CN113409095A

CN113409095A - Data processing method, device, server and storage medium

Info

Publication number: CN113409095A
Application number: CN202110950420.6A
Authority: CN
Inventors: 钟子宏
Original assignee: Tencent Technology Shenzhen Co Ltd
Current assignee: Tencent Technology Shenzhen Co Ltd
Priority date: 2021-08-18
Filing date: 2021-08-18
Publication date: 2021-09-17
Anticipated expiration: 2041-08-18
Also published as: CN113409095B

Abstract

The application discloses a data processing method, a data processing device, a server and a storage medium, and relates to the technical field of Internet of vehicles. The data processing method is applied to a server and comprises the following steps: acquiring a user account of a vehicle; acquiring first data corresponding to a vehicle of a user account generated by an ETC system; determining target discount information based on a target probability which is obtained in advance, wherein the target probability is determined in advance according to historical data of sample users in the ETC system, the historical data comprises the number of times that each sample user is added into a blacklist, and the target probability is used for representing the probability that any user in the ETC system is added into the blacklist; and determining second data according to the target discount information and the first data, and initiating a data processing request for the user account based on the second data. Therefore, the discount information can be changed along with the number of times that the user account is added into the blacklist, and the discount information is more flexible.

Description

Data processing method, device, server and storage medium

Technical Field

The present application relates to the field of data processing technologies, and in particular, to a data processing method, an apparatus, a server, and a storage medium.

Background

The conventional ETC system usually processes user data of the ETC system by using a fixed discount, wherein the fixed discount is mainly determined according to industry experience, and the fixed discount mode is too single and cannot accurately meet the requirements of the ETC system.

Disclosure of Invention

The application provides a data processing method, a data processing device, a server and a storage medium, so as to overcome the defects.

In a first aspect, an embodiment of the present application provides a data processing method, which is applied to a server, and the method includes: acquiring a user account of a vehicle; acquiring first data corresponding to a vehicle of the user account generated by an ETC (electronic toll collection) system; determining target discount information based on a target probability which is obtained in advance, wherein the target probability is determined in advance according to historical data of sample users in the ETC system, the historical data comprises the number of times that each sample user is added into a blacklist, and the target probability is used for representing the probability that any user in the ETC system is added into the blacklist; and determining second data according to the target discount information and the first data, and initiating a data processing request for the user account based on the second data.

In a second aspect, an embodiment of the present application provides a data processing apparatus, which is applied to a server, and the apparatus includes: the device comprises a first acquisition unit, a second acquisition unit, a first determination unit and a second determination unit. The system comprises a first acquisition unit, a second acquisition unit and a control unit, wherein the first acquisition unit is used for acquiring a user account of a vehicle; a second acquisition unit configured to acquire first data corresponding to a vehicle of the user account generated by an Electronic Toll Collection (ETC) system; a first determination unit, configured to determine target discount information based on a target probability acquired in advance, where the target probability is determined in advance according to historical data of sample users in the ETC system, the historical data includes the number of times each sample user is added to a blacklist, and the target probability is used for representing the probability that any user in the ETC system is added to the blacklist; and the second determining unit is used for determining second data according to the target discount information and the first data and initiating a data processing request for the user account based on the second data.

In some embodiments of the present application, based on the foregoing solution, the data processing apparatus further includes: the first prediction unit is used for determining the average number of times of adding each sample user into a blacklist according to the number of times of adding each sample user into the blacklist in the historical data; and the second prediction unit is used for predicting the probability of any user being added into a blacklist in the ETC system by using Poisson distribution based on the average times, and taking the probability as the target probability.

In some embodiments of the present application, the blacklist includes user accounts which do not process the present to-be-processed data generated by the ETC system within a specified time period, where the specified time period corresponds to the present to-be-processed data, and the first determining unit includes: the device comprises an initial discount acquisition unit, a first adjustment unit, a discount grade determination unit and a target discount determination unit. The initial discount obtaining unit is used for obtaining a plurality of initial discount information; the first adjusting unit is used for adjusting the plurality of initial discount information based on the target probability to obtain a plurality of reference discount information, wherein each reference discount information corresponds to one discount level, and the target probability is inversely related to the plurality of reference discount information; the discount grade determining unit is used for determining a target discount grade used when the user account currently processes the data processing request based on historical data of the user account; the target discount determination unit is used for acquiring the target discount information corresponding to the target discount grade from the plurality of reference discount information.

In some embodiments of the present application, based on the foregoing scheme, the discount level determination unit includes, with reference to that the discount information is positively correlated with the discount level: the historical discount acquisition unit is used for determining the historical discount grade used when the user account processes to-be-processed data generated by the ETC system last time; and the target level determining unit is used for determining a target discount level used when the data processing request is currently processed by the user account according to a predetermined level transfer rule, the historical data of the user account and the historical discount level, wherein the level transfer rule specifies that the target discount level is in a negative correlation with the historical data of the user account.

In some embodiments of the present application, based on the foregoing solution, the first adjusting unit includes: a distribution probability determination unit configured to determine a distribution probability of the plurality of reference discount information based on the target probability, the distribution probability being used to indicate a probability that each of the reference discount information is used by the any user; and the second adjusting unit is used for adjusting the plurality of reference discount information according to the plurality of initial discount information and the distribution probability.

In some embodiments of the present application, based on the foregoing scheme, the distribution probability determining unit includes: a matrix determining unit, configured to determine, based on the target probability, a state transition matrix for characterizing a probability of mutual transition among a plurality of discount levels, where the state transition matrix is used for characterizing that the discount level of any user is in a negative correlation with the target probability of any user; and the distribution probability determining subunit is used for obtaining the distribution probability of the plurality of pieces of reference discount information in a steady state according to the state transition matrix, wherein in the steady state, the probability of using each piece of reference discount information by any user is kept unchanged before and after the mutual transition among the discount grades.

In some embodiments of the present application, based on the foregoing scheme, with reference to that the discount information is positively correlated with the discount level, the matrix determination unit includes: a probability determination unit, configured to determine a first probability that the any user is not added to a blacklist based on the target probability, where the target probability is a second probability; a first transition probability determining unit, configured to, if the any user is at a lowest level of the discount levels, set a probability that the any user keeps the lowest level unchanged as the second probability, set a probability that the any user rises to an adjacent level as the first probability, and set a probability that the any user rises to another level as zero, so as to obtain a transition probability corresponding to the lowest level; a second transition probability determining unit, configured to set, if the any user is at a highest level of the discount levels, a probability that the any user falls to an adjacent level as the second probability, set, as the first probability, a probability that the any user keeps the highest level unchanged, and set, as the zero, a probability that the any user falls to another level, so as to obtain a transition probability corresponding to the highest level; a third transition probability determining unit, configured to set, if the any user is at an intermediate discount level between the lowest level and the highest level, a probability that the any user falls to an adjacent level to the second probability, a probability that the any user rises to the adjacent level to the first probability, and probabilities that the any user maintains the intermediate discount level and transitions to another level to zero, so as to obtain transition probabilities corresponding to the intermediate discount level; a matrix determination subunit, configured to generate the state transition matrix from the transition probability corresponding to the lowest level, the transition probability corresponding to the highest level, and the transition probability corresponding to the intermediate discount level.

In some embodiments of the present application, based on the foregoing solution, the second adjusting unit includes: the second adjustment subunit is used for determining the predicted values and unbiased estimated values of the plurality of reference discount information according to the distribution probability; and the optimal discount determining unit is used for calculating optimal discount information which enables the deviation between the predicted value and the unbiased estimated value to meet a preset threshold condition on the basis of the initial discount information to serve as the reference discount information.

In some embodiments of the present application, based on the foregoing solution, the second adjusting subunit includes: a first iteration unit for iteratively updating the plurality of initial discount information based on the distribution probability; and the second iteration unit is used for determining the weighted sum of the plurality of initial discount information and the distribution probability before each iteration update as the unbiased estimation value, and determining the plurality of initial discount information obtained after each iteration update as the predicted value.

