector satisfies the following constraints:
||h||2≤1,||r||2≤1,||t||2≤1 (2)
Figure BDA0002739353840000051
2. triple relationship model training
The training goal of the triplet relation model is to minimize the loss function, which is expressed as follows:
Figure BDA0002739353840000052
s.t.
Figure BDA0002739353840000053
wherein,
Figure BDA0002739353840000054
representing a set of triples;
Figure BDA0002739353840000055
a negative sample representing (h, r, t) is obtained by randomly replacing a head entity h or a tail entity t in the training process; and, if
Figure BDA0002739353840000056
Figure BDA0002739353840000057
Figure BDA0002739353840000058
S4: and constructing a triple path model, training the triple path model, and determining the reliability between the relation r of the entity h and the tail entity t according to a path score function of the triple path model, wherein the path with the highest path score is an inference result.
For example, if the suspicious vehicle feature knowledge graph contains relationships (li x, driving, yu a 00000), (yu a00000, affiliated to Chongqing shipping Co., Ltd.), then the missing relationships (li x, working at Chongqing shipping Co., Ltd.) may be obtained.
The invention calculates the characteristic value function s of each path based on a random walk modelh,P(t)Thereby establishing a series of paths. A path P is defined by a series of relationships r1,…,rl,…,rnConsists of the following components:
Figure BDA0002739353840000059
wherein, Tn-1Is a relation rnHas a scope of relationship rn-1Value range of (i.e. T)n-1＝ran(rn)＝ dom(rn-1). Scope and value of the relationship, i.e. type of entity, T0＝{h}，TnT. Function of eigenvalues sh,P(t)Is the probability that the tail entity t can be reached starting from the head entity h along path P. When the path goes to any intermediate entity e, sh,P(e)The updating method is
Figure BDA0002739353840000061
Wherein, in the initial stage of random walk, sh,P(e)1 if e ∈ P; otherwise sh,P(e)0. I (e', e) is an indicator function, I (r)l(e', e)) -1 if rl(e', e) present, otherwise I (r)l(e′,e))＝0；
For the relation r, a series of path characteristics P are obtained through a random walk algorithmr＝{P1,…,PnAfter that, for each training sample under the relation r(i.e., a combination of head and tail entities) a scoring function is established:
Figure BDA0002739353840000062
the probability for each sample is:
Figure BDA0002739353840000063
the minimization loss function is:
min wk(yk log Pk+(1-yk)log(1-Pk)) (7)
wherein, ykFor training the sample (h)k,tk) Whether or not there is a flag of the relation r, ykIf triplet (h) is 1k,r,tk) (ii) present; otherwise yk＝0。
The method can well establish the 1-to-N, N-to-1 and N-to-N relationships and other complex relationships, is simpler and higher in calculation efficiency than other methods of the same type, and is suitable for establishing the data knowledge graph of the mass suspicious vehicles in the management department platforms such as the highway. The model training of the method is based on open world assumption, the effect on incomplete knowledge maps is better, and in model training fine tuning, the model effect based on the open world assumption is better.
Finally, the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all of them should be covered in the claims of the present invention.

Claims (7)

