Method, device and electronic equipment for processing electronic road toll collection account of vehicle

Abstract

The present application provides a method, device, electronic device and computer-readable storage medium for processing a road electronic toll collection account of a vehicle; applied to the field of transportation, the method includes: displaying an electronic map based on a vehicle map system account login; in response to a navigation operation, displaying a navigation route from a set starting point to an end point in the electronic map; obtaining the account status of the road electronic toll collection system account of the vehicle, the account status representing the status of the road electronic toll collection system account when the vehicle travels according to the navigation route; and displaying the account status. The present application can prompt the account status of the road electronic toll collection account in a timely manner to ensure the normal driving of the vehicle.

Description

Technical Field

[0001] The present application relates to artificial intelligence technology, and more particularly to a method, device, electronic device and computer-readable storage medium for processing a road electronic toll collection account of a vehicle. Background Art

[0002] Intelligent Vehicle Infrastructure Cooperative Systems (IVICS), referred to as IVICS, is a development direction of intelligent transportation systems. IVICS uses advanced wireless communications and new generation Internet technologies to implement all-round dynamic real-time information interaction between vehicles and roads, and conducts active vehicle safety control and road cooperative management based on the collection and integration of dynamic traffic information in all time and space, fully realizing the effective coordination of people, vehicles and roads, ensuring traffic safety, and improving traffic efficiency, thus forming a safe, efficient and environmentally friendly road traffic system.

[0003] For vehicles that have applied for Electronic Toll Collection (ETC), when passing through highways or bridges with manual toll lanes and ETC lanes, passing through the ETC lanes greatly improves the smoothness of passage. In actual applications, due to forgetting to recharge or ETC card failure, the vehicle's ETC business status will be in an abnormal state (commonly known as "blacklisted"), which will affect the normal passage of subsequent vehicles through the toll lanes, which will cause great congestion and inconvenience in traffic, and also increase travel risks and cause unnecessary losses. Summary of the invention

[0004] The embodiments of the present application provide a method, device, electronic device and computer-readable storage medium for processing a road electronic toll collection account of a vehicle, which can promptly prompt the account status of the road electronic toll collection account to ensure the normal driving of the vehicle.

[0005] The technical solution of the embodiment of the present application is implemented as follows:

[0006] The present application embodiment provides a method for processing a road electronic toll collection account of a vehicle, comprising:

[0007] Display electronic maps based on the vehicle's map system account login;

[0008] In response to the navigation operation, displaying a navigation route from a set starting point to an end point on the electronic map;

[0009] Acquiring an account status of an electronic road toll collection system account of the vehicle, the account status representing a status that the electronic road toll collection system account will have when the vehicle travels according to the navigation route;

[0010] Displays the status of the account.

[0011] The embodiment of the present application provides a vehicle road electronic toll collection account processing device, comprising:

[0012] A display module, used to display an electronic map based on a vehicle's map system account login;

[0013] The display module is further used to display a navigation route from a set starting point to an end point in the electronic map in response to a navigation operation;

[0014] a processing module, configured to obtain an account status of an electronic road toll collection system account of the vehicle, wherein the account status represents a status that the electronic road toll collection system account will have when the vehicle travels according to the navigation route;

[0015] The display module is also used to display the account status.

[0016] An embodiment of the present application provides an electronic device, including:

[0017] A memory for storing executable instructions;

[0018] The processor is used to implement the vehicle road electronic toll collection account processing method provided in the embodiment of the present application when executing the executable instructions stored in the memory.

[0019] An embodiment of the present application provides a computer-readable storage medium storing executable instructions for implementing a method for processing a road electronic toll collection account of a vehicle provided in an embodiment of the present application when executed by a processor.

[0020] The embodiments of the present application have the following beneficial effects:

[0021] The electronic map prompts the status of the road electronic toll collection system account when the vehicle travels according to the navigation route, so that the user can promptly know and maintain the account status of the road electronic toll collection account, thereby ensuring the normal driving of the vehicle. In addition, since the account status prompt is integrated in the electronic map, it saves the operation of repeatedly switching between different functional interfaces, has extremely high human-computer interaction efficiency, and improves the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1A It is a structural diagram of a road electronic toll collection account processing system for a vehicle provided in an embodiment of the present application;

[0023] Figure 1B This is a schematic diagram of the structure of the road electronic toll account processing system for vehicles based on the blockchain network provided in the embodiment of the present application.

[0024] Figure 2 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application;

[0025] Figures 3A-3D It is a flowchart of a method for processing a road electronic toll collection account of a vehicle provided in an embodiment of the present application;

[0026] Figure 4 It is a schematic diagram of the algorithm architecture of the method for processing the road electronic toll collection account of a vehicle provided in an embodiment of the present application;

[0027] Figure 5 It is a schematic diagram of the interface of the method for processing the road electronic toll collection account of a vehicle provided in an embodiment of the present application;

[0028] Figure 6 It is a logical schematic diagram of a method for processing a road electronic toll collection account of a vehicle provided in an embodiment of the present application;

[0029] Figure 7 It is a schematic diagram of the training and testing process of the method for processing the road electronic toll collection account of a vehicle provided in an embodiment of the present application;

[0030] Figure 8 It is a schematic diagram of a prediction flow of a method for processing a road electronic toll collection account of a vehicle provided in an embodiment of the present application;

[0031] Fig. 9 is a schematic diagram of a navigation interface provided in an embodiment of the present application;

[0032] Fig.10 A schematic diagram of a navigation interface provided in an embodiment of the present application;

[0033] Fig.11 A schematic diagram of a navigation interface provided in an embodiment of the present application;

[0034] Fig.12 A schematic diagram of a navigation interface provided in an embodiment of the present application. DETAILED DESCRIPTION

[0035] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0036] In the following description, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it can be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0037] In the following description, the terms "first\second\third" involved are merely used to distinguish similar objects and do not represent a specific ordering of the objects. It can be understood that "first\second\third" can be interchanged with a specific order or sequence where permitted, so that the embodiments of the present application described here can be implemented in an order other than that illustrated or described here.

[0038] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0039] Before further describing the embodiments of the present application in detail, the nouns and terms involved in the embodiments of the present application are explained. The nouns and terms involved in the embodiments of the present application are subject to the following interpretations.

[0040] 1) ETC: It is an automatic toll collection system used on roads (such as highways or bridges). It uses dedicated short-range communication between the on-board electronic tag installed on the vehicle windshield and the microwave antenna on the ETC lane at the toll station, and uses computer networking technology to conduct back-end settlement processing with the bank, so that vehicles can pay highway or bridge fees without stopping at highway or bridge toll stations.

[0041] 2) Map account system: map applications, map applets or map software, etc. The map account system includes personal basic information, vehicle information, track information, violation records, etc. The map account system is an account system registered using a social account or mobile phone number.

[0042] 3) Image processing: technology that processes images through computers to achieve the desired effect. Image processing technology includes image compression, enhancement and restoration, matching description recognition, etc. Common specific processing includes image digitization, image coding, image enhancement, image restoration, image segmentation and image analysis.

[0043] 4) Unbiased estimation: The mathematical expectation of the estimator is equal to the true value of the estimated parameter.

[0044] 5) State transition: The state of this stage is often the result of the state and decision of the previous stage. If the state Sk of the Kth stage and the decision u are given k (S k ), then the state S of the K+1th stage k+1 That's completely certain.

[0045] In the related art, the account status of a vehicle's electronic road toll collection system account is determined based on the balance status of the road electronic road toll collection system account when the vehicle is traveling on the highway. When the account balance is not enough to offset the highway toll and the recharge is still not completed in the next deduction cycle, the road electronic road toll collection system will blacklist the vehicle's account status, thereby affecting the user's travel experience. When implementing the embodiments of the present application, the applicant found that, for the sake of user information security, privacy information such as balance status and credit status is difficult to obtain from the client or backend of the road electronic road toll collection system. Therefore, it is impossible to obtain the account status of the road electronic road toll collection system account at a certain moment in the future in real time.

[0046] The embodiments of the present application provide a method, device, electronic device and computer-readable storage medium for processing a road electronic toll collection account of a vehicle, which can timely obtain the account status of the road electronic toll collection account to ensure the normal driving of the vehicle.

[0047] The vehicle road electronic toll collection account processing method provided in the embodiment of the present application can be implemented by various electronic devices, for example, it can be implemented by a terminal (including a smart phone, a tablet computer, a vehicle-mounted terminal) or a server alone, or it can be implemented by a terminal and a server in collaboration.

[0048] The following describes an exemplary application of an electronic device implemented as a server in a road electronic toll collection account processing system for a vehicle. Figure 1A , Figure 1A It is a structural diagram of the road electronic toll collection account processing system for a vehicle provided in an embodiment of the present application. The target vehicle has handled the road electronic toll collection business (installed with a road electronic toll collection device). The terminal 400 is connected to the road electronic toll collection device of the target vehicle 300 through a network. The terminal 400 is connected to the server 200 through a network. The server 200 is connected to the road electronic toll collection device of the target vehicle 300 through a network. The network can be a wide area network or a local area network, or a combination of the two, and a wireless link is used to realize data transmission.

[0049] In an application scenario, the function of the vehicle's road electronic toll collection account processing system is implemented based on the server 200. When the user uses the terminal 400, the terminal 400 collects the map system data and the road toll collection system data of the first time period and sends them to the server 200, so that the server 200 predicts the account status of the road electronic toll collection system account in the second time period based on the map system data and the road toll collection system data.

