CN114625884A

CN114625884A - Method, device and equipment for processing track data, storage medium and program product

Info

Publication number: CN114625884A
Application number: CN202210190779.2A
Authority: CN
Inventors: 杨宁; 陈建国; 王亦乐
Original assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Current assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Priority date: 2022-02-28
Filing date: 2022-02-28
Publication date: 2022-06-14

Abstract

The disclosure provides a processing method, a device, equipment, a storage medium and a program product of trajectory data, relating to the field of artificial intelligence, in particular to the fields of big data, knowledge maps and intelligent transportation. The specific implementation scheme is as follows: establishing a knowledge graph according to the trajectory data of each user device by acquiring the trajectory data of the user devices of various different data sources; searching a first user vertex of which the attribute information meets a first condition based on the knowledge graph, and marking the first user vertex as being applied to the construction vehicle; according to the attribute information marked as the user vertex applied to the construction vehicle, the user equipment information applied to the construction vehicle of each data source is determined, the user equipment applied to the construction vehicle can be automatically mined under the condition that the user equipment is not specifically applied to which vehicle, the track of the construction vehicle can be further mined on the basis, and the method can be applied to various different application scenes.

Description

Method, device and equipment for processing track data, storage medium and program product

Technical Field

The present disclosure relates to the field of big data, knowledge graph, intelligent transportation, and the like in artificial intelligence, and in particular, to a method, an apparatus, a device, a storage medium, and a program product for processing trajectory data.

Background

With the development of artificial intelligence technology, in the field of intelligent transportation, products with track tracking and recording functions, such as a network car booking platform, intelligent delivery applications (such as a takeout platform and a logistics platform for takeout delivery), a vehicle data recorder and a navigation map, appear, and devices for acquiring track data in different types of products are called user devices, for example, a smart phone with a network car booking platform client application installed, a smart phone with a takeout delivery client application installed, a vehicle data recorder and the like.

By summarizing the track data of the user equipment of various different data sources in a certain region, more complete track data in the region can be known, and a lot of useful information can be obtained by carrying out data mining on the track data. Under many scenes in practical application, the track data of the construction vehicles need to be excavated from the track data, which roads are construction roads and which roads can normally pass can be excavated based on the track data of the construction vehicles, and a data basis is provided for applications such as map navigation and intelligent road opening. Without knowing which vehicles the user devices are specifically applied to, there is currently no technical solution that can mine which user devices are applied to the construction vehicle based on trajectory data.

Disclosure of Invention

The disclosure provides a method, an apparatus, a device, a storage medium and a program product for processing track data.

According to a first aspect of the present disclosure, there is provided a method for processing trajectory data, including:

responding to a user equipment information mining request applied to a construction vehicle, and acquiring track data of user equipment of various different data sources;

according to the trajectory data of the user equipment, constructing a knowledge graph, wherein the knowledge graph comprises a user vertex corresponding to each user equipment and a data source vertex corresponding to each data source, each user vertex is connected with the data source vertex corresponding to the data source to which the corresponding user equipment belongs through edges, the attribute information of each user vertex comprises the trajectory characteristic information of the corresponding user equipment, and the attribute information of each data source vertex is determined according to the attribute information of all the connected user vertices;

searching a first user vertex of which the attribute information meets a first condition in the knowledge graph, and marking the first user vertex as being applied to a construction vehicle;

user device information applied to the construction vehicle for each data source is determined from the attribute information marked as user vertices applied to the construction vehicle.

According to a second aspect of the present disclosure, there is provided a processing apparatus of trajectory data, comprising:

the track data acquisition module is used for responding to a user equipment information mining request applied to a construction vehicle and acquiring track data of user equipment of various different data sources;

the knowledge graph building module is used for building a knowledge graph according to the track data of the user equipment, wherein the knowledge graph comprises a user vertex corresponding to each user equipment and a data source vertex corresponding to each data source, each user vertex is connected with the data source vertex corresponding to the data source to which the corresponding user equipment belongs through edges, the attribute information of each user vertex comprises the track characteristic information of the corresponding user equipment, and the attribute information of each data source vertex is determined according to the attribute information of all the connected user vertices;

the first mining processing module is used for searching a first user vertex of which the attribute information meets a first condition in the knowledge graph and marking the first user vertex as being applied to a construction vehicle;

and the information determining module is used for determining the user equipment information applied to the construction vehicle of each data source according to the attribute information marked as the user vertex applied to the construction vehicle.

According to a third aspect of the present disclosure, there is provided an electronic device comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of the first aspect.

According to a fourth aspect of the present disclosure, there is provided a non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of the first aspect.

According to a fifth aspect of the present disclosure, there is provided a computer program product comprising: a computer program, stored in a readable storage medium, from which at least one processor of an electronic device can read the computer program, execution of the computer program by the at least one processor causing the electronic device to perform the method of the first aspect.

Techniques according to the present disclosure can automatically mine user devices for application to construction vehicles based on trajectory data of the user devices.

It should be understood that the statements in this section are not intended to identify key or critical features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.

Drawings

The drawings are included to provide a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:

FIG. 1 is a flow chart of a method of processing trajectory data according to a first embodiment of the present disclosure;

FIG. 2 is a schematic diagram of a graph structure model of a knowledge-graph according to an embodiment of the present disclosure;

FIG. 3 is a diagram illustrating a mapping relationship between data source vertices and user vertices, according to an embodiment of the present disclosure;

FIG. 4 is a flow chart of a method for processing trajectory data according to a second embodiment of the present disclosure;

fig. 5 is a schematic configuration diagram of a processing apparatus of trajectory data according to a third embodiment of the present disclosure;

fig. 6 is a schematic configuration diagram of a processing apparatus of trajectory data according to a fourth embodiment of the present disclosure;

fig. 7 is a block diagram of an electronic device for implementing a method of processing trajectory data according to an embodiment of the present disclosure.

Detailed Description

Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of the embodiments of the disclosure are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

The terms "first", "second", "third", etc. referred to in this disclosure are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. In the description of the following examples, "plurality" means two or more unless specifically limited otherwise.

