CN113610279A - Accident prediction method based on data set regularity - Google Patents
Accident prediction method based on data set regularity Download PDFInfo
- Publication number
- CN113610279A CN113610279A CN202110817970.0A CN202110817970A CN113610279A CN 113610279 A CN113610279 A CN 113610279A CN 202110817970 A CN202110817970 A CN 202110817970A CN 113610279 A CN113610279 A CN 113610279A
- Authority
- CN
- China
- Prior art keywords
- data
- control unit
- capacity
- data set
- standard
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000010606 normalization Methods 0.000 claims abstract description 27
- 230000008569 process Effects 0.000 claims abstract description 7
- 238000004364 calculation method Methods 0.000 claims description 53
- 230000001788 irregular Effects 0.000 claims description 21
- 102100037651 AP-2 complex subunit sigma Human genes 0.000 claims description 9
- 101000806914 Homo sapiens AP-2 complex subunit sigma Proteins 0.000 claims description 9
- 206010039203 Road traffic accident Diseases 0.000 description 6
- 230000001276 controlling effect Effects 0.000 description 3
- 230000006855 networking Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000003449 preventive effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06Q50/265—Personal security, identity or safety
-
- 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
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Primary Health Care (AREA)
- Development Economics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computer Security & Cryptography (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to an accident prediction method based on data set regularity, which comprises the steps of receiving a user prediction node, collecting a historical data set and an actual data set according to the user prediction node, and carrying out data normalization on the collected actual data set; predicting according to the structured data set to obtain a prediction result, and feeding the prediction result back to a user sending a prediction node; and controlling the data normalization process of the actual data set corresponding to the prediction node of the user. The data volume of the actual data set is compared with the standard data volume to determine whether the data is regular, the data volume difference value is compared with the standard data volume difference value to determine the data compensation parameter and the data volume adjustment quantity, the adjusted data volume is compared with the standard data volume to determine whether the data in the data set is regular again, and therefore a more accurate prediction result can be obtained under the condition that the data are regular, and the accuracy of the prediction result is effectively improved.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to an accident prediction method based on data set regularity.
Background
With the development of society, traffic facilities are developed more and more, the travel demand of people is also improved continuously, but the traffic safety problem is increased more and more. Conventional vehicle accident prevention measures include passive safety systems and active safety systems. With the development of science and technology in recent years, a new generation of safety systems for assisting driving and the like slowly gets on the stage, but researches show that the more reasonable safety systems are necessarily preventive safety systems based on the combination of the car networking technology and the accident prediction technology, because the car networking technology solves the problem that the visual field of a driver is limited, and the vehicles can communicate with each other under the condition of non-visual distance. The car networking technology can judge whether the car is in a dangerous state in real time by combining accident prediction, so that the safety of passengers is better guaranteed, and potential loss is reduced.
Traffic accidents occur as a result of a combination of factors such as road environment, driver behavior, real-time traffic flow, and vehicles traveling on the road. However, the existing accident prediction has hysteresis, and cannot prevent and warn the occurrence of an accident in advance, so the existing accident prediction method needs to be optimized.
Disclosure of Invention
Therefore, the accident prediction method based on the data set regularity can solve the problem of accident prediction hysteresis.
In order to achieve the above object, the present invention provides an accident prediction method based on data set regularity, including:
receiving a user prediction node, collecting a historical data set and an actual data set according to the user prediction node, and carrying out data normalization on the collected actual data set;
predicting according to the structured data set to obtain a prediction result, and feeding the prediction result back to a user sending a prediction node;
controlling a data normalization process of an actual data set corresponding to a prediction node of a user;
when data normalization is carried out on an actual data set corresponding to a prediction node of a user, comparing the capacity A of the actual data set with the capacity of standard data to determine whether data are normalized or not, comparing the difference value P of the data capacity with the difference value of the standard data capacity to determine a data compensation parameter and a data capacity adjustment quantity delta Q, determining an adjusted data capacity Q 'according to a preset formula, and comparing the adjusted data capacity Q' with the standard data capacity to determine whether data are normalized or not again;
the actual data set capacity A is determined according to an actual data set R and a data capacity calculation parameter, and the actual data set R is determined according to a historical data set.
Further, when data normalization is performed on an actual data set corresponding to a prediction node of a user, a control unit obtains a data capacity A of the actual data set corresponding to the prediction node, compares the data capacity A of the actual data set with a standard data capacity to determine whether the data is normalized or not, when the control unit determines that the data is normalized, the control unit transmits the prediction node of the user to the prediction unit to perform prediction to obtain a prediction result, and when the control unit determines that the data is not normalized, a data capacity difference value is calculated;
wherein the control unit is provided with standard data capacities including a standard data first capacity Q1 and a standard data second capacity Q2, wherein Q1 < Q2;
if A is less than Q1, the control unit judges that the data is irregular;
if Q1 is not less than A not more than Q2, the control unit judges that the data is structured;
if A > Q2, the control unit determines that the data is irregular.
