CN115440038A

CN115440038A - Traffic information determination method and electronic equipment

Info

Publication number: CN115440038A
Application number: CN202211057177.6A
Authority: CN
Inventors: 张贤贤; 王朋; 张彤; 魏立夏; 贾立; 韩晓宁
Original assignee: Hisense TransTech Co Ltd
Current assignee: Hisense TransTech Co Ltd
Priority date: 2022-08-31
Filing date: 2022-08-31
Publication date: 2022-12-06
Anticipated expiration: 2042-08-31
Also published as: CN115440038B

Abstract

The application relates to the technical field of traffic control, and discloses a traffic information determination method and electronic equipment, wherein the method comprises the following steps: determining historical target values of a plurality of indexes of a target area in each historical period of a historical cycle; aiming at any time interval of the period, determining a predicted value of each index in the time interval based on a historical target value of each index in a target historical time interval; the target historical time interval is a historical time interval corresponding to the time interval; and determining the traffic information of the target area in the period based on the predicted values of all the indexes in each period of the period. The embodiment determines the predicted value of the index dynamic change of the target area in each period of the period, the influence items of different indexes are different, a plurality of indexes represent the factor of the dynamic change in the target area, and the predicted values of the indexes reflect the traffic state of the target area more comprehensively; and then accurately determining the traffic information of the target area in the period based on the predicted values of the indexes in each period of the period.

Description

Traffic information determination method and electronic equipment

Technical Field

The present application relates to the field of traffic control technologies, and in particular, to a traffic information determining method and an electronic device.

Background

With the increase of the quantity of motor vehicles kept, the urban traffic problem becomes more serious. In order to actively perform traffic control, it is necessary to customize reasonable traffic information, such as a traffic flow distribution period, a split ratio, and the like.

In the related art, traffic information is determined by adopting a non-parameter statistical method, namely the traffic information of each position is determined based on fixed traffic influence factors corresponding to each position.

However, the non-parametric statistical method does not consider the dynamically changing factors, and therefore, the reasonable traffic information cannot be accurately determined.

Disclosure of Invention

The application provides a traffic information determining method and electronic equipment, which are used for determining traffic information suitable for a target area.

In a first aspect, an embodiment of the present application provides a traffic information determining method, where the method includes:

determining historical target values of a plurality of indexes of a target area in each historical period of a historical cycle;

for any time interval of the cycle, determining a predicted value of each index in the time interval based on a historical target value of each index in a target historical time interval; wherein the target historical time period is a historical time period corresponding to the time period;

and determining the traffic information of the target area in the period based on the predicted values of all the indexes in each period of the period.

According to the scheme, the predicted value of the dynamic change of the indexes of the target area in each historical time period of the historical period is accurately determined based on the historical target values of the indexes of the target area in each historical time period of the historical period, the influence items of different indexes are different, the indexes represent the dynamic change factors of the target area, and the predicted values of the indexes comprehensively reflect the traffic state of the target area; and then accurately determining the traffic information of the target area in the period based on the predicted values of the indexes in each period of the period.

In some optional embodiments, determining that the target area is after the traffic information of the current period further includes:

for any index, after the measured value of the index in each period of the cycle is acquired, whether to update the historical target value of the index is determined based on the predicted value and the measured value of the index in each period of the cycle.

According to the scheme, after the actual measurement value of the index in each time period of the period is obtained, the stability and the reliability of the actual measurement value of the period are reflected by the predicted value and the actual measurement value of the index in each time period of the period; because the measured value is dynamically changed, based on the predicted value and the measured value of the index in each time interval of the period, the historical target value of the index can be reasonably updated, the accuracy of the subsequent predicted value is improved, and the influence of unstable or unreliable measured values on the subsequent prediction in the period is reduced.

In some alternative embodiments, determining whether to update the historical target value of the index based on the predicted value and the measured value of the index in each period of the cycle includes:

determining an accumulated prediction error of the index in the period based on the deviation of the predicted value of the index relative to the actually measured value in each time period of the period;

if the accumulated prediction error of the index in the period is smaller than the preset error, updating the historical target value of the index based on the measured value of the index in each period of the period; or alternatively

If the accumulated prediction error of the index in the period is larger than or equal to the preset error, determining the accumulated trend deviation of the index in the period based on the deviation of the predicted trend value of the index relative to the actual trend value in each period of the period, and determining whether to update the historical target value of the index based on the accumulated trend deviation.

According to the scheme, if the accumulated prediction error of the index in the period is smaller than the preset error, the stability of the measured value of the index in the period is high, the measured value accords with the historical change rule of the index, and the historical target value of the index is reasonably updated directly on the basis of the measured value of the index in each period of the period; if the accumulated prediction error of the index in the period is larger than or equal to the preset error, the stability of the measured value of the index in the period is low, at least part of the measured value is not in accordance with the historical change rule of the index, whether the historical target value of the index is updated or not is determined based on the accumulated trend deviation, and the influence of the unstable or unreliable measured value on subsequent prediction in the period is reduced.

In some optional embodiments, determining whether to update the historical target value of the indicator based on the cumulative trend deviation includes:

if the accumulated trend deviation is smaller than a preset trend deviation, adjusting the measured value of the time period based on the predicted value of the index in at least one time period of the period, and updating the historical target value of the index based on the adjusted value; or alternatively

And if the accumulated trend deviation is greater than or equal to the preset trend deviation, not updating the historical target value of the index.