1. A suspicious vehicle discrimination method based on knowledge graph reasoning is characterized by comprising the following steps:
s1: the method comprises the steps of obtaining suspicious vehicle knowledge, representing the suspicious vehicle knowledge in a triple (h, r, t) mode based on a knowledge graph construction mode, and establishing a suspicious vehicle knowledge graph; wherein h represents a head entity, r represents a relationship, and t represents a tail entity;
s2: embedding the triple suspicious vehicle knowledge graph into a vector space in a fusion manner to obtain a triple expression vector;
s3: constructing a triple relation model, training the triple relation model, and determining the vector similarity between the relation r of the entity h and the tail entity t according to a relation score function;
s4: and constructing a triple path model, training the triple path model, and determining the reliability between the relation r of the entity h and the tail entity t according to a path score function of the triple path model, wherein the path with the highest path score is an inference result.
2. The method for distinguishing suspicious vehicles based on knowledge graph reasoning according to claim 1, wherein the constructing of the triple relationship model specifically comprises:
and establishing one-to-one, one-to-many, many-to-one or many-to-many relationship between the entity h and the entity t through mapping of the entity space and the relationship space.
3. The method of claim 2, wherein the method of suspect vehicle discrimination based on knowledgegraph reasoning is based on a relational score function fr(h, t) determining the vector similarity between the relation r of the entity h and the tail entity t, said relation scoring function fr(h, t) is calculated using formula (1):
Figure FDA0002739353830000011
wherein, wh、wt、wrMapping functions between entity/relationship representations; i is an identity matrix; each vector satisfies the following constraints:
||h||2≤1，||r||2≤1，||t||2≤1 (2)
Figure FDA0002739353830000021
4. the method of claim 3, wherein the training objective of the triplet relational model is a minimization loss function, the minimization loss function being expressed as follows:
Figure FDA0002739353830000022
s.t.
Figure FDA0002739353830000023
wherein,
Figure FDA0002739353830000024
representing a set of triples;
Figure FDA0002739353830000025
a negative sample representing (h, r, t) is obtained by randomly replacing a head entity h or a tail entity t in the training process; and, if
Figure FDA0002739353830000026
yhrt＝1；
Figure FDA0002739353830000027
yhrt＝-1。
5. The method for suspicious vehicle discrimination based on knowledge-graph reasoning according to claim 4, wherein the constructing the triple path model specifically comprises:
generating path representation according to the relation between the entities h and t, and according to the characteristic value function s of each pathh，p(e)Establishing a series of paths, wherein the path set is represented as:
p(h，t)＝{...，pi(h，t)，...}
wherein p isi(h，t)＝(h，r1，e1，r2，e2，...，ek-1，rkT), k is the path length, ek-1Are entities on the path.
6. The method of claim 5, wherein a path score function f is usedp(h, t) to determine the reliability between the relation r of the entity h and the tail entity t, the path score function fp(h, t) is calculated by the formula (5):
Figure FDA0002739353830000028
probability of each sample being
Figure FDA0002739353830000031
7. The method of claim 6, wherein the training objective of the triplet path model is a minimization loss function, the minimization loss function being expressed as follows:
Figure FDA0002739353830000032
CN202011144715.6A 2020-10-23 2020-10-23 Suspicious vehicle discrimination method based on knowledge graph reasoning Active CN112733874B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011144715.6A CN112733874B (en) 2020-10-23 2020-10-23 Suspicious vehicle discrimination method based on knowledge graph reasoning

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011144715.6A CN112733874B (en) 2020-10-23 2020-10-23 Suspicious vehicle discrimination method based on knowledge graph reasoning

Publications (2)

Publication Number Publication Date
CN112733874A true CN112733874A (en) 2021-04-30
CN112733874B CN112733874B (en) 2023-04-07

Family

ID=75597309

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011144715.6A Active CN112733874B (en) 2020-10-23 2020-10-23 Suspicious vehicle discrimination method based on knowledge graph reasoning

Country Status (1)

Country Link
CN (1) CN112733874B (en)

Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120096042A1 (en) * 2010-10-19 2012-04-19 Microsoft Corporation User query reformulation using random walks
CN103098111A (en) * 2010-09-24 2013-05-08 丰田自动车株式会社 Track estimation device and program
CN109799477A (en) * 2018-12-06 2019-05-24 北京邮电大学 A kind of sequential vehicle fingerprint localization method and device towards millimeter wave car networking
CN110119355A (en) * 2019-04-25 2019-08-13 天津大学 A kind of knowledge based map vectorization reasoning common software defect modeling method
CN110232186A (en) * 2019-05-20 2019-09-13 浙江大学 The knowledge mapping for merging entity description, stratification type and text relation information indicates learning method
CN110781254A (en) * 2020-01-02 2020-02-11 四川大学 Automatic case knowledge graph construction method, system, equipment and medium
CN110795543A (en) * 2019-09-03 2020-02-14 腾讯科技（深圳）有限公司 Unstructured data extraction method and device based on deep learning and storage medium
CN111026875A (en) * 2019-11-26 2020-04-17 中国人民大学 Knowledge graph complementing method based on entity description and relation path
CN111291135A (en) * 2020-01-21 2020-06-16 深圳追一科技有限公司 Knowledge graph construction method and device, server and computer readable storage medium
CN111597350A (en) * 2020-04-30 2020-08-28 西安理工大学 Rail transit event knowledge map construction method based on deep learning
CN111753101A (en) * 2020-06-30 2020-10-09 华侨大学 Knowledge graph representation learning method integrating entity description and type