Further, when the control unit determines that the data is irregular, the control unit calculates a data capacity difference value P, when the calculation is completed, the control unit compares the data capacity difference value P with a standard data capacity difference value to determine a data compensation parameter, and when the control unit determines that the data compensation parameter is σ i, the control unit calculates a data capacity adjustment quantity Δ Q, and sets Δ Q to σ i × P, i to 1, 2, 3, 4;
wherein the control unit is further provided with a standard data capacity difference value and a standard data compensation parameter, the standard data capacity difference value comprises a standard data capacity first difference value P1, a standard data capacity second difference value P2 and a standard data capacity third difference value P3, wherein P1 < P2 < P3; the standard data compensation parameter comprises a first standard data compensation parameter sigma 1, a second standard data compensation parameter sigma 2, a third standard data compensation parameter sigma 3 and a fourth standard data compensation parameter sigma 4, wherein sigma 1+ sigma 2+ sigma 3+ sigma 4 is 1;
if P is less than P1, the control unit judges the data compensation parameter to be sigma 1;
if P1 is not less than P < P2, the control unit judges that the data compensation parameter is sigma 2;
if P2 is not less than P < P3, the control unit judges that the data compensation parameter is sigma 3;
if P is larger than or equal to P3, the control unit judges that the data compensation parameter is sigma 4.
Further, when the control unit determines the data capacity adjustment amount Δ Q, the control unit calculates the adjusted data capacity Q' according to the following calculation formula:
Q′＝A±△Q；
where a denotes the data capacity of the actual data set, and Q '═ a +. DELTA.q when a < Q1, and Q' ═ a-. DELTA.q when a > Q2.
Further, when the control unit determines the adjusted data capacity Q ', the control unit compares the adjusted data capacity Q' with the standard data capacity to determine whether the data is regular again, when the control unit determines that the data is regular, the control unit transmits the prediction node of the user to the prediction unit to perform prediction to obtain a prediction result, and when the control unit determines that the data is irregular, the control unit collects an actual data set corresponding to the prediction node of the user again;
if Q' < Q1, the control unit determines that the data is irregular;
if Q1 is not less than Q' ≦ Q2, the control unit determines that the data is structured;
if Q' > Q2, the control unit determines that the data is irregular.
Further, when the control unit determines that the data is irregular, the control unit calculates a data capacity difference value P according to the following calculation formula:
P-Q1-a or P-a-Q2;
where a denotes a data capacity of an actual data set, Q1 denotes a standard data first capacity, Q2 denotes a standard data second capacity, and when a < Q1, P is Q1-a, and when a > Q2, P is a-Q2.
Further, when data normalization is performed on an actual data set corresponding to a prediction node of a user, the control unit acquires an actual data set R corresponding to the prediction node, and compares the actual data set R with a preset data length to determine a data capacity calculation parameter;
the control unit is provided with preset data length and standard data capacity calculation parameters, wherein the preset data length comprises a first preset data length R1, a second preset data length R2 and a third preset data length R3, and R1 is more than R2 and more than R3; the standard data capacity calculation parameters comprise a standard data capacity first calculation parameter alpha 1, a standard data capacity second calculation parameter alpha 2, a standard data capacity third calculation parameter alpha 3 and a standard data capacity fourth calculation parameter alpha 4, wherein alpha 1+ alpha 2+ alpha 3+ alpha 4 is 1;
if R < R1, the control unit determines that the data capacity calculation parameter is alpha 1;
if R1 is equal to or less than R < R2, the control unit determines that the data capacity calculation parameter is alpha 2;
if R2 is equal to or less than R < R3, the control unit determines that the data capacity calculation parameter is alpha 3;
if R is larger than or equal to R3, the control unit judges that the data capacity calculation parameter is alpha 4.
Further, when the control unit determines that the data volume calculation parameter is α i, the control unit calculates an actual data set volume a, setting a ═ R × α i, i ═ 1, 2, 3, 4.
Further, when data normalization is performed on an actual data set corresponding to a prediction node of a user, the control unit acquires a historical data set corresponding to the prediction node of the user and sets the historical data set to be K, and when the setting is completed, the control unit compares the historical data set K with a preset historical data set to determine an actual data set R;
the control unit is further provided with preset historical data sets and standard data lengths, wherein the preset historical data sets comprise a first preset historical data set K01, a second preset historical data set K02 and a third preset historical data set K03, and K01 is more than K02 and less than K03; the standard data length comprises a first standard data length L1, a second standard data length L2, a third standard data length L3 and a fourth standard data length L4, wherein L1 < L2 < L3 < L4;
if K < K01, the control unit determines that the data length of the actual data set is L1;
if K01 is not less than K < K02, the control unit judges that the data length of the actual data set is L2;
if K02 is not less than K < K03, the control unit judges that the data length of the actual data set is L3;
if K is larger than or equal to K03, the control unit judges that the data length of the actual data set is L4.
