Vehicle Identification Method, System, Device and Computer Readable Storage Medium

Abstract

The present invention discloses a vehicle identification method, system, device and computer-readable storage medium. The method includes: when detecting an event that a vehicle enters / leaves a berth, collecting Bluetooth signals of the environment around the berth and performing preprocessing to obtain Bluetooth information; filtering multiple Bluetooth IDs through a signal exclusion library stored in a server to obtain filtered Bluetooth information; receiving an uploaded inspection photo-taking event; triggering data association to construct associated data according to the event of leaving the berth or the inspection photo-taking event, where the associated data includes an associated event, an associated license plate number and a set of associated Bluetooth IDs; and using the associated data to determine the correspondence between the license plate number and the Bluetooth ID. By combining the Bluetooth signal changes generated when a vehicle enters / leaves a berth with the license plate information obtained by manual inspection, and using data association and statistical analysis, the correspondence between the license plate and the Bluetooth ID is established. This method can effectively eliminate environmental interference and improve the accuracy and reliability of vehicle identification.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent transportation, and particularly to a vehicle identification method, system, device and computer-readable storage medium. Background Art

[0002] In the field of urban public parking, license plates are usually used as the sole identifier of vehicles. Existing vehicle recognition technologies mainly rely on license plate recognition, such as license plate recognition technology based on image processing. However, this technology is easily affected by factors such as lighting, weather, and occlusion, resulting in a decrease in the recognition rate. In addition, for some special situations, such as license plate defacement, fake plates, and cloned plates, license plate recognition technology is also difficult to effectively handle.

[0003] With the improvement of vehicle intelligence, vehicles will actively emit various wireless signals, such as Bluetooth, RFID, etc. Using the wireless signals emitted by vehicles for identification can be an effective supplement to license plate recognition. However, due to the presence of a large number of wireless signal interferences in the environment, how to accurately identify the signals of target vehicles and associate them with license plates is the main challenge faced by this technology.

[0004] Based on this, a new solution is needed. Summary of the Invention

[0005] The main purpose of the present invention is to provide a vehicle identification method and system.

[0006] To achieve the above object, the present invention provides a vehicle identification method, including the following steps:

[0007] When a vehicle entry / exit berth event is detected, collect the Bluetooth signals in the surrounding environment of the berth and perform preprocessing to obtain Bluetooth information, where the Bluetooth information includes multiple Bluetooth IDs, event time, berth code, and event type;

[0008] Upload the Bluetooth information to the server, and filter the multiple Bluetooth IDs through a signal exclusion library stored in the server to obtain filtered Bluetooth information;

[0009] Receive the inspection photo-taking event uploaded by the inspector, where the inspection photo-taking event includes berth code, license plate number, berth photo, and photo-taking time;

[0010] Trigger data association according to the vehicle exit berth event or the inspection photo-taking event, and construct associated data, where the associated data includes associated events, associated license plate numbers, and associated Bluetooth ID sets; and

[0011] Use the associated data to determine the correspondence between the license plate number and the Bluetooth ID.

[0012] In the vehicle identification method provided by the present invention, in the step of triggering data association according to the event of driving out of the berth and constructing associated data, when receiving the event of driving out of the berth, find the most recent driving-in event of the corresponding berth, the inspection and photographing events after the most recent driving-in event and before the current driving-out event, and associate the filtered Bluetooth information corresponding to the most recent driving-in event with the license plate number in the inspection and photographing event; when receiving the inspection and photographing event, find the most recent driving-in event of the corresponding berth before the current inspection and photographing event, and associate the filtered Bluetooth information corresponding to the most recent driving-in event with the license plate number in the current inspection and photographing event.

[0013] In the vehicle identification method provided by the present invention, the steps of using the associated data to determine the corresponding relationship between the license plate number and the Bluetooth ID include:

[0014] Collect multiple groups of associated data of the same license plate number;

[0015] When the number of groups of associated data reaches the first preset threshold, count the number of occurrences of each Bluetooth ID in the set of associated Bluetooth IDs, and calculate the proportion of the number of occurrences in the total number of groups as the confidence level of the corresponding Bluetooth ID;

[0016] When the occurrence proportion of one of the Bluetooth IDs exceeds the second preset threshold, mark the corresponding Bluetooth ID as the confirmed Bluetooth ID of the corresponding license plate number;

[0017] Save the corresponding relationship between the license plate number and the confirmed Bluetooth ID, and at the same time save the confidence level of each Bluetooth ID.

[0018] In the vehicle identification method provided by the present invention, after the steps of using the associated data to determine the corresponding relationship between the license plate number and the Bluetooth ID, it further includes:

[0019] When the number of consecutive times that the set of associated Bluetooth IDs does not contain the confirmed Bluetooth ID exceeds the third preset threshold, lower the confidence level of the corresponding Bluetooth ID and add the Bluetooth ID to the candidate failure set.