In the scheme, the accumulated trend deviation of the index in the period is smaller than the preset trend deviation, which indicates that short-time sudden change of the traffic state exists, the overall reliability of the measured value of the index in the period is high, and the historical target value of the index can be updated after the partial measured value (the missing or jumping measured value) is adjusted; on the contrary, if the accumulated trend deviation of the index in the period is greater than or equal to the preset trend deviation, it indicates that the overall reliability of the measured value of the index in the period is low, and the historical target value of the index cannot be updated based on the data of the period, so as to avoid the influence on subsequent prediction due to the instability or unreliability of the measured value of the period.

In some optional embodiments, adjusting the measured value of the at least one time period of the present cycle based on the predicted value of the index in the time period includes:

for any time period in the period, if the deviation of the predicted trend value of the index relative to the actual trend value in the time period is greater than or equal to the preset trend deviation, replacing the measured value of the index in the time period with the predicted value of the index in the time period; or alternatively

And if the deviation of the predicted trend value of the index relative to the actual trend value in the time period is smaller than the preset trend deviation, not adjusting the actual measured value of the index in the time period.

According to the scheme, the measured value which does not accord with the historical change rule of the index is adjusted, so that the adjusted value obtained by adjustment accords with the historical change rule of the index, and the historical target value of the index is reasonably updated based on the adjusted value of the index in each period of the period.

In some optional embodiments, if the historical target value of the index is not updated, the method further includes:

determining whether other indexes are stable or not based on the accumulated prediction errors of the other indexes in the period;

if other indexes are stable, determining influence information corresponding to the indexes; or alternatively

And if other indexes are unstable, determining classification information corresponding to the indexes.

In some alternative embodiments, determining whether the other indicators are stable based on the accumulated prediction errors of the other indicators in the current period includes:

if the accumulated prediction error of the other indexes in the period is smaller than the preset error, determining that the other indexes are stable; or

And if the accumulated prediction error of the other indexes in the period is greater than or equal to the preset error, determining that the other indexes are unstable.

In a second aspect, an embodiment of the present application provides an electronic device, including a communication unit and a processor;

the communication unit is used for carrying out data transmission with a measuring device of a target area;

the processor is used for determining historical target values of a plurality of indexes of the target area in each historical period of the historical cycle; for any time interval of the cycle, determining a predicted value of each index in the time interval based on a historical target value of each index in a target historical time interval; wherein the target historical time interval is a historical time interval corresponding to the time interval; and determining the traffic information of the target area in the period based on the predicted values of all the indexes in each period of the period.

In a third aspect, an embodiment of the present application provides a traffic information determining apparatus, including:

a target value determination module for determining historical target values of a plurality of indexes of a target area in each historical period of a historical cycle;

the predicted value determining module is used for determining the predicted value of each index in a target historical time interval based on the historical target value of each index in the target historical time interval aiming at any time interval of the period; wherein the target historical time period is a historical time period corresponding to the time period;

and the traffic information determining module is used for determining the traffic information of the target area in the period based on the predicted values of all the indexes in all the time periods of the period.

In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which a computer program is stored, and when the computer program is executed by a processor, the method for determining traffic information according to any one of the first aspect is implemented.

In addition, for technical effects brought by any one implementation manner of the second aspect to the fourth aspect, reference may be made to technical effects brought by different implementation manners of the first aspect, and details are not described herein again.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the description below are only some embodiments of the present application, and it is obvious for those skilled in the art that other drawings may be obtained according to these drawings without inventive labor.

Fig. 1 is a schematic view of a first application scenario provided in an embodiment of the present application;

fig. 2 is a schematic view of a street light group provided in an embodiment of the present application;

fig. 3 is a schematic flow chart of a first traffic information determining method according to an embodiment of the present application;

fig. 4 is a schematic view of a second application scenario provided in an embodiment of the present application;

FIG. 5 is a system architecture diagram provided in accordance with an embodiment of the present application;

fig. 6 is a schematic flow chart of a second traffic information determining method according to an embodiment of the present application;

FIG. 7 is a schematic flow chart of a method for determining whether to update a historical target value according to an embodiment of the present disclosure;

fig. 8 is a schematic flow chart of a third traffic information determining method according to an embodiment of the present application;

fig. 9 is a schematic flow chart of a fourth traffic information determining method according to an embodiment of the present application;

fig. 10 is a schematic flow chart of a fifth traffic information determining method according to an embodiment of the present application;

fig. 11 is a schematic flow chart of a sixth traffic information determining method according to an embodiment of the present application;

fig. 12 is a schematic flow chart of a seventh traffic information determining method according to an embodiment of the present application;

fig. 13 is a schematic flow chart of an eighth traffic information determining method according to an embodiment of the present application;

fig. 14 is a schematic flow chart of a ninth traffic information determining method according to an embodiment of the present application;

fig. 15 is a schematic flow chart of a tenth traffic information determining method according to an embodiment of the present application;

fig. 16 is a schematic flow chart of an eleventh traffic information determining method according to an embodiment of the present application;

fig. 17 is a schematic structural diagram of a first traffic information determining apparatus according to an embodiment of the present application;

fig. 18 is a schematic structural diagram of a second traffic information determination device according to an embodiment of the present application;

fig. 19 is a schematic structural diagram of a third traffic information determination device according to an embodiment of the present application;

fig. 20 is a schematic block diagram of an electronic device provided in an embodiment of the present application.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application clearer, the present application will be described in further detail with reference to the accompanying drawings, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present application without making any creative effort belong to the protection scope of the present application.

