WO2019079934A1

WO2019079934A1 - Traffic data processing method and server

Info

Publication number: WO2019079934A1
Application number: PCT/CN2017/107318
Authority: WO
Inventors: 阳光
Original assignee: 深圳配天智能技术研究院有限公司
Priority date: 2017-10-23
Filing date: 2017-10-23
Publication date: 2019-05-02
Also published as: CN110892738A; CN110892738B

Abstract

Disclosed are a traffic data processing method and a server, wherein same are used for improving the accuracy of data of a cloud database. The method comprises: acquiring target data of a target location, wherein the target data is traffic data collected by a vehicle-mounted client at the target location, and the target data comprises several pieces of sub-data; respectively matching each piece of sub-data in the target data with each piece of sub-data in first traffic data to determine the level of each piece of sub-data in the target data, wherein the first traffic data is traffic data, stored in a cloud database, of the target location, and each piece of sub-data in the first traffic data is data that has been classified; and updating the first traffic data according to the level of each piece of sub-data in the target data.

Description

Traffic data processing method and server

Technical field

The present invention relates to the field of communications, and in particular, to a method and a server for processing traffic data.

Background technique

The in-vehicle system collects data of the current vehicle through the visual system, and uploads data of the current vehicle to the cloud database for use by other vehicles as valid data. At this point, there are two problems:

(1) Is the data collected by the current vehicle correct?

(2) Different vehicles upload data to the cloud at different time points and at different angles. Which of the uploaded data is usable and which data is not used. Is the minority data correct or wrong?

In view of these problems, in the prior art, algorithms such as machine learning are generally used, and a large amount of sample data is generally used as a positive enhancement, that is, the more times the data appears, the higher the correctness of the data, and the data is Will be saved, and when a certain data in the data changes, the changed data will be discarded as invalid data.

However, when the traffic sign or the building changes, for example, one traffic sign of a certain place is replaced with another traffic sign, and a traffic sign or building is newly appeared. According to the prior art, a large amount of sample data is added as a positive direction in order to delete the newly appearing traffic sign or the replaced traffic sign or the data corresponding to the newly appearing building. However, the newly appearing traffic sign or the replaced traffic sign or the data corresponding to the newly appearing building is exactly the data that needs to be sent to the cloud database for updating, so there is no way to maintain the traffic data in the road section.

Summary of the invention

The embodiment of the invention provides a method for processing traffic data and a server for ensuring the correct rate of data in the cloud database.

A first aspect of the embodiments of the present invention provides a method for processing traffic data, including:

Obtaining target data of a target location, where the target data is collected by the in-vehicle client at the target location Set of traffic data, the target data includes a plurality of sub-data;

Matching each sub-data in the target data with each sub-data in the first traffic data to determine a level of each sub-data in the target data, where the first traffic data is stored in a cloud database Traffic data of the target location, and each subdata in the first traffic data is data that has been classified;

The first traffic data is updated according to a level of each sub data in the target data.

In conjunction with the first aspect, in a first possible implementation manner of the first aspect, the sub-data in the target data is matched with each sub-data in the first traffic data to determine the target The levels of each subdata in the data include:

Matching each sub-data in the target data with each sub-data in the first traffic data to determine a matching degree between each sub-data in the target data and each sub-data in the first traffic data;

And determining the level of each sub-data in the target data according to the matching degree of each sub-data with each sub-data in the first traffic data.

A second aspect of the embodiments of the present invention provides a server, including:

a central processing unit, a storage medium, and an input and output interface;

The storage medium stores a cloud database and program code, and the central processor calls and executes the program code for:

Obtaining target data of the target location, where the target data is traffic data collected by the in-vehicle client at the target location, where the target data includes several sub-data;

In the technical solution provided by the embodiment of the present invention, when the cloud server needs to update the traffic data of the target location or receives the target data of the target location uploaded by the vehicle, the target data of the target location may be acquired, and the target data is obtained. Each sub-data and each sub-number in the first traffic data The matching is performed to determine the level of each sub-data in the target data, and the traffic data of the target location in the cloud database is updated according to the level of each sub-data in the target data. It can be seen that when new data is added to the cloud database, the newly added data is automatically classified according to the graded data in the existing database, thereby automatically maintaining data in the cloud database and improving the cloud database. The correct rate of data.

DRAWINGS

1 is a schematic diagram of an embodiment of a method for processing traffic data according to an embodiment of the present invention;

2 is a schematic diagram of another embodiment of a method for processing traffic data according to an embodiment of the present invention;

FIG. 3 is a schematic structural diagram of a hardware of a server according to an embodiment of the present invention.

