Intelligent management and control method of intelligent electric bicycle and intelligent control system of electric bicycle

Abstract

The invention relates to the technical field of artificial intelligence, and discloses an intelligent management and control method of an intelligent electric bicycle and an intelligent control system of the electric bicycle. The method comprises the following steps: determining electric vehicle passing information of a vehicle driving scene through an electric vehicle intelligent control platform provided by a system based on RFID read-write equipment arranged in at least one key node area of the vehicle driving scene; monitoring video image data of a vehicle driving scene based on a video acquisition device of each key node area; executing preset deep analysis operation on the passing information of the electric vehicles and the video image data to obtain label information of the electric vehicles in each key node area; and classifying all the electric vehicles in the key node area according to the label information of all the electric vehicles in the key node area to obtain a classification result of the key node area, thereby executing corresponding management and control operation. Therefore, the traffic control efficiency and accuracy of the electric bicycle can be improved.

Description

Technical Field

[0001] This invention relates to the field of artificial intelligence technology, and in particular to an intelligent control method for smart electric bicycles and an intelligent control system for electric bicycles. Background Technology

[0002] Due to their energy-saving, environmentally friendly, convenient, and economical characteristics, electric bicycles (also known as e-bikes) have become a major mode of transportation for the public, with a large and rapidly growing number of them. Because of the large number of electric bicycle riders and the low barrier to entry for driving them, most owners have a weak awareness of traffic safety. Therefore, traffic violations such as running red lights, riding against traffic, and occupying lanes are frequent, and traffic accidents caused by electric bicycles account for a high proportion, resulting in many deaths and injuries, posing a significant threat to road traffic safety. Therefore, the management of electric bicycles is an urgent priority in improving traffic order.

[0003] Currently, the management of electric bicycles mainly relies on physical license plates for identification and on roadside police patrols or fixed video surveillance to identify violations. However, practice has revealed the following technical shortcomings in traditional electric bicycle management methods: Firstly, physical license plates are easily counterfeited, forged, altered, or deliberately obscured, resulting in low accuracy and efficiency in identification. Secondly, the methods of identifying violations through roadside police patrols or fixed video surveillance are relatively limited and have low accuracy and efficiency in identifying complex violation scenarios. These technical shortcomings both contribute to low accuracy and efficiency in traffic management.

[0004] Therefore, it is particularly important to propose a new intelligent management and control scheme for smart electric bicycles to improve the efficiency and accuracy of electric bicycle traffic management. Summary of the Invention This invention provides an intelligent management and control method for smart electric bicycles and an intelligent control system for electric bicycles, which can improve the efficiency and accuracy of traffic management for electric bicycles.

[0005] To address the aforementioned technical problems, the first aspect of this invention discloses an intelligent control method for smart electric bicycles. This method is applied to an intelligent control system for electric bicycles, which includes an RFID reader / writer, a video acquisition device, and an intelligent control platform. The intelligent control system is used to control the vehicle within a driving scenario. The method includes: The electric vehicle intelligent control platform determines the electric vehicle traffic information of the vehicle driving scenario based on the RFID signal data collected by RFID reading and writing devices deployed in at least one key node area of ​​the vehicle driving scenario. The electric vehicle intelligent control platform monitors video image data of the vehicle driving scene based on video acquisition devices in each of the key node areas. For each key node area, the electric vehicle intelligent control platform performs a preset deep analysis operation on the electric vehicle traffic information and the video image data to obtain the tag information of each electric vehicle in the key node area. The deep analysis operation includes index evaluation operation and / or key personnel clustering operation. The tag information includes first type tag information or second type tag information. The electric vehicle intelligent control platform classifies all electric vehicles in the key node area based on the tag information of all electric vehicles in the key node area, and obtains the classification result of the key node area. The classification result includes a first type of electric vehicle set and a second type of electric vehicle set. The first type of electric vehicle set is empty or the tag information of all electric vehicles in the first type of electric vehicle set is the first type of tag information. The second type of electric vehicle set is empty or the tag information of all electric vehicles in the second type of electric vehicle set is the second type of tag information. The first type of electric vehicle set and the second type of electric vehicle set are not both empty. The electric vehicle intelligent control platform performs corresponding control operations on each electric vehicle in the key node area based on the classification results of the key node area. The control operations include release operations or warning operations.

[0006] As an optional implementation, in the first aspect of the present invention, the electric vehicle intelligent control platform determines the electric vehicle traffic information of the vehicle driving scenario based on RFID signal data collected by RFID reading and writing devices deployed in at least one key node area of ​​the vehicle driving scenario, including: The electric vehicle intelligent control platform determines the scenario type of at least one electronic tag in the key node area based on RFID reading and writing devices deployed in at least one key node area of ​​the vehicle driving scenario. The electronic tag is carried by the digital license plate installed on the electric vehicle to which it belongs. For each of the aforementioned electronic tags, the electric vehicle intelligent control platform determines the data exchange method between the electronic tag and the RFID reading and writing devices deployed in the corresponding key node area based on the scenario type of the electronic tag in the corresponding key node area. The electric vehicle intelligent control platform, based on the data exchange method, collects RFID signal data of each electronic tag in each key node area through the RFID reader / writer device in each key node area; The electric vehicle intelligent control platform determines the RFID signal data of all electronic tags in all key node areas of the vehicle driving scenario as the electric vehicle traffic information of the vehicle driving scenario.

[0007] As an optional implementation, in the first aspect of the present invention, the electric vehicle intelligent control platform determines the scenario type of at least one electronic tag in at least one key node area of ​​the vehicle driving scenario based on RFID reading and writing devices deployed in at least one key node area of ​​the key node area, including: The electric vehicle intelligent control platform obtains the deployment location of RFID reading and writing devices in at least one key node area of ​​the vehicle driving scenario, as well as the device performance parameters of the RFID reading and writing devices. For each of the key node areas, the electric vehicle intelligent control platform detects the tag position parameters of at least one electronic tag within the key node area based on the RFID reader / writer device in that key node area. For each of the aforementioned electronic tags, the electric vehicle intelligent control platform determines the target communication distance between the electronic tag and the RFID reader / writer based on the device performance parameters of the RFID reader / writer, the deployment location of the RFID reader / writer, and the tag position parameters of the electronic tag. The electric vehicle intelligent control platform detects the target communication distance of the electronic tag; and when the target communication distance of the electronic tag is detected to be within a first preset distance range, the scene type of the electronic tag is determined to be the near-field type; and when the target communication distance of the electronic tag is detected to be within a second preset distance range, the scene type of the electronic tag is determined to be the far-field type.

[0008] As an optional implementation, in the first aspect of the present invention, the tag position parameter includes at least the current position of the tag and also the changed position of the tag, wherein the changed position of the tag represents the position change of the corresponding electronic tag within a preset time period; Furthermore, for each of the aforementioned electronic tags, the electric vehicle intelligent control platform determines the target communication distance between the electronic tag and the RFID reader / writer based on the device performance parameters of the RFID reader / writer, the deployment location of the RFID reader / writer, and the tag position parameters of the electronic tag, including: For each of the aforementioned electronic tags, the electric vehicle intelligent control platform determines the reference communication distance between the electronic tag and the RFID reader / writer based on the deployment location of the RFID reader / writer, the current location of the electronic tag, and the location where the electronic tag changes position. The electric vehicle intelligent control platform determines the signal diffusion distribution of the RFID reader / writer within the key node area to which the electronic tag belongs based on the device performance parameters of the RFID reader / writer; and determines the signal detection strength of the RFID reader / writer for the electronic tag based on the signal diffusion distribution and the current position of the electronic tag. The electric vehicle intelligent control platform determines the distance adjustment coefficient corresponding to the electronic tag based on the signal detection strength corresponding to the electronic tag; and calculates the target communication distance of the electronic tag based on the distance adjustment coefficient corresponding to the electronic tag and the reference communication distance of the electronic tag.

[0009] As an optional implementation, in the first aspect of the present invention, for each of the electronic tags, the electric vehicle intelligent control platform determines the reference communication distance between the electronic tag and the RFID reader / writer based on the deployment location of the RFID reader / writer, the current location of the electronic tag, and the changed location of the electronic tag, including: For each of the aforementioned electronic tags, the electric vehicle intelligent control platform calculates the initial communication distance between the electronic tag and the RFID reader / writer based on the deployment location of the RFID reader / writer and the current location of the electronic tag. The electric vehicle intelligent control platform analyzes the movement parameters of the electronic tag based on the tag's changing position. The movement parameters include the movement direction and at least one sub-type of movement parameters in the movement direction. All the sub-type of movement parameters include at least one of the movement distance, movement speed, and movement duration. The electric vehicle intelligent control platform predicts the distance change trend between the electronic tag and the RFID reader / writer within the key node area based on the electronic tag's movement parameters and its initial communication distance. The electric vehicle intelligent control platform predicts multiple expected communication distances of the electronic tag under the influence of the distance change trend and the initial communication distance of the electronic tag, and selects one of the communication distances from the set of all expected communication distances of the electronic tag and the initial communication distance of the electronic tag as the reference communication distance between the electronic tag and the RFID reader / writer.

[0010] As an optional implementation, in the first aspect of the present invention, the scene type includes a near-field type or a far-field type; the data exchange method includes a load modulation method or a backscatter modulation method; Furthermore, for each of the aforementioned electronic tags, the electric vehicle intelligent control platform determines the data exchange method between the electronic tag and the RFID reading / writing devices deployed in the corresponding key node area based on the scenario type of the electronic tag in the corresponding key node area, including: For each of the aforementioned electronic tags, when the scenario type of the electronic tag is the near-field type, the electric vehicle intelligent control platform determines that the data exchange method between the electronic tag and the RFID reading and writing device deployed in the corresponding key node area is the load modulation method; When the scenario type of the electronic tag is the far-field type, the electric vehicle intelligent control platform determines that the data exchange method between the electronic tag and the RFID reading and writing devices deployed in the corresponding key node area is the backscatter modulation method.

