CN111754261B - Method and device for evaluating taxi willingness and terminal equipment - Google Patents

Method and device for evaluating taxi willingness and terminal equipment Download PDF

Info

Publication number
CN111754261B
CN111754261B CN202010567210.4A CN202010567210A CN111754261B CN 111754261 B CN111754261 B CN 111754261B CN 202010567210 A CN202010567210 A CN 202010567210A CN 111754261 B CN111754261 B CN 111754261B
Authority
CN
China
Prior art keywords
price
vehicle
data
rental
state
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202010567210.4A
Other languages
Chinese (zh)
Other versions
CN111754261A (en
Inventor
罗欣
李斓
朱超余
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanghai Lexiang Sijin Technology Co ltd
Original Assignee
Shanghai Lexiang Sijin Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shanghai Lexiang Sijin Technology Co ltd filed Critical Shanghai Lexiang Sijin Technology Co ltd
Priority to CN202010567210.4A priority Critical patent/CN111754261B/en
Publication of CN111754261A publication Critical patent/CN111754261A/en
Application granted granted Critical
Publication of CN111754261B publication Critical patent/CN111754261B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0201—Market modelling; Market analysis; Collecting market data
    • G06Q30/0202—Market predictions or forecasting for commercial activities
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G06F18/2148—Generating training patterns; Bootstrap methods, e.g. bagging or boosting characterised by the process organisation or structure, e.g. boosting cascade
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0201—Market modelling; Market analysis; Collecting market data
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0283—Price estimation or determination
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0645—Rental transactions; Leasing transactions
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/40—Business processes related to the transportation industry

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Accounting & Taxation (AREA)
  • Strategic Management (AREA)
  • Finance (AREA)
  • Development Economics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Marketing (AREA)
  • Entrepreneurship & Innovation (AREA)
  • General Business, Economics & Management (AREA)
  • Economics (AREA)
  • Game Theory and Decision Science (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Biology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Human Resources & Organizations (AREA)
  • Primary Health Care (AREA)
  • Tourism & Hospitality (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The embodiment of the invention discloses a method and a device for evaluating the renting willingness of a vehicle and terminal equipment. The method comprises the following steps: obtaining order data of a tested vehicle, and determining order characteristic information corresponding to the tested vehicle according to the order data; inputting the order characteristic information into a pre-trained rental prediction model to obtain the output predicted rental state of the detected vehicle; and if the predicted rental state is a rentable state, determining the rental willingness evaluation result of the tested vehicle according to the evaluation parameter data of the tested vehicle. According to the method and the device, the renting state of the vehicle is predicted according to the order data of the vehicle, and the renting intention evaluation result of the vehicle is determined according to the evaluation parameter data, so that the problem that the renting state of the vehicle is inaccurate is solved, the matching efficiency between the tenant demand and the rentable vehicle and the utilization rate of the on-shelf vehicle on a renting platform are improved, and the vehicle demand of the tenant and the economic demand of a vehicle owner are met.