Detailed ways

The technical solutions in the embodiments of the present invention are clearly and completely described in the following with reference to the accompanying drawings in the embodiments of the present invention. It is obvious that the described embodiments are only a part of the embodiments of the present invention, but not all embodiments.

The terms "first", "second", "third" and "fourth", etc. (if present) in the specification and claims of the present invention and the above figures are used to distinguish similar objects without having to use To describe a specific order or order. It is to be understood that the data so used may be interchanged where appropriate so that the embodiments described herein can be implemented in a sequence other than what is illustrated or described herein. In addition, the terms "comprises" and "comprises" and "the" and "the" are intended to cover a non-exclusive inclusion, for example, a process, method, system, product, or device that comprises a series of steps or units is not necessarily limited to Those steps or units may include other steps or units not explicitly listed or inherent to such processes, methods, products or devices.

Referring to FIG. 1, an embodiment of a method for processing traffic data in an embodiment of the present invention includes:

101. Obtain target data of the target location.

In this embodiment, when the cloud server needs to maintain the traffic data of the target location stored in the cloud database or when receiving the target data of the target location uploaded by the vehicle, the target data of the target location may be acquired, and the target data is Traffic data collected by the vehicle at the target location, the target The data includes several sub-data, including visual data of the target location and other data, such as weather data of the target location, traffic identification of the target location, and altitude data of the target location, and the cloud server includes the cloud database and Some other functional modules (such as receiving commands, sending data, storing data, etc.), the cloud server and the vehicle are connected wirelessly.

102. Match each sub-data in the target data with each sub-data in the first traffic data to determine a level of each sub-data in the target data. The first traffic data is traffic data of the target location stored in a cloud database. Each of the traffic data includes a plurality of sub-data, and each sub-data is data that has been ranked. At the same time, it should be noted that each traffic data may include the same or similar sub-data, for example, multiple sub-data collected and uploaded by different vehicles for the same-distance traffic identifier.

In this embodiment, after the server obtains the target data of the target location, since the target data includes several sub-data, and the data in the first traffic data of the target location stored in the cloud database has been classified, the server may Each sub-data in the target data is matched with each sub-data in the first traffic data to determine the level of each sub-data in the target data. See below for specific solutions.

It should be noted that, in this embodiment, the data in the cloud database is classified into: normal-accurate data, normal data, data to be added, miscellaneous data, data to be deleted, and deleted data, where

Normal - accurate data representation: accurate data;

Normal data indicates that a large probability is determined to be correct data;

Data to be added indicates: uncertain data;

Miscellaneous data means: data that can be ignored;

The data to be deleted indicates that the large probability is determined to be erroneous data;

Deleted data indicates: incorrect data.

Among them, the grades of these hierarchical data are normal accurate data, normal data, data to be added, miscellaneous data, data to be deleted, deleted data, the highest level of normal accurate data, the lowest registration of deleted data, and can be used by users. It is normal data as well as normal and accurate data.

The above classification is only based on normal data, normal-accurate data, data to be added, miscellaneous data, to be deleted. Except for the data and the deleted data as an example, the first file data, the second file data, the third file data, the fourth file data, the fifth file data, and the sixth file data may also be used, and the specific hierarchical name is not made. limited.

103. Update the first traffic data according to the level of each sub data in the target data.

In this embodiment, after the cloud server determines the level of each sub-data in the target data, the sub-data after the determined level is added to the first traffic data. Specifically, the sub-data after determining the level is added to the sub-data set of the first traffic data.

In this embodiment, when the cloud server needs to update the traffic data of the target location or receives the target data of the target location uploaded by the vehicle, the target data of the target location may be acquired, and each sub-data in the target data is separately Matching each sub-data in the first traffic data to determine the level of each sub-data in the target data, and updating the traffic data of the target location in the cloud database according to the level of each sub-data in the target data. It can be seen that when new data is added to the cloud database, the newly added data is automatically classified according to the graded data in the existing database, thereby automatically maintaining data in the cloud database and improving the cloud database. The correct rate of data.

Referring to FIG. 2, another embodiment of a method for processing traffic data in an embodiment of the present invention includes:

201. Obtain target data of the target location.

In this embodiment, when the cloud server needs to maintain the traffic data of the target location stored in the cloud database or when receiving the target data of the target location uploaded by the vehicle, the target data of the target location may be acquired, and the target data is Traffic data collected by the vehicle at the target location, the target data includes a plurality of sub-data including visual data of the target location and other data, such as weather data of the target location, traffic identification of the target location, and altitude of the target location Data and other data, the cloud server includes a cloud database and some other functional modules (such as receiving commands, sending data, storing data, etc.), and the cloud server and the vehicle are connected by wireless.