In the description of the present application, unless otherwise explicitly stated or limited, the term "coupled" is to be construed broadly and can mean, for example, directly coupled or indirectly coupled through intervening media, or the communication between two devices. The specific meaning of the above terms in the present application can be understood by those of ordinary skill in the art as the case may be.

With the increase of the quantity of motor vehicles kept, the urban traffic problem becomes more and more serious. In order to actively perform traffic control, reasonable traffic information needs to be customized. Referring to fig. 1, active traffic control is performed for region 1, region 2, \ 8230 \ 8230:and region N.

The traffic information refers to information related to traffic control, such as a traffic flow distribution cycle, a split ratio, and the like. The split ratio is a time ratio that can be used for vehicle passing in a traffic flow distribution cycle, and referring to fig. 2, the street lamp group includes street lamps of three colors, and the split ratio is adjusted by controlling the lighting of the street lamps of the three colors respectively.

Based on this, the embodiment of the application provides a traffic information determination method and an electronic device, and the method includes: determining historical target values of a plurality of indexes of a target area in each historical period of a historical cycle; for any time interval of the cycle, determining a predicted value of each index in the time interval based on a historical target value of each index in a target historical time interval; wherein the target historical time period is a historical time period corresponding to the time period; and determining the traffic information of the target area in the period based on the predicted values of all the indexes in each period of the period.

According to the scheme, the predicted value of the dynamic change of the indexes of the target area in each period of the historical period is accurately determined based on the historical target values of the indexes of the target area in each historical period of the historical period, the influence items of different indexes are different, the indexes represent the dynamic change factors of the target area, and the predicted values of the indexes comprehensively reflect the traffic state of the target area; and then accurately determining the traffic information of the target area in the period based on the predicted values of the indexes in each period of the period.

The following detailed description will be given with reference to the accompanying drawings and specific embodiments to explain the technical solutions of the present application and how to solve the above technical problems. The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments.

An embodiment of the present application provides a first traffic information determining method, which is applicable to the electronic device, and as shown in fig. 3, the method may include:

step S301: historical target values of a plurality of indexes of the target area in each historical period of the historical cycle are determined.

In this embodiment, different indexes have different influence items, and multiple indexes represent factors of dynamic change in a target area, such as a flow index or a speed index; the predicted values of the indexes reflect the traffic state of the target area comprehensively;

accordingly, in order to accurately determine the predicted values of the plurality of indices, it is necessary to determine the historical target values of the plurality of indices in the historical period.

The flow index is the flow of an inlet road of the intersection, and comprises flow data of all lanes on the inlet road;

the speed index is a road section speed, and comprises an average value of speeds of floating vehicles running on the road section.

In an implementation, the history periods may be one or more, such as one or more history periods adjacent to the present period.

In some embodiments, the cycle may be classified, and in order to determine the predicted values of the multiple indicators more accurately, the cycle type of the historical cycle is the same as the cycle type of the present cycle. For example:

the cycle is weekend, and the historical cycle is also weekend; this cycle is a workday, as is the historical cycle. Under the influence of commuting traffic on a working day, the number of traffic streams has obvious peak phenomena in the morning and the evening; the influence of entertainment traffic is small on weekends, and the number of traffic flow has small peak. The working day or weekend cycles, and similar patterns are presented in a fixed interval in a certain time period, so that the phenomenon of commuting seasonality is presented. The traffic flow has obvious gentle rising and falling trends when the flow is gathered under the condition that the peak is close to the saturation state, the traffic speed presents opposite trends and rises after falling; the flat peak in the unsaturated state generally runs smoothly in a motorcade form, the speed is stable, and an obvious stability trend is achieved; the sparse traffic distribution speed at night under the low saturation state is stable and higher than that during the day. The phenomenon of obvious trend change 'time period trend' is presented in a periodic cycle, namely in a fixed time period of each day; the change of the traffic flow between adjacent time periods has stable continuity, and when no short-time sudden change influence of the traffic state exists, the traffic flow or traffic speed numerical value has no obvious jump, namely, the traffic data points show the phenomenon of 'similar similarity'. Therefore, the predicted value of each index in the present cycle can be determined based on the historical target value of each index in the target historical period.

Step S302: for any time interval of the cycle, determining a predicted value of each index in the time interval based on a historical target value of each index in a target historical time interval; wherein the target history period is a history period corresponding to the period.

In the implementation, the time period division modes in the periods are the same (i.e. the time granularity is the same), for example, one period is 1 day, the time granularity is 10 minutes, each period is divided into 144 time periods (period periods), and the time periods in the same order in different periods are corresponding time periods, that is, every two adjacent corresponding time periods are separated by 144 time periods.

Illustratively, there are 5 history cycles (history cycle 1, history cycle 2, history cycle 3, history cycle 4, and history cycle 5), and the target history period of the i-th period of the cycle is the i-th period of history cycle 1, the i-th period of history cycle 2, the i-th period of history cycle 3, the i-th period of history cycle 4, and the i-th period of history cycle 5.

The following is a specific example:

velocity prediction value X of i + k-th period (i-th period of the present cycle) _i+k ＝f _i +h*d _i +c _i ；

Wherein f is _i As similarity parameter, f _i ＝α*(x _i -c _i-k )+(1-α)*(f _i-1 +d _i-1 )；

d _i To predict trend values, d _i ＝β*(f _i -f _i-1 )+(1-β)*d _i-1 ；

c _i As a seasonal parameter, c _i ＝γ*(x _i -f _i )+(1-γ)*c _i-k ；

k is a period, i.e., the total number of periods in one cycle; x is the number of _i Is a target value (measured value, or adjusted to measured value) of the speed in the i-th period.

