Rerent behavior prediction method and device, electronic equipment and storage medium
By analyzing the starting interval and operating mileage in vehicle rental information, screening and predicting the re-leasing time of the re-leasing object, the problem of inaccurate judgment of re-leasing time in the prior art is solved, and the re-leasing conversion rate is improved.
Patent Information
- Application Number
- CN202410987590.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-22
- Publication Date
- 2024-11-15
AI Technical Summary
The existing technology cannot accurately determine the re-leasing time of the re-leasing object, resulting in a missed opportunity for conversion.
By obtaining the vehicle rental information of the candidate releasing objects, calculate the starting time and historical running mileage, filter out the target releasing objects, and predict the next starting date based on the releasing interval.
It can accurately filter out the objects that are interested in releasing, and predict their releasing time to improve the conversion rate of the object.
Smart Images

Figure CN118967208A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the fields of data analysis technology and financial technology, and in particular to a method for predicting re-leasing behavior, a device for predicting re-leasing behavior, an electronic device, and a computer-readable storage medium. Background Art
[0002] Re-leasing refers to the act of a subject (customer or user) renting the same brand or product again. In the field of fintech, if a subject has rented a vehicle before, there is a high probability that the subject will rent a vehicle again.
[0003] In the related art, data analysis can be performed based on object data (such as the mileage of the object's vehicle) to find objects that are interested in re-renting. However, the related art cannot determine the exact re-renting time. There is a situation where the object that is interested in re-renting is found, but the object has already been re-rented, and the opportunity for object conversion is missed. Summary of the invention
[0004] The main purpose of the embodiments of the present application is to propose a method for predicting re-leasing behavior, a device for predicting re-leasing behavior, an electronic device and a computer-readable storage medium, which can find objects that are interested in re-leasing and predict the re-leasing time, and can also improve the object conversion rate.
[0005] To achieve the above-mentioned purpose, a first aspect of an embodiment of the present application proposes a method for predicting re-rental behavior, the method comprising:
[0006] Acquire vehicle rental information of a candidate re-rental object to obtain target rental vehicle information; wherein the target rental vehicle information includes a target rental vehicle and multiple rental start dates;
[0007] Calculate the interval between two adjacent rental start dates among the multiple rental start dates to obtain the rental start interval duration;
[0008] Perform interval statistical analysis based on the start-lease interval to obtain the re-lease interval;
[0009] Perform mileage statistics analysis based on the historical running mileage of the target leased vehicle to obtain the re-lease running mileage; wherein the historical running mileage is the running mileage of the target leased vehicle within the starting lease interval;
[0010] The plurality of candidate re-leasing objects are screened according to the re-leasing interval and the re-leasing running mileage to obtain a target re-leasing object; wherein the target re-leasing object represents a candidate re-leasing object whose actual running mileage is greater than the re-leasing running mileage and whose interval between the last lease start date and the actual date is less than the re-leasing interval;
[0011] For the target re-leasing object, a lease start prediction is performed according to the last lease start date and the re-leasing interval duration to obtain a target predicted lease start date.
[0012] In some embodiments, before acquiring the vehicle rental information of the candidate re-rental object and obtaining the object rental vehicle information, the method further includes:
[0013] The initial sub-leasing object is screened to obtain the candidate sub-leasing object, which specifically includes:
[0014] Obtaining the region where the initial sub-leasing object is located, and obtaining the region category;
[0015] Obtain the industry of the initial sub-leasing object and obtain the industry category;
[0016] Obtain the model of the vehicle leased by the initial sub-leasing object, and obtain the model category;
[0017] The multiple initial sub-lease objects are screened according to the region category, the industry category and the vehicle model category to obtain the candidate sub-lease objects; wherein any two of the candidate sub-lease objects are located in the same region and the same industry, and the models of the leased vehicles are also the same.
[0018] In some embodiments, the method is applied to a first service provider, wherein the first service provider has a database;
[0019] The step of obtaining the vehicle rental information of the candidate re-rental object and obtaining the rental vehicle information of the object includes:
[0020] Obtaining the identity identifier of the candidate re-leasing object to obtain a target query identifier;
[0021] Acquire the vehicle rental information of the candidate re-rental object from the database according to the target query identifier to obtain the object partial rental vehicle information;
[0022] Generate an information acquisition request based on the target query identifier, and send the information acquisition request to the rental information server;
[0023] Receiving the object global rental vehicle information sent by the rental information server based on the information acquisition request;
[0024] The object rental vehicle information is obtained by integrating the object local rental vehicle information and the object global rental vehicle information.
[0025] In some embodiments, the object global rental vehicle information includes first rental vehicle registration information shared by the first service provider to the rental information server, and second rental vehicle registration information shared by the second service provider to the rental information server;
[0026] The step of integrating the local rental vehicle information of the object and the global rental vehicle information of the object to obtain the rental vehicle information of the object includes:
[0027] Obtaining the identity of the first service provider to obtain a target filtering identifier;
[0028] filtering the first rental vehicle registration information from the object global rental vehicle information based on the target filtering identifier to obtain the second rental vehicle registration information;
[0029] The target rental vehicle information is obtained by merging the target local rental vehicle information and the second rental vehicle registration information.
