Intelligent management method and system for rented vehicles

Abstract

The invention relates to the technical field of car rental management, in particular to a car rental intelligent management method and system, and the method comprises the following steps: obtaining the time difference between reservation and use, judging whether to give an early warning or not, counting the number of early warning times, adjusting the credit rating if the number exceeds the limit, judging the renewal time and the return time, and recognizing abnormal renewal. Behavior nodes are constructed, abnormal statistical behavior chain early warning numbers are aggregated, resource request priorities are judged in combination with multiple factors, and a vehicle planning table is established. In the invention, through difference calculation, a short-time frequent reservation behavior is identified, abnormal renewal is determined, deep modeling of continuous abnormity on a user behavior rule is aggregated, credit rating records and behavior chain characteristics are combined, a user resource request priority is dynamically adjusted, and interference of a high-risk behavior on resource scheduling is controlled. The early warning response capability to abnormal behaviors and the pertinence of resource management are improved, behavior risk constraint and intelligent cooperation of vehicle configuration are realized, and a vehicle rental management system with timeliness, hierarchy and adaptive characteristics is constructed.

Description

Technical Field

[0001] The present invention relates to the technical field of car rental management, and in particular to an intelligent management method and system for car rental vehicles. Background Art

[0002] The field of car rental management technology includes vehicle information processing, rental business scheduling, user order management, vehicle positioning and status monitoring. The core content is to achieve effective allocation of vehicle resources and improve operational efficiency through the collection of vehicle usage information and the reasonable arrangement of rental time and routes. Car rental management technology covers real-time vehicle information collection, rental process management, platform user interaction control and rule-based task scheduling. It is a typical resource management information processing technology for commercial operations.

[0003] Intelligent vehicle rental management refers to a technical solution for the unified planning and management of rental vehicles throughout the entire rental cycle. It covers vehicle usage status identification, scheduling logic design based on usage rules, time and location matching control during the rental process, and matching rental orders with vehicle resources. This typically involves collecting vehicle location information through location-based sensor equipment, combining it with server-side business rule processing to match rental requests with resources, and providing feedback on vehicle instructions via remote communication. Furthermore, an information system is used to jointly determine the rental time window and vehicle idle status to complete planning and management.

[0004] Existing car rental management systems lack a unified, structured approach to user behavior data. Instead, their scope is limited to vehicle status and the rental process itself, lacking a continuous anomaly tracking mechanism based on a behavioral chain. The system fails to incorporate time-series aggregation criteria for identifying multiple instances of irregular behavior, resulting in an inability to accurately respond to short-term, frequent operational anomalies. This makes it easy for frequent anomalies to evade monitoring. For example, a user repeatedly initiating and rapidly canceling temporary reservations within a short period of time fails to constitute a valid record, disrupting resource scheduling. The existing model relies solely on vehicle status updates and rental time changes to monitor renewals. It lacks a thorough understanding of actual return intentions and the logic surrounding these operations, making it difficult to identify intentional circumvention of return rules. Furthermore, vehicle allocation fails to consider user behavior history or behavioral risk, placing frequent offenders and compliant users on the same priority list in resource allocation. This results in the duplication of high-value resources, impacting service fairness and scheduling rationality. The lack of closed-loop management of behavioral pathways and the lack of a hierarchical response framework for risk assessments results in insufficient responsiveness and precise control capabilities for complex behavior scenarios. Summary of the Invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose an intelligent management method and system for rental vehicles.

[0006] In order to achieve the above-mentioned purpose, the present invention adopts the following technical solution: a method for intelligent management of rental vehicles, comprising the following steps:

[0007] S1: Obtain the time when the user submits the reservation request on the platform and the start time of vehicle use, calculate the difference and compare it with the shortest reservation lead time, mark the user's reservation warning behavior, and count the number of reservation warning recognitions;

[0008] S2: Based on the number of scheduled warning identifications, if the number of identifications is greater than the upper limit of the cumulative warning number in the period, a credit rating downgrade process is triggered, the credit rating is bound to the vehicle number, and a credit rating adjustment record unit is generated;

[0009] S3: Obtain the current status of the unreturned vehicle and record the renewal trigger time initiated by the user, determine the return confirmation time, compare the renewal trigger time with the return confirmation time, mark abnormal renewal behavior, and generate an abnormal renewal identification tag;

[0010] S4: Combining the credit rating adjustment record unit and the abnormal lease renewal identification tag, obtaining the corresponding behavior timestamp, vehicle number, and behavior type, constructing a behavior node sequence, aggregating abnormal nodes, and statistically obtaining the number of behavior chain warning nodes;

[0011] S5: Based on the number of warning nodes in the behavior chain, combined with the number of reservation warning identifications and the credit level in the credit level adjustment record unit, a priority judgment is performed on the user's current vehicle resource request to establish a rental vehicle planning table.

[0012] As a further solution of the present invention, the number of appointment warning identifications includes abnormal behavior density, trigger frequency threshold, and identification time dimension; the credit rating adjustment record unit includes rating change type, bound behavior node number, and associated vehicle unique number; the abnormal renewal identification tag includes identification tag type, trigger timestamp, and corresponding vehicle status code; the number of behavior chain warning nodes includes continuous node statistics, node behavior type aggregation, and node time series structure; the car rental vehicle planning table includes priority sorting results, user request level labeling, and vehicle allocation basis.

[0013] As a further solution of the present invention, the specific steps for obtaining the number of appointment warning identification times are as follows:

[0014] S111: Obtain the reservation request time submitted by the user on the platform and the vehicle use start time, calculate the time interval between the reservation request time and the vehicle use start time, count the time difference corresponding to each user reservation data, and generate the vehicle reservation advance time value;

[0015] S112: Compare the vehicle appointment lead time value with the shortest appointment lead time benchmark value one by one, filter out records whose time difference is less than the shortest appointment lead time benchmark value, create a record index, and generate a shortest lead time offset index set;

[0016] S113: extracting corresponding record entries from the original user reservation data according to the shortest lead time offset index set, and counting the number of occurrences of the corresponding record in the current time window, counting the number of lead time abnormal behavior records in the time window, and generating the number of reservation warning identifications.