The determination method of the predicted value of other indexes is similar to that of the predicted value of the speed, and is not described herein again.

Step S303: and determining the traffic information of the target area in the period based on the predicted values of all the indexes in each period of the period.

Because the predicted values of the multiple indexes reflect the traffic state of the target area relatively comprehensively, the traffic information suitable for the target area in the period can be determined based on the predicted values of the multiple indexes in each period of the period.

For example, if the predicted value of the speed index in a certain period of time is smaller and the predicted value of the flow index is larger, the green letter in the certain period of time is larger, for example, the lighting time of the green light in the certain period of time is controlled to be longer than the lighting time of the red light in the certain period of time; if the predicted value of the speed index in a certain period is large and the predicted value of the flow index is small, the green letter in the certain period is small, for example, the lighting time of the green light of the street lamp group in the certain period is controlled to be shorter than the lighting time of the red light, and the like, which is not illustrated herein.

The traffic system has complexity, and besides the overall influence of political, economic, cultural and other requirements on design-guided macroscopic planning on traffic, various factors such as people, vehicles, roads, external environments and the like can also influence the internal traffic running state. Road conditions and vehicle operation characteristics mainly design guide type influence factors for demands, and have great influence on the whole operation situation, while human influence factors and external environments have great influence on long-term stability, non-strong stability and short-time mutation of data.

The artificial influence factors are formed by the group trip activities which are formed by convention and comprise main stable rules, non-strong stable rules and short-time mutation rules, wherein national legal working days, holidays and the like are national specified artificial activity dates, are stable for a long time, are basically suitable for Chinese cities, and are main stable rules; large-scale exhibitions, large-scale meetings and the like are regional scope conventions, namely, formed common events of year, month, week or day are appointed, the traffic running state of a specific space is influenced at a specific time, and the law is a non-strong stability law; under the condition that the road section demand is greater than the traffic bearing capacity, such as the condition of traffic flow overflow or temporary management and control during a peak period, the data of the specific point at variable time is changed suddenly, and the rule is changed suddenly and temporarily. In addition, for external environment influence factors, influence items causing data non-strong stability include weather, equipment abnormality and the like, and the change of the traffic state can be caused for days or hours; the influence items causing the short-time sudden change of the data have the conditions of network transmission interruption and the like.

For example, the information of the influence factors and the influence items can be referred to table 1:

TABLE 1

It can be seen that the measured value is affected by a plurality of factors, and thus the measured value may be unstable or unreliable during the period. Therefore, in the embodiment, the historical target value of the index needs to be selectively updated based on the measured value, so that not only the dynamic updating requirement of the historical target value is met, but also the influence of the unstable or unreliable measured value on the subsequent prediction in the period is reduced.

Referring to fig. 4, each target area is provided with a measuring device for detecting measured values of a plurality of indexes of the target area in each time period of the cycle;

referring to fig. 5, the electronic device is connected to the measuring apparatus, and obtains measured values of a plurality of indexes of the target area in each time period of the cycle.

Correspondingly, an embodiment of the present application provides a second traffic information determining method, which is applicable to the electronic device described above, and as shown in fig. 6, the method may include:

step S601: historical target values of a plurality of indexes of the target area in each historical period of the historical cycle are determined.

Step S602: for any time interval of the cycle, determining a predicted value of each index in the time interval based on a historical target value of each index in a target historical time interval; wherein the target history period is a history period corresponding to the period.

Step S603: and determining the traffic information of the target area in the period based on the predicted values of all the indexes in all the time periods of the period.

The specific implementation manner of steps S601 to S603 may refer to the above embodiments, and details are not described here.

Step S604: for any index, after the measured value of the index in each period of the cycle is acquired, whether to update the historical target value of the index is determined based on the predicted value and the measured value of the index in each period of the cycle.

After the actual measurement values of the indexes in all the time periods of the period are obtained, the fact that all the time periods of the period become historical time periods is shown, and the period becomes a new historical period; the measured values are dynamically changed, and in order to improve the accuracy of the subsequent predicted values, it is necessary to determine whether to update the historical target values of the indexes.

According to the scheme, after the measured value of the index in each time period of the period is obtained, the predicted value and the measured value of the index in each time period of the period reflect the stability and the reliability of the measured value of the period; because the measured value is dynamically changed, based on the predicted value and the measured value of the index in each time interval of the period, the historical target value of the index can be reasonably updated, the accuracy of the subsequent predicted value is improved, and the influence of unstable or unreliable measured values on the subsequent prediction in the period is reduced.

In some alternative embodiments, the step S604 may be implemented by the method shown in fig. 7:

step S701: and determining the accumulated prediction error of the index in the period based on the deviation of the predicted value of the index relative to the measured value in each period of the period.

The deviation of the predicted value of the index from the measured value is the error of the predicted value from the measured value in the corresponding time period. Exemplary, all ofDeviation from trend

Wherein x is _i Is the measured value of the speed index in the i-th time period, X _i K is the cycle period, i.e., the total number of periods in one cycle, which is the predicted value of the speed index at the i-th period.

In this embodiment, the accumulated prediction error of the index in this period represents the stability of the measured value of the index in this period, that is, whether the measured value meets the history change rule of the index.

Based on this, it is possible to determine whether or not the historical target value of the index can be directly updated, based on the accumulated prediction error of the index in the present cycle.

