A method, device and equipment for calculating the correlation degree of traffic events

Abstract

The present invention provides a method, device and equipment for calculating the correlation of traffic events, belonging to the field of data processing technology. The method includes determining a first event and a second event that is associated with the first event; obtaining first event information of the first event and second event information of the second event; calculating the correlation between the first event and the second event based on the first event information and the second event information; the first event information includes at least one of the following: the type of the first event, the occurrence time of the first event, the duration of the first event, the average speed of the first road section where the first event occurs, the average flow of the first road section, the slipperiness of the first road section and the visibility of the first road section; the second event information includes at least one of the following: the event type and duration of the second event. The scheme of the present invention can quantitatively calculate the correlation between traffic events.

Description

Technical Field

[0001] The present invention belongs to the technical field of data processing, and in particular relates to a method, device and equipment for calculating the correlation degree of traffic events. Background Art

[0002] With the increase in the density of expressway networks, the number and severity of expressway traffic accidents and secondary accidents caused by traffic accidents are also increasing. Regarding the correlation analysis of major events and secondary events in traffic accidents, existing studies are based on the time-space threshold method. Whether it is a dynamic time-space threshold or a static time-space threshold, it only analyzes from the perspective of time and space. The accuracy of the qualitative analysis of the correlation between major events and secondary events is low, and there is a lack of quantitative calculation of the correlation between major events and secondary events. Summary of the invention

[0003] The embodiments of the present invention provide a method, device and equipment for calculating the correlation degree of traffic events, which solve the problem of lack of quantitative calculation of the correlation degree between events in the prior art.

[0004] In a first aspect, an embodiment of the present invention provides a method for calculating a traffic event correlation, comprising:

[0005] Determine a first event and a second event associated with the first event;

[0006] Acquire first event information of the first event and second event information of the second event;

[0007] Calculating the correlation between the first event and the second event according to the first event information and the second event information;

[0008] The first event information includes at least one of the following: the type of the first event, the time of occurrence of the first event, the duration of the first event, the average speed of the first road section where the first event occurs, the average traffic volume of the first road section, the slipperiness of the first road section, and the visibility of the first road section; the second event information includes at least one of the following: the event type and duration of the second event.

[0009] Further, the determining of the first event and the second event associated with the first event includes:

[0010] Determine the first event, and obtain first data of the first event, where the first data includes an occurrence location, an occurrence time, and a duration of the first event;

[0011] Acquire a plurality of third events and second data of the third events, wherein the second data includes an occurrence location and an occurrence time of the third events;

[0012] The second event is determined according to the first data and the second data.

[0013] Further, determining the second event according to the first data and the second data includes:

[0014] Determine a target spatiotemporal threshold according to the first data, the target spatiotemporal threshold being used to indicate a time threshold from the occurrence time of the first event to a first preset time after the occurrence of the first event, and a spatial threshold from the occurrence location of the first event to a preset distance upstream of the occurrence location in the first road section;

[0015] According to the second data, a second event in the third event that occurs within the time threshold and the space threshold is determined.

[0016] Further, obtaining the second data of the third event includes:

[0017] Acquire third data of the third event from a database, wherein the third data includes an event type and a duration of the third event;

[0018] Filter the third event according to the third data, and determine the second data corresponding to the filtered third event;

[0019] The third event that passes the screening is an event whose duration is greater than or equal to a preset time lower limit, and / or whose event type is a preset event type.

[0020] Further, determining the target spatiotemporal threshold according to the first data includes:

[0021] Determine a first spatiotemporal threshold according to the first data;

[0022] determining, based on the first spatiotemporal threshold, a first number of the second events corresponding to the first spatiotemporal threshold;

[0023] reducing the first space-time threshold to obtain a second space-time threshold;

[0024] determining, according to the second spatiotemporal threshold, a second number of the second events corresponding to the second spatiotemporal threshold;

[0025] If the second number is less than or equal to a preset ratio of the first number, the first spatiotemporal threshold is the target spatiotemporal threshold;

[0026] Alternatively, if the second number is greater than a preset ratio of the first number, the second spatiotemporal threshold continues to be reduced until the number of second events corresponding to the reduced spatiotemporal threshold is less than or equal to a preset ratio of the first number.

[0027] Furthermore, before calculating the correlation between the first event and the second event according to the first event information and the second event information, the method further includes:

[0028] Dividing the numerical features in the first event information and the second event information into numerical ranges, converting the numerical features into type features, and obtaining the first event information and the second event information that are all type features;

[0029] The numerical features include at least one of the following: the occurrence time of the first event, the duration of the first event, the average speed of the first road section, the average flow rate of the first road section, the slipperiness of the first road section, the visibility of the first road section and the duration of the second event.

[0030] Further, the calculating the correlation between the first event and the second event according to the first event information and the second event information includes:

[0031] According to each event feature in the first event information and the second event information, determining a plurality of frequent item sets corresponding to one of the event features;

[0032] According to each of the 1 frequent item sets, determine N frequent item sets and K frequent item sets by using the association rule mining algorithm, where N and K are both integers greater than 1, and K is greater than N;

[0033] Calculating the first support of the N frequent item sets and the second support of the K frequent item sets;

[0034] The quotient of the second support and the first support is the correlation between the first event and the second event;

[0035] The N frequent item sets are item sets about the first event information, and the K frequent item sets are item sets about the first event information and the second event information.

[0036] Further, the N frequent item sets are 7 frequent item sets, and the K frequent item sets are 9 frequent item sets.