In a third aspect, an embodiment of the present application provides a server, including: one or more processors; a memory; one or more application programs, wherein the one or more application programs are stored in the memory and configured to be executed by the one or more processors, the one or more application programs configured to perform the data processing methods described above.

In a fourth aspect, the present application provides a computer-readable storage medium, in which a program code is stored, where the program code can be called by a processor to execute the above data processing method.

In a fifth aspect, embodiments of the present application provide a computer program product or a computer program comprising computer instructions stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions to cause the computer device to perform the above-described method.

According to the data processing method, the data processing device, the server and the storage medium, after a user account of a vehicle and first data which are generated by an ETC (electronic toll collection) system and correspond to the vehicle of the user account are acquired, target discount information is determined based on a pre-acquired target probability, wherein the target probability is determined in advance according to historical data of sample users in the ETC system, the historical data comprise the number of times that each sample user is added into a blacklist, the target probability is used for representing the probability that any user in the ETC system is added into the blacklist, then second data are determined according to the target discount information and the first data, and finally a data processing request is initiated for the user account based on the second data. Therefore, discount information used when the data processing request initiated in the ETC system is processed by the user account bound with the vehicle can be determined according to the probability that the user account is added into the blacklist, which is obtained by historical data estimation, so that the discount information can be changed along with the number of times that the user account is added into the blacklist, and the discount information is more flexible.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

Fig. 1 is a schematic view illustrating an application scenario of a data processing method according to an embodiment of the present application.

Fig. 2 is a schematic flowchart illustrating a data processing method according to an embodiment of the present application.

Fig. 3 is a schematic diagram illustrating a system architecture of a data processing method according to an embodiment of the present application.

Fig. 4 is a schematic flowchart illustrating a data processing method according to another embodiment of the present application.

Fig. 5 is a flowchart illustrating step S440 in the data processing method according to an embodiment of the present application.

Fig. 6 is a schematic flowchart illustrating step S441 in a data processing method according to another embodiment of the present application.

Fig. 7 is a flowchart illustrating step S442 in a data processing method according to another embodiment of the present application.

Fig. 8 is a flowchart illustrating step S450 of a data processing method according to another embodiment of the present application.

Fig. 9 shows a flow chart of a data processing method according to an embodiment of the present application.

Fig. 10 is a block diagram showing a data processing apparatus according to an embodiment of the present application.

Fig. 11 shows a block diagram of a server according to an embodiment of the present application.

Fig. 12 shows a block diagram of a computer-readable storage medium according to an embodiment of the present application.

Detailed Description

In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application.

Currently, in an Electronic Toll Collection (ETC) system, a fixed discount is generally used for processing user data of a user account in the ETC system. With the continuous development of computer technology, the operation strategy made by the operation unit of the ETC system changes more and more rapidly, but the fixed discount mode is too single to meet the multiple requirements of the ETC system at the same time. The user data may be account data of a user account bound to the vehicle in the ETC system, and the account data may include vehicle identification information, vehicle mileage information, a to-be-paid fee of the vehicle generated by the ETC system, an account balance, and the like.

The inventor finds that the discount information can be adaptively changed according to the number of times that a user account in the ETC system is added into a blacklist by collecting user data in the ETC system by using a computer technology, so that the discount information is more flexible, and a more reliable information source can be provided for data decision of an operation unit. Therefore, the inventor proposes a data processing method, a data processing device, a server and a storage medium.

The system architecture of a server to which the present application relates will be described below.

Referring to fig. 1, fig. 1 is a schematic diagram illustrating an application scenario of a data processing method according to an embodiment of the present application. In some embodiments of the present application, the data processing method may be applied to a server in an Electronic Toll Collection (ETC) system, taking as an example that the vehicle 140 using the ETC system passes through an exit gate. In the application scenario of the internet of vehicles, when a vehicle 140 enters a road section such as a high speed or a bridge, the vehicle 140 may pass through an entrance gate and an exit gate, the entrance gate and the exit gate are usually equipped with communication devices 130, and may respectively collect vehicle identification information, entrance information, and exit information of the vehicle 140, and according to the entrance information and the exit information, vehicle data such as a vehicle driving path, vehicle mileage information, and the like of the vehicle 140 may be calculated and obtained, the communication devices 130 may transmit the vehicle identification information, the entrance information, the exit information, the vehicle data, and the like to a server, and the server may obtain a user account number associated with the vehicle 140 through the vehicle identification information, and then process data related to the vehicle 140 in the user account number according to the information such as the entrance information, the exit information, the vehicle data, and the like. It is understood that a user may log in a user account associated with the vehicle 140 by using one or more electronic devices 110, and the user may perform corresponding processing operations on the data processing request sent by the server through the electronic devices 110, wherein data interaction between the electronic devices 110 and the server 120 and between the communication device 130 and the server 120 may be performed in a wired or wireless manner.

It should be noted that the electronic device 110 may be a mobile terminal, a smart phone, a portable game device, a laptop computer, a PDA, a portable internet device, a music player, a data storage device, a vehicle-mounted smart terminal, and the like.

As one way, the electronic device 110 may be a handheld device, an in-vehicle smart terminal, or the like having a wireless connection function. Alternatively, the electronic device 110 may be a mobile phone, a tablet computer, a notebook computer, a palm computer, a wearable device, a Virtual Reality (VR) device, an Augmented Reality (AR) device, a wired or wireless terminal in industrial control, a wireless terminal in unmanned driving, a wired or wireless terminal in smart home, and the like, which is not limited herein.

The server 120 may be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, a cloud server providing basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a Network service, cloud communication, a middleware service, a domain name service, a security service, a CDN (Content Delivery Network), a big data and an artificial intelligence platform, or a dedicated or platform server providing a car networking service, a road Network cooperation, a vehicle road cooperation, intelligent transportation, automatic driving, an industrial internet service, and data communication (such as 4G, 5G).

Referring to fig. 2, fig. 2 is a schematic flowchart illustrating a data processing method according to an embodiment of the present application, where the data processing method can be applied to the server 120 shown in fig. 1. The method comprises the following steps: s210 to S240.

Step S210: a user account of the vehicle is obtained.

In some embodiments, the server may obtain vehicle identification information sent by the communication device in the ETC system, and based on the vehicle identification information, the server may search for a user account associated with the vehicle by querying a database, and the like, and may use the user account as the user account of the vehicle. In other embodiments, the user may actively send the user account associated with the vehicle to the server directly through an electronic device such as a vehicle-mounted smart terminal. It will be appreciated that in some embodiments, the user account and the vehicle may be in a one-to-one, one-to-many, or many-to-many relationship, and in the case of a one-to-many relationship, the same user account may be associated with multiple vehicles, but only one user account may be associated with one vehicle at a time.

Step S220: first data corresponding to a vehicle of the user account generated by an ETC system is acquired.

In an embodiment of the present application, the server may acquire first data corresponding to a vehicle of the user account generated in the ETC system. The first data may include one or more types of information such as a vehicle travel path of the vehicle, vehicle mileage information, and the like.

In some embodiments, the server may obtain the first data from a communication device in the ETC system. For example, when a vehicle passes through the communication equipment of the entrance gate, the data acquisition equipment such as a camera and an infrared sensing device which are communicated with the communication equipment can acquire vehicle identification information by scanning a license plate and the like, when the vehicle passes through one communication equipment, the communication equipment can correlate and record the current passing position, time and the like of the vehicle with the vehicle identification information of the vehicle, and then the server can obtain first data by comparing the recorded position, time and the like of each communication equipment through which the vehicle passes.

In other embodiments, the server may further obtain the first data from an in-vehicle intelligent terminal carried by the vehicle. For example, in the vehicle driving process, the intelligent vehicle-mounted terminal can record information such as a vehicle driving path and vehicle mileage information in a real-time positioning mode and the like, and then transmit the information to the server as first data through the communication equipment on the road side in the internet of vehicles.