The present disclosure provides a trajectory data processing method, apparatus, device, storage medium, and program product, which are applied to the fields of big data, knowledge maps, intelligent transportation, etc. in artificial intelligence, and can dig out which user devices are applied to a construction vehicle based on trajectory data of the user devices without knowing which vehicle the user devices are specifically applied to, thereby providing a data base for further digging a construction trajectory and applying the construction trajectory.

The track data processing method can be particularly used for various different application scenes such as electronic maps, intelligent traffic control systems and the like, can acquire the track data of the user equipment from various different data sources, and can construct a knowledge graph according to the track data of each user equipment; searching a first user vertex of which the attribute information meets a first condition based on the knowledge graph, and marking the first user vertex as being applied to the construction vehicle; and determining the user equipment information of each data source, which is applied to the construction vehicle, according to the attribute information of the user vertex marked as being applied to the construction vehicle, so as to mine the user equipment applied to the construction vehicle, and further mining the track of the construction vehicle on the basis of the user equipment information, wherein the track of the construction vehicle can be mined and the application can be applied to various application scenes.

The knowledge graph comprises a user vertex corresponding to each user device and a data source vertex corresponding to each data source, wherein each user vertex is connected with the data source vertex corresponding to the data source to which the corresponding user device belongs through an edge, the attribute information of each user vertex comprises track characteristic information of the corresponding user device, and the attribute information of each data source vertex is determined according to the attribute information of all the connected user vertices.

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

Fig. 1 is a flowchart of a processing method of trajectory data according to a first embodiment of the present disclosure. The method for processing the trajectory data provided by the embodiment can be specifically applied to electronic equipment, and the electronic equipment can realize different functions according to different actual application scenes, for example, functions such as electronic maps and intelligent traffic control.

As shown in fig. 1, the method comprises the following specific steps:

and S101, responding to a user equipment information mining request applied to the construction vehicle, and acquiring track data of user equipment of various different data sources.

In this embodiment, when it is necessary to mine the user equipment applied to the construction vehicle, a user equipment information mining request applied to the construction vehicle may be submitted to the electronic equipment. The electronic device obtains trajectory data for the user device for a plurality of different data sources in response to the request.

In different application scenes, according to the requirements of actual application scenes, a time range and a geographic range for data mining can be designated, the track data in the designated time range and the designated geographic range are mined, and the user equipment applied to the construction vehicle is determined.

Step S102, a knowledge graph is constructed according to the track data of the user equipment, wherein the knowledge graph comprises a user vertex corresponding to each user equipment and a data source vertex corresponding to each data source, each user vertex is connected with the data source vertex corresponding to the data source to which the corresponding user equipment belongs through edges, the attribute information of each user vertex comprises the track characteristic information of the corresponding user equipment, and the attribute information of each data source vertex is determined according to the attribute information of all the connected user vertices.

After the trajectory data of the user equipment of various different data sources are acquired, a knowledge graph is constructed according to the acquired trajectory data of all the user equipment.

Illustratively, the graph structure of the knowledge-graph employs a model as shown in FIG. 2, including two types of vertices: user vertices and data source vertices. The user vertex is a vertex corresponding to the user equipment, the data source vertex is a vertex corresponding to the data source, and an edge is formed between the user vertex of the user equipment and the data source vertex of the data source to which the user equipment belongs. The user vertex has attribute information, and the attribute information of the user vertex is the track characteristic information of the user equipment. The data source vertex also has attribute information, and the attribute information of the data source vertex can be obtained by summarizing the attribute information of the user vertex connected with the data source vertex.

The data source vertex and the user vertex can be represented by a one-to-one key, and the data source vertex and the user vertex form a one-to-many mapping relation through the edge.

For example, taking an example that one data source has multiple user devices, a mapping relationship between a data source vertex a corresponding to the data source and a user vertex B corresponding to the multiple user devices is shown in fig. 3, a circle with mesh padding in the middle represents one data source vertex a, a circle without padding around a and connected with the data source vertex a through an edge represents a user vertex B, and multiple user vertices B are shown in fig. 3.

After the construction of the knowledge graph is completed according to the track data of the user equipment, the related search of the user vertex and the data source vertex can be realized based on the knowledge graph.

Step S103, searching a knowledge graph for a first user vertex with attribute information meeting a first condition, and marking the first user vertex as being applied to the construction vehicle.

Wherein the first condition is set based on the historical trajectory data of the large data amount by analyzing and extracting a feature unique to the trajectory of the construction vehicle and according to the feature possessed by the trajectory of the construction vehicle. For any user vertex, if the attribute information of the user vertex satisfies the first condition, it may be determined that the user vertex is a user vertex applied to the construction vehicle, that is, the user device corresponding to the user vertex is a user device applied to the construction vehicle, for example, a vehicle event data recorder installed on the construction vehicle.

After the knowledge graph is constructed, first user vertices satisfying a first condition are determined by searching the knowledge graph for the first user vertices whose attribute information satisfies the first condition, the first user vertices are taken as user vertices applied to a construction vehicle, and the first user vertices are marked as being applied to the construction vehicle.

And step S104, determining user equipment information applied to the construction vehicle of each data source according to the attribute information marked as the user vertex applied to the construction vehicle.

After the user vertices applied to the construction vehicle are marked in the knowledge graph, user device information applied to the construction vehicle for each data source may be searched for according to the attribute information marked as user vertices applied to the construction vehicle.

Based on the user equipment information of each data source applied to the construction vehicle, the trajectory data of the construction vehicle can be further mined, and a data base is provided for downstream tasks.

In the embodiment, the knowledge graph is constructed according to the track data of each user device by acquiring the track data of the user devices from a plurality of different data sources; searching a first user vertex of which the attribute information meets a first condition based on the knowledge graph, and marking the first user vertex as being applied to the construction vehicle; according to the attribute information marked as the user vertex applied to the construction vehicle, the user equipment information applied to the construction vehicle of each data source is determined, the user equipment applied to the construction vehicle can be automatically mined under the condition that the user equipment is not specifically applied to which vehicle, the track of the construction vehicle can be further mined on the basis, and the method can be applied to various different application scenes.

Fig. 4 is a flowchart of a method for processing trajectory data according to a second embodiment of the present disclosure. On the basis of the first embodiment described above, in the present embodiment,

as shown in fig. 4, the method comprises the following specific steps:

step S401, responding to a user equipment information mining request applied to a construction vehicle, and acquiring track data of user equipment of various different data sources.

