Data processing method, device, electronic device and computer-readable storage medium

Abstract

The embodiments of the present application provide a data processing method, device, electronic device, and computer-readable storage medium, which can be applied to fields such as artificial intelligence, big data, cloud technology, map technology, and transportation, as well as scenarios such as smart transportation and assisted driving. The method includes: obtaining the penetration volume of the target road and map road data, and obtaining the road status of the target road from the map road data. Based on the penetration volume of the target road and the road status of the target road, the probability of switching the penetration volume of the target road and the road status of the target road is determined, and based on the probability of switching the road status of the target road, the map road data is updated. This method can simply and quickly update the map road data based on the probability of switching the road status of the target road, thereby better meeting practical needs.

Description

Technical Field

[0001] This application relates to fields such as artificial intelligence, big data, cloud technology, map technology, and transportation, as well as scenarios such as smart transportation and assisted driving. Specifically, this application relates to a data processing method, device, electronic device, computer-readable storage medium, and computer program product. Background Art

[0002] With the development of science and technology, how to better determine road capacity and accurately predict road conditions has become a technical problem that needs to be solved urgently in this field.

[0003] Related technologies primarily determine road capacity by collecting large amounts of traffic flow data, road parameters, and environmental parameters, and then establishing a multi-layer statistical analysis model. However, this approach, which requires a large amount of multidimensional data, faces challenges such as difficulty in data collection and high costs. Furthermore, since multi-layer statistical analysis models are trained using multidimensional data, their calculations are relatively complex and significantly affected by data from various dimensions, making them difficult to apply widely. Summary of the Invention

[0004] The embodiments of the present application provide a data processing method, device, electronic device, computer-readable storage medium and computer program product, which can quickly and simply determine road capacity, can be widely used, and can better meet practical needs.

[0005] According to one aspect of the present application, a data processing method is provided, the method comprising:

[0006] Obtaining a penetration volume of a target road and map road data, wherein the penetration volume of the target road represents the number of vehicle penetrations from a starting point to an end point of the target road;

[0007] Obtaining a road status of the target road from the map road data, where the road status includes a closed state or an open state;

[0008] Determining a probability of a road state switching of the target road based on the penetration volume of the target road and the road state of the target road;

[0009] The map road data is updated based on the probability of the target road's road state switching.

[0010] Optionally, the determining of the probability of the target road's road state switching based on the target road's penetration volume and the target road's road state includes:

[0011] Determining, according to the penetration volume of the target road and the road state of the target road, a first probability of a road state switching of the target road and a second probability of a road state switching of the target road in two different ways;

[0012] The probability of the target road's road state switching is determined based on the first probability and the second probability.

[0013] According to another aspect of the present application, a data processing device is provided, which includes a data acquisition module, a probability determination module, and a map road data update module:

[0014] a data acquisition module, configured to acquire the penetration volume of a target road and map road data, wherein the penetration volume of a target road represents the number of vehicle penetrations from a starting point to an end point of the target road;

[0015] The data acquisition module is further used to obtain the road status of the target road from the map road data, where the road status includes a closed state or an open state;

[0016] a probability determination module, configured to determine a probability of a road state switching of the target road based on the penetration volume of the target road and the road state of the target road;

[0017] The data updating module is used to update the map road data according to the probability of the road state of the target road switching.

[0018] Optionally, the probability determination module determines the probability of the target road's road state switching according to the penetration amount of the target road and the road state of the target road, specifically for:

[0019] Determining, according to the penetration volume of the target road and the road state of the target road, a first probability of a road state switching of the target road and a second probability of a road state switching of the target road in two different ways;

[0020] The probability of the target road's road state switching is determined based on the first probability and the second probability.

[0021] Optionally, the penetration volume of the target road includes at least two historical penetration volumes corresponding to at least two historical time periods of the target road and a current penetration volume corresponding to a current time period of the target road.

[0022] When the road state of the target road is an open state, the probability determination module is specifically configured to determine a first probability of the target road's road state switching and a second probability of the target road's road state switching in two different ways:

[0023] Determine the standard deviation, mean and minimum penetration of the penetration based on at least two historical penetrations;

[0024] determining a first probability based on the penetration standard deviation, the penetration mean, and the current penetration;

[0025] determining a second probability based on the penetration standard deviation, the minimum penetration, and the current penetration;

[0026] The determining of the probability of the target road's road state switching based on the first probability and the second probability includes:

[0027] The larger value of the first probability and the second probability is determined as the probability that the road state of the target road switches.

[0028] Optionally, when determining the first probability based on the penetration standard deviation, the penetration mean, and the current penetration, the probability determination module is specifically configured to:

[0029] A normal distribution model is constructed based on the above penetration amount mean and the above penetration amount standard deviation;

[0030] Determining, based on the normal distribution model, a third probability corresponding to a penetration amount that is less than or equal to the current penetration amount;

[0031] If the third probability and the current penetration rate satisfy a first condition, determining a first ratio of the current penetration rate to the average penetration rate;

[0032] Determining the first probability according to the first ratio;

[0033] The first condition is that the third probability is less than the first value and the current penetration amount is less than the second value.

[0034] Optionally, if the third probability and the current penetration value do not satisfy the first condition, determining the probability of the target road state switching based on the first probability and the second probability includes:

[0035] The second probability is determined as a probability that the road state of the target road switches.

[0036] Optionally, when determining the second probability based on the penetration standard deviation, the minimum penetration, and the current penetration, the probability determination module is specifically configured to:

[0037] If the minimum penetration and the current penetration meet a second condition, determining a second ratio of the current penetration to the minimum penetration;

[0038] determining the second probability according to the second ratio;

[0039] The second condition is that the difference between the minimum penetration and the current penetration is greater than a preset multiple of the penetration standard deviation, and the current penetration is less than a third value.

[0040] Optionally, if the minimum penetration amount and the current penetration amount do not satisfy the second condition, determining the probability of the target road state switching based on the first probability and the second probability includes:

[0041] The first probability is determined as a probability that the road state of the target road switches.

[0042] Optionally, when determining the minimum penetration value t according to at least two historical penetration values ​​t, the probability determination module is specifically configured to:

[0043] Randomly selecting a predetermined number of historical penetration quantities from at least two historical penetration quantities, wherein the predetermined number is less than or equal to the total number of the at least two historical penetration quantities;

[0044] According to a predetermined number of historical penetration amounts, a minimum value among the predetermined number of historical penetration amounts is determined, and the minimum value is determined as the minimum penetration amount.

[0045] Optionally, the target road is determined according to the following method:

[0046] Get historical driving routes;

[0047] Based on trajectory map matching, a target road corresponding to the historical driving route in the map road data is determined.

[0048] According to another aspect of the present application, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the above method.

[0049] According to another aspect of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above method are implemented.

[0050] According to another aspect of the present application, a computer program product is provided, comprising a computer program, which implements the steps of the above method when executed by a processor.

[0051] The beneficial effects of the technical solution provided by the embodiments of the present application are:

[0052] In the data processing method, device, electronic device, computer-readable storage medium, and computer program product provided in the embodiments of the present application, the target road's road state is obtained from the map road data by obtaining the target road's road penetration and map road data. Based on the target road's road penetration and road state, the probability of the target road's road state switching is determined. Since this solution requires less data, the method for obtaining data is also easier, and the calculation method is simple. Therefore, through this solution, the probability of the target road's road state switching can be quickly determined. Furthermore, based on the probability of the target road's road state switching, the map road data can be updated in a timely manner, more conveniently providing users with more suitable driving routes with open road states based on their driving needs, and reasonably avoiding driving routes with closed road states. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for describing the embodiments of the present application.

[0054] Figure 1 A schematic diagram of the structure of an optional data processing system in this scenario is shown;

[0055] Figure 2 A flow chart showing a data processing method executed by a data processing system in this application scenario is shown;

[0056] Figure 3 A flowchart of processing A in an embodiment of the present application is shown;

[0057] Figure 4 A flow chart showing a data processing method provided by an embodiment of the present application is shown;

[0058] Figure 5 A schematic diagram showing the determination of a target road based on geometric matching in an embodiment of the present application is shown;

[0059] Figure 6 A schematic diagram showing the third probability of an embodiment of the present application is shown;

[0060] Figure 7a and Figure 7b A schematic diagram showing a specific application scenario of the present application is shown;

[0061] Figure 8 A flowchart illustrating the implementation of the above method in a specific application scenario of the present application is shown;

[0062] Figure 9 A schematic diagram of a data processing device provided in an embodiment of the present application is shown;

[0063] Figure 10A schematic diagram of an electronic device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0064] The following describes the embodiments of the present application in conjunction with the accompanying drawings. It should be understood that the embodiments described below in conjunction with the accompanying drawings are exemplary descriptions for explaining the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions of the embodiments of the present application.

