Driver management and control method, device and equipment based on hierarchical dimension and storage medium

Abstract

The invention relates to the technical field of online car-hailing services, and discloses a driver management and control method, device and equipment based on hierarchical dimensionality and a storage medium, and the method comprises the steps: obtaining a driver evaluation index, and constructing a driver portrait hierarchical rule based on the driver evaluation index; the driver evaluation indexes comprise a driver compliance transport capacity index, a driver classification index and a driver performance value index; matching drivers according with the driver portrait layering rule from a preset database, and counting the evaluation indexes of the successfully matched drivers to obtain a statistical result; formulating a management and control strategy of the corresponding driver based on the statistical result; and managing and controlling the corresponding driver based on the management and control strategy. According to the method, the value of the driver is accurately and comprehensively evaluated through the multi-dimensional and comprehensive layering rule, the management and control strategy is formulated based on the layering rule, effective management and control of the driver are achieved, and conditions are provided for further improving the service quality of the driver.

Description

Technical Field

[0001] The present invention relates to the technical field of online car-hailing services, and in particular to a driver management method, device, equipment and storage medium based on a hierarchical dimension. Background Art

[0002] As the number of operating service providers increases, the number of online operating drivers also increases, and the service quality of drivers varies. In addition, due to the rise of short videos in recent years, the poor service quality of individual drivers not only brings a poor fulfillment experience to passengers, but also easily spreads and ferments into public events, which to some extent affects the brand value of online car-hailing channels and SP platforms (Service Provider, the direct provider of mobile Internet service content application services).

[0003] Regarding the hierarchical management of drivers, drivers of a certain type are usually identified through simple indicators, and then managed through simple rules. However, there are major problems with the reliability of the identification indicators and the effectiveness of the management strategy, and the following disadvantages exist:

[0004] (1) The driver stratification evaluation is inaccurate, that is, the driver cannot be evaluated correctly, and is only evaluated based on a single indicator such as the number of completed orders. The single indicator evaluation standard cannot fully express the value of the driver to the platform;

[0005] (2) The driver control strategy is simple. It only uses control measures directly on drivers based on the configuration of certain rules. It is unable to maximize the control goals in the overall situation, and the actual control business effect is limited.

[0006] In summary, for the driver stratification control problem, a certain type of driver is generally identified through simple indicators, and then controlled through simple rules. There are major problems in the reliability of identification indicators and the effectiveness of control strategies. Therefore, a driver control method with comprehensive driver stratification standards is urgently needed. Summary of the invention

[0007] In view of this, the present invention provides a driver management method, device, equipment and storage medium based on hierarchical dimensions to solve the problem that the effectiveness of driver management strategies is poor due to incomplete driver hierarchical dimensions.

[0008] In a first aspect, the present invention provides a driver management method based on hierarchical dimensions, the method comprising:

[0009] Obtain driver evaluation indicators and build driver profile stratification rules based on the driver evaluation indicators; driver evaluation indicators include driver compliance capacity indicators, driver classification indicators and driver performance value indicators;

[0010] Matching drivers that meet the driver profile stratification rules from the preset database, and obtaining statistical results by counting the evaluation indicators of successfully matched drivers;

[0011] Formulate corresponding driver control strategies based on statistical results;

[0012] Control the corresponding drivers based on the control strategy.

[0013] The driver management and control method based on hierarchical dimensions provided by the present invention obtains driver evaluation indicators and constructs driver portrait hierarchical rules based on the driver evaluation indicators; wherein the driver evaluation indicators include driver compliance capacity indicators, driver classification indicators and driver performance value indicators; drivers who meet the driver portrait hierarchical rules are matched from a preset database, and the evaluation indicators of successfully matched drivers are statistically analyzed to obtain statistical results; management and control strategies for corresponding drivers are formulated based on the statistical results; corresponding drivers are managed and controlled based on the management and control strategies, and the driver value is accurately and comprehensively evaluated through multi-dimensional and comprehensive hierarchical rules, and management and control strategies are formulated based on the hierarchical rules to achieve effective management and control of drivers, thereby providing conditions for further improving the quality of driver service, and the management and control strategies are more detailed and intelligent, reducing manual intervention, improving service operational efficiency, and solving the problem of poor effectiveness of driver management and control strategies due to incomplete driver stratification dimensions.

[0014] In an optional implementation, obtaining a driver evaluation index and constructing a driver profile stratification rule based on the driver evaluation index includes:

[0015] Obtain driver compliance capacity indicators, driver classification indicators, and driver performance value indicators;

[0016] Thresholds for driver compliance capacity indicators, driver classification indicators, and driver performance value indicators are set separately and combined to construct driver portrait stratification rules.

