Heavy-duty freight vehicle monitoring method, medium and equipment based on remote online data

Abstract

The present invention relates to the field of emission monitoring, and in particular to a heavy-duty freight vehicle monitoring method, medium and equipment based on remote online data. It includes: obtaining the speed emission sequence A of the monitored vehicle within a preset monitoring period; clustering A into the corresponding target group using K-Means clustering, and using the road type identification corresponding to the target group as the predicted operating road identification corresponding to the monitored vehicle within the preset monitoring period; if the actual operating road identification corresponding to the monitored vehicle within the preset monitoring period is the same as the predicted operating road identification, no alarm information is generated. The present invention reflects the characteristics of the driving section corresponding to the monitored vehicle in real time through the performance of two dimensions, namely the average speed of the vehicle and the average emission of the vehicle in multiple monitoring sub-periods. Then use K-Means clustering to obtain the corresponding predicted operating road identification. Finally, the corresponding actual operating road identification is compared with the predicted operating road identification to determine whether the emission data has been tampered with.

Description

Background Art

[0002] Heavy-duty freight vehicles usually refer to vehicles used for long-distance or heavy-weight cargo transportation, mainly including trucks, trailers, etc. These vehicles are characterized by large load capacity, large size, and strong power. Based on the transportation characteristics of heavy-duty freight vehicles, heavy-duty freight vehicles have become the main means of transportation in modern logistics transportation.

[0003] However, since the harmful substances in the exhaust emissions of heavy-duty freight vehicles include but are not limited to nitrogen oxides (NOx), particulate matter (PM), carbon monoxide (CO), hydrocarbons (HC), etc., these substances have a negative impact on air quality and pose a threat to human health. In order to control the exhaust emissions of heavy-duty freight vehicles, the prior art installs such corresponding vehicle status acquisition sensors (such as exhaust emission sensors) on the vehicle, uses OBD (On-Board Diagnostics) to collect data in real time, and then cooperates with technical means such as telematics to remotely monitor the emission status of the vehicle in real time.

[0004] However, in order to circumvent the monitoring of the above-mentioned technical means, third-party software (the so-called "cheater") is usually used to modify the data read by the OBD, so that vehicles that do not meet the emission standards can pass the inspection, thereby making it impossible for existing monitoring methods to accurately detect vehicles with excessive exhaust emissions. Summary of the invention

[0005] In view of the above technical problems, the technical solution adopted by the present invention is:

[0006] According to one aspect of the present invention, a method for monitoring a heavy-duty freight vehicle based on remote online data is provided, the method comprising the following steps:

[0007] Obtain the speed emission sequence A=(A1, A2, ..., Ai, ..., Az) of the monitored vehicle in the preset monitoring period; wherein Ai is the detection characteristic value corresponding to the i-th monitoring sub-period in the preset monitoring period, Ai=(V avg i,P avg i), V avg i is the average speed of the monitored vehicle in the i-th monitoring sub-period; P avg i is the average emission of the monitored vehicles in the i-th monitoring sub-period; z is the total number of monitoring sub-periods in the preset monitoring cycle, i = 1, 2, ..., z;

[0008] Use K-Means clustering to cluster A into the corresponding target group, and use the road type identification corresponding to the target group as the predicted operating road identification corresponding to the monitored vehicle within the preset monitoring period; the target group is one of the multiple existing groups completed by K-Means clustering;

[0009] If the actual operating road sign corresponding to the monitored vehicle within the preset monitoring period is the same as the predicted operating road sign, no alarm information is generated; the actual operating road sign and the predicted operating road sign are both one of the preset operating road signs.

[0010] Furthermore, after using the road type identification corresponding to the target group as the predicted operating road identification corresponding to the monitored vehicle within the preset monitoring period, the method further includes:

[0011] If the actual operating road sign corresponding to the monitored vehicle within the preset monitoring period is different from the predicted operating road sign, and the similarity between A and the road operation feature corresponding to the actual operating road sign is greater than the first similarity threshold, no alarm information is generated.

[0012] Furthermore, after using the road type identification corresponding to the target group as the predicted operating road identification corresponding to the monitored vehicle within the preset monitoring period, the method further includes:

[0013] If the actual operating road sign corresponding to the monitored vehicle within the preset monitoring period is different from the predicted operating road sign, and the similarity between A and the road operation characteristics corresponding to the actual operating road sign is less than the second similarity threshold, an alarm message is generated; the second similarity threshold is less than the first similarity threshold.

