Parking auxiliary management method and related equipment

Abstract

The invention discloses a parking auxiliary management method and related equipment, and relates to the technical field of auxiliary parking, and the method comprises the steps: obtaining a plurality of candidate parking positions in a preset range with a destination corresponding to a parking request as the center under the condition that a target vehicle requests for parking; acquiring current environment sensing data and historical safety data of each candidate parking position; based on the current environment perception data and the historical safety data of each candidate parking position, determining a safety analysis result of the corresponding candidate parking position; and generating parking position recommendation information based on the safety analysis result of each candidate parking position. According to the invention, the decision-making difficulty and time cost of safe parking in a strange or complex environment by a user are reduced, and the safety and decision-making efficiency of the parking process are improved.

Description

Technical Field

[0001] This application relates to the field of assisted parking technology, and in particular to a parking assistance management method and related equipment. Background Technology

[0002] With the continuous growth of urban motor vehicle ownership, parking difficulties have become a widespread problem. Currently available parking navigation systems primarily focus on providing users with information on available parking spaces and navigation services. Their functions are mostly limited to parking space search, reservation, and route guidance, lacking a comprehensive assessment of parking environment safety. Especially at night, in remote areas, or during specific times, vehicle theft, vandalism, and harassment are frequent security incidents, posing a potential threat to the travel safety of users, particularly women and nighttime drivers. Therefore, there is an urgent need for a parking assistance management method that can integrate multi-source information and assess parking safety to address the aforementioned technical problems. Summary of the Invention

[0003] The summary section introduces a series of simplified concepts, which will be further explained in detail in the detailed description section. This summary section is not intended to limit the key and essential technical features of the claimed technical solutions, nor is it intended to determine the scope of protection of the claimed technical solutions.

[0004] This application aims to address the problem that existing parking navigation systems only focus on parking space availability and lack assessment of parking environment safety, leading to safety threats to users in high-risk scenarios such as nighttime and remote areas. By sensing real-time information about the vehicle's surrounding environment, integrating historical safety event big data and user feedback, and utilizing multimodal feature fusion technology to score the safety of candidate parking locations, personalized safe parking recommendations are generated based on the scoring results. Furthermore, the evaluation model is optimized based on user feedback, elevating parking selection from simply finding available spaces to making safe decisions, thus improving the parking safety experience for users, especially specific groups.

[0005] Firstly, this application provides a parking assistance management method, including: When a target vehicle requests parking, obtain multiple candidate parking locations within a preset range centered on the destination corresponding to the parking request; Obtain the current environmental perception data and historical safety data for each of the candidate parking locations; Based on the current environmental perception data and the historical safety data of each candidate parking location, the safety analysis result of the corresponding candidate parking location is determined; Based on the safety analysis results of each of the candidate parking locations, parking location recommendation information is generated.

[0006] In some implementations, acquiring the current environmental perception data and historical safety data for each of the candidate parking locations includes: Environmental information is collected for each of the candidate parking locations to generate initial perception data; The initial sensing data is processed to determine the current environmental sensing data for each candidate parking location; Based on a preset data interface, obtain the safety event records of each candidate parking location within the target historical time period; Based on the security event records, the historical security data for each candidate parking location is determined.

[0007] In some implementations, the step of processing the initial sensing data to determine the current environmental sensing data for each candidate parking location includes: Perform feature extraction on the initial sensing data to determine at least one environmental feature indicator; Perform a quantitative scoring operation on each of the environmental characteristic indicators to determine the environmental characteristic score corresponding to each environmental characteristic indicator; Based on preset fusion weights, a weighted fusion operation is performed on all the environmental feature scores to determine the current environmental perception data for each candidate parking location.

[0008] In some embodiments, the environmental characteristic indicators include at least one of light intensity data, ambient sound data, moving object density data, and lighting facility data.

[0009] In some implementations, determining the historical security data for each candidate parking location based on the security event records includes: Based on the security event records, determine the event statistics information of at least one security dimension for each candidate parking location within the target historical time period; Based on the event statistics for each security dimension, a security dimension score is determined. Based on preset dimension weights, a weighted fusion operation is performed on the safety dimension scores of all safety dimensions to determine the historical safety data of each candidate parking location.

[0010] In some implementations, determining the safety analysis result for each candidate parking location based on the current environmental perception data and the historical safety data includes: Based on a preset fusion model, a first dynamic weight corresponding to the current environmental perception data and a second dynamic weight corresponding to the historical security data are determined. Based on the first dynamic weight and the current environmental perception data, and the second dynamic weight and the historical safety data, the safety analysis result of the corresponding candidate parking location is determined by weighted calculation.

[0011] In some implementations, generating parking location recommendation information based on the safety analysis results of each of the candidate parking locations includes: Based on the safety analysis results of each candidate parking location, all candidate parking locations are sorted to determine a safety score sequence; Based on a preset number of recommendations, target candidate parking locations with the highest safety ranking are selected from the safety score sequence; Based on the location information of the target candidate parking location and the safety analysis results, parking location recommendation information containing location identifiers and recommendation reasons is generated.