In the embodiment of the present application, the first data may also be vehicle charging information. For example, if the ETC system is applied to parking lot management, the first data may be parking charge information of the vehicle; if the ETC system is applied to a highway or a bridge scenario, the first data may be route charging information of the vehicle, or the like.

Step S230: and determining target discount information based on a target probability which is obtained in advance, wherein the target probability is determined in advance according to historical data of sample users in the ETC system, the historical data comprises the number of times that each sample user is added into a blacklist, and the target probability is used for representing the probability that any user in the ETC system is added into the blacklist.

In the embodiment of the application, after the user account of the vehicle and the first data corresponding to the vehicle generated by the ETC system are acquired, the server determines the target discount information based on the pre-acquired target probability.

In some embodiments, the pre-acquired target probability may be determined based on historical data of sample users in the ETC system. The sample user may be all user accounts in the ETC system, or may be a part of user accounts extracted from all user accounts of the ETC system, which is not limited in the embodiment of the present application. As an embodiment, the historical data may include the number of times each sample user is blacklisted, and correspondingly, the target probability is used to characterize the probability that any user in the ETC system is blacklisted.

For example, in order to ensure that a user in the ETC system can use the user account according to the specification, an operation unit of the ETC system can make punishment rules for the user account with abnormality under the condition that the user knows the user. For example, the user account with the abnormality may be added to a blacklist, where the use of the user account added to the blacklist may also be limited to a certain extent, for example, the user account added to the blacklist may not use part of services provided by the ETC system. The case that the user account is added to the blacklist due to the occurrence of the abnormality includes, but is not limited to, the following situations: abnormality occurs in user data of a user account, for example, the account balance of the user account is insufficient for a long time; the user account does not process the data generated by the ETC system in time, if the cost generated by the ETC system is not paid in time; and abnormal behaviors of the vehicle bound with the user account, such as violation of countercrossing rules and the like, occur.

If the ETC system has abnormal user accounts or the number of times of abnormality of each user account is increased gradually, correspondingly, except for restricting the abnormal behaviors by adding the user accounts into the blacklist, the current use discount information of each user account in the ETC system can be adjusted according to the historical condition that the user accounts are added into the blacklist. In an embodiment of the application, a probability that any user in the ETC system is added to the blacklist may be estimated based on the number of times each sample user is added to the blacklist in the historical data, the probability is taken as a target probability, and then target discount information may be determined according to the target probability. Wherein the target discount information may indicate the degree of discount available to the user. Alternatively, the larger the targeted discount information, the more discounts are available to the user; conversely, the smaller the targeted discount information, the less discount the user may receive.

For example, the higher the target probability is, the more abnormal behaviors of the user account in the ETC system can be represented, and the discount strength of the ETC system can be correspondingly reduced, which means that the discount available to the user becomes less, and the discount can be used as a penalty for frequently adding the user account into a blacklist, so that the purpose of restricting the abnormal behaviors of the user account is achieved to a certain extent. For example, the discount rate used when the target probability is 0.2 is 8, the target discount information corresponding to the discount available to the user may be 0.2, if the target probability is increased to 0.3, the target discount information is decreased when the target probability is increased, the discount rate may be increased correspondingly, for example, the discount rate may be adjusted to 9, and the target discount information corresponding may be 0.1. Alternatively, the target discount information may be in the form of the discount rate, or in other forms in different application scenarios. For example, the target discount information may be in the form of a coupon, and in this case, if the target probability is higher, the target discount information may be reduced, that is, the discount amount of the coupon is reduced, and the discount available to the user is reduced. In addition, different discount criteria can be established in different application scenarios, for example, different discount information can be established for different time periods.

Step S240: and determining second data according to the target discount information and the first data, and initiating a data processing request for the user account based on the second data.

In the embodiment of the present application, after the target discount information is determined, the second data may be determined according to the target discount information and the first data. As an embodiment, the server may initiate a data processing request for the user account of the vehicle based on the second data, where according to the data processing request, the user may process the user data of the user account of the vehicle according to the second data, and the like.

For example, if the first data includes one or more of the vehicle travel path of the vehicle, the vehicle mileage information, etc., the second data may be the amount to be paid for the vehicle. For example, the vehicle charging information of the vehicle may be calculated according to the driving path of the vehicle, the vehicle mileage information, and the like, and the fee to be paid for the vehicle may be determined based on the vehicle charging information and the target discount information. Wherein the second data may be determined by multiplying the target discount information by the vehicle charge information if the target discount information is in the form of the discount rate; if the targeted discount information is in the form of a coupon, the second data may be determined by the cost of the vehicle charging information minus the coupon's amount. Taking an example that the ETC system is applied to a charging scene of an expressway or a bridge, if the vehicle mileage information of the vehicle C after passing through a section of high speed is 100 kilometers, and the charging standard of the section is x per kilometer, the corresponding vehicle charging information is 100x, the target discount information is calculated in a discount rate manner, and if the target discount information obtained by calculation according to the above embodiment is y, wherein y is greater than zero and less than 1, the fee to be paid for the vehicle can be a product of 100x and y.

After determining the fee to be paid, the server may initiate a debit request to a user account of the vehicle based on the fee to be paid. In some embodiments, the account balance of the user account may be updated based on the deduction request, for example, the current account balance is updated to the account balance after deducting the to-be-paid fee, and the like. Optionally, the server may be a payment server, and the fee to be paid may be deducted directly from the user account of the vehicle; the server may also be a data server, and may notify a payment server to deduct the fee to be paid from the user account of the vehicle. In addition, as shown in fig. 3, the server 120 may further send a fee deduction request to the electronic device 110 bound with the user account of the vehicle, and after the electronic device 110 receives the fee deduction request, if the account balance of the user account of the vehicle is less than the fee to be paid, which means that the processing of the fee deduction request fails, the user may be prompted to recharge the fee on the electronic device 110.

It is understood that, in the embodiment of the present application, the form of the target discount information is not limited, the discount information may be determined based on the pre-obtained target probability, and the second data is obtained according to the discount information and the first data of the vehicle, and a data processing request may be initiated for the user account of the vehicle based on the second data, so that the discount information is referred to as the target discount information in the embodiment of the present application.

To sum up, the data processing method that this application provided, after the user account number that acquires the vehicle and through the first data that the ETC system of electronic toll collection produced with the vehicle of user account number corresponds, target discount information is confirmed based on the target probability that acquires in advance, wherein, target probability is according to in advance the historical data of the sample user in the ETC system and confirms, the historical data includes the number of times that every sample user is added into the blacklist, target probability is used for the characterization the probability that any user is added into the blacklist in the ETC system, then according to target discount information with the second data is confirmed to first data, and is based on at last the second data is right the user account number initiates the data processing request. Therefore, discount information used when the data processing request initiated in the ETC system is processed by the user account bound with the vehicle can be determined according to the probability that the user account is added into the blacklist, which is obtained by historical data estimation, so that the discount information can be changed along with the number of times that the user account is added into the blacklist, and the discount information is more flexible.

Referring to fig. 4, fig. 4 is a schematic flow chart illustrating a data processing method according to another embodiment of the present application. The data processing method may be applied to the server 120 shown in fig. 1, for example. As will be described in detail with respect to the flow shown in fig. 4, the data processing method may specifically include: s410 to S470.

Step S410: a user account of the vehicle is obtained.

In the embodiment of the present application, step S410 may refer to the contents of the foregoing embodiments, and is not described herein again.

Step S420: first data corresponding to a vehicle of the user account generated by an ETC system is acquired.

In the embodiment of the present application, step S420 may refer to the contents of the foregoing embodiments, and is not described herein again.

Step S430: a plurality of initial discount information is obtained.