[0030] In some embodiments, performing interval statistical analysis according to the initial lease interval to obtain the re-lease interval includes:
[0031] Count the number of the same rental start interval durations to obtain the number of re-rental times corresponding to the rental start interval durations;
[0032] The lease start interval duration corresponding to the maximum number of re-leasing times is determined as the re-leasing interval duration.
[0033] In some embodiments, before counting the same starting lease interval duration to obtain the number of re-rental times, the method further includes:
[0034] Update the lease start interval duration, specifically including:
[0035] Obtaining multiple benchmark interval durations that increase arbitrarily;
[0036] Calculate the difference between the rental start interval and each of the benchmark intervals to obtain an absolute value of the difference in duration corresponding to the benchmark interval;
[0037] The lease start interval duration is updated to the reference interval duration corresponding to the minimum absolute value of the duration difference.
[0038] In some embodiments, performing mileage statistical analysis based on the historical running mileage of the target leased vehicle to obtain the re-leasing running mileage includes:
[0039] If the starting lease interval is the same as the re-leasing interval, the historical running mileage is determined as the target historical running mileage;
[0040] Calculate the average running mileage according to the target historical running mileage and the length of the re-lease interval;
[0041] Obtain multiple mileage segments that increase arbitrarily;
[0042] For each mileage segment, the proportion of the candidate re-leasing objects whose average running mileage is greater than the mileage segment is accumulated to obtain the object cumulative proportion;
[0043] The multiple mileage segments are screened according to the cumulative proportion of the objects to obtain the re-lease operation mileage.
[0044] To achieve the above-mentioned purpose, a second aspect of an embodiment of the present application proposes a device for predicting re-rental behavior, the device comprising:
[0045] The object management module is used to obtain the vehicle rental information of the candidate re-rental object and obtain the target rental vehicle information; wherein the target rental vehicle information includes the target rental vehicle and multiple rental start dates;
[0046] An interval calculation module, used to perform interval calculation according to each two adjacent start dates among the plurality of start dates to obtain the start interval duration;
[0047] An interval analysis module, used to perform interval statistical analysis according to the start-lease interval duration to obtain the re-lease interval duration;
[0048] A mileage analysis module, used to perform mileage statistics analysis based on the historical running mileage of the target leased vehicle to obtain the re-rental running mileage; wherein the historical running mileage is the running mileage of the target leased vehicle within the starting lease interval;
[0049] An object screening module is used to screen the plurality of candidate re-lease objects according to the re-lease interval time and the re-lease running mileage to obtain a target re-lease object; wherein the target re-lease object represents a candidate re-lease object whose actual running mileage is greater than the re-lease running mileage and whose interval between the last lease start date and the actual date is less than the re-lease interval time;
[0050] The lease start prediction module is used to perform a lease start prediction for the target re-leasing object according to the last lease start date and the re-leasing interval duration to obtain a target predicted lease start date.
[0051] To achieve the above-mentioned purpose, the third aspect of an embodiment of the present application proposes an electronic device, which includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the method for predicting re-leasing behavior described in the first aspect is implemented.
[0052] To achieve the above-mentioned purpose, the fourth aspect of an embodiment of the present application proposes a storage medium, which is a computer-readable storage medium, and the storage medium stores a computer program. When the computer program is executed by a processor, the method for predicting re-leasing behavior described in the first aspect above is implemented.
[0053] The re-lease behavior prediction method, re-lease behavior prediction device, electronic device and computer-readable storage medium proposed in the present application obtain the re-lease interval duration by performing interval statistical analysis on multiple start dates in the target rental vehicle information; and performing mileage statistical analysis based on the historical running mileage of the target rental vehicle to obtain the re-lease running mileage; then screening multiple candidate re-lease objects based on the re-lease interval duration and the re-lease running mileage to obtain the target re-lease object; and performing a start-lease prediction based on the last start date and the re-lease interval duration to obtain the target predicted start date. It can be seen that the present application combines the re-lease running mileage and the re-lease interval duration to screen objects, and also predicts the next start date of the object based on the re-lease interval duration, which can not only screen out the target re-lease object, but also more accurately predict the next re-lease time of the target re-lease object. The present application can find objects that are interested in re-lease and can predict the re-lease time, and can also improve the object conversion rate.
[0054] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS
[0055] Figure 1 is a flow chart of a method for predicting re-rental behavior provided in an embodiment of the present application;
[0056] Figure 2 is a flow chart of a method for predicting re-rental behavior provided by another embodiment of the present application;
[0057] Figure 3 yes Figure 1 Flow chart of step 101 in;
[0058] Figure 4 yes Figure 3 Flow chart of step 305 in;
[0059] Figure 5 yes Figure 1 Flow chart of step 103 in;
[0060] Figure 6 is a flow chart of a method for predicting re-rental behavior provided by another embodiment of the present application;
[0061] Figure 7 yes Figure 1Flowchart of step 104 in;
[0062] Figure 8 It is a module structure diagram of the device for predicting re-rental behavior provided in an embodiment of the present application;
[0063] Fig. 9 It is a schematic diagram of the hardware structure of the electronic device provided in the embodiment of the present application. DETAILED DESCRIPTION
[0064] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.
[0065] It should be noted that, although the functional modules are divided in the device schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first", "second", etc. in the specification, claims and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.
[0066] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.