Description

Method and device for evaluating taxi willingness and terminal equipment
Technical Field
The embodiment of the invention relates to the technical field of vehicle renting platforms, in particular to a method and a device for evaluating vehicle renting willingness and terminal equipment.
Background
The shared economy is an economic model that an organization or an individual with idle resources can transfer the use right of the resources to other people temporarily for compensation, so that the resource allocation can be optimized, the consumption demand can be enlarged, and the wealth circulation efficiency can be improved.
The shared taxi renting platform belongs to a shared mode of shared economy, through the shared taxi renting platform, a vehicle owner can rent own vehicles in idle time to obtain partial economic benefits, and a tenant can obtain the use right of non-own vehicles to meet the use requirements of the vehicles. Most car owners on the shared car renting platform do not perform full-time car renting service processing, so that data on the shared car renting platform are not updated timely, and the situation that car owners do not want to rent or cannot rent the searched cars after the renters leave the seats according to the searched cars is easily caused, so that matching efficiency and user experience are reduced, and platform resources are wasted.
Disclosure of Invention
The embodiment of the invention provides a method and a device for evaluating vehicle renting willingness and terminal equipment, which are used for improving matching efficiency between a tenant demand and rentable vehicles and the utilization rate of on-frame vehicles on a renting platform and simultaneously meeting the vehicle using demand of the tenant and the economic demand of a vehicle owner.
In a first aspect, an embodiment of the present invention provides a method for evaluating rental willingness of a vehicle, where the method includes:
obtaining order data of a tested vehicle, and determining order characteristic information corresponding to the tested vehicle according to the order data;
inputting the order characteristic information into a pre-trained rental prediction model to obtain the output predicted rental state of the detected vehicle;
and if the predicted rental state is a rentable state, determining the rental willingness evaluation result of the tested vehicle according to the evaluation parameter data of the tested vehicle.
In a second aspect, an embodiment of the present invention further provides an apparatus for evaluating rental willingness of a vehicle, including:
the order characteristic information determining module is used for acquiring order data of the tested vehicle and determining order characteristic information corresponding to the tested vehicle according to the order data;
the predicted rental state determining module is used for inputting the order characteristic information into a rental prediction model which is trained in advance to obtain the output predicted rental state of the detected vehicle;
and the renting intention evaluation result determining module is used for determining the renting intention evaluation result of the tested vehicle according to the evaluation parameter data of the tested vehicle if the predicted renting state is a rentable state.
In a third aspect, an embodiment of the present invention further provides a terminal device, where the terminal device includes:
one or more processors;
a memory for storing one or more programs;
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement any of the above-mentioned methods of assessing vehicle rental willingness.
In a fourth aspect, embodiments of the present invention further provide a storage medium containing computer-executable instructions, which when executed by a computer processor, are used for executing any one of the above-mentioned methods for assessing a vehicle rental willingness.
According to the method and the device, the renting state of the vehicle is predicted according to the order data of the vehicle, and the renting intention evaluation result of the vehicle is determined according to the evaluation parameter data, so that the problem that the renting state of the vehicle is inaccurate is solved, the matching efficiency between the renter demand and the rentable vehicle and the utilization rate of the on-shelf vehicle on the renting platform are improved, and the vehicle demand of the renter and the economic demand of a vehicle owner are met.
Drawings
Fig. 1 is a flowchart of a method for evaluating rental willingness of a vehicle according to an embodiment of the present invention.
Fig. 2 is a flowchart of a method for evaluating rental willingness of a vehicle according to a second embodiment of the present invention.
Fig. 3 is a flowchart of a method for evaluating rental willingness of a vehicle according to a third embodiment of the present invention.
Fig. 4 is a flowchart of a specific example of a method for evaluating rental willingness of a vehicle according to a third embodiment of the present invention.
Fig. 5 is a schematic diagram of an apparatus for evaluating rental willingness of a vehicle according to a fourth embodiment of the present invention.
Fig. 6 is a schematic structural diagram of an apparatus according to a fifth embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
Example one
Fig. 1 is a flowchart of a method for evaluating rental intention of a vehicle according to an embodiment of the present invention, where the embodiment is applicable to a case where a rental status of a rental vehicle is evaluated, and the method may be executed by a device for evaluating rental intention of a vehicle, where the device may be implemented in software and/or hardware, and the device may be configured in a terminal device. The method specifically comprises the following steps:
and S110, obtaining order data of the tested vehicle, and determining order characteristic information corresponding to the tested vehicle according to the order data.
The tested vehicle comprises a vehicle registered in the vehicle renting platform, the order data of the tested vehicle comprises data of order acceptance and order rejection of the tested vehicle, and the order data can be data of time of order acceptance, time of order rejection, number of order acceptance, number of order rejection, order information and the like. The order information includes information filled by a renter, and exemplarily, the order information includes, but is not limited to, information such as car renting time, car renting brand, car renting type, and car renting price. In one embodiment, the order data of the tested vehicle optionally comprises owner order data of the tested vehicle. Illustratively, the vehicle owner order data includes order data for vehicles other than the vehicle under test. In another embodiment, optionally, the order data of the tested vehicle includes vehicle basic information of the tested vehicle. For example, the basic information of the vehicle may be information of the service life, mileage, engine model, current parking geographical position, remaining oil amount, and the like. The order data of the vehicle under test is not particularly limited herein.
In an embodiment, optionally, determining the order characteristic information corresponding to the tested vehicle according to the order data includes: and performing characteristic engineering processing on the order data to obtain order characteristic information corresponding to the detected vehicle. The feature engineering processing method includes, but is not limited to, at least one of feature cleaning, feature sampling, feature selection, and feature extraction. The characteristic cleaning is used for removing abnormal data in the order data, the characteristic sampling is used for setting the weight of each characteristic data in the order data, and exemplarily, the weight of the order receiving times is greater than the weight of the order information. Feature selection is used to remove features of the order data that are not relevant to the outcome, exemplary methods of feature selection include, but are not limited to, at least one of filtering, wrapping, and embedding. Feature extraction is used for extracting features which are relatively large in relation to results from order data, and exemplary methods for feature extraction include, but are not limited to, principal component analysis, unsupervised clustering and the like.
And S120, inputting the order characteristic information into a pre-trained rental prediction model to obtain the output predicted rental state of the detected vehicle.
