Data Processing Method and Related Device

Abstract

Embodiments of the present application disclose a data processing method and related devices, which can be applied to cloud servers and are at least related to machine learning in artificial intelligence. The state probability of the target account in the (i + 1)-th cycle is determined according to the user feature data of the vehicle in the i-th cycle, that is, whether the user behavior of the target account passing through the ETC system in the i-th cycle is qualified will affect the magnitude of this state probability. Since this state probability reflects the possibility that the target account will be added to the ETC blacklist in the (i + 1)-th cycle, for discount levels with different discount rates, the discount distribution weight of the target account in the (i + 1)-th cycle is obtained based on this state probability, and the comprehensive discount rate of the target account in the (i + 1)-th cycle is determined according to the discount distribution weight and the discount level, so as to determine the discount rate corresponding to the ETC for the user in the next cycle, and it can also be displayed through an electronic map application in a terminal device such as an on-vehicle computer. Thus, the ETC system discount rate system is more reasonable, reducing traffic congestion.

Description

Technical Field

[0001] This application relates to the technical field of data processing, and in particular, to a data processing method and related devices. Background Art

[0002] An Electronic Toll Collection (ETC) system conducts dedicated short-range communication between an on-vehicle electronic tag installed on a vehicle windshield and a microwave antenna on an ETC lane at a toll station, and uses computer networking technology to perform background settlement processing with a bank, so that a vehicle can pay highway or bridge tolls without stopping when passing through a highway or bridge toll station. Compared with a manual toll collection lane, the ETC lane is more convenient and fast.

[0003] If a user using the ETC system operates improperly, such as the balance in the bank card is insufficient resulting in a failed deduction by the ETC system, the user may be added to the ETC blacklist, and the user does not care whether they may be added to the ETC blacklist, which causes congestion in the ETC lane and reduces the travel experience of other users. Summary of the Invention

[0004] To solve the above technical problems, this application provides a data processing method and related devices, which are used to encourage users to travel civilizedly, reduce the number of congestions in the ETC lane, and improve the travel experience of users.

[0005] The embodiments of this application disclose the following technical solutions:

[0006] On the one hand, this application provides a data processing method, and the method includes:

[0007] Obtain user characteristic data of a vehicle in the i-th cycle, where the user characteristic data is used to identify the user behavior generated by the target account of the vehicle passing through the Electronic Toll Collection (ETC) system;

[0008] Determine the state probability of the target account in the (i + 1)-th cycle according to the user characteristic data, where the state probability is used to identify the probability that the target account is added to the ETC blacklist in the (i + 1)-th cycle, and the ETC blacklist is used to identify the accounts that are not allowed to use the ETC system;

[0009] Obtain the discount distribution weight of the target account in the (i + 1)-th cycle based on the state probability, where the discount distribution weight is used to identify the degree of association between the target account and different discount levels under the state probability;

[0010] Determine the comprehensive discount rate of the target account in the (i + 1)-th cycle according to the discount distribution weight and the discount level, and determine the comprehensive discount rate as the discount rate corresponding to the ETC system for the target account in the (i + 1)-th cycle.

[0011] On the other hand, the present application provides a data processing method, and the method includes:

[0012] In the (i + 1)-th cycle, start an electronic map application based on the map account;

[0013] If it is determined that the map account has an associated target account in the electronic toll collection (ETC) system, display the discount information corresponding to the comprehensive discount rate of the target account in the (i + 1)-th cycle corresponding to the ETC system. The comprehensive discount rate is determined according to the discount level of the ETC system and the state probability of the target account in the (i + 1)-th cycle. The state probability is used to identify the probability that the target account is added to the ETC blacklist in the (i + 1)-th cycle, and the state probability is determined based on the user behavior generated by the target account passing through the ETC system in the i-th cycle.

[0014] On the other hand, the present application provides a data processing device, and the device includes: an acquisition unit, a state probability determination unit, a discount distribution weight acquisition unit, and a comprehensive discount rate determination unit;

[0015] The acquisition unit is configured to acquire user feature data of a vehicle in the i-th cycle, and the user feature data is used to identify the user behavior generated by the target account of the vehicle passing through the electronic toll collection (ETC) system;

[0016] The state probability determination unit is configured to determine the state probability of the target account in the (i + 1)-th cycle according to the user feature data. The state probability is used to identify the probability that the target account is added to the ETC blacklist in the (i + 1)-th cycle, and the ETC blacklist is used to identify the accounts that are not allowed to use the ETC system;

[0017] The discount distribution weight acquisition unit is configured to obtain the discount distribution weight of the target account in the (i + 1)-th cycle based on the state probability. The discount distribution weight is used to identify the degree of association between the target account and different discount levels under the state probability;

[0018] The comprehensive discount rate determination unit is configured to determine the comprehensive discount rate of the target account in the (i + 1)-th cycle according to the discount distribution weight and the discount level, and determine the comprehensive discount rate as the discount rate corresponding to the ETC system for the target account in the (i + 1)-th cycle.

[0019] On the other hand, the present application provides a data processing device, which includes: an opening unit and a display unit;

[0020] The opening unit is configured to open an electronic map application based on a map account in the (i + 1)-th cycle;

[0021] The display unit is configured to, if it is determined that the map account has an associated target account in the electronic toll collection (ETC) system, display discount information corresponding to the comprehensive discount rate of the target account for the ETC system in the (i + 1)-th cycle, where the comprehensive discount rate is determined according to the discount level of the ETC system and the state probability of the target account in the (i + 1)-th cycle, and the state probability is used to identify the probability that the target account is added to the ETC blacklist in the (i + 1)-th cycle, and the state probability is determined based on the user behavior of the target account passing through the ETC system in the i-th cycle.

[0022] On the other hand, the present application provides a computer device, which includes a processor and a memory:

[0023] The memory is configured to store program code and transmit the program code to the processor;

[0024] The processor is configured to execute the method described in the above aspect according to the instructions in the program code.

[0025] On the other hand, an embodiment of the present application provides a computer-readable storage medium, which is configured to store a computer program, and the computer program is configured to execute the method described in the above aspect.

[0026] On the other hand, an embodiment of the present application provides a computer program product or a computer program, which includes computer instructions, and the computer instructions are 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 method described in the above aspect.

[0027] As can be seen from the above technical solution, the user behavior of the target account of the vehicle generated by the ETC system is determined according to the user characteristic data of the vehicle in the i-th cycle, and the state probability of the target account in the (i + 1)-th cycle is determined based on the user characteristic data. Thus, based on the continuity of the user's usage habits, whether the user behavior of the target account through the ETC system in the i-th cycle is qualified will directly affect the magnitude of this state probability. Since this state probability reflects the possibility that the target account will be added to the ETC blacklist in the (i + 1)-th cycle, for the discount levels with different discount rates, the discount distribution weights of the target account in the (i + 1)-th cycle are obtained based on this state probability. The discount distribution weights indicate the degree of association between the target account and different discount levels. The comprehensive discount rate of the target account in the (i + 1)-th cycle is determined according to the discount distribution weights and the discount levels, so as to determine the discount rate corresponding to the ETC for the user in the next cycle. Thus, when the user uses the ETC system through the target account, it is no longer based on a fixed discount rate. The personalized user behaviors of different users based on the ETC system in this cycle will directly affect the discount rate used by the account in the ETC system in the next cycle. Poor user behaviors may be at the cost of being assigned a poor discount rate, so that users will regulate their user behaviors of using the ETC system in order to avoid this cost and prevent being added to the ETC blacklist and unable to use a better discount rate. Assigning corresponding discount rates based on user personalized behaviors is beneficial to the rationalization of the ETC system's discount rate system and helps the healthy development of the ETC system. Further, it will effectively reduce the inventory of accounts in the ETC blacklist and reduce the number of times of congestion at the ETC lanes. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0029] Figure 1 Schematic diagram of an application scenario of a data processing method provided by an embodiment of the present application;

[0030] Figure 2 Flowchart of a data processing method provided by an embodiment of the present application;

[0031] Figure 3 Schematic diagram of an electronic map application showing discount information provided by an embodiment of the present application;

[0032] Figure 4 Schematic diagram of an application scenario embodiment of a data processing method provided by an embodiment of the present application;

[0033] Figure 5 A schematic diagram of an application scenario embodiment of a data processing method provided by an embodiment of the present application;

[0034] Figure 6 A schematic diagram of a data processing device provided by an embodiment of the present application;

[0035] Figure 7 A schematic diagram of a data processing device provided by an embodiment of the present application;

[0036] Figure 8 A schematic diagram of the structure of a server provided by an embodiment of the present application;

[0037] Figure 9 A schematic diagram of the structure of a terminal device provided by an embodiment of the present application. Detailed implementation manners

[0038] The embodiments of the present application will be described below with reference to the accompanying drawings.

[0039] When the user is removed from the ETC blacklist, the user will enjoy the same treatment as other users who have not been added to the ETC blacklist. For example, the treatment in terms of the ETC discount rate and the like will not be affected by whether the user has ever been added to the ETC blacklist. Therefore, the user does not care whether they may be added to the ETC blacklist, and as a result, the ETC lane often becomes congested due to users in the ETC blacklist, losing the meaning of the convenience and speed of the ETC lane.