And S402, constructing a knowledge graph according to the track data of the user equipment.

Alternatively, the edge between the data source vertex and the user vertex may be a directed edge, the directed edge being pointed to the user vertex by the data source vertex (as shown in fig. 2), the starting vertex of the directed edge being the data source vertex, and the ending vertex of the directed edge being the user vertex.

Alternatively, the edge between the data source vertex and the user vertex may be an undirected edge, which indicates that there is an association between the user vertex and the data source vertex, and the user vertex and the data source vertex may be distinguished by the attribute of the vertex.

For example, taking an example that one data source has multiple user devices, a mapping relationship between a data source vertex a corresponding to the data source and user vertices B corresponding to the multiple user devices is shown in fig. 3, a dot in the middle represents one data source vertex a, and there are multiple user vertices B connected to the data source vertex a through edges. Assuming that there are 100 user devices of the data source, 100 user vertices B corresponding to the 100 user devices are respectively connected to the data source vertex a corresponding to the data source through an edge. Therefore, the track characteristic information of each user device can be injected into the attribute information of the user vertex in the knowledge graph, and then various attribute information of the data source vertex can be determined through graph reasoning, so that the calculation efficiency can be improved.

Optionally, the trajectory characteristic information of the user equipment includes at least one of:

the method comprises the following steps of data source identification, data source name, location information, average mileage of a track, average interval mileage between adjacent track points, average duration of the track, average interval duration between adjacent track points, total mileage of all tracks of all user equipment of a data source, total duration of all tracks of all user equipment of a data source, average confidence of the track, average vehicle traveling probability of the track points, average emission probability of the track points, average projection distance of the track points, average speed of the track points and maximum speed of the track points.

Each piece of track data of the user equipment comprises track information such as total mileage, total duration, track confidence coefficient and the like, information of the user equipment to which the user equipment belongs and the like.

The data source identification refers to identification information of a data source to which the user vertex corresponds and the user equipment belongs.

The data source name is the name of the data source of the user vertex corresponding to the user equipment.

The location information is information of an area where the track data of the user equipment corresponding to the user vertex is located, such as province, city, country, and the like.

The average mileage of a trace is: the user vertex corresponds to an average of the total mileage of the different trajectory data of the user device.

The average interval mileage between adjacent track points refers to: and the user vertex corresponds to the average value of the interval duration between the adjacent track points in all the track data of the user equipment.

The average duration of the trace is: the user vertex corresponds to an average value of the total time lengths of different trajectory data of the user equipment.

The average interval mileage between adjacent track points is as follows: and the user vertex corresponds to the average value of the interval mileage between the adjacent track points in all the track data of the user equipment.

The total mileage of all traces of all user devices of the data source refers to: the user vertex corresponds to the sum of the total mileage of all the trajectory data of all the user devices of the data source to which the user device belongs.

The total duration of all traces of all user devices of the data source refers to: the user vertex corresponds to the sum of the total duration of all the trajectory data of all the user equipment of the data source to which the user equipment belongs.

The average confidence of the trace refers to: the user vertices correspond to the average of the trajectory confidence values of the different trajectory data of the user device.

The average driving probability of the track points is as follows: and the user vertex corresponds to the average value of the probability that the track point belongs to the vehicle track in all the track data of the user equipment.

The average emission probability of the trace points is as follows: the user vertex corresponds to the average value of the emission probabilities of the trace points in all the trace data of the user equipment.

The average projection distance of the track points is as follows: the user vertex corresponds to the average value of the projection distances of the track points in all the track data of the user equipment.

The average velocity of the trace points is: the user vertex corresponds to the average of the velocities at the trajectory point in all trajectory data for the user device.

The maximum speed of the trace point is: the user vertex corresponds to the maximum of the velocities at the trajectory point in all trajectory data of the user device.

Whether to be applied to the construction vehicle means: the user vertex corresponds to whether the user equipment is applied to the construction vehicle.

In practical application, when the knowledge graph is constructed, the attribute information of the user vertex corresponding to the user equipment may include multiple items of track feature information in the track feature information of the user equipment, wherein each item of track feature information is used as one item of attribute information, and the richer the attribute information contained in the user vertex, the more the accuracy of the user equipment applied to the construction vehicle determined based on knowledge graph mining can be improved.

The knowledge graph is constructed by extracting the rich track characteristic information of the user equipment and taking the rich track characteristic information as the attribute information of the corresponding user vertex, so that the knowledge graph contains the rich track characteristic information of each user equipment, and a data basis is provided for accurately mining the user equipment applied to the construction vehicle.

Optionally, the attribute information of the user vertex may further include the following two items: and the confidence coefficient of whether the user vertex is applied to the construction vehicle is used as the label information of whether the user vertex is applied to the construction vehicle, so that the marking of the user vertex applied to the construction vehicle is realized.

Wherein, the confidence applied to the construction vehicle means: the user vertices correspond to the confidence level that the user device is applied to the construction vehicle.

The confidence of whether or not to apply to the construction vehicle and to the construction vehicle is attribute information that needs to be determined by data mining through subsequent steps.

Alternatively, the attribute information of the data source vertex in the knowledge graph can be set corresponding to the attribute information of the user vertex.

Illustratively, a user vertex in the knowledge-graph may include the following attribute information: the data source identification, the data source name, the location information, the track average mileage, the average interval mileage between adjacent track points, the average duration of the track, the average interval duration between adjacent track points, the total mileage of all tracks of all user equipment of the data source, the total duration of all tracks of all user equipment of the data source, the average confidence coefficient of the track, the average driving probability of the track points, the average emission probability of the track points, the average projection distance of the track points, the average speed of the track points, the maximum speed of the track points, whether the construction vehicle is applied or not, and the confidence coefficient of the construction vehicle is applied.

Accordingly, data source vertices in the knowledge-graph may include the following attribute information: the data source identification, the data source name, location information, the average mileage of orbit, the average interval mileage between adjacent track points, the average duration of orbit, the average interval duration between adjacent track points, the total mileage of all orbits of all user equipment, the total duration of all orbits of all user equipment, the average confidence coefficient of orbit, the average driving probability of track point, the average emission probability of track point, the average projection distance of track point, the average speed of track point, the maximum speed of track point, whether be applied to the construction vehicle, the confidence coefficient of being applied to the construction vehicle. The two items of attribute information, namely whether the data source vertex is applied to the construction vehicle and the confidence coefficient applied to the construction vehicle, are used as the label information of whether the data source vertex is applied to the construction vehicle, so that the marking of the data source vertex applied to the construction vehicle is realized.

