Data processing method and device, storage medium, equipment and program product

Abstract

The embodiment of the invention relates to the technical field of computers, and discloses a data processing method and device, a storage medium, equipment and a program product, and the method comprises the steps: obtaining road data from a plurality of track data sources, and determining the road data corresponding to a changing road from the road data of each track data source; performing data change prediction on the road data corresponding to the changed road to obtain a predicted change time point of a road element in the changed road; based on the actual change time point and the predicted change time point of the road elements in the changing road, the change prediction contribution degree of each track data source to the road elements is obtained; and based on the change prediction contribution degree corresponding to each track data source, selecting a target data source from the plurality of track data sources, and taking the target data source as a business data source of the road business associated with the road elements. By adopting the embodiment of the invention, the data source helpful for business analysis can be accurately screened out.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to data processing methods, apparatus, storage media, devices and program products. Background Technology

[0002] With the rise of the Internet of Vehicles (IoV), applications in fields such as mapping and navigation are increasing; correspondingly, the number of data sources providing driving trajectory data for vehicles and other objects is also growing. Currently, data from these sources can assist in the analysis of some IoV business operations. However, not all data sources are helpful for business analysis. Therefore, accurately selecting data sources that are helpful for business analysis is a pressing issue that needs to be addressed. Summary of the Invention

[0003] This application provides a data processing method, apparatus, and storage medium that can accurately filter out data sources that are helpful for business analysis.

[0004] On one hand, embodiments of this application provide a data processing method, including:

[0005] Acquire road data from multiple trajectory data sources, and determine the road data corresponding to changed roads from the road data of each trajectory data source; changed roads refer to roads whose road features have changed within a historical time period;

[0006] Data change prediction is performed on the road data corresponding to the changed road to obtain the predicted change time points of road elements in the changed road;

[0007] Based on the actual and predicted change times of road elements in the changing road, the contribution of each trajectory data source to the prediction of changes in road elements is obtained.

[0008] Based on the change prediction contribution of each trajectory data source, a target data source is selected from multiple trajectory data sources, and the target data source is used as the business data source for road operations associated with road elements.

[0009] On one hand, embodiments of this application provide a data processing apparatus, which includes an acquisition unit, a prediction unit, a processing unit, and a filtering unit, wherein:

[0010] The acquisition unit is used to acquire road data from multiple trajectory data sources and determine the road data corresponding to the changed roads from the road data of each trajectory data source; the changed roads refer to roads whose road elements have changed within a historical time period;

[0011] The prediction unit is used to predict the changes in road data corresponding to the changed road, and to obtain the predicted time points of change of road elements in the changed road.

[0012] The processing unit is used to obtain the contribution of each trajectory data source to the prediction of changes in road elements based on the actual and predicted change times of road elements in the changing road.

[0013] The filtering unit is used to select a target data source from multiple trajectory data sources based on the change prediction contribution corresponding to each trajectory data source, and to use the target data source as the business data source for road operations associated with road elements.

[0014] In one embodiment of this application, based on the aforementioned scheme, when the processing unit obtains the predicted contribution of each trajectory data source to the change of road elements based on the actual change time point and the predicted change time point of road elements in the changing road, it can specifically perform the following: calculate the time difference between the actual change time point and the predicted change time point; obtain the first traffic flow of the changing road within a first preset time period before the actual change time point, and the second traffic flow of the changing road within a second preset time period after the actual change time point; and obtain the predicted contribution of each trajectory data source to the change of road elements based on the time difference, the first traffic flow, and the second traffic flow.

[0015] In one embodiment of this application, based on the aforementioned scheme, when the processing unit obtains the predicted contribution of each trajectory data source to the change of road elements according to the time difference, the first traffic flow, and the second traffic flow, it can specifically perform the following: calculate the traffic flow difference between the first traffic flow and the second traffic flow; obtain the initial predicted contribution based on the traffic flow difference and the time difference; obtain the data confidence of each trajectory data source, and obtain the predicted contribution of each trajectory data source to the change of road elements according to the data confidence of each trajectory data source and the initial predicted contribution.

[0016] In one embodiment of this application, when the prediction unit performs data change prediction on the road data corresponding to the changed road to obtain the predicted change time point of the road elements in the changed road, it can also be used to perform: obtaining the traffic flow time series data of the changed road from the road data corresponding to the changed road; performing change point detection on the traffic flow time series data to obtain the predicted change time point of the road elements in the changed road.

[0017] In one embodiment of this application, the traffic flow time series data includes traffic flow data corresponding to multiple dates. When the prediction unit performs change point detection on the traffic flow time series data to obtain the predicted change time points of road elements in the changing road, it can specifically perform the following: dividing the traffic flow data corresponding to the same date based on multiple preset time intervals to obtain the traffic flow data corresponding to the same date in each preset time interval; constructing interval traffic flow time series data corresponding to each preset time interval based on the traffic flow data corresponding to different dates in the same preset time interval; and performing change point detection on each interval traffic flow time series data to obtain the predicted change time points of road elements in each preset time interval.

[0018] In one embodiment of this application, when the prediction unit obtains the predicted contribution of each trajectory data source to the change of road elements based on the actual change time point and the predicted change time point of road elements in the changing road, it can specifically perform the following: based on the predicted change time point and the actual change time point corresponding to the traffic flow time series data of each interval, obtain the predicted contribution of each interval traffic flow time series data to the change of road elements; and based on the predicted contribution of each interval traffic flow time series data to the change of road elements, obtain the predicted contribution of each trajectory data source to the change of road elements.

[0019] In one embodiment of this application, based on the aforementioned scheme, when the processing unit obtains the change prediction contribution of each trajectory data source to road elements according to the change prediction contribution corresponding to the time series data of each interval traffic flow, it can specifically perform the following: obtain the time weight corresponding to each preset time interval; perform weighted processing on the change prediction contribution corresponding to the time series data of the corresponding interval traffic flow based on the time weight corresponding to each preset time interval, to obtain the weighted prediction contribution corresponding to the time series data of each interval traffic flow; and obtain the change prediction contribution of each trajectory data source to road elements according to the weighted prediction contribution corresponding to the time series data of each interval traffic flow.

[0020] In one embodiment of this application, based on the aforementioned scheme, when the prediction unit performs change point detection on traffic flow time series data to obtain the predicted change time points of road elements in the changing road, it can specifically perform the following: for each time point in the traffic flow time series data, obtain the prior probability and likelihood of each time point; calculate the posterior probability of each time point based on the prior probability and likelihood; and take the time point with the highest posterior probability in the traffic flow time series data as the predicted change time point of road elements in the changing road.

[0021] In one embodiment of this application, based on the aforementioned scheme, when the acquisition unit acquires road data from multiple trajectory data sources, it can specifically perform the following: acquire driving trajectory data collected by each candidate trajectory data source among multiple candidate trajectory data sources; select multiple trajectory data sources that meet a preset magnitude standard from the multiple candidate trajectory data sources based on the driving trajectory data corresponding to each candidate trajectory data source; wherein, the preset magnitude standard is set based on the data requirements of road business; and obtain road data from multiple trajectory data sources based on the driving trajectory data corresponding to the selected multiple trajectory data sources.

[0022] In one embodiment of this application, based on the aforementioned scheme, when the screening unit selects a target data source from multiple trajectory data sources based on the change prediction contribution corresponding to each trajectory data source, it can specifically perform the following: compare the change prediction contribution corresponding to each trajectory data source with a preset contribution to obtain a comparison result; if the comparison result indicates that the change prediction contribution corresponding to each trajectory data source is greater than or equal to the preset contribution, then each trajectory data source is determined as the target data source.