Compared with the prior art, the method has the advantages that when data normalization is carried out on a data set corresponding to a prediction node of a user, whether data are normalized or not is determined by comparing the data capacity of an actual data set with the standard data capacity, the data capacity difference value is compared with the standard data capacity difference value to determine a data compensation parameter and a data capacity adjustment quantity, the adjusted data capacity is determined according to a preset formula, the adjusted data capacity is compared with the standard data capacity to determine whether the data in the data set are normalized or not again, wherein the data capacity of the actual data set is determined according to the actual data length and the data capacity calculation parameter, the data capacity of the data set is further determined according to the data length, the data capacity is further accurately determined according to the data capacity difference data capacity to accurately judge whether the data are normalized or not, and further more accurate prediction results can be obtained under the condition that the data normalization is ensured, the accuracy of the prediction result is effectively improved.
Particularly, whether data are normalized or not is determined by comparing the actual data capacity A with the standard data capacity, the data capacity difference value P is compared with the standard data capacity difference value to determine the data compensation parameter and the data capacity adjustment quantity delta Q, the adjusted data capacity Q 'is determined according to a preset formula, the adjusted data capacity Q' is compared with the standard data capacity to determine whether the data are normalized or not again, the data capacity is accurately determined through the data capacity difference value to accurately judge whether the data are normalized or not, a more accurate prediction result can be obtained under the condition that the data are normalized, and the accuracy of the prediction result is effectively improved.
Particularly, whether data are regular or not is determined by comparing the actual data capacity A with the standard data capacity, and then whether the data are regular or not is accurately determined by accurately determining the data capacity through the data capacity difference value, so that a more accurate prediction result can be obtained under the condition of ensuring that the data are regular, and the accuracy of the prediction result is effectively improved.
Particularly, the data capacity difference value P is compared with the standard data capacity difference value to determine a data compensation parameter, and then the data capacity adjustment quantity delta Q is determined through a preset formula, so that the data capacity can be determined, and then the data capacity is accurately determined through the data capacity difference value to accurately judge whether the data is regular or not, so that a more accurate prediction result can be obtained under the condition that the data is regular, and the accuracy of the prediction result is effectively improved.
Particularly, whether the data are regular or not is determined again by comparing the adjusted data capacity Q' with the standard data capacity, so that the data capacity can be determined, the data capacity is accurately determined through the data capacity difference value to accurately judge whether the data are regular or not, a more accurate prediction result can be obtained under the condition that the data are regular, and the accuracy of the prediction result is effectively improved.
Particularly, the data capacity is accurately determined through the data capacity difference value so as to accurately judge whether the data is regular or not, and further, a more accurate prediction result can be obtained under the condition of ensuring the data to be regular, so that the accuracy of the prediction result is effectively improved.
Particularly, the data capacity A of the actual data set is determined by combining the data capacity calculation parameters and a preset formula, so that the data capacity can be determined according to the data length in the data set, the data capacity is accurately determined by the data capacity difference value to accurately judge whether the data is regular or not, a more accurate prediction result can be obtained under the condition of ensuring the data to be regular, and the accuracy of the prediction result is effectively improved.
Particularly, the historical data set K is compared with the preset historical data set to determine the data length R of the actual data set, so that the data capacity can be determined according to the data length, the data capacity is accurately determined through the data capacity difference value to accurately judge whether the data is regular or not, a more accurate prediction result can be obtained under the condition that the data is regular, and the accuracy of the prediction result is effectively improved.
Drawings
Fig. 1 is a schematic flow chart of an accident prediction method based on data set regularity according to an embodiment of the present invention.
Detailed Description
In order that the objects and advantages of the invention will be more clearly understood, the invention is further described below with reference to examples; it should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only for explaining the technical principle of the present invention, and do not limit the scope of the present invention.
Furthermore, it should be noted that, in the description of the present invention, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations.
Referring to fig. 1, an accident prediction method based on data set regularity according to an embodiment of the present invention includes:
step S100: receiving a user prediction node, collecting a historical data set and an actual data set according to the user prediction node, and carrying out data normalization on the collected actual data set;
step S200: predicting according to the structured data set to obtain a prediction result, and feeding the prediction result back to a user sending a prediction node;
step S300: controlling a data normalization process of an actual data set corresponding to a prediction node of a user;
in step S300, when data normalization is performed on an actual data set corresponding to a prediction node of a user, comparing an actual data set capacity a with a standard data capacity to determine whether data is normalized, comparing a data capacity difference value P with a standard data capacity difference value to determine a data compensation parameter and a data capacity adjustment quantity Δ Q, determining an adjusted data capacity Q 'according to a preset formula, and comparing the adjusted data capacity Q' with the standard data capacity to determine whether data is normalized again;
the actual data set capacity A is determined according to an actual data set R and a data capacity calculation parameter, and the actual data set R is determined according to a historical data set.