[0011] As an optional implementation, in the first aspect of the present invention, the electric vehicle intelligent control platform monitors video image data of the vehicle driving scene based on video acquisition devices in each of the key node areas, including: Based on the video acquisition device in each of the key node areas, monitor the video stream data in the vehicle driving scene; Based on video AI technology, the video stream data is analyzed frame by frame to obtain multiple initial video image data; Based on a pre-trained image recognition model, all the initial video image data are identified to obtain at least one active object in the vehicle driving scene; Based on the preset alarm rule information corresponding to the video acquisition device, each active object is identified to obtain the driving behavior of the active object; When the driving behavior of the active object constitutes a safety threat that violates the alarm rule information, a warning message is determined for the active object based on the driving behavior of the active object, and the warning message is sent to the active object; and the initial video image data containing the active object is filtered from all the initial video image data; By integrating the initial video image data of all active objects involved in the driving behavior that poses the safety threat, video image data of the vehicle driving scene is obtained.

[0012] A second aspect of this invention discloses an intelligent control system for electric bicycles, comprising an RFID reader / writer, a video acquisition device, and an intelligent control platform for electric bicycles. The intelligent control system is used to manage and control the vehicle within a driving scenario. The intelligent control platform for electric bicycles includes: The determination module is used to determine the electric vehicle traffic information of the vehicle driving scenario based on the RFID signal data collected by RFID reading and writing devices deployed in at least one key node area of ​​the vehicle driving scenario. The monitoring module is used to monitor video image data of the vehicle driving scene based on the video acquisition device of each of the key node areas; The analysis module is used to perform a preset deep analysis operation on the electric vehicle traffic information and the video image data for each key node area to obtain the tag information of each electric vehicle in the key node area. The deep analysis operation includes index evaluation operation and / or key personnel clustering operation. The tag information includes first type tag information or second type tag information. The classification module is used to classify all electric vehicles in the key node area according to the tag information of all electric vehicles in the key node area, and obtain the classification result of the key node area. The classification result includes a first type of electric vehicle set and a second type of electric vehicle set. The first type of electric vehicle set is empty or the tag information of all electric vehicles in the first type of electric vehicle set is the first type of tag information. The second type of electric vehicle set is empty or the tag information of all electric vehicles in the second type of electric vehicle set is the second type of tag information. The first type of electric vehicle set and the second type of electric vehicle set are not empty at the same time. The control module is used to perform corresponding control operations on each electric vehicle in the key node area based on the classification results of the key node area. The control operations include release operations or warning operations.

[0013] As an optional implementation, in a second aspect of the present invention, the specific method by which the determining module determines the electric vehicle traffic information of the vehicle driving scenario based on the RFID signal data collected by RFID reading and writing devices deployed in at least one key node area of ​​the vehicle driving scenario includes: The electric vehicle intelligent control platform determines the scenario type of at least one electronic tag in the key node area based on RFID reading and writing devices deployed in at least one key node area of ​​the vehicle driving scenario. The electronic tag is carried by the digital license plate installed on the electric vehicle to which it belongs. For each of the aforementioned electronic tags, the electric vehicle intelligent control platform determines the data exchange method between the electronic tag and the RFID reading and writing devices deployed in the corresponding key node area based on the scenario type of the electronic tag in the corresponding key node area. The electric vehicle intelligent control platform, based on the data exchange method, collects RFID signal data of each electronic tag in each key node area through the RFID reader / writer device in each key node area; The electric vehicle intelligent control platform determines the RFID signal data of all electronic tags in all key node areas of the vehicle driving scenario as the electric vehicle traffic information of the vehicle driving scenario.

[0014] As an optional implementation, in the second aspect of the present invention, the specific method by which the determining module determines the scene type of at least one electronic tag in at least one key node area of ​​a vehicle driving scenario based on RFID reading and writing devices deployed in that key node area includes: The electric vehicle intelligent control platform obtains the deployment location of RFID reading and writing devices in at least one key node area of ​​the vehicle driving scenario, as well as the device performance parameters of the RFID reading and writing devices. For each of the key node areas, the electric vehicle intelligent control platform detects the tag position parameters of at least one electronic tag within the key node area based on the RFID reader / writer device in that key node area. For each of the aforementioned electronic tags, the electric vehicle intelligent control platform determines the target communication distance between the electronic tag and the RFID reader / writer based on the device performance parameters of the RFID reader / writer, the deployment location of the RFID reader / writer, and the tag position parameters of the electronic tag. The electric vehicle intelligent control platform detects the target communication distance of the electronic tag; and when the target communication distance of the electronic tag is detected to be within a first preset distance range, the scene type of the electronic tag is determined to be the near-field type; and when the target communication distance of the electronic tag is detected to be within a second preset distance range, the scene type of the electronic tag is determined to be the far-field type.

[0015] As an optional implementation, in the second aspect of the present invention, the tag position parameter includes at least the current position of the tag and also the changed position of the tag, wherein the changed position of the tag represents the position change of the corresponding electronic tag within a preset time period; Furthermore, the specific method by which the determining module determines the target communication distance between the electronic tag and the RFID reader / writer based on the device performance parameters of the RFID reader / writer, the deployment location of the RFID reader / writer, and the tag location parameters of the electronic tag includes: For each of the aforementioned electronic tags, the electric vehicle intelligent control platform determines the reference communication distance between the electronic tag and the RFID reader / writer based on the deployment location of the RFID reader / writer, the current location of the electronic tag, and the location where the electronic tag changes position. The electric vehicle intelligent control platform determines the signal diffusion distribution of the RFID reader / writer within the key node area to which the electronic tag belongs based on the device performance parameters of the RFID reader / writer; and determines the signal detection strength of the RFID reader / writer for the electronic tag based on the signal diffusion distribution and the current position of the electronic tag. The electric vehicle intelligent control platform determines the distance adjustment coefficient corresponding to the electronic tag based on the signal detection strength corresponding to the electronic tag; and calculates the target communication distance of the electronic tag based on the distance adjustment coefficient corresponding to the electronic tag and the reference communication distance of the electronic tag.

[0016] As an optional implementation, in the second aspect of the present invention, the determining module, for each of the electronic tags, determines the reference communication distance between the electronic tag and the RFID reader / writer based on the deployment location of the RFID reader / writer, the current location of the electronic tag, and the changed location of the electronic tag, in the following specific ways: For each of the aforementioned electronic tags, the electric vehicle intelligent control platform calculates the initial communication distance between the electronic tag and the RFID reader / writer based on the deployment location of the RFID reader / writer and the current location of the electronic tag. The electric vehicle intelligent control platform analyzes the movement parameters of the electronic tag based on the tag's changing position. The movement parameters include the movement direction and at least one sub-type of movement parameters in the movement direction. All the sub-type of movement parameters include at least one of the movement distance, movement speed, and movement duration. The electric vehicle intelligent control platform predicts the distance change trend between the electronic tag and the RFID reader / writer within the key node area based on the electronic tag's movement parameters and its initial communication distance. The electric vehicle intelligent control platform predicts multiple expected communication distances of the electronic tag under the influence of the distance change trend and the initial communication distance of the electronic tag, and selects one of the communication distances from the set of all expected communication distances of the electronic tag and the initial communication distance of the electronic tag as the reference communication distance between the electronic tag and the RFID reader / writer.

[0017] As an optional implementation, in the second aspect of the present invention, the scene type includes a near-field type or a far-field type; the data exchange method includes a load modulation method or a backscatter modulation method; Furthermore, for each of the aforementioned electronic tags, the electric vehicle intelligent control platform determines, based on the scenario type of the electronic tag in the corresponding key node area, the specific method for data exchange between the electronic tag and the RFID reading and writing devices deployed in the corresponding key node area, including: For each of the aforementioned electronic tags, when the scenario type of the electronic tag is the near-field type, the electric vehicle intelligent control platform determines that the data exchange method between the electronic tag and the RFID reading and writing device deployed in the corresponding key node area is the load modulation method; When the scenario type of the electronic tag is the far-field type, the electric vehicle intelligent control platform determines that the data exchange method between the electronic tag and the RFID reading and writing devices deployed in the corresponding key node area is the backscatter modulation method.

[0018] As an optional implementation, in a second aspect of the present invention, the monitoring module monitors video image data of the vehicle driving scene based on video acquisition devices in each of the key node areas in the following specific manner: Based on the video acquisition device in each of the key node areas, monitor the video stream data in the vehicle driving scene; Based on video AI technology, the video stream data is analyzed frame by frame to obtain multiple initial video image data; Based on a pre-trained image recognition model, all the initial video image data are identified to obtain at least one active object in the vehicle driving scene; Based on the preset alarm rule information corresponding to the video acquisition device, each active object is identified to obtain the driving behavior of the active object; When the driving behavior of the active object constitutes a safety threat that violates the alarm rule information, a warning message is determined for the active object based on the driving behavior of the active object, and the warning message is sent to the active object; and the initial video image data containing the active object is filtered from all the initial video image data; By integrating the initial video image data of all active objects involved in the driving behavior that poses the safety threat, video image data of the vehicle driving scene is obtained.

[0019] A third aspect of this invention discloses an intelligent control system for electric bicycles, the intelligent control system for electric bicycles comprising: Memory containing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the intelligent management and control method for smart electric bicycles disclosed in the first aspect of the present invention.

[0020] The fourth aspect of the present invention discloses a computer storage medium storing computer instructions, which, when invoked, are used to execute the intelligent control method for smart electric bicycles disclosed in the first aspect of the present invention.