[0014] Furthermore, the existing groups are obtained as follows:

[0015] Respectively obtain a plurality of historical speed emission sequences generated when a heavy freight vehicle is running on sections of a plurality of preset road types;

[0016] K-Means clustering is used to cluster multiple historical speed emission sequences to generate multiple groups. The K value of K-Means clustering is the number of preset road types, and the operating road identification corresponding to each group is the operating road identification corresponding to the most elements in the group.

[0017] Furthermore, the road operation features corresponding to the actual operation road sign and the predicted operation road sign are respectively the centroid vectors of the groups corresponding to the actual operation road sign and the predicted operation road sign.

[0018] Furthermore, if the actual running road sign corresponding to the monitored vehicle within the preset monitoring period is different from the predicted running road sign, and the similarity between A and the road running feature corresponding to the actual running road sign is within the range between the second similarity threshold and the first similarity threshold, a secondary recognition process is performed; the secondary recognition process includes the following steps:

[0019] Obtain the historical monitoring data of the monitored vehicle in multiple historical periods; the historical monitoring data is the predicted operating road identifier and the actual operating road identifier corresponding to each historical monitoring period;

[0020] Obtain a dataset to be detected from the multiple historical monitoring data; the dataset to be detected is composed of the historical monitoring data corresponding to the actual operating road identifier with the largest quantity;

[0021] Obtain the quantity ratio B1:B2:…:Bn:…:Bf(m) among various predicted operating road identifiers in the dataset to be detected; where Bn is the quantity of the nth predicted operating road identifier in the dataset to be detected; f(m) is the total number of types of predicted operating road identifiers in the dataset to be detected; n = 1, 2, …, f(m);

[0022] Obtain the similarity ratio C1:C2:…:Cn:…:Cf(m) of the road operating characteristics corresponding to various predicted operating road identifiers in the detection dataset respectively; where Cn is the vector similarity between the road operating characteristics corresponding to the nth predicted operating road identifier in the dataset to be detected and the road operating characteristics corresponding to the first predicted operating road identifier in the dataset to be detected;

[0023] Obtain the cosine similarity L between two vectors respectively transformed from B1:B2:…:Bn:…:Bf(m) and C1:C2:…:Cn:…:Cf(m);

[0024] If L < L1, no alarm information is generated; L1 is the vector similarity threshold.

[0025] Furthermore, obtain the speed emission sequence A of the monitored vehicle within a preset monitoring period, including:

[0026] Obtain the average speed and average emissions of the vehicle corresponding to each monitoring sub-period through the OBD system of the monitored vehicle.

[0027] Furthermore, the preset road types include: highway congested sections, highway non-congested sections, national road congested sections, national road non-congested sections, provincial, county and township road congested sections, and provincial, county and township road non-congested sections.

[0028] According to the second aspect of the present invention, there is provided a non-transitory computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, it implements the above-mentioned heavy-duty freight vehicle monitoring method based on remote online data.

[0029] According to the third aspect of the present invention, there is provided an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, it implements the above-mentioned heavy-duty freight vehicle monitoring method based on remote online data.

[0030] The present invention has at least the following beneficial effects:

[0031] The present invention obtains the speed emission sequence of the monitored vehicle within the preset monitoring period, and can reflect the characteristics of the corresponding driving section of the monitored vehicle within the preset monitoring period in real time through the performance of the average speed of the vehicle and the average emission of the vehicle in multiple monitoring sub-periods. Then, the speed emission sequence is clustered into the existing groups corresponding to the corresponding road section type using K-Means clustering, and the corresponding predicted operating road identification is obtained. Finally, the actual operating road identification corresponding to the monitored vehicle within the preset monitoring period is compared with the predicted operating road identification to determine whether the emission data has been tampered with. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0033] Figure 1 A flowchart of a heavy-duty freight truck monitoring method based on remote online data provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0034] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0035] As a possible embodiment of the present invention, Figure 1 As shown, a heavy-duty freight vehicle monitoring method based on remote online data is provided, and the method comprises the following steps:

[0036] S100: Obtain the speed emission sequence A=(A1, A2, ..., Ai, ..., Az) of the monitored vehicle in the preset monitoring period. Wherein Ai is the detection characteristic value corresponding to the i-th monitoring sub-period in the preset monitoring period, Ai=(V avg i,P avg i), V avg i is the average speed of the monitored vehicle in the i-th monitoring sub-period. avgi is the average emission of the monitored vehicle in the ith monitoring sub-period. z is the total number of monitoring sub-periods in the preset monitoring cycle, i=1, 2, ..., z.