Specifically, in the process of predicting the traffic accident, the selection of data in the data set is crucial to determining the prediction accuracy, so the embodiment of the invention controls the data set for predicting the accident so as to realize the completeness of the prediction reference data set and improve the accuracy of the traffic accident prediction. In the actual application process, the actual data set may include a plurality of data, the data in the historical data set may include a plurality of types, such as human data, vehicle data, weather data, and the like, and different data adopt different data structures, and the data lengths of different data during storage are also different, and when the real-time data set is acquired, the acquired real-time data may be complete, may also have a lot of redundant information, and may also have a lot of data missing, so that a certain error exists when the accident prediction is directly performed on the actual data set, so that the accuracy of the accident prediction fluctuates, and therefore, the actual data set needs to be regulated and controlled, the regularity of the actual data set is improved, and the accuracy of the accident prediction is improved.
Specifically, when data normalization is performed on a data set corresponding to a prediction node of a user, the embodiment of the invention compares the data capacity of an actual data set with a standard data capacity to determine whether data is normalized or not, compares a data capacity difference value with a standard data capacity difference value to determine a data compensation parameter and a data capacity adjustment amount, determines the adjusted data capacity according to a preset formula, and compares the adjusted data capacity with the standard data capacity to determine whether data in the data set is normalized again, wherein the data capacity of the actual data set is determined according to an actual data length and a data capacity calculation parameter, and further determines the data capacity of the data set according to the data length, and further precisely determines the data capacity according to the data capacity difference value to accurately judge whether data is normalized or not, so that a more accurate prediction result can be obtained under the condition of ensuring data normalization, the accuracy of the prediction result is effectively improved.
Specifically, when data normalization is performed on an actual data set corresponding to a prediction node of a user, a control unit obtains a data capacity A of the actual data set corresponding to the prediction node, compares the data capacity A of the actual data set with a standard data capacity to determine whether data are normalized or not, when the control unit determines that data are normalized, the control unit transmits the prediction node of the user to a prediction unit to perform prediction to obtain a prediction result, and when the control unit determines that data are not normalized, a data capacity difference value is calculated;
wherein the control unit is provided with standard data capacities including a standard data first capacity Q1 and a standard data second capacity Q2, wherein Q1 < Q2;
if A is less than Q1, the control unit judges that the data is irregular;
if Q1 is not less than A not more than Q2, the control unit judges that the data is structured;
if A > Q2, the control unit determines that the data is irregular.
Specifically, the embodiment of the invention compares the actual data capacity a with the standard data capacity to determine whether the data is regular, compares the data capacity difference P with the standard data capacity difference to determine the data compensation parameter and the data capacity adjustment quantity Δ Q, determines the adjusted data capacity Q 'according to the preset formula, compares the adjusted data capacity Q' with the standard data capacity to determine whether the data is regular again, and then accurately determines the data capacity through the data capacity difference to determine whether the data is regular, so that a more accurate prediction result can be obtained under the condition of ensuring the data is regular, and the accuracy of the prediction result is effectively improved.
Specifically, when the control unit judges that the data is irregular, the control unit calculates a data capacity difference value P, when the calculation is completed, the control unit compares the data capacity difference value P with a standard data capacity difference value to determine a data compensation parameter, and when the control unit determines that the data compensation parameter is σ i, the control unit calculates a data capacity adjustment quantity Δ Q, and sets Δ Q to σ i × P, i to 1, 2, 3, 4;
wherein the control unit is further provided with a standard data capacity difference value and a standard data compensation parameter, the standard data capacity difference value comprises a standard data capacity first difference value P1, a standard data capacity second difference value P2 and a standard data capacity third difference value P3, wherein P1 < P2 < P3; the standard data compensation parameter comprises a first standard data compensation parameter sigma 1, a second standard data compensation parameter sigma 2, a third standard data compensation parameter sigma 3 and a fourth standard data compensation parameter sigma 4, wherein sigma 1+ sigma 2+ sigma 3+ sigma 4 is 1;
if P is less than P1, the control unit judges the data compensation parameter to be sigma 1;
if P1 is not less than P < P2, the control unit judges that the data compensation parameter is sigma 2;
if P2 is not less than P < P3, the control unit judges that the data compensation parameter is sigma 3;
if P is larger than or equal to P3, the control unit judges that the data compensation parameter is sigma 4.
