Full-link quality monitoring method, device, storage medium and vehicle for Internet of Vehicles

Abstract

The present invention discloses a method, device, storage medium and vehicle for monitoring the quality of the entire link of the Internet of Vehicles. The method comprises: obtaining the collected data of each node device among multiple node devices in the entire link of the Internet of Vehicles; obtaining at least one target collected data group based on the correlation between the collected data of each node device in the same time period, wherein the target collected data group includes the collected data of at least one node device in the same time period; comparing the collected data in the target collected data group to obtain a comparison result; based on the comparison result, determining the abnormal node devices in the entire link among multiple node devices. The present invention solves the technical problem of poor efficiency in evaluating the quality of remote vehicle control services on the vehicle side.

Description

Technical Field

[0001] The present invention relates to the field of vehicles, and in particular to a method, device, storage medium and vehicle for monitoring the full-link quality of an Internet of Vehicles. Background Art

[0002] At present, in the remote control of the Internet of Vehicles, since the technical implementation link of the remote control service of the Internet of Vehicles is relatively long, when problems occur in the remote control of the vehicle, the problem analysis cycle is long and it is difficult to locate the cause of the problem. Therefore, there is still a technical problem of poor efficiency in evaluating the quality of the remote control service on the vehicle side.

[0003] With regard to the technical problem of poor efficiency in evaluating the quality of vehicle-side remote control services in the above-mentioned related technologies, no effective solution has been proposed so far. Summary of the invention

[0004] Embodiments of the present invention provide a method, device, storage medium and vehicle for monitoring the full-link quality of a connected vehicle network, so as to at least solve the technical problem of poor evaluation effect of the quality of a vehicle-side remote control service.

[0005] According to one aspect of an embodiment of the present invention, a method for monitoring the quality of a full link of an Internet of Vehicles is provided. The method may include: obtaining collected data of each node device among multiple node devices in the full link of the Internet of Vehicles; obtaining at least one target collected data group based on the association relationship between the collected data of each node device in the same time period, wherein the target collected data group includes the collected data of at least one node device in the same time period; comparing the collected data in the target collected data group to obtain a comparison result; and determining abnormal node devices in the full link among multiple node devices based on the comparison result.

[0006] Optionally, based on the correlation between the collected data of each node device in the same time period, at least one target collected data group is obtained, including: converting the collected data to obtain standardized data of each node device; based on the correlation between the standardized data of each node device in the same time period, at least one target collected data group is obtained.

[0007] Optionally, based on the correlation relationship between the standardized data of each node device in the same time period, at least one target acquisition data group is obtained, including: sorting the standardized data of each node device in chronological order to obtain multiple groups of standardized data groups, wherein the number of standardized data groups is consistent with the number of node devices; extracting standardized data in the same time period from the multiple groups of standardized data groups, establishing a correlation relationship between the extracted standardized data, and obtaining at least one target acquisition data group, wherein the number of target acquisition data groups is the same as the number in the time period.

[0008] Optionally, based on the comparison result, an abnormal node device in the entire link is determined among multiple node devices, including: in response to the comparison result that there is a standardized data in the target collection data group that is different from other standardized data, determining that a standardized data is abnormal; in response to the node device having a target number of abnormal standardized data, determining that the node device is an abnormal node device.

[0009] Optionally, in response to the presence of an abnormal node device in the entire link, a prompt message is output.

[0010] Optionally, the abnormal node device is corrected, and the quality of the corrected full link is tested; in response to each node device being normal within the target time period, the output of the prompt information is stopped.

[0011] According to another aspect of an embodiment of the present invention, a vehicle network full-link quality monitoring device is also provided, which may include: a first acquisition unit, used to acquire collected data of each node device among multiple node devices in the full link of the vehicle network; a second acquisition unit, used to acquire at least one target collected data group based on the correlation relationship between the collected data of each node device in the same time period, wherein the target collected data group includes the collected data of at least one node device in the same time period; a processing unit, used to compare the collected data in the target collected data group to obtain a comparison result; and a determination unit, used to determine abnormal node devices in the full link among multiple node devices based on the comparison result.

[0012] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is further provided. The computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the full-link quality monitoring method of the Internet of Vehicles of the embodiment of the present invention.

[0013] According to another aspect of an embodiment of the present invention, a processor is further provided. The processor is used to run a program, wherein the program executes the full-link quality monitoring method of the Internet of Vehicles of the embodiment of the present invention when it is run.

[0014] According to another aspect of an embodiment of the present invention, a vehicle is further provided, wherein the vehicle is used to execute the full-link quality monitoring method of a vehicle network according to an embodiment of the present invention.