[0065] Those skilled in the art will understand that, unless otherwise stated, the singular forms "a," "an," "said," and "the" used herein may also include plural forms. It should be further understood that the terms "including" and "comprising" used in the embodiments of the present application mean that the corresponding features can be implemented as the presented features, information, data, steps, operations, elements, and / or components, but do not exclude implementation as other features, information, data, steps, operations, elements, components, and / or combinations thereof supported by the present technical field. It should be understood that when we refer to an element as being "connected" or "coupled" to another element, the element can be directly connected or coupled to the other element, or it can refer to the element and the other element establishing a connection relationship through an intermediate element. In addition, the "connection" or "coupling" used herein may include wireless connection or wireless coupling. The term "and / or" used herein indicates at least one of the items defined by the term, for example, "A and / or B" indicates implementation as "A," or implementation as "A," or implementation as "A and B."

[0066] In order to make the objectives, technical solutions and advantages of this application clearer, the implementation methods of this application will be further described in detail below with reference to the accompanying drawings.

[0067] Road closure: This refers to a situation where all or some vehicles are unable to pass due to construction, road closures, changes in traffic rules, or poor road conditions, resulting in a significant reduction in road capacity, the entire road being impassable, or certain types of vehicles being unable to pass. Road closure is the opposite of road openness, which refers to a state where vehicles are allowed to pass.

[0068] Penetrations: The number of vehicle penetrations from the start point to the end point of the current road. For example, if a user drives from the start point of the current road to the end point of the current road and then enters the next road, the penetration of the current road is considered to have increased by 1.

[0069] Related technologies primarily calculate road capacity by collecting traffic flow data, road parameters, and environmental parameters, and establishing a multi-layered statistical analysis model. Traffic flow data includes vehicle volume, speed, occupancy, vehicle type, lane, and detection time. Road and environmental parameters include the number of lanes, lane width, lateral clearance, slope, and plan alignment.

[0070] However, it's clear that related technical methods for determining road capacity require the use of multidimensional data, which is difficult and costly to collect. Furthermore, the availability of this data, such as weather and road load saturation, must be assessed. Furthermore, because multi-layer statistical analysis models are trained on multidimensional data, their computational process is relatively complex and significantly influenced by data from various dimensions, making them difficult to apply broadly and limited in practicality.

[0071] In response to at least one of the above-mentioned technical problems or areas for improvement in the related art, the present application proposes a data processing method, apparatus, electronic device, computer-readable storage medium, and computer program product. The data processing method obtains the penetration rate of a target road and map road data, obtains the road state of the target road from the map road data, and determines the probability of the target road's road state switching based on the penetration rate and road state of the target road. Because this solution requires less data, the method for obtaining data is also relatively easy. Since this solution does not require multi-dimensional data to determine the probability of the target road's road state switching, the calculation method is simple, is less affected by multi-dimensional data, and has strong anti-interference ability against abnormal data. Therefore, through this solution, not only can the probability of the target road's road state switching be quickly determined, but the map road data (also known as map dynamic road network data) can also be updated in a timely manner based on the probability of the target road's road state switching. This makes it more convenient to provide users with more suitable driving routes with open road states according to their driving needs, and reasonably avoid driving routes with closed road states.

[0072] Optionally, the data processing method provided in the embodiment of the present application can be implemented by a data processing system including interaction between a terminal device and a server, or can be implemented by a terminal device or a server. Optionally, the server can be a cloud server. Optionally, the terminal device can be a user equipment (UE), a mobile device, a user terminal, a terminal, a cellular phone, a cordless phone, a personal digital assistant (PDA), a handheld device, a computing device or a wearable device, etc. Among them, the user terminal includes but is not limited to a mobile phone, a computer, an intelligent voice interaction device, a smart home appliance, a vehicle-mounted terminal, etc. The embodiments of the present invention can be applied to various scenarios, including but not limited to cloud technology, artificial intelligence, smart transportation, assisted driving, etc.

[0073] Optionally, the data processing method provided in the embodiments of the present application can be implemented based on artificial intelligence (AI) technology. AI is a theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use knowledge to achieve optimal results. With the research and advancement of artificial intelligence technology, artificial intelligence technology has been widely studied and applied in many fields. It is believed that with the development of technology, artificial intelligence technology will be applied in more fields and play an increasingly important role.

[0074] With the research and progress of artificial intelligence technology, artificial intelligence technology has been studied and applied in many fields, such as common smart homes, smart wearable devices, virtual assistants, smart speakers, smart marketing, unmanned driving, automatic driving, drones, robots, smart medical care, smart customer service, Internet of Vehicles, automatic driving, smart transportation, etc. It is believed that with the development of technology, artificial intelligence technology will be applied in more fields and play an increasingly important role.

[0075] The data processing method provided in the embodiments of the present application can be applied to various fields of cloud technology, such as cloud computing and cloud services in cloud technology, and related data computing and processing fields in the field of big data.

[0076] Cloud technology refers to a hosting technology that unifies hardware, software, network and other resources within a wide area network or local area network to achieve data computing, storage, processing and sharing. The virtual scene simulation processing method provided in the embodiment of the application can be implemented based on cloud computing in cloud technology.

[0077] Cloud computing refers to obtaining required resources on demand and in an easily scalable manner through the Internet. It is the product of the integration of traditional computer and network technologies such as grid computing, distributed computing, parallel computing, utility computing, network storage technologies, virtualization, and load balancing.

[0078] Artificial intelligence cloud services, also commonly referred to as AIaaS (AI as a Service), are a mainstream AI platform service model. Specifically, AIaaS platforms break down several common AI services and provide independent or packaged services in the cloud, such as processing virtual scene simulation requests.

[0079] Big data refers to data sets that cannot be captured, managed, and processed within a specific timeframe using conventional software tools. These are massive, high-growth, and diverse information assets that require new processing models to enhance decision-making, insight discovery, and process optimization. With the advent of the cloud era, big data has attracted increasing attention. Effectively implementing the data processing methods provided in this embodiment requires specialized technologies based on big data. Technologies suitable for big data include massively parallel processing databases, data mining, distributed file systems, distributed databases, and the aforementioned cloud computing.

[0080] Optionally, the data processing method provided in the embodiments of the present application can also be based on map technology and traffic neighborhoods. For example, it can be applicable to intelligent traffic systems (ITS, also known as intelligent transportation systems) and intelligent vehicle infrastructure cooperative systems (IVICS).

[0081] Among them, the intelligent transportation system effectively integrates advanced science and technology (information technology, computer technology, data communication technology, sensor technology, electronic control technology, automatic control theory, operations research, artificial intelligence, etc.) into transportation, service control and vehicle manufacturing, strengthens the connection between vehicles, roads and users, and thus forms a comprehensive transportation system that ensures safety, improves efficiency, improves the environment and saves energy.

[0082] Intelligent Vehicle-Infrastructure Cooperation (IVICS), or simply VIS, is a development direction for intelligent transportation systems. VIS utilizes advanced wireless communications and next-generation internet technologies to implement comprehensive, real-time information exchange between vehicles and roads. It also integrates dynamic traffic information across time and space, enabling active vehicle safety control and collaborative road management. This system effectively achieves effective coordination between drivers, vehicles, and roads, ensuring traffic safety and improving traffic efficiency, resulting in a safe, efficient, and environmentally friendly road transportation system.

[0083] Optionally, the data processing method provided in the embodiments of the present application can also be implemented based on blockchain technology. Specifically, the data used in the data processing method, such as penetrations, historical driving routes, map road data, road status, etc., can be stored on the blockchain.

[0084] To facilitate understanding of the application value of the data processing method provided in the embodiment of the present application, the data processing method is first described below in conjunction with a specific application scenario embodiment. In this specific application scenario embodiment, the data processing method provided in the embodiment of the present application is implemented by a data processing system including a terminal device and a server interacting.

[0085] Figure 1 A schematic diagram of the structure of an optional data processing system in this scenario is shown. Figure 1 As shown, the system includes a user's terminal device 10, a network 20 and a server 30, and the terminal device 10 communicates with the server 30 via the network 20. The server 30 is provided with a database for storing historical driving routes and map road data. The map road data includes multiple roads in the map and the road status of each road. The terminal device 10 may be installed with an application for data processing, or a plug-in for data processing may be provided in the terminal device 10. The application may be an application for navigation. By opening the application for data processing or clicking on the plug-in provided with the above-mentioned data processing, the terminal is started to perform the data processing method provided in the embodiment of the present application. The terminal device 10 may be a user equipment (UE), a mobile device, a user terminal, a terminal, a cellular phone, a cordless phone, a personal digital assistant (PDA), a handheld device, a computing device or a wearable device, etc.

[0086] Optionally, the terminal device 10 includes a user terminal, wherein the user terminal may include but is not limited to a mobile phone, a computer, an intelligent voice interaction device, a smart home appliance, a vehicle-mounted terminal, a wearable electronic device, an AR / VR device, etc.