[0040] Based on this, the embodiments of the present application provide a data processing method and related devices, which allocate corresponding ETC discount rates based on the personalized behaviors of users, facilitating the rationalization of the ETC system discount rate system, enabling users to regulate their behaviors, and further reducing the number of times of congestion in the ETC lane. The data processing method provided by the present application can be applied to data processing devices with data processing capabilities, such as terminal devices and servers. Among them, the terminal device can specifically be a smart phone, a desktop computer, a laptop computer, a tablet computer, an in-vehicle computer, a smart watch, etc., but is not limited thereto; the server can be an independent physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal device and the server can be directly or indirectly connected through wired or wireless communication methods, and the present application does not make any restrictions here.

[0041] The data processing method provided by the embodiments of this application can be implemented based on cloud computing technology. Among them, cloud computing refers to the delivery and usage model of IT infrastructure, which means obtaining the required resources in a on-demand and easily scalable manner through the network; in a broad sense, cloud computing refers to the delivery and usage model of services, which means obtaining the required services in a on-demand and easily scalable manner through the network. Such services can be related to IT and software, the Internet, or other services. Cloud computing is the product of the development and integration of traditional computer and network technologies such as Grid Computing, Distributed Computing, Parallel Computing, Utility Computing, Network Storage Technologies, Virtualization, and Load Balance.

[0042] With the development of the Internet, real-time data streams, and diverse connected devices, as well as the promotion of demands such as search services, social networks, mobile commerce, and open collaboration, cloud computing has developed rapidly. Different from previous parallel distributed computing, the emergence of cloud computing will, in concept, drive revolutionary changes in the entire Internet model and enterprise management model.

[0043] In the data processing method provided by the embodiments of this application, the cloud server can determine the comprehensive discount rate that conforms to the user's personalized behavior in the (i + 1)-th cycle based on the user behavior generated by the vehicle's target account through the ETC system in the i-th cycle.

[0044] The data processing method provided by the embodiments of this application can also be implemented based on artificial intelligence. Artificial Intelligence (AI) is to use a digital computer or a machine controlled by a digital computer to simulate, extend, and expand human intelligence, and is a theory, method, technology, and application system that can perceive the environment, acquire knowledge, and use knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technology in computer science. It attempts to understand the essence of intelligence and produce a new intelligent machine that can respond in a way similar to human intelligence. Artificial intelligence is also the study of the design principles and implementation methods of various intelligent machines, enabling the machines to have the functions of perception, reasoning, and decision-making.

[0045] Artificial intelligence technology is an interdisciplinary subject that involves a wide range of fields, including both hardware-level and software-level technologies. The basic technologies of artificial intelligence generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, and mechatronics. The software technologies of artificial intelligence mainly include several major directions such as computer vision technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0046] In the embodiments of this application, the artificial intelligence technologies mainly involved include the above-mentioned directions such as machine learning / deep learning.

[0047] The aforementioned data processing device may also have the ability of machine learning. Machine learning is an interdisciplinary subject that involves multiple disciplines such as probability theory, statistics, approximation theory, convex analysis, and algorithm complexity theory. It specifically studies how computers simulate or implement human learning behaviors to acquire new knowledge or skills and reorganize the existing knowledge structure to continuously improve their own performance. Machine learning is the core of artificial intelligence and the fundamental way to make computers intelligent, and its applications cover all fields of artificial intelligence. Machine learning and deep learning usually include technologies such as artificial neural networks.

[0048] In the data processing method provided in the embodiments of this application, the artificial intelligence model adopted mainly involves the application of machine learning, and determines the state probability of the target account in the (i + 1)-th cycle through models such as deep learning based on user characteristic data.

[0049] To facilitate the understanding of the technical solution of this application, the following introduces the data processing method provided in the embodiments of this application by taking a server as the data processing device in combination with an actual application scenario.

[0050] See Figure 1 , this figure is a schematic diagram of the application scenario of a data processing method provided in the embodiments of this application. In the application scenario shown in Figure 1 , it includes a terminal device 100 and a server 200. An application (Application, APP) corresponding to the ETC system can be installed in the terminal device 100, hereinafter referred to as ETC APP for short. The user can log in to the ETC APP based on the target account and generate user behaviors such as clicks, recharges, and consumptions in the ETC system. The target account can be an ETC account, and a vehicle is bound to an ETC account.

[0051] The server 200 obtains the user feature data of the vehicle in the i-th cycle from the terminal device 100. The user feature data is used to identify the user behavior generated by the target account of the vehicle through the ETC system, such as n user behaviors corresponding to the ETC account, such as click data, recharge data, consumption data, comment data, account data, vehicle toll deduction, etc.

[0052] The user feature data can reflect the usage habits of the user using the ETC system. The usage habits are continuous. Therefore, the server 200 can determine the state probability of the target account in the (i + 1)-th cycle according to the user feature data. The state probability is used to identify the probability that the target account is added to the ETC blacklist in the (i + 1)-th cycle. That is to say, the user behavior generated by the account through the ETC system in the i-th cycle will directly affect the size of the state probability in the (i + 1)-th cycle. For example, if the user behavior of the account in the i-th cycle is bad, resulting in the account being frequently added to the ETC blacklist, the state probability of the account in the (i + 1)-th cycle is relatively large, that is, the probability that the account is added to the ETC blacklist is relatively large.

[0053] In the related art, there are multiple discount levels in the ETC system, and different discount levels correspond to different discount rates. For example, multiple discount levels are 10% off, 20% off, and 30% off, and the corresponding discount rates are 10%, 20%, and 30% respectively. However, the discount rate is fixed, and regardless of whether the account has been added to the ETC blacklist or not, it will not affect the discount rate of the account, resulting in users not caring whether they are added to the ETC blacklist.

[0054] In order to enable users to standardize their user behaviors of using the ETC system, the server 200 determines the corresponding discount rate based on the user behavior, that is, obtains the discount distribution weight of the target account in the (i + 1)-th cycle based on the state probability, and determines the comprehensive discount rate of the target account in the (i + 1)-th cycle according to the discount distribution weight and the discount level, and determines the discount rate corresponding to the ETC of the target account in the (i + 1)-th cycle.

[0055] Among them, the discount distribution weight is used to identify the degree of association between the target account and different discount levels under the state probability. For example, in the Figure 1 shown application scenario, since the user behavior of the user in the i-th cycle is relatively good, the state probability of the target account in the (i + 1)-th cycle is 20%. Therefore, in the (i + 1)-th cycle, the target account can correspond to a relatively high discount rate. The discount distribution weights obtained based on the state probability are 4.8%, 19%, and 76.2% respectively. That is, the probability that the target account gets a 10% discount in the (i + 1)-th cycle is 4.8%, the probability of getting a 20% discount is 19%, and the probability of getting a 30% discount is 76.2%. Furthermore, the comprehensive discount rate of the target account in the (i + 1)-th cycle is 27.14%, and the user can get a relatively large discount fee.

[0056] Thus, when a user uses the ETC system through a target account, it is no longer based on a fixed discount rate. The personalized user behaviors of different users based on the ETC system in this period will directly affect the discount rate used by the account in the ETC system in the next period. Poor user behaviors may result in a poor discount rate being assigned as a cost, causing users to regulate their user behaviors when using the ETC system in order to avoid this cost and prevent being added to the ETC blacklist and thus unable to obtain a better discount rate. Assigning corresponding discount rates based on user personalized behaviors is beneficial to the rationalization of the ETC system's discount rate system and contributes to the healthy development of the ETC system. Further, it will effectively reduce the stock of accounts in the ETC blacklist and reduce the number of times of congestion at the ETC lanes.

[0057] Next, in conjunction with the accompanying drawings, taking a cloud server as the data processing device, the data processing method provided by the embodiments of the present application will be introduced.

[0058] See Figure 2 , which is a flowchart of a data processing method provided by the embodiments of the present application. As Figure 2 shown, the data processing method includes the following steps:

[0059] S201: Obtain the user feature data of the vehicle in the i-th period.

[0060] In practical applications, a user registers an account for a vehicle in the ETC system, and the vehicle corresponds to the account one by one. The user can use devices such as terminal devices to use the ETC system based on the account, generating user feature data that identifies user behaviors. The user feature data can be click data, recharge data, consumption data, comment data, account data, vehicle passing toll deduction, etc. Through the user feature data, the usage habits of the user when using the ETC system can be analyzed.

[0061] The ETC system can accumulate the user feature data of different users based on different accounts. As a possible implementation, the cloud server can obtain and store the user feature data from the ETC system through the network. Or preprocess the obtained user feature data in the database format and store the user feature data in the database of the cloud server. Even different user feature data sets corresponding to different users can be generated based on different accounts.

[0062] The embodiments of the present application do not specifically limit the time length of the period. For example, one week is a period, one month is a period, one year is a period, etc.