[0050] In an application scenario, when the vehicle's road electronic toll collection account processing system is applied to a vehicle driving scenario, during the vehicle's driving, the terminal 400 corresponding to the vehicle collects map system data and road toll collection system data of a first time period and sends them to the server 200, so that the server 200 predicts the account status of the road electronic toll collection system account in a second time period based on the map system data and the road toll collection system data, and the server 200 returns the predicted account status to the terminal 400 for presentation.

[0051] In other embodiments, when the vehicle road electronic toll collection account processing method provided in the embodiments of the present application is implemented by a terminal alone, in the various application scenarios described above, the terminal can determine the account status of the road electronic toll collection system account in the second time period, and directly present the account status of the road electronic toll collection system account in the second time period.

[0052] In some embodiments, the server 200 may be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The terminal 400 may be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, a smart TV, a smart car device, etc. The terminal 400 may be provided with a client, such as an instant messaging client, a learning client, a game client, a map client, a client of a road toll system, etc., but is not limited thereto. The terminal and the server may be directly or indirectly connected via wired or wireless communication, which is not limited in the embodiments of the present application.

[0053] In some embodiments, see Figure 1B , Figure 1B is a schematic diagram of the structure of the road electronic toll collection account processing system for vehicles based on the blockchain network provided by the embodiment of the present application. The following describes an exemplary application of the embodiment of the present application based on the blockchain network. Figure 1B , including a blockchain network 600 (exemplarily showing nodes 610 - 1 and node 610 - 2 included in the blockchain network 600 ), a server 200 , and a terminal 400 , which are described below respectively.

[0054] The server 200 (mapped as node 610-2) and the terminal 400 (mapped as node 610-1) can both join the blockchain network 600 and become nodes therein. Figure 1BThe figure exemplarily shows that the terminal 400 is mapped as a node 610-1 of the blockchain network 600, and each node (such as node 610-1, node 610-2) has a consensus function and a bookkeeping function (i.e., maintaining a state database library, such as a key-value database).

[0055] The status database of each node (for example, node 610-1) records the road electronic toll collection system account and the account status of each time period corresponding to the road electronic toll collection system account, so that terminal 400 can query the road electronic toll collection system account and the account status of each time period corresponding to the road electronic toll collection system account recorded in the status database.

[0056] In some embodiments, in response to receiving the map system data and the road toll collection system data of the first time period, multiple servers 200 (each server is mapped as a node in the blockchain network) determine the account status of the road electronic toll collection system account in the second time period. For a certain account status of the predicted road electronic toll collection system account in the second time period, when the number of nodes that pass the consensus exceeds the node number threshold, it is determined that the consensus is passed, and the server 200 (mapped as node 610-2) sends the candidate account status that passes the consensus to the terminal 400 (mapped as node 610-1), and presents it on the human-computer interaction interface of the terminal 400, and stores the road electronic toll collection system account and the account status of each time period corresponding to the road electronic toll collection system account on the chain. Since the predicted account status is obtained after consensus by multiple servers, the reliability of the account status prediction of the road electronic toll collection system account can be effectively improved. Because the blockchain network is not easy to be tampered with, the road electronic toll collection system account and the account status of each time period corresponding to the road electronic toll collection system account stored on the chain will not be maliciously tampered with.

[0057] Next, the structure of the electronic device for implementing the method for processing the road electronic toll collection account of a vehicle provided in the embodiment of the present application is described. As mentioned above, the electronic device provided in the embodiment of the present application may be Figure 1A The server 200 or the terminal 400 in FIG. Figure 2 , Figure 2 4 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application, and the electronic device is taken as a terminal 400 as an example for explanation. Figure 2 The terminal 400 shown includes: at least one processor 410, a memory 450, at least one network interface 420 and a user interface 430. The various components in the terminal 400 are coupled together via a bus system 440. It is understood that the bus system 440 is used to achieve connection and communication between these components. In addition to the data bus, the bus system 440 also includes a power bus, a control bus and a status signal bus. However, for the sake of clarity, the bus system 440 is not shown in FIG. Figure 2 Various buses are labeled as bus system 440 .

[0058] Processor 410 can be an integrated circuit chip with signal processing capabilities, such as a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc., where the general-purpose processor can be a microprocessor or any conventional processor, etc.

[0059] The user interface 430 includes one or more output devices 431 that enable display of media content, including one or more speakers and / or one or more visual display screens. The user interface 430 also includes one or more input devices 432, including user interface components that facilitate user input, such as a keyboard, mouse, microphone, touch screen display, camera, other input buttons and controls.

[0060] The memory 450 may be removable, non-removable, or a combination thereof. Exemplary hardware devices include solid-state memory, hard disk drives, optical disk drives, etc. The memory 450 may optionally include one or more storage devices that are physically remote from the processor 410.

[0061] The memory 450 includes a volatile memory or a non-volatile memory, and may also include both volatile and non-volatile memories. The non-volatile memory may be a read-only memory (ROM), and the volatile memory may be a random access memory (RAM). The memory 450 described in the embodiments of the present application is intended to include any suitable type of memory.

[0062] In some embodiments, memory 450 can store data to support various operations, examples of which include programs, modules, and data structures, or a subset or superset thereof, as exemplarily described below.

[0063] Operating system 451, including system programs for processing various basic system services and performing hardware-related tasks, such as a framework layer, a core library layer, a driver layer, etc., for implementing various basic services and processing tasks based on hardware;

[0064] A network communication module 452, used to reach other electronic devices via one or more (wired or wireless) network interfaces 420, exemplary network interfaces 420 include: Bluetooth, Wireless Compatibility Authentication (WiFi), and Universal Serial Bus (USB), etc.;

[0065] a display module 453 for enabling display of information via one or more output devices 431 (e.g., display screens, speakers, etc.) associated with the user interface 430 (e.g., a user interface for operating peripheral devices and displaying content and information);

[0066] The input processing module 454 is used to detect one or more user inputs or interactions from one of the one or more input devices 432 and translate the detected inputs or interactions.

[0067] In some embodiments, the electronic road toll collection account processing device for a vehicle provided in the embodiments of the present application may be implemented in software. Figure 2 A vehicle road electronic toll collection account processing device 455 stored in a memory 450 is shown, which may be software in the form of a program and a plug-in, including the following software modules: a display module 4551 and a processing module 4552. These modules are logical, and therefore may be arbitrarily combined or further split according to the functions implemented. The functions of each module will be described below.

[0068] Next, the method for processing the electronic road toll collection account of a vehicle provided in the embodiment of the present application is described. In actual implementation, the method for processing the electronic road toll collection account of a vehicle provided in the embodiment of the present application can be performed by Figure 1A The terminal 400, the vehicle terminal of the target vehicle 300 with electronic road toll collection service or the server 200 shown are implemented separately, or the terminal 400, the vehicle terminal of the target vehicle 300 with electronic road toll collection service and the server 200 can be implemented in coordination.

[0069] The following is an example of a method for processing a vehicle road electronic toll collection account provided by an embodiment of the present application being implemented solely by the terminal 400.

[0070] See also Figure 3A , Figure 3A is a flow chart of a method for processing a road electronic toll collection account of a vehicle provided in an embodiment of the present application, which will be combined with Figure 3A The steps shown are explained.

[0071] In step 101 , a first state feature of a first time period is determined based on map system data of a map system account of a vehicle in a first time period and road toll collection system data of an electronic road toll collection system account of the vehicle in the first time period.

[0072] As an example, the vehicle's map system account is the account of the map client used by the vehicle's user (for example, the driver or passenger), and the vehicle's road electronic toll collection system account is the account used by the vehicle to pay corresponding tolls when traveling on toll roads. The map system account and the road electronic toll collection system account can belong to the same user (registered by the same person), or the map system account and the road electronic toll collection system account may belong to different users (registered by different people). When the map system account and the road electronic toll collection system account belong to different users, there is a binding relationship between the map system account and the road electronic toll collection system account, that is, multiple users use the same road electronic toll collection system account to deduct fees.

[0073] In some embodiments, see Figure 3B , Figure 3B is a flow chart of a method for processing a road electronic toll collection account of a vehicle provided in an embodiment of the present application. In step 101, based on the map system data of the vehicle's map system account in the first time period and the road toll collection system data of the vehicle's road electronic toll collection system account in the first time period, a first state feature of the first time period is determined, which can be obtained by Figure 3B The process is implemented in steps 1011-1013 shown.

[0074] In step 1011 , the map system data and the road toll system data are combined into status data for a first time period.

[0075] As an example, the first time period is the current time period or a historical time period, and the time period can be days, hours or minutes. For example, the current time is 12:00 noon on April 4, then the first time period can be the time period between 12:00 noon on April 3 and 11:00 noon on April 4 (historical time period), or can be the time period between 12:00 noon on April 3 and 12:00 noon on April 4 (including the time period at the current time). The map system data and the road toll system data of the first time period are data generated in the first time period. For example, the map system data of the first time period is the data collected by the map client installed on the mobile electronic device during the first time period in the map system by the user. The various feature data in the map system mainly include: user click data, navigation data, recharge data, consumption data, comment data, etc. in the map client. The road toll system data for the first time period is the various feature data of the user in the road toll system for the first time period collected through mobile electronic devices. The various feature data in the road toll system mainly include: user click data, recharge data, consumption data, comment data, account data, vehicle toll deduction data, status label data, vehicle passing image data, etc. in the client of the road toll system. The obtained feature data is used as the status data of the first time period.

[0076] The embodiment of the present application has rich data features, and adopts various features in the map (including: user click data, navigation data, recharge data, consumption data, comment data, etc. in the map client); various data features in the road toll system (including: user click data, recharge data, consumption data, comment data, account data, vehicle toll deduction data, status label data, etc. in the road toll system APP); image features collected by the road toll system (including: vehicle traffic information extracted by image processing, vehicle waiting time information, lane queue data, etc.), which can effectively improve the prediction accuracy of subsequent account status.