[0015] In an embodiment of the present invention, in the full link of the Internet of Vehicles, the collected data of each node device in multiple node devices is obtained; based on the association relationship between the collected data of each node device in the same time period, at least one target collected data group is obtained, wherein the target collected data group includes the collected data of at least one node device in the same time period; the collected data in the target collected data group are compared to obtain a comparison result; based on the comparison result, the abnormal node device in the full link is determined among multiple node devices. That is to say, the embodiment of the present invention extracts the collected data of the node devices in the full link of the Internet of Vehicles, and can associate the collected data in the same time period with each other to determine the association relationship, and can obtain the target collected data group based on the association relationship, and by comparing and analyzing the collected data in the target collected data group, if the comparison result of a certain collected data in the target collected data group is different from that of other collected data, it can be determined that there is an abnormal node device in the full link of the Internet of Vehicles; if the comparison results are the same, the node devices in the full link of the Internet of Vehicles are all normal node devices, thereby solving the technical problem of poor efficiency in evaluating the quality of remote control service on the vehicle side, and achieving the technical effect of improving the efficiency of evaluating the quality of remote control service on the vehicle side. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0017] Figure 1 is a flow chart of a vehicle data processing method according to an embodiment of the present invention;

[0018] Figure 2 is a flow chart of a method for monitoring the full-link quality of a remote control service of an Internet of Vehicles according to an embodiment of the present invention;

[0019] Figure 3 is a schematic diagram of a remote control function implementation link when a vehicle is in a wake-up state according to an embodiment of the present invention;

[0020] Figure 4 is a schematic diagram of a remote control function implementation link when a vehicle is in an unawakened state according to an embodiment of the present invention;

[0021] Figure 5 is a schematic diagram of a vehicle data processing device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0022] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings 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 ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0023] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0024] Example 1

[0025] According to an embodiment of the present invention, an embodiment of a vehicle data processing method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0026] Figure 1 is a flow chart of a vehicle data processing method according to an embodiment of the present invention. Figure 1 As shown, the method may include the following steps:

[0027] Step S102, in the entire link of the Internet of Vehicles, acquiring collected data of each node device among multiple node devices.

[0028] In the technical solution provided in the above step S102 of the present invention, there are multiple node devices in the full link of the Internet of Vehicles, and the collected data of multiple node devices can be obtained, wherein the node devices may include an application end (Application, referred to as APP), a vehicle remote service provider (Telematics Service Provider, referred to as TSP), a vehicle-mounted electrical component (Telematics BOX, referred to as T-BOX), a cloud, etc. The cloud can be the Internet of Things (Internet of Things, referred to as IOT). The collected data may include status information and network information stored in the node device. For example, the collected data of the application end may include data such as the vehicle components controlled by the remote control command, the sending time of the remote control command, the time when the next node device receives the remote control command, and the result status. The collected data of the vehicle remote service provider may include quality data of all other node devices in the full link. The collected data of vehicle electrical components may include network standard (for example, fourth-generation mobile information system or fifth-generation mobile information system), signal strength, controller status (for example, door status, engine status or window status, etc.), status information (for example, wake-up status, power-on status, start-up status, ignition off status, power-off status and sleep status, etc.).

[0029] It should be noted that the above-mentioned node devices and the collected data of the node devices are only for illustration and are not specifically limited here and may be changed according to actual conditions.

[0030] Optionally, the collected data can be processed to generate logs. For example, the collected data of each node device in the full-link node can be obtained, and features can be extracted from the collected data. Logs of node devices can be automatically generated through knowledge graph construction or graph convolutional neural network models. It should be noted that the methods and processes for generating logs here are all examples and are not specifically limited.

[0031] For example, a real-time monitoring model may be established to periodically obtain and store logs of all node devices. The storage period of the model may be seven days.

[0032] Step S104: acquiring at least one target collection data group based on the association relationship between the collection data of each node device in the same time period, wherein the target collection data group includes the collection data of at least one node device in the same time period.

[0033] In the technical solution provided in the above step S104 of the present invention, the collected data of each node device in the same time period is determined, and the collected data of each node device in the same time period can be associated to determine the association relationship between the collected data. Based on the association relationship, at least one target collected data group can be determined, wherein the association relationship can be used to characterize that there is an association relationship between the data of the node devices. The target collected data group may include the collected data of at least one node device in the same time period. The same time period may be a preset time period.

[0034] Optionally, by modifying the logs of each node device, the logs can be associated to associate the collected data of the node devices. Based on the association relationship, the target collected data group can be determined. It should be noted that the method of associating the node devices here is only for illustration and no specific limitation is imposed.

[0035] For example, when the vehicle is woken up, the logs of the node device application end, the vehicle remote service provider and the on-board electrical components can be standardized. The application end in the same time period can be associated with the log of the vehicle remote service provider, and the log of the vehicle remote service provider can be associated with the log of the on-board electrical components, so as to obtain the association relationship between the logs of the above-mentioned node devices. Based on the association relationship, the collected data of the application end, the vehicle remote service provider and the on-board electrical components in the same time period can be determined, and the above-mentioned collected data can be determined as a group of target collected data groups.

[0036] Step S106, comparing the collected data in the target collected data group to obtain a comparison result.

[0037] In the technical solution provided in the above step S106 of the present invention, the collected data of each node device in the target collected data group can be compared to obtain a comparison result, wherein the comparison result can be the similarity between the collected data, which can be used to characterize whether the collected data of multiple node devices are the same.

[0038] Optionally, the collected data of each node device within the same time period can be determined as a target collected data group, and the collected data of each node device in the target collected data group can be compared to determine the comparison result, so as to determine whether the collected data of each node device within the same time period are the same based on the comparison result.