In embodiments of the present application, the target discount information may be related to the initial discount information in addition to the target probability. In some embodiments, the initial discount information may be determined according to actual operation conditions of an ETC system operation unit. For example, if the operation unit determines that discount information that can be provided by the unit is 9-fold according to the past operation situation, the plurality of pieces of initial discount information may be determined to be 9-fold. In other embodiments, because the discount information determined by the operation unit may not reflect the actual operation situation, in this embodiment of the application, the discount information determined by the operation unit may also be adjusted based on the historical operation situation, and the adjusted discount information is used as a plurality of initial discount information.

Step S440: adjusting the plurality of initial discount information based on the target probability to obtain a plurality of reference discount information, wherein each reference discount information corresponds to a discount level, and the target probability is inversely related to the plurality of reference discount information.

As can be seen from the foregoing description of the embodiments, the target probability is determined in advance according to the historical data of the sample users in the ETC system, and represents the probability that any user in the ETC system is added to the blacklist. In some embodiments, the blacklist may include a user account number that does not process the current to-be-processed data generated by the ETC system within a specified period of time, where the specified period of time corresponds to the current to-be-processed data.

For example, the data to be processed may be data that needs to be processed by a user and is generated by the ETC system, and for example, the second data generated in the embodiment of the present application may be used as the data to be processed. If the to-be-processed data is the to-be-paid fee of the vehicle, in some embodiments, the ETC system may support the user account of the vehicle to complete the processing of the fee deduction request corresponding to the to-be-paid fee within a specified time period. For example, a fee to be paid is generated according to the travel of the vehicle C on the day, a fee deduction request is initiated for the user account of the vehicle C for the fee to be paid, and it may be agreed that the user account of the vehicle C is added to the blacklist when the fee deduction request is not processed yet at 24 o' clock of the day, and the user account of the vehicle C is not released from the blacklist until the fee deduction request is processed completely. The fee deduction request deducts the fee to be paid from the account balance of the user account of the vehicle C, and if the account balance is larger than or equal to the fee to be paid, the fee to be paid can be directly deducted from the account balance according to the fee deduction request; if the account balance is less than the charge to be paid, the user can be prompted to recharge the charge, and if the account balance after the charge recharging is more than or equal to the charge to be paid, the charge to be paid can be directly deducted from the account balance after the charge recharging according to the fee deduction request. It will be appreciated that in this embodiment, the deduction request may be counted as processing completion until the fee to be paid is deducted successfully, and thus the number of times the user account is blacklisted may correspond to the number of times the data to be processed generated by the ETC system is not processed within a specified period of time. In addition, each item of data to be processed corresponds to a specified time interval, which means that when counting the number of times that the user account is added into the blacklist, if each item of data to be processed is not completed for a long time, the data to be processed can be added into the blacklist only in the initial counting, so that the situation of repeated counting is avoided.

For example, the probability that any user in the ETC system is added to the blacklist can be predicted by using the poisson distribution, and the predicted probability is used as the target probability. In some embodiments, the number of times each sample user is blacklisted in the sample user's historical data is first counted, and then the average number of times the sample user is blacklisted is determined. For example, the average number of times a sample user is blacklisted may be obtained by dividing the sum of the number of times each sample user is blacklisted by the total number of sample users. The average number of times a sample user is blacklisted may then be used as the average number of times any user in the ETC system is likely to be blacklisted, and as a mathematical expectation of poisson distribution, using an unbiased estimation approach

Wherein X is used to indicate the number of times any user in the ETC system may be blacklisted.

Further, the probability that any user in the ETC system is added into the blacklist can be estimated according to the Poisson distribution, and the probability that any user is not added into the blacklist is recorded as the probability that any user is not added into the blacklist

Wherein

. Furthermore, the probability that any user in the ETC system is added into the blacklist for more than or equal to 1 can be predicted, the probability can be taken as the probability that any user is added into the blacklist, namely the target probability, and the target probability can be recorded as the probability

Wherein

。

In an embodiment of the application, before determining the target discount information of the user account, a plurality of initial discount information may be further adjusted based on the target probability to obtain a plurality of reference discount information, where each reference discount information corresponds to one discount level. In order to ensure the normal operation of an ETC system operation unit, when the abnormal behaviors of the user account number are more and the target probability is higher, the reference discount information of the ETC system can be correspondingly reduced, and the target probability and the reference discount information can be in a negative correlation relationship.

For example, the initial discount information may represent an actual operating state of an operating unit of the ETC system, and as the abnormal behavior of the user account changes, the target probability increases or decreases, both of which may affect the operating condition of the operating unit. In some embodiments, the initial discount information may be adjusted periodically based on the target probability, for example, the sample user and the historical data of the sample user are collected once every preset time interval, and then the target probability is updated periodically according to the historical data of the sample user, and the initial discount information may be adjusted again according to the updated target probability every preset time. It should be noted that, since the operation status of the operation unit may change within each preset time, the initial discount information of each period may be updated correspondingly.

For convenience of description, a preset time may be referred to as a period, where the preset time may be set according to actual needs of an operation unit, for example, the period may be set to be one week, one month, or one quarter. In some embodiments, the last cycle may be referred to as a t-th cycle, a cycle in which the first data corresponding to the vehicle is obtained may be referred to as a t + 1-th cycle, and then the plurality of reference discount credits for the t + 1-th cycleInformation processing device

Target probability calculated according to historical data of the t period sample user

And a plurality of initial discount information given in the t +1 th period

Calculated, where m represents the number of levels of the discount level. Specifically, referring to fig. 5, step S440 may include: s441 to S442.

Step S441: determining a distribution probability of the plurality of reference discount information based on the target probability, wherein the distribution probability is used for representing the probability of each reference discount information used by any user.

If the target probability is higher, the frequency that the user account is added into the blacklist in the sample user is high, the abnormal behaviors of the user account are more, and the discount strength of the operation unit can be reduced for ensuring the benefit of the operation unit. In some embodiments, a distribution probability representing a probability that the user account in the ETC system uses each of the reference discount information may be adjusted according to the target probability, for example, when the target probability is increased, the distribution probability may be appropriately decreased, and the like. Specifically, referring to fig. 6, step S441 may include: s4411 to S4412.

Step S4411: and determining a state transition matrix for representing the probability of mutual transition among a plurality of discount grades based on the target probability, wherein the state transition matrix is used for representing that the discount grade of any user is in a negative correlation with the target probability of any user.

As one way, in order to better restrict the abnormal behavior of the user account, the discount information of the user account which is blacklisted more times may be reduced. Illustratively, the relationship between the discount level of the user account and the target probability can be represented by constructing a state transition matrix, wherein the higher the target probability is, the higher the discount level of the user account isThe lower the discount level will be. The state transition matrix represents the probability of mutual transition among a plurality of discount levels in the ETC system, and it can be understood that if the number of the discount levels is m, the state transition matrix can be m

Of the matrix of (a).

As an example, the target probability may be based on a negative correlation between the discount level of the user account and the target probability

A state transition matrix P is determined.

For example, for any user a in the ETC system, a first probability that the user account a is not blacklisted in the t +1 th period can be predicted based on a target probability, and a probability that the user account a is blacklisted in the t +1 th period is recorded as a second probability, where the first probability can be, for example, the first probability

The second probability may be, for example

。

Further, a corresponding transition probability is determined when the user account a is at the lowest of the discount levels. Illustratively, assume that the discount levels include: the 1 st rank, the 2 nd rank, the 3 rd rank, …, and the m th rank, the 1 st rank being the lowest rank, and the m th rank being the highest rank.