[0077] In step 1012, when the state data is non-numeric data, one-hot encoding is performed on the state data to obtain a first state feature of a first time period.

[0078] In step 1013, when the state data is numerical data, at least one of the following processes is performed on the state data to obtain the first state feature of the first time period: decorrelation processing is performed on the state data; standardization processing is performed on the state data; discretization processing is performed on the state data.

[0079] As an example, the obtained status data is divided into sparse feature data and dense feature data, wherein the sparse feature data is processed by one-hot encoding to obtain status features, and the dense feature data is processed by decorrelation, standardization, feature discretization, etc. to obtain status features. The sparse feature data is categorical feature data such as gender, and the dense feature data refers to feature data with specific numerical meanings such as user recharge amount and number of clicks.

[0080] In step 102, a second state probability of the electronic road toll collection system account in a second time period is determined based on the first state feature and the first state probability of the electronic road toll collection system account corresponding to each candidate account state in the first time period.

[0081] As an example, the second time period is later than the first time period. For example, the current time is 12:00 noon on April 4. If the first time period is the time period between 12:00 noon on April 3 and 12:00 noon on April 4, then the second time period is the time period later than 12:00 noon on April 4. At this time, the second time period is a time period that has not yet arrived. If the first time period is the time period between 12:00 noon on April 2 and 12:00 noon on April 3, the second time period may also be only the time period later than 12:00 noon on April 3. At this time, the second time period may also include the time that has arrived. Therefore, the embodiment of the present application can be used to predict the account status of the second time period in the following three situations: Situation 1: predicting the account status in the second time period in the future; Situation 2: being unable to obtain the account status of the road electronic toll collection system account in the current second time period from the road electronic toll collection system in real time; Situation 3: being unable to obtain query data for directly determining the account status of the road electronic toll collection system account in the second time period in the future from the road electronic toll collection system in real time, for example, being unable to query the current balance for directly determining the status in the second time period in the future. In the above three situations, it is necessary to predict the account status of the road electronic toll collection system account in the second time period so that users can take corresponding measures in advance to prevent the account from being blacklisted and affecting normal travel.

[0082] In some embodiments, see Figure 3C , Figure 3C is a flow chart of the method for processing a road electronic toll collection account of a vehicle provided in an embodiment of the present application. In step 102, according to the first state feature and the first state probability of the road electronic toll collection system account corresponding to each candidate account state in the first time period, the second state probability of the road electronic toll collection system account in the second time period is determined, which can be obtained by Figure 3C Steps 1021-1022 in are implemented.

[0083] In step 1021, a first state probability for each candidate account state in a plurality of consecutive third time periods is obtained.

[0084] As an example, each third time period is earlier than the first time period. For example, the current time is 12:00 noon on April 4, the first time period can be the time period between 12:00 noon on April 3 and 12:00 noon on April 4, the third time period is the time period earlier than 12:00 noon on April 3, and the third time period is an arrived time period.

[0085] In some embodiments, obtaining the first state probability for each candidate account state in multiple consecutive third time periods in step 1021 can be achieved by the following technical solution: performing the following processing for each third time period: obtaining the number of candidate accounts corresponding to each candidate account state in the third time period; determining the ratio of the number of candidate accounts corresponding to each candidate account state in the third time period to the total number of candidate accounts as the first state probability for each candidate account state in the third time period; wherein the candidate accounts include road electronic toll collection system accounts and any similar accounts.

[0086] As an example, take the Bayesian third-order state transition as an example. The account state S in the K+1 time period k+1 The account status S of the Kth time period, the K-1th time period, ..., the Kmth time period k , S k-1 ,…,S k-m and decision u k (S k )、u k-1 (S k-1 ),…,u k-m (S k-m ) influence, and can be expressed as the following expression: k+1 (S k+1 |S k ,S k-1 ,…,S k-m )=A 1×(m+1) U(S) (m+1)×1 , A 1×(m+1) =(α1,α2,…,α m+1 ) represents a coefficient matrix of 1 row and m+1 columns, U(S) (m+1)×1 =(u k (S k ),u k-1 (S k-1 ),u k-m (S k-m )) T represents a decision matrix with m+1 rows and 1 columns, where K is an integer greater than m, and m is an integer greater than or equal to 1. If there are two candidate account states, namely, black account state and normal state, the candidate account in black account state is the black account sample, and the candidate account state in normal state is the normal sample. The label Y of the account state in the first time period is used. k Calculate the ratio of blacklist samples to normal samples, where K is an integer greater than or equal to 2. For example, a label of 1 indicates that the candidate account is in a blacklist state, and a label of 0 indicates that the candidate account is in a normal state. Through the label of each candidate account, the ratio of the number of candidate accounts in each candidate account state can be determined. The ratio of blacklist samples is The proportion of normal samples is The above proportion is taken as the first-order state transition probability (p 0,k , 1-p 0,k ) is an unbiased estimate; using an account status label Y in a third time period k-1 Calculate the ratio of black household samples to normal samples. The ratio of black household samples is The proportion of normal samples is The above proportion is taken as the second-order state transition probability (p 0,k-1 , 1-p 0,k-1 ) is an unbiased estimate; using the account status label Y in another third time period k-2 Calculate the ratio of black household samples to normal samples. The ratio of black household samples is The proportion of normal samples is The above proportion is taken as the second-order state transition probability (p 0,k-2 , 1-p 0,k-2 ), thereby constructing an unbiased estimate matrix of the third-order state transition probability in the prediction stage

[0087] In step 1022, a second state probability of the electronic road toll collection system account in a second time period is predicted based on the plurality of first state probabilities and the first state characteristics.

[0088] In some embodiments, in step 1022, predicting the second state probability of the road electronic toll collection system account in the second time period based on multiple first state probabilities and first state characteristics can be achieved by the following technical solution: combining any candidate account state in the first time period with any candidate account state in each third time period to obtain multiple combination results; performing the following processing on each combination result: mapping the first state characteristic according to the combination result to obtain a mapping processing result; correcting the mapping processing result according to the combination result and multiple first state probabilities to obtain the third state probability corresponding to the combination result; summing the third state probability corresponding to each combination result to obtain the second state probability of the road electronic toll collection system account in the second time period.

[0089] As an example, any candidate account status in the first time period is combined with any candidate account status in each third time period to obtain multiple combination results. For example, the label value of the candidate account status in the first time period is i m-1 , the label values ​​of the candidate account states in the third time period are i0,i1,...,i m-2, assuming that there is a first time period and a third time period, there are 4 combination results, including the following 4 combination results: the candidate account status of the first time period is a black account (label value is 1) + the candidate account status of the third time period is a black account (label value is 1), the candidate account status of the first time period is a black account (label value is 1) + the candidate account status of the third time period is normal (label value is 0), the candidate account status of the first time period is normal (label value is 0) + the candidate account status of the third time period is a black account (label value is 1), the candidate account status of the first time period is normal (label value is 0) + the candidate account status of the third time period is normal (label value is 0), and the following processing is performed on each combination result: mapping processing is performed on the first state feature according to the combination result to obtain a mapping processing result; according to the combination result and multiple first state probabilities, the mapping processing result is corrected to obtain the third state probability of the corresponding combination result; the third state probability corresponding to each combination result (for example, the above 4 combination results) is summed to obtain the second state probability of the road electronic toll collection system account in the second time period.

[0090] In some embodiments, the above-mentioned mapping processing includes linear processing and logistic regression processing. The above-mentioned mapping processing of the first state feature according to the combination result to obtain the mapping processing result can be achieved through the following technical solutions: determining the first intercept according to the candidate account state corresponding to the first time period and each third time period represented by the combination result; performing linear processing on the first state feature according to the first intercept and the first weight corresponding to the first state feature to obtain the linear processing result of the first state feature; performing logistic regression processing on the linear processing result to obtain the mapping processing result.

[0091] As an example, the first state feature is mapped according to the combination result, and the process of obtaining the mapping result can refer to formula (1):

[0092]

[0093] Among them, A is the mapping result, W X is the first weight, X k is the first state feature of the first time period, is the first intercept, I(Y k-j =i j ) value and i j Same (0 or 1).

[0094] In some embodiments, the above-mentioned determination of the first intercept based on the candidate account status corresponding to the first time period and corresponding to each third time period represented by the combination result can be achieved through the following technical scheme: determining the label value corresponding to the candidate account status of the first time period, multiplying the label value corresponding to the candidate account status of the first time period by the second weight corresponding to the first time period, and obtaining the second intercept corresponding to the first time period; performing the following processing for each third time period: determining the label value corresponding to the candidate account status of the third time period, multiplying the label value corresponding to the candidate account status of the third time period by the second weight corresponding to the third time period, and obtaining the second intercept corresponding to the third time period; summing the second intercept corresponding to the first time period and the second intercept corresponding to each third time period to obtain the first intercept.

[0095] As an example, the process of determining the first intercept according to the candidate account status corresponding to the first time period and each third time period represented by the combination result can refer to formula (2):

[0096]

[0097] Where D is the first intercept, is the second intercept of the first time period or any third time period, It is the second weight of the first time period or any third time period.

[0098] In some embodiments, the above-mentioned correction processing of the mapping processing result according to the combination result and multiple first-state probabilities to obtain the third-state probability corresponding to the combination result can be achieved through the following technical scheme: determining the first correction parameter according to the combination result and multiple first-state probabilities; multiplying the mapping processing result with the first correction parameter to obtain the third-state probability corresponding to the combination result.