[0020] In addition, to achieve the above object, the present invention also provides a vehicle identification system, including:

[0021] A Bluetooth information acquisition device, configured to collect Bluetooth signals in the surrounding environment of the berth and perform preprocessing when detecting a vehicle driving into / out of the berth event, so as to obtain Bluetooth information, where the Bluetooth information includes multiple Bluetooth IDs, event time, berth code, and event type;

[0022] A Bluetooth information filtering module, configured to filter the multiple Bluetooth IDs through a signal exclusion library stored in the server to obtain filtered Bluetooth information;

[0023] The patrol inspection photo-taking event receiving module is used to receive the patrol inspection photo-taking events uploaded by the patrol inspectors. The patrol inspection photo-taking events include berth codes, license plate numbers, berth photos, and photo-taking times.

[0024] The associated data construction module is used to trigger data association according to the berth departure event or the patrol inspection photo-taking event, and construct associated data. The associated data includes associated events, associated license plate numbers, and associated Bluetooth ID sets; and

[0025] The statistical analysis module is used to utilize the associated data to determine the correspondence between the license plate number and the Bluetooth ID.

[0026] In the vehicle identification system provided by the present invention, when a berth departure event is received, the associated data construction module is used to find the most recent entry event of the corresponding berth, and the patrol inspection photo-taking events after the most recent entry event and before the current berth departure event, and associate the filtered Bluetooth information corresponding to the most recent entry event with the license plate number in the patrol inspection photo-taking event; when a patrol inspection photo-taking event is received, the associated data construction module is used to find the most recent entry event of the corresponding berth before the current patrol inspection photo-taking event, and associate the filtered Bluetooth information corresponding to the most recent entry event with the license plate number in the current patrol inspection photo-taking event.

[0027] In the vehicle identification system provided by the present invention, the statistical analysis module includes:

[0028] The data collection unit is used to collect multiple groups of associated data of the same license plate number;

[0029] The data statistics unit is used to, when the number of groups of associated data reaches the first preset threshold, count the number of occurrences of each Bluetooth ID in the associated Bluetooth ID set, and calculate the proportion of the number of occurrences to the total number of groups as the confidence level of the corresponding Bluetooth ID;

[0030] The data marking unit is used to, when the occurrence proportion of one of the Bluetooth IDs exceeds the second preset threshold, mark the corresponding Bluetooth ID as the confirmed Bluetooth ID of the corresponding license plate number;

[0031] The data storage unit is used to store the correspondence between the license plate number and the confirmed Bluetooth ID, and simultaneously store the confidence level of each Bluetooth ID.

[0032] In the vehicle identification system provided by the present invention, there is also a data adjustment module, which is used to, when the number of consecutive times that the associated Bluetooth ID set does not contain the confirmed Bluetooth ID exceeds the third preset threshold, lower the confidence level of the corresponding Bluetooth ID and add the Bluetooth ID to the candidate failure set.

[0033] The present invention also provides a vehicle identification device, including a processor and a memory. The memory stores a computer program, and when the computer program is executed by the processor, the steps of the vehicle identification method described above are implemented.

[0034] The vehicle identification system and method provided by the present invention have the following beneficial effects: The present invention combines Bluetooth signals with manual inspections for vehicle identification, making full use of the complementary advantages of Bluetooth signal changes and manual inspection data, and can significantly improve the accuracy and reliability of vehicle identification; By combining the changes in Bluetooth signals with the license plate information collected through manual inspections, and establishing the corresponding relationship between Bluetooth IDs and license plate numbers through data association and statistical analysis, some challenges that may be faced in traditional license plate recognition technologies are solved, such as environmental interference, equipment failures, or insufficient recognition accuracy; Through data association technology, the changes in Bluetooth signals are matched with license plate information; Statistical analysis helps evaluate the effectiveness of the data, reduce noise and false matches, and ensure high-precision vehicle identification. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only the embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained according to the provided drawings:

[0036] Figure 1 The flowchart of the vehicle identification method provided by an embodiment of the present invention is shown. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0037] To facilitate the understanding of the present invention, the present invention will be described more comprehensively below with reference to the relevant drawings. The typical embodiments of the present invention are shown in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive.

[0038] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs. The terms used in the description of the present invention herein are only for the purpose of describing specific embodiments and are not intended to limit the present invention.