[0087] The following combination Figure 1 The data processing system shown illustrates the data processing method in this application scenario. Figure 2 FIG. 1 shows a flow chart of a data processing method executed by a data processing system in this application scenario. Figure 2 As shown, this application scenario is described by taking the determined road state of the target road as an open state as an example. Specifically, the method may include the following steps S10 to S40.

[0088] Step S10: The terminal device 10 sends an instruction generated according to the user's travel demand to the server 30 via the network 20;

[0089] Step S20: The server 30 receives the instruction generated according to the user's driving demand via the network 20;

[0090] Step S30: The server 30 performs processing A to update the map road data according to the request instruction, and determines the user's future travel route corresponding to the instruction generated according to the user's future travel demand based on the updated map road data and the instruction generated according to the user's future travel demand, wherein the future travel route may include at least one road with an open road status;

[0091] Step S40: The server 30 sends the instruction generated according to the user's route to be traveled to the terminal device 10 through the network 20, so that the terminal device 10 performs driving operations according to the instruction generated according to the user's route to be traveled.

[0092] Figure 3 Flowchart of A processing in the embodiment of the present application is shown. Figure 3 As shown, process A can be implemented through the following steps S31 to S38.

[0093] Step S31: calling a database configured on the server 30 side to obtain multiple historical driving routes and map road data. The multiple historical driving routes obtained may be historical driving routes from multiple users.

[0094] Step S32: Based on the trajectory map matching, determine the target road corresponding to each historical driving route in the map road data.

[0095] In the embodiments of the present application, the target road may be one or more roads in the map road data, or one or more roads corresponding to historical driving routes obtained based on trajectory map matching, and this application does not impose any restrictions on this. Optionally, when determining the target road based on trajectory map matching, trajectory map matching may be performed on multiple historical driving routes and the map road data until the determined target road traverses every road in the map road data.

[0096] Step S33: Obtain, for each target road, 60 historical penetrations corresponding to, for example, 60 historical time periods, as well as the current penetration corresponding to the current time period, and obtain the road status of all target roads from the map road data. The time interval corresponding to each historical time period is the same as the time interval corresponding to each current time period. The current time period is the period starting from the current time point and tracing back to a predetermined time interval.

[0097] For any target road, steps S34 to S37 are executed in sequence.

[0098] Step S34: Determine the standard deviation and mean of penetrations based on the 60 historical penetrations of the target road;

[0099] Also, 30 historical penetration amounts are randomly selected from the 60 historical penetration amounts, for example, and a minimum value among the 30 historical penetration amounts is determined based on the selected 30 historical penetration amounts, and the minimum value is determined as the minimum penetration amount.

[0100] Step S35: constructing a normal distribution model according to the penetration mean and the penetration standard deviation, and determining a third probability corresponding to a penetration less than or equal to the current penetration based on the normal distribution model;

[0101] If the third probability is less than the first value and the current penetration is less than the second value, determining a first ratio of the current penetration to the mean penetration, and based on the first ratio, determining a first difference between 1 and the first ratio, and determining the first difference as the first probability;

[0102] If the third probability is greater than or equal to the first value, or the current penetration amount is greater than or equal to the second value, the first probability is determined to be 0.

[0103] In this implementation, the first and second values ​​can be configured based on actual needs (e.g., empirical values ​​or experimental values). When the target road is in an open state and the probability of the target road's road state switching (i.e., switching from an open state to a closed state) is determined based on the target road's penetration rate, the first and second values ​​are related to the accuracy of the first probability to be determined. Taking into account the empirical rule of normal distribution (almost all data are within ± three standard deviations of the mean), the first value is negatively correlated with the accuracy of the first probability to be determined, and the second value is negatively correlated with the accuracy of the first probability to be determined. For example, for a certain target road, the first value can be set to 0.05 and the second value to 15.

[0104] It is understood that for different target roads, the same first value can be set for each target road, or different first values ​​can be set for each target road. For example, for two different target roads, the first value of the first target road and the first value of the second target road can both be set to 0.05. Alternatively, the first value of the first target road can be set to 0.05, and the first value of the second target road can be set to 0.03.

[0105] Of course, for different target roads, the same second value can be set for each of the different target roads, or different second values ​​can be set for each of the different target roads. For example, for two different target roads, the second value of the first target road and the second value of the second target road can both be set to 15. Alternatively, the second value of the first target road can be set to 13, and the second value of the second target road can be set to 18.

[0106] Step S36: If the difference between the minimum penetration and the current penetration is greater than n times the penetration standard deviation, and the current penetration is less than the third value, a second ratio of the current penetration to the minimum penetration is determined, and based on the second ratio, a second difference between 1 and the second ratio is determined, and the second difference is determined as the second probability.

[0107] If the difference between the minimum penetration and the current penetration is less than or equal to a preset multiple of the standard deviation of the penetration, or if the current penetration is greater than or equal to the third value, the second probability is determined to be 0.

[0108] Similarly, in this implementation, the value of the third value can be configured based on actual needs (e.g., it can be an empirical value or an experimental value), wherein the value of the third value is related to the accuracy of the second probability to be determined, and the value of the third value is negatively correlated with the accuracy of the second probability to be determined. For the same target road, the value of the third value can be the same as or different from the value of the second value. For example, for the same target road, the value of the second value and the value of the third value can both be set to 15; or the value of the second value can be set to 12 and the value of the third value can be set to 15.

[0109] It is understood that the third value set for different target roads can be the same or different. For example, for two different target roads, the third value of the first target road and the third value of the second target road can both be set to 16; or the third value of the first target road can be set to 14 and the third value of the second target road can be set to 17.

[0110] In this implementation, the value of n can be configured according to actual needs (for example, it can be an empirical value or an experimental value), combined with the empirical rule of normal distribution, where 1≤n≤3, n is a positive integer, for example, the value of n can be 1, 2, or 3, preferably 2. The value of n is positively correlated with the accuracy of determining the second probability. It can be understood that for different target roads, the value of n can be the same or different. For example, for two different target roads, the value of n for the first target road and the value of n for the second target road can both be set to 2. The value of n for the first target road can also be set to 1, and the value of n for the second target road can be set to 2.

[0111] Step S37: Determine the larger value of the first probability and the second probability as the probability that the road state of the target road switches.

[0112] Step S38: After obtaining the probability of the road status switching of all target roads, the map road data is updated according to the probability of the road status switching of all target roads to obtain updated map road data.

[0113] Through the above method, after receiving a request for a route to be traveled from a user, the probability of a road state switching of each target road in the map road data can be simply and quickly determined, thereby updating the map road data based on the probability of a road state switching of each target road. This makes it more convenient to recommend a more suitable driving route with an open road state to the user based on the user's driving needs, and reasonably avoid driving routes with a closed road state.

[0114] The following describes several exemplary embodiments to illustrate the technical solutions of the embodiments of the present application and the technical effects produced by the technical solutions of the present application. It should be noted that the following embodiments can refer to, draw on, or combine with each other, and the same terms, similar features, and similar implementation steps in different embodiments will not be repeated.

[0115] Figure 4 FIG. 1 is a flow chart showing a data processing method provided in an embodiment of the present application. Figure 4 As shown, the method includes steps S110 to S140, specifically:

[0116] Step S110: Obtaining the penetration volume of the target road and map road data, wherein the penetration volume of the target road represents the number of vehicle penetrations from the starting point to the end point of the target road.

[0117] In the embodiment of the present application, the target road may be one or more roads in the map road data, or one or more roads determined by other means, and the present application does not impose any restrictions on this.

[0118] It is understood that a through-travel drive refers to a complete travel across the entire road. The target road penetration count represents both the number of through-travels from the starting point to the end point of the target road, and the number of through-travels from the end point to the starting point of the target road. That is, this application does not restrict the directions of the starting and end points of the target road penetration count. As long as a vehicle through-travels the entire target road, the number of vehicle through-travels is considered to be 1, and naturally, the target road penetration count will also increase by 1.

[0119] Among them, there are many ways to determine the penetration volume of the target road, and this application does not limit this. For example, in the current traffic system, for the same road, image acquisition devices are set at different positions of the road (including the starting point, the end point, and other positions between the starting point and the end point). Therefore, it is possible to determine whether there are vehicles running through the road through the images captured by the image acquisition devices set in the road, and thus determine the penetration volume of the road in the specific time period based on the number of vehicles running through the road in the specific time period. Optionally, trajectory map matching can also be performed on the historical driving routes of all vehicles in the specific time period, so that the number of times a road is determined as the target road is determined as the penetration volume of the road in the specific time period.