[0099] As an example, the process of correcting the mapping result according to the combination result and the multiple first state probabilities to obtain the third state probability corresponding to the combination result can refer to formula (3):

[0100]

[0101] Where C is the third state probability, is the result of the mapping process, is the first correction parameter.

[0102] In some embodiments, the above-mentioned determination of the first correction parameter based on the combination result and multiple first state probabilities can be achieved through the following technical scheme: for the first time period, query the first target state probability from multiple first state probabilities as the second correction parameter corresponding to the first time period; wherein the first target state probability is the first state probability of the candidate account state corresponding to the first time period in the combination result; for each third time period, query the second target state probability from multiple first state probabilities as the second correction parameter corresponding to the third time period; wherein the second target state probability is the first state probability of the candidate account state corresponding to the third time period in the combination result; and multiply multiple second correction parameters to obtain the first correction parameter.

[0103] As an example, the process of determining the first correction parameter according to the combination result and the plurality of first state probabilities can refer to formula (4):

[0104]

[0105] Among them, B is the first correction parameter, is the second correction parameter of the first time period or any third time period, for For example, if the label value of the first time period / third time period is 0 (corresponding to the normal candidate account status), the corresponding first target state probability / second target state probability is 1-p 0,k-j , if the label value of the first time period / third time period is 1 (corresponding to the candidate account status of black account), then the corresponding probability of the first target state / the probability of the second target state is p 0,k-j .

[0106] In some embodiments, before predicting the second state probability of the road electronic toll collection system account in the second time period based on multiple first state probabilities and first state characteristics, determine the second state characteristics of each candidate account in the fourth time period based on the map system data and road toll collection system data of each candidate account in any fourth time period; forward propagate the second state characteristics, the third state probability of the candidate account corresponding to each candidate account state in the fourth time period, and the third state probability of the candidate account corresponding to each candidate account state in each fifth time period in the state prediction model to obtain the fourth state probability of the candidate account in the sixth time period; wherein the candidate account includes the road electronic toll collection system account and any similar account; wherein the fourth time period is later than the fifth time period, the sixth time period is later than the fourth time period, and the sixth time period is not earlier than the first time period; perform gradient descent processing on the fourth state probability to obtain the first weight and the change value of each second weight in the state prediction model; update the first weight and each second weight according to the change value of the first weight and each second weight.

[0107] As an example, the first weight and the second weight are both trainable parameters. Therefore, before predicting the second state probability of the road electronic toll collection system account in the second time period based on multiple first state probabilities and first state characteristics, it is necessary to train the first weight and the second weight, which is equivalent to processing the multiple first state probabilities and first state characteristics through the account state prediction model to obtain the second state probability of the road electronic toll collection system account in the second time period, wherein the first weight and the second weight are trainable parameters of the account state prediction model, and the method of training the account state prediction model includes forward propagation and backward propagation. The process of forward propagation is similar to the aforementioned embodiment, except that the first time period is replaced by the fourth time period, the second time period is replaced by the sixth time period, and the third time period is replaced by the fourth time period. There are five time periods. The relationship between the fourth time period, the fifth time period and the sixth time period is similar to the relationship between the first time period, the second time period and the third time period. The only difference is that the sixth time period is not earlier than the first time period, that is, the account status of the candidate account in the sixth time period is known (that is, it belongs to labeled data), so reliable training can be performed. The back propagation process is to perform gradient descent processing on the fourth state probability to obtain the change value of the first weight and each second weight in the state prediction model, and update the first weight and each second weight according to the change value of the first weight and each second weight, that is, determine the error between the fourth state probability and the label value of the account status of the candidate account in the sixth time period, and perform gradient descent processing on the error to reversely update the first weight and the second weight.

[0108] In step 103, the account status of the electronic road toll collection system account in the second time period is determined according to the second status probability.

[0109] As an example, the type of account status can be distinguished by balance, for example, an account status with sufficient balance and an account status with insufficient balance; the type of account status can be distinguished by credit, for example, an account status in a normal state and an account status to be blacklisted, the account status to be blacklisted means that the road electronic toll collection system account will be blacklisted by the road electronic toll collection system, and the reason for blacklisting may be that the accumulated arrears exceed the prepaid credit limit. According to the label value pre-set during training, the second state probability is mapped to the account state of the road electronic toll collection system account in the second time period, for example, during training, the label value of the black account state is set to 1, the label value of the normal account state is set to 0, and the threshold is set to 0.5, that is, when the second state probability is greater than 0.5, the account state of the road electronic toll collection system account in the second time period is determined to be a black account state, and when the second state probability is not greater than 0.5, the account state of the road electronic toll collection system account in the second time period is determined to be a normal account state.

[0110] See also Figure 3D , Figure 3D is a flow chart of a method for processing a road electronic toll collection account of a vehicle provided in an embodiment of the present application, which will be combined with Figure 3D The steps shown are explained.

[0111] In step 201, an electronic map based on a vehicle's map system account login is displayed.

[0112] In step 202, in response to the navigation operation, a navigation route from a set starting point to an end point is displayed on an electronic map.

[0113] As an example, when a user navigates a vehicle through a map application on a terminal (such as a map applet or a map client), the terminal presents an electronic map for the vehicle. When the user enters a departure place and a destination in the navigation map, the electronic map in the terminal will perform route navigation based on the departure place and destination entered by the user, obtain at least one navigation route, and present at least one navigation route in the navigation map for the user to select.

[0114] As an example, a user can establish an association between a map system account and a road electronic toll collection system account based on an electronic map. In actual applications, an electronic map is set up on the terminal. The user can register a map system account in the electronic map through a social account, mobile phone number, email address, etc., and fill in the vehicle license plate number, vehicle type (non-pickup, pickup), power type (pure electric, hybrid, oil vehicle), vehicle model information and other vehicle information in the map system account to complete the registration of the map system account and generate a registered map system account identifier. Register a road electronic toll collection system account in the road toll collection system and associate the map system account. The user can register a road electronic toll collection system account in the road toll collection system using the vehicle license plate number, thereby generating a road electronic toll collection system account with the license plate number as the account identifier, and associate the road electronic toll collection system account with the license plate number in the electronic map, thereby establishing an association relationship between the map system account and the road electronic toll collection system account, and based on the established association relationship, realize information exchange between the map system account and the road electronic toll collection system account.

[0115] In step 203, the account status of the electronic road toll collection system account of the vehicle is obtained, the account status representing the status that the electronic road toll collection system account will have when the vehicle travels according to the navigation route.

[0116] In some embodiments, obtaining the account status of the road electronic toll collection system account in step 203 can be achieved through the following technical solution: querying the road electronic toll collection system corresponding to the road electronic toll collection system account for query data used to directly determine the account status of the road electronic toll collection system account, and determining the account status of the road electronic toll collection system account based on the query data.

[0117] As an example, the query data used to directly determine the account status of the road electronic toll collection system account can be the balance. The status of the road electronic toll collection system account when the vehicle travels according to the navigation route is determined by the queried balance. For example, the balance is 10 yuan, but the road electronic toll collection system account will be charged 15 yuan when the vehicle travels according to the navigation route, so the account status will become negative 5 yuan. Then the status of the road electronic toll collection system account when the vehicle travels according to the navigation route will be a black account status.

[0118] In some embodiments, query data for directly determining the account status of the road electronic toll collection system account is queried from the road electronic toll collection system corresponding to the road electronic toll collection system account; when the query data is queried, the account status of the road electronic toll collection system account is determined according to the query data; when the query data is not queried, it is determined that the processing of determining the first status characteristics of the first time period will be executed, that is, it is determined that the following technical solution will be executed: based on the map system data of the vehicle's map system account in the first time period, and the road toll system data of the vehicle's road electronic toll collection system account in the first time period, the first status characteristics of the first time period are determined; based on the first status characteristics, and the first status characteristics of the road electronic toll collection system account corresponding to each candidate account status in the first time period The state probability is used to determine the second state probability of the road electronic toll collection system account in the second time period; wherein, the second time period is later than the first time period. The implementation method of the above technical solution can refer to steps 101-103. The account state of the road electronic toll collection system account in the second time period is the state that the road electronic toll collection system account will have when the vehicle travels according to the navigation route. If the query data for directly determining the account state can be obtained directly by query, the account state can be determined directly according to the query data, effectively saving the calculation complexity and the processing resource occupancy rate. If the account state is predicted by connecting the data of the two systems, the security of the privacy information can be ensured. The account state can be predicted in advance under the premise of ensuring the security of the information, thereby ensuring the normal driving of the vehicle.

[0119] As an example, in actual application, the query data of the account status of the road electronic toll collection system account may be the balance. The queried balance is used to determine the status of the road electronic toll collection system account when the vehicle travels along the navigation route. For example, the balance is 10 yuan, but the road electronic toll collection system account will be charged 15 yuan when the vehicle travels along the navigation route, so the account status will become negative 5 yuan. When the vehicle travels along the navigation route, the road electronic toll collection system account will be in a black account status. However, query data such as the balance is information with privacy attributes, and the balance of the road electronic toll collection system account may not be queried through the client of the map system. When the balance, which is used to directly determine the account status of the road electronic toll collection system account, cannot be queried, it is determined that the processing of determining the first status feature of the first time period will be executed, thereby predicting the account status of the second time period through the account status prediction model.

[0120] In some embodiments, obtaining the account status of the road electronic toll collection system account in step 203 can be achieved through the following technical solutions: determining a first state feature of the first time period based on the map system data of the vehicle's map system account in the first time period and the road toll collection system data of the vehicle's road electronic toll collection system account in the first time period; determining a second state probability of the road electronic toll collection system account in the second time period based on the first state feature and the first state probability of the road electronic toll collection system account corresponding to each candidate account state in the first time period; wherein the second time period is later than the first time period, the implementation method of the above technical solution can refer to steps 101-103, and the account status of the road electronic toll collection system account in the second time period is the status that the road electronic toll collection system account will have when the vehicle travels according to the navigation route.