[0023] On one hand, embodiments of this application provide an electronic device, which includes an input interface and an output interface, and further includes:

[0024] A processor, adapted to implement one or more instructions; and,

[0025] A computer storage medium storing one or more instructions adapted to be loaded by the processor and executed by the above-described data processing method.

[0026] On one hand, embodiments of this application provide a computer-readable medium storing computer program instructions, which, when executed by a processor, are used to perform the aforementioned data processing method.

[0027] On one hand, embodiments of this application provide a computer program product or computer program, the computer program product or computer program including computer instructions, the computer instructions being stored in a computer-readable storage medium; a processor of an electronic device reads the computer instructions from the computer-readable storage medium, the processor executes the computer instructions, and when the computer instructions are executed by the processor, they are used to perform the above-described data processing method.

[0028] In the technical solution provided by the embodiments of this application, the predicted change time point for road elements in the changed road is obtained based on the road data corresponding to the changed road in each trajectory data source. Based on the actual change time point and the predicted change time point of the road element, the degree of perception of the road element change by the data in each trajectory data source can be well evaluated, thus obtaining the contribution of each trajectory data source to the prediction of road element change. Subsequently, selecting target data sources based on the change prediction contribution is equivalent to filtering target data sources based on the degree of perception of road element change by each trajectory data source. It is easy to see that the data in the target data sources filtered by the change prediction contribution has a positive contribution to perceiving changes in road elements, thereby helping road-related businesses conduct business analysis, research, or decision-making. Therefore, the embodiments of this application can accurately filter out data sources that are helpful for business analysis, thereby assisting in better business operations and having broad application prospects. Attached Figure Description

[0029] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0030] Figure 1 This is a schematic diagram of the structure of a data processing system provided in an embodiment of this application;

[0031] Figure 2 This is a flowchart illustrating a data processing method provided in an embodiment of this application;

[0032] Figure 3 This is a flowchart illustrating another data processing method provided in an embodiment of this application;

[0033] Figure 4 This is a schematic diagram illustrating the selection process of a business data source provided in an embodiment of this application;

[0034] Figure 5 This is a schematic diagram of a data source selection process provided in an embodiment of this application;

[0035] Figure 6 This is a schematic diagram of an interval flow time series data provided in an embodiment of this application;

[0036] Figure 7 This is a schematic diagram of the structure of a data processing device provided in an embodiment of this application;

[0037] Figure 8This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0038] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0039] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0040] In this application embodiment, the terms "module" or "unit" refer to a computer program or part of a computer program that has a predetermined function and works with other related parts to achieve a predetermined goal, and can be implemented wholly or partially using software, hardware (such as processing circuitry or memory), or a combination thereof. Similarly, a processor (or multiple processors or memory) can be used to implement one or more modules or units. Furthermore, each module or unit can be part of an overall module or unit that includes the functionality of that module or unit.

[0041] The flowcharts shown in the accompanying diagrams are merely illustrative and do not necessarily include all content and operations, nor do they necessarily have to be executed in the described order. For example, some operations may be broken down, while others may be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

[0042] It should also be noted that "multiple" as mentioned in this application refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. The character " / " generally indicates that the preceding and following related objects have an "or" relationship.

[0043] With the rise of the Internet of Vehicles (IoV), applications in fields such as mapping and navigation are increasing; correspondingly, there is a growing number of trajectory data sources that can provide driving trajectory data for various objects such as vehicles and pedestrians. This driving trajectory data can be effectively used for data analysis, research, and decision-making in IoV, mapping, and navigation-related businesses or projects. Data collected by one application can form a data source.

[0044] In practical applications, it has been found that not every data source is beneficial to the business; in fact, the addition of some data sources can bias data analysis, research, or decision-making. Therefore, different types of businesses may require different types of data support. Selecting the most suitable data source based on the specific business needs can effectively help relevant personnel achieve optimal data analysis, research, or decision-making for that business.

[0045] Based on this, this application provides a data processing scheme. After acquiring road data from multiple trajectory data sources, the scheme identifies changing roads from the road data of each trajectory data source and predicts the predicted change time points of road elements within those changing roads based on the road data corresponding to the changing roads. Subsequently, based on the actual and predicted change time points of the road elements, the contribution of each trajectory data source to the prediction of road element changes can be predicted. The prediction contribution of each trajectory data source can be used to filter out target data sources from multiple trajectory data sources. These target data sources will serve as the business data source for road-related business activities associated with the road elements.

[0046] Road data can include road attribute data, road environment data, and traffic flow data. Specifically, road attribute data can include the road's location, length, destination direction, number of lanes, and sidewalk width. Road environment data can include the surrounding vegetation, buildings, and other environmental conditions. Traffic flow data can include at least one of the following traffic flow parameters: the number of vehicles passing through the road (vehicle flow), the number of pedestrians (pedestrian flow), and the number of animals (animal flow).

[0047] A changing road refers to a road whose road features have changed over a historical period. These road features can specifically include factors related to the road itself or its environment that affect its operation. Specifically, road features can include at least one of the following: traffic signs, road environmental conditions, and road load-bearing capacity. For example, road features could include the addition or removal of traffic lights, or the presence of road construction.

[0048] In real life, changes in road features have a significant impact on the travel of vehicles and pedestrians. Therefore, most road-related services in fields such as vehicle-to-everything (V2X) and map navigation, such as route planning and traffic flow optimization, require analysis, research, or decision-making based on changes in road features. Thus, if data from a data source can help perceive changes in road features, it indicates that the data source is positively helpful for the analysis of road-related services.

[0049] It is easy to see that this solution obtains the predicted change time point for road elements on the changing roads based on the road data corresponding to the changing roads in each trajectory data source. Based on the actual and predicted change time points of these road elements, the solution can effectively assess the degree to which the data collected by each trajectory data source perceives changes in road elements, thus obtaining the contribution of each trajectory data source to the prediction of road element changes. Subsequently, selecting target data sources based on this change prediction contribution is equivalent to filtering target data sources based on the degree to which each trajectory data source perceives changes in road elements. Therefore, the data in the target data sources filtered by this solution based on change prediction contribution has a positive contribution to perceiving changes in road elements, thereby helping road-related businesses conduct business analysis, research, or decision-making. Furthermore, by using the target data sources as business data sources for road-related businesses, this solution can accurately filter out data sources that are helpful for business analysis.

[0050] Based on the above data processing method, this application provides a data processing system, which can be found in [reference needed]. Figure 1 , Figure 1 The data processing system shown may include multiple terminal devices 101 and multiple servers 102, wherein a communication connection is established between any terminal device and any server. Terminal devices 101 may include any one or more of the following: sensors, smartphones, tablets, laptops, desktop computers, smart vehicles, and smart wearable devices. Terminal devices 101 may run various vehicle-to-everything (V2X) applications (apps) related to maps and navigation, such as driving navigation clients and hiking route clients; terminal devices 101 may also run various other applications, such as multimedia playback clients, social media clients, browser clients, news feed clients, educational clients, and so on.

[0051] Server 102 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms. Terminal device 101 and server 102 can communicate directly or indirectly via wired or wireless communication; this application does not impose any restrictions on this.

[0052] In one embodiment, the above data processing method can be performed solely by... Figure 1The server 102 in the data processing system described above executes the following process: Server 102 acquires road data from multiple trajectory data sources and determines the road data corresponding to changed roads from the road data of each trajectory data source. Changed roads refer to roads whose road elements have changed within a historical time period. Server 102 performs data change prediction on the road data corresponding to the changed roads to obtain the predicted change time points of road elements in the changed roads. Based on the actual change time points and predicted change time points of road elements in the changed roads, Server 102 obtains the contribution of each trajectory data source to the change prediction of road elements. Based on the change prediction contribution of each trajectory data source, Server 102 selects a target data source from multiple trajectory data sources and uses the target data source as the business data source for road business associated with road elements.