[0017] In an optional implementation, the compliance capacity index includes dual certificate information, the driver performance value index includes the driver's completed orders, completed order amount, violation rate and vehicle dispatch time; the driver classification index includes active population, driver life cycle, service group and driver asset information;

[0018] The thresholds of driver compliance capacity index, driver classification index and driver performance value index are set respectively and combined to construct driver profile stratification rules, including:

[0019] At least two thresholds are set for the driver's completed order volume, completed order amount, violation rate, dispatch time, dual-certificate information, active population, driver life cycle, service grouping and driver asset information, and combined to construct driver portrait stratification rules.

[0020] The driver management method based on hierarchical dimensions provided by the present invention increases the characteristics of driver stratification, increases dimensions such as active population, service points and groups, driver life cycle, and driver asset information, enriches the scope and characteristics of driver stratification combinations, and constructs driver portrait stratification rules based on information dimensions such as the number of completed orders, the amount of completed orders, the violation rate, the vehicle departure time, and double certificate information, so that the constructed driver portrait stratification rules are more comprehensive and complete, providing conditions for subsequent driver management.

[0021] In an optional implementation, matching drivers that meet the driver profile stratification rules from a preset database, and performing statistics on evaluation indicators of successfully matched drivers to obtain statistical results include:

[0022] Use big data analysis tools to match drivers who meet the driver profile stratification rules from the preset database;

[0023] The evaluation indicators of the successfully matched drivers are counted by the online analytical processing engine to obtain statistical results.

[0024] The driver management method based on hierarchical dimensions provided by the present invention matches drivers who meet the driver portrait hierarchical rules from a preset database through a big data analysis tool; and obtains statistical results by statistically analyzing the evaluation indicators of successfully matched drivers through an online analysis and processing engine, thereby improving the accuracy and statistical efficiency of the statistical results of the corresponding driver evaluation indicators.

[0025] In an optional implementation, formulating a control strategy for the corresponding driver based on the statistical results includes:

[0026] Core features are extracted from the statistical results, and corresponding driver management strategies are formulated based on the core features using natural language processing tools; the core features are any one or more of the number of completed orders, completed order amount, violation rate, dispatch time, dual-certificate information, active population, driver life cycle, service grouping, and driver asset information.

[0027] The driver management method based on hierarchical dimensions provided by the present invention extracts core features from statistical results, and formulates corresponding driver management strategies based on the core features using natural language processing tools; the core features are the number of completed orders, the amount of completed orders, the violation rate, the vehicle dispatch time, double-certificate information, the active population, the driver life cycle, the service classification and grouping, and the driver asset information, which achieves the purpose of using flexible core features according to the emphasis on different service objectives in the actual formulation of management strategies, can flexibly adjust the driver management strategies, and adapt to the driver management of various service objectives, which greatly improves the service quality of all drivers of the service provider as a whole, and helps to continuously optimize the transportation capacity structure.

[0028] In an optional implementation, controlling the corresponding driver based on the control strategy includes:

[0029] Count the core feature control values ​​of the driver's control strategy within the preset time period;

[0030] Based on the core feature control value and the preset feature evaluation standard, labeling is performed to obtain the control results of positive sample labeling and / or negative sample labeling;

[0031] Build a multi-objective model based on the control results of positive sample labeling and / or negative sample labeling;

[0032] Based on the multi-objective model, corresponding control measures or severity level measures are implemented on drivers.

[0033] The driver control method based on hierarchical dimensions provided by the present invention establishes a multi-objective model for driver control, and generalizes the driver control results better through the model, so as to select appropriate control means and severity level means to control the drivers, thereby realizing intelligent control of the drivers, reducing manual intervention, and improving the operational efficiency of the service.

[0034] In an optional implementation, the driver management method based on hierarchical dimensions further includes:

[0035] Obtain historical data on driver control results, and train and iterate the multi-objective model based on the historical data to improve the business effect of the multi-objective model.

[0036] The driver management method based on hierarchical dimensions provided by the present invention obtains historical data of driver management results, and trains and iterates the multi-objective model based on the historical data, which is beneficial to improving the business effect of the multi-objective model and achieving effective operation to continuously improve the driver service quality.

[0037] In a second aspect, the present invention provides a driver control device based on hierarchical dimensions, the device comprising:

[0038] A rule building module is used to obtain driver evaluation indicators and build driver profile stratification rules based on the driver evaluation indicators; the driver evaluation indicators include driver compliance capacity indicators, driver classification indicators and driver performance value indicators;

[0039] A matching statistics module is used to match drivers that meet the driver profile stratification rules from a preset database, and to collect statistics on the evaluation indicators of successfully matched drivers to obtain statistical results;

[0040] The strategy formulation module is used to formulate the corresponding driver control strategy based on the statistical results;

[0041] The driver control module is used to control the corresponding drivers based on the control strategy.