Specifically, the embodiment of the invention compares the actual data capacity A with the standard data capacity to determine whether the data is regular, and then accurately determines the data capacity through the data capacity difference value to accurately judge whether the data is regular, so that a more accurate prediction result can be obtained under the condition of ensuring the data to be regular, and the accuracy of the prediction result is effectively improved.
Specifically, when the control unit determines the data capacity adjustment amount Δ Q, the control unit calculates the adjusted data capacity Q' by the following calculation formula:
Q′＝A±△Q；
where a denotes the data capacity of the actual data set, and Q '═ a +. DELTA.q when a < Q1, and Q' ═ a-. DELTA.q when a > Q2.
Specifically, the data capacity difference value P is compared with the standard data capacity difference value to determine the data compensation parameter, and then the data capacity adjustment quantity Δ Q is determined through a preset formula, so that the data capacity can be determined, and then the data capacity is accurately determined through the data capacity difference value to accurately judge whether the data is regular, so that a more accurate prediction result can be obtained under the condition that the data is regular, and the accuracy of the prediction result is effectively improved.
Specifically, when the control unit determines the adjusted data capacity Q ', the control unit compares the adjusted data capacity Q' with the standard data capacity to determine whether the data is regular again, when the control unit determines that the data is regular, the control unit transmits the prediction node of the user to the prediction unit to perform prediction to obtain a prediction result, and when the control unit determines that the data is irregular, the control unit collects an actual data set corresponding to the prediction node of the user again;
if Q' < Q1, the control unit determines that the data is irregular;
if Q1 is not less than Q' ≦ Q2, the control unit determines that the data is structured;
if Q' > Q2, the control unit determines that the data is irregular.
Specifically, the embodiment of the invention compares the adjusted data capacity Q' with the standard data capacity to determine whether the data is regular again, so that the data capacity can be determined, and then the data capacity is accurately determined through the data capacity difference value to accurately judge whether the data is regular, so that a more accurate prediction result can be obtained under the condition of ensuring the data is regular, and the accuracy of the prediction result is effectively improved.
Specifically, when the control unit determines that the data is irregular, the control unit calculates a data capacity difference value P according to the following calculation formula:
P-Q1-a or P-a-Q2;
where a denotes a data capacity of an actual data set, Q1 denotes a standard data first capacity, Q2 denotes a standard data second capacity, and when a < Q1, P is Q1-a, and when a > Q2, P is a-Q2.
Specifically, the embodiment of the invention accurately determines the data capacity through the data capacity difference value to accurately judge whether the data is regular or not, so that a more accurate prediction result can be obtained under the condition of ensuring the data to be regular, and the accuracy of the prediction result is effectively improved.
Specifically, when data normalization is performed on an actual data set corresponding to a prediction node of a user, the control unit acquires an actual data set R corresponding to the prediction node, and compares the actual data set R with a preset data length to determine a data capacity calculation parameter;
the control unit is provided with preset data length and standard data capacity calculation parameters, wherein the preset data length comprises a first preset data length R1, a second preset data length R2 and a third preset data length R3, and R1 is more than R2 and more than R3; the standard data capacity calculation parameters comprise a standard data capacity first calculation parameter alpha 1, a standard data capacity second calculation parameter alpha 2, a standard data capacity third calculation parameter alpha 3 and a standard data capacity fourth calculation parameter alpha 4, wherein alpha 1+ alpha 2+ alpha 3+ alpha 4 is 1;
if R < R1, the control unit determines that the data capacity calculation parameter is alpha 1;
if R1 is equal to or less than R < R2, the control unit determines that the data capacity calculation parameter is alpha 2;
if R2 is equal to or less than R < R3, the control unit determines that the data capacity calculation parameter is alpha 3;
if R is larger than or equal to R3, the control unit judges that the data capacity calculation parameter is alpha 4.
Specifically, when the control unit determines that the data volume calculation parameter is α i, the control unit calculates the actual data set volume a, and sets a to R × α i, i to 1, 2, 3, 4.
Specifically, the data capacity A of the actual data set is determined by combining the data capacity calculation parameters and the preset formula, so that the data capacity can be determined according to the data length in the data set, the data capacity is accurately determined through the data capacity difference value to accurately judge whether the data is regular or not, a more accurate prediction result can be obtained under the condition that the data is regular, and the accuracy of the prediction result is effectively improved.