[0053] Alternatively, the above data processing method can also be performed solely by... Figure 1 The terminal device 101 in the data processing system shown executes the process, and its specific execution process can be found in the specific execution process of the server 102 during data processing, which will not be repeated here. Optionally, after the server 102 uses the target data source as the business data source for road services associated with road elements, it can analyze and process the aforementioned road services based on the data in the target data source. Furthermore, since the data in the data source is constantly updated, the server 102 can also continuously acquire data from the target data source and analyze and process the aforementioned road services based on the continuously acquired data.

[0054] In another embodiment, the above data processing method can be provided by Figure 1 The data processing system shown in the diagram is jointly executed by terminal devices 101 and server 102. Specifically, multiple applications running on the terminal devices 101 send collected driving trajectory data to server 102. Server 102 receives the driving trajectory data from each terminal device 101, forming multiple trajectory data sources, and retrieves road data corresponding to the changed roads from each trajectory data source. Server 102 performs data change prediction on the road data corresponding to the changed roads, obtaining the predicted change time points of road elements in the changed roads. Based on the actual and predicted change time points of road elements in the changed roads, server 102 obtains the contribution of each trajectory data source to the predicted change of road elements. Based on the predicted change contribution of each trajectory data source, server 102 selects a target data source from the multiple trajectory data sources and uses the target data source as the business data source for road services associated with the road elements.

[0055] It should be noted that the embodiments of this application can be applied to various scenarios, including but not limited to smart transportation, cloud technology, AI (Artificial Intelligence), intelligent driving, and so on, and are not limited thereto.

[0056] Furthermore, in specific embodiments of this application, if road data, road elements, or other data or information involve objects, when the embodiments of this application are applied to specific products or technologies, permission or consent from the objects is required, and the collection, use, and processing of related data or information must comply with the relevant laws, regulations, and standards of the relevant countries and regions.

[0057] Based on the above data processing scheme and system, this application provides a data processing method. See also... Figure 2 This is a flowchart illustrating a data processing method provided in an embodiment of this application. Figure 2 The data processing method shown can be executed by a server or a terminal device. In this embodiment, the method is described using an example of execution by a server.

[0058] in, Figure 2 The data processing method shown may include steps S201 to S204:

[0059] S201, acquire road data from multiple trajectory data sources, and determine the road data corresponding to the changed roads from the road data of each trajectory data source; changed roads refer to roads whose road elements have changed within a historical time period.

[0060] In this embodiment, driving trajectory data collected through the same application can form a trajectory data source. Road data is obtained based on the driving trajectory data generated by the user on the application client. For example, if a user uses a navigation client to assist driving through a certain road, then the data collected by the navigation client during the user's passage through that road is the driving trajectory data about that road generated by the user on the navigation client.

[0061] Road data can include road attribute data, road environment data, and road traffic flow data. Specifically, a segment of a road can be represented by a route on a map; since applications may collect data from the road at any given time, road data can be recorded in time series format; therefore, road data is essentially time-series data.

[0062] Road elements can specifically include factors related to the road itself or the road environment that affect road operation. For example, road elements can include traffic lights, road construction status, etc.; correspondingly, changes in road elements can include the addition or removal of traffic lights, and whether there is road construction.

[0063] The changed path contains at least one changing path element within the historical time period. The historical time period can be manually set or set by the terminal devices or servers in the aforementioned data processing system; no limitation is made here. For example, the historical time period could be the most recent 30 days, the most recent week, 8:00 AM to 8:00 PM on a certain day, or September 10, 2024 to October 10, 2024, etc.

[0064] In one embodiment, the changed roads whose road features have changed over a historical period can be identified through actual inspection and manual annotation; then, data related to the changed roads can be retrieved from the data of each trajectory data source as the road data of the changed roads.

[0065] Optionally, the aforementioned different types of business may require different types of data support. Therefore, if you want to subsequently select data sources that are accurately adapted to a specific road business, when identifying changed roads, you can identify roads whose road elements associated with that road business have changed during the historical time period as changed roads.

[0066] Optionally, if the road elements of a massive number of roads may have changed over a historical period, to avoid excessive data computation burdening the server and to improve data processing efficiency, a certain number of roads can be sampled from the multiple roads whose road elements have changed as the changed roads. This ensures that the data source suitable for the business can be accurately selected later, while also improving data processing efficiency.

[0067] In one embodiment, since different road services have different data requirements, the data volume standards for different road services will also differ. For example, some road services may require a large enough data volume, some road services may require the data to cover a wide enough range of cities, and some road services may require the data to cover certain cities or streets, etc.

[0068] Therefore, the specific process of obtaining road data from multiple trajectory data sources may include: obtaining driving trajectory data collected by each candidate trajectory data source among multiple candidate trajectory data sources; selecting multiple trajectory data sources that meet the preset magnitude standard from multiple candidate trajectory data sources based on the driving trajectory data corresponding to each candidate trajectory data source; and obtaining road data from multiple trajectory data sources based on the driving trajectory data corresponding to the selected multiple trajectory data sources.

[0069] The preset data volume standards can be set manually or by the terminal devices or servers in the aforementioned data processing system; no limitation is made here. Specifically, the preset data volume standards can be set based on the data requirements of specific road operations. In this way, by setting preset data volume standards, some data sources with significant data defects or unsuitability for road operations can be eliminated, which helps improve the efficiency of data source filtering.

[0070] Optionally, the preset threshold can be that the number of cities is greater than or equal to a preset number. Therefore, the specific process of acquiring road data from multiple trajectory data sources can include: acquiring the driving trajectory data collected by each candidate trajectory data source from multiple candidate trajectory data sources, and the number of cities covered by each driving trajectory data; selecting multiple trajectory data sources from the multiple candidate trajectory data sources whose corresponding number of cities is greater than or equal to a preset number; and obtaining the road data from the multiple trajectory data sources based on the driving trajectory data corresponding to the selected multiple trajectory data sources.

[0071] Optionally, the specific process of obtaining road data from multiple trajectory data sources based on the driving trajectory data corresponding to the selected multiple trajectory data sources may include: performing data preprocessing on the driving trajectory data corresponding to the selected multiple trajectory data sources to obtain road data from multiple trajectory data sources. Data preprocessing may include at least one of data cleaning and data imputation. Data cleaning may specifically include at least one method such as deleting duplicate data, invalid data, or other dirty data, data error correction, and data standardization. Data imputation may specifically include at least one method such as interpolation imputation, mean imputation, and median imputation.

[0072] S202, perform data change prediction on the road data corresponding to the changed road to obtain the predicted change time points of road elements in the changed road.

[0073] In this embodiment, it is considered that as road elements change, road data such as traffic flow, pedestrian flow, and the number of lanes available for traffic will also be affected and change accordingly; that is, changes in road data often reflect changes in road elements. Therefore, the predicted time point of change for road elements can be obtained by predicting the changes in road data corresponding to the changed roads.

[0074] In one embodiment, since the aforementioned road data is time-series data, the predicted change time points of road elements in changing roads can be obtained by performing change point detection on the road data. Change point detection is a statistical method used to identify points in time-series data where the state or distribution has undergone significant changes. Specifically, at least one of the following change point detection algorithms can be used: Bayesian online change point detection algorithm, Cumulative Sum Control Chart (CUSUM, a statistical method for detecting changes in the mean in time-series data).