[0039] Step S108: Based on the comparison result, an abnormal node device in the entire link is determined from among the multiple node devices.

[0040] In the technical solution provided in the above step S108 of the present invention, it can be determined whether the collected data are the same based on the comparison result. If they are not the same, it can be explained that there are abnormal node devices in the node devices in the whole link of the Internet of Vehicles at this time, and the abnormal node devices can be further determined from multiple node devices; if they are the same, it can be explained that all node devices in the whole link of the Internet of Vehicles at this time are in normal state.

[0041] In the above steps S102 to S108 of the present application, in the full link of the Internet of Vehicles, the collected data of each node device in multiple node devices are obtained; based on the association relationship between the collected data of each node device in the same time period, at least one target collected data group is obtained, wherein the target collected data group includes the collected data of at least one node device in the same time period; the collected data in the target collected data group are compared to obtain a comparison result; based on the comparison result, the abnormal node device in the full link is determined among the multiple node devices. The embodiment of the present invention extracts the collected data of the node devices in the full link of the Internet of Vehicles, and can associate the collected data in the same time period with each other to determine the association relationship. Based on the association relationship, the target collected data group can be obtained. By comparing and analyzing the collected data in the target collected data group, if the comparison result of a certain collected data in the target collected data group is different from that of other collected data, it can be determined that there is an abnormal node device in the full link of the Internet of Vehicles; if the comparison results are the same, the node devices in the full link of the Internet of Vehicles are all normal node devices, thereby solving the technical problem of poor efficiency in evaluating the quality of remote control service on the vehicle side, and achieving the technical effect of improving the efficiency of evaluating the quality of remote control service on the vehicle side.

[0042] The above method of this embodiment is further introduced below.

[0043] As an optional implementation method, step S104, based on the correlation relationship between the collected data of each node device in the same time period, obtains at least one target collected data group, including: converting the collected data to obtain standardized data of each node device; based on the correlation relationship between the standardized data of each node device in the same time period, obtains at least one target collected data group.

[0044] In this embodiment, the collected data can be converted to obtain standardized data corresponding to the collected data of all node devices. The collected data can be processed to achieve the purpose of converting the collected data into standardized data. The standardized data of each node device in the same time period can be associated to obtain an association relationship. Based on the association relationship, at least one target collected data group can be determined.

[0045] Optionally, the logs of all node devices may be uniformly standardized to obtain standardized data, and then the standardized data of each node device may be correlated with each other. Based on the correlation, a group of target collection data groups within the same time period may be obtained.

[0046] For example, the purpose of converting collected data into standardized data can be achieved by establishing a link tracking model. The model can specify a unified log normalization format for the logs of all node devices, and open the logs according to the log normalization format, so as to achieve standardization of the logs and obtain standardized data, which can then make the standardized data of each node device interrelated. It should be noted that this does not impose specific restrictions on the log normalization format and the process and method of converting collected data into standardized data, and can be changed according to the actual collected data.

[0047] As an optional implementation method, step S104, based on the association relationship between the standardized data of each node device in the same time period, obtains at least one target acquisition data group, including: sorting the standardized data of each node device in time order to obtain multiple standardized data groups, wherein the number of standardized data groups is consistent with the number of node devices; extracting standardized data in the same time period from the multiple standardized data groups, establishing an association relationship between the extracted standardized data, and obtaining at least one target acquisition data group, wherein the number of target acquisition data groups is the same as the number in the time period. The time order can be the order from the front to the back of the time.

[0048] In this embodiment, the standardized data of each node device can be sorted in chronological order to obtain multiple standardized data groups, from which standardized data in the same time period can be extracted, and the standardized data can be associated according to the chronological order of all standardized data in the same time period to obtain an association relationship, and at least one target acquisition data group is obtained based on the association relationship, wherein the number of standardized data groups is consistent with the number of node devices. The number of target acquisition data groups is the same as the number of time periods.

[0049] Optionally, data mining technology can be used to determine the time series of standardized data. Based on this technology, the standardized data can be subjected to spatiotemporal analysis, the standardized data of each node device can be correlated and processed, the standardized data can be converted into a corresponding time series, and feature extraction can be performed on the time series to obtain the features of the time series (for example, the time when a remote control command is sent or the time when a remote control command is received, etc.). It should be noted that the method and process for determining the time series of standardized data here are for illustrative purposes only and are not specifically limited here.

[0050] Optionally, the time series of standardized data can be sorted in chronological order through a link tracking model. The model can divide the standardized data into multiple time periods based on the time series, and then associate the standardized data in each time period through the time series. Combined with the topological relationship configured in the model, the association relationship of the standardized data in the same time period can be mined, and the technical effect of visually displaying the standardized data of each node device can be achieved.

[0051] For example, the collected data of three node devices are obtained, including three node devices, an application end, a vehicle remote service provider, and an on-board electrical component. Feature extraction can be performed on the collected data. Logs can be automatically generated by constructing a knowledge graph or a graph convolutional neural network model. The logs of each node device are standardized to generate corresponding standardized data. Data mining technology can be used to determine the time series of the standardized data. Feature extraction is performed on the time series to obtain the receiving and sending time of the remote control instructions corresponding to each node device. The standardized data can be sorted and associated based on the time sequence to obtain multiple groups of standardized data groups. Standardized data groups in the same time period can be extracted from the multiple groups of standardized data groups. According to the time order of all standardized data in the same time period from front to back, a group of target collected data groups can be determined.

