Hospital vehicle parking scheduling method, apparatus and device, and medium

Abstract

The invention relates to a hospital vehicle parking scheduling method and device, equipment and a medium. According to the method, a data association model of a doctor-seeing type and a historical parking time length is established, a vehicle doctor-seeing type is dynamically matched to generate a personalized parking time limit, a parking priority score is adjusted in a linkage manner by combining real-time monitoring and an overtime punishment mechanism, and accurate matching of parking resources and medical demands is realized based on a time-phased differential allocation strategy, so that the parking efficiency is improved. The rationality and turnover efficiency of parking space distribution are effectively improved, and meanwhile, the duration prediction accuracy is continuously optimized through a closed-loop feedback mechanism, so that the comprehensive technical effects of relieving peak congestion, balancing resource utilization and constraining illegal behaviors are finally achieved.

Description

Technical Field

[0001] The present invention belongs to the technical field of traffic control, and in particular relates to a hospital vehicle parking scheduling method, device, equipment and medium. Background Art

[0002] In the current field of hospital parking management, traditional methods generally use fixed timekeeping rules or a simple first-come, first-served model to allocate parking resources. This model fails to fully consider the actual needs of different types of patients. For example, emergency patients require quick parking and longer stays, while general outpatient patients have more manageable stays. Due to the lack of in-depth analysis of patient behavior characteristics, the estimated parking time deviates significantly from the actual situation, resulting in low parking space turnover efficiency and the coexistence of vehicle queues and idle parking spaces during peak hours.

[0003] While existing parking management solutions based on reservations exist, they fail to effectively dynamically adjust priority strategies based on patient visit types. There's also a lack of intelligent coordination between the reservation system and real-time parking status, making it difficult to balance the parking needs of scheduled and non-scheduled patients during peak visit periods. Furthermore, traditional methods lack effective constraints on overstaying parking, leaving offending vehicles unrestricted, which compromises the fairness of subsequent parking resource allocation. Furthermore, existing systems generally lack a continuous optimization feedback loop, making it impossible to dynamically adjust parking duration prediction models based on historical data. This creates a dilemma in which resource scheduling strategies gradually become disconnected from actual conditions.

[0004] The above defects together lead to low utilization of hospital parking spaces, poor patient experience and high management costs. Summary of the Invention

[0005] Based on this, it is necessary to provide a hospital vehicle parking scheduling method, device, equipment and medium to address the above technical problems.

[0006] In a first aspect, the present application provides a hospital vehicle parking scheduling method, comprising:

[0007] Based on the historical time data in the pre-established medical visit type database, the expected parking time is determined for different medical visit types to form an initial time benchmark table;

[0008] Obtain the vehicle's visit type information based on the initial duration benchmark table; when the vehicle enters the parking area, match the expected parking duration value corresponding to the visit type information using a preset allocation strategy, and bind the expected parking duration value to the vehicle ID to generate a personalized parking time limit record;

[0009] Real-time monitoring of the vehicle's actual parking time. If the actual parking time exceeds the expected parking time in the personalized parking time limit record, a time-exceeded flag is triggered. The penalty status of the vehicle is determined by associating the time-exceeded flag with the vehicle identification.

[0010] Adjusting the next parking priority score of the vehicle according to the penalty status, and updating the adjusted next parking priority score into the priority database; wherein the next parking priority score is calculated according to a preset priority scoring rule;

[0011] Based on the next parking priority score in the priority database, parking spaces are allocated first to vehicles of scheduled patients with scores higher than the preset score threshold during peak hours, and the restriction rules are lifted during off-peak hours; among which, the restriction rules are to allocate parking spaces first to vehicles of scheduled patients with next parking priority scores higher than the preset score threshold.

[0012] In a second aspect, the present application further provides a hospital vehicle parking scheduling device, comprising:

[0013] A historical data analysis module is used to determine the expected parking duration for different types of medical visits based on the historical time data in the pre-established medical visit type database, and form an initial duration benchmark table;

[0014] The vehicle information processing module is used to obtain the vehicle's medical treatment type information based on the initial duration benchmark table; when the vehicle enters the parking area, it matches the expected parking duration value corresponding to the medical treatment type information through a preset allocation strategy, and binds the expected parking duration value to the vehicle identification to generate a personalized parking time limit record;

[0015] The parking duration monitoring module is used to monitor the actual parking duration of the vehicle in real time. If the actual parking duration exceeds the expected parking duration in the personalized parking time limit record, the duration exceeded flag is triggered. The penalty status of the vehicle is determined by associating the duration exceeded flag with the vehicle identification;

[0016] A priority score adjustment module is used to adjust the next parking priority score of the vehicle according to the penalty status and update the adjusted next parking priority score into the priority database; wherein the next parking priority score is calculated according to a preset priority score rule;

[0017] The parking space allocation control module is used to give priority to allocating parking spaces to vehicles of scheduled patients with scores higher than a preset score threshold during peak hours based on the next parking priority score in the priority database, and to cancel the restriction rules during off-peak hours; wherein the restriction rule is to give priority to allocating parking spaces to vehicles of scheduled patients with scores higher than a preset score threshold for the next parking priority.

[0018] In a third aspect, the present application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, a hospital vehicle parking scheduling method as in the first aspect is implemented.

[0019] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a hospital vehicle parking scheduling method as in the first aspect.