[0067] The embodiments of the present application propose a method for predicting re-leasing behavior, a device for predicting re-leasing behavior, an electronic device, and a computer-readable storage medium, which can find objects that are interested in re-leasing and predict the re-leasing time, and can also improve the object conversion rate.
[0068] The re-leasing behavior prediction method provided in the embodiment of the present application can be applied to the terminal and the server side, and can also be software running on the server side. The server side can be configured as an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application that implements the re-leasing behavior prediction method, etc., but is not limited to the above forms.
[0069] The present application can be used in many general or special computer system environments or configurations. For example: server computers, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.
[0070] The embodiments of the present application provide a method for predicting re-leasing behavior, a device for predicting re-leasing behavior, an electronic device, and a storage medium, which are specifically explained through the following embodiments. First, the method for predicting re-leasing behavior in the embodiments of the present application is described.
[0071] It should be noted that in each specific implementation method of the present application, when it comes to processing data related to the user's identity or characteristics such as the user's behavioral data, the user's permission or consent will be obtained first, and the collection, use and processing of such data will comply with relevant laws, regulations and standards.
[0072] Reference Figure 1 , Figure 1 It is an optional flowchart of the method for predicting re-leasing behavior provided in an embodiment of the present application, which may include but is not limited to steps 101 to 106.
[0073] Step 101, obtaining vehicle rental information of a candidate re-rental object, and obtaining target rental vehicle information; wherein the target rental vehicle information includes a target rental vehicle and multiple rental start dates;
[0074] Step 102, calculating the interval between two adjacent rental start dates among the multiple rental start dates to obtain the rental start interval duration;
[0075] Step 103, performing interval statistical analysis according to the start-lease interval duration to obtain the re-lease interval duration;
[0076] Step 104, performing mileage statistical analysis based on the historical running mileage of the target leased vehicle to obtain the re-lease running mileage; wherein the historical running mileage is the running mileage of the target leased vehicle within the starting lease interval;
[0077] Step 105, multiple candidate re-lease objects are screened according to the re-lease interval and the re-lease running mileage to obtain a target re-lease object; wherein the target re-lease object represents a candidate re-lease object whose actual running mileage is greater than the re-lease running mileage and whose interval between the last lease start date and the actual date is less than the re-lease interval;
[0078] Step 106, for the target re-lease object, a lease start prediction is performed based on the last lease start date and the re-lease interval duration to obtain a target predicted lease start date.
[0079] Steps 101 to 106 shown in the embodiment of the present application are to obtain the re-lease interval duration by performing interval statistical analysis on multiple start dates in the target rental vehicle information; and performing mileage statistical analysis based on the historical running mileage of the target rental vehicle to obtain the re-lease running mileage; then screening multiple candidate re-lease objects based on the re-lease interval duration and the re-lease running mileage to obtain the target re-lease object; and performing a start prediction based on the last start date and the re-lease interval duration to obtain the target predicted start date. It can be seen that the present application combines the re-lease running mileage and the re-lease interval duration to screen objects, and also predicts the next start date of the object based on the re-lease interval duration, which can not only screen out the target re-lease object, but also more accurately predict the next re-lease time of the target re-lease object. The present application can find objects that are interested in re-leasing and can predict the re-lease time, and can also improve the object conversion rate.
[0080] The above-mentioned re-rental behavior prediction method is executed by the first service provider, and the first service provider has a database. In one embodiment, the first service provider has an object management system, a mileage calculation system and an object re-rental system. The object management system is used to: obtain the vehicle rental information of the candidate re-rental object from the database to obtain the object rental vehicle information; the mileage calculation system is used to: obtain the running mileage of the target rental vehicle to obtain the historical running mileage; the object re-rental system is used to: perform interval calculation according to the start-up dates of each two adjacent start-up dates among multiple start-up dates to obtain the start-up interval duration; perform interval statistical analysis according to the start-up interval duration to obtain the re-rental interval duration; perform mileage statistical analysis according to the historical running mileage of the target rental vehicle to obtain the re-rental running mileage; screen multiple candidate re-rental objects according to the re-rental interval duration and the re-rental running mileage to obtain the target re-rental object; for the target re-rental object, perform a start-up prediction according to the last start-up date and the re-rental interval duration to obtain the target predicted start-up date.
[0081] In one embodiment, the first service provider also has an outbound call system, an object review system, and an object release system. The object re-lease system is used to: push the target re-lease object and the target predicted lease start date to the outbound call system. The outbound call system is used to: introduce the latest leasing plan, etc. according to the lease start requirements of the target re-lease object (including the target leased vehicle and the target predicted lease start date), to guide the target re-lease object to lease again. When the target re-lease object applies for re-lease, the object review system is used to: conduct a qualification review of the target re-lease object. When the review is passed, the object release system is used to: perform release and other operations to complete the lease start process.
[0082] In one embodiment, before step 101, the re-rental behavior prediction method may further include screening the initial re-rental object to obtain a candidate re-rental object. The initial re-rental object is an object that has rented a vehicle and may rent a vehicle again.
[0083] In one case, the database stores multiple initial sub-lease objects, and the initial sub-lease object can be directly obtained from the database. In another case, the database does not store multiple initial sub-lease objects, and an object acquisition request needs to be sent to the rental information server, and then the initial sub-lease object sent by the rental information server based on the object acquisition request is received.