[0063] S202: Determine the state probability of the target account in the (i + 1)-th period according to the user feature data.

[0064] Since users' usage habits generally have continuity, the state probability of the user in the (i + 1)-th cycle can be predicted based on the user feature data in the i-th cycle. This state probability is used to identify the likelihood that the target account will be added to the ETC blacklist in the (i + 1)-th cycle. Vehicles corresponding to accounts in the ETC blacklist are not allowed to automatically pass through the ETC lane.

[0065] That is to say, the user behavior generated by the user through the ETC system in the i-th cycle will directly affect the magnitude of the state probability in the (i + 1)-th cycle. For example, if the user often recharges their account in the i-th cycle, ensuring that there is sufficient balance in the account to successfully complete each deduction operation of the ETC system, the user has good usage habits. Therefore, in the (i + 1)-th cycle, the probability that the user has good usage habits is relatively high, the likelihood that their account will be added to the ETC blacklist is relatively low, and the corresponding state probability is relatively low.

[0066] As a possible implementation, the state probability of the target account in the (i + 1)-th cycle can be determined based on the user feature data through a classification model. The subsequent training method of the classification model will be described in S2021 - S2022 and will not be elaborated here.

[0067] Thus, based on the user feature data in the i-th cycle, the usage habits of the target account using the ETC system are mined through the trained classification model, and then the state probability 1 - P0 of the target account in the (i + 1)-th cycle is predicted, where P0 can be expressed as P0 = P(Y i+1 = 0|X t ), that is, the probability that the number of times the target account is added to the ETC blacklist in the (i + 1)-th cycle is zero. Further, the state probabilities corresponding to different vehicles can be stored in the cloud server based on the account.

[0068] S203: Obtain the discount distribution weight of the target account in the (i + 1)-th cycle based on the state probability.

[0069] The ETC system implements non-discriminatory basic discounts for ETC vehicles passing through this area. To encourage users to use the ETC system, in related technologies, there can also be different discount levels, and different discount levels correspond to different discount rates. For example, the discount rates corresponding to the discount levels of 10%, 20%, and 30% are 10%, 20%, and 30% respectively. However, the discount rate is fixed, and regardless of whether the account has been added to the ETC blacklist, it will not affect the final discount rate obtained by the user in the ETC system, resulting in users not caring whether they are added to the ETC blacklist, which is not conducive to the healthy development of the ETC system.

[0070] Based on this, in order to enable users to standardize their user behavior in using the ETC system and determine the discount rate based on user behavior, that is, to obtain the discount distribution weight of the target account in the (i + 1)-th period through the predicted state probability of the (i + 1)-th period, so that the comprehensive discount rate e corresponding to the target account is dynamically adjusted based on user behavior, that is, the discount rate finally obtained by the user in the ETC system is no longer fixed. If the user wants to obtain a higher comprehensive discount rate, they need to standardize their user behavior in the ETC system and obtain a larger comprehensive discount rate e through better user behavior.

[0071] Among them, the discount distribution weight is used to identify the degree of association between the target account and different discount levels under the state probability. If the state probability is large, it means that the user behavior corresponding to the target account performs poorly in the i-th period, and its degree of association with the lower discount level is larger and the degree of association with the higher discount level is smaller in the (i + 1)-th period, and so on. The following takes three discount levels as an example for illustration.

[0072] The three discount levels are θ1, θ2, and θ3 respectively, where 0 ≤ θ1 < θ2 < θ3 ≤ 1. The corresponding discount distribution sequence can be expressed as θ = [θ1, θ2, θ3]. The discount levels can be obtained according to the discount standards of different sections of the ETC system, and the present application does not make specific limitations on this. Correspondingly, the discount distribution weights can be π1, π2, and π3, that is, under the state probability 1 - P0, the probability of the target account obtaining the discount level θ1 is π1, the probability of obtaining the discount level θ2 is π2, and the probability of obtaining the discount level θ3 is π3. If the state probability 1 - P0 is large, then π1 > π2 > π3.

[0073] The present application does not specifically limit the method of obtaining the discount distribution weight according to the state probability. The following takes one method as an example for illustration. Refer to S2031 - S2033.

[0074] S2031: Determine the level transfer parameter between the discount levels identified based on the state probability of the account according to the up - grading and down - grading relationships between the discount levels.

[0075] There is generally a magnitude relationship between multiple discount levels. For example, in the discount distribution sequence [θ1, θ2, θ3], θ1 represents the lowest discount level (such as 10% off), θ2 represents the middle discount level (such as 20% off), and θ3 represents the highest discount level (such as 30% off). The up - grading relationship between the discount levels can be upgrading from the discount level θ1 to the discount level θ2, and from the discount level θ2 to the discount level θ3. The down - grading relationship is the same and will not be elaborated here.

[0076] According to the up - grading and down - grading relationships between the discount levels, determine the level transfer parameter P between the discount levels identified based on the state probability of the account. The mathematical expression form of the level transfer parameter P can be a matrix, and each element P in the matrixmn Denote the probability of transferring from the m-th discount level to the n-th discount level, where m can be equal to n. Continuing with the example of the aforementioned three discount levels θ1, θ2, and θ3, the level transfer parameter P can be expressed as

[0077] This level transfer parameter P shows a discount level transfer rule: If the target account of the vehicle has not been added to the ETC blacklist in the i-th cycle, then raise the discount level of the target account by one level or stay at the highest discount level θ3; if the target account of the vehicle has been added to the ETC blacklist in the i-th cycle, then lower the discount level of the target account by one level or stay at the lowest discount level θ1. The discount level transfer cannot skip levels up or down. This discount level transfer rule can be expressed by the following formula:

[0078]

[0079] where P0 represents the probability that the target account has not been added to the ETC blacklist in the (i + 1)-th cycle, and 1 - P0 = P(Y i+1 ≥ 1|X t ) represents the probability that the target account has been added to the ETC blacklist once or more in the (i + 1)-th cycle. The meaning of the discount level transfer rule is as follows:

[0080] θ1→θ1: 1 - P0 means that when at the lowest discount level θ1, if the target account has been added to the ETC blacklist, then the discount level θ1 does not increase, and the probability of staying at the lowest discount level θ1 is 1 - P0;

[0081] θ1→θ2: P0 means that when at the lowest discount level θ1, if the target account has not been added to the ETC blacklist, then the probability of the discount level θ1 increasing by one level to the discount level θ2 is P0;

[0082] θ1→θ3: 0 means that when at the lowest discount level θ1, since the discount level cannot skip, the discount level θ1 cannot directly increase to the discount level θ3, so the probability is 0;

[0083] θ2→θ1: 1 - P0 means that when at the discount level θ2, if the target account has been added to the ETC blacklist, then the probability of the discount level θ2 decreasing by one level to the discount level θ1 is 1 - P0;

[0084] θ2→θ2: 0 means that when at the discount level θ2, the probability of staying at the discount level θ2 is 0;

[0085] θ2 → θ3: P0 represents the probability that when in the discount level θ2, if the target account has not been added to the ETC blacklist, the discount level θ2 rises by one level to the discount level θ3, which is P0;

[0086] θ3 → θ1: 0 represents that when in the highest discount level θ3, since the discount level cannot jump, the discount level θ3 cannot directly drop to the discount level θ1, so the probability is 0;

[0087] θ3 → θ2: 1 - P0 represents that when in the highest discount level θ3, if the target account has been added to the ETC blacklist, the probability that the discount level θ3 drops by one level to the discount level θ2 is 1 - P0;

[0088] θ3 → θ3: P0 represents that when in the highest discount level θ3, if the target account has not been added to the ETC blacklist, the probability that the discount level θ3 does not rise and stays at the highest discount level θ3 is P0.

[0089] S2032: Determine the discount distribution sequence based on the level transfer parameter.

[0090] The discount distribution sequence is used to identify the association relationship between the state probabilities of the account and the discount levels. A steady-state equation can be constructed, which can be expressed as π·P = π, where π represents the discount distribution sequence and P represents the level transfer parameter.

[0091] If we continue to take the previous three discount levels θ1, θ2, θ3 as an example, the discount distribution sequence π obtained according to the steady-state equation can be expressed as π = [π1, π2, π3].

[0092] Among them,

[0093] Thus, the constructed discount distribution sequence can be pre-saved to the cloud server so that after obtaining the state probability, the discount distribution weight of the target account in the (i + 1)-th period can be calculated based on the discount distribution sequence. Further, the discount distribution weight of the target account in the (i + 1)-th period can also be stored in the billing system database of the cloud server so that the discount fee of the target account can be directly calculated by calling the discount distribution weight in the (i + 1)-th period.

[0094] S2033: Obtain the discount distribution weight of the target account in the (i + 1)-th period based on the state probability and the discount distribution sequence.

[0095] Substitute the obtained state probability 1 - P0 into the discount distribution sequence π = [π1, π2, π3] to obtain the discount distribution weights π1, π2, and π3.

[0096] S204: Determine the comprehensive discount rate of the target account in the (i + 1)-th cycle according to the discount distribution weight and the discount level, and determine the comprehensive discount rate as the discount rate of the target account corresponding to the ETC system in the (i + 1)-th cycle.