[0020] The above-mentioned hospital vehicle parking scheduling method, device, equipment and medium establish a data association model between medical treatment type and historical parking time, dynamically match vehicle medical treatment type to generate personalized parking time limit, combine real-time monitoring with overtime penalty mechanism to adjust parking priority score, and based on differentiated allocation strategy by time period, realize accurate matching of parking resources and medical needs, effectively improve the rationality of parking space allocation and turnover efficiency, and continuously optimize the accuracy of time prediction through closed-loop feedback mechanism, ultimately achieving the comprehensive technical effect of alleviating peak congestion, balancing resource utilization and restraining illegal behavior. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0022] Figure 1 A schematic flow chart of a hospital vehicle parking scheduling method provided by the present invention;

[0023] Figure 2 A schematic diagram of a flow chart for determining a penalty status of a vehicle in an optional embodiment of the present invention;

[0024] Figure 3 This is a structural schematic diagram of a hospital vehicle parking scheduling device provided by the present invention. DETAILED DESCRIPTION

[0025] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0026] refer to Figure 1 , which presents a flow chart of a hospital vehicle parking scheduling method provided by this application, the method comprising the following steps:

[0027] S1. Based on the historical time data in the pre-established medical consultation type database, the expected parking time is determined for different medical consultation types to form an initial time benchmark table.

[0028] Specifically, a visit type database is pre-established to collect historical time data for different visit types (such as emergency, outpatient, and inpatient). This data covers the entire process from patient entry to exit of the hospital parking area, including time spent searching for a parking space, parking, visiting the hospital, and retrieving the vehicle. This historical data is analyzed and mined using statistical methods, such as calculating the mean, median, and standard deviation. Taking into account the data's distributional characteristics, a reasonable expected parking time is determined for each visit type. For example, for emergency patients, given their urgency and the need for quick parking and potentially prolonged stays, the average parking time is calculated based on historical data, with an appropriate buffer time added to determine the expected parking time. For general outpatient patients, whose stays are relatively manageable, a relatively short and accurate expected parking time is determined based on data such as the outpatient visit process and waiting times. Different visit types and their corresponding expected parking times are organized into an initial time benchmark table. This table serves as the basis for subsequent parking time allocations and is stored in the system's database for easy access by the scheduling algorithm.

[0029] S2. Obtain the vehicle's visit type information based on the initial duration benchmark table; when the vehicle enters the parking area, match the expected parking duration value corresponding to the visit type information through a preset allocation strategy, and bind the expected parking duration value to the vehicle identification to generate a personalized parking time limit record.

[0030] Specifically, when a vehicle approaches the hospital parking area, it first passes through the hospital's entrance identification system. The system can use license plate recognition technology combined with the hospital's medical appointment information or patient registration information to obtain the vehicle's medical treatment type. For example, when the patient makes an appointment, the system has already recorded his or her medical treatment type. When the vehicle enters, the medical treatment type information is quickly obtained by associating the license plate with the appointment information. At the moment the vehicle enters the parking area, the expected parking time value corresponding to the medical treatment type is retrieved from the initial time reference table. At the same time, the vehicle identification (such as the license plate number) is bound to the expected parking time value to generate a personalized parking time limit record. This process can be achieved through the background's fast data matching and binding algorithm to ensure that the vehicle can immediately obtain accurate parking time limits after entering the parking area, providing a basis for subsequent parking monitoring and management.

[0031] S3. Real-time monitoring of the actual parking time of the vehicle. If the actual parking time exceeds the expected parking time in the personalized parking time limit record, a time-exceeded flag is triggered; and the penalty status of the vehicle is determined by associating the time-exceeded flag with the vehicle identification.

[0032] Specifically, during the parking process, the actual parking time of the vehicle is monitored in real time through the parking space sensor and the time timing module. The parking space sensor is installed on each parking space and can accurately detect whether the vehicle is parked in the parking space. After detecting that the vehicle is parked, the timing starts. When the timing reaches the expected parking time value in the personalized parking time limit record, the time limit exceeded flag is automatically triggered. This flag is associated with the vehicle identifier as a status identifier. At this time, the penalty status of the vehicle is further determined. For example, for vehicles that exceed the parking time, they are marked as "overdue parking" status. This status will affect the vehicle's subsequent parking priority score. A real-time data update mechanism can be used to ensure that the parking status of the vehicle can be recorded and updated in a timely and accurate manner when the vehicle exceeds the time limit, providing data support for subsequent penalty measures and priority adjustments.

[0033] S4. Adjust the next parking priority score of the vehicle according to the penalty status, and update the adjusted next parking priority score into the priority database; wherein the next parking priority score is calculated according to a preset priority scoring rule.

[0034] Specifically, priority scoring rules can take into account a variety of factors, such as the vehicle's visit type, historical parking behavior (including frequent overstays), and reservation status. For example, for vehicles that frequently overstay, their next parking priority score will be appropriately lowered; while for vehicles that adhere to parking time regulations, their scores will be maintained or appropriately increased. The adjusted next parking priority score is updated through a data update operation in the priority database, which stores parking priority score information for all vehicles and provides a basis for subsequent parking space allocation decisions.

[0035] S5. Based on the next parking priority score in the priority database, parking spaces are preferentially allocated to vehicles of scheduled patients with scores higher than a preset score threshold during peak hours, and the restriction rules are canceled during off-peak hours; wherein the restriction rule is to preferentially allocate parking spaces to vehicles of scheduled patients with next parking priority scores higher than a preset score threshold.

[0036] Specifically, during peak hours, parking spaces are preferentially allocated to vehicles with scheduled patients whose scores exceed a preset threshold, based on the next parking priority score in the priority database. This threshold can be determined by analyzing historical data and evaluating the hospital's parking resources and patient flow. For example, a reasonable threshold, such as 80 points (out of 100), can be determined based on parking supply and demand during previous peak hours and patient appointment data to ensure that limited parking resources are allocated first to high-priority vehicles with greater need. During off-peak hours, the restriction rule is lifted, disregarding vehicle priority scores, and allowing all vehicles (including scheduled and non-scheduled vehicles) to use parking spaces on a first-come, first-served basis. This dynamic parking allocation strategy can effectively improve the utilization efficiency of hospital parking resources, alleviating parking pressure during peak hours and ensuring the parking needs of critically ill patients, while fully utilizing available spaces during off-peak hours to improve parking turnover. By monitoring parking flow and space occupancy during the current period in real time, the parking allocation mode is automatically switched, achieving intelligent parking scheduling and management for hospital vehicles.