[0052] As an optional implementation method, step S104, based on the comparison result, determines the abnormal node device in the entire link among multiple node devices, including: in response to the comparison result that there is a standardized data in the target collection data group that is different from other standardized data, determining that a standardized data is abnormal; in response to the node device having a target number of abnormal standardized data, determining that the node device is an abnormal node device.

[0053] In this embodiment, the standardized data in the target acquisition data group within the same time period can be compared to obtain a comparison result. When the comparison result is that there is a standardized data in the target acquisition data group that is different from other standardized data, it can be determined that there is a standardized data anomaly. When there are a target number of abnormal standardized data in a certain node device, the node device can be determined to be an abnormal node device.

[0054] Optionally, by performing comparison processing on all standardized data in a target acquisition data group, it can be determined whether all standardized data are the same. When there is at least one standardized data that is different from other standardized data, it can be said that at least one standardized data is abnormal, and the node device corresponding to the abnormal standardized data can be further determined.

[0055] Optionally, in an embodiment of the present invention, multiple standardized data can be processed by constructing a remote service quality alarm model. The model can compare the standardized data according to customized related alarm rule expressions to obtain comparison results, thereby achieving the technical effect of real-time monitoring of whether the standardized data is abnormal. If the comparison result is that the standardized data is the same, it can be explained that the node devices in the entire link are all normal node devices, that is, the remote control is successful; if the comparison result is that there is a certain standardized data that is different from other standardized data, it can be explained that there is an abnormal node device in the entire link, that is, the remote control of the vehicle fails. It should be noted that the method and model for processing standardized data here are only for example and are not specifically limited.

[0056] Optionally, the standardized data and comparison results can be regularly acquired and monitored through a real-time monitoring model, which can realize multiple monitoring tasks in parallel, and can transmit the standardized data and comparison results to the real-time monitoring model. The real-time monitoring model can observe the changing trend of the standardized data within the target time period, and can actively calculate and generate real-time monitoring indicators (for example, remote control failure rate), thereby achieving the technical effect of regularly determining whether the full-link quality of the Internet of Vehicles remote control service within a period of time meets the standards, and the real-time monitoring indicators and other data can be visualized through a visual data analysis method. It should be noted that the above-mentioned method for evaluating the full-link quality of the Internet of Vehicles remote control service and the method for visualizing the data are only for example and are not specifically limited here.

[0057] As an optional implementation manner, in step S108, in response to the existence of an abnormal node device in the entire link, a prompt message is output.

[0058] In this embodiment, when an abnormal node device exists in the entire link of the Internet of Vehicles, a prompt message may be output to alert the user, wherein the prompt message may include information such as the name and standardized data of the abnormal node device.

[0059] Optionally, when there are abnormal node devices in the entire link of the Internet of Vehicles, the prompt information can be output by constructing a remote service quality alarm model. The alarm rules of the model are triggered, and the prompt information can be output through a medium (such as phone, email, and text message) to contact the person in charge of the Internet of Vehicles. Among them, the alarm rules can be used to characterize the existence of abnormal node devices in the entire link, and the change trend of the standardized data monitored by the real-time monitoring unit model can be abnormal. It should be noted that the above-mentioned model and medium for outputting prompt information are only for example and are not specifically limited.

[0060] For example, if the standardized data of the on-board electrical components in the full link of the Internet of Vehicles is abnormal, a pop-up text window "The on-board electrical components are abnormal, please correct them in time" can be output to the user through the graphical user interface, or a voice prompt can be given, and a relevant email can be sent to the person in charge of the Internet of Vehicles through the mailbox for prompting, where the graphical user interface can be the car screen or the car navigation. It should be noted that the above prompting of the user through the graphical user interface or voice is only for example, and no specific limitation is made here.

[0061] Optionally, if the change trend of the standardized data monitored by the real-time monitoring model within a certain period of time shows a sudden increase or decrease, since this situation is not included in the alarm rule, in an embodiment of the present invention, a neural network model can be added to the real-time monitoring model, and the above situation can be learned and trained to achieve a technical effect of more accurate diagnosis of abnormal node equipment. A neural network model can also be added to the remote service alarm model, and the neural network model can be used to continuously self-learn the standardized data and comparison results in the process of full-link quality monitoring to improve the ability to output prompt information, thereby solving the technical problem of the effectiveness of the vehicle-side remote control service quality evaluation and achieving the technical effect of improving the efficiency of the vehicle-side remote control service quality evaluation.

[0062] As an optional implementation manner, in step S108, the abnormal node device is corrected, and the quality of the corrected full link is detected; in response to each node device being normal within the target time period, the output of the prompt information is stopped.

[0063] In this embodiment, when there are abnormal node devices in the entire link of the Internet of Vehicles, the abnormal node devices can be corrected, and the quality of the corrected entire link can be checked. When all node devices in the entire link are in a normal state within the target time period, the output of prompt information can be stopped.