[0012] In some implementations, it also includes: Based on the user's response to the parking location recommendation information, the target parking location used by the user is determined; After the user finishes using the target parking location, obtain the feedback and evaluation data submitted by the user; The consistency between the feedback evaluation data and the safety analysis results corresponding to the target parking location is verified to determine the verification result; When the verification result is greater than the preset confidence range, an adjustment operation is performed on at least one of the preset fusion weight, the preset dimension weight, the first dynamic weight, and the second dynamic weight based on the verification result.

[0013] Secondly, this application proposes a parking assistance management device, comprising: The candidate location determination unit is used to obtain multiple candidate parking locations within a preset range centered on the destination corresponding to the parking request when the target vehicle requests parking. An auxiliary data acquisition unit is used to acquire current environmental perception data and historical safety data for each of the candidate parking locations; The safety result analysis unit is used to determine the safety analysis result of the corresponding candidate parking location based on the current environmental perception data and the historical safety data of each candidate parking location; The target parking space recommendation unit is used to generate parking space recommendation information based on the safety analysis results of each of the candidate parking spaces.

[0014] Thirdly, an electronic device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program stored in the memory to implement the steps of the parking assistance management method of any of the first aspects.

[0015] Fourthly, this application also proposes a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the parking assistance management method of any one of the first aspects.

[0016] In summary, the parking assistance management method provided in this application ensures the source of parking location recommendations by acquiring multiple candidate parking locations within a preset range centered on the destination corresponding to the parking request. It improves processing efficiency by selecting parking locations within the user's actual needs. By collecting current environmental perception data for each candidate parking location, it promptly reflects the environmental conditions of each location at the current moment, such as lighting, pedestrian flow, vehicle flow, and abnormal sounds, thereby capturing real-time risk information that traditional static data cannot provide. Simultaneously, acquiring historical safety correlation data for each candidate parking location allows for the assessment of its safety risk patterns and potential hazards using long-term statistical information such as past violations, accidents, and user feedback. Based on the aforementioned current environmental perception data and historical safety correlation data, a comprehensive safety score is calculated for each candidate parking location, achieving a fusion assessment of dynamic real-time status and long-term statistical patterns. This makes the safety judgment more comprehensive and objective, avoiding the one-sidedness of single-dimensional assessments. Finally, based on the comprehensive safety score, a recommended parking location is determined from multiple candidate parking locations. This ensures that the final recommendation presented to the user directly corresponds to the safety level after quantitative comparison. Users do not need to compare complex information themselves, thereby reducing the difficulty and time cost for users to make safe parking decisions in unfamiliar or complex environments, and improving the safety and decision-making efficiency of the parking process. Attached Figure Description

[0017] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit this specification. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings: Figure 1 This is a schematic diagram of a parking assistance management method provided in an embodiment of this application; Figure 2 This is a schematic diagram of a parking assistance management device provided in an embodiment of this application; Figure 3 This is a schematic diagram of a parking assistance management electronic device provided in an embodiment of this application. Detailed Implementation

[0018] The terms "first," "second," "third," "fourth," etc. (if present) in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in a sequence other than that illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus. The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them.

[0019] In the specific embodiments of this application, the proposed parking assistance management method involves real-time perception and collection of information about the vehicle's surrounding environment, acquisition and analysis of historical safety event data for specific areas, and collection and utilization of subjective feedback evaluation data from users after parking. The acquisition, transmission, storage, and processing of data such as environmental images, environmental sounds, public safety records, user ratings, and tags involved in the above processes must strictly comply with national and regional laws, regulations, and industry standards related to personal information protection, data security, and privacy. Any data associated with an individual or specific location must ensure that explicit authorization or consent has been obtained from the data subject, or that it originates from legally disclosed and permitted information sources, before being applied to the system or services described in this method. Implementers shall establish a data compliance management system, take necessary technical and management measures to ensure the security and legal compliance of data throughout its entire lifecycle, and respect and protect user privacy and public interests.

[0020] Please see Figure 1 This is a schematic diagram of a parking assistance management method provided in an embodiment of this application, which may specifically include: S110. When the target vehicle requests parking, obtain multiple candidate parking locations within a preset range centered on the destination corresponding to the parking request. For example, when a target vehicle requests parking, the system aims to respond to the user's parking needs by using the user-specified destination location as an anchor point and performing spatial retrieval and filtering operations on an electronic map or parking space database based on pre-defined geographical range parameters. The result of this operation is a set of spatially accessible candidate parking locations located around the destination, laying the foundation for safety analysis of each specific location and ensuring that the evaluated and recommended locations are clear and consistent with the user's actual parking intentions.