[0084] It should be explained that the first service provider is a terminal for providing rental services. For example, the first service provider is a terminal where the rental company Z1 is located. The rental information server is a server for passing rental information. In addition to the initial re-rental object mentioned above, the rental information also includes the global rental vehicle information that appears below.
[0085] In one example, the initial re-lease object can be directly used as a candidate re-lease object. The candidate re-lease object is also an object that has rented a vehicle and may rent a vehicle again. Considering that the different regions, industries, and models of the rented vehicles of different initial re-lease objects have different wear and tear on the vehicles, the impact on the re-lease interval length and re-lease mileage is not the same. It is also considered that the re-lease interval length and re-lease mileage of objects in the same region, the same industry, and the same model have a certain regularity and concentration.
[0086] In one embodiment, referring to Figure 2 The above step of screening the initial sub-leasing object to obtain the candidate sub-leasing object specifically includes:
[0087] Step 201, obtaining the region where the initial sub-leasing object is located and obtaining the region category;
[0088] Step 202, obtaining the industry of the initial sub-leasing object and obtaining the industry category;
[0089] Step 203, obtaining the model of the vehicle leased by the initial sub-leasing object, and obtaining the model category;
[0090] Step 204, screening multiple initial sub-lease objects according to region category, industry category and vehicle type category to obtain candidate sub-lease objects.
[0091] In step 201, the region category is used to indicate the main location of the initial sub-leasing object. For example, the region category of object D1 is S city, the region category of object D2 is S city, and the region category of object D3 is H city.
[0092] In step 202, the industry category is used to indicate the main industry of the initial sub-leasing object. For example, the industry category of object D1 is the express industry, the industry category of object D2 is the express industry, and the industry category of object D3 is the takeaway industry.
[0093] In step 203, the vehicle type category is used to indicate the vehicle type of the vehicle leased by the initial sub-lease object. For example, the vehicle type category of object D1 is a truck, the vehicle type category of object D2 is a truck, and the vehicle type category of object D3 is an electric car.
[0094] In step 204, any two candidate re-lease objects are located in the same region and in the same industry, and the models of the leased vehicles are also the same. For example, objects D1, D2, and D3 are screened according to the region category, industry category, and model category, and the candidate re-lease objects include objects D1 and D2. Combined with the above, objects D1 and D2 are both located in S City, both are in the express delivery industry, and both are trucks.
[0095] The benefit of the embodiment of step 201 to step 204 is that the initial sub-leasing objects can be effectively screened, and the multiple candidate sub-leasing objects obtained have a certain regularity and concentration in the sub-leasing behavior, which helps to improve the accuracy of the sub-leasing behavior prediction.
[0096] After obtaining the candidate sub-lease object, in step 101 of some embodiments, the vehicle rental information of the candidate sub-lease object is obtained to obtain the object rental vehicle information. Vehicle rental information refers to the information of the vehicle rented by the object. The vehicle rental information may include that a candidate sub-lease object rented a certain vehicle on a certain date. By obtaining the vehicle rental information of a candidate sub-lease object, the target rental vehicle and multiple rental start dates can be obtained. The target rental vehicle refers to the vehicle rented by the object. The rental start date refers to the date when the object starts renting the vehicle.
[0097] In one example, the vehicle rental information includes: object A1 rented vehicle C1 on January 1, 2024, object A1 rented vehicle C2 on March 1, 2024, and object A1 rented vehicle C3 on May 1, 2024. After obtaining the vehicle rental information of object A1, the obtained target rental vehicle information includes "the target rental vehicle is vehicle C1" and "the rental start date is January 1, 2024", "the target rental vehicle is vehicle C2" and "the rental start date is March 1, 2024", and "the target rental vehicle is vehicle C3" and "the rental start date is May 1, 2024".
[0098] It should be noted that the vehicle C1, the vehicle C2, and the vehicle C3 are vehicles with different vehicle identifications, but may be vehicles of the same model. For example, the vehicle C1, the vehicle C2, and the vehicle C3 are all trucks.
[0099] In one embodiment, referring to Figure 3 , step 101 comprises:
[0100] Step 301, obtaining the identity of the candidate re-rental object and obtaining the target query identifier;
[0101] Step 302, obtaining vehicle rental information of a candidate multiple rental object from a database according to the target query identifier, and obtaining partial rental vehicle information of the object;
[0102] Step 303: Generate an information acquisition request based on the target query identifier, and send the information acquisition request to the rental information server;
[0103] Step 304, receiving the object global rental vehicle information sent by the rental information server based on the information acquisition request;
[0104] Step 305: Integrate the object's local rental vehicle information and the object's global rental vehicle information to obtain the object's rental vehicle information.
[0105] Specifically, the database stores the vehicle rental information of the candidate re-lease object. The identity identifier of the candidate re-lease object can be used as the target query identifier, and then the database is read according to the target query identifier to obtain the object's partial rental vehicle information. The object's partial rental vehicle information refers to the information of the vehicle that the candidate re-lease object has rented on the first service provider. There are many terminals that provide rental services. For example, in addition to the first service provider (also known as the terminal where the rental company Z1 is located), there is also a second service provider (also known as the terminal where the rental company Z2 is located). In actual situations, the candidate re-lease object has rented vehicles not only from the rental company Z1, but also from the rental company Z2. However, due to information isolation, the first service provider cannot obtain the information stored in the second service provider in a timely manner. Therefore, the database in the first service provider can only provide partial rental information of the candidate re-lease object, that is, the object's partial rental vehicle information.