For example, if the accumulated prediction error of the indicator in the present period is smaller than the preset error, which indicates that the stability of the measured value of the indicator in the present period is high and conforms to the historical change rule of the indicator, step S702 is executed to update the historical target value of the indicator directly based on the measured value of the indicator in each time period of the present period;

otherwise, if the accumulated prediction error of the indicator in the present period is greater than or equal to the preset error, which indicates that the stability of the measured value of the indicator in the present period is low, and at least a portion of the measured value does not conform to the historical change rule of the indicator, step S703 is executed to determine whether to update the historical target value of the indicator based on the accumulated trend deviation.

Step S702: and if the accumulated prediction error of the index in the period is smaller than the preset error, updating the historical target value of the index based on the measured value of the index in each period of the period.

Illustratively, the measured value of the index in each period of the present cycle is taken as the historical target value of the index of the latest historical cycle.

Step S703: if the accumulated prediction error of the index in the period is larger than or equal to the preset error, determining the accumulated trend deviation of the index in the period based on the deviation of the predicted trend value of the index relative to the actual trend value in each period of the period, and determining whether to update the historical target value of the index based on the accumulated trend deviation.

The above embodiments can be referred to for determining the predicted trend values, and the details are not repeated herein.

The actual trend value of a certain time period is the difference between the measured value of the time period and the measured value of the previous time period. I.e. the actual trend value c of the speed indicator in the i-th period _i ′＝x _i -x _i-1 (ii) a Wherein x is _i Is the measured speed, x, of the i-th period _i-1 Is the measured speed of the i-1 th time period.

Exemplary, cumulative Trend bias

Wherein, c _i ' is the actual trend value of the speed index in the i-th period, c _i K is the period of the cycle, i.e., the total number of periods in one cycle, for the predicted trend value of the speed index in the i-th period.

In this embodiment, the cumulative trend deviation of the index in the present period represents the overall reliability of the measured value of the index in the present period.

Based on this, when the measured value of the index is unstable, it is possible to determine whether or not the historical target value of the index can be updated based on the cumulative trend deviation of the index in the present cycle.

Correspondingly, the embodiment of the present application provides a third traffic information determining method, as shown in fig. 8, the method may include:

step S801: determining historical target values of a plurality of indexes of a target area in each historical period of a historical cycle;

step S802: for any time interval of the cycle, determining a predicted value of each index in the time interval based on a historical target value of each index in a target historical time interval; wherein the target historical time interval is a historical time interval corresponding to the time interval;

step S803: determining traffic information of the target area in the period based on the predicted values of all indexes in all time periods of the period;

step S804: for any index, after acquiring an actual measurement value of the index in each time period of the period, determining an accumulated prediction error of the index in the period based on a deviation of a predicted value of the index in each time period of the period relative to the actual measurement value;

step S805: and if the accumulated prediction error of the index in the period is smaller than the preset error, updating the historical target value of the index based on the measured value of the index in each period of the period.

The embodiment of the present application further provides a fourth traffic information determining method, as shown in fig. 9, the method may include:

step S901: determining historical target values of a plurality of indexes of a target area in each historical period of a historical cycle;

step S902: for any time interval of the cycle, determining a predicted value of each index in the time interval based on a historical target value of each index in a target historical time interval; wherein the target historical time period is a historical time period corresponding to the time period;

step S903: determining the traffic information of the target area in the period based on the predicted values of all indexes in all time periods of the period;

step S904: for any index, after the actual measurement value of the index in each time period of the period is obtained, the accumulated prediction error of the index in the period is determined based on the deviation of the predicted value of the index in each time period of the period relative to the actual measurement value;

step S905: and if the accumulated prediction error of the index in the period is greater than or equal to a preset error, determining the accumulated trend deviation of the index in the period based on the deviation of the prediction trend value of the index relative to the actual trend value in each period of the period, and determining whether to update the historical target value of the index based on the accumulated trend deviation.

The specific implementation of the method shown in fig. 8 and fig. 9 may refer to the foregoing embodiments, and details are not repeated here.

In some optional embodiments, the steps S703 and S905 may be implemented as follows:

if the accumulated trend deviation is smaller than a preset trend deviation, adjusting the measured value of the time period based on the predicted value of the index in at least one time period of the period, and updating the historical target value of the index based on the adjusted value; or

And if the accumulated trend deviation is greater than or equal to a preset trend deviation, not updating the historical target value of the index.

As described above, the cumulative trend deviation of the index in the present cycle represents the overall reliability of the measured value of the index in the present cycle.

Based on this, it is possible to determine whether the historical target value of the index can be updated, based on the cumulative trend deviation of the index in the present cycle.

Illustratively, if short-term sudden changes of traffic conditions exist in the period, short-term data abnormality occurs, and the duration of the abnormal data is usually short, namely, only a few measured values of the abnormality exist.

The accumulated trend deviation of the index in the period is smaller than the preset trend deviation, which indicates that short-term sudden change of the traffic state exists, the overall reliability of the measured value of the index in the period is higher, and the historical target value of the index can be updated after partial measured values (the missing or jumping measured values) are adjusted;

on the contrary, if the accumulated trend deviation of the index in the period is greater than or equal to the preset trend deviation, it indicates that the overall reliability of the measured value of the index in the period is low, and the historical target value of the index cannot be updated based on the data of the period, so as to avoid the influence on subsequent prediction due to the instability or unreliability of the measured value of the period.

