CN115410386B - Short-time speed prediction method and device, computer storage medium and electronic equipment - Google Patents

Short-time speed prediction method and device, computer storage medium and electronic equipment Download PDF

Info

Publication number
CN115410386B
CN115410386B CN202211079066.5A CN202211079066A CN115410386B CN 115410386 B CN115410386 B CN 115410386B CN 202211079066 A CN202211079066 A CN 202211079066A CN 115410386 B CN115410386 B CN 115410386B
Authority
CN
China
Prior art keywords
speed
section
time
real
target
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.)
Active
Application number
CN202211079066.5A
Other languages
Chinese (zh)
Other versions
CN115410386A (en
Inventor
王尔昕
郭庆锋
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.)
Tongdun Technology Co ltd
Original Assignee
Tongdun Technology 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 Tongdun Technology Co ltd filed Critical Tongdun Technology Co ltd
Priority to CN202211079066.5A priority Critical patent/CN115410386B/en
Publication of CN115410386A publication Critical patent/CN115410386A/en
Application granted granted Critical
Publication of CN115410386B publication Critical patent/CN115410386B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/052—Detecting movement of traffic to be counted or controlled with provision for determining speed or overspeed
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0125—Traffic data processing
    • G08G1/0129—Traffic data processing for creating historical data or processing based on historical data

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The disclosure belongs to the technical field of traffic safety, and relates to a short-time speed prediction method and device, a computer storage medium and electronic equipment. The method comprises the following steps: acquiring a section historical speed in a target historical date, and calculating the section historical speed to obtain speed trend data; acquiring a first section real-time speed at the current moment and a second section real-time speed in a target time range corresponding to a short time; and calculating the real-time speed of the first section, the real-time speed of the second section and the speed trend data, and predicting the speed of the passing section in a short time. In the method, on one hand, the short-time speed prediction is predicted according to the section historical data, the first section real-time speed and the second section real-time speed, so that the required data quantity and the consumption of calculation resources are reduced, and the efficiency of the short-time speed prediction is improved; on the other hand, by predicting the speed of the cross section in a short time, the speed change rule of the cross section itself is reflected.