[0120] Optionally, the map road data may be in digital or electronic form, which is not limited in this application. The map road data may be used to characterize road features, including at least one road and the road conditions of each road. Of course, the map road data may also include other elements, such as scales, legends, direction markers, landmark buildings, spatially related locations, etc., which are not limited in this application.

[0121] Step S120: Obtaining the road status of the target road from the map road data, where the road status includes a closed state or an open state.

[0122] Based on the above description, this application does not limit the specific method of representing road status. Optionally, when the map road data is in electronic form, different road statuses can be represented by different colors. For example, a road can be set to green to represent an open state, and a road can be set to red to represent a closed state.

[0123] Step S130: determining the probability of the target road's road state switching according to the target road's penetration amount and the target road's road state.

[0124] Optionally, the probability P1 of the target road's road state switching from an open state to a closed state can be used to represent the probability of the target road's road state switching, or the probability P2 of the target road's road state switching from a closed state to an open state can be used to represent the probability of the target road's road state switching. This application does not impose any restrictions on this.

[0125] When the probability P1 of the target road's road state switching from an open state to a closed state is used to represent the probability of the target road's road state switching, the probability of the target road's road state switching from a closed state to an open state is P2=1-P1.

[0126] Step S140: updating the map road data according to the probability of the target road's road state switching.

[0127] Optionally, the map road data can be updated based on the above-mentioned method of characterizing the road state and the probability of the road state of the target road switching. As an example, when different road states are represented by different colors (green represents an open state, and red represents a closed state), the probability of the road state of each road in the updated map road data switching can be represented by the depth of the same color based on the probability of the road state switching. Among them, the greater the probability of the road state switching, the lighter the color corresponding to the current road state, and the darker the color corresponding to the road state after the possibility of switching. Based on this, if the road state of the target road has the possibility of switching from an open state to a closed state, that is, the probability of the road state of the target road switching is not 0, and the greater the probability of the switching, the lighter the green can be used to represent the road state of the target road.

[0128] The data processing method provided in the embodiments of the present application obtains the target road's penetration volume and map road data, and then determines the target road's road status based on the map road data. Based on the target road's penetration volume and road status, the probability of the target road's road status switching is determined. Because this solution requires less data, the data acquisition method is relatively easy, and the calculation method is simple, the probability of the target road's road status switching can be quickly determined. Furthermore, based on the target road's road status switching probability, the map road data can be updated more promptly, facilitating the provision of better routes with open roads and avoiding routes with closed roads, tailored to the user's driving needs.

[0129] Optionally, in the embodiment of the present application, the target road may be determined according to the following method, specifically:

[0130] Get historical driving routes;

[0131] Based on trajectory map matching, the target road corresponding to the historical driving route in the map road data is determined.

[0132] Optionally, the historical driving route may be in digital form or in electronic form, which is not limited in this application.

[0133] The historical driving route can be determined based on historical driving needs. For example, the historical driving route can be data generated during vehicle driving and uploaded via navigation software. If the directly acquired historical driving route is generally not a regular straight line, to facilitate subsequent processing, the directly acquired historical driving route can be first fitted to obtain a regular straight line corresponding to the directly acquired historical driving route, and subsequent operations can be performed based on the processed regular straight line. The historical driving route can include multiple historical driving routes of multiple users, and this application does not impose any restrictions on this.

[0134] Optionally, when the directly acquired historical driving route is not a regular straight line, the directly acquired historical driving route may be referred to as a historical driving trajectory, and the regular straight line obtained after fitting the historical driving trajectory may be referred to as a historical driving route.

[0135] It is understandable that in the specific implementation of this application, related data such as user information (such as the user's historical driving routes) is involved. When the above embodiments of this application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards of relevant countries and regions.

[0136] In the embodiments of the present application, various methods of trajectory map matching are available, as long as a road that matches the historical driving route can be found in the map road data. Alternatively, methods such as geometric matching, probability matching, and Markov chain matching can be used to combine the map road data and the historical driving route to determine the target road in the map road data that corresponds to the historical driving route.

[0137] In the embodiment of the present application, the number of target roads determined can be one or more, and this application does not impose any restrictions on this. Optionally, in the case where the historical driving route includes multiple roads, for example, in the case where the historical driving route L1→L2→L3→L4 includes multiple roads L1, L2, L3, and L4, the target roads l1, l2, l3, and l4 corresponding to each road L1, L2, L3, and L4 in the historical driving route L1→L2→L3→L4 can be determined in sequence in the map road data based on trajectory map matching.

[0138] Optionally, trajectory map matching may be performed on multiple historical driving routes, so that the determined target road corresponding to the historical driving route may traverse all roads in the map road data.

[0139] In this embodiment of the present application, historical driving routes can be determined based on navigation data. Furthermore, based on trajectory map matching, the target road corresponding to the historical driving route can be accurately identified in the map road data. Furthermore, combined with the above steps, the probability of the target road's road state switching can be quickly determined. Based on the probability of the target road's road state switching, the map road data can be updated more promptly, conveniently providing users with better routes with open roads according to their driving needs, and reasonably avoiding routes with closed roads.

[0140] Based on the above, when determining the target road corresponding to the historical driving route in the map road data based on trajectory map matching, the target road corresponding to the historical driving route in the map road data can be determined based on geometric matching, combining the map road data and the historical driving route. Specifically, the geometry-based matching method is: by determining the matching degree between the historical driving route and multiple roads to be matched in the map road data, the road to be matched with the highest matching degree with the historical driving route is determined as the target road corresponding to the historical driving route. Among them, the method for determining the matching degree is: match = ω1*d+ω2*cosα, where d represents the distance between the current road and the road to be matched, ω1 represents the weight value of the distance d, α represents the angle between the current road and the road to be matched, ω2 represents the weight value of the angle α, and ω1+ω2=1. Optionally, the values ​​of ω1 and ω2 can be configured according to actual needs (for example, they can be empirical values ​​or experimental values), and this application does not impose any restrictions on this. For example, ω1 can be set to 0.6 and ω2 can be set to 0.4.

[0141] As an example, Figure 5 FIG. 1 shows a schematic diagram of determining a target road based on geometric matching in an embodiment of the present application. Figure 5 As shown in the figure, the acquired trajectory data is the historical driving trajectory S of user 1 from point A to point B, and the road line1 and road line2 to be matched in the map road data are used as an example. First, the historical driving trajectory S is fitted to obtain the historical driving route L, as shown in the figure. Figure 5The dotted line from point A to point B in the figure is shown. The distance d1 between the historical driving route L and the road to be matched, line1, and the angle α1 between the historical driving route L and the road to be matched, line2, are determined. The distance d2 between the historical driving route L and the road to be matched, line2, and the angle α2 between the historical driving route L and the road to be matched, line2, are determined. Clearly, d1 < d2, and α1 < α2. The matching degree match1 between the historical driving route L and the road to be matched, line1, and the matching degree match2 between the historical driving route L and the road to be matched, line2, are determined using the matching degree formula match = ω1*d + ω2*cosα. Calculation shows that the larger value of match1 and match2 is match2, indicating that the road to be matched, line2, is the target road corresponding to the historical driving route L (i.e., the historical actual driving trajectory S).

[0142] Optionally, the determining of the probability of the target road's road state switching based on the target road's penetration volume and the target road's road state includes:

[0143] Determining, according to the penetration volume of the target road and the road state of the target road, a first probability of a road state switching of the target road and a second probability of a road state switching of the target road in two different ways;

[0144] The probability of the target road's road state switching is determined based on the first probability and the second probability.

[0145] In this implementation method, by using two different methods to determine the first probability of the target road's road state switching and the second probability of the target road's road state switching according to the target road's penetration volume and the target road's road state, and determining the probability of the target road's road state switching based on the first probability and the second probability, it is possible to combine multiple probability determination methods to more accurately determine the probability of the target road's road state switching.

[0146] Optionally, the penetration volume of the target road includes at least two historical penetration volumes corresponding to at least two historical time periods of the target road and a current penetration volume corresponding to a current time period of the target road. When the road state of the target road is an open state, the above-mentioned two different methods are used to respectively determine a first probability of a road state switching of the target road and a second probability of a road state switching of the target road, including:

[0147] Determine the standard deviation, mean and minimum penetration of the penetration based on at least two historical penetrations;

[0148] Determining a first probability based on the penetration standard deviation, the penetration mean, and the current penetration;

[0149] A second probability is determined according to the penetration standard deviation, the minimum penetration, and the current penetration.

[0150] Determining the probability of the target road state switching based on the first probability and the second probability includes:

[0151] The larger value of the first probability and the second probability is determined as the probability that the road state of the target road switches.

[0152] The at least two historical penetration values ​​can be determined based on the penetration values ​​of the target road in at least two historical time periods. Optionally, the value of each historical time period can be configured based on actual needs (e.g., it can be an empirical value or an experimental value), and this application does not impose any restrictions on this. For example, the value of each historical time period can be any time interval such as 24 hours, 3 hours, 30 minutes, etc. The shorter the historical time period, the more accurate the probability of the road state switching of the corresponding target road.