[0042] In a third aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the driver management method based on hierarchical dimensions of the above-mentioned first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0043] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the driver management method based on hierarchical dimensions of the above-mentioned first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0045] Figure 1 is a flowchart of a driver management method based on hierarchical dimensions according to an embodiment of the present invention;

[0046] Figure 2 is a flowchart of another driver management method based on hierarchical dimensions according to an embodiment of the present invention;

[0047] Figure 3 is a flowchart of another driver control method based on hierarchical dimensions according to an embodiment of the present invention;

[0048] Figure 4 is a schematic diagram of a driver analysis page according to an embodiment of the present invention;

[0049] FIG5( a ) is a schematic diagram of driver life cycle distribution according to an embodiment of the present invention;

[0050] FIG5( b ) is a schematic diagram of the distribution of violations according to an embodiment of the present invention;

[0051] Figure 6 is a schematic diagram of a driver dashboard page in a driver analysis page according to an embodiment of the present invention;

[0052] Figure 7 is a structural block diagram of a driver control device based on hierarchical dimensions according to an embodiment of the present invention;

[0053] Figure 8 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0054] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0055] Currently, there is a strong business demand for the brand value of online car-hailing channels and SP platforms. It is necessary to provide SP platforms with backend management and control tools, and to have operational grasps for the education, supervision, and disposal of drivers, so as to achieve effective operation and continuous improvement of driver service quality. Through operational actions, service providers are continuously guided and educated to enable them to self-manage their drivers. It is necessary to rely on backend tools to quickly find drivers that need to be managed and perform relevant management and control actions efficiently and at low cost. Therefore, it is necessary to implement population stratification capabilities in the background of the SP platform to show the service providers a full picture of driver violations, help the SP platform locate problems and make quick decisions to take actions to manage drivers efficiently and conveniently. An embodiment of the present invention provides a driver management and control method based on hierarchical dimensions, which achieves the effect of effective driver management and control through a comprehensive and complete driver stratification dimension.

[0056] According to an embodiment of the present invention, an embodiment of a driver management method based on a hierarchical dimension is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0057] In this embodiment, a driver management method based on hierarchical dimensions is provided, which can be used in mobile terminals, such as central processing units, tablet computers, servers, etc. Figure 1 is a flowchart of a driver control method based on hierarchical dimensions according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0058] Step S101, obtaining driver evaluation indicators, and constructing driver portrait stratification rules based on the driver evaluation indicators; the driver evaluation indicators include driver compliance capacity indicators, driver classification indicators and driver performance value indicators.

[0059] Specifically, driver compliance capacity indicators include but are not limited to driver certificate information such as whether the driver's certificates are complete; driver classification indicators may include but are not limited to driver population classification (such as high-activity drivers, medium-activity drivers, low-activity drivers, etc.), service classification or driver level (such as bronze drivers, gold drivers, platinum drivers, diamond drivers), etc. Driver performance value indicators include but are not limited to the number of completed orders, number of violations, and vehicle dispatch time.

[0060] The driver portrait stratification rule refers to building a corresponding violation type distribution driver dashboard page on the driver analysis page according to business needs from the perspectives of driver compliance capacity indicators, driver classification indicators, and driver performance value indicators. Drivers can be grouped and the indicator charts in the violation type distribution dashboard can be used to intuitively reflect the service quality of a group of drivers. For example, based on the characteristics of the online car-hailing industry, the driver portrait stratification rule will quantify the evaluation of a driver from three aspects, namely: the number of completed orders, vehicle dispatch time (performance contribution), completeness of both certificates (compliant capacity), violation rate and / or customer complaint rate (service quality). Figure 4 As shown in the figure, when constructing the driver portrait stratification rules, add the portrait information according to the recommended template or custom template on the driver display page, select the portrait information type according to the label attribute distribution and attribute cross-distribution, and the portrait information type corresponds to each driver evaluation index. After selecting the portrait information type, set the portrait information, select the portrait template name under the portrait basic information directory, and select the threshold corresponding to each evaluation index under the portrait condition. For example, select according to the attribute cross-distribution type, select the violation distribution for the portrait template name, set the violation amount threshold and violation rate threshold under the portrait condition, and finally form the driver portrait stratification rules.

[0061] Step S102, matching drivers that meet the driver portrait stratification rules from a preset database, and performing statistics on the evaluation indicators of successfully matched drivers to obtain statistical results.