[0021] S120. Obtain the current environmental perception data and historical safety data for each candidate parking location; For example, current environmental perception data focuses on capturing the physical environment surrounding the parking location in real time through onboard sensors, such as lighting conditions, sound environment, personnel and vehicle activity, and the presence of public safety facilities. This information reflects the actual safety of the location at the time of assessment. Historical safety data, on the other hand, focuses on extracting objective records and subjective evaluation statistics related to safety at the location over a past period from various data sources. This includes the frequency of safety incidents that have occurred in the area, records of violations, and feedback from past users regarding their parking experiences. This information identifies long-term patterns of safety risks and potential hazards at the location. These two types of data together form the data foundation for conducting safety analysis on a specific parking location.

[0022] S130. Based on the current environmental perception data and historical safety data of each candidate parking location, determine the safety analysis results of the corresponding candidate parking location; For example, for each candidate parking location, data fusion and safety assessment calculations are performed based on its corresponding current environmental perception data and historical safety data to generate safety analysis results. This step aims to combine perception data reflecting the immediate environmental state with historical data reflecting long-term risk patterns, and through a preset model or algorithm, such as a weighted fusion or machine learning model, output an analytical value or level that can characterize the safety level of the location, providing a decision-making basis for parking location recommendations.

[0023] S140. Based on the safety analysis results of each candidate parking location, generate parking location recommendation information.

[0024] For example, after obtaining the safety analysis results of each candidate parking location, all candidate locations are compared and ranked according to the safety level represented by the results, thereby identifying the parking options with relatively better safety conditions. According to a preset recommendation strategy, such as selecting the top-ranked locations, the location information and their corresponding safety analysis basis are integrated into user-facing prompts, and finally, parking location recommendation information is generated and output. This completes the transformation from multi-source data fusion analysis to specific safety decision suggestions, directly assisting users in making safer parking choices.

[0025] In summary, the parking assistance management method provided in this application determines multiple candidate parking locations around a user's destination when the user submits a parking request. It then fuses and analyzes real-time environmental perception data and historical safety data for each location to generate a safety analysis result. Based on this result, it filters and recommends parking locations with better safety conditions. This method elevates traditional parking navigation from a single-dimensional decision-making process focused solely on parking space availability to a multi-dimensional safety decision-making process that comprehensively considers both the immediate environment and long-term risk patterns. Its real-time environmental perception capability can capture dynamically changing risk factors such as lighting, pedestrian flow, and abnormal sounds, compensating for the lag in purely historical data assessment. Furthermore, its historical data analysis can characterize the inherent safety risk patterns of a region, avoiding misjudgments of instantaneous environmental fluctuations. By using weighted fusion and other models to unify the two types of heterogeneous data into a comparable safety score, it achieves objectivity and comprehensiveness in the assessment basis. Ultimately, recommendations with safety justifications are generated based on the rating ranking, transforming the decision-making process that originally required users to collect and compare complex environmental and historical information into safety guidance. This reduces the burden and time cost of parking decisions for users in unfamiliar or high-risk scenarios, thereby improving parking safety for various user groups, especially in specific scenarios such as nighttime, remote areas, or solo travel.

[0026] In some instances, when a target vehicle requests parking, multiple candidate parking locations within a preset range centered on the destination corresponding to the parking request are obtained, including: For example, when a vehicle user initiates a parking request through the in-vehicle system or a related mobile application, the system receives and parses the request, extracting the user-specified destination location information. This destination is typically the navigation endpoint or a manually entered target location. Then, using the destination coordinates as the center point, a circular or custom-shaped search area is defined based on a pre-set or configurable geographical distance threshold (e.g., 300 meters). This area is the "preset range." After defining the range, a local or cloud-based parking space database and electronic map service are accessed to perform spatial queries and data matching within the preset range. Query criteria include identifying all legal parking spaces or parking areas marked as permitted within the area. These parking spaces come from various types, such as on-street parking spaces, public parking lots, and commercial parking facilities. Geographic Information System (GIS) algorithms filter out all locations that meet the criteria and aggregate them into a set of candidate parking locations. The generation of this set ensures that the recommended locations are all located in the vicinity of the user's actual destination, thus guaranteeing the rationality of the recommendations.

[0027] In some instances, current environmental awareness data and historical safety data are acquired for each candidate parking location, including: Environmental information is collected for each candidate parking location to generate initial perception data; The initial sensing data is processed to determine the current environmental sensing data for each candidate parking location; Based on a preset data interface, obtain the safety event records of each candidate parking location within the target historical time period; Based on security incident records, historical security data for each candidate parking location is determined.

[0028] For example, current environmental perception data for each candidate parking location is obtained by sending a data request to a cloud data platform or by using the onboard sensors of the target vehicle. When using the data request method, the geographical coordinates of the candidate parking location and the collection time are submitted to the platform. The platform then returns anonymized raw environmental perception data recently collected and uploaded by other vehicles near that location using their onboard devices. If the vehicle itself collects data, its onboard cameras, microphones, and other sensors are triggered when it actually arrives at or passes near a candidate parking location to scan its immediate environment. Regardless of the method, the obtained data reflects the physical environment of a specific location at a specific time, such as images and audio.