[0017] As a further solution of the present invention, the specific steps of obtaining the credit rating adjustment record unit are:

[0018] S211: Based on the number of appointment warning identifications and the upper limit of the periodic cumulative warning number, a judgment operation is performed to extract user indexes whose number of times exceeds the upper limit of the periodic cumulative warning number and form a set list to generate an over-limit warning user index set;

[0019] S212: Read the over-limit warning user index set and locate the credit rating status node in the current user database, calculate the credit rating downgrade of the over-limit warning user based on the user's existing corresponding credit rating, confirm the current status, and generate a credit rating downgrade record;

[0020] S213: Extract the current behavior node number according to the credit rating downgrade record and the corresponding user index, and extract the vehicle number by linking the vehicle allocation record, and bind them to generate a credit rating adjustment record unit.

[0021] As a further solution of the present invention, the credit rating of the user with over-limit warning is calculated based on the user's existing corresponding credit rating, using the formula:

[0022]

[0023] Calculate the credit rating downgrade indicator value and confirm the current status, where: Represents the credit rating downgrade value of the user, N ui Represents user U i The number of appointment warning recognitions in a unit period, N max Represents the upper limit of the cumulative number of warnings in the set period, L cui Represents user U i The hierarchical position value of the current credit rating in the credit rating system, T ui Represents user U i The number of days since registration on the platform, Represents user U iThe credit rating impact factor caused by each default behavior in the past k behavior nodes, N is the total number of historical behavior nodes included in the statistics, and j is the traversal index from 1 to N.

[0024] As a further solution of the present invention, the specific steps for obtaining the abnormal renewal identification tag are as follows:

[0025] S311: Obtain all records of vehicles whose current status is not returned, filter the renewal request data submitted by the corresponding user, extract the renewal trigger time corresponding to each renewal request, and match the corresponding vehicle's entry time and return click time to generate a statistical collection of renewal and return times;

[0026] S312: Based on the vehicle entry time and return click time of each record in the renewal and return time set, the maximum value is selected as the return confirmation time, and the return confirmation time and the renewal trigger time are sequentially judged to filter out records whose renewal trigger time is earlier than the return confirmation time, and generate a renewal timing conflict record;

[0027] S313: extracting the corresponding record number according to the renewal timing conflict record, constructing the behavior state label of the corresponding conflict record in the current task record table, marking it as abnormal renewal, and generating an abnormal renewal identification label.

[0028] As a further solution of the present invention, the specific steps for obtaining the number of warning nodes in the behavior chain are:

[0029] S411: Combining the credit rating adjustment record unit and the abnormal lease renewal identification tag, extracting the corresponding behavior timestamps, vehicle numbers, and behavior types from the two types of records, sorting all records in ascending chronological order based on the behavior timestamps, and aggregating the sorted record information into a single structure to generate a time-series behavior node sequence;

[0030] S412: Reading the behavior type in the time series behavior node sequence, marking the abnormal behavior according to the behavior type, counting the abnormal marks in adjacent continuous records, filtering out abnormal node segments with three or more consecutive abnormal nodes, and recording the corresponding start and end node numbers to generate a continuous abnormal segment number group;

[0031] S413: Based on the continuous abnormal segment number group, the total value of the abnormal nodes is counted, and all abnormal nodes are aggregated to generate the number of behavior chain warning nodes.

[0032] As a further solution of the present invention, the specific steps for obtaining the rental vehicle planning table are as follows:

[0033] S511: Based on the number of warning nodes in the behavior chain and the number of reservation warning identifications, extract the corresponding user's abnormal behavior records and abnormal reservation records, and construct a joint abnormality indicator table indexed by the user number in combination with the user credit level corresponding to each record in the credit level adjustment record unit;

[0034] S512: Match the user number in the current vehicle resource request list with the joint abnormality index table, calculate the user's request priority, add a low priority mark to the user record with an abnormal identification mark, mark the remaining records as normal priority, and generate a vehicle request priority label set;

[0035] S513: According to the user request priority and vehicle resource information of each record in the vehicle request priority tag set, the request record is connected with the vehicle resources, and the available rental vehicles are allocated and sorted according to the priority to generate a rental vehicle planning table.

[0036] As a further solution of the present invention, the user request priority adopts the formula:

[0037]

[0038] Calculate, where P k Indicates that the user number in the joint abnormal index table is U k Request priority, X k Represents the total number of abnormal behavior nodes of the corresponding user, Y k Represents the number of abnormal reservations for the corresponding user. represents the adjustment value of the corresponding user's current credit rating, G is the total number of all users in the joint abnormality index table, X g represents the number of abnormal behavior nodes of the user in the g-th record, Y g Represents the number of abnormal reservations for the user in the g-th record. Represents the credit rating adjustment value of the user in the g-th record.

[0039] The intelligent management system for car rental vehicles includes:

[0040] The appointment warning recognition module obtains the appointment request time and the usage start time, calculates the time difference, compares it with the shortest appointment lead time, determines whether it is a warning behavior, and generates the appointment warning recognition number;

[0041] The credit rating adjustment module determines whether a credit rating change is triggered based on the comparison of the number of scheduled warning identifications with the upper limit of the periodic cumulative warning number, and generates a credit rating adjustment record unit;

[0042] The abnormal renewal marking module obtains the renewal trigger time, storage time, and return click time to determine whether the sequence relationship is abnormal. If so, it generates an abnormal renewal identification tag;

[0043] The behavior chain aggregation module combines the credit rating adjustment record unit and the abnormal lease renewal identification tag, calls the behavior timestamp, vehicle number, and behavior type to build a sequence, aggregates continuous abnormal behavior nodes, and generates the number of behavior chain warning nodes;

[0044] The request priority determination module marks the current vehicle request priority based on the number of warning nodes in the behavior chain, the number of reservation warning identification times and the credit level adjustment record unit, and generates a rental vehicle scheduling table.

[0045] Compared with the prior art, the advantages and positive effects of the present invention are:

[0046] In the present invention, short-term frequent reservation behaviors are identified through difference calculation, a behavior warning mechanism is introduced to enhance recognition sensitivity, abnormal renewal is determined based on the temporal relationship between return confirmation time and renewal operation, and the behavior screening capability in the rental process is improved. The behavior timestamp, vehicle number and behavior type are used to construct a node sequence, and continuous abnormal operations are aggregated to generate a behavior chain to achieve deep modeling of user behavior patterns. Combined with credit rating records and behavior chain characteristics, the priority of user resource requests is dynamically adjusted to control the interference of high-risk behaviors on resource scheduling. The linkage design of behavior recognition accuracy, temporal judgment logic and scheduling decision-making mechanism improves the warning response capability for abnormal behaviors and the pertinence of resource management, realizes the intelligent coordination of behavior risk constraints and resource allocation, and constructs a car rental management system with timeliness, hierarchy and self-adaptation. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 Schematic diagram of the steps of the present invention;

[0048] Figure 2 It is a system module diagram of the present invention. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0050] In the description of the present invention, it should be understood that the terms "length," "width," "up," "down," "front," "back," "left," "right," "vertical," "horizontal," "top," "bottom," "inside," "outside," and the like, indicating positions or relationships, are based on the positions or relationships shown in the accompanying drawings and are intended only to facilitate the description of the present invention and simplify the description. They do not indicate or imply that the devices or elements referred to must have a specific orientation, be constructed, or operate in a specific orientation. Therefore, they should not be construed as limiting the present invention. Furthermore, in the description of the present invention, "plurality" means two or more, unless otherwise expressly and specifically defined.