Specifically, when data normalization is performed on an actual data set corresponding to a prediction node of a user, the control unit acquires a historical data set corresponding to the prediction node of the user and sets the historical data set to be K, and when the setting is completed, the control unit compares the historical data set K with a preset historical data set to determine an actual data set R;
the control unit is further provided with preset historical data sets and standard data lengths, wherein the preset historical data sets comprise a first preset historical data set K01, a second preset historical data set K02 and a third preset historical data set K03, and K01 is more than K02 and less than K03; the standard data length comprises a first standard data length L1, a second standard data length L2, a third standard data length L3 and a fourth standard data length L4, wherein L1 < L2 < L3 < L4;
if K < K01, the control unit determines that the data length of the actual data set is L1;
if K01 is not less than K < K02, the control unit judges that the data length of the actual data set is L2;
if K02 is not less than K < K03, the control unit judges that the data length of the actual data set is L3;
if K is larger than or equal to K03, the control unit judges that the data length of the actual data set is L4.
Specifically, the historical data set K is compared with the preset historical data set to determine the data length R of the actual data set, so that the data capacity can be determined according to the data length, the data capacity is accurately determined through the data capacity difference value to accurately judge whether the data is regular or not, a more accurate prediction result can be obtained under the condition that the data is regular, and the accuracy of the prediction result is effectively improved.
Specifically, an embodiment of the present invention further provides a traffic accident prediction system based on machine learning, where the system includes:
the receiving unit is used for receiving the user prediction node so as to collect the historical data set and the actual data set according to the user prediction node and carry out data normalization on the collected actual data set;
the prediction unit is used for predicting according to the structured data set to obtain a prediction result and feeding the prediction result back to a user sending a prediction node;
the control unit is used for controlling the data normalization process of the actual data set corresponding to the prediction node of the user;
the control unit is further configured to compare the actual data set capacity a with the standard data capacity to determine whether data is regular when data normalization is performed on an actual data set corresponding to a prediction node of a user, compare the data capacity difference value P with the standard data capacity difference value to determine a data compensation parameter and a data capacity adjustment quantity Δ Q, determine an adjusted data capacity Q 'according to a preset formula, and compare the adjusted data capacity Q' with the standard data capacity to determine whether data is regular again;
the actual data set capacity A is determined according to an actual data set R and a data capacity calculation parameter, and the actual data set R is determined according to a historical data set.
Specifically, the traffic accident prediction system based on machine learning provided by the embodiment of the present invention is configured to execute the accident prediction method based on data set regularity, and can execute the traffic accident prediction method to achieve the same technical effect, which is not described herein again.
So far, the technical solutions of the present invention have been described in connection with the preferred embodiments shown in the drawings, but it is easily understood by those skilled in the art that the scope of the present invention is obviously not limited to these specific embodiments. Equivalent changes or substitutions of related technical features can be made by those skilled in the art without departing from the principle of the invention, and the technical scheme after the changes or substitutions can fall into the protection scope of the invention.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention; various modifications and alterations to this invention will become apparent to those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (9)
1. An accident prediction method based on data set regularity, comprising:
receiving a user prediction node, collecting a historical data set and an actual data set according to the user prediction node, and carrying out data normalization on the collected actual data set;
predicting according to the structured data set to obtain a prediction result, and feeding the prediction result back to a user sending a prediction node;
the control unit controls a data normalization process of an actual data set corresponding to a prediction node of a user;
when data normalization is carried out on an actual data set corresponding to a prediction node of a user, comparing the capacity A of the actual data set with the capacity of standard data to determine whether data are normalized or not, comparing the difference value P of the data capacity with the difference value of the standard data capacity to determine a data compensation parameter and a data capacity adjustment quantity delta Q, determining an adjusted data capacity Q 'according to a preset formula, and comparing the adjusted data capacity Q' with the standard data capacity to determine whether data are normalized or not again;
the actual data set capacity A is determined according to an actual data set R and a data capacity calculation parameter, and the actual data set R is determined according to a historical data set.
2. The data set regularity-based incident prediction method of claim 1,
when data normalization is carried out on an actual data set corresponding to a prediction node of a user, a control unit obtains the data capacity A of the actual data set corresponding to the prediction node, compares the data capacity A of the actual data set with a standard data capacity to determine whether the data is normalized or not, when the control unit determines that the data is normalized, the control unit transmits the prediction node of the user to a prediction unit to carry out prediction to obtain a prediction result, and when the control unit determines that the data is not normalized, a data capacity difference value is calculated;
wherein the control unit is provided with standard data capacities including a standard data first capacity Q1 and a standard data second capacity Q2, wherein Q1 < Q2;
if A is less than Q1, the control unit judges that the data is irregular;
if Q1 is not less than A not more than Q2, the control unit judges that the data is structured;
if A > Q2, the control unit determines that the data is irregular.