[0097] Thus, when a user uses the ETC system through the target account, instead of being based on a fixed discount rate, the discount rate used by different users in the ETC system in the (i + 1)-th cycle is determined by the personalized user behaviors of different users based on the ETC system in the i-th cycle. The personalized behaviors of users will affect the discount rate ultimately obtained by their accounts in the ETC system. In order to obtain a higher comprehensive discount rate, users will standardize their user behaviors and try to reduce or even prevent the number of times they are added to the ETC blacklist, thereby reducing the number of accounts in the ETC blacklist. At the same time, the comprehensive discount rate of the user's account in different cycles will be dynamically adjusted based on the user characteristic data of different cycles, so that users will not only ensure their user behaviors in each cycle, achieving the effect of encouraging users to travel civilized.

[0098] Furthermore, the comprehensive discount rate corresponding to each account can be stored in the billing system database of the cloud server, so as to directly call the comprehensive discount rate in the (i + 1)-th cycle to calculate the discount fee of the target account.

[0099] The embodiments of the present application do not specifically limit the determination method of the comprehensive discount rate. Hereinafter, three discount levels and their corresponding discount distribution weights are taken as examples to illustrate by two methods.

[0100] The first method: Take the target discount level whose discount distribution weight in the discount level meets the preset condition as the comprehensive discount rate of the target account in the (i + 1)-th cycle.

[0101] Determine the target discount distribution weight that meets the threshold condition from the discount distribution weights, and take the discount level corresponding to the target discount distribution weight as the target discount level. For example, take the discount level θ3 corresponding to the largest discount distribution weight π3 among the discount distribution weights π1, π2, π3 as the target discount level, and the discount rate corresponding to the target discount level θ3 is the comprehensive discount rate e of the target account in the (i + 1)-th cycle.

[0102] The second method: Obtain the comprehensive discount rate of the target account in the (i + 1)-th cycle based on the influence degree of the discount distribution weight on the discount level.

[0103] The discount distribution weights π1, π2, π3 can be used as the coefficients corresponding to the discount levels θ1, θ2, θ3. Based on the expectation formula Obtain the comprehensive discount rate e of the target account in the (i + 1)-th cycle.

[0104] As can be seen from the above technical solution, the user behavior of the target account of the vehicle generated by the ETC system is determined according to the user characteristic data of the vehicle in the i-th cycle, and the state probability of the target account in the (i + 1)-th cycle is determined based on the user characteristic data. Thus, based on the continuity of the user usage habit, whether the user behavior of the target account passing through the ETC system in the i-th cycle is qualified will directly affect the magnitude of the state probability. Since the state probability reflects the possibility that the target account will be added to the ETC blacklist in the (i + 1)-th cycle, for the discount levels with different discount rates, the discount distribution weight of the target account in the (i + 1)-th cycle is obtained based on the state probability. The discount distribution weight indicates the degree of association between the target account and different discount levels. The comprehensive discount rate of the target account in the (i + 1)-th cycle is determined according to the discount distribution weight and the discount level, and the discount rate corresponding to the user for the ETC in the next cycle is determined. Thus, when the user uses the ETC system through the target account, it is no longer based on a fixed discount rate. The personalized user behaviors of different users based on the ETC system in this cycle will directly affect the discount rate used by the account in the ETC system in the next cycle. Poor user behaviors may be at the cost of being assigned a poor discount rate, so that users will standardize their user behaviors of using the ETC system in order to avoid this cost and prevent being added to the ETC blacklist and thus unable to use a better discount rate. Assigning corresponding deduction rates based on user personalized behaviors is conducive to the rationalization of the ETC system discount rate system and helps the healthy development of the ETC system. Further, it will effectively reduce the inventory of accounts in the ETC blacklist and reduce the number of times of congestion at the ETC lanes.

[0105] As a possible implementation manner, the state probability of the target account in the (i + 1)-th cycle can be determined according to the user characteristic data through a classification model. A training method of the classification model will be described below. Refer to S2021 - S2022.

[0106] S2021: Obtain user sample data based on the cycle.

[0107] The user sample data includes the sample user behaviors generated by the account of the vehicle passing through the ETC system within one cycle. The label of the user sample data is used to identify whether the account of the vehicle will be added to the ETC blacklist in the next cycle.

[0108] For example, in the cloud server, the stored user characteristic data is divided into user characteristic data of t cycles in chronological order by using database technology. Among them, the database technology can be SQL (Structured Query Language, a database language) technology, Hive (a data warehouse tool) technology, SPARK (a computing engine) technology.

[0109] Among the user feature data for t cycles, whether the vehicle's account is added to the ETC blacklist in the (j + 1)-th cycle can be used as the label for the user feature data in the j-th cycle. For example, if the vehicle's account is added to the ETC blacklist in the (j + 1)-th cycle, the label for the user feature data in the j-th cycle can be represented by 1; if the vehicle's account is not added to the ETC blacklist in the (j + 1)-th cycle, the label for the user feature data in the j-th cycle can be represented by 0. The user feature data with labels can be used as user sample data, and the user sample data in the j-th cycle is used to identify the sample user behavior generated by the vehicle's account passing through the ETC system in the j-th cycle, where j < t.

[0110] S2022: Train the initial classification model according to the user sample data to obtain a classification model.

[0111] The embodiment of the present application does not limit the classification model. The classification model can be a binary classification model or a multi-classification model. For example, the initial classification model is trained and tested through machine learning algorithms such as supervised binary classification algorithms to obtain a classification model.

[0112] As a possible implementation, the user sample data can be divided into training user sample data and test user sample data. The initial classification model is trained through the training user sample data, the trained initial classification model is tested through the test user sample data, and it is determined whether the initial classification model is trained based on the obtained error, so as to obtain a classification model. Further, the classification model can be stored in a cloud server.

[0113] Thus, according to the user feature data, the state probability of the target account in the (i + 1)-th cycle is determined through the trained classification model.

[0114] As a possible implementation, the user feature data can also include the discount rate of the target account corresponding to the ETC system in the i-th cycle. The state probability in the (i + 1)-th cycle is jointly determined by the discount rate of the user corresponding to the ETC system in the i-th cycle and the user behavior generated by the user passing through the ETC system in the i-th cycle, so as to avoid the account with a relatively low discount rate of the ETC system in the i-th cycle jumping multiple discount levels in the (i + 1)-th cycle by constraining the state probability obtained by the discount rate of the user corresponding to the ETC system in the i-th cycle.

[0115] For example, in the i-th cycle, both user A and user B maintain good user behavior and have not been added to the ETC blacklist. However, the discount rate of user A is 30% and the discount rate of user B is 10%. If the state probability is determined only based on the user behavior generated by the user through the ETC system in the i-th cycle, then user A and user B will obtain the same state probability, and thus user A and user B will be determined to have the same comprehensive discount rate, such as 35%, in the (i + 1)-th cycle. At this time, the discount rate corresponding to the account of user B in the ETC system has increased by multiple discount levels. If the discount rates corresponding to the ETC system of user A and user B in the i-th cycle are used as constraints to ensure that the discount level transfer cannot jump up or down, and the state probability in the (i + 1)-th cycle is jointly determined according to the discount rates corresponding to the ETC system of user A and user B in the i-th cycle and the user behavior generated by user A and user B through the ETC system in the i-th cycle, then the state probabilities obtained by user A and user B are different.

[0116] As a possible implementation, the user sample data may further include the discount rate corresponding to the ETC system of the vehicle's account in the i-th cycle. The classification model is trained through, for example, S2021 - S2022, so as to determine the state probability of the target account in the (i + 1)-th cycle according to the user feature data including the discount rate corresponding to the ETC system of the target account in the i-th cycle, realizing that under the premise that the user behaviors of multiple users are relatively similar, if the discount rates corresponding to the ETC systems of multiple users in the current cycle are different, the obtained state probabilities are different.

[0117] As a possible implementation, the labels of the user sample data may also be 0, 1, 2, etc., indicating the probability that the target account has not been added to the ETC blacklist in the (j + 1)-th cycle, the probability of being added to the ETC blacklist once, the probability of being added to the ETC blacklist twice, etc., further refining the user behavior. According to the classification model trained based on the refined user sample data and the user feature data in the i-th cycle, the state probability in the (i + 1)-th cycle can be predicted. At this time, the state probability is used to indicate the probability that the target account is added to the ETC blacklist once or multiple times in the (i + 1)-th cycle, so as to give different degrees of discount distribution weights to different degrees of the target account being added to the blacklist subsequently.

[0118] For example, the greater the probability that the target account is added to the ETC blacklist in the (i + 1)-th cycle, the lower its corresponding comprehensive discount rate. This makes the comprehensive discount rate of the account with more times of being added to the ETC blacklist lower, and the comprehensive discount rate of the account with fewer times of being added to the ETC blacklist higher. By differentiating the number of times an account is added to the ETC blacklist, even if a user's account has been added to the ETC blacklist, the user will try to regulate their own user behavior to avoid the comprehensive discount rate getting lower and lower due to more and more times of being added to the ETC blacklist. This is more conducive to the rationalization of the discount rate system of the ETC system, effectively reducing the stock of accounts in the ETC blacklist and reducing the number of times of congestion at the ETC lane, and encouraging users to travel civilizedly.