[0075] Optionally, other methods or algorithms can be used to predict data changes, such as the magnitude of data changes or the distribution of data, to obtain the predicted time point of change. This is not limited here.

[0076] S203, based on the actual and predicted change times of road elements in the changing road, obtain the contribution of each trajectory data source to the prediction of changes in road elements.

[0077] In this embodiment, the actual change time point refers to the time point at which the road elements in the changed road actually change. The actual change time point can be manually marked.

[0078] Specifically, the smaller the difference between the predicted and actual change times, the more accurate the prediction of changes in road elements based on road data. This means that the road data can be well-predicted to predict changes in road elements, and thus the road data provides greater positive assistance to the road business associated with the road elements. Therefore, the contribution of each trajectory data source to the prediction of changes in road elements can be obtained based on the time difference between the actual and predicted change times of road elements in the changing road.

[0079] Optionally, if the difference between the road data before and after the actual change time of the road elements is greater, it indicates that the road data is more sensitive to changes in road elements and can perceive changes in road elements well. This also means that the road data is more helpful to road operations. Therefore, in order to further improve the accuracy of the change prediction contribution, in addition to the time difference, the contribution of each trajectory data source to the change prediction of road elements can be obtained based on the partial data before the actual change time and the partial data after the actual change time in the road data.

[0080] In one embodiment, the specific process of obtaining the change prediction contribution may include: calculating the time difference between the actual change time point and the predicted change time point; obtaining the first traffic flow of the changed road within a first preset time period before the actual change time point, and the second traffic flow of the changed road within a second preset time period after the actual change time point; and obtaining the change prediction contribution of each trajectory data source to the road element based on the time difference, the first traffic flow, and the second traffic flow.

[0081] The first traffic flow includes the number of traffic objects passing through the changed road within a first preset time period; the traffic objects may include at least one of vehicles, pedestrians, and animals. Furthermore, the first road traffic flow can be at least one of the total traffic flow, median traffic flow, and average traffic flow of the changed road within the first preset time period, and is not limited here. The second traffic flow is similar and will not be elaborated further here.

[0082] The first and second preset time periods can be set manually or by the terminal devices or servers in the aforementioned data processing system; no limitation is made here. Specifically, the lengths of the first and second preset time periods can be the same or different.

[0083] As mentioned earlier, the greater the difference in road data before and after the actual change in road elements, the more sensitive the data is to changes in road elements. Therefore, the contribution of each trajectory data source to the prediction of changes in road elements can be obtained based on the time difference and the traffic flow difference between the first and second roads.

[0084] In one embodiment, considering that the reliability of data from different trajectory data sources may vary—for example, the reliability of data from map applications is generally higher than that of data from third-party ride-hailing applications—the confidence level of different trajectory data sources can be pre-set based on their reliability.

[0085] The process of obtaining the change prediction contribution can specifically include: calculating the traffic flow difference between the first and second traffic flows; obtaining the initial prediction contribution based on the traffic flow difference and the time difference; obtaining the data confidence of each trajectory data source; and obtaining the change prediction contribution of each trajectory data source to road elements based on the data confidence of each trajectory data source and the initial prediction contribution.

[0086] Specifically, the data confidence level and initial prediction contribution of each trajectory data source can be multiplied to obtain the prediction contribution of each trajectory data source to the changes in road features.

[0087] S204, based on the change prediction contribution of each trajectory data source, selects a target data source from multiple trajectory data sources, and uses the target data source as the business data source for road operations associated with road elements.

[0088] In this embodiment, the change prediction contribution of the target data source is greater than the change prediction contribution of other trajectory data sources among multiple trajectory data sources. The number of target data sources may include one or more.

[0089] In one embodiment, the specific method for selecting a target data source from multiple trajectory data sources may include: comparing the change prediction contribution of each trajectory data source with a preset contribution to obtain a comparison result; if the comparison result indicates that the change prediction contribution of each trajectory data source is greater than or equal to the preset contribution, then each trajectory data source is determined as the target data source.

[0090] The preset contribution level can be set manually or by the terminal devices or servers in the aforementioned data processing system; no limitation is made here. Specifically, the preset contribution level can also be flexibly set by the server for the change prediction contribution levels corresponding to multiple trajectory data sources. For example, if a preset number of trajectory data sources need to be selected as the business data sources for road operations, then multiple change prediction contribution levels can be sorted from largest to smallest, and the change prediction contribution level whose sequence number matches the preset number can be set as the preset contribution level.

[0091] In one embodiment, the change prediction contributions corresponding to multiple trajectory data sources can be sorted to obtain multiple sorted change prediction contributions. Then, the trajectory data sources corresponding to change prediction contributions with serial numbers less than or equal to a preset number are selected from the sorted multiple change prediction contributions as the target data source. The preset number can be manually set or set by the terminal device or server in the aforementioned data processing system, and is not limited here.

[0092] In one possible implementation, after using the target data source as the business data source for road operations associated with road elements, the data in the target data source can be directly used as the business data for road operations to perform business analysis on the road operations.

[0093] Optionally, the application will continuously collect driving trajectory data and upload it to the corresponding trajectory data source. Therefore, it can also continuously acquire data from the target data source and use the continuously acquired data as business data for road operations to conduct business analysis.

[0094] In practical implementation, in business scenarios involving the mining of changes in road elements, the contribution of multiple applications to change prediction can be evaluated through the embodiments of this application, thereby selecting a data source suitable for the road element change mining business. Then, the driving trajectory data from the trajectory data source can be aggregated, and the aggregated data can be preprocessed, such as data cleaning and filling in missing data, to obtain processed data. Finally, based on the processed data, a relevant model algorithm is constructed to predict roads whose road elements have changed within the current period. After manual verification that the road elements have indeed changed, the changed road elements are written into the map master database. This ensures that the maps presented to users based on the map master database data are more accurate and closer to the actual road conditions.

[0095] In one embodiment, as business operations change, the original data source may no longer be suitable for the business. Therefore, in order to further improve the adaptability of the data source to the business, steps S201 to S204 can be executed periodically or irregularly to re-select the business data source for the road business.

[0096] In this embodiment, the predicted change time point for road elements in the changed road is obtained based on the road data corresponding to the changed road in each trajectory data source. Based on the actual and predicted change time points of these road elements, the perceptibility of each trajectory data source's road data to changes in road elements can be effectively assessed, thus obtaining the contribution of each trajectory data source to the prediction of road element changes. Subsequently, selecting target data sources based on the change prediction contribution is equivalent to filtering target data sources based on the perceptibility of each trajectory data source to changes in road elements. It is easy to see that the data in the target data sources filtered by the change prediction contribution has a positive contribution to perceiving changes in road elements, thereby helping road-related businesses conduct business analysis, research, or decision-making. Therefore, this embodiment can accurately filter data sources that are helpful for business analysis, thereby assisting in better business operations and has broad application prospects.

[0097] Based on the above data processing scheme and system, this application provides another data processing method. See also... Figure 3 This is a flowchart illustrating another data processing method provided in an embodiment of this application. Figure 3 The data processing method shown can be derived from Figure 1 The method is executed by the server or terminal device shown. In this embodiment, the method is described using the server as an example. Figure 3 The method shown has been extended.

[0098] in, Figure 3The data processing method shown may include the following steps S301 to S305:

[0099] S301, acquire road data from multiple trajectory data sources, and determine the road data corresponding to the changed road from the road data of each trajectory data source; the changed road refers to the road whose road elements have changed within a historical time period.

[0100] The specific implementation of step S301 can be found in the specific implementation of step S201, and will not be repeated here.