[0062] Specifically, the preset database refers to a database that includes information on all online car-hailing drivers. The data in the database is the same as the driver's evaluation index data, including basic attribute information of each driver, such as whether the driver's credentials are complete, driver classification level indicators, and driver performance value indicators.

[0063] Taking the driver portrait stratification rules of completed orders, dispatch time (performance contribution), completeness of both certificates (compliant capacity), violation rate and / or customer complaint rate (service quality) as an example, evaluation criteria are set for completed orders, dispatch time (performance contribution), completeness of both certificates (compliant capacity), violation rate and / or customer complaint rate (service quality) on the driver dashboard page. Drivers whose completed orders, dispatch time (performance contribution), completeness of both certificates (compliant capacity), violation rate and / or customer complaint rate (service quality) in the driver portrait stratification rules are lower than the evaluation criteria in the preset database are the corresponding successfully matched drivers. The values ​​of evaluation indicators such as completed orders, dispatch time (performance contribution), completeness of both certificates (compliant capacity), violation rate and / or customer complaint rate (service quality) of the successfully matched drivers are statistically analyzed to obtain statistical results. The schematic diagram of the driver dashboard page in the driver analysis page is shown as follows: Figure 6 As shown, the statistical results of the evaluation indicators of the corresponding drivers can be seen on the driver dashboard page.

[0064] Step S103, formulating a control strategy for the corresponding driver based on the statistical results.

[0065] Specifically, taking the statistical results of the number of completed orders, vehicle dispatch time (performance contribution), completeness of both certificates (compliant capacity), violation rate and / or customer complaint rate (service quality) of the successfully matched drivers in step S102 as an example, a management and control strategy is formulated according to the actual operational objectives. For example, a management and control strategy is formulated with the goal of reducing the violation rate and / or customer complaint rate in the next week to reduce the driver's violation rate and / or customer complaint rate.

[0066] Step S104: Control the corresponding driver based on the control strategy.

[0067] Specifically, in the coming week, a control strategy to reduce the violation rate and / or customer complaint rate will be used to control drivers. That is, drivers will be given the task of reducing the violation rate and / or customer complaint rate, so that they can work towards the goals in the control strategy.

[0068] The driver management method based on hierarchical dimensions provided in this embodiment obtains driver evaluation indicators and constructs driver portrait hierarchical rules based on the driver evaluation indicators; wherein the driver evaluation indicators include driver compliance capacity indicators, driver classification indicators and driver performance value indicators; drivers who meet the driver portrait hierarchical rules are matched from a preset database, and the evaluation indicators of successfully matched drivers are statistically analyzed to obtain statistical results; management strategies for corresponding drivers are formulated based on the statistical results; corresponding drivers are managed based on the management strategies, and the driver's value is accurately and comprehensively evaluated through multi-dimensional and comprehensive hierarchical rules, and management strategies are formulated based on the hierarchical rules to achieve effective management of drivers, thereby providing conditions for further improving the quality of driver services, making the management strategies more detailed and intelligent, reducing manual intervention, improving the operational efficiency of services, and solving the problem of poor effectiveness of driver management strategies due to incomplete driver hierarchical dimensions.

[0069] In this embodiment, a driver management method based on hierarchical dimensions is provided, which can be used in mobile terminals, such as central processing units, tablet computers, servers, etc. Figure 2 is a flowchart of a driver control method based on hierarchical dimensions according to an embodiment of the present invention. Figure 2 As shown, the process includes the following steps:

[0070] Step S201, obtaining driver evaluation indicators, and constructing driver portrait stratification rules based on the driver evaluation indicators; the driver evaluation indicators include driver compliance capacity indicators, driver classification indicators and driver performance value indicators.

[0071] Specifically, the above step S201 includes:

[0072] Step S2011, obtaining the driver's compliance capacity index, driver classification index and driver performance value index.

[0073] Specifically, the compliance capacity indicators include dual-certificate information, the driver performance value indicators include the number of orders completed by the driver, the amount of completed orders, the violation rate and the time of departure; the driver classification indicators include the active population, the driver life cycle, the service group and the driver asset information. The active population is divided into: high-activity drivers, medium-activity drivers, and low-activity drivers; from the service classification, they are divided into: bronze drivers, gold drivers, platinum drivers, and diamond drivers; from the driver life cycle classification, they are divided into: novice period and veteran period; from the driver asset information classification, they are divided into: self-employed drivers and franchised drivers. For example, on the driver dashboard page, you can see the schematic diagrams of the driver life cycle distribution and violation distribution as shown in Figure 5(a) and Figure 5(b) respectively.