For each item of numerical attribute information of a data source vertex, the attribute information can be determined by integrating the values of the same attribute information of all user vertices connected with the data source vertex.

For example, the track average mileage of the data source vertices is equal to the average of the track average mileage of all the connected user vertices. The total mileage of all the tracks of all the user devices of the data source vertices is equal to the total mileage of all the tracks of all the user devices of the data source to which any one of the user vertices is connected. The maximum speed of the track points of the data source vertexes is equal to the maximum of the maximum speeds of the track points of all the connected user vertexes. Other attribute information of the data source vertex can be determined by adopting a similar method, and the description is not repeated.

Specifically, this step can be implemented as follows:

extracting track characteristic information of each user equipment according to the track data of each user equipment; constructing a knowledge graph according to the track characteristic information of each user device, wherein the attribute information of each user vertex in the knowledge graph comprises the track characteristic information of the corresponding user device, and the attribute information of each data source vertex is initialized to a preset attribute value; and determining the attribute information of the data source vertex according to the attribute information of all user vertices connected with each data source vertex, and updating the attribute information of each data source vertex in the knowledge graph.

The preset attribute value can be determined according to possible values of the track characteristic information of the user equipment, and the preset attribute value is not in the possible values of all the track characteristic information. For example, the preset attribute value may be a negative number, such as-1.

Therefore, by filling the track characteristic information of each user device into the attribute information of the user vertex in the knowledge graph, the attribute information of each data source vertex can be determined through graph reasoning subsequently, and the calculation efficiency can be improved. The constructed knowledge graph contains rich track characteristic information of each user device and overall track characteristic information of each data source, and provides a data base for mining the user devices and the data sources applied to the construction vehicle.

Step S403, searching the knowledge graph for a first user vertex with attribute information meeting a first condition, and marking the first user vertex as being applied to the construction vehicle.

Wherein the first condition is set based on the historical trajectory data of the large data amount by analyzing and extracting a feature unique to the trajectory of the construction vehicle and according to the feature possessed by the trajectory of the construction vehicle. For any user vertex, if the attribute information of the user vertex meets the first condition, it may be determined that the user vertex is a user vertex applied to the construction vehicle, that is, the user device corresponding to the user vertex is a user device applied to the construction vehicle, for example, a vehicle event data recorder installed on the construction vehicle.

In a practical application scenario, based on analysis of a large amount of historical trajectory data, it may be determined that if one user device is applied to a construction vehicle, then the user device typically has the following characteristics:

long-section tracks appear on normal roads, and the construction vehicles are necessary to run on the normal roads no matter whether the construction vehicles are lifting vehicles, cranes or road pressing vehicles. A certain proportion of the tracks appear in the construction area, which may be a missing road network area or a gray level road network area (i.e. the road network is made but not on-line).

In conjunction with these two-part characteristics, trajectory data applied to a user device of a construction vehicle typically has the following characteristic information:

1) the trajectory data of this user device should be of sufficient mileage rather than short.

2) The mileage per trace data should be averaged to a certain level.

3) The average confidence of the track should be in a certain interval (not the best or the worst), and the average confidence of the track is an evaluation of the track quality.

4) The probability of the track points to be driven should be within a certain interval.

5) The probability of transmission of the trace points should be within a certain interval.

6) The average projected distance of the trace points should be within a certain interval.

7) The total number of the track points reaches a certain scale.

8) The number of matching failure points is up to a certain magnitude, wherein the matching failure points refer to track points which are not matched to a road network (link).

9) The number of far, middle and near points determined by matching should reach a certain magnitude. Wherein, the far point is a track point with the shortest distance to the link greater than a first distance threshold. The midpoint is a trace point where the shortest distance to the link is less than or equal to a first distance threshold and the shortest distance to the link is greater than a second distance threshold. The near point is a track point of which the shortest distance to the link is less than or equal to a second distance threshold. The first distance threshold and the second distance threshold can be set and adjusted according to actual application scenarios.

The user equipment applied to the construction vehicle may be mined based on the above-described characteristic information. And determining whether the track data of the user equipment has the characteristic information according to the attribute information of the user vertex corresponding to the user equipment.

By collectively analyzing the characteristic information of 1) to 9) described above, it is possible to determine a first condition for determining whether the user equipment is applied to the construction vehicle.

Illustratively, the first condition may be that the trajectory data of the user device simultaneously satisfies the following condition:

(1) the sum of the number of the matching failure points and the number of the far points is greater than or equal to a first condition threshold, and the proportion of the sum of the number of the matching failure points and the number of the far points is greater than a second condition threshold.

(2) The sum of the number of matching success points and the number of near points is greater than or equal to a third condition threshold. Wherein, the matching success point refers to the track point successfully matched to the road network (link).

(3) The total mileage of all the tracks is greater than or equal to a fourth condition threshold value, the average mileage of different tracks is greater than or equal to a fifth condition threshold value, and the total number of track points of all the tracks is greater than or equal to a sixth condition threshold value.

(4) The average confidence of the track is in a first value interval, the driving probability of the track is in a second value interval, and the emission probability of the track is in a third value interval.

In the above conditions, the first condition threshold, the second condition threshold, the third condition threshold, the fourth condition threshold, the fifth condition threshold, the sixth condition threshold, the first value-taking interval, the second value-taking interval, and the third value-taking interval may be analyzed and determined according to a large amount of historical data of an actual application scenario, and are not specifically limited herein.

Optionally, the first condition may also be determined by performing summary analysis by superimposing other conditions besides the conditions (1) to (4), specifically by using the characteristic information of 1) to 9), and the specific content of the first condition is not specifically limited herein.

Optionally, after searching a first user vertex of which the attribute information meets the first condition in the knowledge graph, determining a confidence coefficient of the first user vertex corresponding to the user equipment applied to the construction vehicle according to the attribute information of the first user vertex; and updating attribute information of the confidence coefficient, applied to the construction vehicle, of the first user vertex according to the confidence coefficient, applied to the construction vehicle, of the user equipment corresponding to the first user vertex.