[0101] S302, Obtain the traffic flow time series data of the changed road from the road data corresponding to the changed road.

[0102] In this embodiment, the traffic flow time series data includes traffic flow data corresponding to multiple time points. The traffic flow data may include at least one of pedestrian traffic data, vehicle traffic data, and animal traffic data. Each time point in the traffic flow time series data can represent a certain period of time, a certain date, or a certain moment, and is not limited thereto.

[0103] S303 performs change point detection on traffic flow time series data to obtain the predicted change time points of road elements in the changing road.

[0104] In this embodiment of the application, the specific process of change point detection may include: for each time point in the traffic flow time series data, obtaining the prior probability and likelihood of each time point; calculating the posterior probability of each time point based on the prior probability and likelihood; and taking the time point with the highest posterior probability in the traffic flow time series data as the predicted change time point of the road elements in the changing road.

[0105] In specific implementations, at least one of the following change point detection algorithms can be used to detect change points in traffic flow time series data: Cumulative Sum Control Chart (CUSUM, a statistical method for detecting changes in the mean in time series data), Pruned Exact Linear Time (Pelt, an efficient online change point detection algorithm that can find the optimal segmentation scheme in near linear time), and binary search. No specific method is specified here.

[0106] In one possible implementation, traffic flow time-series data can include traffic flow data for multiple dates. Considering that road traffic flow data exhibits different patterns at different times of the day—for example, traffic flow during morning or evening rush hours may be similar to the total daily traffic flow—and that traffic flow changes during these periods are often more sensitive to changes in road features, this approach helps to predict more accurate change timing.

[0107] Therefore, traffic flow data for the same date can be divided into multiple preset time intervals to obtain traffic flow data for the same date in each preset time interval. Then, based on the traffic flow data for different dates in the same preset time interval, interval traffic flow time series data can be constructed for each preset time interval. Finally, change point detection can be performed on each interval traffic flow time series data to obtain the predicted change time points of road elements in each preset time interval.

[0108] The multiple preset time intervals can be manually set or set by the terminal devices or servers in the aforementioned data processing system; no limitation is made here. Specifically, multiple preset time intervals can be set based on the changing patterns of road traffic flow, and the sum of the duration of these multiple preset time intervals can be less than or equal to one day. For example, multiple preset time intervals can include morning peak (e.g., 7:30 to 9:00), noon (e.g., 11:00 to 13:00), evening peak (e.g., 17:00 to 20:00), and early morning (e.g., 11:00 to 12:00), etc.

[0109] S304, based on the actual and predicted change times of road elements in the changing road, obtain the contribution of each trajectory data source to the prediction of changes in road elements.

[0110] In this embodiment, the actual change time point can be manually labeled. The specific process for obtaining the change prediction contribution can be found in step S203, and will not be elaborated here.

[0111] In one embodiment, since step S303 mentions that traffic flow time series data can be divided into multiple interval traffic flow time series data, the predicted change time point and the actual change time point corresponding to each interval traffic flow time series data can be used to obtain the change prediction contribution of each interval traffic flow time series data; then, based on the change prediction contribution of each interval traffic flow time series data, the change prediction contribution of each trajectory data source to road elements can be obtained.

[0112] The specific process for obtaining the change prediction contribution of each interval flow time series data can be found in the specific implementation method in step S203. Optionally, the specific process for obtaining the change prediction contribution of each interval flow time series data may include: calculating the time difference between the predicted change time point and the actual change time point corresponding to each interval flow time series data; then, obtaining the first interval flow within a first preset time period before the actual change time point and the second interval flow within a second preset time period before the actual change time point from each interval flow time series data; and obtaining the change prediction contribution of each interval flow time series data based on the calculated time difference, the first interval flow, and the second interval flow.

[0113] Specifically, the flow difference between the first interval and the second interval can be calculated; then, based on the calculated flow difference and time difference, the predicted contribution of the flow time series data for each interval can be obtained.

[0114] In addition, the change prediction contribution of each trajectory data source can be obtained by performing linear transformations such as addition, multiplication, and subtraction on the change prediction contribution of all interval traffic time series data; alternatively, the change prediction contribution of each trajectory data source can be obtained by performing nonlinear transformations such as activation and mapping on the change prediction contribution of interval traffic time series data. No limitation is imposed here.

[0115] In one embodiment, considering that the traffic flow through roads is affected by changes in road elements to varying degrees within different preset time intervals, the sensitivity of traffic flow time-series data to changes in road elements varies across different intervals. For example, road construction has a significant impact on traffic flow during morning and evening rush hours, but since there are few vehicles passing through the roads in the early morning, road construction has a smaller impact on traffic flow in the early morning. Therefore, different time weights can be assigned to different preset time intervals to improve the accuracy of the final change prediction contribution. Specifically, the time weights of the preset time intervals can be proportional to the degree to which traffic flow is affected by changes in road elements.

[0116] Therefore, the specific process of obtaining the change prediction contribution of each trajectory data source to road element changes based on the change prediction contribution of each interval traffic time series data can include: obtaining the time weight corresponding to each preset time interval; weighting the change prediction contribution of the corresponding interval traffic time series data based on the time weight of each preset time interval to obtain the weighted prediction contribution of each interval traffic time series data; and obtaining the change prediction contribution of each trajectory data source to road element changes based on the weighted prediction contribution of each interval traffic time series data.

[0117] Specifically, the weighted prediction contribution of each interval's traffic flow time series data can be added together to obtain the prediction contribution of each trajectory data source to the changes in road elements.

[0118] S305, based on the change prediction contribution of each trajectory data source, selects a target data source from multiple trajectory data sources, and uses the target data source as the business data source for road operations associated with road elements.

[0119] In this embodiment of the application, the data from the business data source of the road business can be used for business analysis, research and decision-making of the road business, thus becoming the data support for the road business.

[0120] For specific implementation details, please refer to the appendix. Figure 4 This illustrates a schematic diagram of the selection process for a business data source. For example... Figure 4 As shown, the process of selecting a business data source mainly includes stages such as data processing, data source optimization, aggregation, and results. Here, the data source refers to the original source that provides the data. For example... Figure 4 As shown, the trajectory data sources include applications such as AA Maps, BB Social, and CC Taxi.

[0121] After obtaining data from the trajectory data source, the data needs to be processed to obtain the road data corresponding to each trajectory data source. Data processing may include steps such as magnitude filtering, data filling, and data cleaning. The specific implementation process of magnitude filtering can be found in step S201 regarding the specific implementation of the preset magnitude standard, and will not be elaborated here.

[0122] In the data source selection phase, the target data source is chosen from multiple trajectory data sources based primarily on the road data corresponding to each trajectory data source. For example... Figure 4 As shown, the process of selecting the best data source can be simply summarized as follows: marking the actual change time points (i.e., marking the actual change time points of road elements in the changing road), obtaining the predicted change time points (i.e., the predicted change time points of each data source for road elements in the changing road), and calculating the change prediction contribution of each trajectory data source based on the actual change time points. Finally, based on the change prediction contribution of each trajectory data source, a target data source can be selected from multiple trajectory data sources, or two or more target data sources can be selected from multiple trajectory data sources to form a data source set.

[0123] In one embodiment, see Appendix Figure 5 This illustrates a flowchart of a data source selection process. As shown in steps 501 to 502, 2000 changed roads can be randomly sampled from the roads where road features have actually changed. For example, these 2000 changed roads can be denoted as {L1, L2, ... L...} 2000}

[0124] Then, as shown in step 503, the traffic flow time-series data corresponding to each changed road can be obtained from each trajectory data source. Continuing the example above, assuming the number of trajectory data sources is N, the traffic flow time-series data corresponding to each changed road can be found from each of the N trajectory data sources, denoted as . in, The time-series traffic flow data for the changing road 1 in trajectory data source 1 is used to characterize the trajectory. The traffic flow time series data for changing road 2000 in the trajectory data source 2 is represented by the same data for other data, which will not be elaborated here.