[0051] See also Figure 1 , the intelligent management method for car rental vehicles includes the following steps:

[0052] S1: Obtain the time when the user submits the reservation request on the platform and the start time of vehicle use, calculate the difference between the vehicle use start time and the reservation request time, and compare the difference with the shortest reservation lead time (e.g., 2 hours, determined based on industry standards or historical order data analysis). If the difference is less than the shortest reservation lead time, mark the corresponding user's reservation behavior as a warning behavior, and calculate the number of reservation warning identifications;

[0053] S2: Based on the number of scheduled warning recognitions, if the number of recognitions exceeds the upper limit of the cumulative warning number in the period (e.g., a maximum of 3 warnings are allowed per month), the credit rating downgrade process is triggered, the user's credit rating is confirmed, and the current operation behavior node number is bound to the vehicle number to generate a credit rating adjustment record unit;

[0054] S3: Obtain the renewal trigger time initiated by the user when the vehicle's current status is "Not Returned", call the vehicle's entry time and the return click time, and take the maximum of the two as the return confirmation time. Then, determine the order of the renewal trigger time and the return confirmation time. If the renewal trigger time is earlier than the return confirmation time, mark it as "abnormal renewal" and generate an abnormal renewal identification tag;

[0055] S4: Combine the credit rating adjustment record unit and the abnormal renewal identification tag to obtain the corresponding behavior timestamp, vehicle number, and behavior type, construct a behavior node sequence in chronological order, aggregate three or more consecutive abnormal nodes, and calculate the number of behavior chain warning nodes;

[0056] S5: Based on the number of warning nodes in the behavior chain, combined with the number of reservation warning identifications and the credit level in the credit level adjustment record unit, a priority judgment is performed on the user's current vehicle resource request, user requests with behavior warnings or credit adjustment records are marked as low priority, and a rental vehicle planning table is established.

[0057] The number of reservation warning identifications includes the density of abnormal behavior, trigger frequency threshold, and identification time dimension; the credit rating adjustment record unit includes the rating change type, bound behavior node number, and associated vehicle unique number; the abnormal renewal identification label includes the identification label type, trigger timestamp, and corresponding vehicle status code; the number of behavior chain warning nodes includes continuous node statistics, node behavior type aggregation, and node time series structure; the car rental vehicle planning table includes priority sorting results, user request level labeling, and vehicle allocation basis.

[0058] The specific steps of S1 are:

[0059] S111: Obtain the reservation request time submitted by the user on the platform and the vehicle use start time, calculate the time interval between the reservation request time and the vehicle use start time, count the time difference corresponding to each user reservation data, and generate the vehicle reservation advance time value;

[0060] To obtain the reservation request time and vehicle use start time submitted by the user on the platform, it is necessary to first retrieve the user ID, reservation submission time field, and vehicle reservation start time field corresponding to each reservation record from the platform database. The time value accurate to the minute is extracted using the timestamp format of the time field. During the execution process, the time difference between the reservation request time and the vehicle use start time is calculated. The two time fields are converted to numerical format using a unified time unit (such as minutes) and then subtracted. For example, in a reservation record, the reservation time is 09:30 on April 21, 2024, and the vehicle use start time is 08:00 on April 22, 2024. After conversion, the conversion results are 202404210930 and 202404220800, respectively. After further conversion to minutes, the conversion results are (9×60+30)+(21×24×60)=3090+30240=33330 minutes and (8×60)+(22×24×60).

[0061] =480+31680=32160 minutes, the subtraction results in a time difference of 1170 minutes, which is the vehicle reservation advance time value. After all records complete the above extraction and calculation process in sequence, all vehicle reservation advance time values are summarized in the form of a data list, and this value is used as the basic data source for subsequent screening and comparison.

[0062] S112: Compare the vehicle appointment lead time value with the shortest appointment lead time benchmark value one by one, filter out records whose time difference is less than the shortest appointment lead time benchmark value, create a record index, and generate a shortest lead time offset index set;

[0063] Based on the comparison of the vehicle appointment lead time value with the shortest appointment lead time benchmark value, a unified shortest appointment lead time benchmark value τmin must be set first. This benchmark value is configured with reference to the minimum acceptable appointment lead time limit in the platform service agreement, such as 720 minutes (i.e., 12 hours). Then, for each appointment record, the vehicle appointment lead time value δi calculated above is extracted and compared with τmin. That is, the judgment operation of δi < τmin is performed. For records with a "true" judgment result, its index value (which can be the database primary key or appointment number) is stored in a list set to form the shortest lead time offset index set. For example, if a user's appointment lead time value is 500 minutes, which is lower than the 720-minute threshold, the offset condition is met, and the index value "U000023" is added to the offset index set, resulting in a set such as {U000002, U000023, U000067}, which will serve as the basis for the next data extraction.

[0064] S113: Extracting corresponding record entries from the original user reservation data based on the shortest lead time offset index set, and counting the number of occurrences of the corresponding record within the current time window, and counting the number of abnormal lead time behavior records within the time window to generate the number of reservation warning identifications;

[0065] Extract corresponding record entries from the original user reservation data based on the shortest lead time offset index set. Each index value in the offset index set is used to locate the complete reservation record entry in the database through a data query statement. Extracted content includes at least the user ID, reservation time, usage start time, and reservation lead time value fields, and is marked as an "abnormal reservation record." Then, data statistics are performed within a sliding window based on the current system time T0 and the reservation times of historical reservation records. Set the sliding window length to twin (e.g., 7 days) and determine whether the reservation time falls within the time interval [T0 - twin, T0]. If so, it is counted as an abnormal behavior record. For example, if the current time is April 21, 2024, and the sliding window is 7 days, select records with reservation times between April 14 and April 21, 2024, and count their total number. If five reservation times meet the criteria among the abnormal records in the offset index set, the generated reservation warning identification count is 5, which will be used in the subsequent risk modeling and warning output stages.