[0037] The above-mentioned hospital vehicle parking scheduling method establishes a data association model between medical treatment types and historical parking durations, dynamically matches vehicle medical treatment types to generate personalized parking time limits, combines real-time monitoring with an overtime penalty mechanism to adjust parking priority scores, and uses differentiated allocation strategies based on time periods to achieve precise matching of parking resources with medical needs, effectively improving the rationality and turnover efficiency of parking space allocation. At the same time, it continuously optimizes the accuracy of time prediction through a closed-loop feedback mechanism, ultimately achieving the comprehensive technical effects of alleviating peak congestion, balancing resource utilization, and restraining violations.

[0038] In an optional embodiment, step S1 of "determining expected parking duration values ​​for different visit types based on historical time data in a pre-established visit type database to form an initial duration benchmark table" includes the following steps:

[0039] S11. Extract historical time records of various types of medical consultations from the medical consultation type database, organize the historical time records of each medical consultation type, and generate a preliminary time dataset.

[0040] Specifically, the visit type database covers vehicle parking time records for various hospital departments and various types of visits, including the time span from the vehicle entering the hospital parking area to leaving, the patient's visit type, the visit department, registration status, actual visit duration, and other related data. Using a preset data extraction algorithm, the corresponding historical time records are accurately screened and extracted from the database based on the key field of visit type. Data cleaning techniques are then used to remove duplicate, erroneous, or incomplete data items. The remaining valid data is then classified and aggregated according to dimensions such as chronological order and visit type segmentation, ultimately generating a preliminary time dataset for each visit type.

[0041] S12. Calculate the average time value for each type of medical consultation based on the preliminary time dataset and determine the time characteristic value.

[0042] Specifically, after obtaining the preliminary time data set, mathematical statistical methods are used to calculate the arithmetic mean of all historical time data for each type of medical consultation, that is, the average time value. The calculation process can follow the formula: average time value = (the sum of all historical time data for this type of medical consultation) / (the number of historical time data for this type of medical consultation). At the same time, the data distribution characteristics can be further analyzed, such as calculating the standard deviation to evaluate the degree of dispersion of the data, so as to determine the time characteristic value that can represent the typical parking time situation of this type of medical consultation. This characteristic value not only includes the average time value, but can also be combined with statistical indicators such as the median and mode to comprehensively reflect the parking time pattern of this type of medical consultation.

[0043] S13. Derived from the time characteristic value, the expected parking duration value for each type of medical visit is obtained to obtain the duration prediction result.

[0044] Specifically, a mathematical deduction model is established based on the determined time characteristic values, combined with the hospital's operating experience and medical treatment process. For example, taking into account the extra time spent by patients walking to the treatment area after parking, returning to the vehicle after the treatment, and picking up the vehicle and leaving, the time characteristic value is amplified and corrected according to a certain ratio (such as 1.2 times the average time value), so as to derive the expected parking time value for each type of medical treatment. At the same time, for special types of medical treatment (such as chronic patients who need multiple follow-up visits), a time buffer coefficient is introduced to further optimize the calculation logic of the expected parking time value, ensuring that the time prediction results can not only meet the actual parking needs of patients, but also avoid the waste of resources caused by excessive reservation of parking spaces, and ultimately obtain more accurate time prediction results.

[0045] S14. Based on the duration prediction results, construct initial duration benchmark data to form an initial duration benchmark table.

[0046] Specifically, the expected parking time values ​​for various types of medical consultations are organized according to a preset data structure to construct an initial time benchmark data record containing the medical consultation type, the corresponding expected parking time value, and other relevant attributes (such as the scope of applicable departments, priority weight, etc.). Through the database table structure design, these records are stored in the specified database table to form an initial time benchmark table with a complete structure and detailed content. The table can use a key-value pair association method, with the medical consultation type as the unique identification key, to quickly retrieve the corresponding expected parking time value, and provide efficient data query services for the personalized parking time limit allocation when subsequent vehicles enter the parking area, ensuring that the dispatch system can implement differentiated parking management strategies for vehicles with different medical consultation types based on accurate time benchmarks.

[0047] S15. When the deviation between the parking time of a certain type of medical visit and the expected parking time exceeds a preset threshold, the expected parking time of the certain type of medical visit is adjusted through a regression analysis model to obtain a corrected parking time benchmark value.

[0048] Specifically, the actual parking time data of each type of medical consultation is monitored in real time, and compared with the expected values ​​in the initial time benchmark table. When it is detected that the deviation between the average actual parking time of a certain type of medical consultation and the expected value exceeds the preset numerical threshold, the model adjustment mechanism is triggered. At this time, the regression analysis model is called, based on the historical time dataset, with the actual parking time as the dependent variable, and the relevant characteristics of the medical consultation type (such as the medical department, registration time period, patient age distribution, etc.) as the independent variable, to construct a multivariate linear regression model or a nonlinear regression model, and estimate and optimize the model parameters through algorithms such as the least squares method, and refit the expected parking time value of the medical consultation type. After multiple rounds of iterative calculation and verification to ensure that the prediction accuracy of the model reaches the preset standard, the revised time benchmark value is output. This value is closer to the actual trend of changes in parking demand and provides a scientific basis for the dynamic update of the time benchmark table.

[0049] S16. Update the initial duration reference table according to the corrected duration reference value.