[0106] In order to obtain more comprehensive information, it is necessary to generate an information acquisition request based on the target query identifier and send the information acquisition request to the rental information server; then receive the object global rental vehicle information sent by the rental information server based on the information acquisition request. In actual situations, after the candidate sub-rented object has rented a vehicle at rental company Z1, the first service provider shares the vehicle rental information of the candidate sub-rented object with the rental information server. Similarly, after the candidate sub-rented object has rented a vehicle at rental company Z2, the second service provider also shares the vehicle rental information of the candidate sub-rented object with the rental information server, so that the rental information server stores the vehicle rental information shared by different service providers. Therefore, the global rental information of the candidate sub-rented object, that is, the object global rental vehicle information, can be obtained from the rental information server. Finally, the object rental vehicle information can be obtained by integrating the information based on the object local rental vehicle information and the object global rental vehicle information.
[0107] The benefit of the above-mentioned embodiment of step 301 to step 305 is that it can improve the comprehensiveness of the target rental vehicle information, thereby improving the accuracy of the prediction of the re-rental behavior.
[0108] In combination with the above, multiple different service providers (such as the first service provider and the second service provider) will share the vehicle rental information of the candidate re-lease objects stored in their own terminals to the rental information server. Therefore, in the first embodiment, the object global rental vehicle information includes the first rental vehicle registration information shared by the first service provider to the rental information server, and the second rental vehicle registration information shared by the second service provider to the rental information server. The first rental vehicle registration information refers to the vehicle rental information registered by the candidate re-lease object at the first service provider. The second rental vehicle registration information refers to the vehicle rental information registered by the candidate re-lease object at the second service provider.
[0109] Based on the above, in one embodiment, refer to Figure 4 , step 305 may include:
[0110] Step 401, obtaining the identity of the first service provider and obtaining a target filtering identifier;
[0111] Step 402, filtering out the first rental vehicle registration information from the object global rental vehicle information based on the target filtering identifier to obtain the second rental vehicle registration information;
[0112] Step 403: The target rental vehicle information is obtained by merging the target local rental vehicle information and the second rental vehicle registration information.
[0113] Specifically, the object local rental vehicle information is stored by the first service provider, and the first rental vehicle registration information is shared by the first service provider to the rental information server, and the first service provider can selectively share information, or cannot share information in real time, resulting in the first rental vehicle registration information usually being a part of the object local rental vehicle information. The first rental vehicle registration information contains the identity identifier of the first service provider. Therefore, after using the identity identifier of the first service provider as the target filtering identifier, the registration information identified as the target filtering identifier in the object global rental vehicle information is filtered, that is, the first rental vehicle registration information is filtered out, and the remaining registration information is the second rental vehicle registration information, and duplicate information can be filtered out. Finally, the object rental vehicle information can be obtained by directly merging the object local rental vehicle information and the second rental vehicle registration information.
[0114] The benefit of the embodiment of the above steps 401 to 403 is that, on the basis of being able to achieve information integration, the duplication of information in the target rental vehicle information is reduced, and the accuracy of information integration is improved.
[0115] In step 102 of some embodiments, the start-up interval duration is obtained by performing interval calculation based on the interval between every two adjacent start-up dates among the multiple start-up dates. The start-up interval duration is the interval duration between every two adjacent start-up dates. For example, if the start-up dates include "January 1, 2024", "March 1, 2024", and "May 1, 2024", then the start-up interval duration calculated based on "January 1, 2024" and "March 1, 2024" is 2 months, and the start-up interval duration calculated based on "March 1, 2024" and "May 1, 2024" is also 2 months.
[0116] In step 103 of some embodiments, interval statistics analysis is performed based on the start-up interval duration to obtain the re-rental interval duration. A candidate re-rental object may have multiple different start-up interval durations, and the number of candidate re-rental objects corresponding to each start-up interval duration may not be different, so interval statistics analysis can be performed based on the start-up interval duration to obtain the re-rental interval duration.
[0117] In one embodiment, referring to Figure 5 , step 103 comprises:
[0118] Step 501, count the number of the same lease start interval duration to obtain the number of re-rental times corresponding to the lease start interval duration;
[0119] Step 502: Determine the lease start interval duration corresponding to the maximum number of lease renewal times as the lease renewal interval duration.
[0120] In one example, the starting intervals and the corresponding times of the starting intervals for all candidate re-leased objects whose locations are S city, whose industries are express delivery, and whose vehicle types are trucks are plotted on a graph, with the horizontal axis being the starting intervals for the candidate re-leased objects (e.g., 1 month to 20 months), and the vertical axis being the total number of times all candidate re-leased objects have started renting under the starting intervals (i.e., the number of times they have re-leased). It is found that the position with a higher value on the vertical axis is the peak of the re-lease interval, and the peak value of the re-lease interval can be obtained, such as 5 months. This indicates that the group of candidate re-leased objects whose locations are S city, whose industries are express delivery, and whose vehicle types are trucks are more concentrated in re-renting at 5 months.