[0021] Compared with the prior art, the embodiments of the present invention have the following beneficial effects: In this embodiment of the invention, the electric vehicle intelligent control platform of the electric bicycle intelligent control system collects RFID signal data of the vehicle driving scene based on RFID reading and writing devices deployed in at least one key node area of ​​the vehicle driving scene to determine the electric vehicle passage information of the vehicle driving scene; and monitors video image data of the vehicle driving scene based on video acquisition devices in each key node area; for each key node area, a preset deep analysis operation is performed on the electric vehicle passage information and the video image data to obtain the tag information of each electric vehicle in the key node area. The deep analysis operation includes index evaluation operation and / or key personnel clustering operation, and the tag information includes first type tag information or second type tag information; according to The tag information of all electric vehicles within the critical node area is collected, and all electric vehicles within the critical node area are classified to obtain the classification result of the critical node area. The classification result includes a first category set of electric vehicles and a second category set of electric vehicles. The first category set of electric vehicles is empty, or the tag information of all electric vehicles in the first category set is the first category tag information. The second category set of electric vehicles is empty, or the tag information of all electric vehicles in the second category set is the second category tag information. The first category set of electric vehicles and the second category set of electric vehicles are not both empty. Then, according to the classification result of the critical node area, corresponding control operations are performed on each electric vehicle in the critical node area. The control operations include release operations or warning operations. It is evident that implementing this invention enables the automatic collection of electric vehicle traffic information through RFID technology, achieving accurate vehicle identification and real-time tracking, significantly improving data collection efficiency and accuracy. Furthermore, the use of video image data provides visual verification, enhancing information credibility and providing multi-dimensional data support for subsequent intelligent analysis. By employing deep analysis algorithms such as index evaluation and key personnel clustering, electric vehicles and riders are tagged, effectively improving hazard identification capabilities. Based on the tag information obtained from these tags, electric vehicles are accurately classified, laying the foundation for implementing differentiated and refined management strategies. Subsequently, precise control measures such as release or warning are automatically executed based on the classification results, improving the efficiency and accuracy of electric bicycle traffic management and facilitating the optimized allocation of management resources and proactive prevention of safety hazards. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a flowchart illustrating an intelligent management and control method for a smart electric bicycle disclosed in an embodiment of the present invention; Figure 2 This is a flowchart illustrating another intelligent management and control method for smart electric bicycles disclosed in an embodiment of the present invention. Figure 3 This is a schematic diagram of the structure of an intelligent control system for an electric bicycle disclosed in an embodiment of the present invention; Figure 4 This is a schematic diagram of another intelligent control system for electric bicycles disclosed in an embodiment of the present invention. Detailed Implementation

[0024] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0025] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, apparatus, product, or end that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or ends.

[0026] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0027] This invention discloses an intelligent management and control method for smart electric bicycles and an intelligent control system for electric bicycles. It can automatically collect electric bicycle traffic information through RFID technology, achieving accurate vehicle identification and real-time tracking, significantly improving data collection efficiency and accuracy. Furthermore, it utilizes video image data to provide visual verification, enhancing information credibility and providing multi-dimensional data support for subsequent intelligent analysis. It then employs deep analysis algorithms such as index evaluation and key personnel clustering to mark electric bicycles and riders, effectively improving hazard identification capabilities. Based on the tag information obtained from these markings, electric bicycles are accurately classified, laying the foundation for implementing differentiated and refined management strategies. Subsequently, based on the classification results, it automatically executes precise control measures such as release or warning, improving the efficiency and accuracy of electric bicycle traffic management. This facilitates optimized allocation of management resources and proactive prevention of safety hazards. Compared to traditional electric bicycle management methods, this solution integrates comprehensive processing functions such as data collection and analysis, classification management, and precise control through an intelligent electric bicycle control platform, constructing an intelligent and refined electric bicycle governance system. This is beneficial for improving the efficiency of electric bicycle traffic management, accurately identifying risks and hazards, optimizing the allocation of law enforcement resources, and promoting the transformation and upgrading of electric bicycle management from a passive response to a proactive prevention model. Detailed explanations follow.

[0028] Example 1 Please see Figure 1 , Figure 1 This is a flowchart illustrating an intelligent management and control method for smart electric bicycles disclosed in an embodiment of the present invention. Wherein, Figure 1 The described intelligent management and control method for smart electric bicycles can be applied to an intelligent control system for electric bicycles. This system includes RFID reading and writing devices (e.g., RFID readers), video acquisition devices (e.g., various cameras, DVRs, DVSs, and streaming media servers), and an intelligent control platform for electric bicycles. The system also includes antennas for communication between the RFID reading and writing devices and the intelligent control platform, as well as between the video acquisition devices and the intelligent control platform. Furthermore, the intelligent control system is used to manage vehicles within a specific driving scenario, such as collecting data on road violations and vehicle passage. This embodiment of the invention is not limited to these specific methods. Figure 1 As shown, the intelligent management and control method for this smart electric bicycle may include the following operations: 101. The electric vehicle intelligent control platform determines the electric vehicle traffic information based on the RFID signal data collected by RFID reading and writing devices deployed in at least one key node area of ​​the vehicle driving scenario.

[0029] In this embodiment of the invention, optionally, the vehicle driving scenario (e.g., major road intersections, roads around key commercial areas, roads around schools or hospitals, entrances and exits of urban expressways, etc.) may include at least one key node area (e.g., traffic light controlled intersections, median strips of road sections, entrances to restricted areas, administrative districts / jurisdictional boundaries, etc.), and each key node area may be equipped with RFID reading and writing devices to collect RFID signal data carried by the digital license plates installed on electric bicycles passing through the key node area. This embodiment of the invention does not impose any limitations.

[0030] In this embodiment of the invention, RFID (Radio Frequency Identification) technology is a type of automatic identification technology that uses wireless radio frequency for non-contact two-way data communication. It reads and writes data to a recording medium (electronic tag or RFID card) using radio frequency, thereby achieving target identification and data exchange. Specifically, RFID technology utilizes radio waves for non-contact, rapid information exchange and storage. It combines wireless communication with data access technology and connects to a database system to achieve non-contact two-way communication, thus achieving identification and data exchange, forming an extremely complex system. Within the identification system, electromagnetic waves are used to read, write, and communicate with electronic tags.

[0031] In this embodiment of the invention, specifically, historical violation data records for each scene location in the vehicle driving scenario are acquired, and the required level of supervision for each scene location is determined based on the historical violation data records for each scene location (for example, scene locations with a higher frequency of violation data in the historical violation data records require a higher level of supervision); based on the required level of supervision for each scene location and the equipment parameters of the RFID reading and writing devices to be deployed (at least one of the following: device name, device type, device model, device signal coverage range, etc.), all scene locations within the vehicle driving scenario are divided to obtain at least one key node area, and all scene locations within each key node area are used to deploy the corresponding RFID reading and writing devices.

[0032] For example, suppose an electric bicycle with a digital license plate passes through a key node area. The RFID reader / writer deployed in that key node area can collect the RFID signal data carried by the electric bicycle's digital license plate and send this RFID signal data to the electric vehicle intelligent control platform. The electric vehicle intelligent control platform receives the RFID signal data collected by the RFID reader / writer deployed in all key node areas and, based on all the RFID signal data, determines the electric vehicle traffic information for the vehicle driving scenario. This electric vehicle traffic information can be used as the basis for electric vehicle traffic flow information and trajectory information.

[0033] 102. The electric vehicle intelligent control platform monitors video image data of the vehicle driving scene based on video acquisition equipment in each key node area.

[0034] In this embodiment of the invention, video image data can optionally be used to identify at least one of the following: vehicle body information, personnel behavior information, dynamic behavior data, scene environment data, and spatiotemporal correlation information. Optionally, vehicle body information may include at least one of the following: electric bicycle appearance characteristics (color, model, brand), digital license plate characters, and unique vehicle identifiers (special markings, damage features). Personnel behavior information may include at least one of the following: rider facial recognition and attributes (gender, age group, whether wearing a helmet), number and characteristics of passengers (e.g., whether illegally carrying passengers), and riding posture and actions (holding a phone while riding, riding against traffic). Dynamic behavior data may include at least one of the following: traffic signal status and vehicle violation process (running a red light, not driving in the designated lane), driving trajectory and speed (driving against traffic, speeding, illegal lane changes), and cargo status (oversized, overweight, overlength cargo). Scene environment data may include at least one of the following: road signs and markings and surrounding environment, interaction relationships with other traffic participants (motor vehicles, pedestrians), and a complete record of the moment an accident occurs. The spatiotemporal correlation information may include at least one of the following: precise timestamp (millisecond level), camera location number, and geographic coordinates. This embodiment of the invention does not impose any limitations.

[0035] In this embodiment of the invention, optionally, there is no order between step 102 and step 101. That is, step 102 can occur before step 101, after step 101, or simultaneously with step 101. This embodiment of the invention does not impose any limitations.

[0036] 103. For each key node area, the electric vehicle intelligent control platform performs a preset deep analysis operation on the electric vehicle traffic information and video image data to obtain the tag information of each electric vehicle in that key node area.

[0037] In this embodiment of the invention, the in-depth analysis operation may optionally include index evaluation and / or key personnel clustering. Specifically, the electric vehicle intelligent control platform, through interconnection with the computing power center, can perform in-depth analysis such as index evaluation and key personnel (i.e., important personnel) clustering on the electric vehicle traffic information and video image data collected in each key node area, thereby obtaining the tag information of each electric vehicle in each key node area. Optionally, the tag information includes a first type of tag information or a second type of tag information. The first type of tag information is information with an electronic tag and no violation record, while the second type of tag information is information without an electronic tag and / or with a violation record.

[0038] 104. The electric vehicle intelligent control platform classifies all electric vehicles in the key node area based on the tag information of all electric vehicles in the key node area, and obtains the classification result of the key node area.