202. Match each sub-data of the target data with each sub-data in the first traffic data to determine a level of each sub-data in the target data. The first traffic data is traffic data of the target location stored in a cloud database. Each of the traffic data includes a plurality of sub-data, and each sub-data is data that has been ranked. At the same time, it should be noted that each traffic data can include the same Or similar sub-data, for example, multiple sub-data collected and uploaded by different vehicles for the same location traffic identification.

In this embodiment, after acquiring the target data of the target location, the cloud server may include each subdata in the target data because the target data includes the first traffic data of the target location stored in the cloud database by the plurality of subdata. Matching each sub-data in the first traffic data to determine a matching degree between each sub-data in the target data and each sub-data in the first traffic data, and according to each sub-data and each of the first traffic data The matching degree of the sub data determines the level of each sub data in the target data. For example, setting the level of the sub data in the target data to the level of the sub data having the highest degree of matching with the sub data, or setting the level of the sub data in the target data to match the sub data to a preset threshold (for example, 90%) of the level of subdata.

In another embodiment, after acquiring the target data of the target location, the cloud server may include each of the target data because the target data includes the first traffic data of the target location stored in the cloud database by the plurality of sub-data. The sub-data is respectively matched with each sub-data of the same category in the first traffic data to determine the matching degree between each sub-data in the target data and each sub-data of the same category in the first traffic data, and according to each sub-data and the The degree of matching of each sub-data in a traffic data determines the level of each sub-data in the target data. For example, setting the level of the sub data in the target data to the level of the sub data having the highest degree of matching with the sub data, or setting the level of the sub data in the target data to match the sub data to a preset threshold (for example, 90%) of the level of subdata.

At the same time, it should be noted that when the cloud server sets the level of the sub data in the target data to the level of the sub data that matches the sub data to a preset threshold (for example, 90%), and has multiple matching degrees reaching the pre When the sub-data of the threshold is set, the cloud server may set the level of the sub-data in the target data to the level of the sub-data with the highest degree of matching with the sub-data, or the level of the sub-data in the target data. Set to the level of the child data whose time is closest to the current time.

The following example illustrates that the cloud server obtains the target data, if the target data contains two data, one is the first traffic identification data of the target location, and the other is the first landmark building data of the target location, and the cloud server will be the first A traffic identification data is matched with all traffic identification data of the target location stored in the cloud database, and the first landmark building data is matched with all landmark building data of the target location stored in the cloud database, due to the cloud Stored in the database All traffic identification data and all landmark data of the target location have hierarchical attributes, such as normal data, normal accurate data, miscellaneous data, data to be added, data to be deleted or deleted data, if the cloud database The matching degree of the second traffic identification data and the first traffic identification data in the traffic identification data of the stored target location reaches a preset threshold (for example, 90%, or other values, which are not limited), The level of the first traffic identification data is set to the level of the second traffic identification data. If the classification of the second traffic identification data is normal data, the hierarchical calibration of the normal data is added to the attribute of the first traffic identification data. Similarly, if the matching degree of a certain second landmark building data in the landmark building data of the target location stored in the cloud database and the first landmark building data reaches a preset threshold, the first iconic The level of the building data is set to the level of the second iconic data. If the level of the second landmark building data is band-added data, the level of the first landmark building data is set to be the data to be added, that is, The attribute of the first landmark building data is added to the hierarchical calibration of the data to be added.

203. Adjust a level of the sub data in the target data according to the number of times the similar sub data is acquired within the preset time. It should be noted that the similar sub-data refers to that the matching degree is greater than a preset threshold (for example, greater than 90%, and may be other values, which are not limited).

In this embodiment, after the cloud server determines the ranking of each sub-data in the target data, the level of the sub-data in the target data is also adjusted according to the number of times of similar sub-data acquired in the preset time. For example, the level of the sub-data is adjusted according to the range to which the number of times belongs.

For example, in the first preset time (for example, within 1 day, other values may be used, specifically not limited), the number of times the sub-data similar to the first sub-data is acquired is smaller than the first preset value (for example, 20 times, which may be Other values, specifically not limited, reduce the level of the first sub-data by one step, for example, the normal accurate data determined from step 202 is reduced to normal data; and at the same time, within the second preset time (for example, within 3 days) If the number of times the sub-data similar to the first sub-data is obtained is greater than the second preset value (for example, 200 times), the level of the second sub-data is increased by one step, for example, the data to be added determined in step 202 is promoted to Normal data.