Patent Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103098111A (en) * 2010-09-24 2013-05-08 丰田自动车株式会社 Track estimation device and program
US20120096042A1 (en) * 2010-10-19 2012-04-19 Microsoft Corporation User query reformulation using random walks
CN109799477A (en) * 2018-12-06 2019-05-24 北京邮电大学 A kind of sequential vehicle fingerprint localization method and device towards millimeter wave car networking
CN110119355A (en) * 2019-04-25 2019-08-13 天津大学 A kind of knowledge based map vectorization reasoning common software defect modeling method
CN110232186A (en) * 2019-05-20 2019-09-13 浙江大学 The knowledge mapping for merging entity description, stratification type and text relation information indicates learning method
CN110795543A (en) * 2019-09-03 2020-02-14 腾讯科技（深圳）有限公司 Unstructured data extraction method and device based on deep learning and storage medium
CN111026875A (en) * 2019-11-26 2020-04-17 中国人民大学 Knowledge graph complementing method based on entity description and relation path
CN110781254A (en) * 2020-01-02 2020-02-11 四川大学 Automatic case knowledge graph construction method, system, equipment and medium
CN111291135A (en) * 2020-01-21 2020-06-16 深圳追一科技有限公司 Knowledge graph construction method and device, server and computer readable storage medium
CN111597350A (en) * 2020-04-30 2020-08-28 西安理工大学 Rail transit event knowledge map construction method based on deep learning
CN111753101A (en) * 2020-06-30 2020-10-09 华侨大学 Knowledge graph representation learning method integrating entity description and type

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
张健生等: "东莞公安车辆信息库的建设和应用", 《警察技术》 *
朱振华等: "基于知识图谱的人员关系预测方法研究", 《电脑知识与技术》 *
林霄等: "基于随机游走模型的物体识别", 《计算机工程与应用》 *

Also Published As

Publication number Publication date
CN112733874B (en) 2023-04-07

Similar Documents

Publication Publication Date Title
CN110949398B (en) Method for detecting abnormal driving behavior of first-vehicle drivers in vehicle formation driving
Kim et al. Calibration of microsimulation models using nonparametric statistical techniques
CN109871010B (en) Method and system based on reinforcement learning
CN106448267B (en) Road traffic accident chain based on car networking blocks system
CN113808409B (en) Road safety monitoring method, system and computer equipment
CN110562261B (en) Method for detecting risk level of driver based on Markov model
WO2024067135A1 (en) Unmanned aircraft management method and system based on big data identification, and medium
US20230406357A1 (en) Autonomous driving control device and autonomous driving control method
CN110996300A (en) Vehicle-mounted terminal information safety risk control method based on traffic scene safety
Ma et al. Driving style estimation by fusing multiple driving behaviors: a case study of freeway in China
CN111860383B (en) Group abnormal behavior identification method, device, equipment and storage medium
CN111858719A (en) Specific condition early warning method and system based on vehicle accident data mining analysis
CN112927511A (en) Vehicle early warning method based on driver age and gender identification
CN115270400A (en) Test scene construction method for automatic driving simulation and readable storage medium
CN110634288B (en) Multi-dimensional urban traffic abnormal event identification method based on ternary Gaussian mixture model
CN116911610A (en) Method and system for monitoring, evaluating and early warning of driving safety risk of transport vehicle
CN117671887A (en) Intelligent security early warning management method and system based on big data
CN112733874B (en) Suspicious vehicle discrimination method based on knowledge graph reasoning
CN117557961A (en) Public safety management method and system based on big data intelligent analysis
CN117726999A (en) Driver auxiliary early warning system and method based on deep learning coupling scene outside vehicle
CN116153082B (en) Expressway road condition acquisition, analysis and processing system based on machine vision
CN111222587A (en) Method and system for predicting dangerous driving behavior of people with loss of evidence based on feature fusion
CN115985137B (en) Risk assessment method for tunnel traffic operation, electronic equipment and storage medium
CN114999103B (en) Intelligent early warning system and method for expressway road-related operation safety
CN117104245A (en) Driving style dynamic identification method in Internet of vehicles environment

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