[0039] Figure 1 The flowchart of the vehicle identification method provided by an embodiment of the present invention is shown. As Figure 1 shown, the vehicle identification method includes the following steps:

[0040] Step S1: When a vehicle entry / exit berth event is detected, collect the Bluetooth signals in the surrounding environment of the berth and perform preprocessing to obtain Bluetooth information, where the Bluetooth information includes multiple Bluetooth IDs, event time, berth code, and event type;

[0041] Specifically, in an embodiment of the present invention, a Bluetooth signal collector and a geomagnetic device are deployed near the berth. The geomagnetic device is used to detect the event of a vehicle entering or exiting the berth, and the Bluetooth signal collector is used to collect the Bluetooth signals in the surrounding environment of the berth. When the geomagnetic device detects that a vehicle enters or exits the berth, it triggers the Bluetooth signal collector to start working. When the event is triggered, the system records the following information: event time, representing the specific time when the vehicle enters or exits; berth code, identifying the specific berth location; event type, distinguishing whether the vehicle enters or exits the berth.

[0042] Specifically, after the event is triggered, the Bluetooth signal collector will collect the Bluetooth signals in the surrounding environment within a set time window (e.g., 10 seconds); the collected Bluetooth signals will be parsed to extract the following information: Bluetooth ID (DeviceID), the unique identifier of each Bluetooth device; Bluetooth name, the name of the Bluetooth device. Then, sort the collected Bluetooth signals according to the signal strength (RSSI value), and select the M Bluetooth signals with the strongest signal strength (e.g., the first 5); form the Bluetooth information by combining the selected M Bluetooth signals with the event time, berth code, and event type; finally, upload the formed Bluetooth information to the server for further processing and analysis.

[0043] Furthermore, in an embodiment of the present invention, in order to reduce the data processing volume, the system can combine with the built-in database or background service to preliminarily filter the collected Bluetooth signals. For example, exclude non-vehicle Bluetooth devices (such as mobile phones, headphones, etc.), and only retain the signals of vehicle Bluetooth devices. Among them, screening can be performed through the name, type, or other characteristics of the Bluetooth device to ensure that only the Bluetooth signals related to the vehicle are retained.

[0044] Through this step, the system can collect and preprocess the Bluetooth signals in the surrounding environment when the vehicle enters or exits the berth, generate Bluetooth information including Bluetooth ID, event time, berth code, and event type, and upload it to the background system for further processing. This process provides basic data support for subsequent vehicle identification, berth management, and other functions.

[0045] Step S2: Upload the Bluetooth information to the server, and filter the multiple Bluetooth IDs through the signal exclusion library stored in the server to obtain the filtered Bluetooth information;

[0046] Specifically, in an embodiment of the present invention, the Bluetooth information (including multiple Bluetooth IDs, event time, berth code, and event type) generated in step S1 is uploaded to the background server through the network. There is a dynamically updated signal exclusion library stored in the background server. This library contains information on known irrelevant Bluetooth device IDs, such as: Bluetooth devices of surrounding shops (such as Bluetooth speakers in shopping malls, advertising devices, etc.), Bluetooth signals of pedestrians' mobile phones, and other non-vehicle-related Bluetooth devices. The M uploaded Bluetooth IDs are matched with the known irrelevant Bluetooth IDs in the signal exclusion library. If a certain Bluetooth ID exists in the signal exclusion library, it is excluded from the uploaded set of Bluetooth IDs; finally, the set of excluded Bluetooth IDs is obtained, and these Bluetooth IDs are considered signals that may be related to vehicles. Subsequently, the background system stores the relevant information of this event in the database, including: event time, the specific time when the vehicle enters or exits; berth code, identifying the specific berth location; event type, distinguishing whether the vehicle enters or exits the berth; the set of excluded Bluetooth IDs, the Bluetooth IDs retained after filtering.

[0047] In this embodiment, the system can use the signal exclusion library to filter the uploaded Bluetooth information, exclude known non-vehicle-related Bluetooth signals, and thus obtain a more accurate set of Bluetooth IDs. These filtered Bluetooth information provides a reliable data basis for subsequent vehicle identification.

[0048] Step S3: Receive the inspection photo-taking event uploaded by the inspector. The inspection photo-taking event includes the berth code, license plate number, berth photo, and photo-taking time.

[0049] Specifically, in an embodiment of the present invention, the inspector uses a device (such as a smartphone or tablet computer) to take a photo of the vehicle in the parking space, recording the specific state and location of the vehicle. The photos taken by the inspector can be processed through image recognition technology to automatically extract the berth code and license plate number in the photo. The image recognition technology can scan the photo and identify the license plate number of the vehicle and the berth code information, and automatically fill in the relevant data. If the image recognition cannot accurately extract the relevant information, the inspector can also manually input the berth code and license plate number to ensure the accuracy of the data. The inspector uploads the taken photos and relevant information (photo-taking time, berth code, license plate number) to the background system. The background system receives the data uploaded by the inspector and stores it in the database. The stored data includes: photo-taking time, recording the time when the inspector takes the photo, as a time stamp, facilitating later data analysis; berth code, the unique identifier of each parking space, facilitating the positioning and management of the parking space; license plate number, the unique identifier of the vehicle, facilitating the identification of the vehicles parked in each berth.