[0037] In a second aspect, an embodiment of the present invention provides a traffic event correlation calculation device, comprising: a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the traffic event correlation calculation method described above are implemented.

[0038] In a third aspect, an embodiment of the present invention provides a traffic event correlation calculation device, comprising:

[0039] A determination module, used to determine a first event and a second event associated with the first event;

[0040] An acquisition module, used to acquire first event information of the first event and second event information of the second event;

[0041] a calculation module, configured to calculate a correlation between the first event and the second event according to the first event information and the second event information;

[0042] The first event information includes at least one of the following: the type of the first event, the time of occurrence of the first event, the duration of the first event, the average speed of the first road section where the first event occurs, the average traffic volume of the first road section, the slipperiness of the first road section, and the visibility of the first road section; the second event information includes at least one of the following: the event type and duration of the second event.

[0043] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method for calculating the degree of correlation of traffic events as described above.

[0044] The beneficial effects of the above technical solution of the present invention are:

[0045] The method for calculating the correlation degree of traffic events in the embodiment of the present invention determines a second event that is associated with a first event, and calculates the correlation degree between the first event and the second event by obtaining the first event information of the first event and the second event information of the second event. The scheme of the present invention comprehensively considers the weather factors when the first event occurs, the event itself of the first event, and the road traffic conditions, and can quantitatively calculate the correlation degree between events that are associated. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 A schematic diagram showing a method for determining a spatiotemporal threshold in the prior art;

[0047] Figure 2 A schematic diagram showing the steps of a method for calculating a traffic event correlation degree according to an embodiment of the present invention;

[0048] Figure 3 A logical schematic diagram showing an association rule mining method according to an embodiment of the present invention;

[0049] Figure 4 A logical schematic diagram showing a method for calculating the degree of association between a first event and a second event using a deep mining association rule algorithm according to an embodiment of the present invention;

[0050] Figure 5 A schematic diagram showing the steps of a method for calculating the degree of relevance of traffic events according to another embodiment of the present invention;

[0051] Figure 6 A schematic diagram showing the structure of a traffic event correlation calculation device according to an embodiment of the present invention;

[0052] Figure 7 A schematic diagram showing the structure of a traffic event correlation degree calculation device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0053] In order to make the technical problems, technical solutions and advantages to be solved by the present invention clearer, the following will be described in detail in conjunction with the accompanying drawings and specific embodiments. In the following description, specific details such as specific configurations and components are provided only to help fully understand the embodiments of the present invention. Therefore, it should be clear to those skilled in the art that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present invention. In addition, for clarity and brevity, the description of known functions and structures is omitted.

[0054] It should be understood that the references to "one embodiment" or "an embodiment" throughout the specification mean that the specific features, structures, or characteristics associated with the embodiment are included in at least one embodiment of the present invention. Therefore, the references to "in one embodiment" or "in an embodiment" appearing throughout the specification do not necessarily refer to the same embodiment. In addition, these specific features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0055] In various embodiments of the present invention, it should be understood that the size of the serial numbers of the following processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0056] Additionally, the terms "system" and "network" are often used interchangeably herein.

[0057] In the embodiments provided in the present application, it should be understood that "B corresponding to A" means that B is associated with A, and B can be determined according to A. However, it should also be understood that determining B according to A does not mean determining B only according to A, and B can also be determined according to A and / or other information.

[0058] When describing the embodiments of the present invention, some concepts used in the following description are first explained.

[0059] If one event is linked to the occurrence of another event, the first event is called the primary event and the event that is at least partially caused by the primary event is called the secondary event.

[0060] In the prior art, the relevance of most events is determined by the static spatiotemporal threshold range, that is, if a secondary event is within a certain time and space range of the main event, the two events are considered to be related. As time changes, the scope of event impact is also constantly changing, but the static spatiotemporal threshold cannot be adjusted in a timely manner, resulting in some unrelated events being determined as related events. Alternatively, a dynamic spatiotemporal threshold method is used to determine whether two traffic events are related. The dynamic spatiotemporal threshold is obtained by fitting the curve to complete the data set based on the partial incomplete data collected by the monitoring equipment to obtain the dynamic spatiotemporal threshold change curve. Finally, the events that meet the dynamic spatiotemporal threshold are considered to be secondary events.

[0061] like Figure 1 As shown in the figure, after a major event occurs at a certain time and place, events A, B, C, D, E, and F also occur within a certain range at this moment. The horizontal axis represents the time after the major event occurs, and the vertical axis represents the growth of the queue starting from the location where the major event occurs. The dotted line represents the static spatiotemporal threshold, and the solid line represents the actual dynamic spatiotemporal threshold. If the static spatiotemporal threshold method is used, events A, B, and C are related events; if the actual dynamic spatiotemporal threshold is fitted, then A, C, and E are related events. It can be seen that there are certain differences in the results determined by different methods, and there is still room for improvement in accuracy.

[0062] Furthermore, for the correlation between the primary event and the secondary event, the only factors considered are the time and location conditions of the event, and the accuracy of the correlation calculation is low.

[0063] First embodiment

[0064] like Figure 2 As shown, an embodiment of the present invention provides a method for calculating the correlation degree of traffic events, comprising the following steps:

[0065] Step 201: determine a first event and a second event associated with the first event.

[0066] That is, the first event is a primary event, and the second event is a secondary event.