[0074] Step S2012, respectively set the thresholds of the driver compliance capacity index, driver classification index and driver performance value index and combine them to construct the driver portrait stratification rules.

[0075] In some optional implementations, the above step S2012 includes:

[0076] Step a. Set at least two thresholds for the driver's completed order quantity, completed order amount, violation rate, vehicle dispatch time, dual certificate information, active population, driver life cycle, service grouping and driver asset information respectively and combine them to construct driver portrait stratification rules.

[0077] For example, according to business needs, thresholds for the number of completed orders, vehicle dispatch time, completeness of both certificates, violation rate and / or customer complaint rate are set and combined to obtain driver profile stratification rules.

[0078] Through driver profile configuration, driver profile stratification rules are customized according to business needs. The driver profile stratification rule configuration will be saved in the rule engine and a computing task approval flow will be initiated. The service provider will approve it through the approval flow page, and the driver profile stratification rule configuration that passes will enter the pending execution state.

[0079] There are two ways to determine whether the driver profile stratification rules are passed:

[0080] The first method requires a historical data backtesting process, that is, using verified recent data for cross-checking. Because the rechecking process is accidental, multiple cross-checking processes can be performed. As long as the new stratification rule reaches the specified positive feedback rate (positive case volume / total regression case volume), it can be considered passed.

[0081] The second type: AB experiment with small traffic flow switching, that is, using real online traffic and selecting a small range of drivers for AB cross comparison. There is a chance in the cross-grouping process, so more than two groups of AB cross comparison can be used. After X days of observation and comparison, when the new stratification rule is better than the original stratification rule, it can be considered passed.

[0082] The driver management method based on hierarchical dimensions provided in this embodiment adds driver stratification features, adds dimensions such as active people, service points and groups, driver life cycle, driver asset information, etc., enriches the scope and characteristics of driver stratification combinations, and constructs driver portrait stratification rules based on information dimensions such as the number of completed orders, the amount of completed orders, the violation rate, the vehicle departure time, and double certificate information, so that the constructed driver portrait stratification rules are more comprehensive and complete, providing conditions for subsequent driver management.

[0083] Step S202, matching drivers that meet the driver portrait stratification rules from a preset database, and performing statistics on the evaluation indicators of successfully matched drivers to obtain statistical results.

[0084] Specifically, the above step S202 includes:

[0085] Step S2021, matching drivers that meet the driver portrait stratification rules from a preset database through a big data analysis tool.

[0086] Specifically, the big data service will regularly scan the computing tasks to be executed. For drivers who meet the driver portrait stratification, the big data BI tool (Business Intelligence, business intelligence analysis tool) will be used to pull the driver big data and use the batch-stream integrated engine calculation process to match drivers who meet the driver portrait stratification rules from the preset database.

[0087] Step S2022: Statistical results are obtained by using the online analysis and processing engine to collect statistics on the evaluation indicators of the successfully matched drivers.

[0088] Specifically, the evaluation indicators of successfully matched drivers are counted through the online analytical processing engine to obtain statistical results. The service provider's backend driver dashboard page uses the OLAP engine (Online analytical processing) to perform multi-dimensional queries, and various statistical indicators are rendered on the page through the large front-end universal image group. Through different filter items, you can also customize the conditions for queries from a certain driver group. Figure 6 shown.

[0089] Step S203: formulate a corresponding driver control strategy based on the statistical results. Figure 1 Step S104 of the illustrated embodiment will not be described in detail here.

[0090] Step S204: Control the corresponding driver based on the control strategy. Figure 1 Step S104 of the illustrated embodiment will not be described in detail here.

[0091] The driver management method based on hierarchical dimensions provided in this embodiment uses a big data analysis tool to match drivers who meet the driver portrait stratification rules from a preset database; the evaluation indicators of successfully matched drivers are statistically analyzed by an online analysis and processing engine to obtain statistical results, thereby improving the accuracy and statistical efficiency of the statistical results of the corresponding driver evaluation indicators.

[0092] In this embodiment, a driver management method based on hierarchical dimensions is provided, which can be used in mobile terminals, such as central processing units, tablet computers, servers, etc. Figure 3 is a flowchart of a driver control method based on hierarchical dimensions according to an embodiment of the present invention. Figure 3 As shown, the process includes the following steps:

[0093] Step S301, obtain driver evaluation indicators, and construct driver portrait stratification rules based on the driver evaluation indicators; driver evaluation indicators include driver compliance capacity indicators, driver classification indicators and driver performance value indicators. For details, please refer to Figure 2 Step S201 of the illustrated embodiment will not be described in detail here.