[0119] As a possible implementation method, the cloud server can push the comprehensive discount rate of the target account in the (i + 1)-th cycle to the user. For example, the cloud server pushes the comprehensive discount rate to the terminal device, and displays the comprehensive discount rate through the electronic map application installed in the terminal device, or pushes the comprehensive discount rate to the user through the client of the ETC system, or sends the comprehensive discount rate to the user through social accounts, mobile phone text messages, etc. The following takes the display of the comprehensive discount rate through the electronic map application as an example for illustration.

[0120] The user can pre-associate the account registered in the ETC system with the map account registered in the electronic map application, so as to realize the information intercommunication between the ETC system and the electronic map application. Among them, the account registered in the ETC system or the map account can be a license plate number, a mobile phone number, a social account, etc.

[0121] In the (i + 1)-th cycle, if the user opens the electronic map application based on the map account through the terminal device, the terminal device sends the map account to the cloud server. If the cloud server determines that the map account has an associated target account in the ETC system, it obtains the comprehensive discount rate corresponding to the target account of the map account in the (i + 1)-th cycle for the ETC system from the database, sends the comprehensive discount rate to the terminal device, and displays the comprehensive discount rate in the electronic map application, so as to realize the display of the comprehensive discount rate to the user when the user is navigating through the electronic map application, so that the user can know the current comprehensive discount rate.

[0122] Among them, the comprehensive discount rate is determined according to the discount level of the ETC system and the state probability of the target account in the (i + 1)-th cycle. The state probability is used to identify the probability that the target account is added to the ETC blacklist in the (i + 1)-th cycle, and the state probability is determined based on the user behavior generated by the target account passing through the ETC system in the i-th cycle. The acquisition method of the comprehensive discount rate can refer to the foregoing S201 - S204, and will not be elaborated here.

[0123] As a possible implementation, the cloud server may also send the discount information corresponding to the comprehensive discount rate to the electronic map application. The electronic map application can display the discount information when the user uses navigation. By displaying the discount information, the discount situation of the current ETC system can be intuitively and conveniently shown to the user, so that the user can regulate their ETC system usage habits based on the matching degree between the discount information and their own needs.

[0124] The discount information may include at least one of the comprehensive discount rate itself, the actual toll to be paid for this trip, and the discounted fee waived. The discounted fee is the waived fee calculated based on the standard fee required for this trip in combination with the comprehensive discount rate. For example, the discounted fee for a standard fee of 100 yuan at a comprehensive discount rate of 10% (equivalent to a 10% discount) is 10 yuan. The actual toll is the fee that the user actually needs to pay after subtracting the discounted fee from the standard fee. It should be noted that after the cloud server sends the discount information to the electronic map application, the electronic map application can display the received discount information. See Figure 3 , which is a schematic diagram of an electronic map application displaying discount information provided by an embodiment of the present application. In this embodiment, it is taken as an example that the discount information includes the discounted fee and the actual toll. If the user enters the departure place as Place A and the destination as Place B in the electronic map application, the discounted fee and the actual toll as the discount information can be displayed during the display of the navigation route from Place A to Place B. This embodiment is only an example and does not limit the actual display form of the discount information and the number of display items.

[0125] Among them, the standard fee from Place A to Place B is f, the discounted fee is c1 = e × f, and the toll to be paid is c2 = (1 - e) × f. For example, if the standard fee from Place A to Place B is 100 yuan and the determined comprehensive discount rate is 10%, then the discounted fee is 10 yuan and the actual toll is 90 yuan.

[0126] As a possible implementation, if the user has multiple vehicles, each vehicle corresponds to an account respectively. When the user opens the electronic map application through the terminal device, the cloud server will obtain multiple associated accounts based on the map account, display the accounts corresponding to the multiple vehicles through the electronic map application, and then determine one account as the target account from the accounts corresponding to the multiple vehicles according to the selection operation triggered by the user through the terminal device.

[0127] It should be noted that if the electronic map application is installed in the in-vehicle computer of the vehicle, the in-vehicle computer carries the vehicle identification of this vehicle, and the in-vehicle computer can determine the target account from the accounts of the multiple vehicles based on the vehicle identification and display the target account on the in-vehicle computer.

[0128] Thus, in the (i + 1)-th cycle, if the electronic map application based on the map account is turned on and it is determined that the map account has an associated target account in the ETC system, then the user behavior of the target account of the vehicle generated through the ETC system is identified based on the user characteristic data of the vehicle in the i-th cycle, and the state probability of the target account in the (i + 1)-th cycle is determined based on the user characteristic data. Thus, due to the continuity of the user usage habits, whether the user behavior of the target account through the ETC system in the i-th cycle is qualified will directly affect the magnitude of this state probability. Since this state probability reflects the possibility that the target account will be added to the ETC blacklist in the (i + 1)-th cycle, the comprehensive discount rate of the target account in the (i + 1)-th cycle is determined according to the discount level of the ETC system and the state probability of the target account in the (i + 1)-th cycle, thereby determining the discount rate corresponding to the ETC for the user in the next cycle. Thus, when the user uses the ETC system through the target account, it is no longer based on a fixed discount rate. The personalized user behaviors of different users based on the ETC system in this cycle will directly affect the discount rate used by the account in the ETC system in the next cycle. Implementing bad user behaviors may result in being assigned a bad discount rate as a cost, causing the user to standardize their user behaviors of using the ETC system in order to avoid this cost and prevent being added to the ETC blacklist and thus unable to use a better discount rate. Assigning corresponding discount rates based on user personalized behaviors is beneficial to the rationalization of the ETC system discount rate system and helps the healthy development of the ETC system. Further, it will effectively reduce the inventory of accounts in the ETC blacklist and reduce the number of times of congestion at the ETC lanes.

[0129] Next, the data processing method provided by the embodiments of the present application will be described in conjunction with Figure 4 and Figure 5 See Figure 4 , which is a schematic diagram of an application scenario embodiment of a data processing method provided by the embodiments of the present application.

[0130] The user first registers through the mobile phone number (map account) in the electronic map application and registers through the license plate number (target account) in the ETC system, establishing a mapping relationship between the mobile phone number and the license plate number, and associating the target account with the map account.

[0131] The ETC system collects user characteristic data and stores the user characteristic data in the cloud server. The cloud server can perform data preprocessing on the obtained user characteristic data in accordance with the database format. The following will describe how the cloud server pushes information such as the comprehensive discount rate to the electronic map application in conjunction with Figure 5 See

[0132] See Figure 5 , which is a schematic diagram of an application scenario embodiment of a data processing method provided by the embodiments of the present application.

[0133] S1: User sample data processing stage.

[0134] Divide the user feature data into user feature data of x cycles in chronological order. Since the user feature data of the first x - 1 cycles has corresponding labels, the user feature data of the first x - 1 cycles is used as user sample data. Randomly divide the user sample data into training user sample data and test user sample data, and use the user feature data of the xth cycle as the user feature data for prediction.

[0135] S2: Classification model training stage.

[0136] Based on the training user sample data and test user sample data, use a binary classification linear regression (linearregression, LR) model for model training and testing to obtain a trained classification model W and save it to the cloud server. The specific process can refer to S2021 - S2022.

[0137] S3: State probability prediction stage.

[0138] Input the user feature data of the xth cycle into the classification model W to calculate the state probability 1 - P0 of each vehicle's account in the (x + 1)th cycle.

[0139] S4: Constructing level transition parameter stage.

[0140] According to the promotion and demotion relationship between discount levels, determine the level transition parameter P between discount levels based on the state probability identification of the account. For details, refer to S2031.

[0141] S5: Determining the discount distribution sequence stage.

[0142] Continuing with the example of three discount levels, determine the discount distribution sequence π = [π1, π2, π3] based on the level transition parameter P. For details, refer to S2032.

[0143] S6: Determining the discount distribution weight stage.

[0144] Substitute the obtained state probability 1 - P0 into the discount distribution sequence π = [π1, π2, π3] to obtain the discount distribution weights π1, π2, and π3.

[0145] S7: Determining the comprehensive discount rate stage.

[0146] Determine the comprehensive discount rate e of the target account in the (i + 1)th cycle according to the aforementioned second method, and determine the comprehensive discount rate as the discount rate corresponding to the ETC system of the target account in the (i + 1)th cycle.

[0147] S8: Discount Information Calculation Stage.

[0148] If in the (x + 1)-th cycle, the electronic map application is enabled based on the map account and obtains the driving route queried by the user, continue to refer to Figure 4 , and calculate the discount fee c1 = e × f and the toll c2 = (1 - e) × f to be paid, etc., according to the standard fee f corresponding to the driving route obtained from the ETC billing system and the comprehensive discount rate e.