If the user account a is in the lowest level, i.e., level 1, of the discount levels, if the user account a is added to the blacklist in the t period, since the user account a is already in the lowest level 1, the discount level of the user account a will remain unchanged, and the probability that the user account a remains unchanged in the lowest level

Is a second probability

I.e. by

(ii) a If the user account A is not blacklisted within the tth period, the user account A will increase by a discount level, and the probability that the user account A increases from the 1 st level to the 2 nd level

First probability for user account A

I.e. by

(ii) a If the individual discount levels cannot be skipped before, the probability of the discount level rising from the 1 st level to a level other than the 2 nd level is 0, that is

。

Further, a corresponding transition probability is determined when the user account a is at the highest of the discount levels. Illustratively, if the user account A is at the highest level of the discount levels, i.e., the mth level, if the user account A is blacklisted within the tth period, the discount level of the user account A is lowered by one level, and the user account A is lowered from the mth level to the mth level

Probability of grade

(ii) a If the user account a is not added to the blacklist within the t-th period, because the user account a is already in the highest m-th level, the user account a keeps the highest level unchanged, and then the probability that the user account a keeps the highest level unchanged

(ii) a If the discount levels cannot be skipped before, the level is lowered from the m-th level to the m-th level

The probability of a discount level outside the level is 0, i.e.

。

Still further, a transition probability is determined corresponding to when the user account a is at an intermediate discount level between the lowest level and the highest level. Illustratively, if the user account A is at the f-th level, where

If the user account A is blacklisted within the tth period, the discount level of the user account A is lowered by one level, and the user account A is lowered from the fth level to the fth level

Probability of grade

(ii) a If the user account A is not blacklisted within the t-th period, the discount level of the user account A is raised by one level, and the user account A is raised from the f-th level to the f-th level

Probability of grade

(ii) a Since the discount levels cannot jump before, the probability of shifting from the f-th level to the discount levels other than the f-1 th level and the f +1 th level is 0, that is

。

Then theTransition probability corresponding to the lowest level

、

、

Highest level corresponding transition probability

、

、

And transition probabilities corresponding to intermediate discount levels

、

、

The state transition matrix P is generated as follows:

it is to be understood that the state transition matrix may be determined according to the target probability, the calculation process of the state transition matrix described in this embodiment is only an exemplary illustration, and is not limited thereto, and the state transition matrix may also be changed according to the actual operation policy of the operation unit.

Step S4412: and obtaining the distribution probability of the plurality of reference discount information in a steady state according to the state transition matrix, wherein in the steady state, the probability of using each reference discount information by any user is kept unchanged before and after the mutual transition among the discount grades.

In some embodiments, the distribution probability of the plurality of reference discount information in the steady state can be obtained according to the state transition matrix determined in the above steps. In a steady state, the probability of any user in the ETC system using each of the reference discount information may be kept constant, that is, the distribution probability may be kept constant in the steady state. For ease of illustration, the distribution probability can be recorded as

，

Wherein, in

For the purpose of example only,

means that any user uses the reference discount information corresponding to the 1 st level

The probability of (c). Illustratively, steady state equations of the distribution probabilities may be constructed from the state transition matrices in steady state, and the distribution probabilities are obtained by solving the steady state equations

E.g. the steady state equation may be

Where P is a state transition matrix, which can be calculated from the target probability in step S4411.

Step S442: and adjusting the plurality of reference discount information according to the plurality of initial discount information and the distribution probability.

In some embodiments, a plurality of reference discount information may be obtained according to the initial discount information and the distribution probability adjustment calculated in the above steps. For example, the initial discount information may be adjusted iteratively from the initial discount information, a deviation between the discount information before and after each adjustment is calculated, optimal discount information in which the deviation satisfies a preset threshold condition under a preset constraint condition is obtained, and the optimal discount information in which the deviation satisfies the preset constraint condition may be used as the plurality of reference discount information. Specifically, referring to fig. 7, step S442 may include: s4421 to S4422.

Step S4421: and determining the predicted values and unbiased estimated values of the plurality of reference discount information according to the distribution probability.

In some approaches, the deviation between the discount information before and after the iterative adjustment may be represented by constructing a loss function. The discount information before adjustment may be referred to as actual values of the plurality of reference discount information, and the discount information after adjustment may be referred to as predicted values of the plurality of reference discount information. Optionally, in this embodiment of the application, unbiased estimated values of a plurality of pieces of reference discount information may be used as real values, and a loss function of the discount information may be constructed by calculating a weighted sum of squares between predicted values and unbiased estimated values of the plurality of pieces of reference discount information. Illustratively, the loss function may be

Wherein

Refers to a predicted value referring to the discount information,

refers to an unbiased estimated value of the reference discount information,

is a pre-set parameter of the process,

is a distribution probability

Square of the first order norm. It will be appreciated that, according to the foregoing embodiment, the preset constraint condition may include a distribution probability

The sum being 1, i.e.

And is and

. In addition, since the mathematical expectation of the predicted value of the parameter to be predicted can be used as the true value of the parameter to be predicted in the unbiased estimation manner, a plurality of initial discount information obtained after each iteration update can be determined as the predicted value, and the weighted sum of the plurality of initial discount information and the distribution probability before each iteration update can be determined as the unbiased estimation value, for example, the unbiased estimation value

。

Step S4422: calculating optimal discount information, which enables the deviation between the predicted value and the unbiased estimated value to meet a preset threshold condition, based on the initial discount information, and using the optimal discount information as the reference discount information.

In the embodiment of the present application, a loss function can be constructed

Wherein

The deviation between the predicted value and the unbiased estimated value may be reflected. Illustratively, a plurality of initial discount information can be iteratively updated according to the target probability, and the initial discount information is obtained by iterative update calculation

Is full ofAnd the optimal discount information which is enough for the preset threshold condition is used as a plurality of reference discount information. Alternatively, the predetermined threshold condition may be that the deviation between the predicted value and the unbiased estimated value is minimal, and a predetermined convergence threshold may be set to apply the loss function

If the unbiased estimated value is the weighted sum of the initial discount information and the distribution probability before each iteration update, the predicted value of the reference discount information obtained after each iteration update is close to the weighted sum of the initial discount information and the distribution probability before each iteration update. Alternatively, the penalty function may be scaled according to a predetermined threshold condition

The derivation results in an iterative formula for the reference discount information, which may be, for example:

wherein,

represents the predicted value of the reference discount information at the ith level obtained by updating the (n + 1) th iteration,

indicating the predicted value of the reference discount information at the j level obtained by the n iteration updates, the arrow indicates that in the (n + 1) th iteration update calculation process,

can be prepared from

And (6) calculating.

Illustratively, at iteration 1 update,

can distribute probability

And initial discount information

Substituting into the above iterative formula to obtain

And

as unbiased estimate of the 1 st iteration

Substituting into the loss function

Calculating to obtain the deviation of the 1 st iteration

And comparing

And a predetermined convergence threshold, if

If the convergence threshold is greater than or equal to the preset convergence threshold, the iteration will continue. It will be appreciated that the probability distribution can be applied in each subsequent iteration

And predicted value generation of reference discount information obtained from previous iterationCalculating to obtain the predicted value of the reference discount information of the current iteration by using an iteration formula, and then calculating the predicted value

And taking the weighted sum of the predicted values of the reference discount information obtained in the previous iteration as an unbiased estimated value of the current iteration, then substituting the predicted value and the unbiased estimated value of the current iteration into a loss function to calculate the deviation until the deviation is smaller than a preset convergence threshold value, taking the predicted value when the deviation is smaller than the preset convergence threshold value as the optimal discount information, and finally taking the optimal discount information as a plurality of reference discount information

。

It will be appreciated that the loss function will be described in accordance with embodiments of the present application

Is less than a preset convergence threshold as a preset threshold condition, and a plurality of reference discount information is obtained at the moment

According to the foregoing embodiment, the distribution probability can be calculated from the target probability, and if the target probability is higher, the plurality of corresponding reference discount information are represented as being larger than the plurality of corresponding initial discount information, so that the target probability and the reference discount information are in a negative correlation relationship.

Step S450: and determining a target discount grade used when the data processing request is processed currently by the user account based on the historical data of the user account.

