CN111976632A

CN111976632A - Equipment data processing method based on Internet of things and vehicle-mounted detector

Info

Publication number: CN111976632A
Application number: CN202011009624.1A
Authority: CN
Inventors: 吴金凤
Original assignee: Individual
Current assignee: Individual
Priority date: 2020-01-07
Filing date: 2020-01-07
Publication date: 2020-11-24
Also published as: CN111976633A; CN111252019A; CN111252019B

Abstract

The invention provides an equipment data processing method based on the Internet of things and a vehicle-mounted detector, which can obtain vehicle-mounted detection data which can be directly used for processing and analyzing according to operation data, and ensure the diversity of data sources and the consistency and normalization of data analysis and processing. The identification weight of the vehicle-mounted detection data is determined according to the equipment type identification, so that at least part of all vehicle-mounted equipment is subjected to grouping detection, different target running state detection results under different number of vehicle-mounted equipment scenes are obtained, detection result clusters are formed, and the current running state detection result of the electric vehicle is determined according to the feature vector of the detection result clusters. The running data of all the vehicle-mounted devices can be taken into consideration, and the running states corresponding to different vehicle-mounted device combinations can be detected, so that the comprehensive analysis and the combined analysis of the running data are realized, and the accuracy of the current running state detection result is ensured.

Description

Equipment data processing method based on Internet of things and vehicle-mounted detector

Technical Field

The invention relates to the technical field of Internet of vehicles, in particular to an equipment data processing method based on the Internet of things and a vehicle-mounted detector.

Background

With the development of science and technology, the concept of interconnection of everything is deeply mastered. The technology of the Internet of things provides great convenience for modern production and life, and can effectively improve the production efficiency and the life quality of the modern society. However, the safety of the internet of things is always a problem which cannot be ignored at present.

With the development of the internet of things, most of the privacy information and the security information of the terminal equipment of the internet of things are stored in the equipment of the internet of things, and if the equipment of the internet of things is attacked by hackers, the privacy information and the important information of the terminal equipment of the internet of things can be lost and leaked, so that the security verification of the equipment of the internet of things is very necessary. However, most of the existing methods for performing security verification on the internet of things devices are performed on the basis of a data communication layer, and internet of things terminal device information acquired by the internet of things devices is not comprehensively analyzed and processed, so that the reliability of the security verification is low.

Disclosure of Invention

In order to overcome at least the above disadvantages in the prior art, an object of the present invention is to provide an apparatus data processing method and a vehicle-mounted detector based on the internet of things.

In a first aspect of the embodiments of the present invention, an internet of things-based device data processing method is provided, which is applied to a vehicle-mounted detector, where the vehicle-mounted detector is disposed in an electric vehicle, the vehicle-mounted detector is in communication connection with a plurality of vehicle-mounted devices in the electric vehicle, and the vehicle-mounted devices include: battery management system, braking equipment, door locking equipment, driving record camera equipment, on-vehicle camera equipment and on-vehicle microphone equipment, the method at least includes:

when the electric vehicle is in a running state, collecting operation data collected by each vehicle-mounted device within a set time period; the data structure and the data display mode of the operation data acquired by different vehicle-mounted equipment are different;

for each group of operation data, converting the group of operation data according to a preset data conversion list to obtain vehicle-mounted detection data corresponding to the group of operation data;

determining the identification weight of each piece of vehicle-mounted detection data based on the equipment type identification of the vehicle-mounted equipment corresponding to each piece of vehicle-mounted detection data;

for every N pieces of vehicle-mounted equipment in the plurality of vehicle-mounted equipment, determining a plurality of target running state detection results corresponding to every N pieces of vehicle-mounted equipment according to vehicle-mounted detection data corresponding to every target vehicle-mounted equipment in every N pieces of vehicle-mounted equipment and identification weights corresponding to the vehicle-mounted detection data; wherein N is an integer greater than or equal to 4;

enabling the N to be added and returned, and determining a plurality of target driving state detection results corresponding to each N pieces of vehicle-mounted equipment according to vehicle-mounted detection data corresponding to each target vehicle-mounted equipment in each N pieces of vehicle-mounted equipment and identification weights corresponding to the vehicle-mounted detection data;

when N reaches a set value after adding one, determining a plurality of target running state detection results corresponding to each N pieces of vehicle-mounted equipment according to vehicle-mounted detection data corresponding to each target vehicle-mounted equipment in each N pieces of vehicle-mounted equipment and identification weights corresponding to the vehicle-mounted detection data; the number of the target running state detection results corresponding to different N is different, and the target running state detection results corresponding to different N form different detection result clusters;

and extracting the characteristics of each detection result cluster to obtain a characteristic vector corresponding to each detection result cluster, and determining the current driving state detection result of the electric vehicle according to each obtained characteristic vector.