[0153] It is understandable that each historical time period can be continuous or discontinuous, and this application does not impose any restrictions on this. For example, when each historical time period is set to be continuous, if the road status of the target road in one or more historical time periods is closed, that is, if the historical penetration volume corresponding to the historical time period cannot be determined, it is possible to continue to trace back based on the currently selected historical time periods until at least two historical penetration volumes of the target road are obtained. Optionally, the specific number of historical penetration volumes can be configured according to actual needs (such as empirical values ​​or experimental values), for example, the number of historical penetration volumes is 30.

[0154] Optionally, the current penetration amount is the penetration amount when the road state of the target road in the current time period is in the open state, wherein the value of the current time period can be consistent with the value of each historical time period. Of course, the two can also be inconsistent, and this application does not impose any restrictions on this. Among them, when the value of the current time period is consistent with the value of each historical time period, the probability of the road state of the determined target road switching is more accurate. For example, assuming that the current time is 9:53 on November 1, 2020 Beijing time, the duration of the selected current time period and the duration of each historical time period are both 1 day, and it is necessary to obtain 30 historical penetration amounts corresponding to, for example, 30 historical time periods, and the target road is in the open state every day from October 1, 2020 to October 31, 2020, then the current penetration amount in the above text is the penetration amount corresponding to October 31, 2020, and the at least two historical penetration amounts in the above text are the historical penetration amounts corresponding to each day from October 1, 2020 to October 30, 2020, for a total of 30 historical penetration amounts.

[0155] In this implementation, when the target road's road state is open, at least two historical penetrations and the current penetration are obtained for the target road to determine the penetration standard deviation, penetration mean, and minimum penetration. A first probability of a road state switch for the target road (i.e., a first probability of the target road's road state switching from open to closed) is determined based on the penetration standard deviation, penetration mean, and current penetration. A second probability of a road state switch for the target road (i.e., a second probability of the target road's road state switching from open to closed) is determined based on the penetration standard deviation, minimum penetration, and current penetration. Finally, the larger of the first and second probabilities is determined as the probability of the target road's road state switching (i.e., the probability of the target road's road state switching from open to closed). By taking into account the target road's historical penetrations and current penetrations, the first and second probabilities are determined, and the larger of the first and second probabilities is ultimately determined as the probability of the target road's road state switching. This allows for a more accurate determination of the probability of a road state switch for the target road by combining multiple probability determination methods.

[0156] In the case where the target road is in a closed state, if the target road has a penetration volume, it can be considered that the target road can be switched from a closed state to an open state. Optionally, the probability of the target road being switched from a closed state to an open state can be determined in the following manner: when a set condition is met, the probability of the target road being switched from a closed state to an open state is determined to be 1; otherwise, the probability of the target road being switched from a closed state to an open state can be determined to be 0 or a smaller probability value. The set condition may include:

[0157] The current penetration distance of the target road is greater than or equal to a first set value.

[0158] The first set value can be configured based on empirical or experimental values, such as a positive integer greater than or equal to 1. Optionally, the setting condition can also include at least one historical penetration value temporally adjacent to the current penetration value being greater than or equal to the second set value. For the same target road, the first set value and the second set value can be the same or different. The first set value corresponding to different target roads can be the same or different, and the second set value corresponding to different target roads can be the same or different.

[0159] When determining the minimum penetration directly based on at least two historical penetrations, the determined minimum penetration may be affected by the extreme values ​​of the at least two historical penetrations, thereby affecting the accuracy of the ultimately determined second probability, or the probability of the target road's road state switching. Therefore, in the embodiments of the present application, the following optional solution is also provided.

[0160] Optionally, determining the minimum penetration according to at least two historical penetrations includes:

[0161] Randomly selecting a predetermined number of historical penetration quantities from at least two historical penetration quantities, wherein the predetermined number is less than or equal to the total number of the at least two historical penetration quantities;

[0162] According to a predetermined number of historical penetration amounts, a minimum value among the predetermined number of historical penetration amounts is determined, and the minimum value is determined as a minimum penetration amount.

[0163] In this implementation, the predetermined number of values ​​can be configured based on actual needs (e.g., empirical or experimental values) and the specific values ​​of the at least two historical penetration values ​​obtained. The predetermined number of values ​​is preferably half of the total number of the at least two historical penetration values. For example, if the value of the at least two historical penetration values ​​is 30, the predetermined number can be configured as 15.

[0164] By randomly extracting a predetermined number of historical penetrations from at least two historical penetrations and then determining the minimum penetration based on the extracted predetermined number of historical penetrations, the influence of extreme values ​​can be avoided and the accuracy of the determined second probability and the probability of the road state of the target road switching can be improved.

[0165] Optionally, determining the first probability according to the penetration standard deviation, the penetration mean, and the current penetration includes:

[0166] According to the mean value and standard deviation of penetration, a normal distribution model is constructed;

[0167] Determining, based on a normal distribution model, a third probability corresponding to a penetration amount that is less than or equal to the current penetration amount;

[0168] If the third probability and the current penetration amount satisfy a first condition, determining a first ratio of the current penetration amount to the average penetration amount;

[0169] determining a first probability according to the first ratio;

[0170] The first condition is that the third probability is less than the first value and the current penetration amount is less than the second value.

[0171] It is understandable that the normal distribution model constructed based on the penetration mean flow_predict_1 and the penetration standard deviation sigma can be a general normal distribution model or a standard normal distribution model. Specifically, the general normal distribution model constructed based on the penetration mean flow_predict_1 and the penetration standard deviation sigma can be converted to a standard normal distribution model by performing data conversion on the penetration mean flow_predict_1 and the penetration standard deviation sigma so that the penetration mean flow_predict_1 is 0 and the penetration standard deviation sigma is 1.

[0172] In this implementation, the third probability p1 is a third probability that the penetration value is not greater than the current penetration value flow_current in the penetration value distribution of the target road determined based on the normal distribution model. Figure 6 The schematic diagram of the third probability of the embodiment of the present application is shown. According to the mean value of the penetration amount flow_predict_1 and the standard deviation of the penetration amount sigma, the normal distribution model constructed is: Figure 6 The "bell-shaped" curve shown in FIG. 1 represents the penetration distribution of the target road determined based on at least two historical penetrations corresponding to at least two historical time periods. The "bell-shaped" curve is symmetrical about the penetration mean flow_predict_1. The larger the determined penetration standard deviation sigma, the lower and fatter the "bell-shaped" curve is. The smaller the determined penetration standard deviation sigma, the taller and thinner the "bell-shaped" curve is. The horizontal axis represents the penetration value, and the total area of ​​the "bell-shaped" curve and the horizontal axis is 1. And as Figure 6 As shown, in the penetration distribution of the target road, most of the penetrations are distributed within the curve corresponding to the penetration mean flow_predict_1±3*penetration standard deviation sigma.

[0173] In this "bell-shaped" curve, taking the value of a certain penetration amount as an example, the penetration amount is determined to correspond to a point on the "bell-shaped" curve. The left curve of this point in the "bell-shaped" curve represents a distribution situation in which a penetration amount is less than this penetration amount in the penetration amount distribution situation, and the area between the left curve of this point and the horizontal axis represents the probability of a distribution situation in which a penetration amount is less than the current penetration amount in the penetration amount distribution situation of the target road; the right curve of this point in the "bell-shaped" curve represents a distribution situation in which a penetration amount is greater than this penetration amount in the entire penetration amount distribution situation, and the area between the right curve of this point and the horizontal axis represents the probability of a distribution situation in which a penetration amount is greater than the current penetration amount in the penetration amount distribution situation of the target road.

[0174] In the embodiments of this application, Figure 6As shown, in the above-mentioned "bell-shaped" curve, a point corresponding to the current penetration flow_current on the horizontal axis is selected, and the area between the point corresponding to the current penetration flow_current on the "bell-shaped" curve and the curve on the left side of the point corresponding to the current penetration flow_current and the horizontal axis is determined ( Figure 6 The area is the third probability p1.

[0175] Optionally, the third probability p1 corresponding to a penetration amount less than or equal to the current penetration amount flow_current may be determined based on a probability density function corresponding to the constructed normal distribution model or by querying a normal distribution table. Specifically, when determining the third probability p1 corresponding to a penetration amount less than or equal to the current penetration amount flow_current based on the probability density function corresponding to the constructed normal distribution model, the third probability p1 corresponding to a penetration amount less than or equal to the current penetration amount flow_current may be obtained by integrating the probability density function.