3. The data set regularity-based incident prediction method of claim 2,
when the control unit judges that the data is irregular, the control unit calculates a data capacity difference value P, when the calculation is completed, the control unit compares the data capacity difference value P with a standard data capacity difference value to determine a data compensation parameter, when the data compensation parameter is determined to be sigma i, the control unit calculates a data capacity adjustment quantity delta Q, and sets the delta Q to be sigma i multiplied by P, and i to be 1, 2, 3 and 4;
wherein the control unit is further provided with a standard data capacity difference value and a standard data compensation parameter, the standard data capacity difference value comprises a standard data capacity first difference value P1, a standard data capacity second difference value P2 and a standard data capacity third difference value P3, wherein P1 < P2 < P3; the standard data compensation parameter comprises a first standard data compensation parameter sigma 1, a second standard data compensation parameter sigma 2, a third standard data compensation parameter sigma 3 and a fourth standard data compensation parameter sigma 4, wherein sigma 1+ sigma 2+ sigma 3+ sigma 4 is 1;
if P is less than P1, the control unit judges the data compensation parameter to be sigma 1;
if P1 is not less than P < P2, the control unit judges that the data compensation parameter is sigma 2;
if P2 is not less than P < P3, the control unit judges that the data compensation parameter is sigma 3;
if P is larger than or equal to P3, the control unit judges that the data compensation parameter is sigma 4.
4. The data set regularity-based incident prediction method of claim 3,
when the control unit determines the data capacity adjustment quantity delta Q, the control unit calculates the adjusted data capacity Q', and the calculation formula is as follows:
Q′＝A±△Q；
where a denotes the data capacity of the actual data set, and Q '═ a +. DELTA.q when a < Q1, and Q' ═ a-. DELTA.q when a > Q2.
5. The data set regularity-based incident prediction method of claim 4,
when the control unit determines the adjusted data capacity Q ', the control unit compares the adjusted data capacity Q' with the standard data capacity to determine whether the data are regular again, when the control unit determines that the data are regular, the control unit transmits the prediction node of the user to the prediction unit to predict to obtain a prediction result, and when the control unit determines that the data are irregular, the control unit collects an actual data set corresponding to the prediction node of the user again;
if Q' < Q1, the control unit determines that the data is irregular;
if Q1 is not less than Q' ≦ Q2, the control unit determines that the data is structured;
if Q' > Q2, the control unit determines that the data is irregular.
6. The method of claim 5, wherein the accident prediction method based on the regularity of the data set,
when the control unit judges that the data is irregular, the control unit calculates a data capacity difference value P, and the calculation formula is as follows:
P-Q1-a or P-a-Q2;
where a denotes a data capacity of an actual data set, Q1 denotes a standard data first capacity, Q2 denotes a standard data second capacity, and when a < Q1, P is Q1-a, and when a > Q2, P is a-Q2.
7. The data set regularity-based incident prediction method of claim 6,
when data normalization is carried out on an actual data set corresponding to a prediction node based on a user, the control unit acquires an actual data set R corresponding to the prediction node, and compares the actual data set R with a preset data length to determine a data capacity calculation parameter;
the control unit is provided with preset data length and standard data capacity calculation parameters, wherein the preset data length comprises a first preset data length R1, a second preset data length R2 and a third preset data length R3, and R1 is more than R2 and more than R3; the standard data capacity calculation parameters comprise a standard data capacity first calculation parameter alpha 1, a standard data capacity second calculation parameter alpha 2, a standard data capacity third calculation parameter alpha 3 and a standard data capacity fourth calculation parameter alpha 4, wherein alpha 1+ alpha 2+ alpha 3+ alpha 4 is 1;
if R < R1, the control unit determines that the data capacity calculation parameter is alpha 1;
if R1 is equal to or less than R < R2, the control unit determines that the data capacity calculation parameter is alpha 2;
if R2 is equal to or less than R < R3, the control unit determines that the data capacity calculation parameter is alpha 3;
if R is larger than or equal to R3, the control unit judges that the data capacity calculation parameter is alpha 4.
8. The data set regularity-based incident prediction method of claim 7,
when the control unit determines that the data volume calculation parameter is α i, the control unit calculates an actual data set volume a, and sets a to R × α i, i to 1, 2, 3, 4.