In an alternative embodiment, the converting, for each set of operation data, the set of operation data according to a preset data conversion list to obtain vehicle-mounted detection data corresponding to the set of operation data includes:

determining the data type of each group of operation data aiming at each group of operation data;

when the data type of the set of operation data is image data, extracting a plurality of identifiable first boundary image blocks and a first relative position of each first boundary image block in the set of operation data from the set of operation data; determining a plurality of boundary image blocks which are the same as the second boundary image block from the plurality of first boundary image blocks to obtain a plurality of third boundary image blocks, wherein the second boundary image block is a reference boundary image block in a reference image in a data conversion list corresponding to the group of operating data, and the reference image comprises: the image coding method comprises the steps of obtaining a plurality of reference boundary image blocks, a second relative position corresponding to each reference boundary image block and image coding data of each reference boundary image, wherein the second relative position is a two-dimensional coordinate value of each reference boundary image block in a reference image; mapping the third relative positions and the second relative positions of the third boundary image blocks to a data conversion list corresponding to the group of operating data to obtain first target data corresponding to each third boundary image block; intercepting a plurality of second target data corresponding to the image coding data of the reference image from the first target data as vehicle-mounted detection data corresponding to the set of operation data; the vehicle-mounted detection data corresponding to the group of running data is binary data;

when the data type of the set of operating data is audio data, determining a digital signal extracted based on the analog signal of the set of operating data; for each segment of the digital signals, determining the proportion of the occurrence times of each segment of the signals in a preset time length based on the first occurrence time of each segment of the signals in the preset time length and the second occurrence time of the digital signals in the preset time length; determining a first signal recurrence frequency of each section of signal between two adjacent preset time lengths according to the proportion of the occurrence times of each section of signal in the two adjacent preset time lengths; determining a second signal recurrence frequency of the digital signal in two adjacent preset time lengths according to the proportion of the occurrence times of each section of signal in two adjacent preset time lengths and the occurrence times of the digital signal in each preset time length; determining whether each signal segment is a valid signal based on the first signal reproduction frequency and the second signal reproduction frequency; for each section of signal, if the section of signal is an effective signal, determining vehicle-mounted detection data corresponding to the section of signal from a data conversion list corresponding to the group of operation data; if the segment signal is an invalid signal, discarding the segment signal;

when the data type of the set of operation data is first numerical data, extracting a three-dimensional coordinate value from the set of operation data; judging whether the three-dimensional coordinate value in the set of operation data is changed relative to the three-dimensional coordinate value in the previous set of operation data of the set of operation data; if so, determining the three-dimensional coordinate value extracted from the set of operation data as a target three-dimensional coordinate value of the set of operation data; otherwise, carrying out weighted sum on the three-dimensional coordinate value extracted from the set of operation data and the three-dimensional coordinate value in the previous set of operation data of the set of operation data, and determining the weighted sum result as the target three-dimensional coordinate value of the set of operation data; carrying out coordinate transformation on the target three-dimensional coordinate value of the set of operation data according to the data conversion list corresponding to the set of operation data to obtain vehicle-mounted detection data corresponding to the set of operation data;

when the data type of the group of operation data is second numerical data, responding to a data transmission protocol of the group of operation data, and sending verification data to the vehicle-mounted equipment corresponding to the group of operation data according to the data transmission protocol; the verification data is added with a first random number which indicates that the vehicle-mounted equipment corresponding to the group of operation data carries out verification calculation according to the identity identification information of the vehicle-mounted equipment, and the first random number is generated in the vehicle-mounted detector; receiving a first verification result obtained by calculating the vehicle-mounted equipment corresponding to the group of running data based on the first random number in the verification data; the first verification result comprises a first character string and a second random number generated by the vehicle-mounted equipment corresponding to the group of running data; analyzing the first check result to obtain the first character string and the second random number, and determining a third random number corresponding to the second random number, wherein the third random number is obtained through a data conversion list corresponding to the group of running data; calculating according to the third random number to obtain a second check result, wherein the second check result comprises a second character string; judging whether the first character string and the second character string are the same; and when the first character string is the same as the second character string, determining that the group of operation data passes data security verification, and converting the group of operation data into vehicle-mounted detection data according to a data conversion list corresponding to the group of operation data.

In an alternative embodiment, the determining, according to the vehicle-mounted detection data corresponding to each target vehicle-mounted device in every N vehicle-mounted devices and the identification weight corresponding to the vehicle-mounted detection data, a plurality of target driving state detection results corresponding to every N vehicle-mounted devices includes:

for each N pieces of vehicle-mounted equipment, determining a corresponding relation between vehicle-mounted detection data of each target vehicle-mounted equipment in each N pieces of vehicle-mounted equipment and identification weight of the vehicle-mounted detection data, wherein the corresponding relation is used for representing the influence degree of the identification weight on the vehicle-mounted detection data, the corresponding relation is represented by a value pair, the value pair comprises a first target value and a second target value, the first target value is used for representing the influence of the weight confidence coefficient of the vehicle-mounted detection data and the identification weight, and the second target data is used for representing the influence of the identification weight on the data accuracy of the vehicle-mounted detection data;