[0176] In this implementation, the first and second values ​​can be configured based on actual needs (e.g., empirical or experimental values). The setting of the first and second values ​​is related to the desired accuracy of the first probability. Considering the empirical rule of normal distribution (almost all data are within three standard deviations), the first value is negatively correlated with the desired accuracy of the first probability p_close_1, and the second value is negatively correlated with the accuracy of the determined first probability p_close_1. For example, for a specific target road, the first value can be set to 0.05 and the second value to 15.

[0177] Optionally, according to the first ratio Determining a first probability p_close_1 includes: determining a ratio of 1 to the first The first difference between The first difference The first probability p_close_1 is determined as follows:

[0178]

[0179] In the embodiment of the present application, an optional implementation is also provided. If the third probability and the current penetration value do not satisfy the first condition, determining the probability of the target road state switching based on the first probability and the second probability includes:

[0180] The second probability is determined as a probability that the road state of the target road switches.

[0181] In this implementation, the third probability and the current penetration amount not satisfying the first condition may include one or more of the following situations:

[0182] The third probability is greater than or equal to the first value;

[0183] The current penetration amount is greater than or equal to the second value.

[0184] By setting a first condition, when the third probability and the current penetration amount satisfy the first condition, a first ratio of the current penetration amount to the mean penetration amount is determined, and a first probability is determined based on the first ratio. When the third probability and the current penetration amount do not satisfy the first condition, the second probability is determined as the probability of a road state switch on the target road. This allows for rapid and accurate determination of the probability of a road state switch on the target road.

[0185] Alternatively, if the third probability p1 and the current penetration flow_current do not satisfy the first condition, the first probability p_close_1 may be set to any value less than the second probability p_close_2, for example, to 0. That is, when determining the first probability p_close_1 of a road state switch on the target road based on the penetration standard deviation sigma, the penetration mean flow_predict_1, and the current penetration flow_current, the probability of a road state switch determined in this manner is low.

[0186] Taking the current closed state of a target road as an example, combined with the empirical rules of normal distribution, when the third probability p1 is less than the first value, it can be determined that the target road is highly likely to remain closed, and the probability of its road state switching is extremely low. Furthermore, based on empirical values, when the current flow_current of a target road is less than the second value, it can also be considered that the target road has low traffic volume and is likely to be closed. Therefore, if the third probability p1 and the current flow_current do not meet the first condition, the first probability p_close_1 can be set to any value less than the second probability, for example, setting the first probability p_close_1 to 0.

[0187] By setting a first condition, when the third probability and the current penetration amount satisfy the first condition, a first ratio of the current penetration amount to the mean penetration amount is determined, and the first probability is determined based on the first ratio. When the third probability and the current penetration amount do not satisfy the first condition, the first probability is set to a value less than the second probability, for example, to 0. This allows for rapid and accurate determination of the first probability.

[0188] Optionally, determining the second probability according to the penetration standard deviation, the minimum penetration, and the current penetration includes:

[0189] If the minimum penetration and the current penetration meet a second condition, determining a second ratio of the current penetration to the minimum penetration;

[0190] determining a second probability based on the second ratio;

[0191] The second condition is that the difference between the minimum penetration and the current penetration is greater than a preset multiple of the penetration standard deviation, and the current penetration is less than a third value.

[0192] In this implementation, the third value can be configured based on actual needs (e.g., an empirical or experimental value). The setting of the third value is related to the accuracy of the determined second probability, and the third value is negatively correlated with the accuracy of the determined second probability p_close_2. For the same target road, the third value can be the same as or different from the second value. For example, for the same target road, the second and third values ​​can both be set to 15; alternatively, the second value can be set to 12 and the third value can be set to 15.

[0193] In this implementation, the value of the preset multiple can be configured according to actual needs (such as empirical values ​​or experimental values). Combined with the empirical rules of normal distribution, the value of the preset multiple can be 1, 2, or 3. The value of the preset multiple can be determined according to the accuracy requirements, wherein the value of the preset multiple is positively correlated with the accuracy required to determine the second probability.

[0194] Optionally, according to the second ratio Determine the second probability p_close_2, including: determining 1 and the second ratio The second difference between The second difference Determined as the second probability p_close_2.

[0195] Optionally, if the minimum penetration amount and the current penetration amount do not satisfy the second condition, determining the probability of the target road state switching based on the first probability and the second probability includes:

[0196] The first probability is determined as a probability that the road state of the target road switches.

[0197] In this implementation, the minimum penetration and the current penetration do not satisfy the second condition may include: a difference between the minimum penetration and the current penetration is less than or equal to a preset multiple of a standard deviation of the penetration.

[0198] By setting a second condition, when the current penetrations and the minimum penetrations meet the second condition, a second ratio of the current penetrations to the minimum penetrations is determined, and a second probability is determined based on the second ratio. When the current penetrations and the minimum penetrations do not meet the second condition, the first probability is determined as the probability that the target road's road state has switched. This allows for rapid and accurate determination of the probability that the target road's road state has switched (i.e., the probability that the target road's road state has switched from an open state to a closed state).

[0199] In this implementation, if the minimum penetration flow_min and the current penetration flow_current do not satisfy the second condition, the second probability can be set to any value less than the first probability p_close_1. For example, the second probability p_close_2 can be determined to be 0. That is, when determining the second probability p_close_2 of a road state switch on the target road based on the penetration standard deviation sigma, the minimum penetration flow_min, and the current penetration flow_current, the probability of a road state switch determined using this method is low.

[0200] Taking the current closed state of a target road as an example, combined with empirical rules of normal distribution, a third probability p1 can be set. When the difference between the minimum penetration flow_min and the current penetration flow_current (flow_min-flow_current) is less than a preset multiple of the penetration standard deviation sigma, the probability that the target road is still closed is high, and the probability of its road state switching is extremely low. Furthermore, based on empirical values, if the current penetration flow_current of a target road is less than the third value, it can be considered that the target road has low traffic volume and is likely to be closed. Therefore, if the minimum penetration flow_min and the current penetration flow_current do not meet the second condition, the second probability p_close_2 can be set to any value less than the first probability, for example, setting the second probability p_close_2 to 0.

[0201] By setting a second condition, when the current penetration amount and the minimum penetration amount meet the second condition, a second ratio of the current penetration amount to the minimum penetration amount is determined, and a second probability is determined based on the second ratio. When the current penetration amount and the minimum penetration amount do not meet the second condition, the first probability is set to any value less than the second probability, for example, the second probability is set to 0. This allows for rapid and accurate determination of the second probability.

[0202] It is understood that if the third probability and the current penetration amount do not satisfy the first condition, and the current penetration amount and the minimum penetration amount do not satisfy the second condition, it can be determined that the probability of the target road's road state switching is extremely low, and the probability of the target road's road state switching can be determined to be a relatively small set value. For example, the set value can be set to 0.

[0203] The following describes in detail the data processing method in the embodiment of the present application with reference to an example in a specific application scenario. Figure 7a 、 Figure 7b 、 Figure 8 . Figure 7a and Figure 7b A schematic diagram showing a specific application scenario of the present application is shown. Figure 8 The flowchart of implementing the above method in a specific application scenario of the present application is shown. In this application scenario, the above method can be implemented through an application of a terminal device or a plug-in in the application. Taking the probability of a road state switching from an open state to a closed state determined by a navigation software in a terminal device as an example, the above method is further explained. Figure 8 As shown, the method may include steps S210 to S240.

[0204] Step S210: Data input. Specifically:

[0205] like Figure 7a As shown, the user's travel needs can be entered by entering "departure place C" and "destination D" on the user interface of the navigation application in the terminal device and clicking the search control "Q".

[0206] In response to the user's travel demand, the user's historical travel route L1 → L2 → L3 → L4 is obtained according to the data uploaded by the navigation application.

[0207] Load the preset map road data and obtain the road status information of each road in the map based on the map road data.

[0208] Step S220: Feature calculation and processing. Specifically:

[0209] Based on trajectory map matching, according to the user's historical driving route (e.g., L1→L2→L3→L4) and map road data, multiple target roads l1, l2, l3, and l4 that match each road L1, L2, L3, and L4 in the user's driving route are determined respectively.

[0210] For example, 30 historical penetrations and a current penetration of each target road among the plurality of target roads l1, l2, l3, and l4 are determined respectively.

[0211] Step S230: Determine the first road closure probability (i.e., the first probability) and the second road closure probability (i.e., the second probability) of the target road according to the road closure probability model.

[0212] For each target road, a first road closure probability p_close_1 is determined according to a normal distribution prediction method (step ① below), and a second road closure probability p_close_2 is determined according to a template prediction method (step ② below).

[0213] Step 1: Normal distribution prediction

[0214] a. Based on, for example, 30 historical penetrations of the current target road, obtain the penetration mean flow_predict_1 and standard deviation sigma, and construct a normal distribution model based on the penetration mean flow_predict_1 and standard deviation sigma.