[0066] The specific steps of S2 are:

[0067] S211: Based on the number of appointment warning identifications and the upper limit of the periodic cumulative warning number, a judgment operation is performed to extract the user indexes whose number of times exceeds the upper limit of the periodic cumulative warning number and form a set list to generate an over-limit warning user index set;

[0068] Based on the number of appointment warning recognitions and the upper limit of the cumulative warning number in a period, the judgment operation is performed. First, the number of appointment warning recognitions N for each user in a unit period (such as 30 days) needs to be extracted from the output results of the previous stage. u , and call the upper limit value N of the cumulative warning times set by the system max The upper limit can be set according to the platform operation specification and is set to 5 times. Then all users are compared one by one and the user index U is called. i And the corresponding recognition times N ui , the comparison operation is performed by judging whether N ui >N max To execute, for each user whose operation result is "true", the index U i Written into a temporary collection List e In this example, if users U001, U009, and U017 have 7, 6, and 3 warning identification records in the cycle respectively, the system determines that U001 and U009 meet the greater than upper limit condition and writes to List e , U017 is not processed, and after looping through all the user indexes and identification times, a list of over-limit warning user index sets is formed. e ={U001, U009}.

[0069] S212: Read the over-limit warning user index set and locate the credit rating status node in the current user database. Calculate the credit rating downgrade of the over-limit warning user based on the user's existing corresponding credit rating, confirm the current status, and generate a credit rating downgrade record.

[0070] Based on the user's existing corresponding credit rating, calculate the credit rating of the over-limit warning user, using the formula:

[0071]

[0072] Calculate the credit rating downgrade indicator value and confirm the current status, where: Represents the credit rating downgrade value of the user, N ui Represents user U i The number of appointment warning recognitions in a unit period, N max Represents the upper limit of the cumulative number of warnings in the set period. Represents user U i The current credit rating's hierarchical position in the credit rating system (e.g. A is 1, B is 2, and so on), T ui Represents user U i The number of days since registration on the platform, Represents user U iThe credit rating impact factor caused by each default behavior in the past k behavior nodes, N is the total number of historical behavior nodes included in the statistics, and j is the traversal index from 1 to N;

[0073] User U001 has 7 appointment warning recognitions in a unit period. The upper limit of the cumulative warning number in the period is set to 5 times. This upper limit is derived from the platform operation specifications. Based on the statistics of users' normal operation frequency, the proportion of users who have exceeded 5 times is 9.3%. The platform sets this as the warning threshold. Let:

[0074] N ui =7;

[0075] N max =5, then N ui -N max =2;

[0076] The user's current credit rating is B. In the platform's credit rating sequence, A is the highest, corresponding to the value 1. In order of numbering, B is 2, so:

[0077] Then there is

[0078] The user registered 210 days ago. The platform calculates the time difference between the account activation timestamp and the current system time. The timestamp difference is converted using the conversion unit to obtain the following:

[0079] T ui =210, so

[0080] The user has two violation records in the last three behavior nodes. The violation impact factor is generated by the platform's behavior risk control model score. The model is weighted based on factors such as the severity of the violation type, the duration of the behavior, and the frequency of intervention. The quantitative results are 1.2 and 1.8 respectively. The node without violation is recorded as 0. The average is:

[0081] N = 3;

[0082]

[0083] Substituting into the formula:

[0084]

[0085] The result shows that the credit rating downgrade index value of user U001 is 1.4132, which represents the composite intensity level of the credit rating adjustment caused by his current behavior and historical status. Combined with the platform's credit rating adjustment rules, if the index value is between 1.0 and 2.0, corresponding to a downgrade of one level, his credit rating will be downgraded from B to C, and this downgrade information will be recorded in the credit rating downgrade record.

[0086] The operational logic of the formula is based on the comprehensive quantification of the intensity of the violation and the user's credit characteristics, where the difference term N ui -N max Used to measure the number of warnings that a user has exceeded the system warning threshold in the current cycle, reflecting the frequency of abnormal behavior and the credit level value Multiplication shows that the lower the credit rating and the more frequent the behavior, the greater the impact. This product is used as the basic risk factor; the denominator is The purpose of performing square root operation is to introduce behavioral stability reduction weight for users with longer registration time. The longer the registration time, the greater the item, and the overall risk value is lowered, which plays a regulatory role. The average value of the default factor is finally added up. It is used to introduce historical behavior quality evaluation to avoid judging grade adjustments based solely on current cycle behavior. The overall structure achieves weight fusion between risk dimensions through weighted multiplication, square root reduction and mean accumulation. The calculation result is wrapped with absolute value to ensure its positive value and logical consistency.

[0087] S213: Extract the current behavior node number based on the credit rating downgrade record and the corresponding user index, and extract the vehicle number from the vehicle allocation record in conjunction with the vehicle allocation record, and bind them to generate a credit rating adjustment record unit;

[0088] According to the credit rating downgrade record and the corresponding user index, the current behavior node number is extracted, and the vehicle allocation record is linked to extract the vehicle number and bound to generate a credit rating adjustment record unit. First, from the credit rating downgrade record set Record l Read the user ID field U in each user record i , then locate the corresponding user's most recent behavior node number N in the behavior log table i The behavior node number is generated by the user's operation track number, such as the reservation behavior number, cancellation behavior number and other identifiers. The positioning method is to query the user behavior time sorting field T i , select the one with the largest time and extract its behavior node number. Next, query the vehicle usage record related to the user reservation in the vehicle dispatch record table and obtain the corresponding vehicle number C by matching the user ID field. iFor example, user U001 uses vehicle number C025 in the reservation record. Through query, it is found that vehicle C025 corresponds to behavior node N112, forming an associated triplet {U001, N112, C025}. This triplet is merged with the aforementioned credit rating downgrade value and written into the record unit to construct a complete field item {user ID, behavior node number, vehicle number, original credit rating, credit rating after downgrade, record time}, for example, generating a record unit {U001, N112, C025, B, C, 20240421}. After completing this operation for all downgrade records in sequence, a complete set of credit rating adjustment record units is obtained.