As can be seen from the foregoing embodiments, each piece of reference discount information corresponds to one discount level, and the target discount level to be currently used by the vehicle corresponding to the first data from the plurality of pieces of reference discount information may be determined first when the user account currently processes the data processing request. In some embodiments, the target discount level at which the user account is currently processing the data processing request is related to historical data of the user account. Specifically, referring to fig. 8, step S450 may include: s451 to S452.

Step S451: and determining the historical discount grade used when the user account processes the data to be processed generated by the ETC system last time by referring to the positive correlation between the discount information and the discount grade.

In some embodiments, the target discount level may be determined according to a historical discount level used when the user account processes to-be-processed data generated last time by the ETC system, and a level transition rule, where the level transition rule may indicate a negative correlation relationship between the target discount level and the historical data of the user account. Thus, prior to determining the target discount level, the historical discount level of the user account needs to be determined. For example, the higher the discount level is, the greater the reference discount information is, the greater the discount strength that can be obtained by the user is, and the target discount level currently used by the user account may be determined according to the historical discount level used when the user account processes the to-be-processed data generated last time by the ETC system.

Step S452: and determining a target discount grade used when the user account currently processes the data processing request according to a predetermined grade transfer rule, historical data of the user account and the historical discount grade, wherein the grade transfer rule specifies that the target discount grade and the historical data of the user account are in a negative correlation relationship.

In some embodiments, the level transition rule may be set to: if the processing of the user account for the data to be processed which is generated last time is completed in a specified time period, the user account is not added into the blacklist, the currently used discount level of the user account can be increased by one discount level or the highest discount level is kept, if the processing of the user account for the data to be processed which is generated last time is not completed in the specified time period, the user account is added into the blacklist, and the currently used discount level of the user account can be decreased by one discount level or the lowest discount level is kept. Based on this, the data processing state of the user account in a specified time period for the to-be-processed data generated last time can be determined according to the historical data of the user account, and then whether the target discount level is increased by one discount level, decreased by one discount level or kept unchanged on the basis of the historical discount level is determined.

In other embodiments, the target discount level may also be determined according to a historical discount level used by the user account in the previous period and a level transition rule, in this case, the discount level used by the user account in the same period when processing the to-be-processed data generated by the ETC system in the period remains unchanged, so that it may be determined whether the user account has been added to the blacklist in the previous period according to the historical data in the previous period, and then the target discount level used in the current period is determined by the historical discount level used in the previous period. Illustratively, the level transition rule may be set as: if the user account is not added to the blacklist in the last period, a discount level is increased or the highest discount level is kept, and if the user account is added to the blacklist in the last period, a discount level is decreased or the lowest discount level is kept. Based on this, it may be determined whether the user account has been blacklisted in the previous period according to the historical data of the user account in the previous period, and then it is determined whether the target discount level is increased by one discount level, decreased by one discount level, or kept unchanged in the previous period based on the historical discount level in the previous period.

Step S460: the target discount information corresponding to the target discount level is acquired from the plurality of reference discount information.

In an embodiment of the application, after determining the target discount level used when the user account of the vehicle is currently processing the data processing request, the target discount information corresponding to the target discount level is obtained from a plurality of reference discount information. Because each piece of reference discount information corresponds to one discount grade, and the reference discount information is positively correlated with the discount grades, a plurality of reference discount information

For example, the correspondence relationship between the reference discount information and the discount level may be determined as the 1 st level correspondence

Grade 2 corresponds to

Grade 3 corresponds to

By analogy, the m-th level corresponds to

Wherein the 1 st level is the lowest level, corresponding to the reference discount information

Minimum, mth level is the highest level, corresponding reference discount information

And max. Finally, target discount information corresponding to the target discount level may be obtained from the plurality of reference discount information according to the corresponding relationship between the reference discount information and the discount level, where the target discount level is the 2 nd level, for example, the target discount information corresponds to the target discount level

。

Step S470: and determining second data according to the target discount information and the first data, and initiating a data processing request for the user account based on the second data.

In the embodiment of the application, after the target discount information is determined according to the target probability and the initial discount information, the second data corresponding to the user account of the vehicle can be determined according to the target discount information and the first data. According to the content of the foregoing embodiment, the first data may be vehicle charging information, and the second data may be, for example, a fee to be paid for the vehicle, which may be determined by multiplying the target discount information by the first data.

After the second data is determined, in this embodiment of the present application, a data processing request may be initiated for the user account of the vehicle. In some exemplary embodiments, the second data may be used as the to-be-processed data generated by the ETC system, and the user data of the user account of the vehicle may be processed based on the second data by initiating a data processing request to the user account.

In summary, according to the data processing method provided by the embodiment of the application, after the user account of the vehicle and the first data corresponding to the vehicle of the user account generated by the Electronic Toll Collection (ETC) system are acquired, a plurality of pieces of initial discount information are acquired, a target probability is determined based on the number of times that each sample user is added to the blacklist in the historical data of the sample users in the ETC system, and the plurality of pieces of initial discount information are adjusted based on the target probability, so that the target probability is inversely related to a plurality of pieces of reference discount information which are finally obtained, and a discount grade can be divided for each piece of reference discount information. Then, a target discount level when the data processing request is currently processed by the user account is determined according to historical data of the user account, so that target discount information corresponding to the target discount level is obtained from the plurality of reference discount information. And finally, determining second data according to the target discount information and the first data, and initiating a data processing request for the user account based on the second data. Therefore, discount information used when a user processes a data processing request generated in the ETC system can be determined according to the target probability estimated by historical data, so that the discount information can change along with the number of times that the user account is added into a blacklist, the flexibility of the discount information is improved, and the effect of restraining abnormal behaviors of the user account can be achieved.

In order to better understand the historical data of the sample users in the ETC system in the embodiment of the application, the determination process of the reference discount information is exemplarily described.

Referring to fig. 9, fig. 9 is a block flow diagram illustrating a data processing method according to an embodiment of the present application. In some embodiments, the determination of the reference discount information may be divided into: s910 to S970. The period in which the first data corresponding to the vehicle is acquired may be referred to as a t +1 th period, and a previous period before the t +1 th period may be referred to as a t-th period.

In step S910, in the data input stage, the server may receive historical data of the tth period of the sample user in the ETC system. It will be appreciated that in some embodiments, the historical data may include other interference data in addition to the number of times each sample user was blacklisted. For example, before extracting the target characteristic data, historical data of a sample user in the ETC system may be stored, and a preprocessing operation may be performed, where the preprocessing operation may include, for example, removing interference data, and the like.

In the step S920, in the target probability estimation stage, the server may calculate, according to the number of times that each sample user is added to the blacklist in the historical data of the t-th period, an average number of times that each sample user is added to the blacklist in the ETC system, and estimate the target probability of the t + 1-th period by using the poisson distribution, taking the average number of times as a mathematical expectation of the poisson distribution.

In step S930, in the state transition matrix building stage, the state transition matrix P may be built by using the target probability of the t +1 th cycle estimated in the previous stage and a predetermined level transition rule.

In step S940, in the steady state equation constructing stage, a steady state equation may be constructed according to the state transition matrix P. Then, step S950 may be executed, and in the distribution probability calculation stage, the distribution probability pi of each discount information in the steady state may be obtained by solving a steady state equation, where in the steady state, the distribution probability pi of each discount information remains unchanged before and after the mutual transition among the plurality of discount levels.

In step S960, in the discount information constraint model construction phase, a discount information constraint model may be constructed through the distribution probability pi. Illustratively, the discount information constraint model can be constructed by using a loss function, and the discount information equation system can be obtained by solving the loss function.

In step S970, in the optimal discount information solving stage, the distribution probability pi and the initial discount information may be substituted into the discount information equation set, an iterative formula is obtained through a gradient descent algorithm, and multiple iterative calculations are performed on the iterative formula, so that the optimal discount information, which enables the value of the loss function to meet the preset threshold condition in the t +1 th cycle, may be obtained. Further, the optimal discount information of the t +1 th cycle may be used as reference discount information, and when the vehicle needs to use the discount information, the target discount information which can be currently used is determined from the reference discount information according to the target discount level of the vehicle. Therefore, the discount information can be periodically determined according to the target probability estimated by the historical data of the sample user in the ETC system, so that the discount information can be changed along with the number of times that the user account is added into the blacklist, the flexibility of the discount information is improved, and the effect of restraining the abnormal behavior of the user account can be achieved.