[0215] b. Determine whether the road is suspected to be closed

[0216] Based on the normal distribution model and the current penetration flow_current, a third probability p1 lower than the current penetration flow_current is calculated. That is, the probability of a penetration less than or equal to the current penetration in the 30 historical penetrations appearing in the normal distribution is obtained by integrating the probability density function.

[0217] When the third probability p1 is less than 0.05 and the current penetration flow_current is less than 15, the road is determined to be in a suspected closed state; otherwise, p_close_1 is determined to be 0.

[0218] c. When the road is suspected to be closed, calculate the first road closure probability p_close_1 according to the following formula.

[0219]

[0220] Step 2: Template prediction

[0221] a. Randomly sample, for example, 30 historical penetrations, extract, for example, 15 historical penetrations, and determine the minimum penetration flow_min' among the 15 extracted historical penetrations.

[0222] b. Determine whether the road is suspected to be closed

[0223] If the difference between the minimum penetration flow_min' and the current penetration flow_current, flow_min'-flow_current, is greater than twice the standard deviation sigma, and the current penetration flow_current is less than 15, the road is determined to be in a suspected closed state; otherwise, p_close_2 is determined to be 0.

[0224] c. If the road is suspected to be closed, calculate the second road closure probability p_close_2 according to the following formula.

[0225]

[0226] Step S240: Outputting the probability p_close of the road closure (ie, the probability that the road state of the target road switches from the open state to the closed state).

[0227] For each target road, the following formula can be used to determine the probability p_close of the target road being closed according to the first road closure probability p_close_1 and the second road closure probability p_close_2 corresponding to the target road.

[0228] p_close=max(p_close_1, p_close_2)

[0229] After step S240, the map road data may be updated according to the probability of each target road being closed, and a driving route matching the user's driving needs may be determined based on the updated map road data and the user's driving needs. Figure 7b The driving route from departure point C to destination D is shown.

[0230] It is understood that the data processing method provided in the embodiments of the present application can be applied to determine a driving route that matches a user's travel needs in different time periods, and the embodiments of the present application are not limited to specific time periods. For example, the data processing method provided in the embodiments of the present application can not only instantly determine a driving route that matches the user's travel needs based on the user's current travel needs, but can also determine a driving route that matches the predetermined travel needs set by the user at the current time (2:00 PM on the first day). The predetermined travel needs can be a travel need for a predetermined time (e.g., 5:30 AM on the third day). In this implementation, when providing a driving route that matches the predetermined travel needs, the user can be provided with a reference prompt, such as "The currently recommended driving route is determined based on current road data for your reference. Since the current time is a long time away from your scheduled trip, road data may change during this period. To ensure a smooth trip, it is recommended that you re-check the route before departure."

[0231] Figure 9 Schematic diagram of the data processing device provided by the embodiment of the present application is shown. Figure 9 As shown, the device 800 includes a data acquisition module 810 , a probability determination module 820 and a data update module 830 .

[0232] The data acquisition module 810 is configured to acquire the penetration volume of a target road and map road data, wherein the penetration volume of a target road represents the number of vehicle penetrations from the starting point to the end point of the target road;

[0233] The data acquisition module 810 is further configured to acquire the road status of the target road from the map road data, where the road status includes a closed state or an open state;

[0234] A probability determination module 820 is configured to determine a probability of a road state switching of the target road based on the penetration amount of the target road and the road state of the target road;

[0235] The data updating module 830 is configured to update the map road data according to the probability of the target road state switching.

[0236] Optionally, the probability determination module 820 determines the probability of the target road's road state switching based on the target road's penetration amount and the target road's road state, specifically for:

[0237] Determining, according to the penetration volume of the target road and the road state of the target road, a first probability of a road state switching of the target road and a second probability of a road state switching of the target road in two different ways;

[0238] The probability of the target road's road state switching is determined based on the first probability and the second probability.

[0239] Optionally, the penetration volume of the target road includes at least two historical penetration volumes of the target road and a current penetration volume of the target road. When the probability determination module 820 adopts two different methods to respectively determine a first probability of a road state switching of the target road and a second probability of a road state switching of the target road, the probability determination module 820 is specifically configured to:

[0240] Determine the standard deviation, mean and minimum penetration of the penetration based on at least two historical penetrations;

[0241] determining a first probability of a road state switching of the target road based on the penetration standard deviation, the penetration mean, and the current penetration;

[0242] determining a second probability of a road state switching of the target road based on the penetration standard deviation, the minimum penetration, and the current penetration;

[0243] When the road state of the target road is open, the probability determination module 820 determines the probability of the road state of the target road switching based on the first probability and the second probability, specifically for:

[0244] The larger value of the first probability and the second probability is determined as the probability that the road state of the target road switches.

[0245] Optionally, when determining the first probability based on the penetration standard deviation, the penetration mean, and the current penetration, the probability determination module 820 is specifically configured to:

[0246] A normal distribution model is constructed based on the above penetration amount mean and the above penetration amount standard deviation;

[0247] Determining, based on the normal distribution model, a third probability corresponding to a penetration amount that is less than or equal to the current penetration amount;

[0248] If the third probability and the current penetration amount satisfy a first condition, determining a first ratio of the current penetration amount to the average penetration amount;

[0249] Determining the first probability according to the first ratio;

[0250] The first condition is that the third probability is less than the first value and the current penetration amount is less than the second value.

[0251] Optionally, if the third probability and the current penetration amount do not satisfy the first condition, the probability determination module 820, when determining the probability of the target road state switching based on the first probability and the second probability, is specifically configured to:

[0252] The second probability is determined as a probability that the road state of the target road switches.

[0253] Optionally, when determining the second probability based on the penetration standard deviation, the minimum penetration, and the current penetration, the probability determination module 820 is specifically configured to:

[0254] If the minimum penetration and the current penetration meet a second condition, determining a second ratio of the current penetration to the minimum penetration;

[0255] determining the second probability according to the second ratio;

[0256] The second condition is that the difference between the minimum penetration and the current penetration is greater than a preset multiple of the penetration standard deviation, and the current penetration is less than a third value.

[0257] Optionally, if the minimum penetration amount and the current penetration amount do not satisfy the second condition, the probability determination module 820, when determining the probability of the road state of the target road switching based on the first probability and the second probability, is specifically configured to:

[0258] The first probability is determined as a probability that the road state of the target road switches.

[0259] Optionally, when determining the minimum penetration value based on at least two historical penetration values, the probability determination module 820 is specifically configured to:

[0260] Randomly selecting a predetermined number of historical penetration quantities from at least two historical penetration quantities, wherein the predetermined number is less than or equal to the total number of the at least two historical penetration quantities;

[0261] According to a predetermined number of historical penetration amounts, a minimum value among the predetermined number of historical penetration amounts is determined, and the minimum value is determined as the minimum penetration amount.

[0262] Optionally, the target road is determined according to the following method:

[0263] Get historical driving routes;

[0264] Based on trajectory map matching, the target road corresponding to the historical driving route in the map road data is determined.

[0265] The device of the embodiment of the present application can execute the method provided by the embodiment of the present application, and its implementation principle is similar. The actions performed by each module in the device of each embodiment of the present application correspond to the steps in the method of each embodiment of the present application. For the detailed functional description of each module of the device, please refer to the description in the corresponding method shown in the previous text, and will not be repeated here.

[0266] An embodiment of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory, and the processor executes the computer program to implement the steps of the above method.

[0267] In an alternative embodiment, an electronic device is provided, such as Figure 10 shown. Figure 10 A schematic diagram of an electronic device provided in an embodiment of the present application is shown. Figure 10 The electronic device 4000 shown includes: a processor 4001 and a memory 4003. The processor 4001 and the memory 4003 are connected, for example, via a bus 4002. Optionally, the electronic device 4000 may further include a transceiver 4004, which may be used for data exchange between the electronic device and other electronic devices, such as data transmission and / or data reception. It should be noted that in actual applications, the number of transceivers 4004 is not limited to one, and the structure of the electronic device 4000 does not constitute a limitation on the embodiments of the present application.

[0268] Processor 4001 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It may implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 4001 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like.

[0269] Bus 4002 may include a path for transmitting information between the above components. Bus 4002 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. Bus 4002 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 10 Only one thick line is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0270] The memory 4003 can be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic disk storage media, other magnetic storage devices, or any other medium that can be used to carry or store computer programs and can be read by a computer, without limitation here.

[0271] The memory 4003 is used to store the computer program for executing the embodiment of the present application, and the execution is controlled by the processor 4001. The processor 4001 is used to execute the computer program stored in the memory 4003 to implement the steps shown in the above method embodiment.

[0272] Based on the same principles as the methods provided in the embodiments of the present application, the embodiments of the present application further provide a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the method provided in any of the above-mentioned optional embodiments of the present application.

[0273] An embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps and corresponding contents of the aforementioned method embodiment can be implemented.