Description

Short-time speed prediction method and device, computer storage medium and electronic equipment
Technical Field
The disclosure relates to the technical field of traffic safety, in particular to a short-time speed prediction method, a short-time speed prediction device, a computer readable storage medium and electronic equipment.
Background
With the development of social economy, the holding amount of domestic private automobiles continues to increase, and speed prediction in short-time traffic becomes particularly important to ensure travel efficiency and travel safety. The speed in short-time traffic is predicted, so that timely traffic conditions, travel time and other information can be provided for the traveler, and the traveler can select a proper travel route; moreover, for traffic managers, speed prediction in short-term traffic can provide scientific and normative data support for decisions so as to take effective traffic management measures in time.
In the prior art, short-time speed prediction is realized by using time sequence, machine learning, deep learning and other technologies. However, when the above-mentioned process is implemented, on one hand, a large amount of history data is used, and the resource consumption of the computer is increased; on the other hand, the model needs to be trained by using historical data, and then prediction is carried out through the trained model, so that the complexity of predicting the short-time speed is increased, and the efficiency of predicting the short-time speed is further reduced.
In view of the foregoing, there is a need in the art to develop a new short-term speed prediction method and apparatus.
It should be noted that the information disclosed in the above background section is only for enhancing understanding of the background of the present disclosure and thus may include information that does not constitute prior art known to those of ordinary skill in the art.
Disclosure of Invention
The present disclosure aims to provide a short-time speed prediction method, a short-time speed prediction apparatus, a computer-readable storage medium, and an electronic device, which further overcome, at least to some extent, the problem of low prediction efficiency due to the related art.
Other features and advantages of the present disclosure will be apparent from the following detailed description, or may be learned in part by the practice of the disclosure.
According to a first aspect of an embodiment of the present invention, there is provided a short-time speed prediction method, the method including: acquiring a section historical speed in a target historical date, and calculating the section historical speed to obtain speed trend data; acquiring a first section real-time speed at the current moment and a second section real-time speed in a target time range corresponding to the short time; and calculating the first section real-time speed, the second section real-time speed and the speed trend data, and predicting the speed of the section passing through in a short time.
In an exemplary embodiment of the present invention, the calculating the first section real-time speed, the second section real-time speed, and the speed trend data predicts a speed of passing through a section in a short time, including: determining the second section real-time speed as a target section real-time speed in a short time, and calculating an average value of the target section real-time speed to obtain a section average speed; calculating the current time and the target time range to obtain target time, and determining a value corresponding to the target time in the speed trend data as real-time speed trend data; calculating the real-time speed trend data and the section average speed to obtain a speed difference value; and predicting the speed of the section passing through in a short time according to the first section real-time speed, the section average speed, the real-time speed trend data and the speed difference value.
In an exemplary embodiment of the present invention, predicting the speed of the passage through the section in a short time based on the first section real-time speed, the section average speed, the real-time speed trend data, and the speed difference value includes: acquiring a congestion speed threshold; if the first section real-time speed is greater than the congestion speed threshold, assigning a sequence number to the target section real-time speed according to the sequence of the time values corresponding to the target section real-time speed; calculating the sequence number and the real-time speed of the target section corresponding to the sequence number to obtain a speed change value; and predicting the speed passing through the section in a short time by combining the real-time speed of the first section, the average speed of the section, the real-time speed trend data and the speed difference value according to the speed change value.
In an exemplary embodiment of the present invention, the predicting the speed of the passing section in a short time according to the speed variation value in combination with the first section real-time speed, the section average speed, the real-time speed trend data, and the speed difference value includes: acquiring a preset speed change threshold; if the speed change value is smaller than the preset speed change threshold value, determining a first calculation relation between the speed difference value and a target weight, and calculating the speed difference value based on the first calculation relation to obtain the target weight; acquiring a preset weight, and if the target weight is greater than the preset weight, changing the target weight into the preset weight; and determining a second calculation relation among the average speed of the section, the target weight, the real-time speed trend data and the predicted speed, and calculating the target weight, the average speed of the section and the real-time speed trend data based on the second calculation relation to predict the speed of the section passing through in a short time.
In an exemplary embodiment of the invention, the method further comprises: if the speed change value is greater than or equal to the preset speed change threshold, determining a third calculation relation between the speed difference value and the target weight, and calculating the speed difference value based on the third calculation relation to obtain the target weight; determining a fourth calculation relation among the target weight, the first section real-time speed, the real-time speed trend data and the predicted speed, calculating the target weight, the first section real-time speed and the real-time speed trend data based on the fourth calculation relation, and predicting the speed of the section passing through in a short time.
In an exemplary embodiment of the invention, the method further comprises: if the real-time speed of the first section is smaller than or equal to the congestion speed threshold value, a preset time range is obtained; and determining the real-time speed of the section to be calculated, which belongs to the preset time range, from the target real-time speed of the section, calculating the real-time speed of the section to be calculated, and predicting the speed of the section passing through in a short time.
In an exemplary embodiment of the present invention, the calculating the historical speed of the section to obtain speed trend data includes: acquiring a preset sampling interval, and sampling the section historical speed of each day in the target historical date according to the preset sampling interval to obtain the section historical speed of different times of each day; if the section historical speeds at different daily moments are not missing, recording the section historical speeds at different daily moments until the date corresponding to the recorded section historical speeds at different daily moments meets the preset day condition; and calculating the historical speeds of the sections at different daily moments to obtain speed trend data.
In an exemplary embodiment of the present invention, the calculating the historical speed of the section at different times of day to obtain speed trend data includes: constructing a section history speed matrix based on the section history speeds at different times of day; singular value decomposition is carried out on the section historical speed matrix to obtain a diagonal matrix, a left singular value matrix and a right singular value matrix; changing the singular value of the diagonal matrix to obtain the changed diagonal matrix; calculating the changed diagonal matrix, the left singular value matrix and the right singular value matrix to obtain a target section historical speed matrix; and carrying out average value calculation on each column of element values in the target section historical speed matrix to obtain speed trend data at different moments.
In an exemplary embodiment of the present invention, the changing the singular value of the diagonal matrix to obtain the changed diagonal matrix includes: acquiring all singular values corresponding to the diagonal matrix, and comparing the magnitudes of all the singular values to obtain a magnitude comparison result; acquiring a preset number, and determining the preset number of target singular values and other singular values from the singular values based on the size comparison result; the preset number of the target singular values and the other singular values form all singular values; obtaining a preset value, maintaining the preset number of the target singular values in the diagonal matrix unchanged, and replacing the other singular values with the preset value to obtain the changed diagonal matrix.
According to a second aspect of the embodiments of the present invention, there is provided a short-time speed prediction apparatus, the apparatus including: the calculation module is configured to acquire the section historical speed in the target historical date and calculate the section historical speed to obtain speed trend data; the acquisition module is configured to acquire the first section real-time speed at the current moment and the second section real-time speed in a target time range corresponding to the short time; and the prediction module is configured to calculate the first section real-time speed, the second section real-time speed and the speed trend data and predict the speed of the section passing through in a short time.
According to a third aspect of an embodiment of the present invention, there is provided an electronic apparatus including: a processor and a memory; wherein the memory has stored thereon computer readable instructions which, when executed by the processor, implement the short-time speed prediction method of any of the above-described exemplary embodiments.
According to a fourth aspect of embodiments of the present invention, there is provided a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the short-time speed prediction method in any of the above-described exemplary embodiments.
As can be seen from the above technical solutions, the short-time speed prediction method, the short-time speed prediction device, the computer storage medium, and the electronic device according to the exemplary embodiments of the present invention have at least the following advantages and positive effects:
in the method and the device provided by the exemplary embodiment of the disclosure, on one hand, the short-time speed prediction is predicted according to the section historical speed, the first section real-time speed and the second section real-time speed, so that the required data volume and the consumption of calculation resources are reduced, and the efficiency of the short-time speed prediction is improved; on the other hand, the speed trend of the section is calculated by predicting the speed of the section in a short time, so that the speed change rule of the section is effectively reflected.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description, serve to explain the principles of the disclosure. It will be apparent to those of ordinary skill in the art that the drawings in the following description are merely examples of the disclosure and that other drawings may be derived from them without undue effort.