The taxi prediction model comprises a binary classification model, and the predicted taxi state of the detected vehicle comprises a rentable state and a non-rentable state. Specifically, when the rental prediction model obtains that the prediction probability corresponding to the rentable state is greater than or equal to the preset probability value, the rentable state of the detected vehicle is output as the rentable state. Correspondingly, when the prediction probability corresponding to the rentable state obtained by the renting prediction model is smaller than the preset probability value, the rentable state of the detected vehicle is output as the non-rentable state. In one embodiment, optionally, the preset probability value is less than or equal to 0.5. The advantage of this arrangement is that it is possible to avoid filtering out vehicles under test that have a low rental desire.
The algorithms used by the two-classification model include, but are not limited to, bayesian classification, decision tree, support vector machine, K-nearest neighbor or logistic regression, and the like. In one embodiment, the algorithm adopted by the rental prediction model is an Adaboost algorithm. The algorithm principle of the Adaboost algorithm is that when training data is initialized, the weight of each training data is the same. In the iterative training process, the weight of the training data which are wrongly classified in the current iterative training is improved, and the weight of the training data which are correctly classified in the current iterative training is reduced. When the classification result is determined by adopting a weighted majority voting method, the weight of the classifier with small classification error rate is improved, and the weight of the classifier with large classification error rate is reduced. Wherein the classification error rate is equal to the sum of the weights of the training data that were misclassified. The method has the advantages that all negative sample training data cannot be accurately acquired when the rental prediction model is trained, and the Adaboost algorithm can effectively avoid the problem of insufficient negative sample training data and improve the classification accuracy.
And S130, if the rental state is predicted to be a rentable state, determining the rental intention evaluation result of the detected vehicle according to the evaluation parameter data of the detected vehicle.
In one embodiment, the evaluation parameter data optionally includes historical rentable setup time data. The renting intention evaluation result comprises predicted renting time within preset time, and correspondingly, the predicted renting time within the future preset time period of the tested vehicle is determined according to the evaluation parameter data of the tested vehicle, and the steps comprise: and counting the historical rentable set time data, and determining the predicted renting time of the tested vehicle within the preset time according to the counting result. The historical rentable setting time data refers to the rentable setting time set by the owner of the tested vehicle before the evaluation. For example, the preset time may be 7 days or 10 days. For example, when the historical rentable setting time is concentrated on monday and wednesday, the rental time assessment result may be the predicted rental time of the tested vehicle within 7 days in the future, monday and wednesday.
In another embodiment, optionally, the evaluation parameter data includes time data, and accordingly, the determining of the rental intention evaluation result of the vehicle under test according to the evaluation parameter data of the vehicle under test includes: determining time characteristic information corresponding to the detected vehicle according to the time data; wherein the time data comprises historical order lease time and lease-able setting time; and inputting the time characteristic information into a pre-trained time prediction model to obtain the output predicted rental time of the detected vehicle within the preset time.
Illustratively, the historical order lease time refers to time corresponding to response operation of a vehicle owner to an order, and the response operation includes rejection or acceptance. Accordingly, historical order lease times include historical order rentable times and historical order non-rentable times. Specifically, when the vehicle owner accepts the order, the time corresponding to the order is historical order rentable time, and when the vehicle owner refuses the order, the time corresponding to the order is historical non-rentable time. For example, if the owner's response to the order for Monday through Monday is accepted, the historical rentable time includes Monday through Monday; if the owner's response to another thursday to friday order is a rejection, the historical non-rentable time includes thursday to friday. The rentable setting time comprises historical rentable setting time and current rentable setting time, wherein the historical rentable time refers to rentable time set by a vehicle owner on a vehicle renting platform before the tested vehicle is evaluated, and the current rentable time refers to rentable time set by the collected vehicle owner on the vehicle renting platform when the tested vehicle is evaluated. For example, the current rentable setup time may be monday through thursday.
Specifically, determining time characteristic information corresponding to the detected vehicle according to the time data includes: and performing characteristic engineering processing on the time data to obtain time characteristic information corresponding to the detected vehicle. The specific method of feature engineering is not limited herein.
In one embodiment, the temporal prediction model is an LSTM (Long Short Term Memory Network) model. For example, the preset time may be 7 days.
The conventional time counting method can only determine the periodic renting time of the detected vehicle according to the historical rentable setting time, but the time counting method cannot obtain an accurate prediction result for irregular rentable setting time or rentable setting time which is easy to change. The recorded technical scheme can improve the accuracy of the rental time prediction, and further improve the subsequent order matching efficiency.
On the basis of the above-described embodiment, optionally, if the predicted rental state is the non-rentable state, the evaluation operation for the vehicle under test is ended, and the predicted rental state is fed back to the user.
According to the technical scheme, the taxi state of the vehicle is predicted according to the order data of the vehicle, and the taxi willingness evaluation result of the vehicle is determined according to the evaluation parameter data, so that the problem of inaccurate taxi state of the vehicle is solved, the matching efficiency between the tenant demand and the rentable vehicle and the utilization rate of the on-shelf vehicle on a taxi platform are improved, and the vehicle demand of the tenant and the economic demand of a vehicle owner are met.
Example two
Fig. 2 is a flowchart of a method for evaluating a rental intention of a vehicle according to a second embodiment of the present invention, and a technical solution of the present embodiment is further detailed based on the second embodiment. Optionally, the determining the result of the assessment of the willingness to rent of the vehicle under test according to the assessment parameter data of the vehicle under test includes: determining price characteristic information corresponding to the detected vehicle according to the price data; wherein the price data comprises a current calibration price; and inputting the current calibration price and the price characteristic information into a price prediction model which is trained in advance to obtain an output target price classification result corresponding to the current calibration price.
The specific implementation steps of this embodiment include:
s210, obtaining order data of the tested vehicle, and determining order characteristic information corresponding to the tested vehicle according to the order data.
And S220, inputting the order characteristic information into a pre-trained rental prediction model to obtain the output predicted rental state of the detected vehicle.
S230, if the predicted rental state is a rentable state, determining price characteristic information corresponding to the detected vehicle according to the price data; wherein the price data includes a current calibration price.
The current calibration price refers to a calibration price set by the vehicle owner on the vehicle renting platform when the vehicle to be detected is evaluated, and may be a price interval or a single price, for example, the calibration price is 80-90 or 80. In one embodiment, the price data further optionally includes at least one of a historical nominal price, a historical rejection nominal price, and a historical order trading price. The historical calibrated price is, for example, the calibrated price set by the owner of the vehicle under test before the evaluation. The historical rejection order calibration price comprises a calibration price corresponding to the situation that the order is not accepted or rejected, wherein the order not accepted refers to the order exceeding the preset order receiving time. The historical order trading price refers to the trading price of a successful trading order of the vehicle under test prior to this evaluation.