[0125] After obtaining the traffic flow time-series data corresponding to each changed road in each trajectory data source, as shown in step 504, the traffic flow time-series data for each changed road can be split into multiple interval traffic flow time-series data. For example, the traffic flow time-series data for changed road 1 in data source 1 in the above example can be split into four interval traffic flow time-series data based on four preset time intervals: morning (7-9 am), noon (11 am-1 pm), evening (5-7 pm), and early morning (11 pm-1 am), and further split by day to obtain four interval traffic flow time-series data, which can be denoted as follows:

[0126] Then, as shown in steps 505 and 506, the actual time points when the road elements in each changed road actually changed can be manually marked, thus obtaining the actual change time points corresponding to each changed road. For example, the actual change time point of changed road 1 can be marked as... The actual time points of change for road 2 are marked as follows: And the actual time points of change of the changed road 2000 are marked as . The same applies to other changes in the path.

[0127] Furthermore, as shown in steps 507 and 508, change point detection can be performed on the traffic flow time series data for each interval to obtain the change prediction time point corresponding to the traffic flow time series data for each interval. In this way, each trajectory data source has multiple change prediction time points for each changing road. Continuing the above example, in practical applications, the four interval traffic flow time series data points obtained from each trajectory data source for each changing road can be input into the Bayesian online change point detection algorithm to obtain the change prediction time point for the traffic flow time series data for each interval. For example, the change prediction time point can be... After being input into the Bayesian online change detection algorithm, the output change prediction time points are denoted as follows: The same applies to other data, which will not be elaborated here.

[0128] For example, please see the appendix. Figure 6 This illustrates a schematic diagram of time-series data for interval flow. Specifically, Figure 6 This diagram illustrates a trajectory data source for interval traffic flow time-series data of 2000 changing roads. The x-axis of each interval traffic flow time-series data represents the date, and the y-axis represents the traffic volume. Furthermore, it can be seen that... Figure 6 The diagram shows the actual time point of change for each changed road. For example, the actual time point of change for the road element in changed road 1 is October 15th.

[0129] At the same time, such as Figure 6As shown, each of the four traffic flow time series data points corresponds to different roads, from 1 to 2000. These four traffic flow time series data points correspond to the aforementioned four preset time intervals: morning, noon, evening, and early morning. After performing change point detection on each traffic flow time series data point, the predicted change time point for each traffic flow time series data point corresponding to each changed road can be obtained.

[0130] After obtaining the actual change time point and multiple predicted change time points for each changed road, as shown in steps 509 to 511, the contribution calculation formula can be called to calculate the contribution of each trajectory data source to the road element change prediction. Finally, based on the change prediction contribution of each trajectory data source, a target data source is selected from multiple trajectory data sources.

[0131] In practical applications, for each changed road of each trajectory data source, the difference in the number of days between the actual change time point and the change prediction time point can be calculated (which can be understood as the mutation residual), and the difference in the mean value within 7 days before and after the actual change time point can be calculated (which can be understood as the degree of mutation). Finally, the contribution of each trajectory data source to change prediction is calculated using the contribution formula, and the trajectory data source with the largest or top few change prediction contributions is determined as the final optimal target data source.

[0132] The formula for calculating contribution is as follows:

[0133]

[0134] Among them, the score represents the contribution of change prediction. The confidence level of each data source (i.e., the aforementioned data confidence level) is represented by β1, β2, β3, and β4. β1 represents the time weight of the preset time period from 7 to 9 o'clock, β2 represents the time weight of the preset time period from 11 to 13 o'clock, β3 represents the time weight of the preset time period from 17 to 19 o'clock, and β4 represents the time weight of the preset time period from 23 to 1 o'clock.

[0135] X represents the difference in traffic flow between each interval and the actual change point on the corresponding road within 7 days (i.e., the degree of abrupt change). X = mean before -mean after ; where, mean before The mean value represents the average traffic flow over the 7 days preceding the actual time of change for each interval's time-series traffic data. after This represents the average traffic flow for each interval within 7 days after the actual change point in the time series data. X1, X2, X3, and X4 represent the degree of abrupt change in the aforementioned four interval traffic time series data, which will not be elaborated upon here.

[0136] Y represents the time difference (i.e., abrupt change residual) between the predicted time point of change in traffic flow time series data for each interval and the actual time point of change for the corresponding changed road. Y1, Y2, Y3, and Y4 represent the abrupt change residuals of the aforementioned four interval traffic flow time series data, which will not be elaborated upon here. For example, for... Figure 6 Changes in Path 1

[0137] After selecting the target data source, such as Figure 5 As shown in the aggregation and result phases, the target data source can be written into the data source collection, and then the data sources in the data source collection can be used as the business data source for road business associated with road elements.

[0138] In summary, the data source selection method based on the contribution of change prediction proposed in the above examples can effectively select the most suitable data source for road business based on the sensitivity of data to mutations (i.e., the degree of mutation) and the degree of difference in actual changes (i.e., mutation residuals), thereby solving the problem that data sources lack the ability to adapt to temporal mutations and real changes in road elements.

[0139] For example, while third-party data sources like ride-hailing apps may perform well in terms of data quality (i.e., less data omissions and larger data volume), their data often shows significant discrepancies in its perception of actual changes in road elements. Therefore, these data sources can actually interfere with the subsequent determination of real-world changes in road elements. Thus, the method proposed in this example effectively eliminates data sources with poor perception of changes in road elements, selecting those that positively contribute to this perception. This allows for accurate selection of data sources helpful for business analysis, reducing the interference from poorly perceptive data sources on road operations and facilitating subsequent precise analysis, research, and decision-making regarding road operations.

[0140] Considering that traffic flow time series data is the road data most affected by changes in road elements and is the most sensitive to changes in road elements, this application embodiment can obtain more accurate predicted change time points for road elements in changing roads by performing change point detection on the traffic flow time series data of changing roads. More accurate prediction of change time points is conducive to obtaining more accurate change prediction contribution, which in turn helps to more accurately select data sources that are helpful to business analysis.

[0141] Based on the above description of the data processing method, this application also discloses a data processing apparatus. This data processing apparatus can be a computer program (including program code) running on the aforementioned computer device. The data processing apparatus can execute, for example... Figure 2 and Figure 3 For the data processing methods shown, please refer to [link / reference]. Figure 7 The data processing device may include at least: an acquisition unit 701, a prediction unit 702, a processing unit 703, and a filtering unit 704.

[0142] The acquisition unit 701 is used to acquire road data from multiple trajectory data sources and determine the road data corresponding to the changed road from the road data of each trajectory data source; the changed road refers to the road whose road elements have changed within a historical time period;

[0143] The prediction unit 702 is used to predict the data changes of the road data corresponding to the changed road, and obtain the predicted change time points of the road elements in the changed road.

[0144] Processing unit 703 is used to obtain the contribution of each trajectory data source to the prediction of changes in road elements based on the actual and predicted change time points of road elements in the changing road;

[0145] The filtering unit 704 is used to select a target data source from multiple trajectory data sources based on the change prediction contribution corresponding to each trajectory data source, and to use the target trajectory data source as the business data source for road business associated with road elements.