[0050] Step S4: Trigger data association according to the event of leaving the berth or the event of taking inspection photos, and construct associated data, where the associated data includes an associated event, an associated license plate number, and a set of associated Bluetooth IDs;

[0051] Specifically, in an embodiment of the present invention, data association operations are triggered according to the event type (incoming / outgoing) or the photo-taking event uploaded by the inspector. Through the association operation, a set of associated data is constructed, including: the associated time, the time when the association operation is triggered (the time of the outgoing event or the photo-taking event); the associated license plate number, the license plate number identified in the inspection photo-taking event; the set of associated Bluetooth IDs: the set of excluded Bluetooth IDs corresponding to the incoming event.

[0052] Specifically, when an event of leaving the berth occurs, first, find the most recent incoming event for this berth; then, find the inspection photo-taking event after this incoming event and before this outgoing event; finally, associate the set of excluded Bluetooth IDs corresponding to the incoming event with the license plate number in the inspection photo-taking event. For example, berth code: A001; outgoing event time: 2023-10-01 10:00:00; incoming event time: 2023-10-01 09:00:00; inspection photo-taking event time: 2023-10-01 09:30:00, license plate number: JingAAAAA; set of Bluetooth IDs corresponding to the incoming event: {ID1, ID2, ID3}; then the association result is: associated time: 2023-10-01 10:00:00 (outgoing event time); associated license plate number: JingAAAAA; set of associated Bluetooth IDs: {ID1, ID2, ID3}.

[0053] Specifically, when receiving the photo-taking event uploaded by the inspector, first, find the most recent incoming event for this berth before this photo-taking event; then, associate the set of excluded Bluetooth IDs corresponding to the incoming event with the license plate number in this photo-taking event. For example, berth code: A001; incoming event time: 2023-10-01 09:00:00; photo-taking event time: 2023-10-01 09:30:00, license plate number: JingAAAAA; set of Bluetooth IDs corresponding to the incoming event: {ID1, ID2, ID3}; association result, associated time: 2023-10-01 09:30:00 (photo-taking event time); associated license plate number: JingAAAAA; set of associated Bluetooth IDs: {ID1, ID2, ID3}.

[0054] Furthermore, in an embodiment of the present invention, in order to avoid associating outdated data, the system can set a time window threshold. When an event occurs, the system will only associate inspection photo-taking events or outgoing events within the set time window, which can avoid outdated or irrelevant associations, thereby improving the accuracy of data processing.

[0055] In this embodiment, by triggering data association, the system can track the Bluetooth signal of the target vehicle in a timely and accurate manner, avoiding omission. By setting the time window threshold, it can effectively prevent the system from using outdated data during processing, thus ensuring the timeliness and accuracy of the data.

[0056] Step S5: Use the associated data to determine the correspondence between the license plate number and the Bluetooth ID;

[0057] Specifically, in an embodiment of the present invention, the associated data (including the association time, the associated license plate number, and the set of associated Bluetooth IDs) is used to determine the correspondence between the license plate number and the Bluetooth ID. For the same license plate number, the system collects multiple groups of associated data, and each group of data includes: the association time, the time when the association operation is triggered; the set of associated Bluetooth IDs, the set of Bluetooth IDs associated with the license plate number; when the number of groups of associated data reaches the preset threshold X, traverse all the sets of associated Bluetooth IDs, and count the number of times each Bluetooth ID appears; for each Bluetooth ID, calculate the proportion of its appearance times to the total number of groups as the confidence level of this Bluetooth ID; when the confidence level of a certain Bluetooth ID exceeds the preset threshold Y, it is determined that this Bluetooth ID has established a stable correspondence with the license plate number, and this Bluetooth ID is marked as the confirmed Bluetooth ID of this license plate number; at the same time, save the correspondence between the license plate number and the confirmed Bluetooth ID and the confidence level of each Bluetooth ID for subsequent analysis and verification.