In one embodiment, optionally, the price data further includes water level price data, where the water level price data is a ratio of the current calibration price to a reference calibration price interval, where the reference calibration price interval includes at least one of a historical calibration price interval of the vehicle to be tested, a current calibration price interval of another vehicle of the same type as the vehicle to be tested, and a current calibration price interval of another vehicle of the same type as the region to which the vehicle to be tested belongs. The reference calibrated price interval can be the current calibrated price interval of other vehicles with the same brand as the tested vehicle, the current calibrated price interval of all vehicles on the taxi platform, and the like.
Specifically, determining the price characteristic information corresponding to the detected vehicle according to the price data includes: and carrying out characteristic engineering processing on the price data to obtain price characteristic information corresponding to the detected vehicle. The specific method of feature engineering is not limited herein.
S240, inputting the current calibration price and the price characteristic information into a price prediction model which is trained in advance to obtain an output target price classification result corresponding to the current calibration price.
In an embodiment, optionally, the price prediction model includes a first price prediction model and a second price prediction model, where the types of the first price prediction model are at least two, the first price prediction model is used to perform price classification on the current calibration price to obtain reference price classification results, and the second price prediction model is used to determine, according to each reference price classification result, a target price classification result corresponding to the current calibration price.
Specifically, the price prediction model comprises at least two first price prediction models, and the types of the first price prediction models are different. In one embodiment, optionally, the first price prediction model comprises a random forest classifier, a support vector machine classifier, and a logistic regression classifier, and the second price prediction model comprises an eXtreme Gradient Boosting (XGBoost) classifier. Specifically, reference price classification results respectively output by the random forest classifier, the support vector machine classifier and the logistic regression classifier are input into the extreme gradient boost classifier, and an output target price classification result corresponding to the current calibration price is obtained.
In an exemplary embodiment, the reference price classification result and the target price classification result include a price type to which the current calibration price belongs and a price probability corresponding to the price type. In one embodiment, optionally, the predicted rental price of the vehicle to be tested is determined according to the price type in the target price classification result and the price probability corresponding to the price type; wherein the price type includes an exact type, a high type, or a low type. Specifically, in one embodiment, a mapping list among the price type, the price probability, the current calibration price and the predicted rental price is established, and after the price type and the price probability to which the current calibration price belongs are obtained according to the time prediction model, the predicted rental price is determined through the mapping list. In another embodiment, the predicted rental price is calculated based on the price type, price probability, and current nominal price. Illustratively, when the price type is a high type, the price probability is 0.8, and the current nominal price is 100, the predicted rental price satisfies LH100- (0.8-0.5) × 100 ═ 70. Illustratively, when the price type is a low type, the price probability is 0.8, and the current nominal price is 100, the predicted rental price satisfies LL100+ (0.8-0.5) × 100 ═ 130. Of course, the predicted rental price may be a price range, and the predicted rental price L is obtained from the above exampleHL is more than or equal to 70HLess than or equal to 100, and predicting the rental price LLSatisfy 100 ≤ LL≤130。
According to the technical scheme of the embodiment, the target price classification result is obtained by inputting the price characteristic information into the price prediction model so as to evaluate the current calibration price, the problem that the current calibration price of the detected vehicle is inaccurate is solved, and the subsequent order matching rate and matching efficiency are improved.
EXAMPLE III
Fig. 3 is a flowchart of a method for evaluating rental willingness of a vehicle according to a third embodiment of the present invention, and a technical solution of the present embodiment is further detailed based on the above-mentioned embodiments. Optionally, the evaluation parameter data includes time data and price data. Further, the method further comprises: acquiring taxi renting data input by a user, and determining at least one target vehicle matched with the taxi renting data based on the taxi renting data of all detected vehicles; and ranking the target vehicles based on the rental states and the rental intention evaluation results of the target vehicles, and displaying the vehicle information of the target vehicles according to the ranking results.
The specific implementation steps of this embodiment include:
s310, obtaining order data of the tested vehicle, and determining order characteristic information corresponding to the tested vehicle according to the order data.
And S320, inputting the order characteristic information into a pre-trained rental prediction model to obtain the output predicted rental state of the detected vehicle.
And S330, if the predicted rental state is a rentable state, respectively determining time characteristic information and price characteristic information corresponding to the detected vehicle according to the time data and the price data.
And S340, respectively inputting the time characteristic information and the price characteristic information into a time prediction model and a price prediction model which are trained in advance to obtain the output predicted renting time of the tested vehicle in the preset time and a target price classification result corresponding to the current calibrated price.
And S350, acquiring the taxi renting data input by the user, and determining at least one target vehicle matched with the taxi renting data based on the taxi renting data of all the tested vehicles.
Exemplary rental car data includes, but is not limited to, rental car time, rental car geographic location, type of vehicle, brand of vehicle, and the like. Exemplary rental data includes, but is not limited to, rental time, current nominal price, geographic location of the rental car, type of vehicle, brand of vehicle, and the like.
In one embodiment, the rental time optionally includes a current rentable set time and a predicted rental time of the vehicle under test. Accordingly, determining at least one target vehicle matching the rental data based on the rental data of all the vehicles under test includes: and when the current rentable set time and/or the predicted rentable time of the tested vehicle in the renting data of the tested vehicle are matched with the renting time in the renting data, taking the tested vehicle as a target vehicle. In the exemplary case, when the rental time in the rental car data is 10:00-12:00 of 5 month 10, the tested vehicle can rent 8:00-9:00 of 5 month 10, but the predicted rental time is 5 month 10, 9:00-13:00, the tested vehicle can be used as the target vehicle.
And S360, sequencing the target vehicles based on the predicted rental states and the rental intention evaluation results of the target vehicles, and displaying the vehicle information of the target vehicles according to the sequencing results.
The leasing willingness evaluation result comprises predicted leasing time within preset time and a target price classification result corresponding to the current calibration price.