determining a corresponding relation matrix according to all the determined corresponding relations, and determining a driving safety parameter corresponding to the vehicle-mounted detection data of each target vehicle-mounted device and a driving safety weight value corresponding to the identification weight corresponding to the vehicle-mounted detection data of each target vehicle-mounted device according to the corresponding relation matrix; the driving safety parameter is used for representing the driving safety state of the electric vehicle, and the driving safety weight value is used for representing the error of the driving safety state of the electric vehicle;

determining a target driving state vector according to each determined driving safety parameter and a driving safety weight value corresponding to each driving safety parameter; correcting the target driving state vector according to the matching degree between each pair of target vehicle-mounted equipment to obtain a corrected driving state vector; obtaining target driving state detection results corresponding to the N pieces of vehicle-mounted equipment according to the corrected driving state vector; the target state driving vector is used for representing multiple safety index parameters corresponding to the driving state of the electric vehicle, and the matching degree between each pair of target vehicle-mounted equipment is obtained through the data type of the running data corresponding to each pair of target vehicle-mounted equipment.

In an alternative embodiment, the performing feature extraction on each detection result cluster to obtain a feature vector corresponding to each detection result cluster includes:

determining the vector dimension of the characteristic vector corresponding to each detection result cluster;

generating a blank vector according to the vector dimension;

and performing keyword processing on each detection result cluster to obtain a keyword processing result, and filling the blank vector according to the keyword processing result to obtain a feature vector corresponding to each detection result cluster.

In an alternative embodiment, the determining a current driving state detection result of the electric vehicle according to each obtained feature vector includes:

judging whether the vector dimension of each feature vector is the same;

when the vector dimensions of each feature vector are different, determining the median of the vector dimensions in all the feature vectors;

determining the vector dimension corresponding to the median as a reference dimension, and adjusting the vector dimension of the feature vector corresponding to the vector dimension different from the reference dimension to obtain an adjusted target feature vector;

determining the target feature vector and the feature vector corresponding to the median as a vector to be processed; determining a target setting vector with the minimum vector distance between each vector to be processed and the vector to be processed in a set of setting vectors for each vector to be processed;

determining the number of target vectors to be processed with the minimum vector distance corresponding to each target setting vector; determining a first running state of the electric vehicle in a running state corresponding to each target setting vector according to the number of the target vectors to be processed with the minimum vector distance corresponding to each target setting vector;

weighting the determined plurality of first driving states to obtain a second driving state, and determining a current driving state detection result of the electric vehicle according to the second driving state.

In a second aspect of the embodiments of the present invention, there is provided an on-board detector disposed in an electric vehicle, the on-board detector being communicatively connected to a plurality of on-board devices in the electric vehicle, the on-board devices including: battery management system, braking equipment, door locking equipment, driving record camera equipment, on-vehicle camera equipment and on-vehicle microphone equipment, on-vehicle detector includes at least:

the collecting module is used for collecting the running data collected by each vehicle-mounted device within a set time period when the electric vehicle is in a running state; the data structure and the data display mode of the operation data acquired by different vehicle-mounted equipment are different;

the conversion module is used for converting each group of operation data according to a preset data conversion list to obtain vehicle-mounted detection data corresponding to the group of operation data;

the determining module is used for determining the identification weight of each piece of vehicle-mounted detection data based on the equipment type identification of the vehicle-mounted equipment corresponding to each piece of vehicle-mounted detection data;

the circulation module is used for determining a plurality of target running state detection results corresponding to each N pieces of vehicle-mounted equipment according to vehicle-mounted detection data corresponding to each target vehicle-mounted equipment in each N pieces of vehicle-mounted equipment and identification weight corresponding to the vehicle-mounted detection data; wherein N is an integer greater than or equal to 4; enabling the N to be added and returned, and determining a plurality of target driving state detection results corresponding to each N pieces of vehicle-mounted equipment according to vehicle-mounted detection data corresponding to each target vehicle-mounted equipment in each N pieces of vehicle-mounted equipment and identification weights corresponding to the vehicle-mounted detection data; when N reaches a set value after adding one, determining a plurality of target running state detection results corresponding to each N pieces of vehicle-mounted equipment according to vehicle-mounted detection data corresponding to each target vehicle-mounted equipment in each N pieces of vehicle-mounted equipment and identification weights corresponding to the vehicle-mounted detection data; the number of the target running state detection results corresponding to different N is different, and the target running state detection results corresponding to different N form different detection result clusters;

and the extraction module is used for extracting the characteristics of each detection result cluster to obtain a characteristic vector corresponding to each detection result cluster, and determining the current driving state detection result of the electric vehicle according to each obtained characteristic vector.