Therefore, the first user vertex applied to the construction vehicle can be mined, the confidence coefficient of the first user vertex applied to the construction vehicle can be given, and the reliability of the mining result can be reflected.

In addition, the first user vertexes are screened based on the confidence degree of the first user vertexes applied to the construction vehicle, the user vertexes with lower confidence degree applied to the construction vehicle are filtered, and only the first user vertexes with the confidence degree reaching the confidence degree threshold value applied to the construction vehicle are marked as the user vertexes applied to the construction vehicle, so that the accuracy of the mining result is improved.

In an alternative embodiment, after the first user vertex is marked as applied to the construction vehicle in this step, step S406 may be directly performed, and the user device information applied to the construction vehicle of each data source is determined according to the attribute information of the user vertex marked as applied to the construction vehicle, and is subsequently applied.

In practical applications, if a large percentage of the user devices of one data source are applied to a construction vehicle, other user devices within the same data source are also more likely to be applied to the construction vehicle.

In an alternative embodiment, after the first user vertex is marked as applied to the construction vehicle, step S406 may be directly performed, and the user device information applied to the construction vehicle of each data source is determined according to the attribute information of the user vertex marked as applied to the construction vehicle, and is subsequently applied.

In another alternative embodiment, after the first user vertex is marked as applied to the construction vehicle, for the data source with a smaller proportion of user devices corresponding to the construction vehicle, a few user devices applied to the construction vehicle in the data source can be considered as error data, the attribute marked as applied to the user vertex of the construction vehicle in the data source is updated, and the attribute of whether the user vertex is applied to the construction vehicle is updated to be negative. For example, the value of the attribute of whether or not these user vertices are applied to the construction vehicle is set to 0, 0 indicating no, and 1 indicating yes.

In another alternative embodiment, after the first user vertex is marked as being applied to the construction vehicle, the user equipment applied to the construction vehicle is mined for the second time through steps S404-S405, and more user equipment applied to the construction vehicle is mined from the data source, so that the recall rate of recalling the construction track based on the user equipment applied to the construction vehicle obtained by mining can be improved.

And S404, determining a first data source vertex to be mined for the second time.

After the first user vertex applied to the construction vehicle is determined by performing the first mining in step S403, the first data source vertex that needs to be mined for the second time may be determined according to the first proportion value occupied by the first user vertex among the user vertices connected to the data source vertex.

Specifically, this step can be implemented as follows:

determining the number of first user vertexes connected with each data source vertex according to the attribute information of the first user vertexes marked as being applied to the construction vehicle in the knowledge graph; determining a first proportion value corresponding to each data source vertex according to the number of first user vertices connected with each data source vertex, wherein the first proportion value is the proportion of the first user vertices in all user nodes connected with the data source vertex; and determining the corresponding first data source vertex of which the first proportion value is larger than the first threshold value to obtain the first data source vertex to be mined for the second time.

The first threshold may be set and adjusted according to an actual application scenario and an empirical value, which is not specifically limited herein.

And S405, searching a second user vertex of which the attribute information meets the second condition and does not meet the first condition from all user vertices connected with the first data source vertex in the knowledge graph, and marking the second user vertex as the second user vertex to be applied to the construction vehicle.

The second condition is relatively loose relative to the first condition, the attribute of the user vertex meeting the first condition necessarily meets the second condition, but the attribute information of the user vertex meeting the second condition does not necessarily meet the first condition. More user vertexes meeting the condition can be mined based on the second condition, so that more user vertexes applied to the construction vehicle are mined, and the recall rate of the mining result in actual application is improved.

After determining the first data source vertices to be mined for the second time, the step of mining more second user vertices of the first data source vertices connections that are applied to the construction vehicle by mining for the second time based on a second condition that is relatively more relaxed than the first condition, searching the knowledge-graph for second user vertices whose attribute information satisfies the second condition and does not satisfy the first condition.

Optionally, after searching a second user vertex, of which the attribute information satisfies the second condition and does not satisfy the first condition, in all user vertices connected to the first data source vertex in the knowledge graph, determining a confidence level of the user equipment corresponding to the second user vertex applied to the construction vehicle according to the attribute information of the second user vertex; and updating attribute information of the confidence coefficient of the second user vertex applied to the construction vehicle according to the confidence coefficient of the second user vertex corresponding to the user equipment applied to the construction vehicle. Therefore, the second user vertex applied to the construction vehicle can be excavated, the confidence coefficient of the second user vertex applied to the construction vehicle can be given, and the reliability of the excavation result can be reflected.

Optionally, before updating attribute information of the confidence coefficient of the second user vertex applied to the construction vehicle, multiplying the confidence coefficient of the second user vertex corresponding to the user equipment applied to the construction vehicle by a preset coefficient, where the preset coefficient is greater than 0 and smaller than 1, so as to reduce the confidence coefficient of the second user vertex applied to the construction vehicle obtained by the second mining, and make the confidence coefficient of the user vertex more reasonable and more accurate.

The preset coefficient may be set and adjusted according to an actual application scenario, and is not specifically limited herein.

And step S406, determining user equipment information applied to the construction vehicle of each data source according to the attribute information marked as the user vertex applied to the construction vehicle.

After all user vertices in the knowledge-graph that apply to the construction vehicle are mined and marked as applying to the construction vehicle, user device information applied to the construction vehicle for each data source is easily queried based on the knowledge-graph.

Optionally, in this step, according to the attribute information marked as the user vertex applied to the construction vehicle, at least one of the following information of any data source may be determined and output:

the number of user devices in the data source that apply to the construction vehicle;

the proportion of user equipment applied to the construction vehicle in the data source;

identification information of a user device applied to the construction vehicle in the data source.

The number, the occupied proportion, the user equipment identification information and the like of the user equipment applied to the construction vehicle in any data source can be easily obtained by inquiring the knowledge graph in response to the inquiry request of a user, so that a data basis is provided for the follow-up excavation of the track of the construction vehicle and the like, and the method can be applied to various application scenes.

Alternatively, the information of each data source applied to the user equipment of the construction vehicle may be formed into a report, and the report may be output for viewing.