In one embodiment, optionally, the sorting of the target vehicles based on the rental status and the rental intention evaluation result of the target vehicles includes: and determining the weight grade of each target vehicle based on the preset weight value corresponding to the renting state and renting willingness evaluation result of the target vehicles, and sequencing each target vehicle based on each weight grade. In an exemplary embodiment, the preset weight values corresponding to the leasing states are sorted from large to small into a leasable state and a non-leasable state. In an exemplary embodiment, the preset weight values corresponding to the target price classification result are sorted from large to small to obtain a low price type and a high price probability of the current calibration price, the low price type and the low price probability of the calibration price, the accurate price type and the high price probability of the current calibration price, and the high price type and the high price probability of the current calibration price. In an exemplary case, the preset weight values corresponding to the predicted rental time are sorted from large to small such that the current rentable setting time is within the preset rental time and the current rentable setting time is outside the preset rental time. The relationship among the rental status, the target price classification result, and the preset weight value corresponding to the predicted rental time is not limited. For example, the preset weight values corresponding to the target price classification result may be all greater than the preset weight value corresponding to the predicted rental time, or the preset weight value a corresponding to the target price classification result may be greater than the preset weight value corresponding to the predicted rental time, and the remaining preset weight values smaller than the preset weight value a are smaller than the preset weight value corresponding to the predicted rental time.
On the basis of the above embodiment, optionally, the user survey strategy is determined according to the predicted rental state and the rental intention evaluation result, and the predicted rental state and the rental intention evaluation result are corrected based on survey data collected according to the user survey strategy. The user survey strategy comprises judgment information of a predicted rental state and a rental intention evaluation result, and can be 'whether the vehicle A is not rentable' when the predicted rental state of the vehicle A is a non-rentable state; when the price type of the current calibration price of the vehicle a is a high type, the user survey strategy may be "whether the calibration price of the vehicle a is higher".
In one embodiment, optionally, the survey data is used as a training standard for the rental prediction model, the time prediction model and the price prediction model, and each prediction model is trained and updated.
Fig. 4 is a flowchart of a specific example of a method for evaluating rental willingness of a vehicle according to a third embodiment of the present invention. And performing characteristic engineering processing on the historical vehicle owner order data, the historical tested vehicle order data and the basic vehicle information, inputting the processed data into a leasing prediction model based on an AdaBoost algorithm, obtaining an output predicted leasing state and determining whether the vehicle is leased. If not, finishing the evaluation operation and generating a comprehensive leasing willingness evaluation result. If yes, time evaluation and price evaluation are respectively carried out on the tested vehicle.
Specifically, historical order lease time and rentable setting time are obtained, wherein the rentable setting time comprises the historical rentable setting time and the current rentable setting time. And performing characteristic engineering processing on the historical order receiving response time and the rentable set time, and inputting the processed result into an LSTM time sequence prediction model to obtain the predicted renting time of the vehicle in 7 days in the future.
Specifically, the historical calibration price, the historical rejection calibration price, the historical order transaction price and the water level price are subjected to feature engineering processing and then input into a Base-Leaner (i.e., a first price prediction model), and in this embodiment, the Base classifier includes a classifier based on a random forest algorithm, a classifier based on a support vector machine algorithm, and a classifier based on a logistic regression algorithm. And inputting the output result of the base classifier into a Meta-classifier (Meta-Leaner) based on the XGboost algorithm, namely a second price prediction model, and obtaining an output target price classification result corresponding to the detected vehicle, wherein the price types in the target price classification result comprise an accurate type, a high type and a low type.
Generating a comprehensive leasing intention evaluation result based on the predicted leasing state, the predicted leasing time and the target price classification result, adding a user investigation strategy in the one-key outbound function based on the comprehensive leasing intention evaluation result, and correcting the comprehensive leasing intention evaluation result according to investigation data acquired based on the user investigation strategy. Meanwhile, vehicles on shelves are sorted and displayed based on the comprehensive rental willingness evaluation result.
According to the technical scheme, the matched target vehicles are sorted based on the predicted rental state and the rental intention evaluation result, and the vehicle information of each target vehicle is displayed according to the sorting result, so that the problem of inaccurate screening result of the target vehicles is solved, a user can firstly look up the vehicle information of the target vehicle with the highest matching degree and the highest predicted matching success rate, the efficiency of selecting the finally matched target vehicle by the user and the probability of successful order receiving of the target vehicle are improved, and the vehicle demand of a tenant and the economic demand of a vehicle owner are met.
Example four
Fig. 5 is a schematic diagram of an apparatus for evaluating rental willingness of a vehicle according to a fourth embodiment of the present invention. The present embodiment is applicable to a case where the rental status of the rental-car is evaluated, and the device may be implemented in software and/or hardware, and may be configured in a terminal device. The device for evaluating the rental intention of a vehicle includes: an order characteristic information determination module 410, a predicted rental status determination module 420, and a rental willingness evaluation result determination module 430.
The order characteristic information determining module 410 is configured to obtain order data of the vehicle to be tested, and determine order characteristic information corresponding to the vehicle to be tested according to the order data;
the predicted rental state determining module 420 is configured to input the order characteristic information into a rental prediction model which is trained in advance, so as to obtain an output predicted rental state of the detected vehicle;
and the renting intention evaluation result determining module 430 is used for determining the renting intention evaluation result of the tested vehicle according to the evaluation parameter data of the tested vehicle if the renting state is predicted to be the rentable state.
According to the technical scheme, the taxi state of the vehicle is predicted according to the order data of the vehicle, and the taxi willingness evaluation result of the vehicle is determined according to the evaluation parameter data, so that the problem of inaccurate taxi state of the vehicle is solved, the matching efficiency between the tenant demand and the rentable vehicle and the utilization rate of the on-shelf vehicle on a taxi platform are improved, and the vehicle demand of the tenant and the economic demand of a vehicle owner are met.
On the basis of the above technical solution, optionally, the evaluation parameter data includes time data, and the rental willingness evaluation result determining module 430 is specifically configured to:
determining time characteristic information corresponding to the detected vehicle according to the time data; wherein the time data comprises historical order lease time and lease-able setting time;
and inputting the time characteristic information into a pre-trained time prediction model to obtain the output predicted rental time of the detected vehicle within the preset time.
On the basis of the above technical solution, optionally, the evaluation parameter data includes price data, and the lease intention evaluation result determining module 430 is specifically configured to:
determining price characteristic information corresponding to the detected vehicle according to the price data; wherein the price data comprises a current calibration price;