Correspondingly, a fifth traffic information determining method is provided in an embodiment of the present application, and as shown in fig. 10, the method may include:

step S1001: determining historical target values of a plurality of indexes of a target area in each historical period of a historical cycle;

step S1002: for any time interval of the cycle, determining a predicted value of each index in the time interval based on a historical target value of each index in a target historical time interval; wherein the target historical time interval is a historical time interval corresponding to the time interval;

step S1003: determining traffic information of the target area in the period based on the predicted values of all indexes in all time periods of the period;

step S1004: for any index, if the accumulated prediction error of the index in the period is greater than or equal to a preset error and the accumulated trend deviation is smaller than a preset trend deviation, adjusting the actual measurement value of the period based on the prediction value of the index in at least one period of the period, and updating the historical target value of the index based on the adjusted value.

The embodiment of the present application further provides a sixth traffic information determining method, as shown in fig. 11, the method may include:

step S1101: determining historical target values of a plurality of indexes of a target area in each historical period of a historical cycle;

step S1102: aiming at any time interval of the period, determining a predicted value of each index in the time interval based on a historical target value of each index in a target historical time interval; wherein the target historical time interval is a historical time interval corresponding to the time interval;

step S1103: determining traffic information of the target area in the period based on the predicted values of all indexes in all time periods of the period;

step S1104: for any index, if the accumulated prediction error of the index in the period is greater than or equal to a preset error and the accumulated trend deviation is greater than or equal to a preset trend deviation, the historical target value of the index is not updated.

For the specific implementation of the method shown in fig. 10 and fig. 11, reference may be made to the above embodiments, which are not described herein again.

In some optional embodiments, the step S1004 may be implemented as follows:

As described above, if the accumulated trend deviation of the index in the present period is smaller than the preset trend deviation, it indicates that the overall reliability of the measured value of the index in the present period is high, and some abnormal measured values with less stability need to be adjusted.

In practice, if the deviation of the predicted trend value of the indicator from the actual trend value in a certain time period is greater than or equal to the preset trend deviation, which indicates that the measured value of the indicator is abnormal in the time period, the measured value of the indicator in the time period needs to be replaced by the predicted value of the indicator in the time period;

on the contrary, if the deviation of the predicted trend value of the indicator relative to the actual trend value in a certain time period is smaller than the preset trend deviation, it indicates that the actual measurement value of the indicator in the time period is normal, and the actual measurement value of the indicator in the time period does not need to be adjusted.

Correspondingly, an embodiment of the present application provides a seventh traffic information determining method, as shown in fig. 12, the method may include:

step S1201: determining historical target values of a plurality of indexes of a target area in each historical period of a historical cycle;

step S1202: for any time interval of the cycle, determining a predicted value of each index in the time interval based on a historical target value of each index in a target historical time interval; wherein the target historical time period is a historical time period corresponding to the time period;

step S1203: determining traffic information of the target area in the period based on the predicted values of all indexes in all time periods of the period;

step S1204: for any time period of the period, if the deviation of the predicted trend value of the index relative to the actual trend value in the time period is greater than or equal to the preset trend deviation, replacing the actual measured value of the index in the time period with the predicted value of the index in the time period; or if the deviation of the predicted trend value of the index relative to the actual trend value in the time period is smaller than the preset trend deviation, not adjusting the measured value of the index in the time period.

The specific implementation of the method shown in fig. 12 can refer to the above embodiments, and is not described herein again.

An eighth traffic information determining method is provided in the embodiments of the present application, and as shown in fig. 13, the method may include:

step S1301: historical target values of a plurality of indexes of the target area in each historical period of the historical cycle are determined.

Step S1302: aiming at any time interval of the period, determining a predicted value of each index in the time interval based on a historical target value of each index in a target historical time interval; wherein the target history period is a history period corresponding to the period.

Step S1303: and determining the traffic information of the target area in the period based on the predicted values of all the indexes in each period of the period.

The specific implementation of steps S1301 to S1303 may refer to the above embodiments, and details are not repeated herein.

Step S1304: for any index, after the actual measurement value of the index in each period of the period is acquired, if the historical target value of the index is determined not to be updated, whether other indexes are stable or not is determined based on the accumulated prediction error of other indexes in the period.

In practice, if the measured value of the period is not stable or reliable, the historical target value of the index cannot be updated based on the measured value of the period.

Because the data of different indexes have regular complementarity, whether other indexes are stable or not is determined based on the accumulated prediction errors of other indexes in the period, and then the reason for causing the unstable or unreliable index data is determined based on the judgment result.

Step S1305: and if other indexes are stable, determining the influence information corresponding to the indexes.

For example, if other indexes are stable, the indexes are indicated that measurement abnormality may occur; based on this, it is necessary to determine influence information corresponding to the index.

The influence information corresponding to the index is a factor causing short-time data jump, such as short-time temporary control, short-time equipment abnormal period, short-time network transmission abnormality, sudden traffic accidents and the like.

In some optional embodiments, after determining that other indexes are stable, a notification of measurement abnormality may be sent to a relevant person, and the relevant person confirms the notification and receives influence information corresponding to the indexes entered by the relevant person.

An embodiment of the present application provides a ninth traffic information determining method, as shown in fig. 14, the method may include:

step S1401: historical target values of a plurality of indexes of the target area in each historical period of the historical cycle are determined.

Step S1402: for any time interval of the cycle, determining a predicted value of each index in the time interval based on a historical target value of each index in a target historical time interval; wherein the target history period is a history period corresponding to the period.

Step S1403: and determining the traffic information of the target area in the period based on the predicted values of all the indexes in each period of the period.

Step S1404: for any index, after the actual measurement value of the index in each period of the period is acquired, if the historical target value of the index is determined not to be updated, whether other indexes are stable or not is determined based on the accumulated prediction error of other indexes in the period.