[0094] Step S302: Match drivers that meet the driver profile stratification rules from the preset database, and collect statistics on the evaluation indicators of successfully matched drivers to obtain statistical results. Figure 2 Step S202 of the illustrated embodiment will not be described in detail here.

[0095] Step S303: formulate a control strategy for the corresponding driver based on the statistical results.

[0096] Specifically, the above step S303 includes:

[0097] Step b. Extract core features from the statistical results, and formulate corresponding driver management strategies based on the core features using natural language processing tools; the core features are any one or more of the number of completed orders, the amount of completed orders, the violation rate, the time of departure, the information of both certificates, the active population, the driver life cycle, the service points and groups, and the driver asset information.

[0098] Specifically, taking the statistical results of the number of completed orders, vehicle dispatch time (performance contribution), completeness of both certificates (compliant capacity), violation rate and / or customer complaint rate (service quality) of successfully matched drivers as an example, a management and control strategy is formulated according to the actual operational objectives. For example, in the next week, the violation rate / or customer complaint rate should be reduced as the core feature and natural language processing tools (for example, TF model (Transformers, a natural language processing model based on deep learning)) are used to formulate a management and control strategy to reduce the driver's violation rate / or customer complaint rate.

[0099] Exemplarily, a control strategy is formulated with the violation rate and / or customer complaint rate between 1% and 5% as the core characteristics, or with the violation rate and / or customer complaint rate between 1% and 5% and the order completion volume of 30 orders per day as the core characteristics.

[0100] It should be noted that for drivers who use custom queries, they can use the circle selection function to directly pull real-time core features from big data BI, then call the TF model (Transformers, a natural language processing model based on deep learning) service to calculate the final control strategy, and finally implement the control measures based on the control strategy.

[0101] Step S304: Control the corresponding driver based on the control strategy.

[0102] Specifically, the above step S304 includes:

[0103] Step S3041, counting the core feature control values ​​in the driver's control strategy within a preset time period.

[0104] Specifically, after the control strategy action takes effect, the core feature of the driver's 7-day, 15-day, and 30-day violation rate / or customer complaint rate is counted to obtain a statistical value, which is used as the core feature control value to evaluate the driver's performance after control. For example, after counting the driver's 7-day, 15-day, and 30-day violation rate / or customer complaint rate, the corresponding core feature control values ​​are 3%, 6%, and 0.5%, respectively. After counting the number of orders completed by the driver in 7 days, 15 days, and 30 days, the corresponding core feature control values ​​are 25 orders / day, 35 orders / day, and 30 orders / day, respectively.

[0105] Step S3042: labeling is performed based on the core feature control value and the preset feature evaluation standard to obtain the control results of positive sample labeling and / or negative sample labeling.

[0106] Specifically, the preset feature evaluation standard is set according to the actual situation and is not specifically limited here. In this embodiment, the preset feature evaluation standard is equal to the target value of the core feature, that is, the violation rate / or customer complaint rate is 1% to 5%, and the order completion volume is 30 orders / day.

[0107] The core feature control values ​​of violation rate and / or customer complaint rate 3%, 6%, and 0.5% are compared with 1% to 5% respectively. 3% is between 1% and 5%, and no positive or negative sample marking is recorded. 6% is higher than 1% to 5%, which is a negative sample marking. 0.5% is lower than 1% to 5%, which is a positive sample marking.

[0108] The core feature control values ​​of the completed order volume of 25 orders / day, 35 orders / day, and 30 orders / day are compared with 30 orders / day respectively. If 25 orders / day is lower than 30 orders / day, it is marked as a negative sample. If 35 orders / day is higher than 30 orders / day, it is marked as a positive sample. 30 orders / day is equal to 30 orders / day, and no positive or negative sample marking is recorded.

[0109] Step S3043, building a multi-objective model based on the control results of positive sample labeling and / or negative sample labeling.

[0110] Specifically, based on the violation rate and / or customer complaint rate recorded in step S3042 and the number of completed orders, the positive sample labeling and negative sample labeling are performed and the MmoE model (Mixture of Experts, MoE, a multi-task learning model based on expert networks) builds a multi-objective model.

[0111] Step S3044, implementing corresponding control measures or severity level measures on the driver based on the multi-objective model.

[0112] Specifically, we use multiple objectives to implement corresponding control measures and severity level measures on drivers to better generalize the driver control results. Among them, the control measures for drivers are divided into three types: driver tasks, driver fines, and driver bans. The corresponding severity level measures are driver tasks, driver fines, and driver bans from light to heavy.