[0029] The initial sensing data is processed to determine the current environmental sensing data for each candidate parking location. This process involves two stages: feature extraction and quantization scoring. In the feature extraction stage, computer vision algorithms analyze image data to extract environmental characteristic indicators such as light intensity, density of moving objects (e.g., pedestrians, vehicles), and visibility of public lighting or monitoring facilities. Simultaneously, audio signal processing algorithms analyze sound data to extract indicators such as average decibel value and abnormal sound spectrum characteristics. In the quantization scoring stage, scoring rules and full scores are preset for each extracted environmental characteristic indicator. The corresponding environmental characteristic score is calculated based on the actual measurement value or recognition result of the indicator. Finally, based on preset fusion weights, all environmental characteristic scores are weighted and summed. The calculated result is determined as the quantified value representing the current comprehensive environmental safety status of the location, i.e., the current environmental sensing data.

[0030] Based on a pre-defined data interface, the system retrieves safety event records for each candidate parking location within a target historical time period. The pre-defined data interface refers to a standardized communication connection established with an authorized third-party data service platform or a locally stored compliant data set. This could be a commercial data platform providing regional security posture services, an open platform for urban public service information, or a self-accumulated and anonymized database of user historical feedback. By calling these interfaces and submitting the geographic coordinates of the candidate parking location and the target historical time period as query conditions, the system can remotely retrieve or locally query a set of anonymized and aggregated historical safety-related information associated with that location. Examples include user safety rating records summarized for the area in past time periods, user-submitted text feedback containing safety keywords, publicly available facility status reports, and risk label records generated based on multi-party data fusion.

[0031] Based on safety incident records, historical safety data for each candidate parking location is determined. This process mainly involves structured classification analysis and quantitative fusion of the acquired information set. First, the information records are classified and statistically analyzed according to preset evaluation dimensions, including environmental facility evaluation, violation risk evaluation, accident hazard evaluation, and public evaluation. For the environmental facility evaluation dimension, statistical information can be based on the frequency of problems such as insufficient lighting and lack of monitoring, derived from historical image data or user-reported information. For the violation risk evaluation dimension, statistical information can be derived from the frequency of parking-related violations in public or third-party data for the area. For the accident hazard evaluation dimension, statistical information can be referenced from the frequency of minor scratches or congestion reports in the surrounding area in historical records. For the public evaluation dimension, statistical information is directly derived from the average historical user ratings of the location's safety and the frequency of negative label terms. For each dimension, based on its statistical information, a safety dimension score is calculated according to preset quantitative rules (e.g., mapping frequency to a percentage score). Based on the pre-set dimension weights for different evaluation dimensions, the security dimension scores of all dimensions are weighted and fused for calculation. Finally, the calculation result is determined as a quantitative value representing the long-term security risk situation of the location, i.e., historical security data.

[0032] In summary, this application's embodiments, through a structured acquisition, processing, and analysis process, transform and fuse real-time environmental raw signals from different sources and discrete historical event records from external data sources into current environmental perception data and historical safety data, respectively. This process constructs a data profile of the safety of a specific parking location from two perspectives: "current immediate state" and "long-term risk patterns," overcoming the limitations of relying solely on real-time perception, which is susceptible to interference from accidental factors, or relying solely on historical data, which cannot reflect sudden situations.

[0033] In some instances, the initial sensing data is processed to determine the current environmental sensing data for each candidate parking location, including: Perform feature extraction on the initial sensing data to determine at least one environmental feature indicator, which includes at least one of light intensity data, ambient sound data, moving object density data, and lighting facility data. Perform a quantitative scoring operation on each environmental characteristic indicator to determine the environmental characteristic score corresponding to each environmental characteristic indicator; Based on preset fusion weights, a weighted fusion operation is performed on all environmental feature scores to determine the current environmental perception data for each candidate parking location.

[0034] For example, feature extraction is performed on the initial sensing data to determine at least one environmental characteristic indicator. This operation involves invoking preset computer vision and audio signal processing algorithms to analyze and identify the initial sensing data, which exists in the form of images and / or audio. Specifically, image data is analyzed using computer vision algorithms to extract illuminance data representing ambient lighting conditions, moving object density data representing the activity of people and vehicles, and lighting facility data representing the visibility of public safety facilities. Simultaneously, sound data is analyzed using audio signal processing algorithms to extract ambient sound data representing ambient sound levels and abnormal sound characteristics. This step aims to transform the raw, unstructured sensor data into a series of measurable environmental characteristic indicators with clear safety orientations.

[0035] Each environmental characteristic indicator is quantitatively scored to determine its corresponding environmental characteristic score. This operation configures independent scoring rules and a full-score benchmark for each predefined environmental characteristic indicator. The scoring rules define how to map the actual measured value or identification result of the indicator to a standardized score. For example, for light intensity data, the scoring rules can compare the detected light intensity measurement with a preset reference safe light intensity value and calculate the corresponding score using a linear or nonlinear function; for ambient sound data, the scoring rules can comprehensively consider whether the average decibel value of the environment is within the quiet range, and whether preset abnormal sound patterns (such as the sound of breaking glass or screams) are detected through spectrum analysis, thereby deriving a score; for moving object density data, the scoring rules can determine the degree of order and give a corresponding score based on the number, mobility, and aggregation status of identified people and vehicles; for lighting facility data, the scoring rules can confirm the presence of streetlights or public surveillance cameras at the location based on visual recognition and map data matching, and assign a score based on their completeness. By performing this scoring operation, each environmental characteristic indicator is converted into an environmental characteristic score.