The specific implementation of steps S1401 to S1404 can refer to the above embodiments, and are not described herein.

Step S1405: and if other indexes are unstable, determining classification information corresponding to the indexes.

For example, if other indexes are unstable, the measurement deviation of the index may occur; based on this, classification information corresponding to the index needs to be determined.

The classification information corresponding to the index is the traffic state change condition of date or time interval, mainly the traffic state change caused by human activities, the periodicity of external environment change and time interval.

Referring to table 2, the classification information includes four classification items:

TABLE 2

The primary classification items cover all dates and time of the year and are updated once a year;

the secondary classification items are conditions of traffic flow increase and the like in the meeting period caused by small-scale artificial activities such as market gathering and meeting activities and are updated according to the contracted custom dates;

the third-level classification item is a period when traffic state change or data cannot be collected occurs on a non-determined date;

the four-level classification item is the abnormal condition occurrence period.

In some optional embodiments, after determining that the other indexes are stable, a notification of measurement deviation may be sent to the relevant person, confirmed by the relevant person, and classification information corresponding to the indexes entered by the relevant person is received.

An embodiment of the present application provides a tenth traffic information determining method, as shown in fig. 15, where the method may include:

step S1501: historical target values of a plurality of indexes of the target area in each historical period of the historical cycle are determined.

Step S1502: for any time interval of the cycle, determining a predicted value of each index in the time interval based on a historical target value of each index in a target historical time interval; wherein the target history period is a history period corresponding to the period.

Step S1503: and determining the traffic information of the target area in the period based on the predicted values of all the indexes in each period of the period.

The embodiments of steps S1501 to S1503 can refer to the above embodiments, and are not described herein again.

Step S1504: for any index, after the measured value of the index in each time period of the period is obtained, if the accumulated prediction error of the other indexes in the period is smaller than a preset error, determining the influence information corresponding to the index.

As described above, the accumulated prediction error of the index in the present cycle represents the stability of the measured value of the index in the present cycle. If the accumulated prediction error of other indexes in the period is smaller than the preset error, the stability of the measured values of the other indexes in the period is high, and the historical change rule of the indexes is met.

For the determination of the accumulated prediction error, reference may be made to the above embodiments, which are not described herein again.

An eleventh traffic information determining method provided in an embodiment of the present application, as shown in fig. 16, may include:

step S1601: historical target values of a plurality of indexes of the target area in each historical period of the historical cycle are determined.

Step S1602: for any time interval of the cycle, determining a predicted value of each index in the time interval based on a historical target value of each index in a target historical time interval; wherein the target history period is a history period corresponding to the period.

Step S1603: and determining the traffic information of the target area in the period based on the predicted values of all the indexes in each period of the period.

The specific implementation of steps S1601 to S1603 can refer to the above embodiments, and will not be described herein.

Step S1604: for any index, after the measured value of the index in each time period of the period is obtained, if the accumulated prediction error of the other indexes in the period is greater than or equal to the preset error, the classification information corresponding to the index is determined.

As described above, the accumulated prediction error of the index in the present cycle represents the stability of the measured value of the index in the present cycle. If the accumulated prediction error of other indexes in the period is greater than or equal to the preset error, the stability of the measured values of the other indexes in the period is low, and the history change rule of the indexes is not met.

As shown in fig. 17, based on the same inventive concept, the present embodiment provides a first traffic information determining apparatus 1700, including:

a target value determination module 1701 for determining historical target values of a plurality of indexes of the target area in each history period of the history cycle;

a predicted value determining module 1702, configured to determine, for any time period of the present cycle, a predicted value of each indicator in the time period based on a historical target value of each indicator in a target historical time period; wherein the target historical time period is a historical time period corresponding to the time period;

and a traffic information determining module 1703, configured to determine traffic information of the target area in the present cycle based on predicted values of all the indicators in each time period of the present cycle.

Referring to fig. 18, in some alternative embodiments, the present application provides a second traffic information determining apparatus 1800, which further includes an updating module 1704, on the basis of the traffic information determining apparatus 1700, for:

for any index, after an actual measurement value of the index in each period of the cycle is acquired, whether to update a historical target value of the index is determined based on a predicted value and an actual measurement value of the index in each period of the cycle.

In some optional embodiments, the update module 1704 is specifically configured to:

if the accumulated prediction error of the index in the period is smaller than the preset error, updating the historical target value of the index based on the measured value of the index in each period of the period; or

In some alternative embodiments, the updating module 1704 is specifically configured to:

for any time period in the period, if the deviation of the predicted trend value of the index relative to the actual trend value in the time period is greater than or equal to the preset trend deviation, replacing the measured value of the index in the time period with the predicted value of the index in the time period; or

And if the deviation of the predicted trend value of the index relative to the actual trend value in the time period is smaller than the preset trend deviation, not adjusting the measured value of the index in the time period.

Referring to fig. 19, in some alternative embodiments, the present application provides a third traffic information determining apparatus 1900, which further includes an abnormality determining module 1905, configured to, based on the traffic information determining apparatus 1800:

if the historical target value of the index is not updated, determining whether other indexes are stable or not based on the accumulated prediction errors of other indexes in the period;

And if other indexes are unstable, determining the classification information corresponding to the indexes.

In some optional embodiments, the anomaly determination module 1905 is specifically configured to:

if the accumulated prediction error of the other indexes in the period is smaller than the preset error, determining that the other indexes are stable; or alternatively

Since the apparatus is the apparatus in the method in the embodiment of the present application, and the principle of the apparatus for solving the problem is similar to that of the method, the implementation of the apparatus may refer to the implementation of the method, and repeated details are not repeated.