[0149] S9: Discount Information Push Stage.

[0150] Continue to refer to Figure 4 , and the cloud server pushes discount information such as the comprehensive discount rate e, the discount fee c1, and the toll c2 to the electronic map application for the electronic map application to display to the user.

[0151] For the data processing method provided in the above embodiments, the embodiments of the present application further provide a data processing device.

[0152] Refer to Figure 6 , which is a schematic diagram of a data processing device provided by the embodiments of the present application. As Figure 6 shown, the data processing device 600 includes: an acquisition unit 601, a state probability determination unit 602, a discount distribution weight acquisition unit 603, and a comprehensive discount rate determination unit 604.

[0153] The acquisition unit 601 is configured to acquire user feature data of the vehicle in the i-th cycle, and the user feature data is used to identify user behaviors generated by the target account of the vehicle through the Electronic Toll Collection (ETC) system;

[0154] The state probability determination unit 602 is configured to determine the state probability of the target account in the (i + 1)-th cycle according to the user feature data, and the state probability is used to identify the probability that the target account is added to the ETC blacklist in the (i + 1)-th cycle, and the ETC blacklist is used to identify accounts that are not allowed to use the ETC system;

[0155] The discount distribution weight acquisition unit 603 is configured to obtain the discount distribution weight of the target account in the (i + 1)-th cycle based on the state probability, and the discount distribution weight is used to identify the degree of association between the target account and different discount levels under the state probability;

[0156] The comprehensive discount rate determination unit 604 is configured to determine the comprehensive discount rate of the target account in the (i + 1)-th cycle according to the discount distribution weight and the discount level, and determine the comprehensive discount rate as the discount rate corresponding to the target account for the ETC system in the (i + 1)-th cycle.

[0157] As a possible implementation, the data processing device 600 further includes a level transfer parameter determination unit, configured to:

[0158] Determine the level transfer parameters between the discount levels based on the status probability identifier of the account according to the upgrade and downgrade relationships between the discount levels;

[0159] Determine a discount distribution sequence based on the level transfer parameters, where the discount distribution sequence is used to identify the association relationships between the status probabilities of the account and the discount levels;

[0160] The discount distribution weight obtaining unit 603 is configured to:

[0161] Obtain the discount distribution weight of the target account in the (i + 1)-th period based on the status probability and the discount distribution sequence.

[0162] As a possible implementation, the user feature data includes the discount rate of the target account corresponding to the ETC system in the i-th period.

[0163] As a possible implementation, the status probability determination unit 602 is configured to:

[0164] Determine the status probability of the target account in the (i + 1)-th period through a classification model according to the user feature data;

[0165] The device further includes a training unit, configured to:

[0166] Obtain user sample data based on the period, where the user sample data includes sample user behaviors generated by the account of the vehicle passing through the ETC system in one period, and the label of the user sample data is used to identify whether the account of the vehicle is added to the ETC blacklist in the next period;

[0167] Train an initial classification model according to the user sample data to obtain the classification model.

[0168] As a possible implementation, the comprehensive discount rate determination unit 604 is configured to:

[0169] Use the target discount level whose discount distribution weight in the discount levels meets a preset condition as the comprehensive discount rate of the target account in the (i + 1)-th period; or,

[0170] Obtain the comprehensive discount rate of the target account in the (i + 1)-th period based on the influence degree of the discount distribution weight on the discount levels.

[0171] As a possible implementation, the state probability is also used to identify the probability that the target account is added to the ETC blacklist once or more times in the (i + 1)-th cycle.

[0172] As a possible implementation, the data processing device 600 further includes a sending unit, configured to:

[0173] Obtain a map account associated with the target account;

[0174] In the (i + 1)-th cycle, if it is determined that the electronic map application is enabled based on the map account, send the discount rate of the target account corresponding to the ETC system in the (i + 1)-th cycle to the electronic map application.

[0175] See Figure 7 , which is a schematic diagram of a data processing device provided in an embodiment of the present application. As Figure 7 shown, the data processing device 700 includes: an enabling unit 701 and a display unit 702.

[0176] The enabling unit 701 is configured to enable the electronic map application based on the map account in the (i + 1)-th cycle;

[0177] The display unit 702 is configured to, if it is determined that the map account has an associated target account in the electronic toll collection (ETC) system, display the discount information corresponding to the comprehensive discount rate of the target account corresponding to the ETC system in the (i + 1)-th cycle. The comprehensive discount rate is determined according to the discount level of the ETC system and the state probability of the target account in the (i + 1)-th cycle. The state probability is used to identify the probability that the target account is added to the ETC blacklist in the (i + 1)-th cycle, and the state probability is determined based on the user behavior generated by the target account passing through the ETC system in the i-th cycle.

[0178] As a possible implementation, the data processing device 700 further includes a target account determination unit, configured to:

[0179] If it is determined that the map account has accounts of multiple vehicles in the ETC system, display the accounts of the multiple vehicles through the electronic map application;

[0180] Determine the target account from the accounts of the multiple vehicles according to the selected operation.

[0181] The data processing device provided by the embodiment of the present application determines the user behavior generated by the target account of the vehicle through the ETC system according to the user characteristic data of the vehicle in the i-th cycle, and determines the state probability of the target account in the (i + 1)-th cycle based on the user characteristic data. Thus, based on the continuity of the user's usage habits, whether the user behavior of the target account through the ETC system in the i-th cycle is qualified will directly affect the magnitude of this state probability. Since this state probability reflects the possibility that the target account will be added to the ETC blacklist in the (i + 1)-th cycle, for the discount levels with different discount rates, the discount distribution weight of the target account in the (i + 1)-th cycle is obtained based on this state probability. The discount distribution weight indicates the degree of association between the target account and different discount levels. The comprehensive discount rate of the target account in the (i + 1)-th cycle is determined according to the discount distribution weight and the discount level, so as to determine the discount rate corresponding to the user for the ETC in the next cycle. Thus, when the user uses the ETC system through the target account, it is no longer based on a fixed discount rate. The personalized user behaviors of different users based on the ETC system in this cycle will directly affect the discount rate used by the account in the ETC system in the next cycle. Poor user behaviors may be at the cost of being assigned a poor discount rate, so that users will regulate their user behaviors of using the ETC system in order to avoid this cost and avoid being added to the ETC blacklist and unable to use a better discount rate. Assigning corresponding discount rates based on user personalized behaviors is beneficial to the rationalization of the ETC system discount rate system and helps the healthy development of the ETC system. Further, it will effectively reduce the inventory of accounts in the ETC blacklist and reduce the number of times of congestion at the ETC lane.

[0182] The aforementioned data processing device may be a computer device. This computer device may be a server or a terminal device. The computer device provided by the embodiment of the present application will be introduced from the perspective of hardware implementation below. Among them, Figure 8 The structure diagram of the server is shown, Figure 9 The structure diagram of the terminal device is shown.

[0183] See Figure 8 , Figure 8It is a schematic diagram of a server structure provided by an embodiment of the present application. The server 1400 may vary greatly due to different configurations or performances, and may include one or more central processing units (CPUs) 1422 (for example, one or more processors) and a memory 1432, and one or more storage media 1430 (for example, one or more mass storage devices) for storing application programs 1442 or data 1444. Among them, the memory 1432 and the storage media 1430 may be transient storage or persistent storage. The program stored in the storage media 1430 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations on the server. Further, the CPU 1422 may be configured to communicate with the storage media 1430 and execute a series of instruction operations in the storage media 1430 on the server 1400.

[0184] The server 1400 may further include one or more power supplies 1426, one or more wired or wireless network interfaces 1450, one or more input / output interfaces 1458, and / or, one or more operating systems 1441, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, and so on.

[0185] The steps performed by the server in the above embodiments may be based on the Figure 8 shown server structure.

[0186] Among them, the CPU 1422 is used to perform the following steps:

[0187] Obtain user feature data of the vehicle in the i-th cycle, where the user feature data is used to identify the user behavior generated by the target account of the vehicle through the electronic toll collection (ETC) system;

[0188] Determine the state probability of the target account in the (i + 1)-th cycle according to the user feature data, where the state probability is used to identify the probability that the target account is added to the ETC blacklist in the (i + 1)-th cycle, and the ETC blacklist is used to identify the accounts that are not allowed to use the ETC system;

[0189] Obtain the discount distribution weight of the target account in the (i + 1)-th cycle based on the state probability, where the discount distribution weight is used to identify the degree of association between the target account and different discount levels under the state probability;

[0190] Determine the comprehensive discount rate of the target account in the (i + 1)-th cycle according to the discount distribution weight and the discount level, and determine the comprehensive discount rate as the discount rate of the target account corresponding to the ETC system in the (i + 1)-th cycle.