[0037] Specifically, S100 includes:

[0038] S101: Obtain the average speed and average emission of the vehicle corresponding to each monitoring sub-period by monitoring the vehicle's OBD system. The preset monitoring period in this embodiment may be 30 minutes. For example, the entire vehicle's path may be segmented into 30-minute segments, or a 30-minute time window may be used for sliding to select the vehicle status information obtained by the OBD system in the corresponding period. Correspondingly, the monitoring sub-period may be 1 minute.

[0039] The OBD system is an on-board diagnostic system that is mainly used to collect real-time operating data and diagnostic information of the vehicle. The following are some typical types of data that can be collected through the OBD system: Engine data: engine speed (RPM), coolant temperature, short-term and long-term fuel correction values, intake manifold absolute pressure (MAP), engine load and engine running time. Emission-related data: oxygen sensor voltage / current, whether the fuel evaporation system is sealed, secondary air injection system status, catalytic converter efficiency, exhaust gas recirculation (EGR) system status, diesel particulate filter (DPF) status, nitrogen oxide sensor measured nitrogen oxide (NOx) content in exhaust gas, particulate matter (PM) content in exhaust gas measured by particulate matter sensor, especially in vehicles equipped with diesel particulate filter (DPF). CO sensor: measured carbon monoxide (CO) content in exhaust gas and HC sensor (hydrocarbon sensor): measured incompletely burned hydrocarbon (HC) content in exhaust gas. Driving behavior-related data: vehicle speed, accelerator pedal position and steering wheel angle. Location and service data: GPS location information.

[0040] Thus, the average speed of the monitored vehicle in the monitoring sub-period is generated based on the vehicle speed information obtained by the OBD system or through the GPS location information and the running time. The average emission of the monitored vehicle in the monitoring sub-period is generated by the sum of various harmful emissions (nitrogen oxides, particulate matter, carbon monoxide and hydrocarbons) in the emission-related data and the running time.

[0041] Since the speed average and emission average can roughly reflect the general working conditions of the vehicle on the corresponding road section, and then reflect the operation conditions of the vehicle in the corresponding road section (such as uphill, downhill, whether it is congested, etc.). Therefore. The speed emission sequence A can be used to roughly reflect the type of road section that the vehicle travels in the preset monitoring period. In addition, in order to further improve the accuracy, the detection characteristic value can also include characteristic values ​​such as the vehicle's current carrying weight, engine load average, fuel consumption and engine running time. Then, the characteristics of the vehicle's running section can be reflected from more characteristic dimensions.

[0042] S200: Use K-Means clustering to cluster A into a corresponding target group, and use the road type identification corresponding to the target group as the predicted operating road identification corresponding to the monitored vehicle within a preset monitoring period. The target group is one of the multiple existing groups completed by K-Means clustering.

[0043] The K-Means clustering method in this step is a K-Means clustering method for generating existing groups. This clustering method clusters multiple historical velocity emission sequences, so that it can more accurately cluster the newly generated A into the corresponding group.

[0044] Existing groups are obtained as follows:

[0045] S201: Acquire a plurality of historical speed emission sequences generated when a heavy-duty freight vehicle is running on sections of a plurality of preset road types.

[0046] Specifically, the preset road types may include: congested sections of highways, non-congested sections of highways, congested sections of national highways, non-congested sections of national highways, congested sections of provincial, county and township roads, non-congested sections of provincial, county and township roads, and sections in mountainous areas. The division of the preset road types in this embodiment is based on the different workmanship characteristics of vehicles in different sections. For example, when running on a non-congested section of a highway, since the running speed can basically be maintained at a high state, the engine's workmanship is less and changes smoothly. When running on a congested section of a national highway or a congested section in an urban area, since repeated starting and braking are required, the running speed varies greatly, and the engine's workmanship is more and the changes are extremely unstable. Therefore, those skilled in the art can also divide the road types according to the different engine workmanship characteristics in the vehicle's running route in actual scenarios.

[0047] S202: Use K-Means clustering to perform clustering processing on multiple historical speed emission sequences to generate multiple groups, wherein the K value of K-Means clustering is the number of preset road types, and the operating road identification corresponding to each group is the operating road identification corresponding to the most elements in the group.