[0113] Step S305, obtaining historical data of driver management results, and training and iterating the multi-objective model based on the historical data to improve the business effect of the multi-objective model.

[0114] Specifically, in terms of the specific means and strategies for drivers, we build a multi-objective model to evaluate which control means to use or the severity, and regularly collect the results for training. We continuously improve business results through training and iterative processing of multi-objective models, perform daily sample labeling and processing through feature engineering, train models together with historical data from the past six months, and replace the currently running multi-objective model as a whole.

[0115] The driver control method based on hierarchical dimensions provided in this embodiment establishes a multi-objective model for driver control, and generalizes the driver control results better through the model, etc., to select appropriate control means and severity level means to control drivers, realize intelligent control of drivers, reduce manual intervention, and improve the operational efficiency of services. Obtaining historical data on driver control results, and training and iteratively processing the multi-objective model based on historical data, is conducive to improving the business effect of the multi-objective model, and achieving effective operation and continuous improvement of driver service quality. In this embodiment, a driver control device based on hierarchical dimensions is also provided, which is used to implement the above-mentioned embodiments and preferred implementation methods, and those that have been explained will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware with predetermined functions. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceived.

[0116] This embodiment provides a driver control device based on hierarchical dimensions, such as Figure 7 As shown, including:

[0117] The rule construction module 701 is used to obtain driver evaluation indicators and construct driver portrait stratification rules based on the driver evaluation indicators; the driver evaluation indicators include driver compliance capacity indicators, driver classification indicators and driver performance value indicators.

[0118] The matching statistics module 702 is used to match drivers that meet the driver portrait stratification rules from a preset database, and to collect statistics on the evaluation indicators of the successfully matched drivers to obtain statistical results.

[0119] The strategy formulation module 703 is used to formulate a management and control strategy for the corresponding driver based on the statistical results.

[0120] The driver control module 704 is used to control the corresponding driver based on the control strategy.

[0121] In some optional implementations, the rule construction module 701 includes:

[0122] The indicator acquisition unit is used to obtain the driver's compliance capacity indicator, driver classification indicator and driver performance value indicator.

[0123] The combination construction unit is used to combine the driver's compliance capacity indicators, driver classification indicators and driver performance value indicators to construct driver portrait stratification rules.

[0124] In some optional implementations, the compliance capacity index includes dual certificate information, the driver performance value index includes the driver's completed order volume, completed order amount, violation rate and vehicle dispatch time; the driver classification index includes active population, driver life cycle, service grouping and driver asset information, and the combination construction unit includes:

[0125] The combination construction sub-unit is used to combine at least two of the driver's completed order volume, completed order amount, violation rate, vehicle dispatch time, dual certificate information, active population, driver life cycle, service grouping and driver asset information to construct driver portrait stratification rules.

[0126] In some optional implementations, the matching statistics module 702 includes:

[0127] The matching unit is used to match drivers who meet the driver profile stratification rules from a preset database through a big data analysis tool.

[0128] The statistical unit is used to obtain statistical results by using the online analytical processing engine to collect statistics on the evaluation indicators of the successfully matched drivers.

[0129] In some optional implementations, the policy formulation module 703 includes:

[0130] The core feature extraction and strategy formulation unit is used to extract core features from the statistical results and formulate corresponding driver management strategies based on the core features using natural language processing tools; the core features are any one or more of the number of completed orders, the amount of completed orders, the violation rate, the time of departure, the information on both certificates, the active population, the driver's life cycle, the service points and groups, and the driver's asset information.

[0131] In some optional implementations, the driver management module 704 includes:

[0132] The numerical statistics unit is used to count the core feature control values ​​in the driver's control strategy within a preset time period.

[0133] The marking unit is used to mark based on the core feature control value and the preset feature evaluation standard to obtain the control results of positive sample marking and / or negative sample marking.

[0134] The model building unit is used to build a multi-objective model based on the control results of positive sample labeling and / or negative sample labeling.

[0135] The control unit is used to implement corresponding control measures or severity level measures on the driver based on the multi-objective model.

[0136] In some optional implementations, the driver control device based on hierarchical dimensions further includes:

[0137] The model improvement module is used to obtain the historical data of driver portrait stratification rules of driver management results, and train and iterate the multi-objective model based on the historical data to improve the business effect of the multi-objective model.

[0138] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0139] The driver control device based on hierarchical dimensions in this embodiment is presented in the form of functional units, where the units refer to ASIC (Application Specific Integrated Circuit) circuits, processors and memories that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0140] The embodiment of the present invention also provides a computer device having the above Figure 7 A driver control device based on hierarchical dimensions is shown.