[0050] Specifically, the revised duration benchmark value replaces the original expected parking duration value for the corresponding visit type in the initial duration benchmark table. The update process follows the transaction management mechanism to ensure the consistency and integrity of the data. Before the update operation is completed, the relevant data records are locked to prevent data conflicts or incorrect readings caused by concurrent operations. At the same time, log information of the update operation is recorded, including key data such as the update time, the type of visit involved, and the change in the duration benchmark value before and after the correction, so as to facilitate subsequent data audits, model effect evaluations, and system optimization tracing. Through this dynamic update mechanism, the initial duration benchmark table can continuously reflect the actual changes in the hospital's parking needs, continuously improve the adaptability and accuracy of the parking scheduling system, and realize the refined and intelligent management of the hospital's vehicle parking resources.

[0051] In an optional embodiment, step S2 of "obtaining the vehicle's medical visit type information based on the initial duration benchmark table; when the vehicle enters the parking area, matching the expected parking duration value corresponding to the medical visit type information using a preset allocation strategy, and binding the expected parking duration value to the vehicle identification to generate a personalized parking time limit record" includes the following steps:

[0052] S21. Extract the medical consultation type information related to the current vehicle from the initial duration benchmark table, and generate basic duration information based on the time when the vehicle enters the parking area.

[0053] Specifically, when a vehicle triggers the sensor at the entrance to the parking area or is identified by the license plate recognition system at the entrance, the information acquisition process is initiated. On the one hand, the patient's medical information associated with the vehicle is retrieved from data sources such as the hospital's medical registration system and appointment platform to accurately locate the type of medical treatment (such as emergency, outpatient, inpatient, etc.). This medical information can be associated with the vehicle information (such as the license plate number) and stored in the hospital database when the patient makes an appointment or registers for admission. On the other hand, the time when the vehicle enters the parking area is accurately recorded. This time is provided by a high-precision clock module to ensure the accuracy of the time recording. The extracted medical treatment type is integrated with the entry time to form basic duration information, which is temporarily stored in the memory in the form of a data structure.

[0054] S22. Based on the basic duration information, the visit type is matched with the expected parking duration value in the initial duration benchmark table through an automatic comparison mechanism to determine the preliminary parking time limit.

[0055] Specifically, the visit type in the basic duration information is used as the query key and matched one by one with the visit type field in the initial duration benchmark table. The initial duration benchmark table is stored in a structured form in the database, which contains the visit type, the corresponding expected parking duration value, and other related attributes. The comparison process follows the preset matching rules, such as exact matching of the visit type name or comparison by visit type code. After a successful match, the expected parking duration value corresponding to the visit type is extracted, and combined with the vehicle entry time for calculation (such as entry time + expected parking duration value), the expected departure time of the vehicle is obtained, thereby determining the preliminary parking time limit.

[0056] S23. When the preliminary parking time limit exceeds a preset time threshold, the preliminary parking time limit is corrected through a logic judgment mechanism to generate corrected parking time limit data.

[0057] Specifically, a time threshold is set in advance based on the hospital's operating strategy and parking resource conditions. This threshold takes into account factors such as the hospital's average patient flow, parking turnover rate, and reasonable parking needs of different types of vehicles. For example, for peak hours during the day on weekdays, the time threshold can be set to a relatively short time (such as 2 hours) to speed up parking turnover; while for nighttime or off-peak hours, the threshold can be appropriately relaxed (such as 3 hours). After the preliminary parking time limit is determined, the preliminary parking time limit will be compared with the corresponding time threshold. If the threshold is exceeded, the correction mechanism is triggered. The correction logic is based on multiple factors, such as the vehicle's historical parking behavior (querying the vehicle's past parking time records from the database), the parking space occupancy rate of the current parking area (obtaining the ratio of the number of vacant parking spaces to the total number of parking spaces in real time through parking sensors), and the hospital's dynamic management strategy (such as temporary adjustments to the medical process, parking time limits, etc.). According to the preset correction algorithm (such as the linear reduction method: corrected time = time threshold × weight coefficient + initial parking time limit × (1-weight coefficient), the weight coefficient can be set between 0.6-0.8 based on experience), the initial parking time limit is reasonably corrected to generate corrected parking time limit data that is more in line with actual needs and management requirements.

[0058] S24. Uniquely associate the corrected parking time limit data with the vehicle identification to generate a personalized parking time limit record.

[0059] Specifically, an association algorithm is used, with the vehicle identification (which can be the license plate number) as the primary key, to establish a unique mapping relationship between the corrected parking time limit data and it. This association operation is performed in the database management system in the form of a transaction to ensure data consistency and integrity. The generated personalized parking time limit record contains key fields such as vehicle identification, corrected parking time limit, corresponding medical treatment type, and record generation timestamp, and is stored in a dedicated parking time limit record database table. At the same time, to facilitate subsequent queries and management, an index is automatically created to speed up data retrieval based on fields such as vehicle identification and parking time limit. This personalized parking time limit record will serve as the only time certificate for the vehicle's stay in the parking area. Subsequent parking monitoring, timeout judgment, and parking space recovery operations all rely on this record for precise management to ensure the rational allocation and efficient utilization of hospital parking resources.

[0060] refer to Figure 2 In an optional embodiment, step S3 of "monitoring the actual parking time of the vehicle in real time, triggering a time-exceeded flag if the actual parking time exceeds the expected parking time in the personalized parking time limit record; and determining the penalty status of the vehicle by associating the time-exceeded flag with the vehicle identification" includes the following steps:

[0061] S31. Acquire actual parking time data of the vehicle in the parking area, compare the actual parking time data with the expected parking time value in the personalized parking time limit record, and obtain a preliminary time comparison result.

[0062] Specifically, after a vehicle enters a parking area, the parking status is monitored in real time using a parking sensor. A timing module records the vehicle's parking start time and current time, and the difference between the two is calculated to obtain the actual parking duration data. Simultaneously, the vehicle's corresponding expected parking duration is retrieved from the personalized parking time limit record database. Using a data comparison algorithm, the actual parking duration data is compared bit by bit with the expected value to produce a preliminary duration comparison result, which includes information such as the actual parking duration, the expected parking duration, and the time difference between the two.