[0048] In the actual operation process, usually due to the similarity of workmanship characteristics between different sections (such as congested highway sections and non-congested national highway sections), a small number of elements may be mis-clustered during the clustering process, such as the historical speed emission sequence of congested highway sections being mis-clustered into the group corresponding to non-congested national highway sections. Therefore, when setting the operating road sign corresponding to each group, the operating road sign corresponding to the most elements in the group is selected.

[0049] Specifically, the road operation features corresponding to the actual operation road sign and the predicted operation road sign are the centroid vectors of the groups corresponding to the actual operation road sign and the predicted operation road sign, respectively.

[0050] S300: If the actual running road sign corresponding to the monitored vehicle in the preset monitoring period is the same as the predicted running road sign, no alarm information is generated. The actual running road sign and the predicted running road sign are both one of the preset running road signs.

[0051] S301: If the actual operating road sign corresponding to the monitored vehicle within the preset monitoring period is different from the predicted operating road sign, and the similarity between A and the road operation feature corresponding to the actual operating road sign is greater than a first similarity threshold, no alarm information is generated.

[0052] S302: If the actual running road sign corresponding to the monitored vehicle in the preset monitoring period is different from the predicted running road sign, and the similarity between A and the road running feature corresponding to the actual running road sign is less than a second similarity threshold, then an alarm message is generated. The second similarity threshold is less than the first similarity threshold.

[0053] Both the first similarity threshold and the second similarity threshold need to be determined based on the similarity of the centroid vectors of the groups corresponding to the multiple types of road sections divided according to the actual scene. Since this embodiment only uses a relatively simple clustering and road sign comparison method to roughly and quickly determine whether the vehicle has tampered with the emission data. Therefore, in the actual clustering process, it is very likely that A will be clustered into another group with higher similarity. Therefore, in order to avoid the occurrence of false alarms in this situation, it is necessary to further judge by calculating the similarity between A and the road operation characteristics corresponding to the actual road signs to reduce the occurrence of false alarms.

[0054] S400: If the actual road sign corresponding to the monitored vehicle in the preset monitoring period is different from the predicted road sign, and the similarity between A and the road operation feature corresponding to the actual road sign is within the range of the second similarity threshold and the first similarity threshold, a secondary recognition process is performed. The secondary recognition process includes the following steps:

[0055] S401: Obtain the historical monitoring data of the monitored vehicle at multiple times. The historical monitoring data is the predicted operating road identifier and the actual operating road identifier corresponding to each historical monitoring period.

[0056] S402: Obtain the dataset to be detected from the multiple historical monitoring data. The dataset to be detected is composed of the historical monitoring data corresponding to the actual operating road identifier with the largest quantity. Usually, the historical monitoring data in the dataset to be detected can be set to more than 200. Only with the support of a large amount of data can it more significantly show a high degree of consistency with the natural similarity ratio between the corresponding road sections in B1: B2: …: Bn: …: Bf(m).

[0057] S403: Obtain the quantity ratio B1: B2: …: Bn: …: Bf(m) between various predicted operating road identifiers in the dataset to be detected. Among them, Bn is the quantity of the nth predicted operating road identifier in the dataset to be detected. f(m) is the total number of types of predicted operating road identifiers in the dataset to be detected. n = 1, 2, …, f(m).

[0058] S404: Obtain the similarity ratio C1: C2: …: Cn: …: Cf(m) of the road operation characteristics corresponding to various predicted operating road identifiers in the detection dataset. Among them, Cn is the vector similarity between the road operation characteristics corresponding to the nth predicted operating road identifier in the dataset to be detected and the road operation characteristics corresponding to the first predicted operating road identifier in the dataset to be detected.

[0059] S405: Obtain the cosine similarity L between two vectors respectively converted from B1: B2: …: Bn: …: Bf(m) and C1: C2: …: Cn: …: Cf(m).

[0060] S406: If L < L1, no alarm information is generated. L1 is the vector similarity threshold.

[0061] The following example is used for illustration: C1 = 1, C2 = 0.8, C3 = 0.85. Then the similarity ratio of the corresponding road operation characteristics is 100: 80: 85, and the corresponding converted vector is (100, 80, 85).