Referring to fig. 10, a block diagram of a data processing apparatus according to an embodiment of the present application is shown. The data processing device is applied to a server. The data processing apparatus includes: a first acquisition unit 1010, a second acquisition unit 1020, a first determination unit 1030, and a second determination unit 1040. The first obtaining unit 1010 is configured to obtain a user account of a vehicle; a second obtaining unit 1020 for obtaining first data corresponding to the vehicle of the user account generated by the Electronic Toll Collection (ETC) system; a first determining unit 1030, configured to determine target discount information based on a target probability obtained in advance, where the target probability is determined in advance according to historical data of sample users in the ETC system, the historical data includes the number of times each sample user is added to a blacklist, and the target probability is used for representing the probability that any user in the ETC system is added to the blacklist; a second determining unit 1040, configured to determine second data according to the target discount information and the first data, and initiate a data processing request for the user account based on the second data.

As one mode, the data processing apparatus further includes: the first prediction unit is used for determining the average number of times of adding each sample user into a blacklist according to the number of times of adding each sample user into the blacklist in the historical data; and the second prediction unit is used for predicting the probability of any user being added into a blacklist in the ETC system by using Poisson distribution based on the average times, and taking the probability as the target probability.

In some embodiments, the blacklist includes user accounts which do not process the current to-be-processed data generated by the ETC system within a specified time period, where the specified time period corresponds to the current to-be-processed data, and the first determining unit 1030 may include: the device comprises an initial discount acquisition unit, a first adjustment unit, a discount grade determination unit and a target discount determination unit. The initial discount obtaining unit is used for obtaining a plurality of initial discount information; the first adjusting unit is used for adjusting the plurality of initial discount information based on the target probability to obtain a plurality of reference discount information, wherein each reference discount information corresponds to one discount level, and the target probability is inversely related to the plurality of reference discount information; the discount grade determining unit is used for determining a target discount grade used when the user account currently processes the data processing request based on historical data of the user account; the target discount determination unit is used for acquiring the target discount information corresponding to the target discount grade from the plurality of reference discount information.

Further, as an embodiment, the reference discount information is positively correlated with the discount level, and the discount level determination unit may include: the historical discount acquisition unit is used for determining the historical discount grade used when the user account processes to-be-processed data generated by the ETC system last time; and the target level determining unit is used for determining a target discount level used when the data processing request is currently processed by the user account according to a predetermined level transfer rule, the historical data of the user account and the historical discount level, wherein the level transfer rule specifies that the target discount level is in a negative correlation with the historical data of the user account.

In this embodiment, the first adjusting unit may include: a distribution probability determination unit configured to determine a distribution probability of the plurality of reference discount information based on the target probability, the distribution probability being used to indicate a probability that each of the reference discount information is used by the any user; and the second adjusting unit is used for adjusting the plurality of reference discount information according to the plurality of initial discount information and the distribution probability.

Further, the distribution probability determining unit may include: a matrix determining unit, configured to determine, based on the target probability, a state transition matrix for characterizing a probability of mutual transition among a plurality of discount levels, where the state transition matrix is used for characterizing that the discount level of any user is in a negative correlation with the target probability of any user; and the distribution probability determining subunit is used for obtaining the distribution probability of the plurality of pieces of reference discount information in a steady state according to the state transition matrix, wherein in the steady state, the probability of using each piece of reference discount information by any user is kept unchanged before and after the mutual transition among the discount grades.

Further, the reference discount information is positively correlated with the discount level, and the matrix determination unit may include: a probability determination unit, configured to determine a first probability that the any user is not added to a blacklist based on the target probability, where the target probability is a second probability; a first transition probability determining unit, configured to, if the any user is at a lowest level of the discount levels, set a probability that the any user keeps the lowest level unchanged as the second probability, set a probability that the any user rises to an adjacent level as the first probability, and set a probability that the any user rises to another level as zero, so as to obtain a transition probability corresponding to the lowest level; a second transition probability determining unit, configured to set, if the any user is at a highest level of the discount levels, a probability that the any user falls to an adjacent level as the second probability, set, as the first probability, a probability that the any user keeps the highest level unchanged, and set, as the zero, a probability that the any user falls to another level, so as to obtain a transition probability corresponding to the highest level; a third transition probability determining unit, configured to set, if the any user is at an intermediate discount level between the lowest level and the highest level, a probability that the any user falls to an adjacent level to the second probability, a probability that the any user rises to the adjacent level to the first probability, and probabilities that the any user maintains the intermediate discount level and transitions to another level to zero, so as to obtain transition probabilities corresponding to the intermediate discount level; a matrix determination subunit, configured to generate the state transition matrix from the transition probability corresponding to the lowest level, the transition probability corresponding to the highest level, and the transition probability corresponding to the intermediate discount level.

Further, as another embodiment, the second adjusting unit may include: the second adjustment subunit is used for determining the predicted values and unbiased estimated values of the plurality of reference discount information according to the distribution probability; and the optimal discount determining unit is used for calculating optimal discount information which enables the deviation between the predicted value and the unbiased estimated value to meet a preset threshold condition on the basis of the initial discount information to serve as the reference discount information.

Further, the second adjusting subunit may include: a first iteration unit for iteratively updating the plurality of initial discount information based on the distribution probability; and the second iteration unit is used for determining the weighted sum of the plurality of initial discount information and the distribution probability before each iteration update as the unbiased estimation value, and determining the plurality of initial discount information obtained after each iteration update as the predicted value.

It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described apparatus and module unit may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

In several embodiments provided in the present application, the coupling between the module units may be electrical, mechanical or other type of coupling.

In addition, functional modules in the embodiments of the present application may be integrated into one processing module, or each of the modules may exist alone physically, or two or more modules are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode.

To sum up, the scheme that this application provided, after the user account number that acquires the vehicle and through the first data that electronic toll collection ETC system produced with the vehicle of user account number corresponds, target discount information is confirmed based on the target probability that acquirees in advance, wherein, target probability is according to in advance the historical data of sample user among the ETC system confirms, historical data includes the number of times that every sample user is added into the blacklist, target probability is used for the characterization the probability that any user is added into the blacklist in the ETC system, then according to target discount information with the second data is confirmed to first data, and is based on at last the second data is right the user account number initiates the data processing request. Therefore, discount information used when the data processing request initiated in the ETC system is processed by the user account bound with the vehicle can be determined according to the probability that the user account is added into the blacklist, which is obtained by historical data estimation, so that the discount information can be changed along with the number of times that the user account is added into the blacklist, and the discount information is more flexible.

Referring to fig. 11, a block diagram of a server according to an embodiment of the present application is shown. The server may be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, a cloud server providing basic cloud computing services such as cloud service, a cloud database, cloud computing, a cloud function, cloud storage, Network service, cloud communication, middleware service, domain name service, security service, CDN (Content Delivery Network), big data and an artificial intelligence platform, and a special or platform server providing car networking service, road Network cooperation, vehicle road cooperation, intelligent traffic, automatic driving, industrial internet service, data communication (such as 4G, 5G, and the like). The server in the present application may include one or more of the following components: a processor 1110, a memory 1120, and one or more applications, wherein the one or more applications may be stored in the memory 1120 and configured to be executed by the one or more processors 1110, the one or more applications configured to perform a method as described in the aforementioned method embodiments.