[0064] Optionally, when there are abnormal node devices in the entire link, if the abnormal node devices are corrected by contacting the person in charge, the corrected entire link can be quality-checked by establishing a statistical analysis model. The statistical analysis model can store the standardized data and comparison results of each node device after correction at the target time, analyze the standardized data, and determine the change trend of each standardized data within the target time period. If there is an abnormality in the change trend of the standardized data within the target time period, it can be said that there are still abnormal node devices. The model can automatically generate a problem analysis report for the abnormal node device, and can send prompt information through the remote service quality alarm model for prompting; if the change trends of all standardized data within the target time period are normal, it can be said that all node devices are in a normal state. The model can release the standardized data and comparison results stored therein, and the remote service quality alarm model can stop outputting prompt information. It should be noted that the model for quality detection of the entire link here is only for example and is not specifically limited.

[0065] In an embodiment of the present invention, in the full link of the Internet of Vehicles, the collected data of each node device in multiple node devices is obtained; based on the association relationship between the collected data of each node device in the same time period, at least one target collected data group is obtained, wherein the target collected data group includes the collected data of at least one node device in the same time period; the collected data in the target collected data group are compared to obtain a comparison result; based on the comparison result, the abnormal node device in the full link is determined among multiple node devices. That is to say, the embodiment of the present invention extracts the collected data of the node devices in the full link of the Internet of Vehicles, and can associate the collected data in the same time period with each other to determine the association relationship, and can obtain the target collected data group based on the association relationship, and by comparing and analyzing the collected data in the target collected data group, if the comparison result of a certain collected data in the target collected data group is different from that of other collected data, it can be determined that there is an abnormal node device in the full link of the Internet of Vehicles; if the comparison results are the same, the node devices in the full link of the Internet of Vehicles are all normal node devices, thereby solving the technical problem of poor efficiency in evaluating the quality of remote control service on the vehicle side, and achieving the technical effect of improving the efficiency of evaluating the quality of remote control service on the vehicle side.

[0066] Example 2

[0067] The technical solution of the embodiment of the present invention is illustrated below in conjunction with preferred implementation modes.

[0068] The Internet of Vehicles is based on the in-vehicle network, inter-vehicle network and in-vehicle mobile network, and is an integrated network that can realize intelligent traffic management, intelligent dynamic information services and intelligent vehicle control in accordance with agreed communication protocols and data exchange standards. It provides remote control services related to vehicle safety, remote vehicle positioning, vehicle condition inquiry, etc., and is a service type that focuses on.

[0069] Remote control of vehicles is one of the important technologies to realize intelligent driving and even unmanned driving of vehicles. At present, the functions of remote control of vehicles mainly include controlling the start and shutdown of the vehicle, turning the air conditioner on or off, seat heating and a series of other functions, and involving the integration of multiple technologies such as smart cars, smart phones, software and mobile networks. However, the current relevant remote control vehicle technology has a long technical implementation link. When problems occur in the technical quality, the problem analysis cycle is long and it is difficult to locate the cause of the problem. Therefore, there is still a technical problem of poor evaluation of the quality of remote control service on the vehicle side.

[0070] In a related technology, a full-link automated testing method for automobile remote control functions is specified, including the following steps: simulating different vehicle states, uploading vehicle state data packets to the Internet of Vehicles system via the Controller Area Network (CAN) bus to simulate data uplink process testing; simulating remote control instructions, receiving remote control instructions to simulate data downlink process testing. Through the above method, different vehicle states can be simulated, i.e., passenger operations on the vehicle side, i.e., simulating remote control instructions, i.e., collecting user operations on the application side, and tracking the full process data of the two situations, to achieve full-link automated testing of automobile remote control functions, reducing development costs while also saving time. However, this method still has the technical problem of poor evaluation of the quality of remote control service on the vehicle side.

[0071] In another related technology, a vehicle network service quality detection system and method are specified, including a service test packet sending module, a service quality acquisition module, a service quality detection module and a service quality adjustment module; the service quality detection module includes a business time consumption calculation unit, a business time consumption comparison unit, a service quality detection and judgment unit; the service quality adjustment module includes a node service quality adjustment unit, a transmission mode adjustment unit, a transmission frequency adjustment unit and a configuration unit. According to a preset time period, a test package is sent to the vehicle network service system, a detailed log file of the vehicle network mobile terminal service quality in the service area is obtained, and the corresponding business service quality is detected according to the log recording time and the preset business time threshold. According to the value of the service quality parameter, it is judged whether the service quality meets the standard, which can avoid occupying too many system resources, thereby comprehensively detecting the business service quality of the vehicle network service system. However, this method still has the technical problem of poor evaluation effect of the vehicle-side remote control service quality.

[0072] However, the present invention proposes a remote control service quality monitoring method based on the Internet of Vehicles, which includes: data collection on relevant nodes (APP, TBOX and TSP, etc.); storage scheme design and data storage for the data collected by each node; parsing and preprocessing the data; spatiotemporal analysis of the data through data mining technology, data fusion processing into time series data, and extraction of time series data features to determine the status of the vehicle before and after the remote command is issued; command monitoring indicators through analysis of data features, and establish a real-time monitoring model to calculate and generate real-time monitoring indicators for the data; construct a remote control service alarm model based on rule expressions to determine whether the status of real-time monitoring data indicators is abnormal. When the alarm rule is triggered, the person in charge can be found through the medium; analyze the collected long-term data to automatically generate problem analysis reports and monitoring alarm strategies; when there is a problem, the node where the problem occurs can be quickly located, and a link tracking model can be established so that the logs of each node can be correlated with each other.