[0058] For example, license plate number: Jing AAAAA; preset threshold X = 5 (at least 5 groups of associated data are required); preset threshold Y = 0.6 (the confidence level needs to exceed 60%);

[0059] Associated data groups:

[0060] | Association Time | Set of Associated Bluetooth IDs |

[0061] |--------------------|----------------------|

[0062] | 2023-10-01 09:30:00 | {ID1, ID2, ID3}|

[0063] | 2023-10-01 10:00:00 | {ID1, ID2}|

[0064] | 2023-10-01 10:30:00 | {ID1, ID3}|

[0065] | 2023-10-01 11:00:00 | {ID1, ID2, ID3}|

[0066] | October 1, 2023 11:30:00 | {ID1, ID2}|

[0067] Then the total number of associated data groups: 5; The number of occurrences of Bluetooth ID: ID1: 5 times; ID2: 4 times; ID3: 3 times; Confidence level: ID1: 5 / 5 = 100%; ID2: 4 / 5 = 80%; ID3: 3 / 5 = 60%; Therefore, the confidence level of ID1 is 100% (exceeding the threshold Y = 60%), and it is marked as the confirmed Bluetooth ID; the confidence level of ID2 is 80% (exceeding the threshold Y = 60%), and it is marked as the confirmed Bluetooth ID; the confidence level of ID3 is 60% (equal to the threshold Y = 60%), and it is not marked as the confirmed Bluetooth ID. Save the result: License plate number: JingAAAAA; Confirmed Bluetooth ID: {ID1, ID2}; Confidence level: ID1: 100%; ID2: 80%.

[0068] Therefore, step S5 includes: collecting multiple groups of associated data of the same license plate number; when the number of groups of associated data reaches the first preset threshold, counting the number of occurrences of each Bluetooth ID in the set of associated Bluetooth IDs, and calculating the ratio of the number of occurrences to the total number of groups as the confidence level of the corresponding Bluetooth ID; when the occurrence ratio of one of the Bluetooth IDs exceeds the second preset threshold, then mark the corresponding Bluetooth ID as the confirmed Bluetooth ID of the corresponding license plate number; save the corresponding relationship between the license plate number and the confirmed Bluetooth ID, and at the same time save the confidence level of each Bluetooth ID.

[0069] In this embodiment, by statistically analyzing the associated data, a corresponding Bluetooth ID is matched for each vehicle. Thus, through the confirmed Bluetooth ID, the system can quickly identify the vehicle identity. At the same time, by evaluating the reliability of the corresponding relationship between the associated Bluetooth ID and the license plate number through the confidence level, it supports subsequent optimization. Through multiple groups of associated data and confidence level calculation, the accuracy of the corresponding relationship between the Bluetooth ID and the license plate number is ensured. Through the above steps, the system can efficiently and accurately establish the corresponding relationship between the license plate number and the Bluetooth ID, providing reliable data support for intelligent parking management.

[0070] Further, in an embodiment of the present invention, after the correspondence relationship between the license plate number and the confirmed Bluetooth ID is established, in the data association step after the inspection tour, the system will check whether the previously confirmed Bluetooth ID is continuously missing in the current associated Bluetooth ID set. If the confirmed Bluetooth ID is not associated in multiple inspection tours and the continuous missing times exceed the preset threshold Z, then the system will consider that the validity of this Bluetooth ID has an abnormality. When the confirmed Bluetooth ID continuously does not appear in multiple inspection events and the number of times exceeds the threshold Z, the system will lower the confidence level of this Bluetooth ID. Once it is found that a certain Bluetooth ID fails to be effectively matched in multiple inspection tours, this Bluetooth ID will be added to the candidate failure set. The candidate failure set is a temporary set used to store those Bluetooth IDs that may fail. The system will decide whether to completely abolish this Bluetooth ID according to the subsequent association situation. If a Bluetooth ID reappears in the subsequent association process and its appearance frequency increases, the system will judge that this Bluetooth ID may have restored its validity. Once the Bluetooth ID reappears and is frequently associated, the system will increase the confidence level of this Bluetooth ID according to its appearance frequency, making it restored to a trustworthy Bluetooth ID and re - establishing a stable association relationship with the license plate number. In this way, the system can dynamically adjust the status of each Bluetooth ID, thereby maintaining accuracy and stability in the vehicle recognition process. Therefore, after step S5, it further includes: when the number of times that the associated Bluetooth ID set continuously does not contain the confirmed Bluetooth ID exceeds the third preset threshold, lower the confidence level of the corresponding Bluetooth ID and add this Bluetooth ID to the candidate failure set

[0071] In this embodiment, by adding a continuous missing detection and dynamic confidence adjustment mechanism in the data association process, the system can adapt to the changes in the correspondence relationship between the license plate number and the Bluetooth ID in real - time, especially automatically adjust in case of abnormal situations. For example, if a certain Bluetooth ID cannot be effectively matched within a period of time, the system will reduce its confidence level and re - evaluate its validity. On the contrary, if it reappears and is frequently matched, the system will increase its confidence level again. This mechanism can not only reduce mis - matching caused by accidental events but also prevent long - term invalid Bluetooth IDs from being wrongly continuously regarded as valid correspondence relationships. Through this dynamic adjustment mechanism, the system can maintain efficient and stable vehicle recognition.