[0039] In this embodiment of the invention, the classification result includes a first set of electric vehicles and a second set of electric vehicles. The first set of electric vehicles is either empty or all electric vehicles within the first set have first-type tag information. The second set of electric vehicles is either empty or all electric vehicles within the second set have second-type tag information. The first and second sets of electric vehicles cannot be empty simultaneously. For example, when the first set of electric vehicles is empty, the second set is not empty, and all electric vehicles within the second set have second-type tag information, meaning that each electric vehicle in the second set does not have an electronic tag and / or has a violation record. Conversely, when the second set of electric vehicles is empty, the first set is not empty, and all electric vehicles within the first set have first-type tag information, meaning that each electric vehicle in the first set has an electronic tag and has no violation record.

[0040] 105. Based on the classification results of the key node area, the electric vehicle intelligent control platform performs corresponding control operations on each electric vehicle within the key node area.

[0041] In this embodiment of the invention, the control operation includes a release operation or a warning operation. Specifically, for each key node area, when the first type of electric vehicle set within the key node area is not empty, a release operation is performed on each electric vehicle within the first type of electric vehicle set; when the second type of electric vehicle set within the key node area is not empty, a warning operation is performed on each electric vehicle within the second type of electric vehicle set.

[0042] It is evident that implementation Figure 1The described intelligent management method for smart electric bicycles can automatically collect electric bicycle traffic information through RFID technology, achieving accurate vehicle identification and real-time tracking, significantly improving data collection efficiency and accuracy. It also utilizes video image data for visual verification, enhancing information credibility and providing multi-dimensional data support for subsequent intelligent analysis. By employing deep analysis algorithms such as index evaluation and key personnel clustering, electric bicycles and riders are tagged, effectively improving hazard identification capabilities. Based on the tag information obtained from these tags, electric bicycles are accurately classified, laying the foundation for implementing differentiated and refined management strategies. Subsequently, based on the classification results, precise control measures such as release or warning are automatically executed, improving the efficiency and accuracy of electric bicycle traffic management. This facilitates optimized allocation of management resources and proactive prevention of safety hazards. Compared to traditional electric bicycle management methods, this solution integrates comprehensive processing functions such as data collection and analysis, classification management, and precise control through an intelligent electric bicycle control platform, constructing an intelligent and refined electric bicycle governance system. This is conducive to improving the efficiency of electric bicycle traffic management, accurately identifying risks and hazards, optimizing the allocation of law enforcement resources, and promoting the transformation and upgrading of electric bicycle management from a passive response to a proactive prevention model.

[0043] Example 2 Please see Figure 2 , Figure 2 This is a flowchart illustrating an intelligent management and control method for smart electric bicycles disclosed in an embodiment of the present invention. Wherein, Figure 2 The described intelligent management and control method for smart electric bicycles can be applied to an intelligent control system for electric bicycles. This system includes RFID reading and writing devices (e.g., RFID readers), video acquisition devices (e.g., various cameras, DVRs, DVSs, and streaming media servers), and an intelligent control platform for electric bicycles. The system also includes antennas for communication between the RFID reading and writing devices and the intelligent control platform, as well as between the video acquisition devices and the intelligent control platform. Furthermore, the intelligent control system is used to manage vehicles within a specific driving scenario, such as collecting data on road violations and vehicle passage. This embodiment of the invention is not limited to these specific methods. Figure 2 As shown, the intelligent management and control method for this smart electric bicycle may include the following operations: 201. The electric vehicle intelligent control platform uses RFID reading and writing devices deployed in at least one key node area of ​​the vehicle driving scenario to determine the scenario type of at least one electronic tag in the key node area.

[0044] In this embodiment of the invention, the electronic tag is carried by the digital license plate installed on the electric vehicle to which it belongs.

[0045] In this embodiment of the invention, optionally, the scene type includes near-field type or far-field type. Optionally, the scene type of each electronic tag can be obtained by analyzing the distance between it and the RFID reading and writing devices deployed in the key node area. For example, if the distance is far, it is determined to be far-field type, and if the distance is close, it is determined to be near-field type. Alternatively, the scene type of each electronic tag can also be obtained by analyzing the signal strength between it and the RFID reading and writing devices deployed in the key node area. For example, if the signal strength is strong, it is determined to be near-field type, and if the signal strength is weak, it is determined to be far-field type. This embodiment of the invention does not impose any limitations.

[0046] 202. For each electronic tag, the electric vehicle intelligent control platform determines the data exchange method between the electronic tag and the RFID reading and writing equipment deployed in the corresponding key node area based on the scenario type of the electronic tag in the corresponding key node area.

[0047] In this embodiment of the invention, the data exchange method includes load modulation or backscatter modulation. Load modulation is a communication technology that modulates the electromagnetic wave characteristics emitted by the reader / writer by changing the load impedance of the electronic tag antenna. Backscatter modulation is an extension of load modulation in ultra-high-definition (UHF) RFID systems, utilizing radar principles to achieve long-distance communication. Load modulation and backscatter modulation are technically similar (both achieve modulation by changing the load impedance), but backscatter modulation specifically refers to an extended form applied to the far-field UHF band, overcoming distance limitations through electromagnetic wave reflection.

[0048] 203. The electric vehicle intelligent control platform is based on data exchange and collects RFID signal data of each electronic tag in each key node area through RFID reading and writing devices in each key node area.

[0049] 204. The electric vehicle intelligent control platform determines the RFID signal data of all electronic tags in all key node areas of the vehicle driving scenario as the electric vehicle traffic information of the vehicle driving scenario.

[0050] 205. The electric vehicle intelligent control platform monitors video image data of the vehicle driving scene based on video acquisition equipment in each key node area.

[0051] In this embodiment of the invention, optionally, there is no order between step 205 and steps 201-204. That is, step 205 can occur before steps 201-204, after steps 201-204, or simultaneously with steps 201-204. This embodiment of the invention does not impose any limitations.

[0052] 206. For each key node area, the electric vehicle intelligent control platform performs a preset deep analysis operation on the electric vehicle traffic information and video image data to obtain the tag information of each electric vehicle in that key node area.

[0053] 206. The electric vehicle intelligent control platform classifies all electric vehicles in the key node area based on the tag information of all electric vehicles in the key node area, and obtains the classification result of the key node area.

[0054] 207. Based on the classification results of the key node area, the electric vehicle intelligent control platform performs corresponding control operations on each electric vehicle in the key node area. The control operations include release operations or warning operations.

[0055] In this embodiment of the invention, for other descriptions of steps 205-207, please refer to the detailed description of steps 102-105 in Embodiment 1. These descriptions will not be repeated in this embodiment of the invention.

[0056] It is evident that implementation Figure 2The described intelligent management method for smart electric bicycles can automatically collect electric bicycle traffic information through RFID technology, achieving accurate vehicle identification and real-time tracking, significantly improving data collection efficiency and accuracy. It also utilizes video image data for visual verification, enhancing information credibility and providing multi-dimensional data support for subsequent intelligent analysis. By employing deep analysis algorithms such as index evaluation and key personnel clustering, electric bicycles and riders are tagged, effectively improving hazard identification capabilities. Based on the tag information obtained from these tags, electric bicycles are accurately classified, laying the foundation for implementing differentiated and refined management strategies. Subsequently, based on the classification results, precise control measures such as release or warning are automatically executed, improving the efficiency and accuracy of electric bicycle traffic management. This facilitates optimized allocation of management resources and proactive prevention of safety hazards. Compared to traditional electric bicycle management methods, this solution integrates comprehensive processing functions such as data collection and analysis, classification management, and precise control through an intelligent electric bicycle control platform, constructing an intelligent and refined electric bicycle governance system. This is conducive to improving the efficiency of electric bicycle traffic management, accurately identifying risks and hazards, optimizing the allocation of law enforcement resources, and promoting the transformation and upgrading of electric bicycle management from a passive response to a proactive prevention model. Furthermore, by identifying the scene type of electronic tags within key node areas and automatically matching the corresponding data exchange method based on the scene type, it helps ensure the stability and reliability of data transmission in both near and far field environments, minimizing signal attenuation and interference. The use of appropriate modulation methods for accurate RFID signal data collection significantly improves the success rate of electronic tag reading, data integrity, and real-time performance, effectively reducing missed and misreading phenomena. Subsequently, by aggregating RFID data from multiple nodes across all scenarios to form unified traffic information, a high-precision, comprehensive dynamic profile of electric vehicles is constructed, providing a high-quality data foundation for subsequent intelligent analysis. This solution provides an intelligent method for determining electric vehicle traffic information. Through scene-adaptive recognition and intelligent modulation matching mechanisms, it achieves efficient, stable, and accurate collection of RFID signals in both near and far field environments, significantly improving data reading success rate and environmental adaptability. This provides a comprehensive, real-time, and reliable traffic information foundation for the electric vehicle intelligent control platform, effectively supporting subsequent precise control decisions.

[0057] In an optional embodiment, the electric vehicle intelligent control platform in step 201 above determines the scenario type of at least one electronic tag in the key node area based on the RFID reading and writing devices deployed in at least one key node area of ​​the vehicle driving scenario, including: The electric vehicle intelligent control platform obtains the deployment location of RFID reading and writing devices and the device performance parameters of RFID reading and writing devices in at least one key node area of ​​the vehicle driving scenario. For each key node area, the electric vehicle intelligent control platform uses the RFID reader / writer device in that key node area to detect the tag position parameters of at least one electronic tag in that key node area. For each electronic tag, the electric vehicle intelligent control platform determines the target communication distance between the electronic tag and the RFID reader / writer based on the device performance parameters, the deployment location of the RFID reader / writer, and the tag location parameters of the electronic tag. The electric vehicle intelligent control platform detects the target communication distance of the electronic tag; and when the target communication distance of the electronic tag is detected to be within a first preset distance range, the scene type of the electronic tag is determined to be near-field type; and when the target communication distance of the electronic tag is detected to be within a second preset distance range, the scene type of the electronic tag is determined to be far-field type.