[0063] S32. When the preliminary time comparison result shows that the actual parking time exceeds the expected time limit, activate the time-exceeded sign, bind the time-exceeded sign to the corresponding vehicle identification, and mark it as a preliminary penalty state.

[0064] Specifically, first set the judgment rules for time exceedance. When the preliminary time comparison result shows that the actual parking time exceeds the expected value, the corresponding event processing process is triggered. The time exceedance flag is a state identifier stored in the status register in the memory, and the initial state is inactive. Set the flag to the active state, and through the association algorithm, uniquely bind the activated flag to the vehicle identification (such as the license plate number). The binding operation can be achieved by establishing a data index. At the same time, the timeout event is marked as a preliminary penalty state. The state record contains information such as the time when the timeout occurred, the timeout duration, and the vehicle location, which is stored in the timeout event database.

[0065] S33. Based on the preliminary penalty status, extract past parking behavior records related to the vehicle identification from historical parking data; determine whether there are repeated exceeding situations based on the past parking behavior records, and generate behavior pattern analysis results.

[0066] Specifically, using the vehicle identification as the query condition, all parking behavior records of the vehicle since the first parking are extracted from the historical parking database. The historical parking database contains detailed information on all previous parkings of the vehicle, such as parking time, parking duration, whether it has exceeded the time limit, and the duration of the overtime. The extracted historical parking behavior records are analyzed using the time series analysis method to count the number of timeouts, distribution of timeout durations, and other characteristics of the vehicle in different time periods. By setting the judgment rules for repeated exceeding (such as the number of timeouts ≥ 3 times in the last 30 days, or there are timeout records every day for 7 consecutive days), it is determined whether the vehicle has repeated exceeding the limit. The analysis results are output in the form of a behavior pattern analysis report, which includes the vehicle's timeout frequency, timeout duration trend chart, repeated exceeding judgment conclusions, and other content.

[0067] S34. When the behavior pattern analysis results show repeated violations, determine the frequency level of the violations, and determine whether to trigger the authority adjustment rules based on the preset threshold range to generate a final penalty status; wherein the final penalty status includes at least one of the following: only recording the current timeout behavior, reducing the parking priority score based on the frequency level of the violations, and triggering the parking authority restriction mechanism.

[0068] Specifically, based on the conclusions regarding repeated violations in the behavioral pattern analysis report, the frequency level of violations is further determined. The frequency levels of violations are categorized according to preset grading criteria. For example, Level I (low frequency) indicates 1-2 violations per month; Level II (medium frequency) indicates 3-5 violations per month; and Level III (high frequency) indicates 6 or more violations per month. The corresponding frequency level is matched based on the vehicle's actual number of violations. Furthermore, pre-defined permission adjustment rules are implemented, including thresholds for triggering penalty measures corresponding to different frequency levels. For example, for Level I, only the current violation is recorded, and no other penalty measures are taken. For Level II, the parking priority score is lowered by 5-10 points (out of a total of 100 points). For Level III, in addition to point deductions, parking permission restriction mechanisms are also triggered, such as limiting the vehicle's reserved parking privileges during peak hours or shortening its maximum permitted parking duration. The rule engine compares the frequency level of violations with the preset threshold range, automatically determining whether the corresponding permission adjustment rule has been triggered, and generating the final penalty status. The final penalty status information will be updated to the vehicle's parking management file, affecting its subsequent parking service experience and resource allocation priority, thereby achieving effective restraint and management of overtime parking behavior and ensuring fair and reasonable use of hospital parking resources.

[0069] In an optional embodiment, the hospital vehicle parking scheduling method further includes the following steps:

[0070] S61. Obtain the allocation records for off-peak hours and the allocation logs for peak hours from the medical consultation type database, combine the medical consultation type classification information, organize the parking duration distribution in different time periods, and generate a preliminary duration distribution data set.

[0071] Specifically, based on pre-set time interval division rules, a 24-hour day or a seven-day weektime range is divided into peak and off-peak periods. Peak periods can be determined based on the hospital's historical patient traffic data, such as weekday peak hours from 7:00 AM to 10:00 AM and 3:00 PM to 6:00 PM; off-peak periods are the remaining time periods. Vehicle allocation records and log information for corresponding time periods are filtered from the patient type database. These records contain key data such as the patient type, precise timestamps of vehicle entry and exit from the parking area, and actual parking duration. Combined with the categorical codes of the patient type (e.g., emergency code "001" and outpatient code "002"), the filtered data is cross-aggregated by both patient type and time period. Using pivot table techniques, statistical indicators such as the frequency distribution, mean, maximum and minimum values ​​of parking duration for each patient type during peak and off-peak periods are calculated to generate a structured preliminary parking duration distribution dataset. This dataset is stored in a two-dimensional table format, with rows representing different patient types and columns corresponding to various parking duration statistical indicators during peak and off-peak periods.

[0072] S62. Incrementally update the historical time usage data through a timed refresh mechanism, integrate the priority scoring rules to determine data integrity, and generate an updated duration distribution set.

[0073] Specifically, scheduled refresh tasks are pre-set, such as executing a data refresh every hour or every morning. The refresh process first connects to the visit type database and uses SQL incremental queries (e.g., using the data change log since the last refresh timestamp) to retrieve newly added parking allocation records since the last refresh. These newly added records are pre-processed according to the established data processing process (including data cleaning, error correction, and formatting) and then merged with the initial duration distribution dataset. During the merging process, priority scoring rules are invoked to verify the integrity of the merged data. Priority scoring rules not only include the calculation logic for expected parking durations but also specify the fields that must be included in data records (e.g., vehicle ID, visit type, and parking duration) and their acceptable value ranges (e.g., parking duration cannot be negative). Records with missing key fields or outliers are corrected according to a pre-defined filling strategy (e.g., filling missing duration fields with the average parking duration for that visit type during the corresponding time period) to ensure data integrity. The verified and corrected dataset is marked as the updated duration distribution set, replacing the original dataset and providing the latest data support for subsequent fluctuation analysis and strategy optimization.