[0121] As an example, the first time period is a time period that includes the current moment but does not include the future moment, or a time period that does not include either the current moment or the future moment. The current moment is the current moment of executing step 203. The second time period is a time period after the first time period, and may include the future moment or exclude the future moment. According to the second state probability, the account state of the road electronic toll collection system account in the second time period is determined.

[0122] In step 204, the account status is displayed on the electronic map.

[0123] As an example, the map system account can be a dedicated account registered in the electronic map system, or it can be a universal login account between clients, such as an instant messaging client account. By authorizing in the instant messaging client, the registered user information in the instant messaging client, such as user name, avatar, etc., can be obtained, so as to log in to the electronic map system through the instant messaging client account.

[0124] In some embodiments, the account status includes at least one of a balance status and a credit status. The display of the account status in step 204 can be achieved by the following technical solution: displaying at least one of the balance status and the credit status of the road electronic toll collection system account, the balance status is used to indicate whether the balance of the road electronic toll collection system account is insufficient when driving along the navigation route, and the credit status is used to indicate whether the credit of the road electronic toll collection system account is abnormal when driving along the navigation route.

[0125] As an example, the type of account status can be distinguished by the balance, for example, an account status with sufficient balance and an account status with insufficient balance; the type of account status can be distinguished by credit, for example, an account status in a normal state and an account status that is about to be blacklisted, and the account status that is about to be blacklisted means that the road electronic toll collection system account will be blacklisted by the road electronic toll collection system, and the reason for blacklisting may be that the accumulated arrears exceed the prepaid credit limit.

[0126] In some embodiments, after obtaining the account status of the vehicle's electronic road toll collection system account, when the entrance and exit of the navigation route correspond to at least two toll lanes, before reaching the entrance of the navigation route or when reaching the exit, navigation information of the toll lane that matches the account status is displayed based on the account status of the vehicle's electronic road toll collection system account; wherein the account status includes whether the balance is exhausted or whether the credit is abnormal, and the toll lane navigation information is used to guide the vehicle to a toll lane that matches the account status.

[0127] In some embodiments, based on the account status of the vehicle's road electronic toll collection system account, navigation information of a toll lane that matches the account status is displayed, which can be achieved through the following technical solutions: when the vehicle's account status indicates that the balance of the road electronic toll collection system account is sufficient when traveling along the navigation route, or the credit of the road electronic toll collection system account is normal when traveling along the navigation route, first navigation information is displayed, and the first navigation information is used to guide the vehicle to the road electronic toll collection lane; when the vehicle's account status indicates that the balance of the road electronic toll collection system account is insufficient when traveling along the navigation route, or the credit of the road electronic toll collection system account is abnormal when traveling along the navigation route, second navigation information is displayed, and the second navigation information is used to guide the vehicle to the manual toll collection lane.

[0128] As an example, see Fig. 9 , Fig. 9 is a schematic diagram of a navigation interface provided in an embodiment of the present application, in which a prompt message 901 of a manual toll lane is presented through a floating layer. The prompt message 901 is the second navigation message, which is used to guide the vehicle to drive to the manual toll lane. Fig.10 , Fig.10A navigation interface schematic diagram is provided for an embodiment of the present application. In the navigation map, a channel navigation prompt 1001 is presented for guiding the target vehicle to the toll lane at Exit 1 at Expressway Toll Station A. The channel navigation prompt 1001 is the first navigation information, and the first navigation information is used to guide the vehicle to the road electronic toll lane.

[0129] In some embodiments, the account status is displayed when at least one of the following conditions is met: a trigger operation to trigger the display of the account status is received; the distance between the real-time coordinates of the vehicle and the fixed coordinates of the road electronic toll collection channel is not greater than a distance threshold.

[0130] As an example, the display of the account status can be directly displayed by default or displayed after the set conditions are met. For example, a trigger operation for triggering the display of the account status is received, and the account status is displayed in response to the trigger operation. For example, the distance between the real-time coordinates of the vehicle and the fixed coordinates of the road electronic toll collection channel is not greater than the distance threshold, indicating that the vehicle is close to the road electronic toll collection channel and the user needs to be reminded of the account status of the vehicle's road electronic toll collection system account, thereby preventing the vehicle from entering an inappropriate toll collection channel. The account status does not need to be displayed when the distance is far, thereby avoiding affecting the effective display of navigation data and improving driving safety.

[0131] In some embodiments, after the account status is displayed in the electronic map, in response to receiving a close operation on the account status, the account status is blocked in the electronic map; in response to receiving a view operation on the account status, detailed information of the corresponding account status is displayed in the electronic map.

[0132] In some embodiments, when the account status includes a balance status, and the balance status indicates that the balance of the electronic road toll collection system account is insufficient to pay for the driving navigation route, a recharge entrance is displayed; in response to a trigger operation on the recharge entrance, a recharge operation is performed based on a payment channel associated with the map system account or the electronic road toll collection system account; based on the result of the recharge operation, an updated account status of the electronic road toll collection system account is obtained, and the updated account status is displayed.

[0133] As an example, see Fig.11 , Fig.11 A schematic diagram of a navigation interface provided in an embodiment of the present application, in addition to displaying the account status, also displays a recharge entry 1101. When the user triggers the recharge entry 1101, in response to the trigger operation, a recharge operation is performed based on a payment channel associated with a map system account or a road electronic toll collection system account. Based on the result of the recharge operation, an updated account status of the road electronic toll collection system account is obtained, and the updated account status is displayed. See Fig.12 , Fig.12A schematic diagram of the navigation interface provided in an embodiment of the present application, when the account status of the vehicle is in an abnormal state, a prompt message 1201 such as "the account status has been blacklisted and navigated to the manual toll collection channel" is displayed; when the user recharges the road electronic toll collection system account, so that the account status of the road electronic toll collection system account changes from an abnormal state to a normal state, a status change prompt message 1202 such as "the account status has changed from a normal state to a normal state" is displayed, and navigation information "navigated to the road electronic toll collection channel" is displayed.

[0134] Below, an exemplary application of the embodiment of the present application in an actual application scenario will be described. Taking the passage of vehicles on a highway as an example, the toll collection methods of the highway include ETC charging (road electronic toll collection) and manual toll collection. Multiple toll collection channels such as ETC channels and manual toll collection channels are set at the entrances and exits of the highway. In the related art, when the account in the vehicle's ETC business account is in arrears (recharge is delayed or forgotten), the ETC business status of the vehicle is in a blacklisted state (that is, the abnormal state mentioned above), thereby affecting the user's normal travel. In order to solve the above technical problems, the vehicle's road electronic toll account processing method provided in the embodiment of the present application predicts the account status of the road electronic toll system account in advance to remind the user to recharge the road electronic toll system account in time, so as to avoid the user being blacklisted due to arrears in the road electronic toll system account, thereby causing a decrease in the user's travel experience.

[0135] See also Figure 5 , Figure 5 It is an interface diagram of the method for processing the road electronic toll collection account of a vehicle provided in an embodiment of the present application. When the account status of the road electronic toll collection system account of the target vehicle is abnormal, an account recharge prompt message 501 such as "Based on your recent travel and consumption records, your car is about to be blacklisted, please recharge in time" is output in the navigation map.

[0136] See also Figure 6 , Figure 6 It is a logical schematic diagram of the method for processing a road electronic toll collection account for a vehicle provided in an embodiment of the present application. The overall process can be mainly divided into the following six stages: account registration and association stage, data collection stage, data storage and preprocessing stage, model training stage, state prediction stage, and user prompting stage.

[0137] During the account registration and association stage, in response to the user's registration operation, the license plate number, mobile phone number, and social account are used to register the user account of the corresponding system in the map system and the road toll collection system respectively, and the user accounts of the two systems are associated through user identifiers such as license plate number, mobile phone number, and social account, thereby realizing information exchange between the map system account and the road electronic toll collection system account.

[0138] In the data collection stage, it mainly involves map system data collection and road toll system data collection. For map system data collection, the map client installed on a mobile electronic device (for example, a mobile phone, a car terminal device, etc.) is used to collect various feature data of the user in the map system. The various feature data in the map system mainly include: click data, navigation data, recharge data, consumption data, comment data, etc. of the user in the map client; for road toll system data collection, the camera device connected to the mobile electronic device and the road toll system is used to collect various feature data of the user in the road toll system. The various feature data in the road toll system mainly include: click data, recharge data, consumption data, comment data, account data, vehicle toll deduction data, status label data, etc. of the user in the client of the road toll system. The camera device connected to the road toll system is used to collect image data (external environment data) of vehicle traffic, and the above-collected data is connected through the user identity (for example, license plate number, mobile phone number, social account, etc.) to generate a data set for each vehicle and upload it to the server.

[0139] During the data storage and preprocessing stage, the server preprocesses the uploaded data set, for example, using image processing methods to process image data, extracting vehicle traffic information, vehicle waiting time information, lane queue data and other information, and storing the preprocessed data in the database system. Database technology is used to preprocess various data of the client of the map system and the road toll system (for example, user behavior data) into a database format and store them in the database.