and inputting the current calibration price and the price characteristic information into a price prediction model which is trained in advance to obtain an output target price classification result corresponding to the current calibration price.
On the basis of the above technical solution, optionally, the price data further includes water level price data, where the water level price data is a ratio of the current calibration price to a reference calibration price interval, and the reference calibration price interval includes at least one of a historical calibration price interval of the vehicle to be tested, a current calibration price interval of another vehicle having the same vehicle type as the vehicle to be tested, and a current calibration price interval of another vehicle having the same area as the vehicle to be tested.
On the basis of the above technical solution, optionally, the price prediction model includes a first price prediction model and a second price prediction model, where the types of the first price prediction model are at least two, the first price prediction model is used to perform price classification on the current calibration price to obtain reference price classification results, and the second price prediction model is used to determine a target price classification result corresponding to the current calibration price according to each reference price classification result.
On the basis of the above technical solution, optionally, the apparatus further includes:
the predicted rental price determining module is used for determining the predicted rental price of the detected vehicle according to the price type in the target price classification result and the price probability corresponding to the price type; wherein the price type includes an exact type, a high type, or a low type.
On the basis of the above technical solution, optionally, the apparatus further includes:
the vehicle information display module is used for acquiring vehicle renting data input by a user and determining at least one target vehicle matched with the vehicle renting data based on the renting data of all the detected vehicles; and sequencing the target vehicles based on the predicted rental states and the rental intention evaluation results of the target vehicles, and displaying the vehicle information of the target vehicles according to the sequencing results.
On the basis of the above technical solution, optionally, the apparatus further includes:
and the leasing intention evaluation result correction module is used for determining a user investigation strategy according to the predicted leasing state and the leasing intention evaluation result and correcting the predicted leasing state and the leasing intention evaluation result based on investigation data acquired according to the user investigation strategy.
The device for evaluating the rental intention of the vehicle provided by the embodiment of the invention can be used for executing the method for evaluating the rental intention of the vehicle provided by the embodiment of the invention, and has corresponding functions and beneficial effects of the executing method.
It should be noted that, in the embodiment of the device for evaluating rental intention of a vehicle, the included units and modules are only divided according to the functional logic, but are not limited to the above division as long as the corresponding functions can be realized; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention.
EXAMPLE five
Fig. 6 is a schematic structural diagram of an apparatus provided in a fifth embodiment of the present invention, where the fifth embodiment of the present invention provides a service for implementing the method for evaluating vehicle rental willingness according to the foregoing embodiment of the present invention, and a device for evaluating vehicle rental willingness in the foregoing embodiment may be configured. Fig. 6 illustrates a block diagram of an exemplary terminal device 12 suitable for use in implementing embodiments of the present invention. The terminal device 12 shown in fig. 6 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiment of the present invention.
As shown in fig. 6, terminal device 12 is in the form of a general purpose computing device. The components of terminal device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that couples various system components including the system memory 28 and the processing unit 16.
Bus 18 represents one or more of any of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, and a processor or local bus using any of a variety of bus architectures. By way of example, such architectures include, but are not limited to, Industry Standard Architecture (ISA) bus, micro-channel architecture (MAC) bus, enhanced ISA bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.
Terminal device 12 typically includes a variety of computer system readable media. Such media may be any available media that is accessible by terminal device 12 and includes both volatile and nonvolatile media, removable and non-removable media.
The system memory 28 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM)30 and/or cache memory 32. Terminal device 12 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 34 may be used to read from and write to non-removable, nonvolatile magnetic media (not shown in FIG. 6, and commonly referred to as a "hard drive"). Although not shown in FIG. 6, a magnetic disk drive for reading from and writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 18 by one or more data media interfaces. Memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of embodiments of the invention.
A program/utility 40 having a set (at least one) of program modules 42 may be stored, for example, in memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which examples or some combination thereof may comprise an implementation of a network environment. Program modules 42 generally carry out the functions and/or methodologies of the described embodiments of the invention.
Terminal device 12 may also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), with one or more devices that enable a user to interact with terminal device 12, and/or with any devices (e.g., network card, modem, etc.) that enable terminal device 12 to communicate with one or more other computing devices. Such communication may be through an input/output (I/O) interface 22. Also, terminal device 12 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, such as the Internet) via network adapter 20. As shown in fig. 6, the network adapter 20 communicates with the other modules of the terminal device 12 via the bus 18. It should be understood that although not shown in the figures, other hardware and/or software modules may be used in conjunction with terminal device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.
The processing unit 16 executes various functional applications and data processing by running a program stored in the system memory 28, for example, implementing a method of evaluating the rental intention of a vehicle provided by the embodiment of the present invention.
Through the equipment, the problem of inaccurate taxi state of the vehicle is solved, the matching efficiency between the taxi requirement and the rentable vehicle and the utilization rate of the on-frame vehicle on the taxi platform are improved, and the vehicle using requirement of the taxi and the economic requirement of a vehicle owner are met.
EXAMPLE six
An embodiment of the present invention further provides a storage medium containing computer-executable instructions, which when executed by a computer processor, perform a method for assessing rental willingness of a vehicle, the method including:
obtaining order data of a detected vehicle, and determining order characteristic information corresponding to the detected vehicle according to the order data;
inputting the order characteristic information into a pre-trained rental prediction model to obtain the output predicted rental state of the detected vehicle;
and if the predicted rental state is a rentable state, determining the rental intention evaluation result of the detected vehicle according to the evaluation parameter data of the detected vehicle.
Computer storage media for embodiments of the invention may employ any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + +, or the like, as well as conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
Of course, the storage medium containing the computer-executable instructions provided by the embodiments of the present invention is not limited to the above method operations, and may also perform related operations in the method for evaluating the rental intention of the vehicle provided by any embodiment of the present invention.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims (7)