It should be noted that when the cloud server determines that the traffic data of the target location stored in the cloud server has the level of the data as the level of the data to be deleted, and in the third preset time (for example, one month, it may be other values). , specifically not limited) the data is always at this level, you can use this number It is calibrated as deleted data.

It should be noted that the cloud server can regularly clean the data in the cloud database classified into the deleted data labels, so that the space in the cloud database can be more optimally utilized, and the data classified into the deleted data labels is prevented from occupying the storage of the cloud database. space.

204. Update the first traffic data according to the level of each sub data in the target data.

In summary, when the cloud server needs to update the traffic data of the target location or receives the target data of the target location uploaded by the vehicle, the target data of the target location may be acquired first, and each subdata in the target data is acquired. Performing matching with each sub-data in the first traffic data to determine the level of each sub-data in the target data, and adjusting the level of the sub-data in the target data according to the number of times of similar sub-data acquired in the preset time, and according to The level of each sub-data in the target data updates the first traffic data. It can be seen that the cloud database can adjust the rating of the sub-data according to the frequency of the sub-data of the acquired target data when the traffic data of the target location actually changes, thereby realizing automatic change of the traffic data at the target location. Maintain the data in the cloud database to mention the correct rate of data such as the cloud database.

The embodiments of the present invention are described above from the perspective of a method for processing traffic data. The embodiments of the present invention are described below from the perspective of a server.

Please refer to FIG. 3. FIG. 3 is a schematic structural diagram of a server according to an embodiment of the present invention. The server 300 may have a large difference due to different configurations or performances, and may include one or more central processing units (central processing units). , CPU) 310 (eg, one or more processors), one or more storage media 330 storing program code 331 or data 332 (the storage medium may be one or one storage device in Shanghai, or one or more A temporary storage device such as a memory may also be used for one or one hard disk, or one or more memories and a hard disk, which are not limited herein. Wherein, the storage medium 330 can be short-term storage or persistent storage. Still further, central processor 310 can be configured to communicate with storage medium 330 to invoke and execute a series of program codes in storage medium 330. The storage medium 330 also stores a cloud The end database, at least the traffic data of the target location is stored in the cloud database, that is, at least the first traffic data of the target location is stored. The server also includes one or more input and output interfaces 320, which may be one or more wired or wireless network interfaces.

The central processing unit 310 of the server invokes and executes the program code, and is used to acquire target data of a target location, where the target data is traffic data collected by the vehicle-mounted client at the target location, where the target data includes several Each sub-data in the target data is matched with each sub-data in the first traffic data to determine a level of each sub-data in the target data, and the first traffic data is a cloud database. Traffic data of the target location stored therein, and each sub-data in the first traffic data is data that has been ranked; updating the first traffic data according to a level of each sub-data in the target data .

Wherein each sub-data in the target data is matched with each sub-data in the first traffic data to determine a level of each sub-data in the target data, including: each sub-input in the target data Data is respectively matched with each sub-data in the first traffic data to determine a matching degree between each sub-data in the target data and each sub-data in the first traffic data; and according to each sub-data and the first traffic data The degree of matching of each sub-data in the determination determines the level of each sub-data in the target data.

In an embodiment, determining the level of each sub-data in the target data according to the matching degree of each sub-data and each sub-data in the first traffic data comprises: setting a level of the sub-data in the target data to the sub-data The level of subdata with the highest data matching.

In another embodiment, determining the level of each sub-data in the target data according to the matching degree of each sub-data and each sub-data in the first traffic data comprises: setting a level of the sub-data in the target data to The level of sub-data whose sub-data match degree reaches the preset threshold.

After matching each sub-data in the target data with each sub-data in the first traffic data to determine the level of each sub-data in the target data, the central processor further: according to The number of times the similar sub-data is acquired within the set time adjusts the level of the sub-data in the target data.

The adjusting the level of the sub data in the target data according to the number of times of the similar sub data acquired in the preset time comprises: when the number of similar sub data acquired in the first preset time is less than the first preset value, The level of the sub-data is lowered by one file; when the number of similar sub-data acquired in the second preset time is greater than the second preset value, the level of the sub-data is increased by one step.

The updating the first traffic data according to the level of each sub-data in the target data comprises: adding each sub-data after the determined level to the sub-data set of the first traffic data.

A person skilled in the art can clearly understand that for the convenience and brevity of the description, the specific working process described above can refer to the corresponding process in the foregoing method embodiments, and details are not described herein again.