[0140] In the model training phase, the user behavior data stored in the server, the label data of the account status of the road electronic toll collection system account, the image processing data, etc. are input. On the server side, the database technology (SQL technology, Hive technology, SPARK technology, etc.) is used to process the data into sample data of multiple time periods. The sample data includes training samples, test samples and prediction samples. The account status prediction model W is trained based on the training samples, and then the account status prediction model W is tested based on the test samples. The account status prediction model W is implemented based on the Bayesian multi-order state transition binary classification algorithm (Formula (5)). The trained and tested account status prediction model W is output. The server stores the account status prediction model W and the prediction sample of the Kth time period. The prediction sample of the Kth time period is the data of the current time period.

[0141] In the model prediction stage, the prediction samples of the Kth time period (including the account status data of the Kth time period) and the account status data of the historical time period are substituted into the account status prediction model W, and the account status probability of each vehicle in the K+1th time period (the second state probability of the road electronic toll collection system account in the second time period) is predicted in the server, and divided according to the set threshold (for example, 0.5). For example, the account status of the road electronic toll collection system account with an account status probability greater than 0.5 is predicted to be "black account" and marked as 1, and the account status of the road electronic toll collection system account with an account status probability not greater than 0.5 is predicted to be "normal" and marked as 0, and the account status classification results are stored in the server.

[0142] In the map prompting user stage, the account status classification results are obtained. For users marked as 1, information is sent through the map client to prompt the user's vehicle's road electronic toll collection system account status. The forms of sending information include: map client message push, social client message push, mobile phone SMS message push, and road toll system client message push.

[0143] In some embodiments, see Figure 4 , Figure 4 : is a schematic diagram of the algorithm architecture of the method for processing a road electronic toll collection account of a vehicle provided in an embodiment of the present application. The account state of the Kth time period is predicted by the known pre-marked account state of the candidate account in the Kth time period, the m-order state transition probability from the K-1th time period to the Kmth time period, the user characteristics of the K-1th time period, and the vehicle characteristics of the K-1th time period. The account state prediction model is trained through the above prediction process, and then the second state probability of the K+1th time period is predicted through the account state prediction model, the user characteristics of the Kth time period, the vehicle characteristics of the Kth time period, and the m-order state transition probability from the Kth time period to the K-m+1th time period. m is an integer greater than or equal to 1, and K is an integer greater than or equal to 1. The algorithm of the account state prediction model can be referred to formula (5):

[0144]

[0145] Among them, W X is the first weight, X k is the first state feature of the first time period, is the first intercept, i j is the label value of the candidate state (0 or 1), I(Y k-j =i j ) value and i j same, is the second weight of the first time period or any third time period, is the second correction parameter of the first time period or any third time period, for For example, if the label value of the first time period / third time period is 0 (corresponding to the normal candidate account status), the corresponding first target state probability / second target state probability is 1-p 0,k-j , if the label value of the first time period / third time period is 1 (corresponding to the candidate account status of black account), then the corresponding probability of the first target state / the probability of the second target state is p 0,k-j , P{Y k+1 =1|X k} is the second state probability.

[0146] In some embodiments, in order to improve the accuracy of the account status prediction model, a Bayesian multi-order state transition binary classification algorithm is applied to the account status prediction model, for example, a third-order state transfer is performed, thereby improving the model accuracy without making the model too complicated. The vehicle road electronic toll collection account processing method provided in the embodiment of the present application is mainly divided into the following six stages: sample data set processing, Bayesian third-order state transition probability calculation stage, model training stage, model testing and evaluation stage, and model prediction classification stage.

[0147] In the sample data set processing stage, training sample construction and test sample construction are first performed, and the feature data of the K-1th time period stored in the server is input, and the feature data includes the user's click data, navigation data, recharge data, consumption data, comment data, etc. on the map client; the user's click data, recharge data, consumption data, comment data, account data, user vehicle status label, vehicle toll deduction data, etc. on the client of the road toll system; vehicle traffic information, vehicle waiting time information, lane queue data and other information extracted through image processing; connected into a whole sample through user identification, and the whole The feature data (state data) in the overall sample are divided into sparse feature data and dense feature data, wherein the sparse feature data is subjected to one-hot encoding, and the dense feature data is subjected to decorrelation, standardization, feature discretization, etc. The sparse feature data is categorical feature data such as gender, and the dense feature data refers to feature data with specific numerical meanings such as user recharge amount and number of clicks. The sparse feature data and dense feature data in the processed overall sample are randomly divided into training samples and test samples in proportion, for example, the training samples and test samples are randomly divided into 8:2 ratios. In the prediction sample construction stage, the feature data of the Kth time period stored in the server is input (the feature data includes: user click data, navigation data, recharge data, consumption data, comment data, etc. in the map client; user click data, recharge data, consumption data, comment data, account data, vehicle toll deduction data, status label data, etc. in the client of the road toll system; vehicle traffic information, vehicle waiting time information, lane queue data, etc. extracted by image processing), and the prediction samples are divided into sparse features and dense features, wherein the sparse features are subjected to one-hot encoding processing, and the dense features are subjected to decorrelation processing, standardization processing, feature discretization processing, etc.

[0148] In the Bayesian third-order state transition probability calculation phase, the third-order state transition probabilities of the training phase and the prediction phase are determined respectively, and the account state label Y in the K-1th time period is used. k-1 Calculate the ratio of black household samples to normal samples. The ratio of black household samples is The proportion of normal samples is The above proportion is taken as the first-order state transition probability (p 0,k-1 , 1-p 0,k-1 ) is an unbiased estimate; using the account status label Y in the K-2 period k-2 Calculate the ratio of black household samples to normal samples. The ratio of black household samples is The proportion of normal samples is The above proportion is taken as the second-order state transition probability (p 0,k-2 , 1-p0,k-2 ) is an unbiased estimate; similarly, using the account status label Y in the K-3 period k-3 Calculate the ratio of black household samples to normal samples. The ratio of black household samples is The proportion of normal samples is The above proportion is taken as the third-order state transition probability (p 0,k-3 , 1-p 0,k-3 ), thereby constructing an unbiased estimate matrix of the third-order state transition probability in the training phase For the third-order state transition probability in the prediction stage, the account state label Y in the Kth time period is used k Calculate the ratio of black household samples to normal samples. The ratio of black household samples is The proportion of normal samples is The above proportion is taken as the first-order state transition probability (p 0,k , 1-p 0,k ) is an unbiased estimate; using the account status label Y in the K-1th time period k-1 Calculate the ratio of black household samples to normal samples. The ratio of black household samples is The proportion of normal samples is The above proportion is taken as the second-order state transition probability (p 0,k-1 , 1-p 0,k-1 ) is an unbiased estimate; using the account status label Y in the K-2 period k-2 Calculate the ratio of black household samples to normal samples. The ratio of black household samples is The proportion of normal samples is The above proportion is taken as the second-order state transition probability (p 0,k-2 , 1-p 0,k-2 ), thereby constructing an unbiased estimate matrix of the third-order state transition probability in the prediction stage

[0149] See also Figure 7 , Figure 7 The diagram is a training and testing flow chart of the method for processing a road electronic toll collection account for a vehicle provided in an embodiment of the present application. In the model training phase, the data is divided into training data and test data, and the third-order state transition probability matrix of the K-1 time period, the K-2 time period, and the K-3 time period is calculated based on the data of each time period. The training data and the third-order state transition probability matrix of the K-1 time period, the K-2 time period, and the K-3 time period are input into the account state prediction model. The weights of the account status prediction model are solved by the gradient descent method under the third-order state transition. The weights measure the contribution of the features to the probability of the second state. The gradient descent method of the three-stage state transition, that is, the gradient descent solution process, is affected by the third-order state transition probability. In the model testing and evaluation stage, the trained account status prediction model is tested and evaluated through test data. The model is tested and evaluated through test data, and the state transition probability matrix of the K-1 time period, the K-2 time period, and the K-3 time period is input. The classification probability and evaluation indicators (recall rate, precision rate, AUC, etc.) under the test sample are calculated by formula (5). If the evaluation indicators meet the evaluation effect, the account status prediction model is saved and output. If the model evaluation fails, it is trained again until the account status prediction model meets the evaluation standard, and the account status prediction model and evaluation results are stored in the server.

[0150] See also Figure 8 , Figure 8 : is a prediction flow diagram of the method for processing a road electronic toll collection account of a vehicle provided in an embodiment of the present application. In the model prediction classification stage, the data includes prediction samples, the model is an evaluated account state prediction model, and the prediction samples of the Kth time period, the third-order state transition probability matrix of the Kth time period, the K-1th time period, and the K-2th time period are converted into the prediction samples of the Kth time period, the K-1th time period, and the K-2th time period. The second state probability of the road electronic toll collection system account is predicted by the account state prediction model (Formula (5)), and the second state probability is divided into black account samples and normal samples according to the set threshold, wherein the black account sample refers to the vehicle's road electronic toll collection system account whose account state is predicted to be "black account" and is marked as 1, and the normal sample refers to the vehicle's road electronic toll collection system account whose account state is predicted to be "normal" and is marked as 0. The state classification result is stored in the server. The state classification result is the second state probability obtained by substituting the predicted sample and the historical state transition probability into Formula (5) of the account state prediction model, and then classified according to the threshold.

[0151] The embodiment of the present application first connects the data of the map system and the data of the road toll system through user identification, realizes information sharing, and then applies the map user characteristics, road toll system user characteristics, and image characteristics to the prediction of the vehicle status of the road toll system through algorithms, predicts the vehicle road toll system account status in advance, prompts the user to recharge in advance, and prompts the user to drive in advance, thereby improving the user's driving experience. Due to the dual system collection of feature data of the map system and the road toll system, the user feature data in the map is effectively used to improve the accuracy of the account status prediction model. The embodiment of the present application uses the license plate number as the user identification, connects the status label, map feature data, and road toll system feature data to construct training and prediction samples, and provides training data for the account status prediction model. The embodiment of the present application considers the influence of historical account status in the account status prediction model. In order to improve the accuracy of the prediction of the account status prediction model, the m-order account status transition probability is added on the basis of the logistic regression algorithm, and a two-classification algorithm based on the Bayesian m-order state transition is proposed, which fully considers the influence of the vehicle's historical road toll system account status changes on the predicted state, and can effectively improve the accuracy of model training and prediction.