1. A method for evaluating rental willingness of a vehicle, comprising:
obtaining order data of a tested vehicle, and determining order characteristic information corresponding to the tested vehicle according to the order data;
inputting the order characteristic information into a pre-trained rental prediction model to obtain the output predicted rental state of the detected vehicle;
if the predicted rental state is a rentable state, determining a rental intention evaluation result of the tested vehicle according to the evaluation parameter data of the tested vehicle;
the leasing prediction model comprises a binary classification model; the predicted renting state of the detected vehicle comprises a rentable state and a non-rentable state; when the prediction probability corresponding to the rentable state obtained by the renting prediction model is greater than or equal to the preset probability value, outputting the predicted rentable state of the detected vehicle as the rentable state; when the prediction probability corresponding to the rentable state obtained by the renting prediction model is smaller than the preset probability value, outputting the predicted rentable state of the detected vehicle as the non-rentable state;
the evaluation parameter data comprises time data, and correspondingly, the step of determining the rental willingness evaluation result of the tested vehicle according to the evaluation parameter data of the tested vehicle comprises the following steps:
determining time characteristic information corresponding to the detected vehicle according to the time data; wherein the time data comprises historical order lease time and rentable set time;
inputting the time characteristic information into a pre-trained time prediction model to obtain the output predicted renting time of the detected vehicle within the preset time;
the evaluation parameter data comprises price data, and correspondingly, the step of determining the rental willingness evaluation result of the tested vehicle according to the evaluation parameter data of the tested vehicle comprises the following steps:
determining price characteristic information corresponding to the detected vehicle according to the price data; wherein the price data comprises a current calibration price;
inputting the current calibration price and the price characteristic information into a price prediction model which is trained in advance to obtain an output target price classification result corresponding to the current calibration price;
the price data also comprises water level price data, and the water level price data is the proportion of the current calibration price to a reference calibration price interval, wherein the reference calibration price interval comprises at least one of a historical calibration price interval of the tested vehicle, a current calibration price interval of other vehicles with the same vehicle type as the tested vehicle and a current calibration price interval of other vehicles with the same region as the tested vehicle.
2. The method according to claim 1, wherein the price prediction models comprise at least two types of first price prediction models and second price prediction models, the first price prediction models are used for carrying out price classification on the current nominal price to obtain reference price classification results, and the second price prediction models are used for determining target price classification results corresponding to the current nominal price according to the reference price classification results.
3. The method according to claim 1, further comprising, after obtaining the outputted target price classification result corresponding to the current calibration price:
determining the predicted rental price of the tested vehicle according to the price type in the target price classification result and the price probability corresponding to the price type; wherein the price type comprises an exact type, a high type, or a low type.
4. The method of claim 1, further comprising:
acquiring taxi renting data input by a user, and determining at least one target vehicle matched with the taxi renting data based on the taxi renting data of all detected vehicles;
and ranking the target vehicles based on the predicted rental states and the rental intention evaluation results of the target vehicles, and displaying the vehicle information of the target vehicles according to the ranking results.
5. The method of claim 1, further comprising:
and determining a user survey strategy according to the forecast leasing state and the leasing intention evaluation result, and correcting the forecast leasing state and the leasing intention evaluation result based on survey data acquired according to the user survey strategy.
6. An apparatus for evaluating rental willingness of a vehicle, comprising:
the order characteristic information determining module is used for acquiring order data of the tested vehicle and determining order characteristic information corresponding to the tested vehicle according to the order data;
the predicted rental state determining module is used for inputting the order characteristic information into a rental prediction model which is trained in advance to obtain the output predicted rental state of the detected vehicle;
the renting intention evaluation result determining module is used for determining the renting intention evaluation result of the tested vehicle according to the evaluation parameter data of the tested vehicle if the predicted renting state is a rentable state;
the leasing prediction model comprises a binary classification model; the predicted renting state of the detected vehicle comprises a rentable state and a non-rentable state; when the prediction probability corresponding to the rentable state obtained by the renting prediction model is greater than or equal to the preset probability value, outputting the predicted rentable state of the detected vehicle as the rentable state; when the prediction probability corresponding to the rentable state obtained by the renting prediction model is smaller than the preset probability value, outputting the predicted rentable state of the detected vehicle as the non-rentable state;
the assessment parameter data comprises time data, and the renting willingness assessment result determining module is specifically used for:
determining time characteristic information corresponding to the detected vehicle according to the time data; wherein the time data comprises historical order lease time and lease-able setting time;
inputting the time characteristic information into a pre-trained time prediction model to obtain the output predicted rental time of the detected vehicle within the preset time;
the assessment parameter data comprises price data, and the lease intention assessment result determining module is specifically configured to:
determining price characteristic information corresponding to the detected vehicle according to the price data; wherein the price data comprises a current calibration price;
inputting the current calibration price and the price characteristic information into a price prediction model which is trained in advance to obtain an output target price classification result corresponding to the current calibration price;
the price data also comprises water level price data, and the water level price data is the proportion of the current calibration price to the reference calibration price interval, wherein the reference calibration price interval comprises at least one of the historical calibration price interval of the tested vehicle, the current calibration price interval of other vehicles with the same vehicle type as the tested vehicle and the current calibration price interval of other vehicles with the same region as the tested vehicle.
7. A terminal device, comprising:
one or more processors;
a memory for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement the method of assessing vehicle rental willingness according to any one of claims 1-5.
CN202010567210.4A 2020-06-19 2020-06-19 Method and device for evaluating taxi willingness and terminal equipment Active CN111754261B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010567210.4A CN111754261B (en) 2020-06-19 2020-06-19 Method and device for evaluating taxi willingness and terminal equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010567210.4A CN111754261B (en) 2020-06-19 2020-06-19 Method and device for evaluating taxi willingness and terminal equipment