In an alternative embodiment, the conversion module is configured to:

In a third aspect of the embodiments of the present invention, a vehicle-mounted detector is provided, including a processor, and a memory and a bus connected to the processor; wherein, the processor and the memory complete mutual communication through the bus; the processor is used for calling the program instructions in the memory so as to execute the data processing method of the equipment based on the Internet of things.

In a fourth aspect of the embodiments of the present invention, a readable storage medium is provided, where a program is stored, and when the program is executed by a processor, the method for processing data of an internet-of-things-based device is implemented.

In a fifth aspect of the embodiments of the present invention, there is provided an on-vehicle detection system, including an on-vehicle detector and a plurality of on-vehicle devices, where the on-vehicle detector and the plurality of on-vehicle devices are disposed in an electric vehicle, the on-vehicle detector is in communication connection with the plurality of on-vehicle devices, and the on-vehicle devices include: the system comprises a battery management system, a brake device, a vehicle door locking device, a driving record camera device, a vehicle-mounted camera device and a vehicle-mounted microphone device;

the vehicle-mounted equipment is used for collecting the running data of the electric vehicle when the electric vehicle is in a running state; the data structure and the data display mode of the operation data acquired by different vehicle-mounted equipment are different;

the vehicle-mounted detector is used for collecting operation data collected by each vehicle-mounted device within a set time period; for each group of operation data, converting the group of operation data according to a preset data conversion list to obtain vehicle-mounted detection data corresponding to the group of operation data; determining the identification weight of each piece of vehicle-mounted detection data based on the equipment type identification of the vehicle-mounted equipment corresponding to each piece of vehicle-mounted detection data; for every N pieces of vehicle-mounted equipment in the plurality of vehicle-mounted equipment, determining a plurality of target running state detection results corresponding to every N pieces of vehicle-mounted equipment according to vehicle-mounted detection data corresponding to every target vehicle-mounted equipment in every N pieces of vehicle-mounted equipment and identification weights corresponding to the vehicle-mounted detection data; wherein N is an integer greater than or equal to 4; enabling the N to be added and returned, and determining a plurality of target driving state detection results corresponding to each N pieces of vehicle-mounted equipment according to vehicle-mounted detection data corresponding to each target vehicle-mounted equipment in each N pieces of vehicle-mounted equipment and identification weights corresponding to the vehicle-mounted detection data; when N reaches a set value after adding one, determining a plurality of target running state detection results corresponding to each N pieces of vehicle-mounted equipment according to vehicle-mounted detection data corresponding to each target vehicle-mounted equipment in each N pieces of vehicle-mounted equipment and identification weights corresponding to the vehicle-mounted detection data; the number of the target running state detection results corresponding to different N is different, and the target running state detection results corresponding to different N form different detection result clusters; and extracting the characteristics of each detection result cluster to obtain a characteristic vector corresponding to each detection result cluster, and determining the current driving state detection result of the electric vehicle according to each obtained characteristic vector.

According to the equipment data processing method and the vehicle-mounted detector based on the Internet of things, provided by the embodiment of the invention, the operation data collected by each vehicle-mounted equipment can be collected, and each group of operation data is converted to obtain vehicle-mounted detection data which can be directly used for processing and analyzing, so that the diversity of data sources and the consistency and the normalization of data analysis and processing are ensured. In addition, the identification weight of the vehicle-mounted detection data can be determined according to the equipment type identification of the vehicle-mounted equipment corresponding to the vehicle-mounted detection data, so that at least part of the vehicle-mounted equipment in all the vehicle-mounted equipment is subjected to hierarchical detection according to the vehicle-mounted detection data and the identification weight, different target running state detection results under different number of vehicle-mounted equipment scenes are obtained, detection result clusters are formed according to the different target running state detection results, and the current running state detection result of the electric vehicle is determined according to the extracted feature vector of the detection result clusters. Therefore, the running data of all the vehicle-mounted devices can be taken into consideration, and the running states corresponding to different vehicle-mounted device combinations can be detected, so that comprehensive analysis and combined analysis of the running data are realized, and the accuracy of the determined current running state detection result of the electric vehicle is ensured.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.

Fig. 1 is a communication connection block diagram of a vehicle-mounted detection system according to an embodiment of the present invention.

Fig. 2 is a flowchart of an apparatus data processing method based on the internet of things according to an embodiment of the present invention.

Fig. 3 is a block diagram of a vehicle detector according to an embodiment of the present invention.

Fig. 4 is a block diagram of a vehicle detector according to an embodiment of the present invention.

Icon:

100-vehicle mounted detection system;

200-a vehicle-mounted device;

300-a vehicle detector; 3011-a collection module; 3012-a conversion module; 3013-determining a module; 3014-a cycle module; 3015-an extraction module; 3021-a processor; 3022-memory; 3023-bus.

Detailed Description

Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

The embodiment of the invention provides an equipment data processing method based on the Internet of things and a vehicle-mounted detector, which are used for solving the technical problem that the running state of an electric vehicle is difficult to accurately determine by the existing electric vehicle running state detection method.