[0191] Alternatively, the CPU 1422 is further configured to perform the following steps:

[0192] In the (i + 1)-th cycle, turn on the electronic map application based on the map account;

[0193] If it is determined that the map account has an associated target account in the electronic toll collection (ETC) system, display the discount information corresponding to the comprehensive discount rate of the target account corresponding to the ETC system in the (i + 1)-th cycle. The comprehensive discount rate is determined according to the discount level of the ETC system and the state probability of the target account in the (i + 1)-th cycle. The state probability is used to identify the probability that the target account is added to the ETC blacklist in the (i + 1)-th cycle, and the state probability is determined based on the user behavior generated by the target account passing through the ETC system in the i-th cycle.

[0194] Optionally, the CPU 1422 may further execute the method steps of any specific implementation manner of the data processing method in the embodiments of the present application.

[0195] See Figure 9 , Figure 9 which is a schematic structural diagram of a terminal device provided by an embodiment of the present application. Figure 9 Shown is a block diagram of a part of the structure of a smart phone related to the terminal device provided by an embodiment of the present application. The smart phone includes: a radio frequency (RF) circuit 1510, a memory 1520, an input unit 1530, a display unit 1540, a sensor 1550, an audio circuit 1560, a wireless fidelity (WiFi) module 1570, a processor 1580, and a power supply 1590 and other components. Those skilled in the art can understand that Figure 9 the smart phone structure shown in

[0196] does not constitute a limitation on the smart phone, and may include more or fewer components than shown in the figure, or combine some components, or arrange different components. Figure 9 The following specifically introduces each component of the smart phone:

[0197] The RF circuit 1510 can be used for receiving and transmitting information or signals during a call. Specifically, after receiving the downlink information from the base station, it is sent to the processor 1580 for processing. Additionally, the uplink data designed is sent to the base station. Generally, the RF circuit 1510 includes, but is not limited to, an antenna, at least one amplifier, a transceiver, a coupler, a low noise amplifier (LNA), a duplexer, etc. In addition, the RF circuit 1510 can also communicate with the network and other devices via wireless communication. The above wireless communication can use any communication standard or protocol, including but not limited to the Global System of Mobile communication (GSM), General Packet Radio Service (GPRS), Code Division Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), Long Term Evolution (LTE), email, Short Messaging Service (SMS), etc.

[0198] The memory 1520 can be used to store software programs and modules. The processor 1580 runs the software programs and modules stored in the memory 1520 to implement various functional applications and data processing of the smart phone. The memory 1520 mainly includes a program storage area and a data storage area. Among them, the program storage area can store an operating system, application programs required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the smart phone (such as audio data, phone book, etc.), etc. In addition, the memory 1520 can include a high-speed random access memory and can also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage devices.

[0199] The input unit 1530 can be used to receive input numerical or character information, and generate key signal inputs related to the user settings and function controls of the smart phone. Specifically, the input unit 1530 can include a touch panel 1531 and other input devices 1532. The touch panel 1531, also known as a touch screen, can collect touch operations of the user thereon or nearby (such as operations of the user using any suitable object or accessory such as a finger, a stylus, etc. on or near the touch panel 1531), and drive corresponding connection devices according to a preset program. Optionally, the touch panel 1531 can include two parts: a touch detection device and a touch controller. Among them, the touch detection device detects the touch position of the user, detects the signal brought by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection device, converts it into contact coordinates, then sends it to the processor 1580, and can receive and execute commands sent by the processor 1580. In addition, various types such as resistive, capacitive, infrared, and surface acoustic wave can be used to implement the touch panel 1531. In addition to the touch panel 1531, the input unit 1530 can also include other input devices 1532. Specifically, the other input devices 1532 can include, but are not limited to, one or more of a physical keyboard, function keys (such as volume control keys, power on / off keys, etc.), a trackball, a mouse, a joystick, etc.

[0200] The display unit 1540 can be used to display information input by the user or information provided to the user and various menus of the smart phone. The display unit 1540 can include a display panel 1541. Optionally, the display panel 1541 can be configured in forms such as a liquid crystal display (LCD) and an organic light-emitting diode (OLED). Further, the touch panel 1531 can cover the display panel 1541. When the touch panel 1531 detects a touch operation thereon or nearby, it is transmitted to the processor 1580 to determine the type of touch event. Subsequently, the processor 1580 provides corresponding visual output on the display panel 1541 according to the type of touch event. Although in Figure 9 the touch panel 1531 and the display panel 1541 are implemented as two independent components to realize the input and output functions of the smart phone, in some embodiments, the touch panel 1531 and the display panel 1541 can be integrated to realize the input and output functions of the smart phone.

[0201] The smart phone may also include at least one sensor 1550, such as a light sensor, a motion sensor, and other sensors. Specifically, the light sensor may include an ambient light sensor and a proximity sensor. Among them, the ambient light sensor can adjust the brightness of the display panel 1541 according to the brightness of the ambient light, and the proximity sensor can turn off the display panel 1541 and / or the backlight when the smart phone is moved to the ear. As a kind of motion sensor, the accelerometer sensor can detect the magnitude of acceleration in all directions (generally three axes), and can detect the magnitude and direction of gravity when stationary, and can be used for applications that identify the posture of the smart phone (such as horizontal and vertical screen switching, related games, magnetometer posture calibration), vibration recognition related functions (such as pedometer, tapping), etc.; as for other sensors such as gyroscopes, barometers, hygrometers, thermometers, and infrared sensors that the smart phone can also be configured with, they will not be elaborated here.

[0202] The audio circuit 1560, the speaker 1561, and the microphone 1562 can provide an audio interface between the user and the smart phone. The audio circuit 1560 can transmit the electrical signal converted from the received audio data to the speaker 1561, and the speaker 1561 converts it into a sound signal for output; on the other hand, the microphone 1562 converts the collected sound signal into an electrical signal, which is received by the audio circuit 1560 and then converted into audio data. After the audio data is output to the processor 1580 for processing, it is sent through the RF circuit 1510 to, for example, another smart phone, or the audio data is output to the memory 1520 for further processing.

[0203] WiFi belongs to short - range wireless transmission technology. The smart phone can help users send and receive emails, browse the web, and access streaming media through the WiFi module 1570, which provides users with wireless broadband Internet access. Although Figure 9 the WiFi module 1570 is shown, it can be understood that it does not belong to the essential components of the smart phone and can be omitted completely within the scope of not changing the essence of the invention according to needs.

[0204] The processor 1580 is the control center of the smart phone, connecting various parts of the entire smart phone through various interfaces and lines. By running or executing software programs and / or modules stored in the memory 1520, and calling data stored in the memory 1520, it executes various functions of the smart phone and processes data. Optionally, the processor 1580 may include one or more processing units; preferably, the processor 1580 may integrate an application processor and a modem processor. Among them, the application processor mainly processes the operating system, user interface, and application programs, etc., and the modem processor mainly processes wireless communication. It can be understood that the above - mentioned modem processor may not be integrated into the processor 1580.

[0205] The smart phone further includes a power source 1590 (such as a battery) for supplying power to each component. Preferably, the power source can be logically connected to the processor 1580 through a power management system, so as to implement functions such as management of charging, discharging, and power consumption management through the power management system.

[0206] Although not shown, the smart phone may further include a camera, a Bluetooth module, etc., which will not be elaborated here.

[0207] In the embodiment of the present application, the memory 1520 included in the smart phone can store program codes and transmit the program codes to the processor.

[0208] The processor 1580 included in the smart phone can execute the data processing method provided in the above embodiment according to the instructions in the program codes.

[0209] The embodiment of the present application further provides a computer-readable storage medium for storing a computer program, and the computer program is used to execute the data processing method provided in the above embodiment.

[0210] The embodiment of the present application further provides a computer program product or a computer program. The computer program product or the computer program includes computer instructions, and the computer instructions are 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 data processing method provided in various optional implementation manners of the above aspects.

[0211] Those of ordinary skill in the art can understand that all or part of the steps for implementing the above method embodiments can be completed by hardware related to program instructions. The foregoing program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps included in the above method embodiments; and the foregoing storage medium can be at least one of the following media: read-only memory (English: read-only memory, abbreviation: ROM), RAM, magnetic disk, or optical disc, etc., which can store program codes.

[0212] It should be noted that the various embodiments in this specification are described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other, and the key point of each embodiment is to illustrate the differences from other embodiments. In particular, for the device and system embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and reference can be made to the corresponding parts of the method embodiments for the relevant content. The device and system embodiments described above are only illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative efforts.

[0213] As described above, this is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by those skilled in the art within the technical scope disclosed in the present application should be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A data processing method, characterized in that, The method includes: Obtaining user feature data of the vehicle in the i-th cycle, where the user feature data is used to identify the user behavior generated by the target account of the vehicle through the Electronic Toll Collection (ETC) system; Determining the state probability of the target account in the (i + 1)-th cycle according to the user feature data, where the state probability is used to identify the probability that the target account is added to the ETC blacklist in the (i + 1)-th cycle, and the ETC blacklist is used to identify the accounts that are not allowed to use the ETC system; Obtaining the discount distribution weight of the target account in the (i + 1)-th cycle based on the state probability, where the discount distribution weight is used to identify the degree of association between the target account and different discount levels under the state probability; Determining the comprehensive discount rate of the target account in the (i + 1)-th cycle according to the discount distribution weight and the discount level, and determining the comprehensive discount rate as the discount rate corresponding to the target account for the ETC system in the (i + 1)-th cycle; Determining the level transition parameter between the discount levels identified based on the state probability of the account according to the up and down grade relationship between the discount levels; Determining the discount distribution sequence based on the level transition parameter, where the discount distribution sequence is used to identify the association relationship between the state probability of the account and the discount levels; The obtaining the discount distribution weight of the target account in the (i + 1)-th cycle based on the state probability includes: Obtaining the discount distribution weight of the target account in the (i + 1)-th cycle based on the state probability and the discount distribution sequence.