[0073] The full-link quality monitoring method of the Internet of Vehicles according to an embodiment of the present invention is further introduced below.

[0074] Figure 2 is a flow chart of a method for monitoring the full-link quality of a remote control service of an Internet of Vehicles according to an embodiment of the present invention. Figure 2 As shown, the method may include the following steps:

[0075] Step S202: Collect data from all node devices.

[0076] In the technical solution provided in the above step S202 of the present invention, in order to monitor the status of each node device in the entire link of the remote service, it is necessary to collect data from the relevant node devices (such as APP, T-BOX, TSP, etc.).

[0077] Optionally, the APP node device needs to record the data content of each remote control instruction, such as the control component, instruction sending time, reception time of the next node device, instruction return time and result status; in the T-BOX node device, it is necessary to record basic status information such as each hardware version, network status, information strength, T-BOX status (including: wake-up, power-on, startup, power-off, shutdown and sleep, etc.); in the TSP node device, the status of the entire link can be recorded in a log to feedback the quality of each node device, and the collected data of each node device can be reported through various methods such as embedding points and protocols.

[0078] It should be noted that the above-mentioned node devices and node device data are only for illustration and are not specifically limited here.

[0079] Step S204, storing the collected data.

[0080] In the technical solution provided in the above step S204 of the present invention, a storage solution can be designed for the data collected by each node device, and a data storage solution can be formulated based on the final usage of the data (for example, whether the data needs to be processed in real time or whether it is historical data processing).

[0081] Step S206, processing the data.

[0082] In the technical solution provided in the above step S206 of the present invention, the data of each node device can be parsed and preprocessed. For example, the vehicle condition data uploaded by T-BOX through the vehicle cloud data protocol; the log data file uploaded by the APP embedding point; and the remote control remote service log file collected by TSP can be parsed.

[0083] Step S208: multi-dimensional data fusion analysis.

[0084] In the technical solution provided in the above step S208 of the present invention, based on data mining technology, the collected data can be analyzed in time and space, the data can be fused and processed into time series data, and features of the time series data can be extracted to obtain features of the time series data. The state of the vehicle before and after the remote control command is issued can be judged, and monitoring indicators can be formulated through correlation analysis of data features. For example, the corresponding relationship between node devices can be obtained through knowledge graphs, relationship tables, etc. It should be noted that this is only an example, and no specific restrictions are imposed on the method and steps for the correlation relationship between node devices.

[0085] Step S210: establishing a real-time monitoring model.

[0086] In the technical solution provided in the above step S210 of the present invention, a real-time monitoring model can be established. The data storage period of the model can be seven days. The model is a multi-task concurrent model. The required data can be obtained from the data mobile phone server in real time, and the data can be actively calculated to generate real-time monitoring indicators (for example, remote control failure rate), thereby realizing the monitoring of data characteristics of each node device in the entire link, and the data can be displayed through a visual data analysis method.

[0087] For example, the real-time monitoring model can observe the changing trend of data in the time series. However, when the changing trend of the data suddenly rises or suddenly falls, these two situations can be continuously learned through the neural network model to determine the abnormal node devices in the entire link. It should be noted that the model and process for solving the special situation of the data changing trend here are only for illustration and no specific limitation is imposed.

[0088] Step S212: establishing a remote control service quality alarm model.

[0089] In the technical solution provided in the above step S212 of the present invention, a remote control service quality alarm model based on a rule expression can be established based on the business logic of the remote control service. The model can determine whether the status of the real-time monitoring data indicator is abnormal according to the custom rules. When the alarm rule is triggered, the person in charge can be found through media such as telephone, email, and text message. It should be noted that the media for contacting the person in charge here is only for example and is not specifically limited.

[0090] Optionally, most existing alarm models are generally models based on alarm rules, while the embodiments of the present invention can train the neural network model through the original data of the node device, and then use the self-learning ability of the neural network model to continuously learn in the subsequent remote control service full-link quality monitoring process. When there is an abnormal node device, an alarm can be issued.

[0091] Step S214, establishing a statistical analysis model.

[0092] In the technical solution provided in the above step S214 of the present invention, a statistical analysis model can be established. The data storage period of the model is long-term, and the data collected over a long period of time can be analyzed. A problem analysis report of the abnormal node can be automatically generated based on the long-term change trend of the data. When the quality problem indicator of a certain abnormal node is in a normal state for a long time, the remote control service quality alarm model can be actively contacted to release relevant data.

[0093] Step S216, establishing a full-link tracking model.

[0094] In the technical solution provided in the above step S216 of the present invention, in order to more quickly and accurately locate the node device where the problem occurs, a full-link tracking model can be established, and the logs of the node devices can be standardized so that the logs of each node can be correlated with each other. Through correlation analysis, the time sequence of related events and the explicit correlation of events, the time series of related events can be extracted from massive Internet of Vehicles monitoring data and the correlation degree can be sorted. The monitoring information within a certain time period can be analyzed by association rules. Combined with the topological relationship of the configuration information, the causal relationship between each node device in the whole link can be excavated, and the status of each node device can be visualized.