[0036] Based on preset fusion weights, a weighted fusion operation is performed on all environmental feature scores to determine the current environmental perception data for each candidate parking location. In this operation, the preset fusion weight is a coefficient pre-assigned to each environmental feature score, representing its relative importance; the sum of all weight coefficients is a fixed value. The weighted fusion operation involves calculating the weighted sum of all environmental feature scores according to the preset fusion weights. Specifically, each environmental feature score is multiplied by its corresponding weight coefficient, and all products are summed to obtain a single numerical value. This value represents the current environmental perception data, which integrates multiple dimensions of real-time environmental safety conditions, such as lighting, sound, pedestrian and vehicle density, and infrastructure, representing the comprehensive environmental safety level of the candidate parking location at the current moment in an aggregated quantitative form. The preset fusion weights can be set empirically and adjusted in subsequent model optimization stages.

[0037] In summary, this application embodiment, through the aforementioned structured data processing flow, transforms initial perceived data into environmental feature indicators via feature extraction, then performs standardized quantitative scoring according to preset rules, and finally fuses them into current environmental perceived data based on preset weights. This process realizes the transformation from raw signals to structured and quantitative data that can be used for safety analysis, providing a data foundation for assessing instantaneous and dynamic environmental safety status and overcoming the subjectivity and bias of manual observation.

[0038] In some instances, historical security data for each candidate parking location is determined based on security event logs, including: Based on safety event records, determine the event statistics for at least one safety dimension for each candidate parking location within the target historical time period; Based on the event statistics for each security dimension, a security dimension score is determined. Based on preset dimension weights, a weighted fusion operation is performed on the safety dimension scores of all safety dimensions to determine the historical safety data of each candidate parking location.

[0039] For example, based on preset safety dimension classification rules, safety event records associated with candidate parking locations obtained from preset data interfaces are classified and statistically analyzed. These safety dimensions include at least the violation risk dimension, accident hazard dimension, facility condition dimension, and public evaluation dimension. For the violation risk dimension, entries in the records belonging to types such as vehicle theft, malicious damage, and illegal parking are identified and counted, and their frequency or number of occurrences within the target historical period is statistically analyzed. For the accident hazard dimension, events involving types such as vehicle scratches, reversing collisions, and obstruction of fire lanes are extracted and statistically analyzed, and their frequency of occurrence is analyzed. For the facility condition dimension, the proportion of records showing insufficient nighttime lighting or lack of public surveillance at the location is determined based on historical image data analysis. For the public evaluation dimension, the average of star ratings submitted by historical users for the location is calculated, and the frequency of negative safety tags added by users (such as "no surveillance" or "few people") is statistically analyzed. By performing the above-mentioned structured classification and statistical operations on the original records, the unstructured and discrete security event records are transformed into event statistical information with clear statistical significance under each security dimension, such as the frequency of violations, the frequency of accidents, the ratio of poor lighting, the average user rating, and the number of times negative tags appear.

[0040] Based on event statistics for each security dimension, a security dimension score is determined. This step predefines independent quantitative scoring rules and benchmark scores for each security dimension. The scoring rules define how to map specific numerical values ​​of event statistics to a standardized score. For example, for the violation risk dimension, the scoring rules could be set as follows: a higher score is awarded when the frequency of statistically derived violation events is below a first preset frequency threshold; a medium score is awarded when the frequency is between the first and second preset frequency thresholds; and a lower score is awarded when the frequency is above the second preset frequency threshold. For the accident hazard dimension, the scoring rules can divide corresponding score intervals based on the frequency of accidents. For the facility condition dimension, the scoring rules can compare the monitoring facility ratio with a preset ratio threshold to determine the score. For the public evaluation dimension, the scoring rules can directly convert the calculated average user rating (e.g., 1 to 5 stars) proportionally into a percentage score and appropriately deduct points based on the frequency of negative labels. By applying these predetermined scoring rules, event statistics for each security dimension are transformed into security dimension scores, thereby unifying different types of historical security performance onto the same evaluation scale.

[0041] Based on preset dimension weights, a weighted fusion operation is performed on the safety dimension scores of all safety dimensions to determine the historical safety data for each candidate parking location. In this step, the preset dimension weight is a pre-assigned weight coefficient for each safety dimension, representing its relative importance in the overall historical safety assessment. The sum of all weight coefficients is a fixed value. For example, the weight of the violation risk dimension can be set to be the highest, followed by the accident hazard and public evaluation dimensions, with relatively lower weights for the facility condition dimension. The weighted fusion operation involves calculating the weighted sum of the safety dimension scores of all safety dimensions according to the preset dimension weights. Specifically, each safety dimension score is multiplied by its corresponding preset dimension weight coefficient, and all products are summed to obtain a final value. This value represents the historical safety data of the candidate parking location, integrating the long-term risk statistical patterns reflected by different safety dimensions and representing the overall safety situation of the location from a historical perspective. This historical safety data complements the current environmental perception data, together forming a complete input for safety analysis.