[0058] In this embodiment of the invention, optionally, the device performance parameters of the RFID reader / writer may include at least one of the following: basic hardware parameters, communication performance parameters, environmental adaptability parameters, functional expansion parameters, and specific performance indicators. The basic hardware parameters may include at least one of the following: operating frequency, transmit power, antenna gain and polarization, and sensitivity. The communication performance parameters may include at least one of the following: modulation method, communication protocol, and read rate. The environmental adaptability parameters may include the operating temperature range and / or anti-interference capability. The functional expansion parameters may include at least one of the following: interface type, data encryption, remote management, and power supply method. The specific performance indicators may include at least one of the following: identification accuracy, positioning accuracy, response latency, and concurrent processing capability. This embodiment of the invention does not impose any limitations on these parameters.

[0059] In this embodiment of the invention, the tag position parameter includes at least the current position of the tag and the changed position of the tag, which indicates the position change of the corresponding electronic tag within a preset time period.

[0060] In this embodiment of the invention, the maximum value of the first preset distance interval is less than the minimum value of the second preset distance interval. For example, the first preset distance interval can be represented as [a, b), and the second preset distance interval can be represented as [b, c).

[0061] As can be seen, this optional embodiment can establish a basic database of device spatial distribution and capabilities by acquiring the deployment location and performance parameters of the reading and writing devices, providing reliable static input parameters for subsequent accurate distance calculation. It can also detect unknown parameters of electronic tags in real time, dynamically capture the spatial coordinates of target vehicles, and provide accurate dynamic location input for communication distance calculation. Subsequently, by integrating multi-dimensional data on device performance, spatial deployment, and tag location, the target communication distance is accurately calculated, transforming the abstract scenario into a quantifiable distance indicator. Then, by automatically determining the near and far field types through preset distance interval thresholds, adaptive recognition and rapid classification of scenario types are achieved. This helps ensure that the subsequent modulation method selection is accurately matched with the actual communication environment. This solution provides a method for determining the scenario type of electronic tags. Through multi-source data fusion and dynamic distance quantification, an automated and high-precision scenario recognition mechanism is constructed, significantly improving the accuracy and real-time performance of near and far field classification. This lays a solid foundation for subsequent intelligent matching of the optimal modulation strategy and effectively enhances the system's adaptability to different communication environments and the reliability of data transmission.

[0062] In this optional embodiment, as an optional implementation method, for each electronic tag, the electric vehicle intelligent control platform determines the target communication distance between the electronic tag and the RFID reader / writer based on the device performance parameters of the RFID reader / writer, the deployment location of the RFID reader / writer, and the tag position parameters of the electronic tag, including: For each electronic tag, the electric vehicle intelligent control platform determines the reference communication distance between the electronic tag and the RFID reader based on the deployment location of the RFID reader, the current location of the electronic tag, and the location where the electronic tag changes. The electric vehicle intelligent control platform determines the signal diffusion distribution of the RFID reader / writer within the key node area where the electronic tag belongs based on the device performance parameters of the RFID reader / writer; and determines the signal detection strength of the RFID reader / writer for the electronic tag based on the signal diffusion distribution and the current position of the electronic tag. The electric vehicle intelligent control platform determines the distance adjustment coefficient corresponding to the electronic tag based on the signal detection strength of the electronic tag; and calculates the target communication distance of the electronic tag based on the distance adjustment coefficient and the reference communication distance of the electronic tag.

[0063] In this embodiment of the invention, the signal detection strength of the RFID reader / writer within each key node area can diffuse outwards from itself to all locations within the key node area. This achieves a negative correlation between the signal detection strength of the RFID reader / writer for the electronic tag and the difference between the device and tag positions, where the difference between the device and tag positions is the difference between the device position of the RFID device and the tag position of the electronic tag. For example, the smaller the difference between the device position of the RFID device and the tag position of the electronic tag, the stronger the signal detection strength of the RFID reader / writer for the electronic tag; conversely, the larger the difference between the device position of the RFID device and the tag position of the electronic tag, the weaker the signal detection strength of the RFID reader / writer for the electronic tag.

[0064] Specifically, for each RFID reader / writer, the electric vehicle intelligent control platform calculates the average signal detection strength of the RFID reader / writer based on the signal detection strength of all electronic tags. For each electronic tag, the electric vehicle intelligent control platform calculates the signal deviation between the signal detection strength of the electronic tag and the average signal detection strength of the RFID reader / writer used to detect the electronic tag, and then determines the signal deviation as the distance adjustment coefficient corresponding to the electronic tag.

[0065] As can be seen, this optional implementation can calculate a precise baseline communication distance by integrating the deployment location of the reading and writing device with the dynamic position change data of the electronic tag, providing a reliable initial value for subsequent fine-tuning. It also introduces device performance parameters and a signal diffusion distribution model, combined with real-time signal detection intensity, to dynamically correlate the theoretical distance with the actual electromagnetic wave propagation characteristics, thereby enhancing environmental adaptability. Based on the signal detection intensity, a distance adjustment coefficient is generated to dynamically correct the baseline communication distance, effectively eliminating errors caused by environmental factors such as obstruction and multipath interference, and significantly improving the accuracy of the final distance calculation. This solution provides a method for determining the target communication distance. By constructing a three-stage processing mode of baseline calculation - signal correction - dynamic optimization, it achieves fine-tuned and adaptive calculation of the communication distance, which is conducive to significantly improving the accuracy of near-field scene classification and anti-interference capability, thereby ensuring that the modulation strategy is highly matched with the actual communication environment.

[0066] In this optional implementation, optionally, for each electronic tag, the electric vehicle intelligent control platform determines the reference communication distance between the electronic tag and the RFID reader / writer based on the deployment location of the RFID reader / writer, the current location of the electronic tag, and the location change of the electronic tag, including: For each electronic tag, the electric vehicle intelligent control platform calculates the initial communication distance between the electronic tag and the RFID reader based on the deployment location of the RFID reader and the current location of the electronic tag. The electric vehicle intelligent control platform analyzes the movement parameters of the electronic tag based on the tag's change position. The movement parameters include the movement direction and at least one sub-type of movement parameters in the movement direction. All sub-type movement parameters include at least one of the movement distance, movement speed, and movement duration. The electric vehicle intelligent control platform predicts the distance change trend between the electronic tag and the RFID reader / writer within the key node area based on the electronic tag's movement parameters and initial communication distance. The electric vehicle intelligent control platform predicts multiple expected communication distances of the electronic tag under the influence of the distance change trend, based on the distance change trend of the electronic tag and the initial communication distance of the electronic tag; and selects one of the communication distances from the set of all expected communication distances of the electronic tag and the initial communication distance of the electronic tag as the reference communication distance between the electronic tag and the RFID reader / writer.

[0067] In this embodiment of the invention, specifically, one of the middle values ​​is selected from the set of communication distances for each electronic tag as the reference communication distance between the electronic tag and the RFID reader / writer.

[0068] As can be seen, this optional implementation can also establish a spatial position benchmark by calculating the initial communication distance in real time, providing an accurate starting reference point for dynamic analysis. By analyzing the movement parameters of the electronic tag, it can accurately characterize the dynamic behavior characteristics of the electric vehicle, providing rich data support for trajectory prediction. Thus, based on the dynamic movement parameters, it can predict the distance change trend, enabling forward-looking analysis of the vehicle's trajectory. This is beneficial to enhancing the system's ability to predict vehicle behavior. Subsequently, through comprehensive evaluation and optimization of multiple expected distances and initial distances, the most representative benchmark communication distance can be determined, which is beneficial to improving the accuracy and reliability of subsequent near-field and far-field classification.

[0069] In another optional embodiment, in step 202 above, for each electronic tag, the electric vehicle intelligent control platform determines the data exchange method between the electronic tag and the RFID reading and writing devices deployed in the corresponding key node area based on the scenario type of the electronic tag in the corresponding key node area, including: For each electronic tag, when the scenario type of the electronic tag is near field, the electric vehicle intelligent control platform determines that the data exchange method between the electronic tag and the RFID reading and writing devices deployed in the corresponding key node area is load modulation. When the scenario type of the electronic tag is far-field, the electric vehicle intelligent control platform determines that the data exchange method between the electronic tag and the RFID reading and writing devices deployed in the corresponding key node area is backscatter modulation.

[0070] As can be seen, this optional embodiment can determine the corresponding data exchange method for each electronic tag based on the scene type, and can achieve accurate matching between scene type and data exchange method. This is beneficial to improve the accuracy and reliability of the RFID signal data subsequently collected based on the accurately matched data exchange method.

[0071] In another optional embodiment, the electric vehicle intelligent control platform in step 205 above monitors video image data of the vehicle driving scene based on video acquisition devices in each key node area, including: Based on video acquisition equipment in each key node area, monitor video stream data in vehicle driving scenarios; Based on video AI technology, the video stream data is analyzed frame by frame to obtain multiple initial video image data. Based on a pre-trained image recognition model, all initial video image data are identified to obtain at least one active object in the vehicle driving scene; Based on the alarm rule information corresponding to the preset video acquisition equipment, each active object is identified to obtain the driving behavior of that active object; When the driving behavior of the active object constitutes a safety threat that violates the alarm rules, the system determines the warning information for the active object based on the driving behavior of the active object and sends the warning information to the active object; and filters out the initial video image data containing the active object from all initial video image data. By integrating the initial video image data of all active objects whose driving behavior poses a safety threat, video image data of the vehicle driving scene is obtained.