[0095] Figure 3 is a schematic diagram of a remote control function implementation link when a vehicle is in a wake-up state according to an embodiment of the present invention, such as Figure 3As shown, the node devices that may be included in the function realization link 300 for remotely controlling a vehicle when the vehicle is in an awake state are: an application end 301, a vehicle remote service provider 302, an Internet of Things 303, an on-board electrical component 304 and a vehicle 305. The command for remotely controlling the vehicle may be sent by the application end 301 and transmitted to the vehicle remote service provider 302. The vehicle remote service provider 302 may transmit the command for remotely controlling the vehicle to the Internet of Things 303. The Internet of Things 303 may transmit the command for remotely controlling the vehicle to the on-board electrical component 304. Finally, the on-board electrical component 304 may transmit the command for remotely controlling the vehicle to the vehicle 305.

[0096] Figure 4 is a schematic diagram of a remote control function implementation link when a vehicle is in an unawakened state according to an embodiment of the present invention, such as Figure 4 As shown, the node devices that may be included in the function realization link 400 of remotely controlling the vehicle when the vehicle is in an unaware state are: an application end 401, a vehicle remote service provider 402, an Internet of Things 403, an on-board electrical component 404, and a vehicle 405. When the vehicle is in an unaware state, there may be two function realization links for remotely controlling the vehicle, one of which is that the remote control vehicle instruction can be sent by the application end 401 and transmitted to the vehicle remote service provider 402, the vehicle remote service provider 402 can transmit the remote control vehicle instruction to the Internet of Things 403, the Internet of Things 403 can transmit the remote control vehicle instruction to the on-board electrical component 404, and finally the on-board electrical component 404 can transmit the remote control vehicle instruction to the vehicle 405; the other is that the remote control vehicle instruction is sent by the application end 401 and transmitted to the vehicle remote service provider 402, and the vehicle remote control service provider can transmit the remote control vehicle instruction to the vehicle 405 through the SMS service.

[0097] The embodiment of the present invention extracts the collected data of the node devices in the whole link of the Internet of Vehicles, and can correlate the collected data in the same time period to determine the correlation relationship. Based on the correlation relationship, a target collected data group can be obtained, and the collected data in the target collected data group is compared and analyzed. If the comparison result of a certain collected data in the target collected data group is different from that of other collected data, it can be determined that there are abnormal node devices in the whole link of the Internet of Vehicles; if the comparison results are the same, the node devices in the whole link of the Internet of Vehicles are all normal node devices, thereby solving the technical problem of poor efficiency in evaluating the quality of vehicle-side remote control service and achieving the technical effect of improving the efficiency of evaluating the quality of vehicle-side remote control service.

[0098] Example 3

[0099] According to an embodiment of the present invention, a full-link quality monitoring device for an Internet of Vehicles is also provided. It should be noted that the full-link quality monitoring device for an Internet of Vehicles can be used to execute the full-link quality monitoring method for an Internet of Vehicles in Example 1.

[0100] Figure 5 Schematic diagram of a full-link quality monitoring device for an Internet of Vehicles according to an embodiment of the present invention. Figure 5 As shown, the full-link quality monitoring device 500 of the Internet of Vehicles may include: a first acquisition unit 502 , a second acquisition unit 504 , a processing unit 506 and a determination unit 508 .

[0101] The first acquisition unit 502 is used to acquire the collected data of each node device among multiple node devices in the whole link of the Internet of Vehicles.

[0102] The second acquisition unit 504 is used to acquire at least one target acquisition data group based on the association relationship between the acquisition data of each node device in the same time period, wherein the target acquisition data group includes the acquisition data of at least one node device in the same time period.

[0103] The processing unit 506 is used to compare the collected data in the target collected data group to obtain a comparison result.

[0104] The determination unit 508 is configured to determine an abnormal node device in the entire link from among the multiple node devices based on the comparison result.

[0105] Optionally, the second acquisition unit 504 may include: a first conversion module, used to convert the collected data to obtain standardized data of each node device, and a first acquisition module, used to acquire at least one target collected data based on the correlation relationship between the standardized data of each node device in the same time period.

[0106] Optionally, the first acquisition module may include: a first sorting submodule, used to sort the standardized data of each node device in chronological order to obtain multiple groups of standardized data groups, wherein the number of standardized data groups is consistent with the number of node devices; a first processing module, used to extract standardized data located in the same time range from the multiple groups of standardized data groups, establish a correlation relationship between the extracted standardized data, and obtain at least one target acquisition data group, wherein the number of target acquisition data groups is the same as the number within the time period.

[0107] Optionally, the determination unit 508 may include: a first determination module, used to determine that a standardized data is abnormal in response to the comparison result that there is a standardized data in the target collection data group that is different from other standardized data; a second determination module, used to determine that the node device is an abnormal node device in response to the node device having a target number of abnormal standardized data.

[0108] Optionally, the device may further include: an output unit, configured to output prompt information in response to the presence of an abnormal node device in the entire link.