[0089] The specific steps of S3 are:

[0090] S311: Obtain all records of vehicles whose current status is not returned, filter the renewal request data submitted by the corresponding user, extract the renewal trigger time corresponding to each renewal request, and match the corresponding vehicle's entry time and return click time to generate a statistical collection of renewal and return times;

[0091] To obtain all records where the vehicle's current status is "Not Returned", we first need to filter out the records whose current status field is "Not Returned" from the vehicle status table. This field value is automatically updated by the system's vehicle status monitoring module. The filtering method uses an equal matching operation between the status field and the target value "Not Returned". The three main fields of vehicle number, associated user ID, and reservation record number are retained in the extraction result. Next, data is matched in the renewal request record table based on these vehicle numbers and user IDs. The matching condition is that the same user ID has one or more renewal application records under the same vehicle number. After filtering out the successfully matched renewal request data set, read the trigger time field T for each renewal request record. r Then, the return operation behavior record corresponding to the matching vehicle number is retrieved from the return behavior log table, which involves two key time fields: one is the operation time Tg recorded when the user clicks the return button, and the other is the actual physical storage time Ts of the vehicle, which respectively represent the system record time when the user subjectively initiates the return operation and the platform confirms that the vehicle has been stored. Both of these need to be extracted from the vehicle storage device record table and the user operation log table. Finally, the system records each renewal request with its matching vehicle number and corresponding T r , Tg, and Ts are associated one by one to form a combination of three time fields, forming a set of renewal and return time structure Record t ={T r , Tg, Ts}.

[0092] S312: Based on the vehicle storage time and the return click time of each record in the renewal and return time set, select the maximum value as the return confirmation time, and perform a sequential judgment on the return confirmation time and the renewal trigger time to filter out the records where the renewal trigger time is earlier than the return confirmation time, and generate renewal timing conflict records;

[0093] During the execution of selecting the maximum value as the return confirmation time based on the vehicle storage time and the return click time of each record in the renewal and return time set, the system sequentially compares Tg and Ts in each group of Record t to determine whether Tg > Ts holds. If it holds, the return confirmation time Tconf = Tg; otherwise, Tconf = Ts. This maximum value selection can be achieved by comparing the magnitudes between the two values, and the judgment is completed using simple conditional statements. After the execution, each group of renewal records can obtain its corresponding Tconf field. Next, compare this Tconf with the renewal trigger time T r sequentially, that is, perform a conditional judgment on each record to determine whether T r < Tconf holds. If it holds, it means that the renewal occurs before the return is not yet confirmed, there is a timing intersection, and the records that meet this condition will be marked as timing conflict records. The system records the conflict judgment result as "Yes", otherwise as "No". The example is as follows: In the record of a vehicle numbered C101, the renewal trigger time T r is 2024-04-19 14:05, the return click time Tg is 2024-04-19 14:30, and the vehicle storage time Ts is 2024-04-19 14:20. It is judged that the return confirmation time is Tconf = 14:30. Further judgment shows that T r < Tconf holds, and this record is included in the renewal timing conflict set List s .

[0094] S313: Extract the corresponding record numbers according to the renewal timing conflict records, construct the behavior status label of the corresponding conflict records in the current task record table, and mark them as abnormal renewals to generate abnormal renewal identification labels;

[0095] To extract the corresponding record numbers according to the renewal timing conflict records, the system first needs to retrieve from the renewal timing conflict set List sExtract the reservation number or renewal record number Rid bound to each record, and then enter the task record summary table. By performing an equal value matching operation on the field Rid, quickly locate the main record position of the conflicting record in the task table, attach the behavior status label field to the position, and write the "abnormal renewal" status value. At the same time, it is necessary to verify the content of the existing behavior status field to avoid duplicate label superposition. If the field is already "normal", it is directly replaced with "abnormal renewal". If other abnormal labels already exist, merge the labels or update them to multi-label status, such as "abnormal renewal; timed return". Each marking operation needs to be attached with an operation timestamp Tflag for subsequent operation tracing, and finally form an abnormal renewal identification label structure unit Record consisting of record number, status label and operation time. a ={Rid, "Abnormal lease renewal", Tflag}. In the example, the record number is R20240419237, and the corresponding conflict record marking time is 2024-04-2109:12:00. The generated label unit is {R20240419237, "Abnormal lease renewal", 2024-04-2109:12:00}. After all records are processed, a complete abnormal lease renewal identification label set is formed.

[0096] The specific steps of S4 are:

[0097] S411: Combine the credit rating adjustment record unit and the abnormal renewal identification tag to extract the corresponding behavior timestamp, vehicle number, and behavior type from the two types of records. Arrange all records in ascending chronological order based on the behavior timestamp, and aggregate the sorted record information into a single structure to generate a time-series behavior node sequence.

[0098] Combined with the credit rating adjustment record unit and the abnormal renewal identification tag, first extract the corresponding field information from the two record sets respectively. In the credit rating adjustment record unit, read the fields including user ID, behavior timestamp T1, vehicle number V1 and behavior type identifier L1 (such as "rating downgrade"), and extract the behavior timestamp T2, vehicle number V2, behavior type identifier L2 (such as "abnormal renewal") and user ID field from the abnormal renewal identification tag. After ensuring the uniformity of the field format, perform the field merge operation on the two sets to construct the intermediate behavior event set E = {(T i , V i , L i , U i )}, then all records in set E are sorted by timestamp field T i Perform ascending sorting operation, and call T in sorting mode iThe field is used as the primary key for sorting, and the time format is compared accurately to the second level. For example, after comparing T1 = 2025-04-1909:31:15 with T2 = 2025-04-1909:29:48, it is determined that T2 is ranked before T1. After all records are sorted, the index is re-arranged according to the sorting results, and a unified structure behavior node sequence S = {Node1, Node2, ..., Node n}, where each Node contains the field {serial number N i , timestamp T i 、Vehicle number V i , behavior type L i 、User ID i}, for example, the first record Node1 = {1, 2025-04-18 14:10:08, C101, abnormal renewal, U001}, the second record Node2 = {2, 2025-04-18 17:43:55, C101, level downgrade, U001}, and finally a complete temporal behavior node sequence structure S is generated.