[0072] In this embodiment of the invention, video AI technology refers to intelligent video analysis technology. The technical principle of intelligent video analysis involves connecting various cameras, DVRs, DVSs, and streaming media servers, and using intelligent image recognition processing technology to proactively issue warnings for various security events. Through real-time analysis, the warning information is transmitted to the integrated monitoring platform and client. Specifically, the intelligent video analysis system uses cameras to "detect enemy activity" and "see" monitored targets in real time. Simultaneously, its intelligent recognition algorithm determines whether the behavior of these monitored targets poses a security threat. For threats that have already occurred or are about to occur, it promptly issues warnings to the integrated monitoring platform or back-end administrators via audio, video, or other means.

[0073] It's important to note that the fundamental difference between intelligent video analytics and motion detection is that the former can accurately identify the actual moving targets in a video, while the latter can only determine changes in the scene and cannot distinguish between the target and background interference. Therefore, intelligent video analytics offers a significantly improved anti-interference capability compared to motion detection. Using intelligent analytics technology, users can preset different warning rules for different camera scenarios based on actual applications. Once a target in the scene violates the predefined rules, the system will automatically issue a warning. Warning information takes several forms, including locally driving warning devices and sending warning data to the backend monitoring center, where the monitoring workstation controls the warning in the form of pop-up videos, automatic pop-up warning messages, and driving warning devices.

[0074] In this embodiment of the invention, specifically, the image recognition model can take multiple acquired historical video image data as input, and the user's recognition result for each historical video image data (including the result of whether there is an active object) as output, and train a pre-built neural network model to obtain an image recognition model that has been trained to convergence. Optionally, the active object may include different targets such as electric vehicles and pedestrians, and this embodiment of the invention does not limit it.

[0075] As can be seen, this optional embodiment can monitor video stream data in real time through multi-node video acquisition devices and analyze it frame by frame using video AI technology to ensure accurate capture of key moments, improve the completeness of behavior recognition and data granularity, and avoid information omissions. It can then use a pre-trained image recognition model to accurately identify various active objects in the scene and automatically identify driving behavior based on preset alarm rules, transforming visual data into structured behavioral information. This enables automated and standardized judgment of violations. When a safety threat is detected, it directly generates warning information and issues timely alerts, proactively intervening in risky behaviors. At the same time, it accurately filters related image data, quickly locks the chain of evidence for violations, and integrates fragmented images of safety threat behaviors into a structured dataset, forming a complete evidence library for violations. This facilitates subsequent tracing, statistics, and in-depth analysis. By constructing a full-chain intelligent video monitoring system encompassing acquisition, analysis, recognition, warning, and evidence collection, it achieves automatic transformation from raw video streams to structured data of safety threat behaviors. This significantly improves the timeliness of violation detection, the accuracy of evidence extraction, and the proactiveness of control response. It also provides high-quality visual decision-making basis for electric vehicle intelligent control platforms.

[0076] Example 3 Please see Figure 3 , Figure 3 This is a schematic diagram of the structure of an intelligent control system for an electric bicycle disclosed in an embodiment of the present invention. Figure 3The described intelligent control system for electric bicycles includes RFID reading and writing devices (such as RFID readers), video acquisition devices (such as various cameras, DVRs, DVSs, and streaming media servers), and an intelligent control platform for electric bicycles. The system also includes antennas for communication between the RFID reading and writing devices and the intelligent control platform, as well as between the video acquisition devices and the intelligent control platform. Furthermore, the intelligent control system is used to manage vehicles within a driving scenario, such as collecting data on road violations and passing vehicles. This embodiment of the invention is not limited to these specific examples. Figure 3 As shown, the electric vehicle intelligent control platform may include: The determination module 301 is used to determine the electric vehicle traffic information of the vehicle driving scenario based on the RFID signal data collected by RFID reading and writing devices deployed in at least one key node area of ​​the vehicle driving scenario.

[0077] The monitoring module 302 is used to monitor video image data of vehicle driving scenes based on video acquisition devices in each key node area.

[0078] The analysis module 303 is used to perform preset deep analysis operations on electric vehicle traffic information and video image data for each key node area to obtain the tag information of each electric vehicle in the key node area. The deep analysis operations include index evaluation operations and / or key personnel clustering operations. The tag information includes first-type tag information or second-type tag information.

[0079] The classification module 304 is used to classify all electric vehicles in the key node area according to the tag information of all electric vehicles in the key node area, and obtain the classification result of the key node area. The classification result includes a first type of electric vehicle set and a second type of electric vehicle set. The first type of electric vehicle set is empty or the tag information of all electric vehicles in the first type of electric vehicle set is the first type of tag information. The second type of electric vehicle set is empty or the tag information of all electric vehicles in the second type of electric vehicle set is the second type of tag information. The first type of electric vehicle set and the second type of electric vehicle set are not both empty.

[0080] The control module 305 is used to perform corresponding control operations on each electric vehicle in the key node area based on the classification results of the key node area. The control operations include release operations or warning operations.

[0081] It is evident that implementation Figure 3The described intelligent control system for electric bicycles can automatically collect electric bicycle traffic information through RFID technology, achieving accurate vehicle identification and real-time tracking, significantly improving data collection efficiency and accuracy. It also utilizes video image data for visual verification, enhancing information credibility and providing multi-dimensional data support for subsequent intelligent analysis. By employing deep analysis algorithms such as index evaluation and key personnel clustering, it marks electric bicycles and riders, effectively improving hazard identification capabilities. Based on the tag information obtained from these markings, electric bicycles are accurately classified, laying the foundation for implementing differentiated and refined management strategies. Subsequently, based on the classification results, it automatically executes precise control measures such as release or warning, improving the efficiency and accuracy of electric bicycle traffic management. This facilitates optimized allocation of management resources and proactive prevention of safety hazards. Compared to traditional electric bicycle management methods, this solution integrates data collection and analysis, classification management, and precise control functions through an intelligent electric bicycle control platform, constructing an intelligent and refined electric bicycle governance system. This is beneficial for improving the efficiency of electric bicycle traffic management, accurately identifying risks and hazards, optimizing the allocation of law enforcement resources, and promoting the transformation and upgrading of electric bicycle management from a passive response to a proactive prevention model.

[0082] In an optional embodiment, the specific method by which the determining module 301 determines the electric vehicle traffic information of the vehicle driving scenario based on the RFID signal data collected by RFID reading and writing devices deployed in at least one key node area of ​​the vehicle driving scenario includes: The electric vehicle intelligent control platform uses RFID reading and writing devices deployed in at least one key node area of ​​the vehicle driving scenario to determine the scenario type of at least one electronic tag in the key node area. The electronic tag is carried by the digital license plate installed on the electric vehicle to which it belongs. For each electronic tag, the electric vehicle intelligent control platform determines the data exchange method between the electronic tag and the RFID reading and writing devices deployed in the corresponding key node area based on the scenario type of the electronic tag in the corresponding key node area. The electric vehicle intelligent control platform is based on data exchange and collects RFID signal data of each electronic tag in each key node area through RFID reading and writing devices in that key node area; The electric vehicle intelligent control platform determines the RFID signal data of all electronic tags in all key node areas of the vehicle driving scenario as the electric vehicle traffic information for the driving scenario.

[0083] As can be seen, this optional embodiment can identify the scene type of electronic tags in key node areas and automatically match the corresponding data exchange method based on the scene type. This helps ensure the stability and reliability of data transmission in both near and far field environments, minimizes signal attenuation and interference, and accurately collects RFID signal data using an appropriate modulation method. This significantly improves the success rate of electronic tag reading, data integrity, and real-time performance, effectively reducing missed readings and misreads. Subsequently, by aggregating RFID data from multiple nodes across all scenarios to form unified access information, a high-precision, full-coverage dynamic profile of electric vehicles is constructed, providing a high-quality data foundation for subsequent intelligent analysis. This solution provides an intelligent method for determining electric vehicle access information. Through scene adaptive recognition and intelligent modulation matching mechanisms, it achieves efficient, stable, and accurate collection of RFID signals in both near and far field environments, significantly improving data reading success rate and environmental adaptability. This provides a comprehensive, real-time, and reliable access information foundation for the electric vehicle intelligent control platform, effectively supporting subsequent precise control decisions.

[0084] In this optional embodiment, as an optional implementation, the specific method by which the determining module 301 determines the scenario type of at least one electronic tag in the key node area based on the RFID reading and writing devices deployed in at least one key node area of ​​the vehicle driving scenario includes: The electric vehicle intelligent control platform obtains the deployment location of RFID reading and writing devices and the device performance parameters of RFID reading and writing devices in at least one key node area of ​​the vehicle driving scenario. For each key node area, the electric vehicle intelligent control platform uses the RFID reader / writer device in that key node area to detect the tag position parameters of at least one electronic tag in that key node area. For each electronic tag, the electric vehicle intelligent control platform determines the target communication distance between the electronic tag and the RFID reader / writer based on the device performance parameters, the deployment location of the RFID reader / writer, and the tag location parameters of the electronic tag. The electric vehicle intelligent control platform detects the target communication distance of the electronic tag; and when the target communication distance of the electronic tag is detected to be within a first preset distance range, the scene type of the electronic tag is determined to be near-field type; and when the target communication distance of the electronic tag is detected to be within a second preset distance range, the scene type of the electronic tag is determined to be far-field type.