FIG. 1 schematically illustrates a flow diagram of a short-time speed prediction method in an embodiment of the present disclosure;
FIG. 2 schematically illustrates a flow chart of calculating a historical speed of a section to obtain speed trend data in a short-time speed prediction method in an embodiment of the disclosure;
FIG. 3 is a schematic flow chart of calculating a historical speed of a section to obtain speed trend data according to another short-time speed prediction method in an embodiment of the disclosure;
fig. 4 schematically illustrates a flow chart of changing singular values corresponding to a diagonal matrix in a short-time speed prediction method in an embodiment of the disclosure, to obtain a changed diagonal matrix;
FIG. 5 schematically illustrates a first flow chart of predicting velocity through a section in a short time velocity prediction method in an embodiment of the present disclosure;
FIG. 6 schematically illustrates a second flow chart of a short time velocity prediction method for predicting velocity through a section in a short time in an embodiment of the present disclosure;
FIG. 7 schematically illustrates a third flow chart of a short time velocity prediction method for predicting velocity through a fracture in a short time in an embodiment of the present disclosure;
FIG. 8 schematically illustrates a fourth flowchart of predicting a velocity through a section in a short time velocity prediction method in an embodiment of the present disclosure;
FIG. 9 schematically illustrates a fifth flow chart of predicting velocity through a section in a short time velocity prediction method in an embodiment of the present disclosure;
FIG. 10 schematically illustrates a flow diagram of a short-time speed prediction method in an application scenario;
fig. 11 schematically illustrates a structural diagram of a short-time speed prediction apparatus in an embodiment of the present disclosure;
FIG. 12 schematically illustrates an electronic device for a short-time speed prediction method in an embodiment of the disclosure;
fig. 13 schematically illustrates a computer-readable storage medium for a short-time speed prediction method in an embodiment of the present disclosure.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. However, the exemplary embodiments may be embodied in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the present disclosure. One skilled in the relevant art will recognize, however, that the aspects of the disclosure may be practiced without one or more of the specific details, or with other methods, components, devices, steps, etc. In other instances, well-known technical solutions have not been shown or described in detail to avoid obscuring aspects of the present disclosure.
The terms "a," "an," "the," and "said" are used in this specification to denote the presence of one or more elements/components/etc.; the terms "comprising" and "having" are intended to be inclusive and mean that there may be additional elements/components/etc. in addition to the listed elements/components/etc.; the terms "first" and "second" and the like are used merely as labels, and are not intended to limit the number of their objects.
Furthermore, the drawings are merely schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus a repetitive description thereof will be omitted. Some of the block diagrams shown in the figures are functional entities and do not necessarily correspond to physically or logically separate entities.
Aiming at the problems in the related art, the disclosure provides a short-time speed prediction method. Fig. 1 shows a schematic flow chart of a short-time speed prediction method, and as shown in fig. 1, the short-time speed prediction method at least comprises the following steps:
s110, acquiring the section historical speed in the target historical date, and calculating the section historical speed to obtain speed trend data.
And S120, acquiring the real-time speed of the first section at the current moment and the real-time speed of the second section in a short time.
And S130, calculating the real-time speed of the first section, the real-time speed of the second section and the speed trend data, and predicting the speed of the section passing through in a short time.
In the method and the device provided by the exemplary embodiment of the disclosure, on one hand, the short-time speed prediction is predicted according to the section historical speed, the first section real-time speed and the second section real-time speed, so that the required data volume and the consumption of calculation resources are reduced, and the efficiency of the short-time speed prediction is improved; on the other hand, the speed trend of the section is calculated by predicting the speed of the section in a short time, so that the speed change rule of the section is effectively reflected.
The following describes each step of the short-time speed prediction method in detail.
In step S110, a section history speed within the target history date is obtained, and speed trend data is calculated from the section history speed.
In the exemplary embodiment of the present disclosure, the target history date refers to a preset history date, and specifically, the target history date may be a date corresponding to 30 days before the current date, a date corresponding to 20 days before the current date, or a date corresponding to 25 days before the current date, which is not particularly limited in this exemplary embodiment.
ETC (Electronic Tool Collection electronic toll collection) portals are arranged on the expressway at intervals, and on the basis of the ETC portals, the expressway is divided into a plurality of sections by adjacent ETC portals. The section history speed refers to the speed at which the vehicle passes through a section. The speed trend data describes the change rule of the historical speed of the section in one period (in days).
The section history speed may be specifically obtained by calculating ETC, or may be obtained by a test device (such as a speed camera, millimeter wave radar, laser radar), which is not particularly limited in this exemplary embodiment.
For example, the current date is D, and the section history speed of 30 days before the current date is obtained, namely, the section history speed of D-30 days to D-1 days is obtained.
It is worth noting that the profile history speed may be sampled at 5 minute sampling intervals for one date. If there is no missing data sampled on the one date, 288 section history speeds should be sampled, and 288 section history speeds corresponding to the date should be stored. If there is a missing data in the data sampled on this date, the section history speed on this date is not stored.
When the section history speed of 14 days is stored, the section history speed of 14 days can be calculated to obtain speed trend data. The stored section history speeds of 14 days may include 288 section history speeds corresponding to D-1 day, D-2 day, D-3 day, D-4 day, D-5 day, D-6 day, D-7 day, D-8 day, D-9 day, D-10 day, D-11 day, D-12 day, D-13 day, and D-14 day, respectively.
In an alternative embodiment, fig. 2 shows a schematic flow chart of calculating the historical speed of the section to obtain the speed trend data in a short-time speed prediction method, and as shown in fig. 2, the method at least includes the following steps:
in step S210, a preset sampling interval is obtained, and the daily section history speed in the target history date is sampled according to the preset sampling interval, so as to obtain the daily section history speeds at different times.
The preset sampling interval refers to an interval of sampling the section history speed, specifically, the preset sampling interval may be 5 minutes, may be 8 minutes, may be 3 minutes, and the present exemplary embodiment is not particularly limited thereto.
For example, assume that the section history speed within the target history date includes a section history speed of D-30 to D-1, where D refers to the date of the predicted day. Based on this, the daily section history speed in D-30 to D-1 days can be sampled at preset sampling intervals of 5 minutes, and then the following values of 00 can be obtained in order: 00. 00: 05. 00: 10. 00: 15. ... 23:55, and 288 cross section historic speeds corresponding to the same time.
In step S220, if there is no loss of the section history speed at different times of day, the section history speed at different times of day is recorded until the date corresponding to the recorded section history speed at different times of day meets the preset day condition.
For each day, for example, for D-1, if the section history speed at different times of D-1 is not lost, the section history speed at different times of D-1 is recorded. Then, the judgment is carried out for D-2 days, and if the section history speed at different times of D-2 days is not missing, the section history speed at different times of D-2 days is recorded. Until the date of the recorded section history speed meets the preset day condition. The preset number of days condition is determined based on the target history date, for example, 30 days before the current date, and the preset number of days condition may be a date of 14 days corresponding to the section history speed recorded, a date of 15 days corresponding to the section history speed recorded, and the present exemplary embodiment is not particularly limited thereto.
It should be noted that, the preset day condition is to limit the number of the section history speeds which are not missing in the target history date, and further to calculate the speed trend data by using a smaller number of data, so if the section history speed 30 days before the current date is obtained, since the section history speed which is complete for 14 days is usually present in the section history speed 30 days before the current date, the preset day condition is set as the date in which the date corresponding to the section history speed is 14 days.
For example, if the cross-sectional history speed at different times in D-1 is not lost, the cross-sectional history speed at different times in D-1 is recorded, the cross-sectional history speeds at different times in D-2, D-3, and D-13 are all not lost, the cross-sectional history speeds at different times in D-2, D-3, and D-13 are recorded, the cross-sectional history speed at different times in D-14 is not recorded, the cross-sectional history speed at different times in D-14, the cross-sectional history speed at different times in D-15 is recorded, and obviously, the date corresponding to the cross-sectional history speed at this time is 14 days, therefore, the preset day condition is satisfied, and based on this, the cross-sectional history speed at the subsequent date is no longer recorded.
In step S230, the historical speeds of the sections at different times of day are calculated to obtain speed trend data.
The speed trend data can be obtained by calculating the historical speeds of the sections at different times of day.
For example, the velocity trend data can be obtained by calculating the section history velocities at different times of 14 days based on the section history velocities at different times of D-1 to D-13 and D-15 obtained at this time.
In the present exemplary embodiment, when the historical speeds of the sections at different times of day are not missing, the historical speeds of the sections at different times are recorded, so that the situation that the speed trend data is calculated incorrectly due to the missing historical speeds of the sections is avoided, and the accuracy of the speed trend data calculation is improved.
In an alternative embodiment, fig. 3 shows another flow chart of calculating the historical speed of the section to obtain the speed trend data in the short-time speed prediction method, and as shown in fig. 3, the method at least includes the following steps:
in step S310, a cross-section history speed matrix is constructed based on the cross-section history speeds at different times of day.
Wherein, the section history speed matrix refers to a matrix formed by section history speeds at different moments every day.
For example, the historical speeds of the sections at different times of day include the historical speeds of the sections at different times of day D-1 to D-13 and D-15. Wherein, the different moments refer to 00: 00. 00: 05. 00: 10. 00: 15. ... 23:55 at 288 times, based on which there are 288 profile histories for each day.