[0067] Optionally, the determining a first event and a second event associated with the first event includes:

[0068] Determine the first event, and obtain first data of the first event, where the first data includes an occurrence location, an occurrence time, and a duration of the first event;

[0069] Acquire a plurality of third events and second data of the third events, wherein the second data includes an occurrence location and an occurrence time of the third events;

[0070] The second event is determined according to the first data and the second data.

[0071] Specifically, the first data is obtained from a database, and the database stores data corresponding to a plurality of events.

[0072] Optionally, the first data and the second data are obtained from a database, and the third event may be any event.

[0073] Step 202, obtaining first event information of the first event and second event information of the second event;

[0074] The first event information includes at least one of the following: the type of the first event, the time of occurrence of the first event, the duration of the first event, the average speed of the first road section where the first event occurs, the average traffic volume of the first road section, the slipperiness of the first road section, and the visibility of the first road section; the second event information includes at least one of the following: the event type and duration of the second event.

[0075] In the solution of the embodiment of the present invention, the first event information includes multiple event features, and the event data is analyzed from multiple angles, including the event itself: event type, event occurrence time, event duration, event location; weather factors: ground slipperiness of the first road section, visibility of the first road section; traffic conditions: average speed and average traffic volume of the first road section.

[0076] Optionally, the duration of the first event can be understood as the duration of the first event.

[0077] Specifically, the average speed of the first road section may be understood as the average speed of the first road section within a second preset time after the first event occurs;

[0078] The average flow rate of the first road section may be understood as the average flow rate of the first road section within a third preset time after the first event occurs;

[0079] The slipperiness of the first road section may be understood as the slipperiness of the first road section within a fourth preset time after the first event occurs;

[0080] The visibility of the first road section may be understood as the visibility of the first road section at a preset distance (for example, ten meters) within a fifth preset time after the occurrence of the first event;

[0081] The second preset time, the third preset time, the fourth preset time and the fifth preset time may be the same or different.

[0082] Step 203: Calculate the correlation between the first event and the second event based on the first event information and the second event information.

[0083] The solution of the embodiment of the present invention can analyze the traffic events that cause secondary events by calculating the correlation between the first event and the second event, and give the impact ratio of the first event on different second events; at the same time, it can predict the secondary events that will be caused by the event based on the event that has occurred, and determine the impact ratio of the event on different secondary events, thereby achieving the purpose of event warning.

[0084] The traffic event correlation calculation of the embodiment of the present invention comprehensively considers the weather factors when the first event occurs, the event itself of the first event, and the road traffic conditions, determines the second event that has a correlation relationship with the first event, and calculates the correlation between the first event and the second event by obtaining the first event information of the first event and the second event information of the second event. The scheme of the present invention can quantitatively calculate the correlation between events that have a correlation relationship.

[0085] Optionally, determining the second event according to the first data and the second data includes:

[0086] Determine a target spatiotemporal threshold according to the first data, the target spatiotemporal threshold being used to indicate a time threshold from the occurrence time of the first event to a first preset time after the occurrence of the first event, and a spatial threshold from the occurrence location of the first event to a preset distance upstream of the occurrence location in the first road section;

[0087] According to the second data, a second event in the third event that occurs within the time threshold and the space threshold is determined.

[0088] The solution of the embodiment of the present invention determines the target space-time threshold through the first data of the first event, thereby determining that the event occurring within the target space-time threshold is the second event that has an associated relationship with the first event.

[0089] Optionally, obtaining the second data of the third event includes:

[0090] Acquire third data of the third event from a database, wherein the third data includes an event type and a duration of the third event;

[0091] Filter the third event according to the third data, and determine the second data corresponding to the filtered third event;

[0092] The third event that passes the screening is an event whose duration is greater than or equal to a preset time lower limit, and / or whose event type is a preset event type.

[0093] Optionally, different types of events correspond to different preset time lower limits.

[0094] In one embodiment of the present invention, the types of the third events include abnormal lane change, ramp with a car, main road with a car, and other types of events with complex occurrence and high uncertainty; therefore, the event types of the third events are screened, and only events of preset event types such as traffic congestion, road construction, vehicle slowing, speeding, abnormal parking, and intrusion events are retained. The third events that pass the screening are events of the preset event type.

[0095] In one embodiment of the present invention, the third event includes events with a short duration, such as traffic jam events, speeding events, intrusion events, and vehicle reversing events that only last for a few seconds. There is no meaning in analyzing such events. Therefore, events with a short duration are eliminated. The third event that passes the screening is an event whose duration is greater than or equal to the preset time lower limit.

[0096] In one embodiment of the present invention, the event type and event duration of the third event are screened simultaneously, and the third event that passes the screening is an event whose event type is a preset event type and whose event duration is greater than a preset time lower limit.

[0097] In one embodiment of the present invention, as shown in Table 1, events whose duration is less than the corresponding preset time lower limit are eliminated for different event types.

[0098] Table 1

[0099] event Preset time limit Traffic congestion 5min ROAD WORK 30min SLOW 2min Speeding 2min Abnormal parking 3min Occupying the emergency lane 3min Break-in incident 1min Vehicle driving in the wrong direction 1min

[0100] Optionally, determining a target spatiotemporal threshold according to the first data includes:

[0101] Determine a first spatiotemporal threshold according to the first data;

[0102] determining, based on the first spatiotemporal threshold, a first number of the second events corresponding to the first spatiotemporal threshold;

[0103] reducing the first space-time threshold to obtain a second space-time threshold;

[0104] determining, according to the second spatiotemporal threshold, a second number of the second events corresponding to the second spatiotemporal threshold;

[0105] If the second number is less than or equal to a preset ratio of the first number, the first spatiotemporal threshold is the target spatiotemporal threshold;

[0106] Alternatively, if the second number is greater than a preset ratio of the first number, the second spatiotemporal threshold continues to be reduced until the number of second events corresponding to the reduced spatiotemporal threshold is less than or equal to a preset ratio of the first number.