[0121] The benefit of the embodiment of step 501 to step 502 is that, on the basis of being able to determine the duration of the re-leasing interval, the complexity of determination is reduced and the efficiency of determination can be improved.
[0122] In one embodiment, before step 501, refer to Figure 6 The re-rental behavior prediction method also includes: updating the lease start interval, specifically including:
[0123] Step 601, obtaining a plurality of equidistantly increasing reference interval durations;
[0124] Step 602, calculating the difference between the rental start interval and each of the benchmark intervals to obtain an absolute value of the difference in duration corresponding to the benchmark interval;
[0125] Step 603: Update the lease start interval duration to the reference interval duration corresponding to the minimum absolute value of the duration difference.
[0126] Specifically, multiple benchmark intervals that increase arbitrarily are, for example, 1 month, 2 months, 3 months, ..., 20 months. In actual situations, the start-of-lease interval calculated based on two start-of-lease dates is not necessarily the same as the benchmark interval. For example, the two start-of-lease dates are January 1, 2024 and March 2, 2024, respectively. At this time, the start-of-lease interval is 2 months and 1 day. After the difference calculation, the absolute values of the time difference are 1 month and 1 day, 1 day, 1 month and 1 day, ..., 17 months and 29 days (1 month is calculated as 30 days), and it can be determined that the minimum absolute value of the time difference is 1 day. Finally, the start-of-lease interval of 2 months and 1 day is updated to 2 months.
[0127] The benefit of the embodiment of steps 601 to 603 is that the lease start interval duration can be standardized, and the number of different lease start interval durations can be reduced without affecting the total number of lease start interval durations, thereby improving the accuracy of determining the re-lease interval duration.
[0128] In step 104 of some embodiments, a mileage statistical analysis is performed based on the historical running mileage of the target leased vehicle to obtain the re-rental running mileage, wherein the historical running mileage is the running mileage of the target leased vehicle within the starting lease interval.
[0129] In one embodiment, with the consent of the lessee (initial sub-lessee, candidate sub-lessee), a GPS positioning device will be installed on the vehicle. The GPS positioning device will upload the vehicle positioning point to the first service provider every few seconds, such as the mileage calculation system of the first service provider. The mileage calculation system can calculate the running mileage of each vehicle based on the vehicle positioning point. The algorithm includes dividing the positioning points into driving state positioning points and staying state positioning points according to the interval distance of the vehicle positioning points. When the N positioning points within 30 consecutive minutes are spaced no more than 500 meters apart, the positioning points within this period can be considered as staying state positioning points, otherwise they are driving state positioning points. The running mileage of the vehicle can be obtained by adding up the distances between all the driving state positioning points. The mileage calculation system will transmit the running mileage of the vehicle to the customer management system of the first service provider.
[0130] In one embodiment, referring to Figure 7 , step 104 comprises:
[0131] Step 701: If the starting lease interval and the re-leasing interval are the same, the historical running mileage is determined as the target historical running mileage;
[0132] Step 702, calculating the average running mileage according to the target historical running mileage and the re-rental interval length;
[0133] Step 703, obtaining a plurality of mileage segments that increase arbitrarily;
[0134] Step 704: for each mileage segment, the proportion of candidate re-leasing objects whose average running mileage is greater than the mileage segment is accumulated to obtain the object cumulative proportion;
[0135] Step 705, screening multiple mileage segments according to the cumulative proportion of the object to obtain the re-lease operation mileage.
[0136] In one example, the historical mileage corresponding to the re-lease interval can be taken and plotted into a scatter plot, with the horizontal axis being the mileage segment (such as from 0km to 20,000km), and the vertical axis being the cumulative proportion of the target historical mileage of the candidate re-lease object that is greater than the mileage segment. It can be found that from 0 to 20,000, the cumulative proportion of the object is from 100% to 0%. In order to improve the success rate of re-lease, the 60% corresponding mileage segment of higher quality can be found as the re-lease mileage. For example, the group of candidate re-lease objects whose location is S City, whose industry is the express delivery industry, and whose vehicle type is a truck, are more concentrated in re-leasing at 5 months, and the objects with a cumulative proportion of 60% have a re-lease mileage of more than 4,000km.
[0137] The benefit of the embodiment of step 701 to step 705 is that the re-lease operation mileage can be accurately determined, and the determination method is simple and efficient.
[0138] In step 105 of some embodiments, multiple candidate re-leased objects are screened according to the re-lease interval duration and the re-lease mileage to obtain a target re-lease object. The target re-lease object represents a candidate re-lease object whose actual mileage is greater than the re-lease mileage and whose interval duration between the last lease start date and the actual date is less than the re-lease interval duration. In one example, the actual mileage of the candidate re-lease object D1 is 4500km and the last lease start date is January 1, 2024, the actual mileage of the candidate re-lease object D2 is 4300km and the last lease start date is January 1, 2024, and the actual mileage of the candidate re-lease object D3 is 4100km and the last lease start date is March 1, 2024. Assume that the re-lease interval duration is 5 months, the re-lease mileage is 4000km, and the actual date is July 1. Through comparison, it is found that the actual operating mileage (4100km) of candidate re-lease object D3 is greater than the re-lease mileage (4000km) and the interval between the last lease start date and the actual date (4 months) is less than the re-lease interval (5 months). Therefore, candidate re-lease object D3 is selected as a target re-lease object.