[0099] S412: Read the behavior type in the time series behavior node sequence, mark the abnormal behavior according to the behavior type, count the abnormal marks in adjacent continuous records, filter out abnormal node segments with three or more consecutive abnormal nodes, and record the corresponding start and end node numbers to generate a continuous abnormal segment number group;

[0100] Read the behavior type in the sequence of sequential behavior nodes, for field L i Perform content recognition operations, and identify behaviors such as "abnormal renewal" and "illegal reduction" as abnormal behaviors, which are marked by adding an abnormal flag field B i , if L i For abnormal behavior type, then B i =1, otherwise 0, the system traverses the behavior node sequence S one by one and executes the judgment operation L i ∈ Abnormal behavior set E e If it is satisfied, it is marked as abnormal. After the traversal is completed, the behavior node sequence is converted into a sequence with abnormal flags S'={Node1(B1), Node2(B2), ...}. On this basis, the abnormal flags of adjacent consecutive nodes are counted and the consecutive B i Is it equal to 1? If three or more Bs appear in a row i =1 record segment, then the starting node of the segment is numbered N s and the ending node number N e Record to number group set List c ={(N s , N e)}, for example, in the four behavior nodes from node 3 to node 6, if B3=B4=B5=B6=1, it is counted as a continuous abnormal behavior segment, and the record number segment (3, 6) is written into List_c. The system traverses the entire node sequence according to this logic, and finally forms a complete continuous abnormal segment number group.

[0101] S413: Based on the continuous abnormal segment number group, the total value of the abnormal nodes is counted, and all abnormal nodes are aggregated to generate the number of behavior chain warning nodes;

[0102] Based on the continuous abnormal segment number group, first read all the number segments (N s , N e ), calculate the number of abnormal nodes in each segment n = N e -N s +1, perform accumulation operation by traversing the number group and counting the total number of abnormal nodes N total =∑(N ei -N si +1), for example, the number group includes (3, 6), (10, 12), then the total number of abnormal nodes is (6-3+1)+(12-10+1)=4+3=7, then the B of all nodes in S' is calculated. i =1 to filter, extract all abnormal node information, aggregate and build abnormal behavior chain set Chain = {Node i |B i =1}, count the number of elements in the set Chain again to confirm whether its length is the same as N total To ensure statistical consistency, the number of abnormal nodes N total Output as the number of warning nodes in the behavior chain, for example, the final number of warning nodes is 7.

[0103] The specific steps of S5 are:

[0104] S511: Based on the number of warning nodes in the behavior chain and the number of appointment warning identifications, the abnormal behavior records and abnormal appointment records of the corresponding user are extracted respectively, and the user credit level corresponding to each record in the credit level adjustment record unit is combined to construct a joint abnormality indicator table indexed by the user number;

[0105] Based on the number of behavior chain warning nodes and the number of appointment warning recognition times, the corresponding user's behavior abnormality records and appointment abnormality records are extracted respectively. First, the field {user number U i , the number of abnormal nodes A i}, the total number of abnormal nodes corresponding to each user is used as a quantitative indicator of the abnormal behavior intensity, and the field {user number U i , the number of abnormal appointments R i}, representing the frequency of reservation warning triggering recorded for the user within the period window, ensuring that both sets are matched with the user number as the index field. After a successful match, the data structure {U i , A i , R i}, then extract the field {User ID U i , current credit rating L i}, add this field to the above structure to form a complete record {U i , A i , R i , L i}, and construct a joint abnormality index table T with user number as the primary index key e In the actual example, if U013 has 5 abnormal behavior nodes, 3 abnormal reservations, and a credit rating of C, then the corresponding record {U013, 5, 3, C} is written into table T. e , which will be used for comprehensive behavioral assessment later.

[0106] S512: Match the user ID in the current vehicle resource request list with the joint abnormality index table to calculate the user's request priority, add a low priority flag to user records with abnormal identification flags, and mark the remaining records as normal priority to generate a vehicle request priority tag set;

[0107] The user's request priority is calculated using the formula:

[0108]

[0109] Calculate, where P k Indicates that the user number in the joint abnormal index table is U k Request priority, X k Represents the total number of abnormal behavior nodes of the corresponding user, Y k Represents the number of abnormal reservations for the corresponding user. represents the adjustment value of the corresponding user's current credit rating (credit ratings C, B, A, and S are mapped to 3, 2, 1, and 0 respectively), G is the total number of all users in the joint anomaly indicator table, and X g represents the number of abnormal behavior nodes of the user in the g-th record, Y g Represents the number of abnormal reservations for the user in the g-th record. Represents the credit rating adjustment value of the user in the g-th record.

[0110] The monitoring source is the data collected by the system behavior chain identification module within the period. The system records that the user behavior deviates from the expected path for a total of 5 times, which is recorded as X1=5;

[0111] The number of reservation anomalies comes from the record of the reservation warning identification module. The user triggers the reservation anomaly warning 3 times within the period window, which is recorded as Y1=3;

[0112] The credit rating is automatically adjusted by the credit adjustment unit according to the integral model. The corresponding rating of this user is C. The credit rating quantitative standard is: S→0, A→1, B→2, C→3, so

[0113] The total number of users in the joint anomaly index table is 5, denoted as G = 5;

[0114] The number of abnormal behavior nodes and abnormal reservation times of all users in the table are counted separately. The field values are as follows: User number U1: X1=5, Y1=3, User number U2: X2=2, Y2=1, User number U3: X3=4, Y3=2, User number U4: X4=1, Y4=0, User ID U5:

[0115] X5=0, Y5=1,

[0116] Substitute the first fractional term into the formula:

[0117]

[0118] Substitute the summation part of the second fraction term and calculate the numerator:

[0119]

[0120] Calculate the denominator

[0121] Calculate the second fractional value:

[0122]

[0123] Substituting the complete formula into the equation gives:

[0124] P1=|60.5-1.583|=58.917;

[0125] The result shows that the request priority characteristic value of user U1 is 58.917. The higher the value, the greater the abnormal intensity and the lower the priority should be. Therefore, this value is used as the core reference indicator for low priority identification judgment in the system. The system sets the threshold value to 40. The setting basis is derived from the priority characteristic value distribution statistics of all users in the joint abnormal index table within the period. After four consecutive periods of monitoring, the median M and standard deviation σ of the characteristic value are constructed for all records, and the upper bound of the distribution is calculated as M+1.2σ. The actual sampling value is calculated to be M≈24.5 and σ≈12.9, and the upper bound threshold is set to 40.98, rounded to 40. The threshold is dynamically adjusted with the fluctuation of indicators in different periods. When a high-density abnormal group appears, the overall value increases, otherwise it decreases. This threshold is used to distinguish the priority status of high-risk, medium-risk and low-risk users. If P1>40, the low priority mark is triggered, and the record priority field P1=0 is generated, which finally corresponds to the annotation result in the vehicle request priority label set generated in step S512.