Based on this, a 14-row, 288-column section history speed matrix can be obtained, wherein each row in the section history speed matrix represents the section history speed at different times of day, and each column represents the section history speed at the same time within the 14 days.
In step S320, singular value decomposition is performed on the cross-section historical speed matrix to obtain a diagonal matrix, a left singular value matrix, and a right singular value matrix.
Wherein the singular value decomposition belongs to a matrix decomposition in linear algebra. Assuming that A is an m×n order matrix and that A is r, there is a unitary matrix U, V such that∑＝diag(v 1 ，v 2 ，......，v r ) As a diagonal matrix, v i (i=1, 2,) r) is the singular value of a, and v 1 ≥v 2 ≥……≥v r And the numerical values are equal to or larger than 0,U, and V is a left singular value matrix and a right singular value matrix of A respectively.
Based on this, for example, singular value decomposition of the cross-section history velocity matrix is to make the cross-section history velocity matrix be matrix a, usingAnd calculating to obtain a diagonal matrix sigma, a left singular value matrix U and a right singular value matrix V.
In step S330, the singular values of the diagonal matrix are changed to obtain a changed diagonal matrix.
Wherein the singular values of the diagonal matrix, v 1 ，v 2 ，......，v r The singular value is changed to obtain a changed singular value matrix Sigma'.
For example, v in the diagonal matrix Σ will be r When the value becomes 0, a changed singular value matrix Σ', is obtained at this time.
In step S340, the changed diagonal matrix, left singular value matrix, and right singular value matrix are calculated to obtain a target section historical speed matrix.
After the changed diagonal matrix is obtained, the changed diagonal matrix, the left singular value matrix and the right singular value matrix can be calculated to obtain a target section historical speed matrix M'.
For example, in the case of a glass,wherein Σ is ’ And U is a left singular value matrix, V is a right singular value matrix and M' is a target section historical speed matrix.
In step S350, an average value is calculated for each column of element values in the target section history speed matrix to obtain speed trend data at different moments.
And calculating the average value of the element values of each column in the target section historical speed matrix to finally obtain a matrix, wherein the elements in the row matrix are speed trend data at different moments.
For example, the target section history speed matrix obtained through the above process is still a matrix of 14×288, based on which, the average value of 14 elements in each column of the target section history speed matrix is calculated, so as to obtain a matrix of 1×288, where 288 elements in the matrix are respectively equal to 00: 00. 00: 05. 00: 10. 00: 15. ... 23:55, and 288 corresponding speed trend data at different times.
In the present exemplary embodiment, singular value decomposition is performed on the section history velocity matrix, which is conducive to obtaining a diagonal matrix representing velocity trend characteristics, thereby laying a foundation for obtaining accurate velocity trend data later.
In an alternative embodiment, fig. 4 shows a schematic flow chart of changing singular values of a diagonal matrix in a short-time velocity prediction method to obtain a changed diagonal matrix, and as shown in fig. 4, the method at least includes the following steps:
in step S410, all singular values of the diagonal matrix are acquired, and the magnitudes of all singular values are compared to obtain a magnitude comparison result.
Wherein singular values refer to values of elements on diagonals in a diagonal matrix, i.e. v 1 ，v 2 ，......，v r R is the rank of the section history speed matrix.
After the singular values are obtained, the magnitude of the singular values need to be compared so as to obtain a magnitude comparison result.
For example, the resulting diagonal matrix Σ=diag (v 1 ，v 2 ，......，v r ) Is v 1 ，v 2 ，......，v r R is the rank of the section history speed matrix. Since, in the diagonal matrix, v 1 ≥v 2 ≥……≥v r 0, therefore, the comparison result is v 1 Greater than or equal to v 2 ，v 2 Greater than or equal to v 3 ，......，v r-1 Greater than or equal to v r 。
In step S420, a preset number is obtained, and based on the size comparison result, a preset number of target singular values and other singular values are determined from the singular values; the preset number of target singular values and other singular values constitute all singular values.
The preset number refers to the number of preset singular values which do not need to be changed.
Assuming that the preset number is 3, the largest 3 singular values among the singular values are determined as target singular values based on the magnitude comparison result, and the singular values other than the largest 3 singular values among the singular values are determined as other singular values.
For example, if the preset number is 3, then v is 1 ，v 2 ，......，v r The maximum 3 singular values are determined as target odd valuesDifferent values, i.e. v 1 ，v 2 V 3 For the target singular value, v 4 ，v 5 ，......，v r Other singular values.
In step S430, a preset value is obtained, a preset number of target singular values in the diagonal matrix are maintained unchanged, and other singular values are replaced with the preset value, so as to obtain a changed diagonal matrix.
The preset value refers to a preset value, which is used to replace other singular values.
For example, the preset value is 0, maintaining the target singular value v in the diagonal matrix Σ 1 ，v 2 V 3 Unchanged, other singular values v 4 ，v 5 ，......，v r And replaced by 0, and the changed diagonal matrix is obtained.
In the present exemplary embodiment, based on the size comparison result, a preset number of target singular values and other singular values are determined from the singular values, the target singular values are maintained unchanged, and the other singular values are replaced with the preset values, so as to obtain a changed diagonal matrix. Because the target singular value is a larger preset number of singular values, the changed diagonal matrix keeps a plurality of characteristic values (namely the target singular value) with larger influence on the speed trend data, and the accuracy of the speed trend data calculated later is greatly improved.
In step S120, a first section real-time speed at the current time and a second section real-time speed within a target time range corresponding to a short time are obtained.
In an exemplary embodiment of the present disclosure, the current time refers to a current time, and the first section real-time speed refers to a section real-time speed acquired at the current time.
Short-term speed prediction, i.e. speed prediction within a short time, typically refers to a time range between 5 minutes and 30 minutes, which may be 15 minutes, for example. Further, the target time range corresponding to the short time may be a time range of 15 minutes. The second section real-time speed refers to the section real-time speed within 15 minutes with the current time as a reference.
For example, assuming that the current time is T, the first section real-time speed refers to a first section real-time speed corresponding to the current time T. The target time range corresponding to the short time is 15 minutes, and the second section real-time speed refers to 15 section real-time speeds from the time of T-14 to the time of T.
In the present exemplary embodiment, the first section real-time speed and the second section real-time speed are obtained, which is helpful for predicting the speed of the section passing through in a short time according to the speed trend data, the first section real-time speed and the second section real-time speed.
In step S130, the first section real-time speed, the second section real-time speed, and the speed trend data are calculated, and the speed of the passing section in a short time is predicted.
In an exemplary embodiment of the present disclosure, the predicted speed of the pass through the section in a short time is calculated by calculating the first section real-time speed, the second section real-time speed, and the speed trend data.
For example, the first section real-time speed is S1, the second section real-time speed specifically includes 15 section real-time speeds at time, and the speed trend data is R, and at this time, according to the first section real-time speed S1, the second section real-time speed, and the speed trend data R, the speed of the section that can pass through in 15 minutes in the future can be predicted.
In an alternative embodiment, fig. 5 shows a first flow chart of predicting the velocity through a section in a short time velocity prediction method, and as shown in fig. 5, the method at least includes the following steps:
in step S510, the second section real-time speed is determined as the target section real-time speed in a short time, and the average value of the target section real-time speed is calculated to obtain the section average speed.
Wherein, since the second section real-time speed is the section real-time speed in a short time, the second section real-time speed can be determined as the target section real-time speed in a short time.
For example, the second section real-time speed is a section real-time speed within the current time T to T-14, and thus, the above 15 section real-time speeds can be determined as target section real-time speeds within a short time (for example, 15 minutes).
And carrying out average calculation on the 15 section real-time speeds to obtain the section average speed speed_mean.
In step S520, the target time is calculated from the current time and the target time range, and the value corresponding to the target time in the speed trend data is determined as the real-time speed trend data.
The target time refers to a calculation result of the current time and the target time range, and specifically may be a result of adding the current time and the target time range.
After the target time is determined, real-time speed trend data corresponding to the target time can be determined from the speed trend data.
For example, the current time is T, the target time range is 15 minutes, and thus the target time is t+15 minutes. And determining the speed trend data corresponding to the time of T+15 minutes from the speed trend data to be the real-time speed trend data speed_trend.
It should be noted that, if the preset sampling interval is 5 minutes, 288 data are recorded in the real-time speed trend data, and the 288 data are respectively equal to 00: 00. 00: 05. 00: 10. 00: 15. ... 23:55 corresponds to 288 times in total. If the target time is 00:19, due to 0:19 is between 00:15 and 00:20 and distance 00:20, thus, will be closer to 00:20 is determined to correspond to a speed trend data of 00:19, corresponding to real-time speed trend data.
In step S530, the real-time velocity trend data and the section average velocity are calculated to obtain a velocity difference.
The real-time speed trend data refer to real-time speed trend data corresponding to the target moment, and the section average speed refers to an average value of the real-time speed of the target section, so that a speed difference speed_diff can be obtained by performing difference calculation on the real-time speed trend data and the section average speed.
For example, the speed difference speed_diff=speed_trend_speed_mean, where speed_trend is the real-time speed trend data and speed_mean is the section average speed.
In step S540, the speed of the first section passing through the section in a short time is predicted according to the first section real-time speed, the section average speed, the real-time speed trend data and the speed difference.
After the first section real-time speed, the section average speed, the real-time speed trend data and the speed difference value are obtained, the first section real-time speed, the section average speed, the real-time speed trend data and the speed difference value can be calculated, and then the speed of the section passing through in a short time can be predicted.