In a possible application scene, for a construction road which is not repaired, the track of a plurality of construction vehicles on the construction road exists, and if the construction track and other tracks are not distinguished, the construction road can be automatically judged to be opened in advance, so that the construction road is opened by mistake.

Optionally, after determining the user equipment information applied to the construction vehicle of each data source according to the attribute information marked as the user vertex applied to the construction vehicle, an automatic opening function of the construction road may be further implemented based on the user equipment information applied to the construction vehicle. The method can be realized by the following steps:

according to the user equipment information of each data source, which is applied to the construction vehicle, construction track data are removed from track data on a preset construction road, wherein the construction track data are the track data of the user equipment applied to the construction vehicle; and judging whether the preset construction road meets the opening condition or not according to the residual track data on the preset construction road after the construction track data are removed.

Therefore, after the track data of the construction vehicles on the construction road are removed based on the user equipment information of each data source, the residual track data of the construction road are the track data of other non-construction vehicles, whether the construction road meets the opening condition is judged based on the track data of the other non-construction vehicles, the condition that the construction road can be opened more accurately can be judged, and the condition that the construction road cannot be opened by mistake when the construction road cannot be started due to the fact that the construction road is covered by the track of the construction vehicles is avoided.

Optionally, the construction track belonging to the user equipment applied to the construction vehicle can also be determined according to the excavated information applied to the user equipment of the construction vehicle; and if the construction road is covered by the construction track, determining that the construction road cannot be opened temporarily. And if the construction road is not covered by the construction track in the latest time period, determining that the construction road can be opened.

Alternatively, the construction track belonging to the user equipment applied to the construction vehicle is determined according to the excavated information of the user equipment applied to the construction vehicle, and a road covered by the construction track may be determined as a construction road, and the construction road which is not opened is specially processed when map matching and map navigation are performed.

The user equipment applied to the construction vehicle, which is obtained by mining through the track data processing method in the embodiment, has the following two applications, namely, on one hand, the real-time task flow is transmitted, the tag is added to the user equipment applied to the construction vehicle, and the data basis is provided for the subsequent task flow. And on the other hand, the method is provided for an offline mining end, the user equipment applied to the construction vehicle can be removed from the offline mining end, and the corresponding scene is processed based on the track data of other user equipment. The present embodiment does not limit the specific application scenario here.

In an optional implementation mode, a graph database service can be built by utilizing an open-source graph database, and functions of constructing and searching a knowledge graph and the like are realized. The functions of data calculation and knowledge graph import are realized locally through writing requests. For example, the open source graph database may be a hugegraph or the like.

When the method is applied, the electronic equipment responds to a user equipment information mining request applied to a construction vehicle, track data of user equipment of various different data sources is obtained, and track characteristic information of each user equipment is extracted according to the track data of each user equipment; and then submitting a request to a database service, so that the database service constructs a knowledge graph according to the track characteristic information of each user device, the attribute information of each user vertex in the knowledge graph comprises the track characteristic information of the corresponding user device, and the attribute information of each data source vertex is initialized to a preset attribute value. And then determining the attribute information of the data source vertex according to the attribute information of all the user vertices connected with each data source vertex based on graph reasoning, and updating the attribute information of each data source vertex in the knowledge graph.

And subsequent functions of updating the knowledge graph, searching and inquiring based on the knowledge graph and the like are carried out by the database service, and result data are fed back to the electronic equipment.

In an exemplary manner, in the application process, when user equipment information of an application construction vehicle needs to be acquired, the electronic equipment submits a request to a database service, the database service inquires attribute information which is connected with a data source vertex corresponding to each data source and is marked as a user vertex applied to the construction vehicle in a knowledge graph according to the data source information, and counts the number, the occupied proportion and identification information of the user vertices applied to the construction vehicle in each data source; and feeds back the query result to the electronic device. And the electronic equipment generates a report according to the query result and displays the report.

Optionally, the knowledge graph can be visually displayed, the overall structure of the knowledge graph can be displayed through a front-end page, a substructure related to any data source is also supported, and query and display of information of any data source and any user equipment are supported.

Illustratively, the overall structure of the knowledge graph can be shown through a front-end page, and when a user clicks one vertex of the data source, the mapping relation between the vertex of the data source and the vertex of the user is expanded and displayed so as to show the related substructure of the data source. In addition, for any vertex in the graph structure shown, attribute information for the vertex may also be displayed based on a user request.

In this embodiment, after the first user vertex is marked as being applied to the construction vehicle, second mining is performed on a data source where the user equipment applied to the construction vehicle has a large proportion, and more user equipment applied to the construction vehicle is mined from the data source, so that the recall rate of recalling the construction trajectory based on the user equipment applied to the construction vehicle obtained by mining can be increased.

Fig. 5 is a schematic structural diagram of a trajectory data processing device according to a third embodiment of the present disclosure. The processing device of the trajectory data provided by the embodiment of the disclosure can execute the processing flow provided by the embodiment of the method for processing the trajectory data. As shown in fig. 5, the track data processing device 50 includes: a trajectory data acquisition module 51, a knowledge graph construction module 52, a first mining processing module 53 and an information determination module 54.

Specifically, the trajectory data acquisition module 51 is configured to acquire trajectory data of user devices of a plurality of different data sources in response to a user device information mining request applied to a construction vehicle.

The knowledge graph constructing module 52 is configured to construct a knowledge graph according to the trajectory data of the user equipment, where the knowledge graph includes a user vertex corresponding to each user equipment and a data source vertex corresponding to each data source, where each user vertex is connected to a data source vertex corresponding to the data source to which the corresponding user equipment belongs through an edge, the attribute information of each user vertex includes trajectory feature information of the corresponding user equipment, and the attribute information of each data source vertex is determined according to the attribute information of all connected user vertices.

The first mining processing module 53 is configured to search the knowledge-graph for a first user vertex for which the attribute information satisfies a first condition, and mark the first user vertex as being applied to the construction vehicle.

An information determination module 54 for determining user equipment information for each data source to apply to the construction vehicle based on the attribute information marked as user vertices to apply to the construction vehicle.

The apparatus provided in the embodiment of the present disclosure may be specifically configured to execute the method embodiment provided in the first embodiment, and specific functions and technical effects achieved are not described herein again.