Publications (2)

Publication Number Publication Date
CN111754261A CN111754261A (en) 2020-10-09
CN111754261B true CN111754261B (en) 2021-12-21

Family

ID=72675764

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010567210.4A Active CN111754261B (en) 2020-06-19 2020-06-19 Method and device for evaluating taxi willingness and terminal equipment

Country Status (1)

Country Link
CN (1) CN111754261B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112561657B (en) * 2020-12-23 2024-01-09 上海乐享似锦科技股份有限公司 Vehicle information processing method and device, electronic equipment and storage medium
CN113592198B (en) * 2021-08-24 2023-09-26 腾讯科技（深圳）有限公司 Method, server and terminal for determining demand reference information

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106530188B (en) * 2016-09-30 2021-06-11 百度在线网络技术（北京）有限公司 Driver order-receiving probability evaluation method and device in online taxi calling service platform
CN110070751B (en) * 2019-05-23 2020-11-20 云盾智能物联有限公司 Parking space sharing and releasing management system, parking space sharing automatic pushing device and method
CN110348880A (en) * 2019-06-18 2019-10-18 深圳市元征科技股份有限公司 Assess the method and device of the rental price of vehicle

Also Published As

Publication number Publication date
CN111754261A (en) 2020-10-09

Similar Documents

Publication Publication Date Title
CN111275491A (en) Data processing method and device
CN111950738A (en) Machine learning model optimization effect evaluation method and device, terminal and storage medium
CN112884224A (en) Method and device for selecting address of entity object, computing equipment and computer storage medium
CN111754261B (en) Method and device for evaluating taxi willingness and terminal equipment
CN112447189A (en) Voice event detection method and device, electronic equipment and computer storage medium
CN109978619B (en) Method, system, equipment and medium for screening air ticket pricing strategy
CN112990294B (en) Training method and device of behavior discrimination model, electronic equipment and storage medium
CN114386856A (en) Method, device and equipment for identifying empty-shell enterprise and computer storage medium
CN113435998A (en) Loan overdue prediction method and device, electronic equipment and storage medium
CN113205403A (en) Method and device for calculating enterprise credit level, storage medium and terminal
CN111582589A (en) Car rental insurance prediction method, device, equipment and storage medium
CN111815435A (en) Visualization method, device, equipment and storage medium for group risk characteristics
CN117437019A (en) Credit card overdue risk prediction method, apparatus, device, medium and program product
CN108830302B (en) Image classification method, training method, classification prediction method and related device
US20230058076A1 (en) Method and system for auto generating automotive data quality marker
CN113487208B (en) Risk assessment method and risk assessment device
CN111860554A (en) Risk monitoring method and device, storage medium and electronic equipment
CN116245630A (en) Anti-fraud detection method and device, electronic equipment and medium
CN114896482A (en) Model training and energy supplementing intention recognition method, device, equipment and medium
CN114330888A (en) Order processing method and system and electronic equipment
CN113537671B (en) Sorting aging prediction method and device, storage medium and electronic equipment
CN111598307A (en) Optimization method and equipment of bus taking order scheduling system
CN114168814A (en) Data processing method and related device
CN117668557A (en) Travel transit sequencing method and device applying balanced representation learning
CN115416690A (en) Method and device for determining coupling relationship, electronic equipment and storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
CB02 Change of applicant information
CB02 Change of applicant information

Address after: Room 587, building 3, 333 Hongqiao Road, Xuhui District, Shanghai 200030

Applicant after: Shanghai Lexiang Sijin Technology Co.,Ltd.

Address before: Room 587, building 3, 333 Hongqiao Road, Xuhui District, Shanghai 200030

Applicant before: Shanghai xinwin Information Technology Co.,Ltd.

GR01 Patent grant
GR01 Patent grant