In order to better understand the technical solutions of the present invention, the following detailed descriptions of the technical solutions of the present invention are provided with the accompanying drawings and the specific embodiments, and it should be understood that the specific features in the embodiments and the examples of the present invention are the detailed descriptions of the technical solutions of the present invention, and are not limitations of the technical solutions of the present invention, and the technical features in the embodiments and the examples of the present invention may be combined with each other without conflict.

Fig. 1 is a communication connection block diagram of a vehicle-mounted detection system 100 according to an embodiment of the present invention. As can be seen, the in-vehicle detection system 100 includes an in-vehicle detector 300 and a plurality of in-vehicle devices 200. Alternatively, the vehicle-mounted detector 300 and the plurality of vehicle-mounted devices 200 are disposed in an electric vehicle, the vehicle-mounted detector 300 is communicatively connected to the plurality of vehicle-mounted devices 200, and the vehicle-mounted device 200 includes: the vehicle-mounted camera device comprises a battery management system, a brake device, a vehicle door locking device, a driving record camera device, a vehicle-mounted camera device and a vehicle-mounted microphone device.

Referring to fig. 2, a flowchart of an internet-of-things-based device data processing method according to an embodiment of the present invention is applied to the vehicle-mounted detector 300 in fig. 1, and the method may include the following steps:

and step S21, collecting the operation data collected by each vehicle-mounted device in a set time period when the electric vehicle is in a running state.

And step S22, converting each group of operation data according to a preset data conversion list to obtain vehicle-mounted detection data corresponding to the group of operation data.

In step S23, an identification weight of each piece of vehicle-mounted detection data is determined based on the device type identification of the vehicle-mounted device corresponding to each piece of vehicle-mounted detection data.

Step S24, for every N pieces of the plurality of vehicle-mounted devices, determining a plurality of target driving state detection results corresponding to every N pieces of the vehicle-mounted devices according to the vehicle-mounted detection data corresponding to each target vehicle-mounted device in every N pieces of the vehicle-mounted devices and the identification weight corresponding to the vehicle-mounted detection data.

Step S25 is performed to self-add N and return a plurality of target driving state detection results determined for each N vehicle-mounted devices based on the vehicle-mounted detection data corresponding to each target vehicle-mounted device of each N vehicle-mounted devices and the identification weight corresponding to the vehicle-mounted detection data.

Step S26, when N reaches the set value after adding one, determining a plurality of target driving state detection results corresponding to each N pieces of vehicle-mounted equipment according to the vehicle-mounted detection data corresponding to each target vehicle-mounted equipment in each N pieces of vehicle-mounted equipment and the identification weight corresponding to the vehicle-mounted detection data.

And step S27, extracting the characteristics of each detection result cluster to obtain a characteristic vector corresponding to each detection result cluster, and determining the current driving state detection result of the electric vehicle according to each obtained characteristic vector.

In step S21, the operation data collected by different in-vehicle devices differ in data structure and data presentation manner.

In step S24, N is an integer of 4 or more.

In step S26, the number of the target running state detection results for different N is different, and the target running state detection results for different N form different detection result clusters.

In the present embodiment, the setting period may be adjusted according to the speed of the electric vehicle, for example, if the speed of the electric vehicle is too fast, a shorter setting period, for example, 5 minutes or 10 minutes, may be selected. For another example, if the speed of the electric vehicle is slow, a longer setting period, such as 20 minutes or 30 minutes or even longer, may be selected, and is not limited herein.

In this embodiment, the data structures and data display modes of the operation data collected by different vehicle-mounted devices are different.

For example, the operation data collected by the battery management system may be the operation state parameters (battery temperature, remaining capacity percentage, power-down rate, etc.) of the power battery.

For another example, the brake device may acquire the angular velocity of the brake lever via a built-in angular velocity sensor, and the door locking device may determine the position data of the door locking buckle via a built-in position sensor.

For another example, the driving record camera device may collect images around the electric vehicle during driving of the electric vehicle, and the vehicle-mounted camera device may collect images inside the electric vehicle, and optionally, may collect a facial image of the driver in a centralized manner. And the vehicle-mounted microphone device can collect voice information input by the driver.

It can be understood that the operation data acquired by the on-board detector can reflect the driving state of the electric vehicle from multiple dimensions.

In this embodiment, the data conversion list is used to convert the data structures and data display modes corresponding to different operation data into a target data structure and a target data display mode that can be processed by the vehicle-mounted detector in a unified manner. Optionally, the vehicle-mounted detector may convert different operation data through the data conversion list, so as to obtain vehicle-mounted detection data that can be directly used and processed by the vehicle-mounted detector.

In this embodiment, the device class identifier may be assigned according to the usage of different vehicle-mounted devices. The value can be assigned through the numerical identifier, and the value can also be assigned through the primary and secondary identifiers, which is not limited herein.