[0107] Optionally, the reduction of the first spatiotemporal threshold can be understood as: shortening the time threshold corresponding to the first spatiotemporal threshold (for example, shortening the first preset time after the occurrence of the first event), and / or reducing the spatial threshold corresponding to the first spatiotemporal threshold (for example, shortening the preset distance upstream of the occurrence location of the first event in the first road section).

[0108] In one embodiment of the present invention, Figure 3 As shown,

[0109] Obtain event data of traffic events within a preset time period, and filter the event type and duration;

[0110] Extracting event features from the screened event data;

[0111] A spatiotemporal threshold of a first event a is pre-given, and a candidate set of second events b that meet the spatiotemporal threshold is determined; here, the number of the first events may be multiple;

[0112] Construct a candidate set, for example, {type of event a, time of occurrence of event a, duration of event a, average speed of the road section where event a is located, average flow of the road section where event a is located, slipperiness of the road section where event a is located, visibility of the road section where event a is located, type of event b, duration of event b}; here, the candidate set may be multiple, each candidate set includes event information of a first event, and event information of a second event corresponding to the first event;

[0113] Process event features and convert numerical features into type features (enumeration class);

[0114] Calculating the correlation between the first events and the second events corresponding thereto;

[0115] Here, narrowing the space-time threshold can be understood as narrowing the space-time threshold for multiple first events, calculating the correlation between each first event and the second event corresponding to the first event, and determining the number of associated information between each first event with a correlation greater than a preset threshold and the second event corresponding to the first event through an in-depth mining method using an association algorithm, and narrowing the space-time threshold based on the number of associated information.

[0116] Specifically, the first spatiotemporal threshold is reduced by 80% to obtain a second spatiotemporal threshold;

[0117] If the amount of associated information corresponding to the second spatiotemporal threshold is less than or equal to 90% of the amount of associated information corresponding to the first spatiotemporal threshold, the range division of the first spatiotemporal threshold is more accurate, that is, the reduction of the spatiotemporal threshold has a greater impact on the second event;

[0118] If the number of associated information corresponding to the second space-time threshold is greater than 90% of the number of associated information corresponding to the first space-time threshold, the range of the first space-time threshold is too large, that is, the reduction of the space-time threshold has little effect on the second event, and it is easy to bring in a second event with a lower correlation with the first event; then continue to reduce the second space-time threshold until the number of associated information corresponding to the reduced space-time threshold is less than or equal to 90% of the number of associated information corresponding to the first space-time threshold, or until the number of associated information corresponding to the Mth space-time threshold after the reduction is less than or equal to 90% of the number of associated information corresponding to the M-1th space-time threshold.

[0119] The traffic event correlation calculation method of the embodiment of the present invention optimizes the division of the time-space threshold through iterative calculation, and can accurately divide the target time-space threshold, thereby screening out the second event that has a relatively large correlation with the first event, and can eliminate the interference events in the second event that have no correlation with the first event. The accuracy of determining the correlation between events is improved, and the influence of noise events on the correlation analysis between events is weakened, the unnecessary complexity in the correlation calculation is reduced, the cache space is increased, and the calculation speed is accelerated.

[0120] In one embodiment of the present invention, the correlation between the first event and the second event is calculated by a deep mining association rule algorithm.

[0121] Optionally, before calculating the correlation between the first event and the second event according to the first event information and the second event information, the method further includes:

[0122] Dividing the numerical features in the first event information and the second event information into numerical ranges, converting the numerical features into type features, and obtaining the first event information and the second event information that are all type features;

[0123] The numerical features include at least one of the following: the occurrence time of the first event, the duration of the first event, the average speed of the first road section, the average flow rate of the first road section, the slipperiness of the first road section, the visibility of the first road section and the duration of the second event.

[0124] To calculate the degree of association through the deep mining association rule algorithm, it is necessary to first construct the event features of the first event information and the second event information to construct the data format. Among them, the event type belongs to the type feature, and the event occurrence time, duration, average speed, average flow, slipperiness, and visibility of the road section belong to the numerical features. The numerical features need to be classified and converted into type features.

[0125] The solution of the embodiment of the present invention can realize quantitative calculation of the correlation between the first event and the second event by converting the numerical features in the first event information and the second event information.

[0126] In one embodiment of the present invention, as shown in Table 2, the numerical feature can be converted into a type feature by dividing the numerical range.

[0127] Table 2

[0128]

[0129] Optionally, calculating the correlation between the first event and the second event according to the first event information and the second event information includes:

[0130] According to each event feature in the first event information and the second event information, determining a plurality of frequent item sets corresponding to one of the event features;

[0131] According to each of the 1 frequent item sets, determine N frequent item sets and K frequent item sets by using the association rule mining algorithm, where N and K are both integers greater than 1, and K is greater than N;

[0132] Calculating the first support of the N frequent item sets and the second support of the K frequent item sets;

[0133] The quotient of the second support and the first support is the correlation between the first event and the second event;

[0134] The N frequent item sets are item sets about the first event information, and the K frequent item sets are item sets about the first event information and the second event information.