[0072] The vehicle identification method and system based on the combination of Bluetooth signals and manual inspection tours combine the Bluetooth signal changes generated when the vehicle enters / leaves the parking space with the license plate information obtained from manual inspection tours, and use data association and statistical analysis to establish the correspondence relationship between the license plate and the Bluetooth ID. This method can effectively eliminate environmental interference, improve the accuracy and reliability of vehicle identification, can be used as an effective supplement to the existing license plate recognition technology, and has a wide application prospect.

[0073] Traditional license plate recognition technologies often rely on cameras and image processing technologies, which may encounter recognition problems in low environmental light or poor viewing angles. The integration of Bluetooth signals can serve as an effective supplementary means to help improve the performance of the overall vehicle identification system. Bluetooth signals are highly affected by environmental factors, such as signal attenuation, reflection, and obstacles. However, this invention uses the combination of Bluetooth signals and manual inspections for vehicle identification, making full use of the complementary advantages of Bluetooth signal variations and manual inspection data, and can significantly improve the accuracy and reliability of vehicle identification. By combining Bluetooth signal variations with license plate information collected through manual inspections, a correspondence relationship between Bluetooth IDs and license plate numbers is established through data association and statistical analysis, thus solving some challenges that traditional license plate recognition technologies may face, such as environmental interference, equipment failures, or insufficient recognition accuracy. Through data association technology, the variations of Bluetooth signals are matched with license plate information. Statistical analysis helps evaluate the effectiveness of the data, reduce noise and false matches, and ensure high-precision vehicle identification.

[0074] By combining Bluetooth signals with manual inspection data, the system can effectively filter out interference, reduce the error rate, and improve the reliability of data association results. Since the system has strong adaptability and robustness and can provide stable recognition effects in various complex environments, it is expected to be widely applied in multiple fields such as intelligent parking, vehicle access management, and intelligent transportation.

[0075] Correspondingly, this invention also provides a vehicle identification system, including: a Bluetooth information collection device, which is used to collect Bluetooth signals in the environment around the parking space and perform preprocessing when detecting a vehicle entering / leaving the parking space event to obtain Bluetooth information, where the Bluetooth information includes multiple Bluetooth IDs, event time, parking space coding, and event type; a Bluetooth information filtering module, which is used to filter the multiple Bluetooth IDs through a signal exclusion library stored in the server to obtain filtered Bluetooth information; an inspection photo-taking event receiving module, which is used to receive the inspection photo-taking events uploaded by the inspector, where the inspection photo-taking events include parking space coding, license plate number, parking space photo, and photo-taking time; an associated data construction module, which is used to trigger data association according to the vehicle leaving the parking space event or the inspection photo-taking event and construct associated data, where the associated data includes associated events, associated license plate numbers, and associated Bluetooth ID sets; and a statistical analysis module, which is used to use the associated data to determine the correspondence relationship between the license plate number and the Bluetooth ID.

[0076] Specifically, in an embodiment of the present invention, when a berth departure event is received, the associated data construction module is configured to find the most recent berth entry event corresponding to the berth, the inspection and photographing events after the most recent berth entry event and before the current berth departure event, and associate the filtered Bluetooth information corresponding to the most recent berth entry event with the license plate number in the inspection and photographing events; when an inspection and photographing event is received, the associated data construction module is configured to find the most recent berth entry event corresponding to the berth before the current inspection and photographing event, and associate the filtered Bluetooth information corresponding to the most recent berth entry event with the license plate number in the current inspection and photographing event.

[0077] Specifically, in an embodiment of the present invention, the statistical analysis module includes: a data collection unit configured to collect multiple groups of associated data of the same license plate number; a data statistics unit configured to, when the number of groups of associated data reaches a first preset threshold, count the number of occurrences of each Bluetooth ID in the associated Bluetooth ID set and calculate the proportion of the number of occurrences to the total number of groups as the confidence level of the corresponding Bluetooth ID; a data marking unit configured to, when the occurrence proportion of one of the Bluetooth IDs exceeds a second preset threshold, mark the corresponding Bluetooth ID as the confirmed Bluetooth ID of the corresponding license plate number; and a data storage unit configured to store the corresponding relationship between the license plate number and the confirmed Bluetooth ID, and simultaneously store the confidence level of each Bluetooth ID.

[0078] Specifically, in an embodiment of the present invention, a data adjustment module is further included, configured to lower the confidence level of the corresponding Bluetooth ID and add the Bluetooth ID to the candidate failure set when the number of consecutive times that the associated Bluetooth ID set does not contain the confirmed Bluetooth ID exceeds a third preset threshold.