[0042] In summary, this application's embodiments characterize long-term security risks in specific geographical locations by classifying, statistically analyzing, and quantifying unstructured, multi-source historical security event records according to preset security dimensions, and finally forming historical security data through weighted fusion. This method overcomes the limitations of relying solely on individual historical events or single-type data for judgment, comprehensively reflecting a region's long-term security performance in terms of violation risk, accident probability, facility conditions, and public perception. The resulting historical security data serves as a key input for assessing parking location safety, providing a basis for integrating real-time environmental perception data and conducting comprehensive and objective security analysis.

[0043] In some instances, based on current environmental awareness data and historical safety data for each candidate parking location, the safety analysis results for the corresponding candidate parking location are determined, including: Based on the preset fusion model, the first dynamic weight corresponding to the current environmental perception data and the second dynamic weight corresponding to the historical security data are determined. Based on the first dynamic weight and current environmental perception data, and the second dynamic weight and historical safety data, the safety analysis results of the corresponding candidate parking locations are determined through weighted calculation.

[0044] For example, a pre-defined fusion model is used to dynamically assign weights and perform weighted fusion calculations on the two types of heterogeneous data sources. The pre-defined fusion model is configured to adaptively determine the relative importance of the two types of data in the final safety assessment based on the specific context of the current assessment task, primarily the current time information and the geographical region attributes of the candidate parking location. This determination results in a first dynamic weight and a second dynamic weight. For instance, the model can embed decision logic based on time period and regional characteristics or a trained lightweight neural network. When the current time is identified as nighttime, or when geocoding indicates that the candidate parking location is located in a remote urban area, the model tends to assign a higher first dynamic weight to the current environmental perception data reflecting the immediate environmental conditions, while correspondingly reducing the second dynamic weight of historical safety data reflecting long-term patterns. Conversely, during the day or in familiar areas, a higher second dynamic weight may be assigned to historical safety data. This dynamic weight determination mechanism ensures that the safety assessment strategy can flexibly adapt to the inherent characteristics of different risk scenarios.

[0045] After determining the first dynamic weight corresponding to the current environmental perception data and the second dynamic weight corresponding to the historical safety data through a preset fusion model, a weighted calculation is performed to determine the safety analysis result. Specifically, the calculation process involves multiplying the current environmental perception data value by the first dynamic weight to obtain a weighted real-time environmental contribution value; simultaneously, multiplying the historical safety data value by the second dynamic weight to obtain a weighted historical safety contribution value. These two contribution values ​​are then summed, and the sum is the safety analysis result for the candidate parking location. This safety analysis result is a comprehensive quantitative score, incorporating both the instantaneous environmental safety status captured by real-time perception and the long-term risk statistical patterns revealed by historical data. In this way, a quantitative safety value can be obtained for each candidate parking location.

[0046] In some instances, parking location recommendations are generated based on the safety analysis results of each candidate parking location, including: Based on the safety analysis results of each candidate parking location, all candidate parking locations are sorted to determine the safety score sequence; Based on a preset number of recommendations, target candidate parking locations with the highest safety ranking are selected from the safety score sequence; Based on the location information and safety analysis results of the target candidate parking locations, parking location recommendation information is generated, which includes location identifiers and reasons for recommendation.

[0047] For example, after obtaining the safety analysis results for each candidate parking location, the locations are sorted according to the safety quantification values ​​represented by these results, either from high to low or from low to high, thus forming an ordered safety score sequence. Based on a pre-set recommendation quantity parameter, the top-ranked locations are selected from this safety score sequence and identified as target candidate parking locations. This pre-set recommendation quantity is a configurable integer value, such as 3, which controls the number of recommended options presented to the user, providing sufficient choices while avoiding information overload. Based on the specific location information of the identified target candidate parking locations and their corresponding safety analysis results, parking location recommendation information containing clear location identifiers and concrete recommendation reasons is constructed. The location identifier allows the user to uniquely identify and locate the recommended parking space, such as using map coordinates, parking space numbers, or descriptive text; the recommendation reason is extracted from the main data dimensions used to generate the location's safety analysis results, for example, it could be stated as "this location has few historical violations and currently has sufficient lighting." Through this series of steps, the abstract safety analysis results are transformed into specific parking suggestions that users can intuitively understand and operate.

[0048] In summary, this application's embodiments, by sorting and filtering the safety analysis results of multiple candidate locations, directly present users with sorted safe parking options. This eliminates the tedious process of users manually reviewing and comparing complex environmental information and historical data, reducing the difficulty and time cost of parking decisions in unfamiliar or high-risk environments. This method transforms the complex multi-source data fusion and safety assessment calculations in the background into front-end safety guidance, effectively improving the decision-making efficiency and user experience of the entire parking assistance management process, especially in scenarios where safety is paramount, such as at night, in remote areas, or when users are traveling alone.