In this embodiment, the identification weight is used to represent the importance degree of the vehicle-mounted detection data, and the value interval of the identification weight is [0, 1], which can be understood that the greater the identification weight is, the greater the importance degree of the vehicle-mounted detection data is. For example, the identification weight of the in-vehicle detection data (related to the power battery) corresponding to the battery management system may be 0.9, and the identification weight of the in-vehicle detection data corresponding to the door locking device may be 0.4, so that it can be seen that the importance degree of the in-vehicle detection data corresponding to the battery management system is greater than that of the in-vehicle detection data corresponding to the door locking device.

In this embodiment, the target driving state result may be presented in a hierarchical form, for example, the target driving state result may include a plurality of levels:

in the first level, the driving state of the electric vehicle is good.

And (3) second grade: the running state of the electric vehicle is abnormal.

And a third stage: the running state of the electric vehicle has slight faults.

Fourth stage: the running state of the electric vehicle has serious faults.

And a fifth level: the driving state of the electric vehicle is dangerous.

In the present embodiment, the set value may be the total number of the in-vehicle devices, for example, if the total number of the in-vehicle devices in the present embodiment is 6, the set value may be 6.

It can be understood that when N is 4, it is necessary to determine a plurality of target driving state detection results corresponding to each N vehicle-mounted devices for each on-board detection data corresponding to each target vehicle-mounted device in each 4 vehicle-mounted devices in the 6 vehicle-mounted devices and the identification weight corresponding to the on-board detection data.

In detail, for convenience of explanation, the battery management system, the brake apparatus, the door lock apparatus, the event-recording camera apparatus, the in-vehicle camera apparatus, and the in-vehicle microphone apparatus are denoted by X1, X2, X3, X4, X5, and X6, respectively.

When N is 4, taking X1, X2, X3, and X4 as examples, the target driving state detection results corresponding to X1, X2, X3, and X4 can be determined, and taking X1, X2, X3, and X5 as examples, the target driving state detection results corresponding to X1, X2, X3, and X5 can be determined, so that a plurality of target driving state detection results are determined when N is 4, and for example, the target driving state detection results determined when N is 4 can be regarded as a.

For another example, when N is 5, the number of corresponding target driving state detection results may be B, where B is a positive integer.

For another example, when N is 6, the corresponding target driving state detection results may be C, where C is a positive integer.

Accordingly, the a target running state detection results, the B target running state detection results, and the C target running state detection results may be clustered as three detection results, respectively.

In this embodiment, the feature vector may be used to represent a driving state parameter of the electric vehicle corresponding to each detection result cluster, such as a vehicle speed, a vehicle condition, a road condition, a driver fatigue degree, and the like, which is not limited herein.

It can be understood that through steps S21-S27, the operation data collected by each vehicle-mounted device can be collected, and each set of operation data is converted into vehicle-mounted detection data which can be directly used for processing and analysis, so that the diversity of data sources and the consistency and normalization of data analysis and processing are ensured. In addition, the identification weight of the vehicle-mounted detection data can be determined according to the equipment type identification of the vehicle-mounted equipment corresponding to the vehicle-mounted detection data, so that at least part of the vehicle-mounted equipment in all the vehicle-mounted equipment is subjected to hierarchical detection according to the vehicle-mounted detection data and the identification weight, different target running state detection results under different number of vehicle-mounted equipment scenes are obtained, detection result clusters are formed according to the different target running state detection results, and the current running state detection result of the electric vehicle is determined according to the extracted feature vector of the detection result clusters. Therefore, the running data of all the vehicle-mounted devices can be taken into consideration, and the running states corresponding to different vehicle-mounted device combinations can be detected, so that comprehensive analysis and combined analysis of the running data are realized, and the accuracy of the determined current running state detection result of the electric vehicle is ensured.

In a specific implementation, the data structure and the data display manner of the operation data corresponding to each vehicle-mounted device are different, and how to convert the operation data into vehicle-mounted detection data that can be directly processed and used by the vehicle-mounted detector without error requires specific analysis on each type of operation data, for this reason, in step S22, for each set of operation data, the set of operation data is converted according to a preset data conversion list to obtain the vehicle-mounted detection data corresponding to the set of operation data, which may specifically include the following contents:

step S221, for each set of operation data, determining a data type of the set of operation data.

Step S222, when the data type of the set of operation data is image data, extracting a plurality of identifiable first boundary image blocks and a first relative position of each first boundary image block in the set of operation data from the set of operation data; determining a plurality of boundary image blocks which are the same as the second boundary image block from the plurality of first boundary image blocks to obtain a plurality of third boundary image blocks, wherein the second boundary image block is a reference boundary image block in a reference image in a data conversion list corresponding to the group of operating data, and the reference image comprises: the image coding method comprises the steps of obtaining a plurality of reference boundary image blocks, a second relative position corresponding to each reference boundary image block and image coding data of each reference boundary image, wherein the second relative position is a two-dimensional coordinate value of each reference boundary image block in a reference image; mapping the third relative positions and the second relative positions of the third boundary image blocks to a data conversion list corresponding to the group of operating data to obtain first target data corresponding to each third boundary image block; intercepting a plurality of second target data corresponding to the image coding data of the reference image from the first target data as vehicle-mounted detection data corresponding to the set of operation data; and the vehicle-mounted detection data corresponding to the group of running data is binary data.