[0152] The following describes an exemplary structure of the electronic road toll collection account processing device 455 of the vehicle provided in the embodiment of the present application implemented as a software module. In some embodiments, such as Figure 2 As shown, the software modules in the vehicle's road electronic toll collection account processing device 455 stored in the memory 450 may include: a display module 4551, used to display an electronic map based on the vehicle's map system account login; the display module 4551 is also used to display the navigation route from the set starting point to the end point in the electronic map in response to the navigation operation; the processing module 4552 is used to obtain the account status of the vehicle's road electronic toll collection system account, and the account status represents the status of the road electronic toll collection system account when the vehicle travels according to the navigation route; the display module 4551 is also used to display the account status.

[0153] In some embodiments, the processing module 4552 is also used to: determine the first state characteristics of the first time period based on the map system data of the vehicle's map system account in the first time period and the road toll system data of the vehicle's road electronic toll collection system account in the first time period; determine the second state probability of the road electronic toll collection system account in the second time period according to the first state characteristics and the first state probability of the road electronic toll collection system account corresponding to each candidate account state in the first time period; wherein the second time period is later than the first time period; and determine the account state of the road electronic toll collection system account in the second time period according to the second state probability.

[0154] In some embodiments, the processing module 4552 is also used to: before determining the first state characteristics of the first time period, query the account status of the road electronic toll collection system account from the road electronic toll collection system corresponding to the road electronic toll collection system account; when no account status is found, determine to enter the processing of determining the first state characteristics of the first time period.

[0155] In some embodiments, the account status includes at least one of a balance status and a credit status. The display module 4551 is also used to: display at least one of the balance status and the credit status of the road electronic toll collection system account. The balance status is used to indicate whether the balance of the road electronic toll collection system account is insufficient when driving along the navigation route. The credit status is used to indicate whether the credit of the road electronic toll collection system account is abnormal when driving along the navigation route.

[0156] In some embodiments, after obtaining the account status of the vehicle's road electronic toll collection system account, the display module 4551 is also used to: when the navigation route corresponds to at least two toll lanes, display navigation information of the toll lane that matches the account status according to the account status of the vehicle's road electronic toll collection system account; wherein the toll lane navigation information is used to guide the vehicle to the toll lane that matches the account status.

[0157] In some embodiments, the display module 4551 is also used to: display first navigation information when the vehicle's account status indicates that the balance of the road electronic toll collection system account is sufficient when traveling along the navigation route, or the credit of the road electronic toll collection system account is normal when traveling along the navigation route, and the first navigation information is used to guide the vehicle to the road electronic toll collection channel; display second navigation information when the vehicle's account status indicates that the balance of the road electronic toll collection system account is insufficient when traveling along the navigation route, or the credit of the road electronic toll collection system account is abnormal when traveling along the navigation route, and the second navigation information is used to guide the vehicle to the manual toll collection channel.

[0158] In some embodiments, the display module 4551 is also used to: display a recharge entrance when the account status includes a balance status, and the balance status indicates that the balance of the road electronic toll collection system account is insufficient to pay for the driving navigation route; in response to a trigger operation on the recharge entrance, perform a recharge operation based on a payment channel associated with the map system account or the road electronic toll collection system account; based on the result of the recharge operation, obtain an updated account status of the road electronic toll collection system account, and display the updated account status.

[0159] In some embodiments, the processing module 4552 is also used to: combine the map system data and the road toll system data into status data for a first time period; when the status data is non-numeric data, perform one-hot encoding on the status data to obtain a first state feature for the first time period; when the status data is numeric data, perform at least one of the following processing on the status data to obtain a first state feature for the first time period: perform decorrelation processing on the status data; perform standardization processing on the status data; and perform discretization processing on the status data.

[0160] In some embodiments, the processing module 4552 is also used to: obtain the first state probability for each candidate account state in multiple consecutive third time periods; wherein each third time period is earlier than the first time period; and predict the second state probability of the road electronic toll collection system account in the second time period based on multiple first state probabilities and first state characteristics.

[0161] In some embodiments, the probability module is also used to: perform the following processing for each third time period: obtain the number of candidate accounts corresponding to each candidate account state in the third time period; determine the ratio of the number of candidate accounts corresponding to each candidate account state in the third time period to the total number of candidate accounts as the first state probability for each candidate account state in the third time period; wherein the candidate accounts include road electronic toll collection system accounts and any similar accounts.

[0162] In some embodiments, the processing module 4552 is also used to: combine any candidate account state in the first time period with any candidate account state in each third time period to obtain multiple combination results; perform the following processing for each combination result: map the first state feature according to the combination result to obtain a mapping processing result; correct the mapping processing result according to the combination result and multiple first state probabilities to obtain the third state probability corresponding to the combination result; sum the third state probability corresponding to each combination result to obtain the second state probability of the road electronic toll collection system account in the second time period.

[0163] In some embodiments, the mapping processing includes linear processing and logistic regression processing, and the processing module 4552 is also used to: determine the first intercept based on the candidate account status corresponding to the first time period and each third time period represented by the combination result; perform linear processing on the first state feature according to the first intercept and the first weight corresponding to the first state feature to obtain the linear processing result of the first state feature; perform logistic regression processing on the linear processing result to obtain the mapping processing result.

[0164] In some embodiments, the processing module 4552 is also used to: determine the label value corresponding to the candidate account status of the first time period, multiply the label value corresponding to the candidate account status of the first time period by the second weight corresponding to the first time period, and obtain the second intercept corresponding to the first time period; perform the following processing for each third time period: determine the label value corresponding to the candidate account status of the third time period, multiply the label value corresponding to the candidate account status of the third time period by the second weight corresponding to the third time period, and obtain the second intercept corresponding to the third time period; sum the second intercept corresponding to the first time period and the second intercept corresponding to each third time period to obtain the first intercept.

[0165] In some embodiments, the processing module 4552 is further used to: determine a first correction parameter based on the combination result and multiple first state probabilities; and multiply the mapping processing result by the first correction parameter to obtain a third state probability corresponding to the combination result.

[0166] In some embodiments, processing module 4552 is also used to: query a first target state probability from multiple first state probabilities as a second correction parameter corresponding to the first time period; wherein the first target state probability is the first state probability of the candidate account state corresponding to the first time period in the combination result; query a second target state probability from multiple first state probabilities as a second correction parameter corresponding to the third time period; wherein the second target state probability is the first state probability of the candidate account state corresponding to the third time period in the combination result; and multiply multiple second correction parameters to obtain a first correction parameter.

[0167] In some embodiments, the processing module 4552 is further used to: determine the second state feature of each candidate account in the fourth time period based on the map system data and the road toll system data of each candidate account in any fourth time period before predicting the second state probability of the road electronic toll collection system account in the second time period according to multiple first state probabilities and first state features; forward propagate the second state feature, the third state probability of the candidate account corresponding to each candidate account state in the fourth time period, and the third state probability of the candidate account corresponding to each candidate account state in each fifth time period in the state prediction model to obtain the fourth state probability of the candidate account in the sixth time period; wherein the candidate account includes the road electronic toll collection system account and any similar account; wherein the fourth time period is later than the fifth time period, the sixth time period is later than the fourth time period, and the sixth time period is not earlier than the first time period; perform gradient descent processing on the fourth state probability to obtain the first weight and the change value of each second weight in the state prediction model; and update the first weight and each second weight according to the change value of the first weight and each second weight.

[0168] The embodiment of the present application provides a computer program product or a computer program, which includes computer instructions stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the road electronic toll collection account processing method of the vehicle described in the embodiment of the present application.

[0169] The present application embodiment provides a computer-readable storage medium storing executable instructions, wherein the executable instructions are stored. When the executable instructions are executed by a processor, the processor will execute the method for processing a road electronic toll collection account of a vehicle provided in the present application embodiment, for example, Figures 3A-3C A method for processing a road electronic toll collection account number of a vehicle is shown.

[0170] In some embodiments, the computer-readable storage medium may be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface storage, optical disk, or CD-ROM; or it may be various devices including one or any combination of the above memories.

[0171] In some embodiments, executable instructions may be in the form of a program, software, software module, script or code, written in any form of programming language (including compiled or interpreted languages, or declarative or procedural languages), and may be deployed in any form, including as a stand-alone program or as a module, component, subroutine or other unit suitable for use in a computing environment.

[0172] As an example, executable instructions may, but need not, correspond to a file in a file system, may be stored as part of a file that stores other programs or data, such as in one or more scripts in a HyperText Markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files storing one or more modules, subroutines, or code portions).

[0173] As an example, the executable instructions may be deployed to be executed on one electronic device, or on multiple electronic devices located at one site, or on multiple electronic devices distributed at multiple sites and interconnected by a communication network.

[0174] In summary, through the embodiments of the present application, the map system data and the road toll system data of the vehicle in the first time period are connected, so as to accurately and timely determine the account status in the second time period by combining the features extracted from the two, thereby providing an important reference for the normal driving of the vehicle in the second time period.

[0175] The above are only embodiments of the present application and are not intended to limit the protection scope of the present application. Any modifications, equivalent replacements and improvements made within the spirit and scope of the present application are included in the protection scope of the present application.