[0141] See also Figure 8 , Figure 8 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 8 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 8 A processor 10 is taken as an example.

[0142] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0143] The memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0144] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0145] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0146] The computer device also includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30 and the output device 40 may be connected via a bus or other means. Figure 8 The example of connecting through bus is taken in the following.

[0147] The input device 30 can receive input digital or character information, and generate key signal input related to the user settings and function control of the computer device, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, an indicator bar, one or more mouse buttons, a trackball, a joystick, etc. The output device 40 may include a display device, an auxiliary lighting device (e.g., an LED) and a tactile feedback device (e.g., a vibration motor), etc. The above-mentioned display device includes but is not limited to a liquid crystal display, a light emitting diode, a display and a plasma display. In some optional embodiments, the display device can be a touch screen.

[0148] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0149] A part of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the existence of the computer program instruction in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc., and accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium accessible to the computer.

[0150] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A driver management method based on hierarchical dimensions, characterized in that: The method comprises: Obtaining driver evaluation indicators, and constructing driver profile stratification rules based on the driver evaluation indicators; the driver evaluation indicators include driver compliance capacity indicators, driver classification indicators, and driver performance value indicators; Matching drivers that meet the driver profile stratification rules from a preset database, and performing statistics on evaluation indicators of successfully matched drivers to obtain statistical results; Formulate a control strategy for the corresponding driver based on the statistical results; The corresponding driver is controlled based on the control strategy.

2. The method according to claim 1, characterized in that The obtaining of driver evaluation indicators and constructing driver profile stratification rules based on the driver evaluation indicators includes: Obtain driver compliance capacity indicators, driver classification indicators, and driver performance value indicators; Thresholds for the driver compliance capacity index, driver classification index, and driver performance value index are set separately and combined to construct driver portrait stratification rules.

3. The method according to claim 2, characterized in that The compliance capacity indicators include dual-certificate information; the driver performance value indicators include the number of completed orders, the amount of completed orders, the violation rate and the time of dispatch; the driver classification indicators include the active population, the driver life cycle, the service group and the driver asset information; The thresholds of the driver compliance capacity index, driver classification index and driver performance value index are set respectively and combined to construct the driver profile stratification rules, including: At least two thresholds are set for the driver's completed order quantity, completed order amount, violation rate, dispatch time, dual-certificate information, active population, driver life cycle, service grouping and driver asset information, and combined to construct a driver portrait stratification rule.

4. The method according to claim 1, characterized in that: Matching drivers that meet the driver portrait stratification rules from the preset database, and statistically analyzing the evaluation indicators of successfully matched drivers to obtain statistical results including: Matching drivers who meet the driver profile stratification rules from a preset database through a big data analysis tool; The evaluation indicators of the successfully matched drivers are counted by the online analytical processing engine to obtain statistical results.

5. The method according to claim 1, characterized in that The control strategies for corresponding drivers based on the statistical results include: Core features are extracted from the statistical results, and corresponding driver management strategies are formulated based on the core features using natural language processing tools; the core features are any one or more of the number of completed orders, the amount of completed orders, the violation rate, the time of departure, double-certificate information, active population, driver life cycle, service points and groups, and driver asset information.

6. The method according to claim 3, characterized in that: The corresponding drivers controlled based on the control strategy include: Count the core feature control values ​​of the driver's control strategy within the preset time period; Based on the core feature control value and the preset feature evaluation standard, labeling is performed to obtain the control results of positive sample labeling and / or negative sample labeling; Building a multi-objective model based on the control results of the positive sample labeling and / or the negative sample labeling; Based on the multi-objective model, corresponding control measures or severity level measures are implemented on the drivers.

7. The method according to claim 6, characterized in that The method further comprises: Obtain historical data on driver management results, and train and iterate the multi-objective model based on the historical data to improve the business effect of the multi-objective model.

8. A driver control device based on hierarchical dimensions, characterized in that: The device comprises: A rule building module, used to obtain driver evaluation indicators and build driver profile stratification rules based on the driver evaluation indicators; the driver evaluation indicators include driver compliance capacity indicators, driver classification indicators and driver performance value indicators; A matching statistics module is used to match drivers that meet the driver portrait stratification rules from a preset database, and to collect statistics on the evaluation indicators of successfully matched drivers to obtain statistical results; A strategy formulation module, used to formulate a control strategy for the corresponding driver based on the statistical results; The driver control module is used to control the corresponding driver based on the control strategy.

9. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the driver control method based on hierarchical dimensions as described in any one of claims 1 to 7 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the driver management method based on hierarchical dimensions as described in any one of claims 1 to 7.

Images