[0049] In some instances, it also includes: Based on the user's response to parking location recommendations, determine the user's target parking location; After the user finishes using the target parking location, obtain the feedback and evaluation data submitted by the user; The consistency between the feedback evaluation data and the safety analysis results corresponding to the target parking location is verified, and the verification results are determined. When the verification result exceeds the preset confidence range, at least one of the preset fusion weight, preset dimension weight, first dynamic weight, and second dynamic weight is adjusted based on the verification result.

[0050] For example, based on the user's actual operational response to the generated parking location recommendations, it is possible to track and determine the specific parking location that the user ultimately selects and actually uses, i.e., the target parking location. This step establishes a correlation between the recommendation information and the user's actual behavior by monitoring the user's selection behavior on the interactive interface, such as clicking to confirm a recommendation, navigating to a specific parking space based on the recommendation information, and completing the parking. This maps the recommendation list to a parking event instance, anchoring a specific evaluation object for collecting feedback data on this parking experience.

[0051] After detecting that a user has ended their use of the target parking location, such as through triggering conditions like turning off the vehicle, locking the car and moving away from it at a certain distance, or the user actively ending the parking event within the app, the system proactively invites the user or provides an entry point to obtain feedback data submitted by the user regarding their parking experience. This feedback data can typically include, but is not limited to, the user's star rating for their parking safety experience, safety condition description tags selected from a preset tag set, and freely entered text or voice evaluations by the user.

[0052] After obtaining user feedback data, it is compared with the previously generated safety analysis results for the target parking location for consistency verification, and the verification results are output. This verification process first transforms the unstructured feedback data into standardized quantitative values ​​comparable to the safety analysis results, such as converting a five-star rating into a percentage score. Then, the absolute value or relative deviation between the transformed feedback score and the original safety analysis results is calculated. This deviation value is compared with a pre-set confidence range threshold that characterizes the allowable error range. If the deviation value is greater than the preset confidence range, it indicates a discrepancy between the user's subjective experience and the objective prediction, and the verification result is judged as unreliable or requiring adjustment; conversely, it indicates that the two are basically consistent, and the verification result is reliable.

[0053] When the aforementioned verification results indicate a discrepancy exceeding the preset confidence level, it signifies a significant difference between the current evaluation model's output in this specific scenario and the actual situation. Based on the deviation information contained in these verification results, adjustments will be made to the model parameters. The adjustment targets a set of key weight parameters affecting the generation of security analysis results. These include preset fusion weights for integrating environmental feature scores, preset dimension weights for integrating historical security dimensions, and at least one of the first and second dynamic weights for dynamically balancing current environmental perception data and historical security data. The adjustment logic typically involves fine-tuning the relevant weight parameters based on the direction and magnitude of the deviation between predicted and actual feedback values ​​using a preset optimization algorithm. This ensures that the security analysis results calculated by the model in similar scenarios in the future are closer to the user's actual experience. This step enables the evaluation model to iterate and optimize based on real-world feedback.

[0054] Please see Figure 2 The diagram below illustrates the structure of a parking assistance management device according to an embodiment of this application, comprising: The candidate location determination unit 21 is used to obtain multiple candidate parking locations within a preset range centered on the destination corresponding to the parking request when the target vehicle requests parking. The auxiliary data acquisition unit 22 is used to acquire the current environmental perception data and historical safety data of each candidate parking location; The safety result analysis unit 23 is used to determine the safety analysis result of each candidate parking location based on the current environmental perception data and historical safety data of each candidate parking location. The target parking space recommendation unit 24 is used to generate parking space recommendation information based on the safety analysis results of each candidate parking space.

[0055] Please see Figure 3 This application also provides an electronic device 300, including a memory 310, a processor 320, and a computer program 311 stored in the memory 310 and executable on the processor. When the processor 320 executes the computer program 311, it implements the steps of the parking assistance management method.

[0056] Since the electronic device described in this embodiment is the device used to implement a parking assistance management device in the embodiments of this application, those skilled in the art can understand the specific implementation method and various variations of the electronic device in this embodiment based on the method described in the embodiments of this application. Therefore, how the electronic device implements the method in the embodiments of this application will not be described in detail here. Any device used by those skilled in the art to implement the method in the embodiments of this application is within the scope of protection of this application.

[0057] In practice, when the computer program 311 is executed by the processor, it can implement any of the embodiments corresponding to the first aspect.

[0058] It should be noted that the descriptions of each embodiment in the above embodiments have different focuses. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0059] Those skilled in the art will understand that embodiments of this application can provide methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-readable storage media containing computer-readable program code.

[0060] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0061] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0062] These computer program instructions can also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0063] This application also provides a computer program product, which includes computer software instructions that, when executed on a processing device, cause the processing device to perform... Figure 1 The flowchart of a parking assistance management method in the corresponding embodiment.