[0074] S63. Based on the parking duration distribution set, if the parking duration fluctuation exceeds a preset fluctuation threshold, the expected parking duration value is adjusted to generate an adjusted prediction data set.

[0075] Specifically, the parking duration data within the duration distribution set is monitored in real time. The fluctuation threshold can be set based on the hospital's operational policies, the flexibility of parking resources, and the natural variability of historical data. For example, the parking duration fluctuation threshold for emergency vehicles can be set to ±10 minutes, while for outpatient vehicles, it can be relaxed to ±20 minutes. When the average parking duration for a particular visit type during a specific time period deviates from the expected value in the initial duration benchmark table by more than the fluctuation threshold (calculated using the formula: fluctuation amplitude = (actual average parking duration - expected parking duration) / expected parking duration × 100%), an adjustment process for the expected parking duration is triggered. The adjustment algorithm can employ a time decay model, assigning a higher weight to recent data and combining historical adjustment records to calculate a new expected parking duration value. For example, the new expected value = (historical expected value × α) + (actual average parking duration × (1-α)), where α is the decay coefficient and can be between 0.7 and 0.9. After the adjusted expected values ​​are verified to ensure their rationality (e.g., they cannot be lower than the minimum actual parking duration for that visit type during the corresponding time period), an adjusted prediction dataset is generated. This dataset contains the updated expected parking duration values ​​for each visit type at different time periods, providing an accurate prediction basis for optimizing parking allocation strategies.

[0076] S64. Extract parking duration features from the adjusted prediction data set; and obtain classification prediction results based on the parking duration features.

[0077] Specifically, based on the data in the adjusted prediction dataset, a feature extraction algorithm is used to extract parking duration features for each visit type and time period combination. These features may include statistical features such as the mean, variance, skewness (reflecting the symmetry of the data distribution), kurtosis (reflecting the steepness of the data distribution), and quantiles of parking duration (such as 25%, 50%, and 75% quantiles). They may also include periodic variation characteristics of parking duration (such as the difference between weekdays and weekends, holiday patterns, etc.). Dimensionality reduction techniques such as principal component analysis (PCA) are used to convert high-dimensional feature datasets into low-dimensional feature vectors, highlighting the main features while reducing data complexity. The extracted feature vectors are input into pre-trained machine learning classification models, such as support vector machines (SVM) or random forest models, which are trained based on the correspondence between features in historical data and actual parking demand patterns. The model outputs classified prediction results. For example, it divides the parking demand patterns of medical visits into categories such as "high demand and long duration", "medium demand and moderate duration", and "low demand and short duration", providing fine-grained demand classification information for the optimization of allocation strategies.

[0078] S65. Optimize the allocation strategy based on the classification prediction results.

[0079] Specifically, based on the classification prediction results, the existing parking allocation strategy is optimized and adjusted in various aspects. For visit types predicted as "high demand and long duration," the proportion of dedicated parking spaces can be increased during peak hours, or the expected parking duration can be adjusted to provide more parking time. During off-peak hours, parking duration restrictions can be appropriately relaxed to improve parking space utilization. For visit types predicted as "medium demand and moderate duration," the existing allocation strategy is maintained, but the expected duration is regularly fine-tuned based on actual data. For visit types predicted as "low demand and short duration," some of their spaces can be flexibly allocated to other high-demand visit types during peak hours, while maintaining a certain number of spaces reserved during off-peak hours to meet basic needs. The optimized allocation strategy is stored as a rule set in a strategy library. Each time a vehicle enters the parking area, the optimized strategy rules are matched based on the visit type and the current time of day, accurately allocating parking duration and space resources. At the same time, a feedback loop is established to continuously collect parking data after the optimization strategy is implemented, which is used to evaluate the optimization effect, form a closed-loop management, and continuously iterate to improve the rationality and effectiveness of the allocation strategy, thereby maximizing the utilization efficiency of the hospital's parking resources, improving patients' medical experience, and reducing the hospital's operating and management costs.

[0080] The above-mentioned hospital vehicle parking scheduling method establishes a data association model between medical treatment types and historical parking durations, dynamically matches vehicle medical treatment types to generate personalized parking time limits, combines real-time monitoring with an overtime penalty mechanism to adjust parking priority scores, and uses differentiated allocation strategies based on time periods to achieve precise matching of parking resources with medical needs, effectively improving the rationality and turnover efficiency of parking space allocation. At the same time, it continuously optimizes the accuracy of time prediction through a closed-loop feedback mechanism, ultimately achieving the comprehensive technical effects of alleviating peak congestion, balancing resource utilization, and restraining violations.

[0081] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0082] Based on the same inventive concept, embodiments of the present application also provide a device for implementing the aforementioned hospital vehicle parking dispatch method. The solution provided by this device is similar to the solution described in the aforementioned method. Therefore, the specific limitations of one or more embodiments of the hospital vehicle parking dispatch device provided below can be found in the aforementioned limitations of the hospital vehicle parking dispatch method and will not be further elaborated here.

[0083] In an exemplary embodiment, Figure 3 As shown, a hospital vehicle parking scheduling device 30 is provided, comprising:

[0084] The historical data analysis module 31 is used to determine the expected parking duration for different types of medical consultations based on the historical time data in the pre-established medical consultation type database, and form an initial duration benchmark table.

[0085] The vehicle information processing module 32 is used to obtain the vehicle's medical treatment type information based on the initial duration benchmark table; when the vehicle enters the parking area, the expected parking duration corresponding to the medical treatment type information is matched through a preset allocation strategy, and the expected parking duration value is bound to the vehicle identification to generate a personalized parking time limit record.