The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to be limiting; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art will understand that The technical solutions described in the embodiments are modified, or the equivalents of the technical features are replaced by the equivalents of the technical solutions of the embodiments of the present invention.

Claims

A method for processing traffic data, comprising:

Obtaining target data of the target location, where the target data is traffic data collected by the in-vehicle client at the target location, where the target data includes several sub-data;

Matching each sub-data in the target data with each sub-data in the first traffic data to determine a level of each sub-data in the target data, where the first traffic data is stored in a cloud database Traffic data of the target location, and each subdata in the first traffic data is data that has been classified;

The first traffic data is updated according to a level of each sub data in the target data.
The method according to claim 1, wherein each of the sub-data in the target data is matched with each sub-data in the first traffic data to determine each sub-data in the target data. Levels include:

Matching each sub-data in the target data with each sub-data in the first traffic data to determine a matching degree between each sub-data in the target data and each sub-data in the first traffic data;

And determining the level of each sub-data in the target data according to the matching degree of each sub-data with each sub-data in the first traffic data.
The method according to claim 2, wherein the determining the level of each sub-data in the target data according to the matching degree of each sub-data with each sub-data in the first traffic data comprises: sub-data in the target data The level is set to the level of the child data that has the highest match with the child data.
The method according to claim 2, wherein the determining the level of each sub-data in the target data according to the matching degree of each sub-data with each sub-data in the first traffic data comprises: sub-data in the target data The level is set to the level of the sub-data that matches the sub-data to a preset threshold.
The method according to claim 1, wherein each of the sub-data in the target data is matched with each sub-data in the first traffic data to determine each sub-data in the target data. After the level, the method further includes:

Adjusting the sub-data in the target data according to the number of times of similar sub-data acquired within the preset time Level.
The method according to claim 5, wherein the adjusting the level of the sub-data in the target data according to the number of times of similar sub-data acquired in the preset time comprises:

When the number of times of similar sub-data acquired in the first preset time is less than the first preset value, the level of the sub-data is lowered by one step;

When the number of times of similar sub-data acquired in the second preset time is greater than the second preset value, the level of the sub-data is increased by one step.
The method according to claim 1, wherein the updating the first traffic data according to a level of each sub data in the target data comprises:

Each sub-data after the determined level is added to the sub-data set of the first traffic data.
A server, characterized by a central processing unit, a storage medium, and an input/output interface;

The storage medium stores a cloud database and program code, and the central processor calls and executes the program code for:

Obtaining target data of the target location, where the target data is traffic data collected by the in-vehicle client at the target location, where the target data includes several sub-data;

Matching each sub-data in the target data with each sub-data in the first traffic data to determine a level of each sub-data in the target data, where the first traffic data is stored in a cloud database Traffic data of the target location, and each subdata in the first traffic data is data that has been classified;

The first traffic data is updated according to a level of each sub data in the target data.
The server according to claim 8, wherein each of the sub-data in the target data is matched with each sub-data in the first traffic data to determine each sub-data in the target data. Levels include:

Matching each sub-data in the target data with each sub-data in the first traffic data to determine a matching degree between each sub-data in the target data and each sub-data in the first traffic data;

And determining the level of each sub-data in the target data according to the matching degree of each sub-data with each sub-data in the first traffic data.
The server according to claim 9, wherein the determining the level of each sub-data in the target data according to the matching degree of each sub-data and each sub-data in the first traffic data comprises: sub-data in the target data The level is set to the level of the child data that has the highest match with the child data.
The server according to claim 9, wherein the determining the level of each sub-data in the target data according to the matching degree of each sub-data and each sub-data in the first traffic data comprises: sub-data in the target data The level is set to the level of the sub-data that matches the sub-data to a preset threshold.
The server according to claim 8, wherein each of the sub-data in the target data is matched with each sub-data in the first traffic data to determine each sub-data in the target data. After the level, the central processor also:

The level of the sub data in the target data is adjusted according to the number of times the similar sub data is acquired within the preset time.
The server according to claim 12, wherein the adjusting the level of the sub-data in the target data according to the number of times of similar sub-data acquired within the preset time comprises:

When the number of times of similar sub-data acquired in the first preset time is less than the first preset value, the level of the sub-data is lowered by one step;

When the number of times of similar sub-data acquired in the second preset time is greater than the second preset value, the level of the sub-data is increased by one step.
The server according to claim 8, wherein the updating the first traffic data according to a level of each sub data in the target data comprises:

Each sub-data after the determined level is added to the sub-data set of the first traffic data.