As shown in fig. 20, based on the same inventive concept, an embodiment of the present application provides an electronic device 2000, including: a processor 2001 and memory 2002;

the memory 2002 may be a volatile memory (volatile memory), such as a random-access memory (RAM); the memory 2002 may also be a non-volatile memory (non-volatile memory), such as a read-only memory (rom), a flash memory (flash memory), a hard disk (HDD) or a solid-state drive (SSD); or the memory 2002 is any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer, but is not limited to such. The memory 2002 may be a combination of the above.

The processor 2001 may include one or more Central Processing Units (CPUs), graphics Processing Units (GPUs), or digital Processing units (dsps), among others.

The specific connection medium between the memory 2002 and the processor 2001 is not limited in this embodiment. In fig. 20, the memory 2002 and the processor 2001 are connected by a bus 2003, the bus 2003 is indicated by a thick line in fig. 20, and the bus 2003 may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, only one thick line is shown in FIG. 20, but this is not intended to represent only one bus or type of bus.

Wherein the memory 2002 stores program code that, when executed by the processor 2001, causes the processor 2001 to perform the following:

aiming at any time interval of the period, determining a predicted value of each index in the time interval based on a historical target value of each index in a target historical time interval; wherein the target historical time period is a historical time period corresponding to the time period;

and determining the traffic information of the target area in the period based on the predicted values of all the indexes in all the time periods of the period.

In some optional embodiments, after determining the traffic information of the target area in the present period, the processor 2001 further performs:

In some alternative embodiments, the processor 2001 performs in particular:

determining the accumulated prediction error of the index in the period based on the deviation of the predicted value of the index relative to the measured value in each time period of the period;

if the accumulated prediction error of the index in the period is smaller than a preset error, updating the historical target value of the index based on the measured value of the index in each period of the period; or

In some alternative embodiments, the processor 2001 performs in particular:

if the accumulated trend deviation is smaller than the preset trend deviation, adjusting the measured value of the time period based on the predicted value of the index in at least one time period of the period, and updating the historical target value of the index based on the adjusted value; or

In some alternative embodiments, the processor 2001 performs in particular:

In some alternative embodiments, if the historical target value of the index is not updated, the processor 2001 further performs:

if other indexes are stable, determining influence information corresponding to the indexes; or

In some alternative embodiments, the processor 2001 performs in particular:

Since the electronic device is an electronic device for executing the method in the embodiment of the present application, and the principle of the electronic device for solving the problem is similar to that of the method, reference may be made to the implementation of the method for the implementation of the electronic device, and repeated details are not described again.

An embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored, and the program, when executed by a processor, implements the steps of the above-mentioned traffic information determination method. The readable storage medium may be a nonvolatile readable storage medium, among others.

The present application is described above with reference to block diagrams and/or flowchart illustrations of methods, apparatus (systems) and/or computer program products according to embodiments of the application. It will be understood that one block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, and/or other programmable apparatus to produce a machine, such that the instructions, which execute via the processor of the computer and/or other programmable apparatus, create means for implementing the functions/acts specified in the block diagrams and/or flowchart block or blocks.

Accordingly, the subject application may also be embodied in hardware and/or in software (including firmware, resident software, micro-code, etc.). Furthermore, the present application may take the form of a computer program product on a computer-usable or computer-readable storage medium having computer-usable or computer-readable program code embodied in the medium for use by or in connection with an instruction execution system. In the context of this application, a computer-usable or computer-readable medium may be any medium that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.

While the preferred embodiments of the present application have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all alterations and modifications as fall within the scope of the application.

It will be apparent to those skilled in the art that various changes and modifications may be made in the present application without departing from the spirit and scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include such modifications and variations as well.

Claims

1. A method for determining traffic information, the method comprising:

2. The method of claim 1, wherein determining that the target area is subsequent to the traffic information of the current period further comprises:

3. The method according to claim 2, wherein determining whether to update the historical target value of the index based on the predicted value and the measured value of the index in each period of the cycle comprises:

4. The method of claim 3, wherein determining whether to update the historical target value of the metric based on the cumulative trend deviation comprises:

5. The method according to claim 4, wherein adjusting the measured value of at least one time segment of the cycle based on the predicted value of the indicator in the time segment comprises:

6. The method according to any one of claims 3 to 5, wherein if the historical target value of the index is not updated, the method further comprises:

7. The method of claim 6, wherein determining whether the other indicators are stable based on accumulated prediction errors of the other indicators during the period comprises:

8. An electronic device, comprising a communication unit and a processor;

the processor is used for determining historical target values of a plurality of indexes of the target area in each historical period of the historical cycle; for any time interval of the cycle, determining a predicted value of each index in the time interval based on a historical target value of each index in a target historical time interval; wherein the target historical time period is a historical time period corresponding to the time period; and determining the traffic information of the target area in the period based on the predicted values of all the indexes in each period of the period.

9. The electronic device of claim 8, wherein after determining that the target area is traffic information of the current period, the processor is further configured to:

10. The electronic device of claim 9, wherein the processor is specifically configured to:

And if the accumulated prediction error of the index in the period is greater than or equal to a preset error, determining the accumulated trend deviation of the index in the period based on the deviation of the prediction trend value of the index relative to the actual trend value in each period of the period, and determining whether to update the historical target value of the index based on the accumulated trend deviation.