[0109] Optionally, the output unit may further include: a second processing module, used to correct the abnormal node device and perform quality detection on the corrected full link; a third processing module, used to stop outputting prompt information in response to each node device being normal within the target time period.

[0110] According to an embodiment of the present invention, the collected data of each node device among multiple node devices in the whole link of the Internet of Vehicles is obtained through the first acquisition unit; based on the correlation relationship between the collected data of each node device in the same time period, at least one target collected data group is obtained through the second acquisition unit, wherein the target collected data group includes the collected data of at least one node device in the same time period; the collected data in the target collected data group is compared by the processing unit to obtain a comparison result; the abnormal node device in the whole link is determined by the determination unit among multiple node devices based on the comparison result, thereby solving the technical problem of poor efficiency in evaluating the quality of vehicle-side remote control service and achieving the technical effect of improving the efficiency of evaluating the quality of vehicle-side remote control service.

[0111] Example 4

[0112] According to an embodiment of the present invention, a computer-readable storage medium is also provided, which includes a stored program, wherein the program executes the full-link quality monitoring method of the Internet of Vehicles described in Example 1.

[0113] Example 5

[0114] According to an embodiment of the present invention, a processor is also provided, which is used to run a program, wherein the program executes the full-link quality monitoring method of the Internet of Vehicles described in Example 1 when running.

[0115] Example 6

[0116] According to an embodiment of the present invention, a vehicle is also provided, which is used to execute the full-link quality monitoring method of the Internet of Vehicles according to an embodiment of the present invention.

[0117] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0118] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0119] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0120] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0121] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0122] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0123] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A full-link quality monitoring method for an Internet of Vehicles, characterized in that: The method comprises: In the full link of the Internet of Vehicles, acquiring collected data of each of the plurality of node devices, wherein the node devices include an application end, a vehicle teleservice provider, an onboard electrical component, and a cloud, and the collected data is used to represent the state information and network information stored in the node devices; Based on the association relationship between the collected data of each of the node devices in the same time period, at least one target collected data group is acquired, wherein the target collected data group includes the collected data of at least one of the node devices in the same time period; Comparing the collected data in the target collected data group to obtain a comparison result; Determining an abnormal node device in the entire link from among the plurality of node devices based on the comparison result; Based on the correlation between the collected data of each of the node devices within the same time period, at least one of the target collected data groups is obtained, including: standardizing the logs corresponding to the collected data to obtain standardized data of each of the node devices; determining the time series of the standardized data, and sorting the standardized data according to the time series; based on the sorted standardized data, at least one of the target collected data groups is obtained.

2. The method according to claim 1, characterized in that Determining a time series of the standardized data and sorting the standardized data according to the time series includes: Sorting the standardized data of each of the node devices in chronological order to obtain a plurality of standardized data groups, wherein the number of the standardized data groups is consistent with the number of the node devices; Based on the sorted standardized data, at least one target acquisition data group is obtained, including: extracting standardized data located in the same time period from multiple groups of standardized data groups, establishing the association relationship between the extracted standardized data, and obtaining at least one target acquisition data group, wherein the number of the target acquisition data groups is the same as the number of the time periods.

3. The method according to claim 2, characterized in that Determining an abnormal node device in the entire link from among the plurality of node devices based on the comparison result includes: In response to the comparison result that there is a standardized data in the target acquisition data group that is different from other standardized data, determining that a standardized data is abnormal; In response to the node device having a target number of abnormal standardized data, the node device is determined to be the abnormal node device.

4. The method according to claim 1, characterized in that The method comprises: In response to the existence of the abnormal node device in the full link, a prompt message is output.

5. The method according to claim 4, characterized in that The method comprises: Correcting the abnormal node device and performing quality detection on the corrected full link; In response to each of the node devices being normal within the target time period, outputting the prompt information is stopped.

6. A full-link quality monitoring device for an Internet of Vehicles, characterized in that: The device comprises: A first acquisition unit is used to acquire collected data of each of the plurality of node devices in the full link of the Internet of Vehicles, wherein the node devices include an application end, a vehicle teleservice provider, an on-board electrical component and a cloud, and the collected data is used to represent the state information and network information stored in the node devices; A second acquisition unit, configured to acquire at least one target acquisition data group based on the association relationship between the acquisition data of each of the node devices in the same time period, wherein the target acquisition data group includes the acquisition data of at least one of the node devices in the same time period; A processing unit, used for comparing the collected data in the target collected data group to obtain a comparison result; A determination unit, configured to determine an abnormal node device in the full link from among the plurality of node devices based on the comparison result; Among them, the second acquisition unit is used to execute the following steps to obtain at least one of the target collection data groups: standardize the logs corresponding to the collection data to obtain standardized data of each of the node devices; determine the time series of the standardized data and sort the standardized data according to the time series; based on the sorted standardized data, obtain at least one of the target collection data groups.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the method according to any one of claims 1 to 5.

8. A processor, characterized in that: The processor is used to run a program, wherein the program executes the method according to any one of claims 1 to 5 when run by the processor.

9. A vehicle, characterized in that: Used to perform the method according to any one of claims 1 to 5.

Images