[0086] The parking time monitoring module 33 is used to monitor the actual parking time of the vehicle in real time. If the actual parking time exceeds the expected parking time value in the personalized parking time limit record, the time limit exceeded flag is triggered; by associating the time limit exceeded flag with the vehicle identification, the penalty status of the vehicle is determined.

[0087] The priority score adjustment module 34 is used to adjust the vehicle's next parking priority score according to the penalty status and update the adjusted next parking priority score into the priority database; wherein the next parking priority score is calculated according to a preset priority score rule.

[0088] The parking space allocation control module 35 is used to allocate parking spaces to vehicles of scheduled patients with scores higher than a preset score threshold during peak hours based on the next parking priority score in the priority database, and to cancel the restriction rules during off-peak hours; wherein the restriction rule is to allocate parking spaces to vehicles of scheduled patients with scores higher than a preset score threshold during the next parking priority score.

[0089] Optional historical data analysis modules include:

[0090] The historical time data extraction unit is used to extract the historical time records of various types of medical consultations from the medical consultation type database.

[0091] The data sorting and generating unit is used to sort the historical time records of each type of medical consultation and generate a preliminary time dataset.

[0092] The average time calculation unit is used to calculate the average time value of each type of medical consultation based on the preliminary time data set and determine the time characteristic value.

[0093] The expected parking time derivation unit is used to derive the expected parking time value of each type of medical visit through the time characteristic value to obtain the parking time prediction result.

[0094] The benchmark table construction unit is used to construct initial duration benchmark data according to the duration prediction result to form an initial duration benchmark table.

[0095] The deviation correction unit is used to adjust the expected parking time value of a certain type of medical treatment through a regression analysis model when the deviation between the parking time of a certain type of medical treatment and the expected parking time value exceeds a preset numerical threshold, so as to obtain a corrected time benchmark value.

[0096] The reference table updating unit is used to update the initial duration reference table according to the corrected duration reference value.

[0097] Optionally, the vehicle information processing module includes:

[0098] The medical consultation type extraction unit is used to extract the medical consultation type information related to the current vehicle from the initial duration benchmark table, and generate basic duration information based on the time when the vehicle enters the parking area.

[0099] The parking time limit matching unit is used to match the visit type with the expected parking time value in the initial time limit benchmark table based on the basic time information through an automatic comparison mechanism to determine the preliminary parking time limit.

[0100] The time limit correction unit is used to correct the preliminary parking time limit through a logical judgment mechanism when the preliminary parking time limit exceeds a preset time threshold, and generate corrected parking time limit data.

[0101] The time limit record generating unit is used to uniquely associate the corrected parking time limit data with the vehicle identification to generate a personalized parking time limit record.

[0102] Optionally, the parking duration monitoring module includes:

[0103] The duration comparison and analysis unit is used to obtain the actual parking time data of the vehicle in the parking area, compare the actual parking time data with the expected parking time value in the personalized parking time limit record, and obtain a preliminary duration comparison result.

[0104] The status marking unit is used to activate the time-exceeded flag when the preliminary time comparison result shows that the actual parking time exceeds the expected time limit, and bind the time-exceeded flag with the corresponding vehicle identification to mark it as a preliminary penalty state.

[0105] The behavior pattern evaluation unit is used to extract previous parking behavior records related to vehicle identification from historical parking data based on the preliminary penalty status; determine whether there are repeated exceeding situations based on the previous parking behavior records, and generate behavior pattern analysis results.

[0106] A penalty status determination unit is used to determine the frequency level of the excess when the behavior pattern analysis results show repeated excesses, determine whether to trigger the authority adjustment rules based on the preset threshold range, and generate a final penalty status; wherein the final penalty status includes at least one of the following: only recording the current timeout behavior, reducing the parking priority score based on the frequency level of the excess, and triggering the parking authority restriction mechanism.

[0107] Optionally, the hospital vehicle parking scheduling device further includes:

[0108] The data collection and collation unit is used to obtain the allocation records of low-peak periods and the allocation logs of peak periods from the medical treatment type database, and to collate the parking duration distribution of different time periods in combination with the medical treatment type classification information to generate a preliminary duration distribution data set.

[0109] The data update and fusion unit is used to incrementally update the historical time usage data through a timed refresh mechanism, integrate the priority scoring rules to determine the data integrity, and generate an updated duration distribution set.

[0110] The expected parking duration adjustment unit is used to adjust the expected parking duration value based on the parking duration distribution set if the parking duration fluctuation exceeds a preset fluctuation threshold, and generate an adjusted prediction data set.

[0111] The feature extraction and classification prediction unit is used to extract parking duration features through the adjusted prediction data set; and obtain classification prediction results based on the parking duration features.

[0112] The allocation strategy optimization unit is used to optimize the allocation strategy according to the classification prediction results.

[0113] An embodiment of the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0114] An embodiment of the present application further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0115] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to the partial description of the method embodiments. The device embodiments described above are merely illustrative, wherein the components described as separate parts may or may not be physically separated, and the parts displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the disclosed solution. A person of ordinary skill in the art can understand and implement it without expending creative work.

[0116] The above-described embodiments merely represent several implementation methods of the embodiments of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the patent application. It should be noted that a person skilled in the art may make various modifications and improvements without departing from the concept of the embodiments of the present application, and these modifications and improvements fall within the scope of protection of the embodiments of the present application.