For example, according to the first section real-time speed speed_last, the section average speed speed_mean, the real-time speed trend data speed_trend, and the speed difference speed_diff, the speed that can pass through the section for 15 minutes in future can be predicted.
In the present exemplary embodiment, the first section real-time speed, the section average speed, the real-time speed trend data, and the speed difference are obtained, which provides data support for predicting the speed of the passing section in a short time later.
In an alternative embodiment, fig. 6 shows a second flow chart of a short-time velocity prediction method for predicting velocity through a section in a short time, and as shown in fig. 6, the method at least includes the following steps:
in step S610, a congestion speed threshold is acquired.
The congestion speed threshold refers to a critical value for measuring whether the road is congested at the moment.
For example, a congestion speed threshold SG is acquired.
In step S620, if the first section real-time speed is greater than the congestion speed threshold, a sequence number is assigned to the target section real-time speed according to the sequence of the time values corresponding to the target section real-time speed.
If the real-time speed of the first section is greater than the congestion speed threshold, it is proved that congestion is likely to occur at the moment. The sequence number refers to a value allocated to the real-time speed of the target section, and the value is allocated according to the sequence of the time values corresponding to the real-time speed of the target section.
For example, the target real-time speed of the section may specifically include real-time speeds of the section at 15 times, and specifically, the 15 real-time speeds of the section respectively correspond to 15 times from time T-14 to time T, where T refers to the current time.
Based on this, the time of T-14 is the first time, and further, the serial number 1 is allocated to the section real-time speed1 corresponding to the time of T-14, and similarly, the serial number 2 is allocated to the section real-time speed2 corresponding to the time of T-13 until the serial number 15 is allocated to the section real-time speed15 corresponding to the time of T.
In step S630, the velocity change value is calculated from the sequence number and the real-time velocity of the target section corresponding to the sequence number.
The speed change value is used for measuring the change value of the real-time speed of the target section in the target time range. Specifically, the speed change value is obtained by calculating the sequence number and the real-time speed of the target section corresponding to the sequence number.
For example, the speed variation k may be obtained by calculating the sequence number and the real-time speed of the target section corresponding to the sequence number by using the formula (1).
Wherein k is a speed variation value, x i Indicating the number, y i The real-time speed of the target section corresponding to the serial number is represented, n can be 15 in particular,the average of the numbers is shown.
In step S640, according to the speed variation value, the speed of the first section passing through the section in a short time is predicted by combining the real-time speed of the first section, the average speed of the section, the real-time speed trend data and the speed difference.
On the basis of the speed change value, the speed passing through the section in a short time can be predicted by combining the real-time speed of the first section, the average speed of the section, the real-time speed trend data and the speed difference value.
For example, according to the speed variation k, the speed of the section passing for 15 minutes in the future can be predicted by combining the first section real-time speed speed_last, the section average speed speed_mean, the real-time speed trend data speed_trend and the speed difference value speed_diff.
In this exemplary embodiment, the speed change value is obtained by calculating the real-time speed of the target section according to the sequence number and the sequence number, so that the situation that the real-time speed of the first section is greater than the congestion speed threshold value can be continuously subdivided according to the speed change value, and further accurate prediction of the speed of the passing section in a short time under different conditions can be realized.
In an alternative embodiment, fig. 7 shows a third flow chart of predicting the velocity through the fracture in a short time velocity prediction method, and as shown in fig. 7, the method at least includes the following steps:
in step S710, a preset speed change threshold is acquired.
The preset speed change threshold value refers to a critical value for measuring a speed change value.
For example, the predetermined speed variation threshold may be 0.75.
In step S720, if the speed variation value is smaller than the preset speed variation threshold, a first calculation relationship between the speed difference value and the target weight is determined, and the speed difference value is calculated based on the first calculation relationship to obtain the target weight.
When the speed change value is smaller than the preset speed change threshold value, the speed is proved to be in stable change. Further, a first calculation relation of the calculation target weight is determined.
The target weight determines the influence degree of the average value of the section and the real-time speed trend data on the prediction result in the process of predicting the speed of the section in a short time.
For example, the first calculation relationship is shown in formula (2).
p＝abs(speed_diff)/20 (2)
Where p is the target weight and speed_diff is the speed difference.
In step S730, a preset weight is obtained, and if the target weight is greater than the preset weight, the target weight is changed to the preset weight.
The preset weight refers to a critical value of the weight, if the target weight is greater than the preset weight, it is proved that the value of the target weight exceeds the critical value at the moment, and therefore the value of the target weight is changed into the preset weight.
For example, the preset weight is 0.9. If the target weight p is 0.95, the target weight p is larger than the preset weight, and the value of the target weight p is changed from 0.95 to 0.9.
In step S740, a second calculation relationship among the average speed of the cross section, the target weight, the real-time speed trend data and the predicted speed is determined, and the target weight, the average speed of the cross section and the real-time speed trend data are calculated based on the second calculation relationship, so that the speed of the cross section passing through in a short time is predicted.
The second calculation relation refers to calculation relation among the average speed of the section, the target weight, the real-time speed trend data and the predicted speed, and the predicted speed is the speed of the predicted section passing in a short time.
For example, the second calculation relationship is shown in formula (3).
pred_speed＝p×speed_mean+(1-p)×speed_trend (3)
Where p is the target weight, pred_speed is the predicted speed of the section in a short time, speed_last is the average speed of the section, and speed_trend is the real-time speed trend data.
In the present exemplary embodiment, when the speed change value is smaller than the preset speed change threshold, the speed of the passing section in a short time may be predicted based on the second calculation relationship, so that short-time speed prediction under the conditions that congestion may be caused and the speed change is relatively stable is realized.
In an alternative embodiment, fig. 8 shows a fourth flowchart of a fourth method for predicting a velocity through a section in a short time according to the short-time velocity prediction method, where the method at least includes the following steps:
In step S810, if the speed variation value is greater than or equal to the preset speed variation threshold, a third calculation relationship between the speed difference value and the target weight is determined, and the speed difference value is calculated based on the third calculation relationship to obtain the target weight.
When the speed change value is larger than or equal to a preset speed change threshold value, the speed change is proved to be urgent. In this case, the target weight needs to be calculated based on the third calculation relationship.
For example, the third calculation relationship is shown in formula (4).
p＝abs(speed_diff)/40 (4)
Where p is the target weight and speed_diff is the speed difference.
In step S820, a fourth calculation relationship among the target weight, the first section real-time speed, the real-time speed trend data and the predicted speed is determined, and the target weight, the first section real-time speed and the real-time speed trend data are calculated based on the fourth calculation relationship, so as to predict the speed of the section passing through in a short time.
After determining the target weight, the speed of the cross section passing through in a short time can be predicted based on the fourth calculation relation. The fourth calculation relation refers to a calculation relation among the target weight, the first section real-time speed, the real-time speed trend data and the predicted speed.
For example, the fourth calculation relationship is shown in formula (5).
pred_speed＝p×speed_last+(1-p)×speed_trend (5)
Wherein pr d_speed is the predicted speed of the section passing in a short time, p is the target weight, speed_last is the real-time speed of the first section, and speed_trend is the real-time speed trend data.
In the present exemplary embodiment, when the speed change value is greater than or equal to the preset speed change threshold, the speed of the passing section in a short time may be predicted based on the fourth calculation relationship, so that short-time speed prediction in a case where congestion may be caused and speed change is relatively urgent is achieved.
In an alternative embodiment, fig. 9 shows a fifth flowchart of a short-time speed prediction method for predicting a speed of a passing section in a short time, and as shown in fig. 9, the method at least includes the following steps:
in step S910, if the real-time speed of the first section is less than or equal to the congestion speed threshold, a preset time range is obtained.
And when the real-time speed of the first section is smaller than or equal to the congestion speed threshold value, proving that no congestion occurs at the moment. In this case, a preset time range needs to be acquired. The preset time range refers to a time range from the current time, and the span of the time range is generally within 10 minutes, specifically, the preset time range may be the last 5 minutes from the current time, the last 4 minutes from the current time, or the last 6 minutes from the current time, which is not particularly limited in this exemplary embodiment.
For example, if the real-time speed of the first section is less than or equal to the congestion speed threshold, the preset time range is obtained as 5 minutes nearest to the current time.
In step S920, the real-time speed of the section to be calculated, which belongs to the preset time range, is determined from the target real-time speed of the section, and the real-time speed of the section to be calculated is calculated to predict the speed of the section passing through in a short time.
The section real-time speed to be calculated refers to the section real-time speed corresponding to a preset time range in the target section real-time speed. After the real-time speed of the section to be calculated is determined, the real-time speed of the section to be calculated can be calculated so as to predict the speed of the section passing through in a short time.
For example, the preset time range is 5 minutes nearest to the current time, and assuming that the current time is T, the preset time range is a time range from the time T-4 to the time T.