9. The data set regularity-based incident prediction method of claim 8,
when data normalization is carried out on an actual data set corresponding to a prediction node of a user, the control unit acquires a historical data set corresponding to the prediction node of the user and sets the historical data set to be K, and when the setting is finished, the control unit compares the historical data set K with a preset historical data set to determine an actual data set R;
the control unit is further provided with preset historical data sets and standard data lengths, wherein the preset historical data sets comprise a first preset historical data set K01, a second preset historical data set K02 and a third preset historical data set K03, and K01 is more than K02 and less than K03; the standard data length comprises a first standard data length L1, a second standard data length L2, a third standard data length L3 and a fourth standard data length L4, wherein L1 < L2 < L3 < L4;
if K < K01, the control unit determines that the data length of the actual data set is L1;
if K01 is not less than K < K02, the control unit judges that the data length of the actual data set is L2;
if K02 is not less than K < K03, the control unit judges that the data length of the actual data set is L3;
if K is larger than or equal to K03, the control unit judges that the data length of the actual data set is L4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110817970.0A CN113610279A (en) | 2021-07-20 | 2021-07-20 | Accident prediction method based on data set regularity |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110817970.0A CN113610279A (en) | 2021-07-20 | 2021-07-20 | Accident prediction method based on data set regularity |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113610279A true CN113610279A (en) | 2021-11-05 |
Family
ID=78337948
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110817970.0A Pending CN113610279A (en) | 2021-07-20 | 2021-07-20 | Accident prediction method based on data set regularity |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113610279A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111179587A (en) * | 2018-11-09 | 2020-05-19 | 丰田自动车北美公司 | Real-time vehicle accident prediction, warning and prevention |
| CN112990612A (en) * | 2021-05-17 | 2021-06-18 | 湖南三湘银行股份有限公司 | Prediction system and method based on federal learning |
| CN112990563A (en) * | 2021-03-05 | 2021-06-18 | 东南大学 | Real-time prediction method for rear-end collision accident risk of expressway |
| KR20210086381A (en) * | 2019-12-30 | 2021-07-08 | 계명대학교 산학협력단 | System and Method for Predicting Traffic Accident Risk |
| CN113760856A (en) * | 2020-06-05 | 2021-12-07 | 京东数字科技控股有限公司 | Database management method and device, computer readable storage medium and electronic device |
-
2021
- 2021-07-20 CN CN202110817970.0A patent/CN113610279A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111179587A (en) * | 2018-11-09 | 2020-05-19 | 丰田自动车北美公司 | Real-time vehicle accident prediction, warning and prevention |
| KR20210086381A (en) * | 2019-12-30 | 2021-07-08 | 계명대학교 산학협력단 | System and Method for Predicting Traffic Accident Risk |
| CN113760856A (en) * | 2020-06-05 | 2021-12-07 | 京东数字科技控股有限公司 | Database management method and device, computer readable storage medium and electronic device |
| CN112990563A (en) * | 2021-03-05 | 2021-06-18 | 东南大学 | Real-time prediction method for rear-end collision accident risk of expressway |
| CN112990612A (en) * | 2021-05-17 | 2021-06-18 | 湖南三湘银行股份有限公司 | Prediction system and method based on federal learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107757525B (en) | Autonomous vehicle fault mode management system and method | |
| EP3266645B1 (en) | Method for operating an electrically driven or electrically drivable vehicle and vehicle | |
| DE102019108607B3 (en) | System and method for determining charging profiles | |
| JP4900133B2 (en) | Travel control plan evaluation device | |
| US8271154B2 (en) | Method for controlling a hybrid drive in a rail vehicle | |
| CN114194207B (en) | Automatic driving method, ADS and automatic driving vehicle | |
| DE102011086903A1 (en) | Electricity demand estimation device for estimating consumption of electrical power during movement of electric car, has estimation portion provided in vehicle to estimate electricity demand for drive of vehicle | |
| JP2009037561A (en) | Traveling plan generation device | |
| CN110364007A (en) | Road conditions management-control method, road furniture, mobile unit based on V2X | |
| DE102011085454A1 (en) | Method for controlling a hybrid drive with an internal combustion engine and an electric motor and an electrical energy store, in particular for a rail vehicle, control device and hybrid drive | |
| EP3323669B1 (en) | Vehicle control unit (vcu) and operating method thereof | |
| EP4055655A1 (en) | Method for predicting an ageing condition of a battery | |
| EP3498525A1 (en) | Control system and method for controlling a rail vehicle | |
| EP3862764B1 (en) | Battery deterioration judging system, battery deterioration judging method, and battery deterioration judging program | |
| JP5083975B2 (en) | Fuel cell vehicle | |
| EP3785978B1 (en) | Vehicle and method for its operation | |
| CN113191588A (en) | Equipment distribution system of distributed driving system | |
| CN112700156A (en) | Construction method of new energy automobile operation safety performance evaluation system | |
| CN113610279A (en) | Accident prediction method based on data set regularity | |
| Pilutti et al. | Fuzzy-logic-based virtual rumble strip for road departure warning systems | |
| KR101934857B1 (en) | Apparatus for monitoring battery status of vehicle | |
| CN117584996A (en) | New energy automobile control method | |
| CN111081014B (en) | Early warning processing system and method for instruction non-compliance rate of automatic driving automobile based on vehicle-road cooperation | |
| CN114093162B (en) | Toll station control method and system under congested road conditions | |
| EP4184270A1 (en) | A device and method for handling a data associated with energy consumption of a vehicle |
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 |