[0085] As can be seen, this optional implementation can establish a basic database of device spatial distribution and capabilities by acquiring the deployment location and performance parameters of the reading and writing devices, providing reliable static input parameters for subsequent accurate distance calculation. It can also detect unknown parameters of electronic tags in real time, dynamically capture the spatial coordinates of target vehicles, and provide accurate dynamic location input for communication distance calculation. Subsequently, by integrating multi-dimensional data on device performance, spatial deployment, and tag location, the target communication distance is accurately calculated, transforming the abstract scenario into a quantifiable distance indicator. Then, by automatically determining the near and far field types through preset distance interval thresholds, adaptive recognition and rapid classification of scenario types are achieved. This helps ensure that the subsequent modulation method selection is accurately matched with the actual communication environment. This solution provides a method for determining the scenario type of electronic tags. Through multi-source data fusion and dynamic distance quantification, an automated and high-precision scenario recognition mechanism is constructed, significantly improving the accuracy and real-time performance of near and far field classification. This lays a solid foundation for subsequent intelligent matching of the optimal modulation strategy and effectively enhances the system's adaptability to different communication environments and the reliability of data transmission.

[0086] In this optional implementation, the tag position parameters may include at least the current tag position and the tag change position, whereby the tag change position indicates the position change of the corresponding electronic tag within a preset time period. Furthermore, the specific method by which the determining module 301 determines the target communication distance between the electronic tag and the RFID reader / writer based on the device performance parameters, the deployment location of the RFID reader / writer, and the tag position parameters of the electronic tag includes: For each electronic tag, the electric vehicle intelligent control platform determines the reference communication distance between the electronic tag and the RFID reader based on the deployment location of the RFID reader, the current location of the electronic tag, and the location where the electronic tag changes. The electric vehicle intelligent control platform determines the signal diffusion distribution of the RFID reader / writer within the key node area where the electronic tag belongs based on the device performance parameters of the RFID reader / writer; and determines the signal detection strength of the RFID reader / writer for the electronic tag based on the signal diffusion distribution and the current position of the electronic tag. The electric vehicle intelligent control platform determines the distance adjustment coefficient corresponding to the electronic tag based on the signal detection strength of the electronic tag; and calculates the target communication distance of the electronic tag based on the distance adjustment coefficient and the reference communication distance of the electronic tag.

[0087] As can be seen, this optional implementation can also calculate a precise baseline communication distance by integrating the deployment location of the reading and writing device with the dynamic position change data of the electronic tag, providing a reliable initial value for subsequent fine-tuning. It also introduces device performance parameters and signal diffusion distribution models, combined with real-time signal detection intensity, to dynamically correlate the theoretical distance with the actual electromagnetic wave propagation characteristics, thereby enhancing environmental adaptability. Based on the signal detection intensity, a distance adjustment coefficient is generated to dynamically correct the baseline communication distance, effectively eliminating errors caused by environmental factors such as obstruction and multipath interference, and significantly improving the accuracy of the final distance calculation. This solution provides a method for determining the target communication distance. By constructing a three-stage processing mode of baseline calculation - signal correction - dynamic optimization, it achieves fine-tuned and adaptive calculation of the communication distance, which is conducive to significantly improving the accuracy of near-field scene classification and anti-interference capability, thereby ensuring that the modulation strategy is highly matched with the actual communication environment.

[0088] In this optional implementation, further optionally, for each electronic tag, the electric vehicle intelligent control platform determines the reference communication distance between the electronic tag and the RFID reader / writer based on the deployment location of the RFID reader / writer, the current location of the electronic tag, and the location where the electronic tag changes position. The specific methods include: For each electronic tag, the electric vehicle intelligent control platform calculates the initial communication distance between the electronic tag and the RFID reader based on the deployment location of the RFID reader and the current location of the electronic tag. The electric vehicle intelligent control platform analyzes the movement parameters of the electronic tag based on the tag's change position. The movement parameters include the movement direction and at least one sub-type of movement parameters in the movement direction. All sub-type movement parameters include at least one of the movement distance, movement speed, and movement duration. The electric vehicle intelligent control platform predicts the distance change trend between the electronic tag and the RFID reader / writer within the key node area based on the electronic tag's movement parameters and initial communication distance. The electric vehicle intelligent control platform predicts multiple expected communication distances of the electronic tag under the influence of the distance change trend, based on the distance change trend of the electronic tag and the initial communication distance of the electronic tag; and selects one of the communication distances from the set of all expected communication distances of the electronic tag and the initial communication distance of the electronic tag as the reference communication distance between the electronic tag and the RFID reader / writer.

[0089] As can be seen, this optional implementation can also establish a spatial position benchmark by calculating the initial communication distance in real time, providing an accurate starting reference point for dynamic analysis. By analyzing the movement parameters of the electronic tag, it can accurately characterize the dynamic behavior characteristics of the electric vehicle, providing rich data support for trajectory prediction. Thus, based on the dynamic movement parameters, it can predict the distance change trend, enabling forward-looking analysis of the vehicle's trajectory. This is beneficial to enhancing the system's ability to predict vehicle behavior. Subsequently, through comprehensive evaluation and optimization of multiple expected distances and initial distances, the most representative benchmark communication distance can be determined, which is beneficial to improving the accuracy and reliability of subsequent near-field and far-field classification.

[0090] In this optional embodiment, as another optional implementation, the scene type includes near-field type or far-field type; the data exchange method includes load modulation method or backscatter modulation method. Furthermore, for each electronic tag, the electric vehicle intelligent control platform determines, based on the scene type of the electronic tag in the corresponding key node area, the specific method of data exchange between the electronic tag and the RFID reader / writer deployed in the corresponding key node area, including: For each electronic tag, when the scenario type of the electronic tag is near field, the electric vehicle intelligent control platform determines that the data exchange method between the electronic tag and the RFID reading and writing devices deployed in the corresponding key node area is load modulation. When the scenario type of the electronic tag is far-field, the electric vehicle intelligent control platform determines that the data exchange method between the electronic tag and the RFID reading and writing devices deployed in the corresponding key node area is backscatter modulation.

[0091] As can be seen, this optional implementation method can determine the corresponding data exchange method for each electronic tag based on the scene type, and can achieve accurate matching between scene type and data exchange method. This is conducive to improving the accuracy and reliability of the RFID signal data subsequently collected based on the accurately matched data exchange method.

[0092] In another optional embodiment, the monitoring module 302 monitors video image data of the vehicle driving scene based on the video acquisition device of each key node area in the following specific ways: Based on video acquisition equipment in each key node area, monitor video stream data in vehicle driving scenarios; Based on video AI technology, the video stream data is analyzed frame by frame to obtain multiple initial video image data. Based on a pre-trained image recognition model, all initial video image data are identified to obtain at least one active object in the vehicle driving scene; Based on the alarm rule information corresponding to the preset video acquisition equipment, each active object is identified to obtain the driving behavior of that active object; When the driving behavior of the active object constitutes a safety threat that violates the alarm rules, the system determines the warning information for the active object based on the driving behavior of the active object and sends the warning information to the active object; and filters out the initial video image data containing the active object from all initial video image data. By integrating the initial video image data of all active objects whose driving behavior poses a safety threat, video image data of the vehicle driving scene is obtained.

[0093] As can be seen, this optional embodiment can monitor video stream data in real time through multi-node video acquisition devices and analyze it frame by frame using video AI technology to ensure accurate capture of key moments, improve the completeness of behavior recognition and data granularity, and avoid information omissions. It can then use a pre-trained image recognition model to accurately identify various active objects in the scene and automatically identify driving behavior based on preset alarm rules, transforming visual data into structured behavioral information. This enables automated and standardized judgment of violations. When a safety threat is detected, it directly generates warning information and issues timely alerts, proactively intervening in risky behaviors. At the same time, it accurately filters related image data, quickly locks the chain of evidence for violations, and integrates fragmented images of safety threat behaviors into a structured dataset, forming a complete evidence library for violations. This facilitates subsequent tracing, statistics, and in-depth analysis. By constructing a full-chain intelligent video monitoring system encompassing acquisition, analysis, recognition, warning, and evidence collection, it achieves automatic transformation from raw video streams to structured data of safety threat behaviors. This significantly improves the timeliness of violation detection, the accuracy of evidence extraction, and the proactiveness of control response. It also provides high-quality visual decision-making basis for electric vehicle intelligent control platforms.

[0094] Example 4 Please see Figure 4 , Figure 4 This is a schematic diagram of another intelligent control system for electric bicycles disclosed in an embodiment of the present invention. (See diagram below.) Figure 4 As shown, the intelligent control system for the electric bicycle may include: Memory 401 storing executable program code; Processor 402 coupled to memory 401; The processor 402 calls the executable program code stored in the memory 401 to execute the steps in the intelligent management and control method for smart electric bicycles described in Embodiment 1 or Embodiment 2 of the present invention.

[0095] Example 5 This invention discloses a computer storage medium storing computer instructions. When these computer instructions are invoked, they are used to execute the steps in the intelligent management and control method for smart electric bicycles described in Embodiment 1 or Embodiment 2 of this invention.

[0096] Example 6 This invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to perform the steps in the intelligent management method for smart electric bicycles described in Embodiment 1 or Embodiment 2.

[0097] The device embodiments described above are merely illustrative. The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0098] Through the detailed description of the above embodiments, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, including read-only memory (ROM), random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), one-time programmable read-only memory (OTPROM), electrically-Erasable Programmable Read-Only Memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0099] Finally, it should be noted that the intelligent management method and intelligent control system for smart electric bicycles disclosed in the embodiments of the present invention are merely preferred embodiments of the present invention and are only used to illustrate the technical solutions of the present invention, not to limit it. Although the present invention 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 the present invention.