Claims

1. A hospital vehicle parking scheduling method, characterized in that: The method comprises: Based on the historical time data in the pre-established medical visit type database, the expected parking time is determined for different medical visit types to form an initial time benchmark table; Obtaining the vehicle's medical visit type information based on the initial duration benchmark table; when the vehicle enters the parking area, matching the expected parking duration value corresponding to the medical visit type information using a preset allocation strategy, and binding the expected parking duration value to the vehicle identification to generate a personalized parking time limit record; monitoring the actual parking time of the vehicle in real time, and triggering a time-exceeded flag if the actual parking time exceeds the expected parking time in the personalized parking time limit record; and determining a penalty status of the vehicle by associating the time-exceeded flag with the vehicle identifier; Adjusting the next parking priority score of the vehicle according to the penalty status, and updating the adjusted next parking priority score into the priority database; wherein the next parking priority score is calculated according to a preset priority scoring rule; For the next parking priority score in the priority database, parking spaces are preferentially allocated to vehicles of scheduled patients with scores higher than a preset score threshold during peak hours, and restriction rules are cancelled during off-peak hours; wherein, the restriction rule is to preferentially allocate parking spaces to vehicles of scheduled patients with the next parking priority score higher than a preset score threshold.

2. The method according to claim 1, characterized in that The method determines the expected parking duration for different types of medical visits based on the historical time data in the pre-established medical visit type database, and forms an initial duration benchmark table, including: Extracting historical time records of various types of medical consultations from the medical consultation type database, sorting the historical time records of each type of medical consultation, and generating a preliminary time dataset; Calculate the average time value of each type of medical consultation based on the preliminary time dataset and determine the time characteristic value; Deducing the expected parking duration value for each type of medical visit through the time characteristic value to obtain a duration prediction result; Constructing initial duration benchmark data based on the duration prediction result to form the initial duration benchmark table; When the deviation between the parking duration of a certain type of medical visit and the expected parking duration exceeds a preset threshold, the expected parking duration of the certain type of medical visit is adjusted using a regression analysis model to obtain a corrected duration benchmark value; The initial duration reference table is updated according to the corrected duration reference value.

3. The method according to claim 2, characterized in that The method includes: obtaining the medical treatment type information of the vehicle according to the initial duration benchmark table; matching the expected parking duration value corresponding to the medical treatment type information with a preset allocation strategy when the vehicle enters the parking area, and binding the expected parking duration value with the vehicle identification to generate a personalized parking time limit record, including: Extracting the medical consultation type information related to the current vehicle from the initial duration reference table and generating basic duration information based on the time when the vehicle enters the parking area; According to the basic duration information, the visit type is matched with the expected parking duration value in the initial duration benchmark table through an automatic comparison mechanism to determine the preliminary parking duration limit; When the preliminary parking time limit exceeds a preset time threshold, the preliminary parking time limit is corrected through a logic judgment mechanism to generate corrected parking time limit data; The corrected parking time limit data is uniquely associated with the vehicle identification to generate the personalized parking time limit record.

4. The method according to claim 3, characterized in that The real-time monitoring of the actual parking time of the vehicle, if the actual parking time exceeds the expected parking time value in the personalized parking time limit record, triggering a time-exceeded flag; Determining the penalty status of the vehicle by associating the time-exceeded flag with the vehicle identifier includes: Acquiring actual parking time data of the vehicle in the parking area, and comparing the actual parking time data with the expected parking time value in the personalized parking time limit record to obtain a preliminary time comparison result; When the preliminary time comparison result shows that the actual parking time exceeds the expected time limit, the time-exceeded flag is activated, and the time-exceeded flag is bound to the corresponding vehicle identifier, marking it as a preliminary penalty state; Extracting past parking behavior records related to the vehicle identification from historical parking data based on the preliminary penalty status; determining whether there are repeated exceeding the limit based on the past parking behavior records, and generating a behavior pattern analysis result; When the behavior pattern analysis results show repeated exceeding of limits, the frequency level of the exceeding is determined, and whether the authority adjustment rules are triggered is determined in combination with the preset threshold range to generate a final penalty status; wherein, the final penalty status includes at least one of the following: only recording the current timeout behavior, reducing the parking priority score according to the frequency level of the exceeding, and triggering the parking authority restriction mechanism.

5. The method according to any one of claims 1 to 4, characterized in that The method further comprises: Obtaining the allocation records of off-peak hours and the allocation logs of peak hours from the visit type database, combining the visit type classification information, sorting out the parking duration distribution of different time periods, and generating a preliminary duration distribution data set; Incrementally update the historical time data through a timed refresh mechanism, integrate the priority scoring rules to determine data integrity, and generate an updated duration distribution set; Based on the parking duration distribution set, if the parking duration fluctuation exceeds a preset fluctuation threshold, adjusting the expected parking duration value to generate an adjusted prediction data set; Extracting parking duration features from the adjusted prediction data set; and obtaining classification prediction results based on the parking duration features. The allocation strategy is optimized according to the classification prediction result.

6. A hospital vehicle parking dispatching device, characterized in that: The device comprises: A historical data analysis module is used to determine the expected parking duration for different types of medical visits based on the historical time data in the pre-established medical visit type database, and form an initial duration benchmark table; a vehicle information processing module configured to obtain the vehicle's medical visit type information based on the initial duration benchmark table; when the vehicle enters a parking area, match the expected parking duration value corresponding to the medical visit type information using a preset allocation strategy, bind the expected parking duration value to the vehicle identification, and generate a personalized parking time limit record; a parking duration monitoring module for monitoring the actual parking duration of the vehicle in real time, and triggering a duration-exceeded flag if the actual parking duration exceeds the expected parking duration in the personalized parking time limit record; and determining the penalty status of the vehicle by associating the duration-exceeded flag with the vehicle identifier; a priority score adjustment module, configured to adjust the vehicle's next parking priority score according to the penalty status, and update the adjusted next parking priority score into a priority database; wherein the next parking priority score is calculated according to a preset priority score rule; A parking space allocation control module is used to give priority to allocating parking spaces to vehicles of scheduled patients with scores higher than a preset score threshold during peak hours based on the next parking priority score in the priority database, and to cancel the restriction rules during off-peak hours; wherein the restriction rule is to give priority to allocating parking spaces to vehicles of scheduled patients with scores higher than a preset score threshold for the next parking priority score.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the method according to any one of claims 1 to 5 is implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

Images