[0079] An embodiment of the present invention further provides a vehicle identification device, which may include:

[0080] A memory for storing a computer program;

[0081] A processor configured to implement the following steps when executing the computer program stored in the above memory:

[0082] When a vehicle entry / exit berth event is detected, collect the Bluetooth signals in the environment around the berth and perform preprocessing to obtain Bluetooth information, where the Bluetooth information includes multiple Bluetooth IDs, event time, berth code, and event type; upload the Bluetooth information to a server, and filter the multiple Bluetooth IDs through a signal exclusion library stored in the server to obtain filtered Bluetooth information; receive the inspection photo-taking event uploaded by an inspector, where the inspection photo-taking event includes a berth code, license plate number, berth photo, and photo-taking time; trigger data association according to the vehicle exit berth event or the inspection photo-taking event to construct associated data, where the associated data includes an associated event, an associated license plate number, and a set of associated Bluetooth IDs; and use the associated data to determine the correspondence between the license plate number and the Bluetooth ID.

[0083] An embodiment of the present invention also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following steps can be implemented;

[0084] When a vehicle entry / exit berth event is detected, collect the Bluetooth signals in the environment around the berth and perform preprocessing to obtain Bluetooth information, where the Bluetooth information includes multiple Bluetooth IDs, event time, berth code, and event type; upload the Bluetooth information to a server, and filter the multiple Bluetooth IDs through a signal exclusion library stored in the server to obtain filtered Bluetooth information; receive the inspection photo-taking event uploaded by an inspector, where the inspection photo-taking event includes a berth code, license plate number, berth photo, and photo-taking time; trigger data association according to the vehicle exit berth event or the inspection photo-taking event to construct associated data, where the associated data includes an associated event, an associated license plate number, and a set of associated Bluetooth IDs; and use the associated data to determine the correspondence between the license plate number and the Bluetooth ID.

[0085] The computer-readable storage medium may include: various media such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disc that can store program codes.

[0086] In the specification provided here, a large number of specific details are described. However, it can be understood that the embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures, and technologies are not shown in detail so as not to obscure the understanding of this specification.

[0087] Similarly, it should be understood that, for the purpose of streamlining the present disclosure and facilitating the understanding of one or more of the various inventive aspects, in the foregoing description of the exemplary embodiments of the present invention, the various features of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. However, the disclosed method should not be construed as reflecting an intention that the claimed invention requires more features than are expressly recited in each claim. Rather, as reflected in the following claims, the inventive aspects lie in less than all the features of the single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into the detailed description, with each claim standing on its own as a separate embodiment of the present invention.

[0088] Those skilled in the art will appreciate that the modules in the devices in the embodiments can be adaptively changed and disposed in one or more devices different from the embodiments. The modules or units or components in the embodiments can be combined into one module or unit or component, and in addition, they can be divided into multiple sub-modules or sub-units or sub-components. Except that at least some of such features and / or processes or units are mutually exclusive, any combination can be used to combine all the features disclosed in this specification (including the accompanying claims, abstract, and drawings) and all the processes or units of any method or device so disclosed. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) can be replaced by an alternative feature that provides the same, equivalent, or similar purpose.

[0089] In addition, those skilled in the art will be able to understand that although some of the embodiments herein include certain features included in other embodiments but not other features, the combination of the features of different embodiments means that it is within the scope of the present invention and forms different embodiments. For example, in the following claims, any one of the claimed embodiments can be used in any combination.

[0090] The various component embodiments of the present invention can be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art should understand that a microprocessor or a digital signal processor (DSP) can be used in practice to implement some or all of the functions of some or all of the components according to the embodiments of the present invention. The present invention can also be implemented as a device or apparatus program (e.g., a computer program and a computer program product) for performing part or all of the methods described herein. Such a program for implementing the present invention can be stored on a computer-readable medium, or can be in the form of one or more signals. Such signals can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0091] It should be noted that the above embodiments are illustrative of the present invention and not restrictive, and those skilled in the art can design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in the claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present invention can be implemented by means of hardware including several different elements and by means of a suitably programmed computer. In the unit claims listing several devices, several of these devices can be embodied by the same item of hardware. The use of the words first, second, and third, etc. does not denote any order. These words can be interpreted as names.