Step S223 of determining a digital signal extracted based on the analog signal of the set of operation data when the data type of the set of operation data is audio data; for each segment of the digital signals, determining the proportion of the occurrence times of each segment of the signals in a preset time length based on the first occurrence time of each segment of the signals in the preset time length and the second occurrence time of the digital signals in the preset time length; determining a first signal recurrence frequency of each section of signal between two adjacent preset time lengths according to the proportion of the occurrence times of each section of signal in the two adjacent preset time lengths; determining a second signal recurrence frequency of the digital signal in two adjacent preset time lengths according to the proportion of the occurrence times of each section of signal in two adjacent preset time lengths and the occurrence times of the digital signal in each preset time length; determining whether each signal segment is a valid signal based on the first signal reproduction frequency and the second signal reproduction frequency; for each section of signal, if the section of signal is an effective signal, determining vehicle-mounted detection data corresponding to the section of signal from a data conversion list corresponding to the group of operation data; if the segment signal is an invalid signal, the segment signal is discarded.

Step S224, when the data type of the set of operation data is the first numerical data, extracting a three-dimensional coordinate value from the set of operation data; judging whether the three-dimensional coordinate value in the set of operation data is changed relative to the three-dimensional coordinate value in the previous set of operation data of the set of operation data; if so, determining the three-dimensional coordinate value extracted from the set of operation data as a target three-dimensional coordinate value of the set of operation data; otherwise, carrying out weighted sum on the three-dimensional coordinate value extracted from the set of operation data and the three-dimensional coordinate value in the previous set of operation data of the set of operation data, and determining the weighted sum result as the target three-dimensional coordinate value of the set of operation data; and carrying out coordinate transformation on the target three-dimensional coordinate value of the set of operation data according to the data conversion list corresponding to the set of operation data to obtain vehicle-mounted detection data corresponding to the set of operation data.

Step S225, when the data type of the group of operation data is the second numerical data, responding to the data transmission protocol of the group of operation data, and sending verification data to the vehicle-mounted equipment corresponding to the group of operation data according to the data transmission protocol; the verification data is added with a first random number which indicates that the vehicle-mounted equipment corresponding to the group of operation data carries out verification calculation according to the identity identification information of the vehicle-mounted equipment, and the first random number is generated in the vehicle-mounted detector; receiving a first verification result obtained by calculating the vehicle-mounted equipment corresponding to the group of running data based on the first random number in the verification data; the first verification result comprises a first character string and a second random number generated by the vehicle-mounted equipment corresponding to the group of running data; analyzing the first check result to obtain the first character string and the second random number, and determining a third random number corresponding to the second random number, wherein the third random number is obtained through a data conversion list corresponding to the group of running data; calculating according to the third random number to obtain a second check result, wherein the second check result comprises a second character string; judging whether the first character string and the second character string are the same; and when the first character string is the same as the second character string, determining that the group of operation data passes data security verification, and converting the group of operation data into vehicle-mounted detection data according to a data conversion list corresponding to the group of operation data.

In this embodiment, the boundary image block may be an image block in which gray scale values in the image data have significant changes, for example, if a difference between a maximum value and a minimum value of the gray scale values in a certain image block exceeds a preset gray scale value, the image block may be determined to be the boundary image block. In this embodiment, the preset gray-level value may be selected according to actual situations, and is not limited herein.

In this embodiment, image partitioning may be performed on the image data with one vertex of the image data as an origin to obtain a plurality of image blocks, and a relative position coordinate value is assigned to each image block. It is understood that the relative position may be a two-dimensional coordinate value.

In this embodiment, the first numerical data may be position data corresponding to the brake device and the door lock device, and the first numerical data may be a three-dimensional coordinate value that can be determined in a vehicle coordinate system of the electric vehicle.

In this embodiment, the second numerical data may be one-dimensional data such as battery temperature data, percentage of remaining power, or voltage fluctuation collected by the battery management system.

It can be understood that, through steps S221 to S225, the data types of the operation data can be classified according to different types of the vehicle-mounted device, so as to obtain four data types of image data, audio data, first numerical data and second numerical data, and the operation data is analyzed and processed according to different data types, so as to obtain binary data corresponding to each set of operation data, so that each type of operation data can be specifically analyzed, and thus, from the viewpoints of data conversion, data safety, data validity and the like, the operation data can be completely and unmistakably converted into vehicle-mounted detection data which can be directly processed and used by a vehicle-mounted detector.