[0146] In one implementation, when the processing unit 703 obtains the predicted contribution of each trajectory data source to the change of road elements based on the actual change time point and the predicted change time point of road elements in the changing road, it can specifically perform the following: calculate the time difference between the actual change time point and the predicted change time point; obtain the first traffic flow of the changing road in a first preset time period before the actual change time point, and the second traffic flow of the changing road in a second preset time period after the actual change time point; and obtain the predicted contribution of each trajectory data source to the change of road elements based on the time difference, the first traffic flow, and the second traffic flow.

[0147] In another embodiment, when the processing unit 703 obtains the predicted contribution of each trajectory data source to the change of road elements based on the time difference, the first traffic flow, and the second traffic flow, it can specifically perform the following: calculate the traffic flow difference between the first traffic flow and the second traffic flow; obtain the initial predicted contribution based on the traffic flow difference and the time difference; obtain the data confidence of each trajectory data source, and obtain the predicted contribution of each trajectory data source to the change of road elements based on the data confidence of each trajectory data source and the initial predicted contribution.

[0148] In another embodiment, when the prediction unit 702 performs data change prediction on the road data corresponding to the changed road to obtain the predicted change time point of the road elements in the changed road, it can also specifically perform: obtaining the traffic flow time series data of the changed road from the road data corresponding to the changed road; performing change point detection on the traffic flow time series data to obtain the predicted change time point of the road elements in the changed road.

[0149] In another embodiment, the traffic flow time series data includes traffic flow data corresponding to multiple dates. When the prediction unit 702 performs change point detection on the traffic flow time series data to obtain the predicted change time points of road elements in the changing road, it can specifically perform the following: dividing the traffic flow data corresponding to the same date based on multiple preset time intervals to obtain the traffic flow data corresponding to the same date in each preset time interval; constructing interval traffic flow time series data corresponding to each preset time interval based on the traffic flow data corresponding to different dates in the same preset time interval; and performing change point detection on each interval traffic flow time series data to obtain the predicted change time points of road elements in each preset time interval.

[0150] In another implementation, when the prediction unit 702 obtains the predicted contribution of each trajectory data source to the change of road elements based on the actual change time point and the predicted change time point of road elements in the changing road, it can specifically perform the following: based on the predicted change time point and the actual change time point corresponding to the traffic flow time series data of each interval, obtain the predicted contribution of each interval traffic flow time series data to the change of road elements; and based on the predicted contribution of each interval traffic flow time series data to the change of road elements, obtain the predicted contribution of each trajectory data source to the change of road elements.

[0151] In another embodiment, when the processing unit 703 obtains the change prediction contribution of each trajectory data source to road elements based on the change prediction contribution corresponding to the time series data of each interval traffic flow, it can specifically perform the following: obtain the time weight corresponding to each preset time interval; perform weighted processing on the change prediction contribution corresponding to the time series data of the corresponding interval traffic flow based on the time weight corresponding to each preset time interval to obtain the weighted prediction contribution corresponding to the time series data of each interval traffic flow; and obtain the change prediction contribution of each trajectory data source to road elements based on the weighted prediction contribution corresponding to the time series data of each interval traffic flow.

[0152] In another embodiment, when the prediction unit 702 performs change point detection on the traffic flow time series data to obtain the predicted change time point of road elements in the changing road, it can specifically perform the following: for each time point in the traffic flow time series data, obtain the prior probability and likelihood of each time point; calculate the posterior probability of each time point based on the prior probability and likelihood; and take the time point with the highest posterior probability in the traffic flow time series data as the predicted change time point of road elements in the changing road.

[0153] In another embodiment, when acquiring road data from multiple trajectory data sources, the acquisition unit 701 may specifically perform the following: acquiring driving trajectory data collected by each candidate trajectory data source among multiple candidate trajectory data sources; selecting multiple trajectory data sources that meet a preset magnitude standard from the multiple candidate trajectory data sources based on the driving trajectory data corresponding to each candidate trajectory data source; wherein the preset magnitude standard is set based on the business requirements of road services; and obtaining road data for multiple applications based on the driving trajectory data corresponding to the selected multiple trajectory data sources.

[0154] In another embodiment, when the screening unit 703 selects a target data source from multiple trajectory data sources based on the change prediction contribution corresponding to each trajectory data source, it can specifically perform the following: compare the change prediction contribution corresponding to each trajectory data source with a preset contribution to obtain a comparison result; if the comparison result indicates that the change prediction contribution corresponding to each trajectory data source is greater than or equal to the preset contribution, then each trajectory data source is determined as the target data source.

[0155] According to one embodiment of this application, Figure 2 and Figure 3 The steps involved in the method shown can be derived from... Figure 7 This is performed by each unit in the data processing apparatus shown. For example, Figure 3 The step S301 shown can be performed by Figure 7 The acquisition unit 701 in the data processing device shown is used to execute the steps; steps S302 and S302 to S303 can be performed by... Figure 7The prediction unit 702 in the data processing device shown is used to perform the step; step S304 can be performed by... Figure 7 The processing unit 703 in the data processing device shown is responsible for executing step S305; step S305 can be performed by... Figure 7 The filtering unit 704 in the data processing device shown performs the operation.

[0156] According to another embodiment of this application, Figure 7 The data processing apparatus shown is divided based on logical functions. These units can be individually or entirely merged into one or more other units, or some of these units can be further divided into multiple functionally smaller units. This achieves the same operation without affecting the technical effects of the embodiments of this application. In other embodiments of this application, the data processing apparatus may also include other units. In practical applications, these functions can be implemented with the assistance of other units, and multiple units can collaborate to achieve them.

[0157] According to another embodiment of this application, a general-purpose computing device, such as a computer device, including processing elements and storage elements such as a central processing unit (CPU), random access memory (RAM), and read-only memory (ROM), can be used to run an application capable of performing tasks such as... Figure 2 or Figure 3 The computer program (including program code) involved in each step of the method shown is used to construct, for example... Figure 7 The data processing apparatus shown herein, and the data processing method for implementing the embodiments of this application, are described. A computer program may be recorded on, for example, a computer storage medium, loaded onto the aforementioned computer device via the computer storage medium, and run therein.

[0158] In this embodiment, the predicted change time point for road elements in the changed road is obtained based on the road data corresponding to the changed road in each trajectory data source. Based on the actual and predicted change time points of these road elements, the perceptibility of each trajectory data source's road data to changes in road elements can be effectively evaluated, thus obtaining the contribution of each trajectory data source to the prediction of road element changes. Subsequently, selecting target data sources based on the change prediction contribution is equivalent to filtering target data sources based on the perceptibility of each trajectory data source to changes in road elements. It is easy to see that the road data collected by the target data sources filtered by the change prediction contribution has a positive contribution to perceiving changes in road elements, thereby helping road-related businesses conduct business analysis, research, or decision-making. Therefore, this embodiment can accurately filter data sources that are helpful for business analysis, thereby assisting in better business operations and has broad application prospects.

[0159] Based on the above method and apparatus embodiments, this application also provides an electronic device. See also Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 8 The electronic device shown may include at least a processor 801, an input interface 802, an output interface 803, and a computer storage medium 804. The processor 801, input interface 802, output interface 803, and computer storage medium 804 may be connected via a bus or other means.

[0160] Computer storage medium 804 can be stored in the memory of electronic devices. Computer storage medium 804 is used to store computer programs, which include program instructions. Processor 801 is used to execute the program instructions stored in computer storage medium 804. Processor 801 (or CPU (Central Processing Unit)) is the computing and control core of electronic devices. It is suitable for implementing one or more instructions, specifically for loading and executing one or more instructions to realize the above-mentioned data processing method flow or corresponding functions.