[0139] In step 106 of some embodiments, for the target re-rented object, a rental start prediction is performed based on the last rental start date and the re-rental interval duration to obtain a target predicted rental start date. In one embodiment, the last rental start date is directly added to the re-rental interval duration to obtain the target predicted rental start date. For example, for the candidate re-rented object D3, March 1, 2024 is added to 5 months to obtain a target predicted rental start date of August 1, 2024.
[0140] Considering that the re-rental interval duration often represents the overall duration of multiple candidate re-rental objects, it cannot fully represent a certain candidate re-rental object. Therefore, in another embodiment, step 106 includes: for the target re-rental object, the average value of multiple start-rental interval durations of the target re-rental object is calculated to obtain a personalized interval duration; weighted calculation is performed based on the personalized interval duration and the re-rental interval duration to obtain the target interval duration; the last start-rental date is added to the target interval duration to obtain the target predicted start-rental date. This embodiment can perform personalized predictions for each target re-rental object, thereby improving the flexibility and applicability of the prediction.
[0141] See also Figure 8 The embodiment of the present application also provides a device for predicting re-leasing behavior, which can implement the above-mentioned method for predicting re-leasing behavior. Figure 8 This is a module structure block diagram of the re-rental behavior prediction device provided in an embodiment of the present application, and the device includes: an object management module 801, an interval calculation module 802, an interval analysis module 803, a mileage analysis module 804, an object screening module 805 and a rental start prediction module 806. Among them, the object management module 801 is used to obtain the vehicle rental information of the candidate re-lease object, and obtain the target rental vehicle information, which includes the target rental vehicle and multiple start dates; the interval calculation module 802 is used to perform interval calculation according to the start dates of each two adjacent start dates among the multiple start dates, and obtain the start interval duration; the interval analysis module 803 is used to perform interval statistical analysis according to the start interval duration, and obtain the re-lease interval duration; the mileage analysis module 804 is used to perform mileage statistical analysis according to the historical running mileage of the target rental vehicle, and obtain the re-lease running mileage; wherein the historical running mileage is the running mileage of the target rental vehicle within the start interval; the object screening module 805 is used to screen multiple candidate re-lease objects according to the re-lease interval duration and the re-lease running mileage, and obtain the target re-lease object; the start prediction module 806 is used to perform a start prediction for the target re-lease object according to the last start date and the re-lease interval duration, and obtain the target predicted start date.
[0142] In one embodiment, the re-rental behavior prediction device further includes: an object acquisition module, which is used to: screen the initial re-rental object to obtain a candidate re-rental object
[0143] In one embodiment, the re-renting behavior prediction device further includes: an interval updating module, which is used to: update the duration of the starting renting interval.
[0144] It should be noted that the specific implementation of the re-leasing behavior prediction device is basically the same as the specific implementation of the above-mentioned re-leasing behavior prediction method, and will not be repeated here.
[0145] The embodiment of the present application also provides an electronic device, which includes: a memory, a processor, a program stored in the memory and executable on the processor, and a data bus for realizing connection and communication between the processor and the memory, and the program is executed by the processor to realize the above-mentioned method for predicting the re-rental behavior. The electronic device can be any intelligent terminal including a tablet computer, a car computer, etc.
[0146] See also Fig. 9 , Fig. 9 The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes:
[0147] The processor 901 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application.
[0148] The memory 902 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 902 can store an operating system and other application programs. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 902, and the processor 901 calls and executes the method for predicting the re-rental behavior of the embodiment of this application;
[0149] Input / output interface 903, used to implement information input and output;
[0150] Communication interface 904, used to realize communication interaction between the device and other devices, which can be realized through wired mode (such as USB, network cable, etc.) or wireless mode (such as mobile network, WI FI, Bluetooth, etc.);
[0151] A bus 905 that transmits information between the various components of the device (e.g., the processor 901, the memory 902, the input / output interface 903, and the communication interface 904);
[0152] The processor 901 , the memory 902 , the input / output interface 903 and the communication interface 904 are connected to each other in communication within the device via a bus 905 .
[0153] The embodiment of the present application also provides a storage medium, which is a computer-readable storage medium used for computer-readable storage. The storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the above-mentioned re-rental behavior prediction method.
[0154] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory 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 embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor 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.
[0155] The embodiments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.
[0156] Those skilled in the art will appreciate that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.
[0157] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0158] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.
[0159] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.
[0160] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.
[0161] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0162] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0163] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0164] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including multiple instructions to enable an electronic device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store programs.
[0165] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the rights of the present invention is not limited thereto. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and essence of the present invention should be within the scope of the rights of the present invention.
Claims
1. A method for predicting re-rental behavior, characterized in that: The method comprises: Acquire vehicle rental information of a candidate re-rental object to obtain target rental vehicle information; wherein the target rental vehicle information includes a target rental vehicle and multiple rental start dates; Calculate the interval between two adjacent rental start dates among the multiple rental start dates to obtain the rental start interval duration; Perform interval statistical analysis based on the start-lease interval to obtain the re-lease interval; Perform mileage statistics analysis based on the historical running mileage of the target leased vehicle to obtain the re-lease running mileage; wherein the historical running mileage is the running mileage of the target leased vehicle within the starting lease interval; The plurality of candidate re-leasing objects are screened according to the re-leasing interval and the re-leasing running mileage to obtain a target re-leasing object; wherein the target re-leasing object represents a candidate re-leasing object whose actual running mileage is greater than the re-leasing running mileage and whose interval between the last lease start date and the actual date is less than the re-leasing interval; For the target re-leasing object, a lease start prediction is performed according to the last lease start date and the re-leasing interval duration to obtain a target predicted lease start date.