Claims

1. A vehicle identification method, characterized in that: The following steps are involved: When a vehicle entering / exiting a parking space event is detected, Bluetooth signals from the parking space surroundings are collected and preprocessed to obtain Bluetooth information, where the Bluetooth information includes multiple Bluetooth IDs, event time, parking space code, and event type; Uploading the Bluetooth information to a server, and filtering the multiple Bluetooth IDs through a signal exclusion library stored in the server to obtain filtered Bluetooth information; Receive inspection photo events uploaded by inspectors, including berth code, license plate number, berth photo and photo time; Triggering data association according to the exiting berth event or the inspection and photographing event to construct associated data, wherein the associated data includes an associated event, an associated license plate number, and an associated Bluetooth ID set; as well as Using the associated data, determining the correspondence between the license plate number and the Bluetooth ID; In the step of triggering data association according to the exiting berth event and constructing associated data, when the exiting berth event is received, the most recent entry event of the corresponding berth, the inspection and photo taking event after the most recent entry event and before the current exiting event are searched, and the filtered Bluetooth information corresponding to the most recent entry event is associated with the license plate number in the inspection and photo taking event; When receiving the inspection photo event, find the most recent entry event of the corresponding berth before the current inspection photo event, and associate the filtered Bluetooth information corresponding to the most recent entry event with the license plate number in the current inspection photo event; The step of determining the correspondence between the license plate number and the Bluetooth ID using the association data includes: Collect multiple sets of associated data for the same license plate number; When the number of groups of associated data reaches a first preset threshold, the number of occurrences of each Bluetooth ID in the associated Bluetooth ID set is counted, and the proportion of the number of occurrences to the total number of groups is calculated as the confidence of the corresponding Bluetooth ID; When the appearance ratio of one of the Bluetooth IDs exceeds a second preset threshold, the corresponding Bluetooth ID is marked as a confirmed Bluetooth ID of the corresponding license plate number; After the step of saving the correspondence between the license plate number and the confirmed Bluetooth ID and saving the confidence of each Bluetooth ID; and using the association data to determine the correspondence between the license plate number and the Bluetooth ID, the method further includes: When the number of times that the confirmed Bluetooth ID is not continuously included in the associated Bluetooth ID set exceeds a third preset threshold, the confidence of the corresponding Bluetooth ID is lowered, and the Bluetooth ID is added to the candidate failure set.

2. A vehicle identification system, characterized in that: include: A Bluetooth information collection device, for collecting and preprocessing Bluetooth signals in the surrounding environment of a parking space when a vehicle entering / exiting a parking space event is detected, to obtain Bluetooth information, wherein the Bluetooth information includes multiple Bluetooth IDs, event time, parking space code and event type; A Bluetooth information filtering module, used for filtering the multiple Bluetooth IDs through a signal exclusion library stored in the server to obtain filtered Bluetooth information; The inspection photo event receiving module is used to receive the inspection photo events uploaded by the inspectors, and the inspection photo events include the berth code, license plate number, berth photo and photo time; A correlation data construction module, used to trigger data association according to a berth exit event or a patrol photo event, and construct correlation data, wherein the correlation data includes a correlation event, a correlation license plate number, and a correlation Bluetooth ID set; as well as A statistical analysis module, used to determine the corresponding relationship between the license plate number and the Bluetooth ID using the associated data; When receiving a berth exit event, the associated data construction module is used to search for the most recent entry event of the corresponding berth, the inspection and photo taking event after the most recent entry event and before the current exit event, and associate the filtered Bluetooth information corresponding to the most recent entry event with the license plate number in the inspection and photo taking event; When receiving the inspection photo event, the associated data construction module is used to find the most recent entry event of the corresponding berth before the current inspection photo event, and associate the filtered Bluetooth information corresponding to the most recent entry event with the license plate number in the current inspection photo event; The statistical analysis module includes: A data collection unit, used for collecting multiple sets of associated data of the same license plate number; A data statistics unit, configured to count the number of occurrences of each Bluetooth ID in the associated Bluetooth ID set when the number of groups of associated data reaches a first preset threshold, and calculate the proportion of the number of occurrences to the total number of groups as the confidence of the corresponding Bluetooth ID; a data marking unit, configured to mark the corresponding Bluetooth ID as a confirmed Bluetooth ID corresponding to the license plate number when the appearance ratio of one of the Bluetooth IDs exceeds a second preset threshold; A data storage unit, used to store the corresponding relationship between the license plate number and the confirmed Bluetooth ID, and also store the confidence level of each Bluetooth ID; It also includes a data adjustment module, which is used to lower the confidence of the corresponding Bluetooth ID and add the Bluetooth ID to the candidate failure set when the number of times that the confirmed Bluetooth ID is not continuously included in the associated Bluetooth ID set exceeds a third preset threshold.

3. A vehicle identification device, characterized in that: The method comprises a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, the steps of the vehicle identification method as claimed in claim 1 are implemented.

4. A computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, characterized in that: When the computer program is executed by a processor, the steps of the vehicle identification method according to claim 1 are implemented.

Images