[0161] This application embodiment also provides a computer storage medium (Memory), which is a memory device in an electronic device used to store programs and data. It is understood that the computer storage medium here can include the built-in storage medium in a terminal, or it can include an extended storage medium supported by the terminal. The computer storage medium provides storage space, which stores the terminal's operating system. Furthermore, this storage space also stores one or more instructions suitable for loading and execution by the processor 801. These instructions can be one or more computer programs (including program code). It should be noted that the computer storage medium here can be a high-speed random access memory (RAM), or it can be non-volatile memory, such as at least one disk storage device; optionally, it can also be at least one computer storage medium located remotely from the aforementioned processor.

[0162] In one embodiment, the processor 801 may load and execute one or more instructions stored in the computer storage medium to implement the aforementioned related... Figure 2 and Figure 3 In the corresponding steps of the data processing method embodiment, in a specific implementation, one or more instructions in the computer storage medium are loaded and executed by the processor 801, such as... Figure 2 and Figure 3 The steps in the data processing method embodiment shown.

[0163] This application provides a computer program product or computer program that includes computer instructions stored in a computer-readable storage medium. The processor of an electronic device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the electronic device to perform the aforementioned actions. Figure 2 and Figure 3 The method embodiment shown. The computer-readable storage medium may be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc.

[0164] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims. Furthermore, this application does not limit the execution order of the various steps in the specific embodiments.

Claims

1. A data processing method, characterized in that, The method includes: Road data from multiple trajectory data sources is acquired, and road data corresponding to changed roads is determined from the road data of each trajectory data source; the changed roads refer to roads whose road features have changed within a historical time period. Data change prediction is performed on the road data corresponding to the changed road to obtain the predicted change time points of road elements in the changed road; Based on the actual change time points of the road elements in the changing road and the predicted change time points, the contribution of each trajectory data source to the change prediction of the road elements is obtained; Based on the change prediction contribution of each trajectory data source, a target data source is selected from the multiple trajectory data sources, and the target data source is used as the business data source for road operations associated with the road elements.

2. The method according to claim 1, characterized in that, The contribution of each trajectory data source to the prediction of changes in the road elements is obtained based on the actual change time points and the predicted change time points of the road elements in the changing road, including: Calculate the time difference between the actual change time point and the predicted change time point; The system obtains the first traffic flow of the changed road during a first preset time period before the actual change time point, and the second traffic flow of the changed road during a second preset time period after the actual change time point. Based on the time difference, the first traffic flow, and the second traffic flow, the contribution of each trajectory data source to the prediction of changes in the road elements is obtained.

3. The method according to claim 2, characterized in that, The step of obtaining the contribution of each trajectory data source to the prediction of changes in the road elements based on the time difference, the first traffic flow, and the second traffic flow includes: Calculate the flow difference between the first flow rate and the second flow rate; The initial predicted contribution is obtained based on the flow rate difference and the time difference; Obtain the data confidence level of each trajectory data source, and based on the data confidence level of each trajectory data source and the initial prediction contribution, obtain the prediction contribution of each trajectory data source to the change of the road element.

4. The method according to claim 1, characterized in that, The step of predicting data changes in the road data corresponding to the changed road to obtain the predicted change time points of road elements in the changed road includes: Obtain the traffic flow time series data of the changed road from the road data corresponding to the changed road; Change point detection is performed on the traffic flow time series data to obtain the predicted change time points of road elements in the changed road.

5. The method according to claim 4, characterized in that, The traffic flow time series data includes traffic flow data corresponding to multiple dates; the step of performing change point detection on the traffic flow time series data to obtain the predicted change time points of road elements in the changed roads includes: Traffic flow data for the same date is divided based on multiple preset time intervals to obtain traffic flow data for the same date in each preset time interval; Based on the traffic flow data corresponding to the same preset time interval on different dates, construct the interval traffic time series data corresponding to each preset time interval; Change point detection is performed on the traffic flow time series data of each interval to obtain the predicted change time point of the road element in each preset time interval.

6. The method according to claim 5, characterized in that, The contribution of each trajectory data source to the prediction of changes in the road elements is obtained based on the actual change time points and the predicted change time points of the road elements in the changing road, including: Based on the predicted change time point corresponding to the traffic flow time series data of each interval, and the actual change time point, the change prediction contribution of the traffic flow time series data of each interval is obtained. Based on the change prediction contribution of the time series data of traffic flow in each interval, the change prediction contribution of each trajectory data source to the road element is obtained.

7. The method according to claim 6, characterized in that, The step of obtaining the predicted contribution of each trajectory data source to the changes in the road elements based on the predicted contribution of changes in the time-series traffic data for each interval includes: Obtain the time weight corresponding to each preset time interval; Based on the time weight corresponding to each preset time interval, the change prediction contribution of the traffic time series data corresponding to the corresponding interval is weighted to obtain the weighted prediction contribution of the traffic time series data for each interval. Based on the weighted prediction contribution of the time-series traffic data for each interval, the prediction contribution of each trajectory data source to the changes in the road elements is obtained.

8. The method according to claim 4, characterized in that, The step of performing change point detection on the traffic flow time series data to obtain the predicted change time points of road elements in the changed road includes: For each time point in the traffic flow time series data, obtain the prior probability and likelihood of each time point; Based on the prior probability and the likelihood, the posterior probability at each time point is calculated; The time point with the highest posterior probability in the traffic flow time series data is used as the predicted change time point for road elements in the changed road.

9. The method according to any one of claims 1 to 8, characterized in that, The acquisition of road data from multiple trajectory data sources includes: Obtain driving trajectory data collected from each of the multiple candidate trajectory data sources; Based on the driving trajectory data corresponding to each candidate trajectory data source, multiple trajectory data sources that meet a preset magnitude standard are selected from the multiple candidate trajectory data sources; wherein, the preset magnitude standard is set based on the data requirements of the road business; Based on the driving trajectory data corresponding to the selected multiple trajectory data sources, the road data of the multiple trajectory data sources is obtained.

10. The method according to any one of claims 1 to 8, characterized in that, The step of selecting a target data source from the plurality of trajectory data sources based on the change prediction contribution corresponding to each trajectory data source includes: The change prediction contribution of each trajectory data source is compared with the preset contribution to obtain the comparison result; If the comparison result indicates that the change prediction contribution of each trajectory data source is greater than or equal to the preset contribution, then each trajectory data source is determined as the target data source.

11. A data processing apparatus, characterized in that, The device includes an acquisition unit, a prediction unit, a processing unit, and a filtering unit, wherein: The acquisition unit is used to acquire road data from multiple trajectory data sources and determine the road data corresponding to the changed road from the road data of each trajectory data source; the changed road refers to a road whose road elements have changed within a historical time period; The prediction unit is used to predict the data changes of the road data corresponding to the changed road, and obtain the predicted change time points of the road elements in the changed road. The processing unit is used to obtain the contribution of each trajectory data source to the prediction of changes in the road elements based on the actual change time points and the predicted change time points of the road elements in the changing road. The filtering unit is used to select a target data source from the plurality of trajectory data sources based on the change prediction contribution corresponding to each trajectory data source, and to use the target data source as the business data source for road business associated with the road element.

12. A computer-readable medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the data processing method as described in any one of claims 1 to 10.

13. An electronic device, characterized in that, include: A processor, adapted to implement one or more instructions; as well as, A computer storage medium storing one or more instructions adapted for loading by the processor and executing the data processing method as described in any one of claims 1 to 10.

14. A computer program product, characterized in that, The computer program product includes a computer program adapted to be loaded by a processor and executed as described in any one of claims 1 to 10.

Images