[0274] An embodiment of the present application also provides a computer program product, including a computer program, which can implement the steps and corresponding contents of the aforementioned method embodiment when executed by a processor.

[0275] It should be understood that, although each operation step is indicated by arrows in the flowchart of the embodiment of the present application, the order of implementation of these steps is not limited to the order indicated by the arrows. Unless otherwise clearly stated herein, in some implementation scenarios of the embodiment of the present application, the implementation steps in each flowchart can be performed in other orders according to demand. In addition, some or all of the steps in each flowchart can include multiple sub-steps or multiple stages based on actual implementation scenarios. Some or all of these sub-steps or stages can be executed at the same time, and each sub-step or stage in these sub-steps or stages can also be executed at different times respectively. Under different scenarios at the execution time, the execution order of these sub-steps or stages can be flexibly configured according to demand, and the embodiment of the present application does not limit this.

[0276] The above description is only an optional implementation method for some implementation scenarios of this application. It should be pointed out that for ordinary technicians in this technical field, without departing from the technical concept of the solution of this application, the use of other similar implementation methods based on the technical ideas of this application also falls within the protection scope of the embodiments of this application.

Claims

1. A data processing method, characterized in that: include: Obtaining a penetration volume of a target road and map road data, wherein the penetration volume of the target road represents the number of vehicle penetrations from a starting point to an end point of the target road; the penetration volume of the target road includes at least two historical penetration volumes corresponding to at least two historical time periods of the target road and a current penetration volume corresponding to a current time period of the target road; Acquiring a road state of the target road from the map road data, the road state including a closed state or an open state; When the target road is in an open state, determining a penetration standard deviation, a penetration mean, and a minimum penetration based on the at least two historical penetrations; determining a first probability of a road state switching of the target road according to the penetration standard deviation, the penetration mean, and the current penetration; If the minimum penetration and the current penetration meet a second condition, determining a second ratio of the current penetration to the minimum penetration; and determining a second probability of a road state switch of the target road based on the second ratio; wherein the second condition is that the difference between the minimum penetration and the current penetration is greater than a preset multiple of the penetration standard deviation, and the current penetration is less than a third value; Determining a probability of a road state switching of the target road based on the first probability and the second probability; The map road data is updated according to the probability of the road state of the target road switching.

2. The method according to claim 1, characterized in that The determining, based on the first probability and the second probability, a probability that the road state of the target road switches, includes: A larger value between the first probability and the second probability is determined as the probability that the road state of the target road switches.

3. The method according to claim 1, characterized in that The determining the first probability according to the penetration standard deviation, the penetration mean, and the current penetration includes: constructing a normal distribution model according to the penetration mean and the penetration standard deviation; determining, based on the normal distribution model, a third probability corresponding to a penetration amount that is less than or equal to the current penetration amount; If the third probability and the current penetration satisfy a first condition, determining a first ratio of the current penetration to the average penetration; determining the first probability according to the first ratio; The first condition is that the third probability is less than a first value, and the current penetration is less than a second value.

4. The method according to claim 3, characterized in that If the third probability and the current penetration amount do not satisfy the first condition, determining the probability of the target road state switching based on the first probability and the second probability includes: The second probability is determined as a probability that the road state of the target road switches.

5. The method according to claim 1, wherein If the minimum penetration amount and the current penetration amount do not satisfy the second condition, determining the probability of the target road state switching based on the first probability and the second probability includes: The first probability is determined as a probability that the road state of the target road switches.

6. The method according to claim 1, characterized in that The determining of the minimum penetration according to the at least two historical penetrations includes: Randomly selecting a predetermined number of historical penetrations from the at least two historical penetrations, where the predetermined number is less than or equal to the total number of the at least two historical penetrations; According to the predetermined number of historical penetrations, a minimum value among the predetermined number of historical penetrations is determined, and the minimum value is determined as the minimum penetration.

7. The method according to claim 1, characterized in that The target road is determined according to the following method: Get historical driving routes; Based on trajectory map matching, the target road corresponding to the historical driving route in the map road data is determined.

8. The method according to claim 7, characterized in that The determining the target road corresponding to the historical driving route in the map road data includes: respectively determining a degree of matching between the historical driving route and each road to be matched in the map road data; The road to be matched that has the highest matching degree with the historical driving route is determined as the target road.

9. The method according to claim 8, characterized in that The determining of the matching degree between the historical driving route and each road to be matched in the map road data includes: For each of the roads to be matched, determining the distance and angle between the historical driving route and the road to be matched; Based on a first weight value corresponding to the distance and a second weight value corresponding to the angle, weighted sums are respectively performed on the distance and the angle to obtain a matching degree corresponding to the to-be-matched road.

10. A data processing device, characterized in that: include: a data acquisition module, configured to acquire a penetration volume of a target road and map road data, wherein the penetration volume of the target road represents the number of vehicle penetrations from a starting point to an end point of the target road; the penetration volume of the target road includes at least two historical penetration volumes corresponding to at least two historical time periods of the target road and a current penetration volume corresponding to a current time period of the target road; The data acquisition module is further configured to acquire the road status of the target road from the map road data, where the road status includes a closed state or an open state; a probability determination module, configured to determine, when the target road is in an open state, a standard deviation of the penetration, a mean of the penetration, and a minimum penetration based on the at least two historical penetrations; The probability determination module is further configured to determine a first probability of a road state switching of the target road based on the penetration standard deviation, the penetration mean, and the current penetration; The probability determination module is further configured to determine a second ratio of the current penetration to the minimum penetration if the minimum penetration and the current penetration meet a second condition; and determine a second probability of a road state switch of the target road based on the second ratio; wherein the second condition is that the difference between the minimum penetration and the current penetration is greater than a preset multiple of the penetration standard deviation, and the current penetration is less than a third value; The probability determination module is further configured to determine a probability of a road state switching of the target road based on the first probability and the second probability; The data updating module is used to update the map road data according to the probability of the road state of the target road switching.

11. The device according to claim 10, characterized in that When the probability determination module determines the probability of the target road state switching based on the first probability and the second probability, it is specifically configured to: A larger value between the first probability and the second probability is determined as the probability that the road state of the target road switches.

12. The device according to claim 10, characterized in that When determining the first probability according to the penetration standard deviation, the penetration mean, and the current penetration, the probability determination module is specifically configured to: constructing a normal distribution model according to the penetration mean and the penetration standard deviation; determining, based on the normal distribution model, a third probability corresponding to a penetration amount that is less than or equal to the current penetration amount; If the third probability and the current penetration satisfy a first condition, determining a first ratio of the current penetration to the average penetration; determining the first probability according to the first ratio; The first condition is that the third probability is less than a first value, and the current penetration is less than a second value.

13. The device according to claim 12, characterized in that If the third probability and the current penetration amount do not satisfy the first condition, the probability determination module, when determining the probability of the target road state switching based on the first probability and the second probability, is specifically configured to: The second probability is determined as a probability that the road state of the target road switches.

14. The device according to claim 10, characterized in that If the minimum penetration amount and the current penetration amount do not satisfy the second condition, the probability determination module, when determining the probability of the target road state switching based on the first probability and the second probability, is specifically configured to: The first probability is determined as a probability that the road state of the target road switches.

15. The device according to claim 10, characterized in that When determining the minimum penetration amount based on the at least two historical penetration amounts, the probability determination module is specifically configured to: Randomly selecting a predetermined number of historical penetrations from the at least two historical penetrations, where the predetermined number is less than or equal to the total number of the at least two historical penetrations; According to the predetermined number of historical penetrations, a minimum value among the predetermined number of historical penetrations is determined, and the minimum value is determined as the minimum penetration.

16. The device according to claim 10, characterized in that The data acquisition module is further configured to determine the target road according to the following method: Get historical driving routes; Based on trajectory map matching, the target road corresponding to the historical driving route in the map road data is determined.

17. The device according to claim 16, characterized in that When determining the target road corresponding to the historical driving route in the map road data, the data acquisition module is specifically configured to: respectively determining a degree of matching between the historical driving route and each road to be matched in the map road data; The road to be matched that has the highest matching degree with the historical driving route is determined as the target road.

18. The device according to claim 17, characterized in that When determining the matching degree between the historical driving route and each road to be matched in the map road data, the data acquisition module is specifically used to: For each of the roads to be matched, determining the distance and angle between the historical driving route and the road to be matched; Based on a first weight value corresponding to the distance and a second weight value corresponding to the angle, weighted sums are respectively performed on the distance and the angle to obtain a matching degree corresponding to the to-be-matched road.

19. An electronic device comprising a memory, a processor, and a computer program stored in the memory, wherein: The processor executes the computer program to implement the steps of the method according to any one of claims 1 to 9.

20. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 9 are implemented.

21. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 9 are implemented.

Images