Claims

1. A method for processing a road electronic toll collection account number of a vehicle, characterized in that: The method comprises: Display electronic maps based on the vehicle's map system account login; In response to the navigation operation, displaying a navigation route from a set starting point to an end point on the electronic map; Based on the map system data of the map system account of the vehicle in the first time period and the road toll collection system data of the road electronic toll collection system account of the vehicle in the first time period, a first state feature of the first time period is determined; based on the first state feature and the first state probability of the road electronic toll collection system account corresponding to each candidate account state in the first time period, a second state probability of the road electronic toll collection system account in the second time period is determined; wherein the second time period is later than the first time period; based on the second state probability, an account state of the road electronic toll collection system account in the second time period is determined, the account state representing the state of the road electronic toll collection system account when the vehicle travels according to the navigation route; Displays the status of the account.

2. The method according to claim 1, characterized in that The account status includes at least one of a balance status and a credit status, and the displaying of the account status includes: At least one of a balance status and a credit status of the electronic road toll collection system account is displayed, wherein the balance status is used to indicate whether the balance of the electronic road toll collection system account is insufficient when driving along the navigation route, and the credit status is used to indicate whether the credit of the electronic road toll collection system account is abnormal when driving along the navigation route.

3. The method according to claim 1, characterized in that After determining the account status of the electronic road toll collection system account in the second time period, the method further includes: When the navigation route corresponds to at least two toll lanes, according to the account status of the electronic road toll collection system account of the vehicle, displaying navigation information of the toll lane matching the account status; The toll lane navigation information is used to guide the vehicle to travel to a toll lane that matches the account status.

4. The method according to claim 3, characterized in that The method of displaying navigation information of a toll lane matching the account status of the electronic road toll collection system account of the vehicle includes: When the account status of the vehicle indicates that the balance of the road electronic toll collection system account is sufficient when traveling along the navigation route, or when the credit of the road electronic toll collection system account is normal when traveling along the navigation route, displaying first navigation information, wherein the first navigation information is used to guide the vehicle to travel to the road electronic toll collection channel; When the account status of the vehicle indicates that the balance of the road electronic toll collection system account is insufficient when traveling along the navigation route, or when the credit of the road electronic toll collection system account is abnormal when traveling along the navigation route, the second navigation information is displayed, and the second navigation information is used to guide the vehicle to travel to the manual toll collection channel.

5. The method according to claim 1, characterized in that When the account status includes a balance status, and the balance status indicates that the balance of the road electronic toll collection system account is insufficient to pay for traveling the navigation route, the method further includes: Display the recharge entrance; In response to a trigger operation on the recharge entry, performing a recharge operation based on a payment channel associated with the map system account or the road electronic toll collection system account; Based on the result of the recharging operation, an updated account status of the electronic road toll collection system account is obtained, and the updated account status is displayed.

6. The method according to claim 1, characterized in that Before determining the first state feature of the first time period, the method further includes: querying query data for directly determining the account status of the electronic road toll collection system account from the electronic road toll collection system corresponding to the electronic road toll collection system account; When the query data is not found, it is determined that a process of determining a first state feature of the first time period will be entered.

7. The method according to claim 1, characterized in that The determining of the first state feature of the first time period based on the map system data of the map system account of the vehicle in the first time period and the road toll collection system data of the road electronic toll collection system account of the vehicle in the first time period includes: combining the map system data and the road toll system data into status data for the first time period; When the state data is non-numeric data, performing one-hot encoding on the state data to obtain a first state feature of the first time period; When the state data is numerical data, at least one of the following processes is performed on the state data to obtain the first state feature of the first time period: performing decorrelation processing on the state data; Performing standardization processing on the status data; Discretization processing is performed on the state data.

8. The method according to claim 1, characterized in that Determining the second state probability of the electronic road toll collection system account in the second time period according to the first state feature and the first state probability of the electronic road toll collection system account corresponding to each candidate account state in the first time period includes: Obtaining a first state probability for each candidate account state in a plurality of consecutive third time periods; Wherein, each of the third time periods is earlier than the first time period; A second state probability of the electronic road toll collection system account in the second time period is predicted based on the plurality of first state probabilities and the first state characteristics.

9. The method according to claim 8, characterized in that The obtaining of the first state probability for each candidate account state in a plurality of consecutive third time periods includes: The following process is performed for each of the third time periods: Obtaining the number of candidate accounts corresponding to each of the candidate account states in the third time period; Determine a ratio of the number of candidate accounts corresponding to each of the candidate account states in the third time period to the total number of candidate accounts as a first state probability for each of the candidate account states in the third time period; The candidate accounts include the road electronic toll collection system account and any similar account.

10. The method according to claim 8, characterized in that The predicting, based on the plurality of the first state probabilities and the first state characteristics, the second state probability of the electronic road toll collection system account in the second time period includes: Combining any one candidate account status in the first time period with any one candidate account status in each of the third time periods to obtain multiple combination results; The following processing is performed for each of the combined results: Performing mapping processing on the first state feature according to the combination result to obtain a mapping processing result; According to the combination result and the plurality of the first state probabilities, the mapping result is corrected to obtain a third state probability corresponding to the combination result; The third state probability corresponding to each of the combination results is summed to obtain the second state probability of the road electronic toll collection system account in the second time period.

11. The method according to claim 10, characterized in that The mapping process includes linear processing and logistic regression processing, and the mapping process is performed on the first state feature according to the combination result to obtain a mapping process result, including: determining a first intercept according to the candidate account status corresponding to the first time period and corresponding to each of the third time periods represented by the combination result; performing the linear processing on the first state feature according to the first intercept and a first weight corresponding to the first state feature to obtain a linear processing result of the first state feature; The logistic regression processing is performed on the linear processing result to obtain the mapping processing result.

12. The method according to claim 11, characterized in that The determining a first intercept according to the candidate account status corresponding to the first time period and each of the third time periods represented by the combination result includes: Determine a label value corresponding to the candidate account status in the first time period, and multiply the label value corresponding to the candidate account status in the first time period by a second weight corresponding to the first time period to obtain a second intercept corresponding to the first time period; For each of the third time periods, the following processing is performed: determining a label value corresponding to the candidate account status of the third time period, and multiplying the label value corresponding to the candidate account status of the third time period by a second weight corresponding to the third time period to obtain a second intercept corresponding to the third time period; The second intercept corresponding to the first time period and the second intercept corresponding to each of the third time periods are summed to obtain the first intercept.

13. The method according to claim 10, characterized in that The step of performing correction processing on the mapping processing result according to the combination result and the plurality of the first state probabilities to obtain a third state probability corresponding to the combination result includes: Determining a first correction parameter according to the combination result and a plurality of the first state probabilities; The mapping result is multiplied by the first correction parameter to obtain a third state probability corresponding to the combination result.

14. The method according to claim 13, characterized in that The determining a first correction parameter according to the combination result and the plurality of first state probabilities includes: Querying a first target state probability from the plurality of first state probabilities as a second correction parameter corresponding to the first time period; The first target state probability is the first state probability of the candidate account state corresponding to the first time period in the combination result; Querying a second target state probability from the plurality of first state probabilities as a second correction parameter corresponding to the third time period; Wherein, the second target state probability is the first state probability of the candidate account state corresponding to the third time period in the combination result; The plurality of the second correction parameters are multiplied to obtain the first correction parameter.

15. The method according to claim 11, characterized in that The method further comprises: predicting the second state probability of the electronic road toll collection system account before the second state probability of the electronic road toll collection system account in the second time period based on the plurality of the first state probabilities and the first state characteristics: Determine, based on the map system data and the road toll system data of each candidate account in any fourth time period, a second state feature of each candidate account in the fourth time period; The second state feature, the third state probability of the candidate account corresponding to each candidate account state in the fourth time period, and the third state probability of the candidate account corresponding to each candidate account state in each fifth time period are forward propagated in the state prediction model to obtain the fourth state probability of the candidate account in the sixth time period; The candidate accounts include the electronic road toll collection system account and any similar account; The fourth time period is later than the fifth time period, the sixth time period is later than the fourth time period, and the sixth time period is not earlier than the first time period; Performing gradient descent processing on the fourth state probability to obtain a change value of the first weight and each second weight in the state prediction model; The first weight and each of the second weights are updated according to the change values ​​of the first weight and each of the second weights.

16. A vehicle road electronic toll collection account processing device, characterized in that: include: A display module, used to display an electronic map based on a vehicle's map system account login; The display module is further used to display a navigation route from a set starting point to an end point in the electronic map in response to a navigation operation; a processing module, configured to determine a first state feature of the first time period based on map system data of the map system account of the vehicle in the first time period and road toll collection system data of the road electronic toll collection system account of the vehicle in the first time period; determine a second state probability of the road electronic toll collection system account in a second time period according to the first state feature and a first state probability of the road electronic toll collection system account corresponding to each candidate account state in the first time period; wherein the second time period is later than the first time period; determine an account state of the road electronic toll collection system account in the second time period according to the second state probability, the account state representing the state of the road electronic toll collection system account when the vehicle travels according to the navigation route; The display module is also used to display the account status.

17. An electronic device, characterized in that: include: A memory for storing executable instructions; The processor is used to implement the road electronic toll collection account processing method for a vehicle as described in any one of claims 1 to 15 when executing the executable instructions stored in the memory.

18. A computer-readable storage medium, characterized in that: Executable instructions are stored, which are used to implement the road electronic toll collection account processing method of the vehicle as described in any one of claims 1 to 15 when executed by the processor.

19. A computer program product comprising computer instructions, characterized in that When the computer instructions are executed by the processor, the method for processing the road electronic toll collection account of a vehicle according to any one of claims 1 to 15 is implemented.

Images