2. The method according to claim 1, characterized in that Before obtaining the vehicle rental information of the candidate re-rental object and obtaining the object rental vehicle information, the method further includes: The initial sub-leasing object is screened to obtain the candidate sub-leasing object, which specifically includes: Obtaining the region where the initial sub-leasing object is located, and obtaining the region category; Obtain the industry of the initial sub-leasing object and obtain the industry category; Obtain the model of the vehicle leased by the initial sub-leasing object, and obtain the model category; The multiple initial sub-lease objects are screened according to the region category, the industry category and the vehicle model category to obtain the candidate sub-lease objects; wherein any two of the candidate sub-lease objects are located in the same region and the same industry, and the models of the leased vehicles are also the same.
3. The method according to claim 1, characterized in that The method is applied to a first service provider, wherein the first service provider has a database; The step of obtaining the vehicle rental information of the candidate re-rental object and obtaining the rental vehicle information of the object includes: Obtaining the identity identifier of the candidate re-leasing object to obtain a target query identifier; Acquire the vehicle rental information of the candidate re-rental object from the database according to the target query identifier to obtain the object partial rental vehicle information; Generate an information acquisition request based on the target query identifier, and send the information acquisition request to the rental information server; Receiving the object global rental vehicle information sent by the rental information server based on the information acquisition request; The object rental vehicle information is obtained by integrating the object local rental vehicle information and the object global rental vehicle information.
4. The method according to claim 3, characterized in that The object global rental vehicle information includes first rental vehicle registration information shared by the first service provider to the rental information server, and second rental vehicle registration information shared by the second service provider to the rental information server; The step of integrating the local rental vehicle information of the object and the global rental vehicle information of the object to obtain the rental vehicle information of the object includes: Obtaining the identity of the first service provider to obtain a target filtering identifier; filtering the first rental vehicle registration information from the object global rental vehicle information based on the target filtering identifier to obtain the second rental vehicle registration information; The target rental vehicle information is obtained by merging the target local rental vehicle information and the second rental vehicle registration information.
5. The method according to any one of claims 1 to 4, characterized in that: The performing interval statistical analysis according to the initial lease interval to obtain the re-lease interval includes: Count the number of the same rental start interval durations to obtain the number of re-rental times corresponding to the rental start interval durations; The lease start interval duration corresponding to the maximum number of re-leasing times is determined as the re-leasing interval duration.
6. The method according to claim 5, characterized in that Before counting the same lease start interval duration to obtain the number of re-rental times, the method further includes: Update the lease start interval duration, specifically including: Obtaining multiple benchmark interval durations that increase arbitrarily; Calculate the difference between the rental start interval and each of the benchmark intervals to obtain an absolute value of the difference in duration corresponding to the benchmark interval; The lease start interval duration is updated to the reference interval duration corresponding to the minimum absolute value of the duration difference.
7. The method according to any one of claims 1 to 4, characterized in that: The mileage statistics analysis is performed based on the historical running mileage of the target leased vehicle to obtain the re-leasing running mileage, including: If the starting lease interval is the same as the re-leasing interval, the historical running mileage is determined as the target historical running mileage; Calculate the average running mileage according to the target historical running mileage and the length of the re-lease interval; Obtain multiple mileage segments that increase arbitrarily; For each mileage segment, the proportion of the candidate re-leasing objects whose average running mileage is greater than the mileage segment is accumulated to obtain the object cumulative proportion; The multiple mileage segments are screened according to the cumulative proportion of the objects to obtain the re-lease operation mileage.
8. A device for predicting re-rental behavior, characterized in that: The device comprises: The object management module is used to obtain the vehicle rental information of the candidate re-rental object and obtain the target rental vehicle information; wherein the target rental vehicle information includes the target rental vehicle and multiple rental start dates; An interval calculation module, used to perform interval calculation according to each two adjacent start dates among the plurality of start dates to obtain the start interval duration; An interval analysis module, used to perform interval statistical analysis according to the start-lease interval duration to obtain the re-lease interval duration; A mileage analysis module, used to perform mileage statistics analysis based on the historical running mileage of the target leased vehicle to obtain the re-rental running mileage; wherein the historical running mileage is the running mileage of the target leased vehicle within the starting lease interval; An object screening module is used to screen the plurality of candidate re-lease objects according to the re-lease interval time and the re-lease running mileage to obtain a target re-lease object; wherein the target re-lease object represents a candidate re-lease object whose actual running mileage is greater than the re-lease running mileage and whose interval between the last lease start date and the actual date is less than the re-lease interval time; The lease start prediction module is used to perform a lease start prediction for the target re-leasing object according to the last lease start date and the re-leasing interval duration to obtain a target predicted lease start date.
9. An electronic device, characterized in that: The electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the method for predicting re-leasing behavior as described in any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method for predicting re-leasing behavior according to any one of claims 1 to 7 is implemented.