[0135] Specifically, the quotient of the first support and the second support can be understood as the conditional probability that the occurrence of the first event leads to the occurrence of the second event.

[0136] In one embodiment of the present invention, if the correlation between the first event and the second event is greater than 60%, it is determined that the second event is caused by the first event.

[0137] Optionally, the N frequent item sets are 7 frequent item sets, and the K frequent item sets are 9 frequent item sets.

[0138] It should be noted that the main idea of ​​the deep mining association rule algorithm is to generate candidate items and their support through connection, and then generate frequent item sets through pruning.

[0139] All non-empty subsets of frequent itemsets must be frequent itemsets. The probability that itemsets A and B occur simultaneously is called the support of the association rule, and the formula is:

[0140]

[0141] Among them, σ(A∪B) represents the number of events in which item sets A and B occur simultaneously, and n represents the number of all events.

[0142] The minimum support is a threshold for measuring support, indicating the minimum importance of the item set in a statistical sense. If item set A occurs, the probability that item set B occurs is the confidence of the association rule, and the formula is:

[0143]

[0144] Among them, σ(A) represents the number of events that occur in item set A.

[0145] The minimum confidence is a threshold for measuring confidence, indicating the minimum reliability of the association rule.

[0146] In one embodiment of the present invention, the event features of the event information of the first event (event a) and the second event (event b) can be stored in a candidate set, for example: {event a type, event a occurrence time, event a duration, average speed of the road section where event a is located, average flow of the road section where event a is located, slipperiness of the road section where event a is located, visibility of the road section where event a is located, event b type, event b duration}, and each element in the candidate set can be a frequent item set. It should be noted that the frequent item set is a frequent item set whose support is greater than the minimum support.

[0147] like Figure 4 As shown, a method for calculating the relevance of traffic events according to an embodiment of the present invention is as follows:

[0148] extracting event features of the first event information and the second event information, and taking the event features as input in the form of a candidate set;

[0149] For a candidate set consisting of one of the event features, support is determined, and the candidate set with support greater than the minimum support is the one frequent item set;

[0150] Combine the frequent item sets in pairs and traverse to obtain the union. Since all non-empty subsets of frequent item sets must be frequent item sets, all the two candidate sets obtained by the union are two frequent item sets.

[0151] Sort the first item of the two frequent item sets and traverse and combine them in pairs. If there is an identical item, take the union of the two frequent item sets to form a three-item candidate set. Since all non-empty subsets of frequent item sets must be frequent item sets, if any two subsets of the three-item candidate set are frequent item sets, then the three-item candidate set is a three-item frequent item set.

[0152] In the same way, k frequent item sets are obtained. There are nine event features in the present invention {type of event a, time of occurrence of event a, duration of event a, average speed of the road section where event a is located, average flow of the road section where event a is located, slipperiness of the road section where event a is located, visibility of the road section where event a is located, type of event b, duration of event b}, among which there are seven important features of the main event a, so 7 frequent item sets and support containing only the features of event a, and 9 frequent item sets and support containing both event a and event b are taken;

[0153] The 7 frequent itemsets containing only the features of event a and the 9 frequent itemsets containing event pairs a and b are traversed in pairs. If the 7 frequent itemsets are subsets of the 9 frequent itemsets, the support of the 9 frequent itemsets is divided by the support of the 7 frequent itemsets. The quotient obtained represents the probability of event b occurring when event a occurs, that is, the correlation between event pairs a and b.

[0154] It should be noted that the deep mining association rule algorithm of the embodiment of the present invention only calculates the support of the 7 frequent item sets containing only the features of event a and the 9 frequent item sets containing event pairs a and b, omits the calculation of the support of each frequent item set, and optimizes the deep mining association rule algorithm.

[0155] The method for calculating the correlation of traffic events in an embodiment of the present invention can analyze the traffic events that cause secondary events by calculating the correlation between the first event and the second event, and give the proportion of the impact of the first event on different second events; at the same time, it can predict the secondary events that will be caused by the event based on the event that has occurred, and determine the proportion of the impact of the event on different secondary events, thereby achieving the purpose of event warning.

[0156] In one embodiment of the present invention, a correlation information database is established by repeatedly performing the traffic event correlation calculation method, and the correlation degree and event information between each first event and second event whose correlation degree is greater than a preset threshold are saved in the correlation information database.

[0157] like Figure 5 As shown, according to the association information library, when judging whether two events are associated:

[0158] The database is queried through the event ID of the primary event a and the event ID of the secondary event b to obtain the event information of the two events;

[0159] Determine whether the primary event and secondary event meet the requirements of the time and space threshold;

[0160] If the primary event and the secondary event meet the requirements of the temporal and spatial thresholds, a data set including the event information of the primary event and the secondary event is further constructed;

[0161] The association information database is queried to determine whether the primary event and the secondary event match the information in the association information database, thereby determining the degree of association between the primary event and the secondary event.

[0162] Second embodiment

[0163] like Figure 6 As shown, an embodiment of the present invention provides a traffic event correlation calculation device 600, comprising:

[0164] A determination module 601 is used to determine a first event and a second event associated with the first event;

[0165] An acquisition module 602 is used to acquire first event information of the first event and second event information of the second event;

[0166] A calculation module 603, configured to calculate the correlation between the first event and the second event according to the first event information and the second event information;

[0167] The first event information includes at least one of the following: the type of the first event, the time of occurrence of the first event, the duration of the first event, the average speed of the first road section where the first event occurs, the average traffic volume of the first road section, the slipperiness of the first road section, and the visibility of the first road section; the second event information includes at least one of the following: the event type and duration of the second event.