[0064] A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the flow or function according to the embodiments of this application is generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another. For example, computer instructions may be transferred from one website, computer, server, or data center to another website, computer, server, or data center via wired or wireless means. The computer-readable storage medium may be any usable medium that a computer can store or a data storage device such as a server or data center that integrates one or more usable media. The usable medium may be a magnetic medium, an optical medium, or a semiconductor medium, etc.

[0065] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0066] In the several embodiments provided in this application, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Furthermore, the mutual couplings or direct couplings or communication connections shown or discussed may be indirect couplings or communication connections through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0067] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0068] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated units described above can be implemented in the form of hardware and / or software functional units.

[0069] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device to execute all or part of the steps of the methods in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory, magnetic disks, or optical disks.

[0070] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

[0071] Although preferred embodiments have been described in this specification, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications that fall outside the scope of this specification.

[0072] Obviously, those skilled in the art can make various modifications to this specification without departing from its spirit and scope. Therefore, this specification also intends to include any modifications that fall within the scope of the claims and their equivalents.

Claims

1. A parking assistance management method, characterized in that, include: When a target vehicle requests parking, obtain multiple candidate parking locations within a preset range centered on the destination corresponding to the parking request; Obtain the current environmental perception data and historical safety data for each of the candidate parking locations; Based on the current environmental perception data and the historical safety data of each candidate parking location, the safety analysis result of the corresponding candidate parking location is determined; Based on the safety analysis results of each of the candidate parking locations, parking location recommendation information is generated.

2. The method according to claim 1, characterized in that, The acquisition of current environmental perception data and historical safety data for each candidate parking location includes: Environmental information is collected for each of the candidate parking locations to generate initial perception data; The initial sensing data is processed to determine the current environmental sensing data for each candidate parking location; Based on a preset data interface, obtain the safety event records of each candidate parking location within the target historical time period; Based on the security event records, the historical security data for each candidate parking location is determined.

3. The method according to claim 2, characterized in that, The step of processing the initial sensing data to determine the current environmental sensing data for each candidate parking location includes: Perform feature extraction on the initial sensing data to determine at least one environmental feature indicator; Perform a quantitative scoring operation on each of the environmental characteristic indicators to determine the environmental characteristic score corresponding to each environmental characteristic indicator; Based on preset fusion weights, a weighted fusion operation is performed on all the environmental feature scores to determine the current environmental perception data for each candidate parking location.

4. The method according to claim 3, characterized in that, The environmental characteristic indicators include at least one of the following: light intensity data, ambient sound data, moving object density data, and lighting facility data.

5. The method according to claim 4, characterized in that, The determination of the historical security data for each candidate parking location based on the security event records includes: Based on the security event records, determine the event statistics information of at least one security dimension for each candidate parking location within the target historical time period; Based on the event statistics for each security dimension, a security dimension score is determined. Based on preset dimension weights, a weighted fusion operation is performed on the safety dimension scores of all safety dimensions to determine the historical safety data of each candidate parking location.

6. The method according to claim 5, characterized in that, The process of determining the safety analysis result for each candidate parking location based on the current environmental perception data and the historical safety data includes: Based on a preset fusion model, a first dynamic weight corresponding to the current environmental perception data and a second dynamic weight corresponding to the historical security data are determined. Based on the first dynamic weight and the current environmental perception data, and the second dynamic weight and the historical safety data, the safety analysis result of the corresponding candidate parking location is determined by weighted calculation.

7. The method according to claim 1, characterized in that, The generation of parking location recommendation information based on the safety analysis results of each of the candidate parking locations includes: Based on the safety analysis results of each candidate parking location, all candidate parking locations are sorted to determine a safety score sequence; Based on a preset number of recommendations, target candidate parking locations with the highest safety ranking are selected from the safety score sequence; Based on the location information of the target candidate parking location and the safety analysis results, parking location recommendation information containing location identifiers and recommendation reasons is generated.

8. The method according to claim 6, characterized in that, Also includes: Based on the user's response to the parking location recommendation information, the target parking location used by the user is determined; After the user finishes using the target parking location, obtain the feedback and evaluation data submitted by the user; The consistency between the feedback evaluation data and the safety analysis results corresponding to the target parking location is verified to determine the verification result; When the verification result is greater than the preset confidence range, an adjustment operation is performed on at least one of the preset fusion weight, the preset dimension weight, the first dynamic weight, and the second dynamic weight based on the verification result.

9. A parking assistance management device, characterized in that, include: The candidate location determination unit is used to obtain multiple candidate parking locations within a preset range centered on the destination corresponding to the parking request when the target vehicle requests parking. An auxiliary data acquisition unit is used to acquire current environmental perception data and historical safety data for each of the candidate parking locations; The safety result analysis unit is used to determine the safety analysis result of the corresponding candidate parking location based on the current environmental perception data and the historical safety data of each candidate parking location; The target parking space recommendation unit is used to generate parking space recommendation information based on the safety analysis results of each of the candidate parking spaces.

10. An electronic device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor, when executing the computer program stored in the memory, implements the steps of the parking assistance management method as described in any one of claims 1 to 8.

Images