Based on the above, the section real-time speed to be calculated 15 corresponding to the time T is obtained in the target section real-time speed, the section real-time speed to be calculated 14 corresponding to the time T-1 is obtained in the target section real-time speed, the section real-time speed to be calculated 13 corresponding to the time T-2 is obtained in the target section real-time speed, and the section real-time speed to be calculated 11 corresponding to the time T-4 is obtained in the target section real-time speed.
Based on the above, the average value calculation is performed on the obtained 5 section real-time speeds speed15, speed14, speed13, speed12 and speed11 to be calculated so as to predict the speed of the section passing through in the future 15 minutes.
In this exemplary embodiment, when the first section real-time speed is less than or equal to the congestion speed threshold, the section real-time speed to be calculated is determined, and the section real-time speed to be calculated is calculated, so as to predict the speed of the section passing through in a short time, and short-time speed prediction without congestion is realized.
In the method and the device provided by the exemplary embodiment of the disclosure, on one hand, the short-time speed prediction is predicted according to the section historical speed, the first section real-time speed and the second section real-time speed, so that the required data volume and the consumption of calculation resources are reduced, and the efficiency of the short-time speed prediction is improved; on the other hand, the speed trend of the section is calculated by predicting the speed of the section in a short time, so that the speed change rule of the section is effectively reflected.
The short-time speed prediction method in the embodiment of the present disclosure is described in detail below in connection with an application scenario.
For highway traffic management personnel, it is necessary to obtain a short time speed of each section in the highway within 15 minutes in the future, so as to effectively manage vehicles on the highway. Fig. 10 schematically illustrates a flow chart of a short-time speed prediction method in an application scenario, as shown in fig. 10, where step S1010 is to obtain a section real-time speed, and the section real-time speed includes a first section real-time speed and a second section real-time speed, and step S1020 is to obtain a section history speed.
Step S1030 is to determine whether the current speed (i.e. the first section real-time speed) is less than or equal to the congestion speed threshold, if the current speed is less than or equal to the congestion speed threshold, step S1031 is executed, and if the current speed is greater than the congestion speed threshold, step S1032 is executed.
In step S1031, the speed of passing through the section within 15 minutes in the future is predicted from the real-time speed of the section. Specifically, the real-time speed of the section to be calculated, which belongs to a preset time range, is determined from the target real-time speed of the section, and the real-time speed of the section to be calculated is calculated to predict the speed of the section passing through within 15 minutes in the future.
In step S1032, the speed of the section passing through in 15 minutes is predicted according to the real-time speed and the speed trend data of the section. Specifically, whether the speed change value is smaller than a preset speed change threshold value is judged, if the speed change value is smaller than the preset speed change threshold value, a target weight is obtained according to a first calculation relation, and then the speed of a passing section within 15 minutes in the future is predicted according to a second calculation relation.
If the speed change value is greater than or equal to the preset speed change threshold value, obtaining target weight according to the third calculation relation, and predicting the speed of the passing section within 15 minutes in the future according to the fourth calculation relation. Step S1021 is executed to calculate the historical speed of the section to obtain speed trend data.
When the speed of passing through the section within 15 minutes in the future is predicted, the speed can be displayed on a terminal used by a traffic manager, and besides, the distance of the section and the predicted speed of passing through the section within 15 minutes in the future can be calculated to obtain the time of passing through the section within 15 minutes in the future, and the time is also displayed on the terminal used by the traffic manager, so that the traffic manager can control vehicles running on the road.
In the application scene, on one hand, the short-time speed prediction is predicted according to the section historical speed, the first section real-time speed and the second section real-time speed, so that the required data volume and the consumption of calculation resources are reduced, and the efficiency of the short-time speed prediction is improved; on the other hand, the speed trend of the section is calculated by predicting the speed of the section in a short time, so that the speed change rule of the section is effectively reflected.
In addition, in an exemplary embodiment of the present disclosure, a short-time speed prediction apparatus is also provided. Fig. 11 shows a schematic configuration of the short-time speed prediction apparatus, and as shown in fig. 11, the short-time speed prediction apparatus 1100 may include: a calculation module 1110, an acquisition module 1120, and a prediction module 1130. Wherein:
a calculation module 1110 configured to obtain a section history speed within a target history date, and calculate the section history speed to obtain speed trend data;
an acquisition module 1120 configured to acquire a first section real-time speed at a current time and a second section real-time speed within a target time range corresponding to a short time;
the prediction module 1130 is configured to calculate the first section real-time speed, the second section real-time speed, and the speed trend data, and predict the speed of the passing section in a short time.
The details of the short-time speed prediction apparatus 1100 are described in detail in the corresponding short-time speed prediction method, and thus are not described herein.
It should be noted that although several modules or units of the short-time speed prediction apparatus 1100 are mentioned in the above detailed description, such a division is not mandatory. Indeed, the features and functionality of two or more modules or units described above may be embodied in one module or unit in accordance with embodiments of the present disclosure. Conversely, the features and functions of one module or unit described above may be further divided into a plurality of modules or units to be embodied.
In addition, in an exemplary embodiment of the present disclosure, an electronic device capable of implementing the above method is also provided.
An electronic device 1200 according to such an embodiment of the invention is described below with reference to fig. 12. The electronic device 1200 shown in fig. 12 is merely an example, and should not be construed as limiting the functionality and scope of use of embodiments of the present invention.
As shown in fig. 12, the electronic device 1200 is in the form of a general purpose computing device. Components of electronic device 1200 may include, but are not limited to: the at least one processing unit 1210, the at least one memory unit 1220, a bus 1230 connecting the different system components (including the memory unit 1220 and the processing unit 1210), and a display unit 1240.
Wherein the storage unit stores program code that is executable by the processing unit 1210 such that the processing unit 1210 performs steps according to various exemplary embodiments of the present invention described in the above-described "exemplary methods" section of the present specification.
The storage unit 1220 may include readable media in the form of volatile storage units, such as Random Access Memory (RAM) 1221 and/or cache memory unit 1222, and may further include Read Only Memory (ROM) 1223.
Storage unit 1220 may also include a program/usage tool 1224 having a set (at least one) of program modules 1225, such program modules 1225 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which may include the reality of a network environment, or some combination thereof.
Bus 1230 may be a local bus representing one or more of several types of bus structures including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or using any of a variety of bus architectures.
The electronic device 1200 may also communicate with one or more external devices 1270 (e.g., keyboard, pointing device, bluetooth device, etc.), one or more devices that enable a user to interact with the electronic device 1200, and/or any device (e.g., router, modem, etc.) that enables the electronic device 1200 to communicate with one or more other computing devices. Such communication may occur through an input/output (I/O) interface 1250. Also, the electronic device 1200 may communicate with one or more networks such as a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network such as the internet through the network adapter 1260. As shown, the network adapter 1260 communicates with other modules of the electronic device 1200 over bus 1230. It should be appreciated that although not shown, other hardware and/or software modules may be used in connection with electronic device 1200, including, but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, data backup storage systems, and the like.
From the above description of embodiments, those skilled in the art will readily appreciate that the example embodiments described herein may be implemented in software, or in combination with the necessary hardware. Thus, the technical solution according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (may be a CD-ROM, a U-disk, a mobile hard disk, etc.) or on a network, and includes several instructions to cause a computing device (may be a personal computer, a server, a terminal device, or a network device, etc.) to perform the method according to the embodiments of the present disclosure.
In an exemplary embodiment of the present disclosure, a computer-readable storage medium having stored thereon a program product capable of implementing the method described above in the present specification is also provided. In some possible embodiments, the various aspects of the invention may also be implemented in the form of a program product comprising program code for causing a terminal device to carry out the steps according to the various exemplary embodiments of the invention as described in the "exemplary methods" section of this specification, when said program product is run on the terminal device.
Referring to fig. 13, a program product 1300 for implementing the above-described method according to an embodiment of the present invention is described, which may employ a portable compact disc read only memory (CD-ROM) and include program code, and may be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited thereto, and in this document, a readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium would include the following: an electrical connection having one or more wires, a portable disk, a hard disk, random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
The computer readable signal medium may include a data signal propagated in baseband or as part of a carrier wave with readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A readable signal medium may also be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Program code for carrying out operations of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device, partly on a remote computing device, or entirely on the remote computing device or server. In the case of remote computing devices, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., connected via the Internet using an Internet service provider).
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any adaptations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.