[0168] The traffic event correlation calculation device of the embodiment of the present invention determines a second event that is correlated with a first event, and calculates the correlation between the first event and the second event by obtaining first event information of the first event and second event information of the second event. The scheme of the present invention can quantitatively calculate the correlation between events that are correlated.

[0169] Optionally, the determining module is further used to:

[0170] Determine the first event, and obtain first data of the first event, where the first data includes an occurrence location, an occurrence time, and a duration of the first event;

[0171] Acquire a plurality of third events and second data of the third events, wherein the second data includes an occurrence location and an occurrence time of the third events;

[0172] The second event is determined according to the first data and the second data.

[0173] Optionally, the determining module is further used to:

[0174] Determine a target spatiotemporal threshold according to the first data, the target spatiotemporal threshold being used to indicate a time threshold from the occurrence time of the first event to a first preset time after the occurrence of the first event, and a spatial threshold from the occurrence location of the first event to a preset distance upstream of the occurrence location in the first road section;

[0175] According to the second data, a second event in the third event that occurs within the time threshold and the space threshold is determined.

[0176] Optionally, the determining module is further used to:

[0177] Determine a first spatiotemporal threshold according to the first data;

[0178] determining, based on the first spatiotemporal threshold, a first number of the second events corresponding to the first spatiotemporal threshold;

[0179] reducing the first space-time threshold to obtain a second space-time threshold;

[0180] determining, according to the second spatiotemporal threshold, a second number of the second events corresponding to the second spatiotemporal threshold;

[0181] If the second number is less than or equal to a preset ratio of the first number, the first spatiotemporal threshold is the target spatiotemporal threshold;

[0182] Alternatively, if the second number is greater than a preset ratio of the first number, the second spatiotemporal threshold continues to be reduced until the number of second events corresponding to the reduced spatiotemporal threshold is less than or equal to a preset ratio of the first number.

[0183] Optionally, the acquisition module is further used to:

[0184] Acquire third data of the third event from a database, wherein the third data includes an event type and a duration of the third event;

[0185] Filter the third event according to the third data, and determine the second data corresponding to the filtered third event;

[0186] The third event that passes the screening is an event whose duration is greater than or equal to a preset time lower limit, and / or whose event type is a preset event type.

[0187] Optionally, the computing module is further used for:

[0188] Dividing the numerical features in the first event information and the second event information into numerical ranges, converting the numerical features into type features, and obtaining the first event information and the second event information that are all type features;

[0189] The numerical features include at least one of the following: the occurrence time of the first event, the duration of the first event, the average speed of the first road section, the average flow rate of the first road section, the slipperiness of the first road section, the visibility of the first road section and the duration of the second event.

[0190] Optionally, the computing module is further used for:

[0191] According to each event feature in the first event information and the second event information, determining a plurality of frequent item sets corresponding to one of the event features;

[0192] According to each of the 1 frequent item sets, determine N frequent item sets and K frequent item sets by using the association rule mining algorithm, where N and K are both integers greater than 1, and K is greater than N;

[0193] Calculating the first support of the N frequent item sets and the second support of the K frequent item sets;

[0194] The quotient of the second support and the first support is the correlation between the first event and the second event;

[0195] The N frequent item sets are item sets about the first event information, and the K frequent item sets are item sets about the first event information and the second event information;

[0196] The N frequent item sets are 7 frequent item sets, and the K frequent item sets are 9 frequent item sets.

[0197] Third embodiment

[0198] In order to better achieve the above goals, Figure 7 As shown, the present invention also provides a traffic event correlation calculation device, including: a processor 700; and a memory 720 connected to the processor 700 through a bus interface, the memory 720 is used to store programs and data used by the processor 700 when performing operations, and the processor 700 calls and executes the programs and data stored in the memory 720.

[0199] Wherein, the transceiver 710 is connected to the bus interface and is used to receive and send data under the control of the processor 700;

[0200] The processor 700 is used to read the program in the memory 720 to execute the following steps:

[0201] Determine a first event and a second event associated with the first event;

[0202] The transceiver 710 is used for:

[0203] Acquire first event information of the first event and second event information of the second event;

[0204] Optionally, the processor 700 is further configured to: calculate a correlation between the first event and the second event according to the first event information and the second event information;

[0205] The first event information includes at least one of the following: the type of the first event, the time of occurrence of the first event, the duration of the first event, the average speed of the first road section where the first event occurs, the average traffic volume of the first road section, the slipperiness of the first road section, and the visibility of the first road section; the second event information includes at least one of the following: the event type and duration of the second event.

[0206] Among them, Figure 7In the embodiment, the bus architecture may include any number of interconnected buses and bridges, specifically one or more processors represented by the processor 700 and various circuits of the memory represented by the memory 720 are linked together. The bus architecture may also link together various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. The bus interface provides an interface. The transceiver 710 may be a plurality of components, namely, a transmitter and a transceiver, providing a unit for communicating with various other devices on a transmission medium. For different traffic event correlation calculation devices, the user interface 730 may also be an interface capable of externally and internally connecting required devices, and the connected devices include but are not limited to a keypad, a display, a speaker, a microphone, a joystick, and the like. The processor 700 is responsible for managing the bus architecture and general processing, and the memory 720 may store data used by the processor 700 when performing operations.