Claims

1. A method for intelligent control of smart electric bicycles, characterized in that, The method is applied to an intelligent control system for electric bicycles, which includes an RFID reader / writer, a video acquisition device, and an intelligent control platform. The intelligent control system is used to manage and control the vehicle within a driving scenario. The method includes: The electric vehicle intelligent control platform determines the electric vehicle traffic information of the vehicle driving scenario based on the RFID signal data collected by RFID reading and writing devices deployed in at least one key node area of ​​the vehicle driving scenario. The electric vehicle intelligent control platform monitors video image data of the vehicle driving scene based on video acquisition devices in each of the key node areas. For each key node area, the electric vehicle intelligent control platform performs a preset deep analysis operation on the electric vehicle traffic information and the video image data to obtain the tag information of each electric vehicle in the key node area. The deep analysis operation includes index evaluation operation and / or key personnel clustering operation. The tag information includes first type tag information or second type tag information. The electric vehicle intelligent control platform classifies all electric vehicles in the key node area based on the tag information of all electric vehicles in the key node area, and obtains the classification result of the key node area. The classification result includes a first type of electric vehicle set and a second type of electric vehicle set. The first type of electric vehicle set is empty or the tag information of all electric vehicles in the first type of electric vehicle set is the first type of tag information. The second type of electric vehicle set is empty or the tag information of all electric vehicles in the second type of electric vehicle set is the second type of tag information. The first type of electric vehicle set and the second type of electric vehicle set are not both empty. The electric vehicle intelligent control platform performs corresponding control operations on each electric vehicle in the key node area based on the classification results of the key node area. The control operations include release operations or warning operations.

2. The intelligent control method for smart electric bicycles according to claim 1, characterized in that, The electric vehicle intelligent control platform determines the electric vehicle traffic information of the driving scenario based on RFID signal data collected by RFID reading and writing devices deployed in at least one key node area of ​​the vehicle driving scenario, including: The electric vehicle intelligent control platform determines the scenario type of at least one electronic tag in the key node area based on RFID reading and writing devices deployed in at least one key node area of ​​the vehicle driving scenario. The electronic tag is carried by the digital license plate installed on the electric vehicle to which it belongs. For each of the aforementioned electronic tags, the electric vehicle intelligent control platform determines the data exchange method between the electronic tag and the RFID reading and writing devices deployed in the corresponding key node area based on the scenario type of the electronic tag in the corresponding key node area. The electric vehicle intelligent control platform, based on the data exchange method, collects RFID signal data of each electronic tag in each key node area through the RFID reader / writer device in each key node area; The electric vehicle intelligent control platform determines the RFID signal data of all electronic tags in all key node areas of the vehicle driving scenario as the electric vehicle traffic information of the vehicle driving scenario.

3. The intelligent control method for smart electric bicycles according to claim 2, characterized in that, The electric vehicle intelligent control platform determines the scenario type of at least one electronic tag within a key node area based on RFID reading and writing devices deployed in at least one key node area of ​​the vehicle driving scenario, including: The electric vehicle intelligent control platform obtains the deployment location of RFID reading and writing devices in at least one key node area of ​​the vehicle driving scenario, as well as the device performance parameters of the RFID reading and writing devices. For each of the key node areas, the electric vehicle intelligent control platform detects the tag position parameters of at least one electronic tag within the key node area based on the RFID reader / writer device in that key node area. For each of the aforementioned electronic tags, the electric vehicle intelligent control platform determines the target communication distance between the electronic tag and the RFID reader / writer based on the device performance parameters of the RFID reader / writer, the deployment location of the RFID reader / writer, and the tag position parameters of the electronic tag. The electric vehicle intelligent control platform detects the target communication distance of the electronic tag; and when the target communication distance of the electronic tag is detected to be within a first preset distance range, the scene type of the electronic tag is determined to be the near-field type; and when the target communication distance of the electronic tag is detected to be within a second preset distance range, the scene type of the electronic tag is determined to be the far-field type.

4. The intelligent control method for smart electric bicycles according to claim 3, characterized in that, The tag location parameter includes at least the current tag location and the tag change location, wherein the tag change location indicates the location change of the corresponding electronic tag within a preset time period; Furthermore, for each of the aforementioned electronic tags, the electric vehicle intelligent control platform determines the target communication distance between the electronic tag and the RFID reader / writer based on the device performance parameters of the RFID reader / writer, the deployment location of the RFID reader / writer, and the tag position parameters of the electronic tag, including: For each of the aforementioned electronic tags, the electric vehicle intelligent control platform determines the reference communication distance between the electronic tag and the RFID reader / writer based on the deployment location of the RFID reader / writer, the current location of the electronic tag, and the location where the electronic tag changes position. The electric vehicle intelligent control platform determines the signal diffusion distribution of the RFID reader / writer within the key node area to which the electronic tag belongs based on the device performance parameters of the RFID reader / writer; and determines the signal detection strength of the RFID reader / writer for the electronic tag based on the signal diffusion distribution and the current position of the electronic tag. The electric vehicle intelligent control platform determines the distance adjustment coefficient corresponding to the electronic tag based on the signal detection strength corresponding to the electronic tag; and calculates the target communication distance of the electronic tag based on the distance adjustment coefficient corresponding to the electronic tag and the reference communication distance of the electronic tag.

5. The intelligent control method for smart electric bicycles according to claim 4, characterized in that, For each of the aforementioned electronic tags, the electric vehicle intelligent control platform determines the reference communication distance between the electronic tag and the RFID reader / writer based on the deployment location of the RFID reader / writer, the current location of the electronic tag, and the changed location of the electronic tag, including: For each of the aforementioned electronic tags, the electric vehicle intelligent control platform calculates the initial communication distance between the electronic tag and the RFID reader / writer based on the deployment location of the RFID reader / writer and the current location of the electronic tag. The electric vehicle intelligent control platform analyzes the movement parameters of the electronic tag based on the tag's changing position. The movement parameters include the movement direction and at least one sub-type of movement parameters in the movement direction. All the sub-type of movement parameters include at least one of the movement distance, movement speed, and movement duration. The electric vehicle intelligent control platform predicts the distance change trend between the electronic tag and the RFID reader / writer within the key node area based on the electronic tag's movement parameters and its initial communication distance. The electric vehicle intelligent control platform predicts multiple expected communication distances of the electronic tag under the influence of the distance change trend and the initial communication distance of the electronic tag, and selects one of the communication distances from the set of all expected communication distances of the electronic tag and the initial communication distance of the electronic tag as the reference communication distance between the electronic tag and the RFID reader / writer.

6. The intelligent control method for smart electric bicycles according to any one of claims 2-5, characterized in that, The scene type includes near-field type or far-field type; the data exchange method includes load modulation method or backscatter modulation method; Furthermore, for each of the aforementioned electronic tags, the electric vehicle intelligent control platform determines the data exchange method between the electronic tag and the RFID reading / writing devices deployed in the corresponding key node area based on the scenario type of the electronic tag in the corresponding key node area, including: For each of the aforementioned electronic tags, when the scenario type of the electronic tag is the near-field type, the electric vehicle intelligent control platform determines that the data exchange method between the electronic tag and the RFID reading and writing device deployed in the corresponding key node area is the load modulation method; When the scenario type of the electronic tag is the far-field type, the electric vehicle intelligent control platform determines that the data exchange method between the electronic tag and the RFID reading and writing devices deployed in the corresponding key node area is the backscatter modulation method.

7. The intelligent control method for smart electric bicycles according to any one of claims 1-5, characterized in that, The electric vehicle intelligent control platform monitors video image data of the vehicle driving scene based on video acquisition devices in each of the key node areas, including: Based on the video acquisition device in each of the key node areas, monitor the video stream data in the vehicle driving scene; Based on video AI technology, the video stream data is analyzed frame by frame to obtain multiple initial video image data; Based on a pre-trained image recognition model, all the initial video image data are identified to obtain at least one active object in the vehicle driving scene; Based on the preset alarm rule information corresponding to the video acquisition device, each active object is identified to obtain the driving behavior of the active object; When the driving behavior of the active object constitutes a safety threat that violates the alarm rule information, a warning message is determined for the active object based on the driving behavior of the active object, and the warning message is sent to the active object; and the initial video image data containing the active object is filtered from all the initial video image data; By integrating the initial video image data of all active objects involved in the driving behavior that poses the safety threat, video image data of the vehicle driving scene is obtained.

8. An intelligent control system for electric bicycles, characterized in that, The electric bicycle intelligent control system includes an RFID reader / writer, a video acquisition device, and an electric bicycle intelligent control platform. The system is used to manage and control the vehicle within a specific driving scenario. The electric bicycle intelligent control platform includes: The determination module is used to determine the electric vehicle traffic information of the vehicle driving scenario based on the RFID signal data collected by RFID reading and writing devices deployed in at least one key node area of ​​the vehicle driving scenario. The monitoring module is used to monitor video image data of the vehicle driving scene based on the video acquisition device of each of the key node areas; The analysis module is used to perform a preset deep analysis operation on the electric vehicle traffic information and the video image data for each key node area to obtain the tag information of each electric vehicle in the key node area. The deep analysis operation includes index evaluation operation and / or key personnel clustering operation. The tag information includes first type tag information or second type tag information. The classification module is used to classify all electric vehicles in the key node area according to the tag information of all electric vehicles in the key node area, and obtain the classification result of the key node area. The classification result includes a first type of electric vehicle set and a second type of electric vehicle set. The first type of electric vehicle set is empty or the tag information of all electric vehicles in the first type of electric vehicle set is the first type of tag information. The second type of electric vehicle set is empty or the tag information of all electric vehicles in the second type of electric vehicle set is the second type of tag information. The first type of electric vehicle set and the second type of electric vehicle set are not empty at the same time. The control module is used to perform corresponding control operations on each electric vehicle in the key node area based on the classification results of the key node area. The control operations include release operations or warning operations.

9. An intelligent control system for an electric bicycle, characterized in that, The intelligent control system for the electric bicycle includes: Memory containing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the intelligent management and control method for smart electric bicycles as described in any one of claims 1-7.

10. A computer storage medium, characterized in that, The computer storage medium stores computer instructions, which, when invoked, are used to execute the intelligent control method for smart electric bicycles as described in any one of claims 1-7.

Images