Claims (11)

1. A short-time speed prediction method, the method comprising:
acquiring a section historical speed in a target historical date, and calculating the section historical speed to obtain speed trend data;
acquiring a first section real-time speed at the current moment and a second section real-time speed in a target time range corresponding to a short time;
determining the second section real-time speed as a target section real-time speed in a short time, and calculating an average value of the target section real-time speed to obtain a section average speed;
calculating the current time and the target time range to obtain target time, and determining a value corresponding to the target time in the speed trend data as real-time speed trend data;
Calculating the real-time speed trend data and the section average speed to obtain a speed difference value;
and predicting the speed of the section passing through in a short time according to the first section real-time speed, the section average speed, the real-time speed trend data and the speed difference value.
2. The short-time speed prediction method according to claim 1, wherein predicting the speed of the passing section in a short time based on the first section real-time speed, the section average speed, the real-time speed trend data, and the speed difference value comprises:
acquiring a congestion speed threshold;
if the first section real-time speed is greater than the congestion speed threshold, assigning a sequence number to the target section real-time speed according to the sequence of the time values corresponding to the target section real-time speed;
calculating the sequence number and the real-time speed of the target section corresponding to the sequence number to obtain a speed change value;
and predicting the speed passing through the section in a short time by combining the real-time speed of the first section, the average speed of the section, the real-time speed trend data and the speed difference value according to the speed change value.
3. The short-time speed prediction method according to claim 2, wherein predicting the speed of the passing section in a short time according to the speed variation value in combination with the first section real-time speed, the section average speed, the real-time speed trend data, and the speed difference value comprises:
acquiring a preset speed change threshold;
if the speed change value is smaller than the preset speed change threshold value, determining a first calculation relation between the speed difference value and a target weight, and calculating the speed difference value based on the first calculation relation to obtain the target weight;
acquiring a preset weight, and if the target weight is greater than the preset weight, changing the target weight into the preset weight;
and determining a second calculation relation among the average speed of the section, the target weight, the real-time speed trend data and the predicted speed, and calculating the target weight, the average speed of the section and the real-time speed trend data based on the second calculation relation to predict the speed of the section passing through in a short time.
4. A short time speed prediction method according to claim 3, characterized in that the method further comprises:
If the speed change value is greater than or equal to the preset speed change threshold, determining a third calculation relation between the speed difference value and the target weight, and calculating the speed difference value based on the third calculation relation to obtain the target weight;
determining a fourth calculation relation among the target weight, the first section real-time speed, the real-time speed trend data and the predicted speed, calculating the target weight, the first section real-time speed and the real-time speed trend data based on the fourth calculation relation, and predicting the speed of the section passing through in a short time.
5. The short-time speed prediction method according to claim 2, characterized in that the method further comprises:
if the real-time speed of the first section is smaller than or equal to the congestion speed threshold value, a preset time range is obtained;
and determining the real-time speed of the section to be calculated, which belongs to the preset time range, from the target real-time speed of the section, calculating the real-time speed of the section to be calculated, and predicting the speed of the section passing through in a short time.
6. The short-term speed prediction method according to any one of claims 1 to 5, wherein the calculating the section history speed to obtain speed trend data includes:
Acquiring a preset sampling interval, and sampling the section historical speed of each day in the target historical date according to the preset sampling interval to obtain the section historical speed of different times of each day;
if the section historical speeds at different daily moments are not missing, recording the section historical speeds at different daily moments until the date corresponding to the recorded section historical speeds at different daily moments meets the preset day condition;
and calculating the historical speeds of the sections at different daily moments to obtain speed trend data.
7. The short-time speed prediction method according to claim 6, wherein the calculating the historical speed of the section at different times of day to obtain speed trend data includes:
constructing a section history speed matrix based on the section history speeds at different times of day;
singular value decomposition is carried out on the section historical speed matrix to obtain a diagonal matrix, a left singular value matrix and a right singular value matrix;
changing the singular value of the diagonal matrix to obtain the changed diagonal matrix;
calculating the changed diagonal matrix, the left singular value matrix and the right singular value matrix to obtain a target section historical speed matrix;
And carrying out average value calculation on each column of element values in the target section historical speed matrix to obtain speed trend data at different moments.
8. The short-time speed prediction method according to claim 7, wherein the changing the singular value of the diagonal matrix to obtain the changed diagonal matrix includes:
acquiring all singular values of the diagonal matrix, and comparing the magnitudes of all the singular values to obtain a magnitude comparison result;
acquiring a preset number, and determining the preset number of target singular values and other singular values from the singular values based on the size comparison result; the preset number of the target singular values and the other singular values form all singular values;
obtaining a preset value, maintaining the preset number of the target singular values in the diagonal matrix unchanged, and replacing the other singular values with the preset value to obtain the changed diagonal matrix.
9. A short-time speed prediction apparatus, comprising:
the calculation module is configured to acquire the section historical speed in the target historical date and calculate the section historical speed to obtain speed trend data;
The acquisition module is configured to acquire the first section real-time speed at the current moment and the second section real-time speed in a target time range corresponding to the short time;
the prediction module is configured to determine the second section real-time speed as a target section real-time speed in a short time, and calculate an average value of the target section real-time speed to obtain a section average speed; calculating the current time and the target time range to obtain target time, and determining a value corresponding to the target time in the speed trend data as real-time speed trend data; calculating the real-time speed trend data and the section average speed to obtain a speed difference value; and predicting the speed of the section passing through in a short time according to the first section real-time speed, the section average speed, the real-time speed trend data and the speed difference value.
10. An electronic device, comprising:
a processor;
a memory for storing executable instructions of the processor;
wherein the processor is configured to perform the short-term speed prediction method of any one of claims 1-8 via execution of the executable instructions.
11. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the short-time speed prediction method of any one of claims 1-8.
CN202211079066.5A 2022-09-05 2022-09-05 Short-time speed prediction method and device, computer storage medium and electronic equipment Active CN115410386B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211079066.5A CN115410386B (en) 2022-09-05 2022-09-05 Short-time speed prediction method and device, computer storage medium and electronic equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211079066.5A CN115410386B (en) 2022-09-05 2022-09-05 Short-time speed prediction method and device, computer storage medium and electronic equipment