Processor 1110 may include one or more processing cores. The processor 1110 interfaces with various parts throughout the server using various interfaces and lines, performs various functions of the server and processes data by executing or executing instructions, programs, code sets, or instruction sets stored in the memory 1120, and calling data stored in the memory 1120. Alternatively, the processor 1110 may be implemented in hardware using at least one of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), and Programmable Logic Array (PLA). The processor 1110 may integrate one or a combination of a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), a modem, and the like. Wherein, the CPU mainly processes an operating system, a user interface, an application program and the like; the GPU is used for rendering and drawing display content; the modem is used to handle wireless communications. It is to be appreciated that the modem can be implemented by a single communication chip without being integrated into the processor 1110.

The Memory 1120 may include a Random Access Memory (RAM) or a Read-Only Memory (Read-Only Memory). The memory 1120 may be used to store instructions, applications, code, sets of codes, or sets of instructions. The memory 1120 may include a stored program area and a stored data area, wherein the stored program area may store instructions for implementing an operating system, instructions for implementing at least one function (such as a touch function, a sound playing function, an image playing function, etc.), instructions for implementing various method embodiments described below, and the like. The storage data area can also be data created by the server in use (such as a phone book, audio and video data, chatting record data) and the like.

Referring to fig. 12, a block diagram of a computer-readable storage medium according to an embodiment of the present application is shown. The computer-readable storage medium 1200 has stored therein program code that can be called by a processor to execute the methods described in the above-described method embodiments.

The computer-readable storage medium 1200 may be an electronic memory such as a flash memory, an EEPROM (electrically erasable programmable read only memory), an EPROM, a hard disk, or a ROM. Alternatively, the computer-readable storage medium 1200 includes a non-volatile computer-readable storage medium. The computer readable storage medium 1200 has storage space for program code 1210 that performs any of the method steps described above. The program code can be read from or written to one or more computer program products. The program code 1210 may be compressed, for example, in a suitable form.

Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit the same; although the present application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not necessarily depart from the spirit and scope of the corresponding technical solutions in the embodiments of the present application.

Claims

1. A data processing method is applied to a server, and the method comprises the following steps:

acquiring a user account of a vehicle;

acquiring first data corresponding to a vehicle of the user account generated by an ETC (electronic toll collection) system;

determining target discount information based on a target probability which is obtained in advance, wherein the target probability is determined in advance according to historical data of sample users in the ETC system, the historical data comprises the number of times that each sample user is added into a blacklist, and the target probability is used for representing the probability that any user in the ETC system is added into the blacklist;

and determining second data according to the target discount information and the first data, and initiating a data processing request for the user account based on the second data.

2. The method according to claim 1, wherein the blacklist includes user accounts that do not process the present data to be processed generated by the ETC system within a specified time period, the specified time period corresponding to the present data to be processed.

3. The method of claim 2, wherein determining target discount information based on a pre-obtained target probability comprises:

acquiring a plurality of initial discount information;

adjusting the plurality of initial discount information based on the target probability to obtain a plurality of reference discount information, wherein each reference discount information corresponds to a discount level, and the target probability is inversely related to the plurality of reference discount information;

determining a target discount grade used by the user account when the user account currently processes the data processing request based on historical data of the user account;

the target discount information corresponding to the target discount level is acquired from the plurality of reference discount information.

4. The method of claim 3, wherein the plurality of reference discount information is positively correlated with the discount levels, and wherein the determining a target discount level for the user account to currently process the data processing request based on historical data of the user account comprises:

determining a historical discount grade used when the user account processes to-be-processed data generated last time by the ETC system;

and determining a target discount grade used when the user account currently processes the data processing request according to a predetermined grade transfer rule, the historical data of the user account and the historical discount grade, wherein the grade transfer rule specifies that the target discount grade and the historical data of the user account are in a negative correlation relationship.

5. The method of claim 3, wherein the adjusting the plurality of initial discount information based on the target probability to obtain a plurality of reference discount information comprises:

determining a distribution probability of the plurality of reference discount information based on the target probability, wherein the distribution probability is used for representing the probability of each reference discount information used by any user;

and adjusting the plurality of reference discount information according to the plurality of initial discount information and the distribution probability.

6. The method of claim 5, wherein determining the distribution probabilities of the plurality of reference discount information based on the target probabilities comprises:

determining a state transition matrix for representing the probability of mutual transition among a plurality of discount grades based on the target probability, wherein the state transition matrix is used for representing that the discount grade of any user is in a negative correlation relation with the target probability of any user;

and obtaining the distribution probability of the plurality of reference discount information in a steady state according to the state transition matrix, wherein in the steady state, the probability of using each reference discount information by any user is kept unchanged before and after the mutual transition among the discount grades.

7. The method of claim 6, wherein the reference discount information is positively correlated with the discount levels, and wherein the determining a state transition matrix for characterizing a probability of a transition between a plurality of discount levels based on the target probability comprises:

determining a first probability that the any user is not added to a blacklist based on the target probability, wherein the target probability is a second probability;

if any user is in the lowest level of the discount levels, setting the probability that the lowest level of any user is kept unchanged as the second probability, setting the probability that any user rises to the adjacent level as the first probability, and setting the probability that any user rises to other levels as zero to obtain the transition probability corresponding to the lowest level;

if any user is at the highest level in the discount levels, setting the probability of any user falling to the adjacent level as the second probability, setting the probability of any user keeping the highest level unchanged as the first probability, and setting the probability of any user falling to other levels as zero to obtain the transition probability corresponding to the highest level;

if any user is in an intermediate discount level between the lowest level and the highest level, setting the probability of descending to the adjacent level of any user as the second probability, setting the probability of ascending to the adjacent level of any user as the first probability, and setting the probabilities of keeping the intermediate discount level and transferring to other levels of any user as zero to obtain the transfer probability corresponding to the intermediate discount level;

and generating the state transition matrix according to the transition probability corresponding to the lowest level, the transition probability corresponding to the highest level and the transition probability corresponding to the intermediate discount level.

8. The method of claim 5, wherein the adjusting the plurality of reference discount information according to the plurality of initial discount information and the distribution probability comprises:

determining predicted values and unbiased estimated values of the plurality of reference discount information according to the distribution probability;

calculating optimal discount information, which enables the deviation between the predicted value and the unbiased estimated value to meet a preset threshold condition, based on the initial discount information, and using the optimal discount information as the reference discount information.

9. The method of claim 8, wherein determining the predicted values and unbiased estimated values of the plurality of reference discount information according to the distribution probability comprises:

iteratively updating the plurality of initial discount information based on the distribution probability;

determining the weighted sum of the plurality of initial discount information and the distribution probability before each iteration update as the unbiased estimation value, and determining the plurality of initial discount information obtained after each iteration update as the predicted value.

10. The method of claim 1, wherein prior to determining the target discount information based on the pre-obtained target probability, further comprising:

determining the average number of times of adding each sample user into a blacklist according to the number of times of adding each sample user into the blacklist in the historical data;

and predicting the probability that any user is added into a blacklist in the ETC system by using Poisson distribution based on the average times, and taking the probability as the target probability.

11. A data processing apparatus, applied to a server, the apparatus comprising:

the system comprises a first acquisition unit, a second acquisition unit and a third acquisition unit, wherein the first acquisition unit is used for acquiring a user account of a vehicle;

a second acquisition unit configured to acquire first data corresponding to a vehicle of the user account generated by an Electronic Toll Collection (ETC) system;

a first determination unit, configured to determine target discount information based on a target probability acquired in advance, where the target probability is determined in advance according to historical data of sample users in the ETC system, the historical data includes the number of times each sample user is added to a blacklist, and the target probability is used for representing the probability that any user in the ETC system is added to the blacklist;

and the second determining unit is used for determining second data according to the target discount information and the first data and initiating a data processing request for the user account based on the second data.

12. A server, characterized by comprising a processor, a memory, said memory storing a computer program, said processor being adapted to execute the data processing method of any of claims 1 to 10 by invoking said computer program.

13. A computer readable storage medium having stored therein at least one instruction, at least one program, a set of codes, or a set of instructions, which is loaded and executed by a processor to implement the method according to any one of claims 1 to 10.