[0062] If the exhaust gas data of the vehicle has not been modified, various predicted operating road identifiers in the dataset to be detected may, due to the clustering error of K-Means clustering, miscluster the corresponding monitoring data into other ethnic groups with higher similarity, and then mislabel the corresponding predicted operating road identifier, and the quantity distribution of such misclustered operating road identifiers should conform to the law between the similarities of the corresponding ethnic groups.

[0063] Based on this, the quantitative ratio between various predicted operating road signs in the data set to be tested should be highly consistent with the naturally existing similarity ratio between the corresponding road sections reflected by the above similarity ratio, such as B1=52, B2=40, B3=46, and the corresponding converted vector is (52,40,46).

[0064] If the vehicle's exhaust data has been tampered with, the number ratios between the various predicted road signs corresponding to the tampered data in the test data set will not follow the rules of the natural similarities between the corresponding groups. That is, the consistency of the natural similarity ratio between the corresponding road sections reflected by the above similarity ratio is poor, such as B1 = 40, B2 = 50, B3 = 48, and the corresponding converted vector is (40, 50, 48).

[0065] Based on the above characteristics, the cosine similarity between vectors can be calculated to more accurately determine whether the vehicle's exhaust emission data has been tampered with.

[0066] In addition, although the steps of the method in the present disclosure are described in a specific order in the drawings, this does not require or imply that the steps must be performed in this specific order, or that all the steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps, etc.

[0067] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0068] In an exemplary embodiment of the present disclosure, an electronic device capable of implementing the above method is also provided.

[0069] It will be appreciated by those skilled in the art that various aspects of the present invention may be implemented as a system, method or program product. Therefore, various aspects of the present invention may be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software, which may be collectively referred to herein as a "circuit", "module" or "system".

[0070] The electronic device according to this embodiment of the present invention is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0071] The electronic device is presented in the form of a general-purpose computing device. The components of the electronic device may include, but are not limited to: the at least one processor mentioned above, the at least one storage device mentioned above, and a bus connecting different system components (including storage devices and processors).

[0072] The storage stores program codes, which can be executed by the processor, so that the processor executes the steps according to various exemplary embodiments of the present invention described in the above “Exemplary Method” section of this specification.

[0073] The memory may include readable media in the form of volatile memory, such as random access memory (RAM) and / or cache memory, and may further include read only memory (ROM).

[0074] The storage may also include a program / utility having a set (at least one) of program modules, such program modules including but not limited to: an operating system, one or more application programs, other program modules and program data, each of which or some combination may include the implementation of a network environment.

[0075] The bus may represent one or more of several types of bus structures including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus architectures.

[0076] The electronic device may also communicate with one or more external devices (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may communicate with one or more devices that enable a user to interact with the electronic device, and / or may communicate with any device (e.g., routers, modems, etc.) that enables the electronic device to communicate with one or more other computing devices. Such communication may be performed through an input / output (I / O) interface. Furthermore, the electronic device may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) through a network adapter. The network adapter communicates with other modules of the electronic device through a bus. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0077] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0078] In an exemplary embodiment of the present disclosure, a computer-readable storage medium is also provided, on which a program product capable of implementing the above method of the present specification is stored. In some possible implementations, various aspects of the present invention may also be implemented in the form of a program product, which includes a program code, and when the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps according to various exemplary embodiments of the present invention described in the above "Exemplary Method" section of the present specification.

[0079] The program product may use any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0080] Computer readable signal media may include data signals propagated in baseband or as part of a carrier wave, in which readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Readable signal media may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0081] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.

[0082] Program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., through the Internet using an Internet service provider).

[0083] In addition, the above-mentioned figures are only schematic illustrations of the processes included in the method according to an exemplary embodiment of the present invention, and are not intended to be limiting. It is easy to understand that the processes shown in the above-mentioned figures do not indicate or limit the time sequence of these processes. In addition, it is also easy to understand that these processes can be performed synchronously or asynchronously, for example, in multiple modules.

[0084] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into multiple modules or units to be embodied.

[0085] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A heavy-duty freight vehicle monitoring method based on remote online data, characterized in that: The method comprises the following steps: Obtain the speed emission sequence A=(A1, A2, ..., Ai, ..., Az) of the monitored vehicle in the preset monitoring period; wherein Ai is the detection characteristic value corresponding to the i-th monitoring sub-period in the preset monitoring period, Ai=(V avg i,P avg i), V avg i is the average speed of the monitored vehicle in the i-th monitoring sub-period; P avg i is the average emission of the monitored vehicles in the i-th monitoring sub-period; z is the total number of monitoring sub-periods in the preset monitoring cycle, i = 1, 2, ..., z; Cluster A into a corresponding target group using K-Means clustering, and use the road type identifier corresponding to the target group as the predicted operating road identifier corresponding to the monitored vehicle within a preset monitoring period; the target group is one of the multiple existing groups completed by K-Means clustering; If the actual operating road sign corresponding to the monitored vehicle within the preset monitoring period is the same as the predicted operating road sign, no alarm information is generated; the actual operating road sign and the predicted operating road sign are both one of the preset operating road signs.