Publications (2)

Publication Number Publication Date
CN115410386A CN115410386A (en) 2022-11-29
CN115410386B true CN115410386B (en) 2024-02-06

Family

ID=84164522

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211079066.5A Active CN115410386B (en) 2022-09-05 2022-09-05 Short-time speed prediction method and device, computer storage medium and electronic equipment

Country Status (1)

Country Link
CN (1) CN115410386B (en)

Citations (21)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102881291A (en) * 2012-10-24 2013-01-16 兰州理工大学 Sensing Hash value extracting method and sensing Hash value authenticating method for voice sensing Hash authentication
KR101266928B1 (en) * 2011-12-07 2013-05-28 에스케이플래닛 주식회사 Dynamic prediction traffic information providing method and system thereof
KR20150072471A (en) * 2013-12-19 2015-06-30 건국대학교 산학협력단 Traffic flow prediction system using spatiotemporal stochastic model
CN106197996A (en) * 2016-06-24 2016-12-07 南京理工大学 Offshore crane Fault Diagnosis of Gear Case device and method based on multivariate data
KR20170062178A (en) * 2015-11-27 2017-06-07 한국과학기술원 Server and method for predicting traffic conditions
CN108062561A (en) * 2017-12-05 2018-05-22 华南理工大学 A kind of short time data stream Forecasting Methodology based on long memory network model in short-term
CN108648457A (en) * 2018-06-28 2018-10-12 苏州大学 A kind of method, apparatus and computer readable storage medium of prediction of speed
CN109784473A (en) * 2018-12-13 2019-05-21 天津大学 A kind of short-term wind power prediction method based on Dual Clocking feature learning
CN110853347A (en) * 2019-10-14 2020-02-28 深圳市综合交通运行指挥中心 Short-time traffic road condition prediction method and device and terminal equipment
CN111341099A (en) * 2020-02-27 2020-06-26 阿里巴巴集团控股有限公司 Data processing method and device and electronic equipment
CN111508230A (en) * 2020-04-16 2020-08-07 中国科学院自动化研究所 Time-interval traffic flow trend prediction method, system and device based on deep learning
CN111640298A (en) * 2020-05-11 2020-09-08 同济大学 Traffic data filling method, system, storage medium and terminal
CN111862595A (en) * 2020-06-08 2020-10-30 同济大学 Speed prediction method, system, medium and device based on road network topological relation
CN112131467A (en) * 2020-09-15 2020-12-25 北京值得买科技股份有限公司 Data prediction method, system, medium and device
CN112382082A (en) * 2020-09-30 2021-02-19 银江股份有限公司 Method and system for predicting traffic running state in congested area
CN112419712A (en) * 2020-11-04 2021-02-26 同盾控股有限公司 Road section vehicle speed detection method and system
CN112614346A (en) * 2020-12-17 2021-04-06 东南大学 Short-term traffic flow prediction method based on singular spectrum analysis and echo state network
KR20210117445A (en) * 2020-03-19 2021-09-29 충북대학교 산학협력단 Road speed prediction method based on machine learning by analyzing road environment data, and recording medium thereof
CN113689699A (en) * 2021-08-25 2021-11-23 浙江数智交院科技股份有限公司 Traffic flow prediction method and device, electronic equipment and storage medium
CN114495494A (en) * 2022-01-06 2022-05-13 电子科技大学 Traffic situation assessment method based on traffic flow parameter prediction
CN114692984A (en) * 2022-04-09 2022-07-01 华东交通大学 Traffic prediction method based on multi-step coupling graph convolution network

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8892345B2 (en) * 2011-04-08 2014-11-18 Here Global B.V. Trend based predictive traffic
US10909470B2 (en) * 2017-02-22 2021-02-02 Here Global B.V. Method and apparatus for providing semantic-free traffic prediction

Patent Citations (21)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR101266928B1 (en) * 2011-12-07 2013-05-28 에스케이플래닛 주식회사 Dynamic prediction traffic information providing method and system thereof
CN102881291A (en) * 2012-10-24 2013-01-16 兰州理工大学 Sensing Hash value extracting method and sensing Hash value authenticating method for voice sensing Hash authentication
KR20150072471A (en) * 2013-12-19 2015-06-30 건국대학교 산학협력단 Traffic flow prediction system using spatiotemporal stochastic model
KR20170062178A (en) * 2015-11-27 2017-06-07 한국과학기술원 Server and method for predicting traffic conditions
CN106197996A (en) * 2016-06-24 2016-12-07 南京理工大学 Offshore crane Fault Diagnosis of Gear Case device and method based on multivariate data
CN108062561A (en) * 2017-12-05 2018-05-22 华南理工大学 A kind of short time data stream Forecasting Methodology based on long memory network model in short-term
CN108648457A (en) * 2018-06-28 2018-10-12 苏州大学 A kind of method, apparatus and computer readable storage medium of prediction of speed
CN109784473A (en) * 2018-12-13 2019-05-21 天津大学 A kind of short-term wind power prediction method based on Dual Clocking feature learning
CN110853347A (en) * 2019-10-14 2020-02-28 深圳市综合交通运行指挥中心 Short-time traffic road condition prediction method and device and terminal equipment
CN111341099A (en) * 2020-02-27 2020-06-26 阿里巴巴集团控股有限公司 Data processing method and device and electronic equipment
KR20210117445A (en) * 2020-03-19 2021-09-29 충북대학교 산학협력단 Road speed prediction method based on machine learning by analyzing road environment data, and recording medium thereof
CN111508230A (en) * 2020-04-16 2020-08-07 中国科学院自动化研究所 Time-interval traffic flow trend prediction method, system and device based on deep learning
CN111640298A (en) * 2020-05-11 2020-09-08 同济大学 Traffic data filling method, system, storage medium and terminal
CN111862595A (en) * 2020-06-08 2020-10-30 同济大学 Speed prediction method, system, medium and device based on road network topological relation
CN112131467A (en) * 2020-09-15 2020-12-25 北京值得买科技股份有限公司 Data prediction method, system, medium and device
CN112382082A (en) * 2020-09-30 2021-02-19 银江股份有限公司 Method and system for predicting traffic running state in congested area
CN112419712A (en) * 2020-11-04 2021-02-26 同盾控股有限公司 Road section vehicle speed detection method and system
CN112614346A (en) * 2020-12-17 2021-04-06 东南大学 Short-term traffic flow prediction method based on singular spectrum analysis and echo state network
CN113689699A (en) * 2021-08-25 2021-11-23 浙江数智交院科技股份有限公司 Traffic flow prediction method and device, electronic equipment and storage medium
CN114495494A (en) * 2022-01-06 2022-05-13 电子科技大学 Traffic situation assessment method based on traffic flow parameter prediction
CN114692984A (en) * 2022-04-09 2022-07-01 华东交通大学 Traffic prediction method based on multi-step coupling graph convolution network

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
Short-Term Traffic Flow Prediction of Expressway: A Hybrid Method Based on Singular Spectrum Analysis Decomposition;Chunyan Shuai等;Hindawi;第1-10页 *
基于网约车轨迹数据的路网速度估计与预测方法研究;周天;中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑;C034-507 *

Also Published As

Publication number Publication date
CN115410386A (en) 2022-11-29

Similar Documents

Publication Publication Date Title
US8718925B2 (en) Collaborative route planning for generating personalized and context-sensitive routing recommendations
CN112435469B (en) Vehicle early warning control method and device, computer readable medium and electronic equipment
US20090006297A1 (en) Open-world modeling
CN103632542A (en) Traffic information processing method, device and corresponding equipment
WO2018207878A1 (en) Demand forecast device
CN114692927A (en) Battery replacement station recommendation method and system, electronic device and storage medium
CN111724184A (en) Transformation probability prediction method and device
CN111444302A (en) Mobility prediction method, system and device based on user classification
CN115034596A (en) Risk conduction prediction method, device, equipment and medium
CN111582589A (en) Car rental insurance prediction method, device, equipment and storage medium
CN113344277B (en) Predictive model training method, state updating method, device, equipment and medium
CN115410386B (en) Short-time speed prediction method and device, computer storage medium and electronic equipment
CN116431923B (en) Traffic travel prediction method, equipment and medium for urban road
Origlia et al. On-line filtering of on-street parking data to improve availability predictions
US10742534B2 (en) Monitoring system for metric data
CN113420942B (en) Sanitation vehicle real-time route planning method based on deep Q learning
KR102601046B1 (en) Method and apparatus for predicting vehicle availability
US20220043732A1 (en) Method, device, and program product for managing computing resource in storage system
US11907857B2 (en) Dynamic selection of parameter threshold values
CN113806585B (en) Method and device for obtaining road section passing duration, electronic equipment and storage medium
CN114463978A (en) Data monitoring method based on rail transit information processing terminal
US20110288839A1 (en) Open-world modeling
CN114693329A (en) Method, system, device and medium for identifying battery swapping user
CN116820539B (en) System software operation maintenance system and method based on Internet
US11829805B2 (en) Software lock management

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