[0207] Optionally, the processor 700 is further configured to:

[0208] Determine the first event, and obtain first data of the first event, where the first data includes an occurrence location, an occurrence time, and a duration of the first event;

[0209] Acquire a plurality of third events and second data of the third events, wherein the second data includes an occurrence location and an occurrence time of the third events;

[0210] The second event is determined according to the first data and the second data.

[0211] Optionally, the processor 700 is further configured to:

[0212] Determine a target spatiotemporal threshold according to the first data, the target spatiotemporal threshold being used to indicate a time threshold from the occurrence time of the first event to a first preset time after the occurrence of the first event, and a spatial threshold from the occurrence location of the first event to a preset distance upstream of the occurrence location in the first road section;

[0213] According to the second data, a second event in the third event that occurs within the time threshold and the space threshold is determined.

[0214] Optionally, the transceiver 710 is used to:

[0215] Acquire third data of the third event from a database, wherein the third data includes an event type and a duration of the third event;

[0216] Filter the third event according to the third data, and determine the second data corresponding to the filtered third event;

[0217] The third event that passes the screening is an event whose duration is greater than or equal to a preset time lower limit, and / or whose event type is a preset event type.

[0218] Optionally, the processor 700 is further configured to:

[0219] Determine a first spatiotemporal threshold according to the first data;

[0220] determining, based on the first spatiotemporal threshold, a first number of the second events corresponding to the first spatiotemporal threshold;

[0221] reducing the first space-time threshold to obtain a second space-time threshold;

[0222] determining, according to the second spatiotemporal threshold, a second number of the second events corresponding to the second spatiotemporal threshold;

[0223] If the second number is less than or equal to a preset ratio of the first number, the first spatiotemporal threshold is the target spatiotemporal threshold;

[0224] Alternatively, if the second number is greater than a preset ratio of the first number, the second spatiotemporal threshold continues to be reduced until the number of second events corresponding to the reduced spatiotemporal threshold is less than or equal to a preset ratio of the first number.

[0225] Optionally, the processor 700 is further configured to:

[0226] Dividing the numerical features in the first event information and the second event information into numerical ranges, converting the numerical features into type features, and obtaining the first event information and the second event information that are all type features;

[0227] The numerical features include at least one of the following: the occurrence time of the first event, the duration of the first event, the average speed of the first road section, the average flow rate of the first road section, the slipperiness of the first road section, the visibility of the first road section and the duration of the second event.

[0228] Optionally, the processor 700 is further configured to:

[0229] According to each event feature in the first event information and the second event information, determining a plurality of frequent item sets corresponding to one of the event features;

[0230] According to each of the 1 frequent item sets, determine N frequent item sets and K frequent item sets by using the association rule mining algorithm, where N and K are both integers greater than 1, and K is greater than N;

[0231] Calculating the first support of the N frequent item sets and the second support of the K frequent item sets;

[0232] The quotient of the second support and the first support is the correlation between the first event and the second event;

[0233] The N frequent item sets are item sets about the first event information, and the K frequent item sets are item sets about the first event information and the second event information;

[0234] The N frequent item sets are 7 frequent item sets, and the K frequent item sets are 9 frequent item sets.

[0235] The traffic event correlation calculation device provided by the present invention determines a second event that is correlated with a first event, and calculates the correlation between the first event and the second event by acquiring first event information of the first event and second event information of the second event. The scheme of the present invention can quantitatively calculate the correlation between events that are correlated.

[0236] Those skilled in the art will understand that all or part of the steps to implement the above embodiments may be accomplished by hardware, or may be accomplished by instructing relevant hardware through a computer program, wherein the computer program includes instructions for executing part or all of the steps of the above method; and the computer program may be stored in a readable storage medium, and the storage medium may be any form of storage medium.

[0237] In addition, a specific embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, the steps of the method in the first embodiment described above are implemented. The same technical effect can be achieved, and to avoid repetition, it will not be described here.

[0238] In addition, it should be noted that in the apparatus and method of the present invention, it is obvious that each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent schemes of the present invention. Moreover, the steps of performing the above-mentioned series of processing can naturally be performed in chronological order according to the order of description, but it is not necessary to perform them in chronological order, and some steps can be performed in parallel or independently of each other. For those of ordinary skill in the art, it is understood that all or any steps or components of the method and apparatus of the present invention can be implemented in any computing device (including processors, storage media, etc.) or a network of computing devices in hardware, firmware, software or a combination thereof, which can be achieved by those of ordinary skill in the art using their basic programming skills after reading the description of the present invention.

[0239] Therefore, the purpose of the present invention can also be achieved by running a program or a group of programs on any computing device. The computing device can be a well-known general device. Therefore, the purpose of the present invention can also be achieved by simply providing a program product containing a program code that implements the method or device. That is to say, such a program product also constitutes the present invention, and the storage medium storing such a program product also constitutes the present invention. Obviously, the storage medium can be any well-known storage medium or any storage medium developed in the future. It should also be pointed out that in the device and method of the present invention, it is obvious that each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent schemes of the present invention. In addition, the steps of performing the above-mentioned series of processing can naturally be performed in chronological order according to the order of description, but it is not necessary to perform them in chronological order. Some steps can be performed in parallel or independently of each other.