2. The method according to claim 1, characterized in that After taking the road type identification corresponding to the target group as the predicted running road identification corresponding to the monitored vehicle within a preset monitoring period, the method further includes: If the actual operating road sign corresponding to the monitored vehicle within the preset monitoring period is different from the predicted operating road sign, and the similarity between A and the road operation feature corresponding to the actual operating road sign is greater than the first similarity threshold, no alarm information is generated.

3. The method according to claim 2, characterized in that After taking the road type identification corresponding to the target group as the predicted running road identification corresponding to the monitored vehicle within a preset monitoring period, the method further includes: If the actual operating road sign corresponding to the monitored vehicle within the preset monitoring period is different from the predicted operating road sign, and the similarity between A and the road operation characteristics corresponding to the actual operating road sign is less than a second similarity threshold, an alarm message is generated; the second similarity threshold is less than the first similarity threshold.

4. The method according to claim 1, characterized in that: Existing groups are obtained as follows: Respectively obtain a plurality of historical speed emission sequences generated when a heavy freight vehicle is running on sections of a plurality of preset road types; K-Means clustering is used to cluster multiple historical speed emission sequences to generate multiple groups. The K value of K-Means clustering is the number of preset road types, and the operating road identification corresponding to each group is the operating road identification corresponding to the most elements in the group.

5. The method according to claim 4, characterized in that The road operation features corresponding to the actual operation road sign and the predicted operation road sign are respectively the centroid vectors of the groups corresponding to the actual operation road sign and the predicted operation road sign.

6. The method according to claim 5, characterized in that If the actual running road sign corresponding to the monitored vehicle in the preset monitoring period is different from the predicted running road sign, and the similarity between A and the road running feature corresponding to the actual running road sign is within the range between the second similarity threshold and the first similarity threshold, a secondary recognition process is performed; the secondary recognition process includes the following steps: Acquire a plurality of historical monitoring data of the monitored vehicle; the historical monitoring data are the predicted operating road signs and the actual operating road signs corresponding to each historical monitoring period; Acquire a data set to be detected from a plurality of historical monitoring data; the data set to be detected is composed of historical monitoring data corresponding to the largest number of actually running road signs; Obtain the quantity ratio B1: B2: …: Bn: …: Bf(m) among various predicted operating road signs in the dataset to be detected; where Bn is the quantity of the nth predicted operating road sign in the dataset to be detected; f(m) is the total number of types of predicted operating road signs in the dataset to be detected; n = 1, 2, …, f(m); Obtain the similarity ratio C1: C2: …: Cn: …: Cf(m) of the road operating characteristics corresponding to various predicted operating road signs in the detection dataset respectively; where Cn is the vector similarity between the road operating characteristics corresponding to the nth predicted operating road sign in the dataset to be detected and the road operating characteristics corresponding to the first predicted operating road sign in the dataset to be detected; Obtain the cosine similarity L between two vectors respectively transformed from B1: B2: …: Bn: …: Bf(m) and C1: C2: …: Cn: …: Cf(m); If L < L1, no alarm information is generated; L1 is the vector similarity threshold.

7. The method according to claim 1, characterized in that Obtain the speed emission sequence A of the monitored vehicle within the preset monitoring period, including: Obtain the average speed and average emissions of the vehicle corresponding to each monitoring sub-period through the OBD system of the monitored vehicle.

8. The method according to claim 4, characterized in that The preset road types include: congested sections of expressways, non-congested sections of expressways, congested sections of national roads, non-congested sections of national roads, congested sections of provincial, county and rural roads, and non-congested sections of provincial, county and rural roads.

9. A non-transitory computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by the processor, it implements the heavy-duty freight vehicle monitoring method based on remote online data as described in any one of claims 1 to 8.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, it implements the heavy-duty freight vehicle monitoring method based on remote online data as described in any one of claims 1 to 8.

Images