Fig. 6 is a schematic structural diagram of a trajectory data processing device according to a fourth embodiment of the present disclosure. The processing device of the trajectory data provided by the embodiment of the disclosure can execute the processing flow provided by the embodiment of the method for processing the trajectory data. As shown in fig. 6, the trajectory data processing device 60 includes: a trajectory data acquisition module 61, a knowledge graph construction module 62, a first mining processing module 63, and an information determination module 64.

Specifically, the trajectory data acquisition module 61 is configured to acquire trajectory data of user devices of a plurality of different data sources in response to a user device information mining request applied to a construction vehicle.

The knowledge graph constructing module 62 is configured to construct a knowledge graph according to the trajectory data of the user equipment, where the knowledge graph includes a user vertex corresponding to each user equipment and a data source vertex corresponding to each data source, where each user vertex is connected to a data source vertex corresponding to the data source to which the corresponding user equipment belongs through an edge, the attribute information of each user vertex includes trajectory feature information of the corresponding user equipment, and the attribute information of each data source vertex is determined according to the attribute information of all connected user vertices.

A first mining processing module 63 for searching the knowledge-graph for a first user vertex for which the attribute information satisfies a first condition, and marking the first user vertex as being applied to the construction vehicle.

An information determination module 64 for determining user device information for each data source to apply to the construction vehicle based on the attribute information marked as user vertices to apply to the construction vehicle.

Optionally, as shown in fig. 6, the knowledge-graph building module 62 includes:

a track feature extracting unit 621, configured to extract track feature information of each user equipment according to the track data of each user equipment.

A knowledge graph constructing unit 622, configured to construct a knowledge graph according to the trajectory feature information of each user device, where the attribute information of each user vertex in the knowledge graph includes the trajectory feature information of the corresponding user device, and the attribute information of each data source vertex is initialized to a preset attribute value.

And the attribute updating unit 623 is configured to determine attribute information of the data source vertex according to the attribute information of all the user vertices connected to each data source vertex, and update the attribute information of each data source vertex in the knowledge graph.

Optionally, the first mining processing module is further configured to:

determining the confidence coefficient of the user equipment corresponding to the first user vertex applied to the construction vehicle according to the attribute information of the first user vertex; and updating attribute information of the confidence coefficient, applied to the construction vehicle, of the first user vertex according to the confidence coefficient, applied to the construction vehicle, of the user equipment corresponding to the first user vertex.

Optionally, as shown in fig. 6, the processing device 60 for trajectory data further includes:

a second mining process module 65 configured to:

determining the number of first user vertexes connected with each data source vertex according to the attribute information of the first user vertexes marked as being applied to the construction vehicle in the knowledge graph; determining a first proportion value corresponding to each data source vertex according to the number of first user vertices connected with each data source vertex, wherein the first proportion value is the proportion of the first user vertices in all user nodes connected with the data source vertex; determining a first data source vertex of which the corresponding first proportion value is larger than a first threshold value; searching all user vertexes connected with the first data source vertex in the knowledge graph for a second user vertex of which the attribute information meets a second condition and does not meet a first condition; the second user vertex is marked as applied to the construction vehicle.

Optionally, the second mining processing module is further configured to:

determining the confidence coefficient of the user equipment corresponding to the second user vertex applied to the construction vehicle according to the attribute information of the second user vertex; and updating attribute information of the confidence coefficient of the second user vertex applied to the construction vehicle according to the confidence coefficient of the second user vertex corresponding to the user equipment applied to the construction vehicle.

Optionally, the second excavation processing module is further configured to:

according to the confidence coefficient of the second user vertex corresponding to the user equipment applied to the construction vehicle, before updating attribute information of the confidence coefficient of the second user vertex applied to the construction vehicle, multiplying the confidence coefficient of the second user vertex corresponding to the user equipment applied to the construction vehicle by a preset coefficient, wherein the preset coefficient is larger than 0 and is smaller than 1.

Optionally, the information determining module is further configured to:

determining and outputting at least one of the following information of any data source according to the attribute information marked as applied to the user vertex of the construction vehicle:

identification information in the data source that applies to the user device of the construction vehicle.

a road fulfillment processing module 66 configured to:

according to the user equipment information of each data source applied to the construction vehicle, construction track data are removed from track data on a preset construction road, wherein the construction track data are the track data of the user equipment applied to the construction vehicle; and judging whether the preset construction road meets the opening condition or not according to the residual track data on the preset construction road after the construction track data are removed.

The apparatus provided in the embodiment of the present disclosure may be specifically configured to execute the method embodiment provided in the second embodiment, and specific functions and technical effects achieved are not described herein again.

It should be noted that the trajectory data of the user equipment in this embodiment is not trajectory data for a specific user, and cannot reflect personal information of a specific user.

In the technical scheme of the disclosure, the collection, storage, use, processing, transmission, provision, disclosure and other processing of the personal information of the related user are all in accordance with the regulations of related laws and regulations and do not violate the good customs of the public order.

The present disclosure also provides an electronic device, a readable storage medium, and a computer program product according to embodiments of the present disclosure.

According to an embodiment of the present disclosure, the present disclosure also provides a computer program product comprising: a computer program, stored in a readable storage medium, from which at least one processor of the electronic device can read the computer program, the at least one processor executing the computer program causing the electronic device to perform the solution provided by any of the embodiments described above.

FIG. 7 illustrates a schematic block diagram of an example electronic device 700 that can be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the disclosure described and/or claimed herein.

As shown in fig. 7, the device 700 comprises a computing unit 701, which may perform various suitable actions and processes according to a computer program stored in a Read Only Memory (ROM)702 or a computer program loaded from a storage unit 708 into a Random Access Memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the device 700 can also be stored. The computing unit 701, the ROM 702, and the RAM 703 are connected to each other by a bus 704. An input/output (I/O) interface 705 is also connected to bus 704.

Various components in the device 700 are connected to the I/O interface 705, including: an input unit 706 such as a keyboard, a mouse, or the like; an output unit 707 such as various types of displays, speakers, and the like; a storage unit 708 such as a magnetic disk, optical disk, or the like; and a communication unit 709 such as a network card, modem, wireless communication transceiver, etc. The communication unit 709 allows the device 700 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.