[0240] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for calculating the correlation degree of traffic events, characterized in that: include: Determine a first event and a second event associated with the first event; Acquire first event information of the first event and second event information of the second event; Calculating the correlation between the first event and the second event according to the first event information and the second event information; The first event information includes at least one of the following: the type of the first event, the occurrence time of the first event, the duration of the first event, the average speed of the first road section where the first event occurs, the average flow rate of the first road section, the slipperiness of the first road section, and the visibility of the first road section; the second event information includes at least one of the following: the event type and duration of the second event; Acquire first data of the first event, where the first data includes an occurrence location, an occurrence time, and a duration of the first event; Determine a target spatiotemporal threshold according to the first data, the target spatiotemporal threshold being used to indicate a time threshold from the occurrence time of the first event to a first preset time after the occurrence of the first event, and a spatial threshold from the occurrence location of the first event to a preset distance upstream of the occurrence location in the first road section; Determine a first spatiotemporal threshold according to the first data; determining, based on the first spatiotemporal threshold, a first number of the second events corresponding to the first spatiotemporal threshold; reducing the first space-time threshold to obtain a second space-time threshold; determining, according to the second spatiotemporal threshold, a second number of the second events corresponding to the second spatiotemporal threshold; If the second number is less than or equal to a preset ratio of the first number, the first spatiotemporal threshold is the target spatiotemporal threshold; Alternatively, if the second number is greater than a preset ratio of the first number, the second spatiotemporal threshold continues to be reduced until the number of second events corresponding to the reduced spatiotemporal threshold is less than or equal to a preset ratio of the first number.

2. The method for calculating the degree of relevance of traffic events according to claim 1, characterized in that: The determining of a first event and a second event associated with the first event includes: Acquire a plurality of third events and second data of the third events, wherein the second data includes an occurrence location and an occurrence time of the third events; The second event is determined according to the first data and the second data.

3. The method for calculating the degree of correlation of traffic events according to claim 2, characterized in that: The determining the second event according to the first data and the second data includes: According to the second data, a second event in the third event that occurs within the time threshold and the space threshold is determined.

4. The method for calculating the degree of relevance of traffic events according to claim 2, characterized in that: The obtaining of second data of the third event includes: Acquire third data of the third event from a database, wherein the third data includes an event type and a duration of the third event; Filter the third event according to the third data, and determine the second data corresponding to the filtered third event; The third event that passes the screening is an event whose duration is greater than or equal to a preset time lower limit, and / or whose event type is a preset event type.

5. The method for calculating the degree of relevance of traffic events according to claim 1, characterized in that: Before calculating the correlation between the first event and the second event according to the first event information and the second event information, the method includes: Dividing the numerical features in the first event information and the second event information into numerical ranges, converting the numerical features into type features, and obtaining the first event information and the second event information that are all type features; The numerical features include at least one of the following: the occurrence time of the first event, the duration of the first event, the average speed of the first road section, the average flow rate of the first road section, the slipperiness of the first road section, the visibility of the first road section and the duration of the second event.

6. The method for calculating the degree of relevance of traffic events according to claim 1, characterized in that: The calculating the correlation between the first event and the second event according to the first event information and the second event information includes: According to each event feature in the first event information and the second event information, determining a plurality of frequent item sets corresponding to one of the event features; According to each of the 1 frequent item sets, determine N frequent item sets and K frequent item sets by using an association rule mining algorithm, where N and K are both integers greater than 1, and K is greater than N; Calculating the first support of the N frequent item sets and the second support of the K frequent item sets; The quotient of the second support and the first support is the correlation between the first event and the second event; The N frequent item sets are item sets about the first event information, and the K frequent item sets are item sets about the first event information and the second event information.

7. The method for calculating the degree of relevance of traffic events according to claim 6, characterized in that: The N frequent item sets are 7 frequent item sets, and the K frequent item sets are 9 frequent item sets.

8. A traffic event correlation calculation device, comprising: A transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method for calculating the degree of correlation of traffic events as described in any one of claims 1 to 7 when executing the computer program.

9. A traffic event correlation calculation device, characterized in that: include: A determination module, used to determine a first event and a second event associated with the first event; An acquisition module, used to acquire first event information of the first event and second event information of the second event; a calculation module, configured to calculate a correlation between the first event and the second event according to the first event information and the second event information; The first event information includes at least one of the following: the type of the first event, the occurrence time of the first event, the duration of the first event, the average speed of the first road section where the first event occurs, the average flow rate of the first road section, the slipperiness of the first road section, and the visibility of the first road section; the second event information includes at least one of the following: the event type and duration of the second event; The acquisition module is further used to acquire first data of the first event, where the first data includes an occurrence location, an occurrence time, and a duration of the first event; The determination module is further used to determine a target spatiotemporal threshold based on the first data, the target spatiotemporal threshold being used to indicate a time threshold from the occurrence time of the first event to a first preset time after the occurrence of the first event, and a spatial threshold from the occurrence location of the first event to a preset distance upstream of the occurrence location in the first road section; Determine a first spatiotemporal threshold according to the first data; determining, based on the first spatiotemporal threshold, a first number of the second events corresponding to the first spatiotemporal threshold; reducing the first space-time threshold to obtain a second space-time threshold; determining, according to the second spatiotemporal threshold, a second number of the second events corresponding to the second spatiotemporal threshold; If the second number is less than or equal to a preset ratio of the first number, the first spatiotemporal threshold is the target spatiotemporal threshold; Alternatively, if the second number is greater than a preset ratio of the first number, the second spatiotemporal threshold continues to be reduced until the number of second events corresponding to the reduced spatiotemporal threshold is less than or equal to a preset ratio of the first number.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for calculating the degree of relevance of traffic events as described in any one of claims 1 to 7 are implemented.

Images