2. The method according to claim 1, wherein The user feature data includes the discount rate corresponding to the target account for the ETC system in the i-th cycle.

3. The method according to claim 1, wherein The determining the state probability of the target account in the (i + 1)-th cycle according to the user feature data includes: Determining the state probability of the target account in the (i + 1)-th cycle through a classification model according to the user feature data; The method further includes: Obtaining user sample data based on the cycle, where the user sample data includes the sample user behavior generated by the account of the vehicle through the ETC system in one cycle, and the label of the user sample data is used to identify whether the account of the vehicle is added to the ETC blacklist in the next cycle; Training an initial classification model according to the user sample data to obtain the classification model.

4. The method according to any one of claims 1 to 3, characterized in that, The determining the comprehensive discount rate of the target account in the (i + 1)-th cycle according to the discount distribution weight and the discount level includes: Taking the target discount level whose discount distribution weight in the discount level meets a preset condition as the comprehensive discount rate of the target account in the (i + 1)-th cycle; or, Obtaining the comprehensive discount rate of the target account in the (i + 1)-th cycle based on the influence degree of the discount distribution weight on the discount level.

5. The method according to any one of claims 1-3, characterized in that The state probability is also used to identify the probability that the target account is added to the ETC blacklist once or multiple times in the (i + 1)-th cycle.

6. The method according to claim 1, wherein The method further includes: Obtaining the map account associated with the target account; In the (i + 1)-th cycle, if it is determined that the electronic map application is enabled based on the map account, send the discount rate corresponding to the ETC system for the target account in the (i + 1)-th cycle to the electronic map application.

7. A data processing method, characterized in that, The method includes: In the (i + 1)-th cycle, enable the electronic map application based on the map account; If it is determined that the map account has an associated target account in the Electronic Toll Collection (ETC) system, display the discount information corresponding to the comprehensive discount rate for the ETC system for the target account in the (i + 1)-th cycle, where the comprehensive discount rate is determined according to the discount level of the ETC system and the discount distribution weight of the target account in the (i + 1)-th cycle, the discount distribution weight is determined based on the state probability of the target account in the (i + 1)-th cycle, the discount distribution weight is used to identify the degree of association between the target account and different discount levels under the state probability, the state probability is used to identify the probability that the target account is added to the ETC blacklist in the (i + 1)-th cycle, and the state probability is determined based on the user behavior generated by the target account of the vehicle through the ETC system in the i-th cycle; Among them, according to the promotion and demotion relationship between the discount levels, determine the level transfer parameter between the discount levels identified based on the state probability of the account; Determine the discount distribution sequence based on the level transfer parameter, where the discount distribution sequence is used to identify the association relationship between the state probability of the account and the discount levels; Determining the discount distribution weight based on the state probability of the target account in the (i + 1)-th cycle includes: obtaining the discount distribution weight of the target account in the (i + 1)-th cycle based on the state probability and the discount distribution sequence.

8. The method according to claim 7, wherein The method further includes: If it is determined that the map account has accounts of multiple vehicles in the ETC system, display the accounts of the multiple vehicles through the electronic map application; Determine the target account from the accounts of the multiple vehicles according to the selected operation.

9. A data processing device, characterized in that, The device includes: an acquisition unit, a state probability determination unit, a discount distribution weight acquisition unit, and a comprehensive discount rate determination unit; The acquisition unit is used to acquire the user feature data of the vehicle in the i-th cycle, where the user feature data is used to identify the user behavior generated by the target account of the vehicle through the Electronic Toll Collection (ETC) system; The state probability determination unit is used to determine the state probability of the target account in the (i + 1)-th cycle according to the user feature data, where the state probability is used to identify the probability that the target account is added to the ETC blacklist in the (i + 1)-th cycle, and the ETC blacklist is used to identify the accounts that are not allowed to use the ETC system; The discount distribution weight acquisition unit is used to obtain the discount distribution weight of the target account in the (i + 1)-th cycle based on the state probability, where the discount distribution weight is used to identify the degree of association between the target account and different discount levels under the state probability; The comprehensive discount rate determination unit is configured to determine the comprehensive discount rate of the target account in the (i + 1)-th period according to the discount distribution weight and the discount level, and determine the comprehensive discount rate as the discount rate of the target account corresponding to the ETC system in the (i + 1)-th period; The apparatus further includes a registration transfer parameter determination unit, configured to: Determine the level transfer parameter between the discount levels based on the status probability identifier of the account according to the promotion and demotion relationship between the discount levels; Determine a discount distribution sequence based on the level transfer parameter, where the discount distribution sequence is used to identify the association relationship between the status probability of the account and the discount levels; The discount distribution weight acquisition unit is configured to: Obtain the discount distribution weight of the target account in the (i + 1)-th period based on the status probability and the discount distribution sequence.

10. The device according to claim 9, wherein The user feature data includes the discount rate of the target account corresponding to the ETC system in the i-th period.

11. The device according to claim 9, characterized in that, The status probability determination unit is configured to: Determine the status probability of the target account in the (i + 1)-th period through a classification model according to the user feature data; The apparatus further includes a training unit, configured to: Obtain user sample data based on the period, where the user sample data includes sample user behaviors generated by the account of the vehicle passing through the ETC system in one period, and the label of the user sample data is used to identify whether the account of the vehicle is added to the ETC blacklist in the next period; Train an initial classification model according to the user sample data to obtain the classification model.

12. The device according to any one of claims 9-11, characterized in that, The comprehensive discount rate determination unit is configured to: Use the target discount level whose discount distribution weight in the discount level meets a preset condition as the comprehensive discount rate of the target account in the (i + 1)-th period; Or, Obtain the comprehensive discount rate of the target account in the (i + 1)-th period based on the influence degree of the discount distribution weight on the discount level.

13. The device according to any one of claims 9-11, characterized in that, The status probability is also used to identify the probability that the target account is added to the ETC blacklist once or multiple times in the (i + 1)-th period.

14. The device according to claim 9, characterized in that, The data processing apparatus further includes a sending unit, configured to: Obtain a map account associated with the target account; In the (i + 1)-th period, if it is determined that the electronic map application is enabled based on the map account, send the discount rate of the target account corresponding to the ETC system in the (i + 1)-th period to the electronic map application.

15. A data processing device, characterized in that, The apparatus includes: an opening unit and a display unit; The opening unit is configured to enable the electronic map application based on the map account in the (i + 1)-th period; The display unit is configured to, if it is determined that the map account has an associated target account in the electronic toll collection (ETC) system, display discount information corresponding to the comprehensive discount rate of the target account for the ETC system in the (i + 1)-th period. The comprehensive discount rate is determined based on the discount level of the ETC system and the discount distribution weight of the target account in the (i + 1)-th period. The discount distribution weight is based on the state probability of the target account in the (i + 1)-th period. The discount distribution weight is used to identify the degree of association between the target account and different discount levels under the state probability. The state probability is used to identify the probability that the target account is added to the ETC blacklist in the (i + 1)-th period. The state probability is based on the user behavior generated by the target account passing through the ETC system in the i-th period; The display unit is further configured to: Determine a level transition parameter between the discount levels identified based on the state probability of the account according to the up / down grade relationship between the discount levels; Determine a discount distribution sequence based on the level transition parameter. The discount distribution sequence is used to identify the association relationship between the state probability of the account and the discount levels; Determining the discount distribution weight based on the state probability of the target account in the (i + 1)-th period includes: obtaining the discount distribution weight of the target account in the (i + 1)-th period based on the state probability and the discount distribution sequence.

16. The device according to claim 15, characterized in that, The apparatus further includes a target account determination unit configured to: If it is determined that the map account has accounts of multiple vehicles in the ETC system, display the accounts of the multiple vehicles through the electronic map application; Determine the target account from the accounts of the multiple vehicles according to a selection operation.

17. A computer device, characterized in that, The device includes a processor and a memory: The memory is configured to store program code and transmit the program code to the processor; The processor is configured to execute the method according to any one of claims 1-6, or execute the method according to claim 7 or 8 according to the instructions in the program code.

18. A computer-readable storage medium, characterized in that, The computer-readable storage medium is configured to store a computer program, and the computer program is configured to execute the method according to any one of claims 1-6, or execute the method according to claim 7 or 8.

19. A computer program product, characterized in that, The computer program product includes instructions, and when the instructions run on a computer device, the computer device is caused to execute the method according to any one of claims 1-6, or execute the method according to claim 7 or 8.

Images