Computing unit 701 may be a variety of general and/or special purpose processing components with processing and computing capabilities. Some examples of the computing unit 701 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and so forth. The calculation unit 701 executes the respective methods and processes described above, such as the processing method of the trajectory data. For example, in some embodiments, the processing of trajectory data may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as storage unit 708. In some embodiments, part or all of a computer program may be loaded onto and/or installed onto device 700 via ROM 702 and/or communications unit 709. When the computer program is loaded into the RAM 703 and executed by the computing unit 701, one or more steps of the processing method of trajectory data described above may be performed. Alternatively, in other embodiments, the computing unit 701 may be configured by any other suitable means (e.g. by means of firmware) to perform the processing method of the trajectory data.

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), system on a chip (SOCs), Complex Programmable Logic Devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.

Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.

The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The Server can be a cloud Server, also called a cloud computing Server or a cloud host, and is a host product in a cloud computing service system, so as to solve the defects of high management difficulty and weak service expansibility in the traditional physical host and VPS service ("Virtual Private Server", or simply "VPS"). The server may also be a server of a distributed system, or a server incorporating a blockchain.

It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present disclosure may be executed in parallel, sequentially, or in different orders, and are not limited herein as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved.

The above detailed description should not be construed as limiting the scope of the disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present disclosure should be included in the scope of protection of the present disclosure.

Claims

1. A method for processing track data comprises the following steps:

2. The method of claim 1, wherein the constructing a knowledge-graph from trajectory data of the user device comprises:

extracting the track characteristic information of each user equipment according to the track data of each user equipment;

constructing a knowledge graph according to the track characteristic information of each user device, wherein the attribute information of each user vertex in the knowledge graph comprises the track characteristic information of the corresponding user device, and the attribute information of each data source vertex is initialized to a preset attribute value;

and according to the attribute information of all user vertexes connected with each data source vertex, determining the attribute information of the data source vertex, and updating the attribute information of each data source vertex in the knowledge graph.

3. The method of claim 1, wherein after searching the knowledge-graph for a first user vertex for which attribute information satisfies a first condition, further comprising:

determining the confidence coefficient of the user equipment corresponding to the first user vertex applied to the construction vehicle according to the attribute information of the first user vertex;

and updating attribute information of the confidence coefficient of the first user vertex applied to the construction vehicle according to the confidence coefficient of the user equipment corresponding to the first user vertex applied to the construction vehicle.

4. The method of any of claims 1-3, wherein the searching the knowledge-graph for a first user vertex for which attribute information satisfies a first condition, after marking the first user vertex as applied to a construction vehicle, further comprises:

determining the number of first user vertexes connected with each data source vertex according to the attribute information of the first user vertexes marked as being applied to the construction vehicle in the knowledge graph;

determining a first proportion value corresponding to each data source vertex according to the number of first user vertices connected with the data source vertex, wherein the first proportion value is the proportion of the first user vertices in all user nodes connected with the data source vertex;

determining a first data source vertex corresponding to the first proportion value larger than a first threshold value;

searching all user vertexes connected with the first data source vertex in the knowledge graph for a second user vertex of which the attribute information meets a second condition and does not meet the first condition;

marking the second user vertex as applied to a construction vehicle.

5. The method of claim 4, wherein after searching for a second user vertex whose attribute information satisfies a second condition and does not satisfy the first condition among all user vertices in the knowledge-graph connected to the first data source vertex, further comprising:

determining the confidence coefficient of the user equipment corresponding to the second user vertex applied to the construction vehicle according to the attribute information of the second user vertex;

and updating attribute information of the confidence coefficient of the second user vertex applied to the construction vehicle according to the confidence coefficient of the second user vertex corresponding to the user equipment applied to the construction vehicle.

6. The method of claim 5, wherein before updating the attribute information of the confidence level applied to the construction vehicle of the second user vertex according to the confidence level applied to the construction vehicle by the user equipment corresponding to the second user vertex, the method further comprises:

multiplying a confidence coefficient of the second user vertex corresponding to the user equipment applied to the construction vehicle by a preset coefficient, wherein the preset coefficient is greater than 0 and is less than 1.

7. The method of any of claims 1-6, wherein said determining user equipment information applied to a construction vehicle for each data source from attribute information tagged as user vertices applied to a construction vehicle comprises:

8. The method of any of claims 1-6, wherein after determining user device information for each data source for application to a construction vehicle based on attribute information tagged as user vertices for application to the construction vehicle, further comprising:

according to the user equipment information of each data source applied to the construction vehicle, construction track data are removed from track data on a preset construction road, wherein the construction track data are the track data of the user equipment applied to the construction vehicle;

and judging whether the preset construction road meets the opening condition or not according to the residual track data on the preset construction road after the construction track data are removed.

9. A trajectory data processing device, comprising:

and the information determining module is used for determining the user equipment information of each data source applied to the construction vehicle according to the attribute information marked as the user vertex applied to the construction vehicle.

10. The apparatus of claim 9, wherein the knowledge-graph building module comprises:

the track feature extraction unit is used for extracting track feature information of each user equipment according to the track data of each user equipment;

the knowledge graph constructing unit is used for constructing a knowledge graph according to the track characteristic information of each user device, the attribute information of each user vertex in the knowledge graph comprises the track characteristic information of the corresponding user device, and the attribute information of each data source vertex is initialized to a preset attribute value;

and the attribute updating unit is used for determining the attribute information of the data source vertex according to the attribute information of all user vertexes connected with each data source vertex, and updating the attribute information of each data source vertex in the knowledge graph.

11. The apparatus of claim 9, wherein the first mining process module is further to:

12. The apparatus of any of claims 9-11, further comprising:

a second mining processing module to:

marking the second user vertex as applied to a construction vehicle.

13. The apparatus of claim 12, the second mining process module further to:

14. The apparatus of claim 13, the second mining process module further to:

15. The apparatus of any of claims 9-14, wherein the information determination module is further to:

16. The apparatus of any of claims 9-14, further comprising:

the road opening processing module is used for:

17. An electronic device, comprising:

at least one processor; and

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-8.

18. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1-8.

19. A computer program product comprising a computer program which, when executed by a processor, carries out the steps of the method of any one of claims 1 to 8.