[0126] The operational logic of the formula reflects the comprehensive weighted assessment of the intensity, frequency, and credit level of user abnormal behavior. The number of abnormal behavior nodes and the number of abnormal reservations are of equal importance. Therefore, the two are added together to form the total basic abnormality amount. Considering the sensitivity of reservation abnormalities in affecting resource scheduling, the number of reservation abnormalities is introduced into the multiple weight coefficient and multiplied by 2, thus forming X in the expression. k +2Y k The structure of , the overall square processing emphasizes the nonlinear amplification effect of abnormal behavior, so that high-frequency anomalies have a significant impact on priority. The denominator is processed by adding 1 to the user's credit level adjustment value and then taking the square root. The purpose is to nonlinearly compress the credit differences between different levels, avoid the linear dominance of the credit level value span on the priority, and ensure that high-level users have more reasonable buffer adjustments. The subsequent subtracted mean term constructs the group average state by aggregating the behavior and credit information of all users, and uses the sum of behavioral anomalies and appointment anomalies to construct the sum of the total behavioral value, and then uses the sum of the credit adjustment value plus 1 to construct the total credit adjustment amount. This structure constructs the overall abnormal baseline of the system in the form of the abnormal average / credit adjustment ratio to balance the relative position of the abnormal behavior of a single user in the group distribution. Finally, a non-negative value is formed through absolute value operation to ensure that all priority values have a unified directional output in the evaluation, which is convenient for subsequent docking with the threshold model to achieve identification and labeling.

[0127] S513: Based on the user request priority and vehicle resource information of each record in the vehicle request priority tag set, the request record is connected to the vehicle resources, and the available rental vehicles are allocated and sorted by priority to generate a rental vehicle planning table;

[0128] According to the user request priority and vehicle resource information of each record in the vehicle request priority tag set, the request record is connected to the vehicle resource. First, the available vehicle information set V = {V1, V2, ...} is extracted from the vehicle resource pool, and the basic resource number and status field are assigned to each vehicle. At the same time, the field {user number U i , request time T r , P i}, according to the priority mark P i All request records are divided into low priority group and normal priority group. First, i = 1, the record set is sorted in ascending order, and the sorting is based on the request time T r , for P i =0 records perform the same sorting operation. After completing the sorting of the two subsets, the resources are docked in order. The vehicle number is assigned to the normal group users first. The docking method is sequential binding, that is, the first request is bound to the first available vehicle in the sorting order. If the number of vehicles in the vehicle pool is insufficient, the low-priority group users cannot complete the binding, and the system records their request failure status. Finally, the rental vehicle planning table structure P is generated. o ={User Number U i , vehicle number V i , priority P i , docking results R o}, where R o = "Success" or "Failure". For example, if U021 successfully connects to vehicle V102, the record is {U021, V102, 1, Success}. If U013 fails to connect due to low priority and insufficient resources, the record is {U013, null, 0, Failure}.

[0129] See also Figure 2 , car rental vehicle intelligent management system, including:

[0130] The appointment warning recognition module obtains the appointment request time and the usage start time, calculates the time difference, compares it with the shortest appointment lead time, determines whether it is a warning behavior, and generates the appointment warning recognition number;

[0131] The credit rating adjustment module compares the number of scheduled warning identifications with the upper limit of the cumulative warning number in the period to determine whether a credit rating change is triggered and generates a credit rating adjustment record unit;

[0132] The abnormal renewal marking module obtains the renewal trigger time, storage time, and return click time to determine whether the sequence relationship is abnormal. If so, it generates an abnormal renewal identification tag;

[0133] The behavior chain aggregation module combines the credit rating adjustment record unit with the abnormal renewal identification tag, calls the behavior timestamp, vehicle number, and behavior type to build a sequence, aggregates continuous abnormal behavior nodes, and generates the number of behavior chain warning nodes;

[0134] The request priority determination module is based on the number of warning nodes in the behavior chain, combined with the number of reservation warning identifications and the credit level adjustment record unit, marking the current vehicle request priority and generating a rental vehicle scheduling table.

[0135] The above are merely preferred embodiments of the present invention and do not limit the present invention in any other form. Any technician familiar with the profession may use the technical content disclosed above to change or modify it into an equivalent embodiment with equivalent changes and apply it to other fields. However, any simple modification, equivalent change and modification made to the above embodiment based on the technical essence of the present invention without departing from the content of the technical solution of the present invention shall still fall within the scope of protection of the technical solution of the present invention.

Claims

1. The intelligent management method for rental vehicles is characterized by: The following steps are involved: S1: Obtain the time when the user submits the reservation request on the platform and the start time of vehicle use, calculate the difference and compare it with the shortest reservation lead time, mark the user's reservation warning behavior, and count the number of reservation warning recognitions; S2: Based on the number of scheduled warning identifications, if the number of identifications is greater than the upper limit of the cumulative warning number in the period, a credit rating downgrade process is triggered, the credit rating is bound to the vehicle number, and a credit rating adjustment record unit is generated; S3: Obtain the current status of the unreturned vehicle and record the renewal trigger time initiated by the user, determine the return confirmation time, compare the renewal trigger time with the return confirmation time, mark abnormal renewal behavior, and generate an abnormal renewal identification tag; S4: Combining the credit rating adjustment record unit and the abnormal lease renewal identification tag, obtaining the corresponding behavior timestamp, vehicle number, and behavior type, constructing a behavior node sequence, aggregating abnormal nodes, and statistically obtaining the number of behavior chain warning nodes; S5: Based on the number of warning nodes in the behavior chain, combined with the number of reservation warning identifications and the credit level in the credit level adjustment record unit, a priority judgment is performed on the user's current vehicle resource request to establish a rental vehicle planning table.

2. The intelligent management method for rental vehicles according to claim 1, characterized in that: The number of reservation warning identifications includes the density of abnormal behavior, the trigger frequency threshold, and the identification time dimension; the credit rating adjustment record unit includes the rating change type, the bound behavior node number, and the associated vehicle unique number; the abnormal renewal identification tag includes the identification tag type, the trigger timestamp, and the corresponding vehicle status code; the number of behavior chain warning nodes includes continuous node statistics, node behavior type aggregation, and node time series structure; the car rental vehicle planning table includes priority sorting results, user request level labels, and vehicle allocation basis.

3. The intelligent management method for rental vehicles according to claim 1, characterized in that: The specific steps to obtain the number of appointment warning recognition times are as follows: S111: Obtain the reservation request time submitted by the user on the platform and the vehicle use start time, calculate the time interval between the reservation request time and the vehicle use start time, count the time difference corresponding to each user reservation data, and generate the vehicle reservation advance time value; S112: Compare the vehicle appointment lead time value with the shortest appointment lead time benchmark value one by one, filter out records whose time difference is less than the shortest appointment lead time benchmark value, create a record index, and generate a shortest lead time offset index set; S113: extracting corresponding record entries from the original user reservation data according to the shortest lead time offset index set, and counting the number of occurrences of the corresponding record in the current time window, counting the number of lead time abnormal behavior records in the time window, and generating the number of reservation warning identifications.

4. The intelligent management method for rental vehicles according to claim 1, characterized in that: The specific steps for obtaining the credit rating adjustment record unit are as follows: S211: Based on the number of appointment warning identifications and the upper limit of the periodic cumulative warning number, a judgment operation is performed to extract user indexes whose number of times exceeds the upper limit of the periodic cumulative warning number and form a set list to generate an over-limit warning user index set; S212: Read the over-limit warning user index set and locate the credit rating status node in the current user database, calculate the credit rating downgrade of the over-limit warning user based on the user's existing corresponding credit rating, confirm the current status, and generate a credit rating downgrade record; S213: Extract the current behavior node number according to the credit rating downgrade record and the corresponding user index, and extract the vehicle number by linking the vehicle allocation record, and bind them to generate a credit rating adjustment record unit.

5. The intelligent management method for rental vehicles according to claim 4, characterized in that: The credit rating of the user with over-limit warning is calculated based on the user's existing corresponding credit rating, using the formula: Calculate the credit rating downgrade indicator value and confirm the current status, where: Represents the credit rating downgrade value of the user, N ui Represents user U i The number of appointment warning recognitions in a unit period, N max Represents the upper limit of the cumulative number of warnings in the set period. Represents user U i The hierarchical position value of the current credit rating in the credit rating system, T ui Represents user U i The number of days since registration on the platform, Represents user U i The credit rating impact factor caused by each default behavior in the past k behavior nodes, N is the total number of historical behavior nodes included in the statistics, and j is the traversal index from 1 to N.

6. The intelligent management method for rental vehicles according to claim 1, characterized in that: The specific steps to obtain the abnormal renewal identification tag are as follows: S311: Obtain all records of vehicles whose current status is not returned, filter the renewal request data submitted by the corresponding user, extract the renewal trigger time corresponding to each renewal request, and match the corresponding vehicle's entry time and return click time to generate a statistical collection of renewal and return times; S312: Based on the vehicle entry time and return click time of each record in the renewal and return time set, the maximum value is selected as the return confirmation time, and the return confirmation time and the renewal trigger time are sequentially judged to filter out records whose renewal trigger time is earlier than the return confirmation time, and generate a renewal timing conflict record; S313: extracting the corresponding record number according to the renewal timing conflict record, constructing the behavior state label of the corresponding conflict record in the current task record table, marking it as abnormal renewal, and generating an abnormal renewal identification label.

7. The intelligent management method for rental vehicles according to claim 1, characterized in that: The specific steps to obtain the number of behavior chain warning nodes are: S411: Combining the credit rating adjustment record unit and the abnormal lease renewal identification tag, extracting the corresponding behavior timestamps, vehicle numbers, and behavior types from the two types of records, sorting all records in ascending chronological order based on the behavior timestamps, and aggregating the sorted record information into a single structure to generate a time-series behavior node sequence; S412: Reading the behavior type in the time series behavior node sequence, marking the abnormal behavior according to the behavior type, counting the abnormal marks in adjacent continuous records, filtering out abnormal node segments with three or more consecutive abnormal nodes, and recording the corresponding start and end node numbers to generate a continuous abnormal segment number group; S413: Based on the continuous abnormal segment number group, the total value of the abnormal nodes is counted, and all abnormal nodes are aggregated to generate the number of behavior chain warning nodes.

8. The intelligent management method for rental vehicles according to claim 1, characterized in that: The specific steps to obtain the car rental vehicle planning table are as follows: S511: Based on the number of warning nodes in the behavior chain and the number of reservation warning identifications, extract the corresponding user's abnormal behavior records and abnormal reservation records, and construct a joint abnormality indicator table indexed by the user number in combination with the user credit level corresponding to each record in the credit level adjustment record unit; S512: Match the user number in the current vehicle resource request list with the joint abnormality index table, calculate the user's request priority, add a low priority mark to the user record with an abnormal identification mark, mark the remaining records as normal priority, and generate a vehicle request priority label set; S513: According to the user request priority and vehicle resource information of each record in the vehicle request priority tag set, the request record is connected with the vehicle resources, and the available rental vehicles are allocated and sorted according to the priority to generate a rental vehicle planning table.

9. The intelligent management method for rental vehicles according to claim 8, characterized in that: The user's request priority is calculated using the formula: Calculate, where P k Indicates that the user number in the joint abnormal index table is U k Request priority, X k Represents the total number of abnormal behavior nodes of the corresponding user, Y k Represents the number of abnormal reservations for the corresponding user. represents the adjustment value of the corresponding user's current credit rating, G is the total number of all users in the joint abnormality index table, X g represents the number of abnormal behavior nodes of the user in the g-th record, Y g Represents the number of abnormal reservations for the user in the g-th record. Represents the credit rating adjustment value of the user in the g-th record.

10. The intelligent management system for car rental vehicles is characterized by: The system is used to implement the intelligent management method for rental vehicles according to any one of claims 1 to 9, and the system includes: The appointment warning recognition module obtains the appointment request time and the usage start time, calculates the time difference, compares it with the shortest appointment lead time, determines whether it is a warning behavior, and generates the appointment warning recognition number; The credit rating adjustment module determines whether a credit rating change is triggered based on the comparison of the number of scheduled warning identifications with the upper limit of the periodic cumulative warning number, and generates a credit rating adjustment record unit; The abnormal renewal marking module obtains the renewal trigger time, storage time, and return click time to determine whether the sequence relationship is abnormal. If so, it generates an abnormal renewal identification tag; The behavior chain aggregation module combines the credit rating adjustment record unit and the abnormal lease renewal identification tag, calls the behavior timestamp, vehicle number, and behavior type to build a sequence, aggregates continuous abnormal behavior nodes, and generates the number of behavior chain warning nodes; The request priority determination module marks the current vehicle request priority based on the number of warning nodes in the behavior chain, the number of reservation warning identification times and the credit level adjustment record unit, and generates a rental vehicle scheduling table.

Images