In order to ensure complete, comprehensive and comprehensive analysis of the driving state of the electric vehicle, it is necessary to determine driving state detection results corresponding to different combinations of vehicle-mounted devices, so as to provide a multi-aspect data basis for subsequently determining the current driving state detection result, for this reason, in step S24, the determining a plurality of target driving state detection results corresponding to each N vehicle-mounted devices according to vehicle-mounted detection data corresponding to each target vehicle-mounted device in each N vehicle-mounted device and identification weights corresponding to the vehicle-mounted detection data may specifically include the following:

and for each N pieces of vehicle-mounted equipment, determining a corresponding relation between vehicle-mounted detection data of each target vehicle-mounted equipment in each N pieces of vehicle-mounted equipment and identification weight of the vehicle-mounted detection data, wherein the corresponding relation is used for representing the influence degree of the identification weight on the vehicle-mounted detection data, the corresponding relation is represented by a value pair, the value pair comprises a first target value and a second target value, the first target value is used for representing the influence of the weight confidence coefficient of the vehicle-mounted detection data and the identification weight, and the second target data is used for representing the influence of the identification weight on the data accuracy of the vehicle-mounted detection data. Determining a corresponding relation matrix according to all the determined corresponding relations, and determining a driving safety parameter corresponding to the vehicle-mounted detection data of each target vehicle-mounted device and a driving safety weight value corresponding to the identification weight corresponding to the vehicle-mounted detection data of each target vehicle-mounted device according to the corresponding relation matrix; the driving safety parameter is used for representing the driving safety state of the electric vehicle, and the driving safety weight value is used for representing the error of the driving safety state of the electric vehicle. Determining a target driving state vector according to each determined driving safety parameter and a driving safety weight value corresponding to each driving safety parameter; correcting the target driving state vector according to the matching degree between each pair of target vehicle-mounted equipment to obtain a corrected driving state vector; obtaining target driving state detection results corresponding to the N pieces of vehicle-mounted equipment according to the corrected driving state vector; the target state driving vector is used for representing multiple safety index parameters corresponding to the driving state of the electric vehicle, and the matching degree between each pair of target vehicle-mounted equipment is obtained through the data type of the running data corresponding to each pair of target vehicle-mounted equipment.

It can be understood that through the above, the driving state detection results corresponding to different vehicle-mounted device combinations can be determined, so as to provide a multi-aspect data basis for subsequently determining the current driving state detection result.

In specific implementation, in order to improve timeliness of determining the current driving state detection result of the electric vehicle, it is required to quickly and accurately determine the feature vector of the detection result cluster, and in step S27, the feature extraction is performed on each detection result cluster to obtain the feature vector corresponding to each detection result cluster, which may specifically include the following contents:

and determining the vector dimension of the characteristic vector corresponding to each detection result cluster. And generating a blank vector according to the vector dimension. And performing keyword processing on each detection result cluster to obtain a keyword processing result, and filling the blank vector according to the keyword processing result to obtain a feature vector corresponding to each detection result cluster.

Further, the above-mentioned content may specifically include the following detailed steps:

and determining the number of the target driving state detection results in the detection result cluster aiming at each detection result cluster, and determining the vector dimension of the characteristic vector corresponding to the detection result cluster according to the determined number of the target driving state detection results in the detection result cluster.

And generating a blank vector with a target dimension according to the determined vector dimension.

Extracting keywords from the detection result texts with the same keywords in the detection result clusters, and classifying all the extracted keywords according to the lengths of the keywords to obtain a plurality of keyword groups; aiming at each keyword group, determining the equipment type of the vehicle-mounted equipment corresponding to the vehicle-mounted detection data corresponding to the keyword group, and numbering the keyword group according to the equipment type; sequencing all the keyword groups according to the serial number of each keyword group to obtain a sequencing sequence; determining a word vector distance between every two keywords in each keyword group in the sequencing sequence and determining a vector value of each keyword group according to all determined word vector distances; adding the vector value of each keyword group into the blank vector according to the sequence of the sequencing sequence to obtain a characteristic vector corresponding to the detection result cluster; wherein the maximum value of the number is the same as the value of the target dimension.

In this embodiment, the keywords may be represented by binary values.

Through the content, the keyword extraction, grouping, numbering, sequencing and vector value determination can be accurately and quickly carried out on each detection result cluster, so that the characteristic vector of the detection result cluster can be accurately and quickly determined, and the timeliness of determining the current driving state detection result of the electric vehicle is improved.

In a specific implementation, in order to ensure the accuracy of the current driving state detection result, in step S27, the determining the current driving state detection result of the electric vehicle according to each obtained feature vector may specifically include the following:

and judging whether the vector dimension of each feature vector is the same.

And when the vector dimension of each feature vector is different, determining the median of the vector dimensions in all the feature vectors.

And determining the vector dimension corresponding to the median as a reference dimension, and adjusting the vector dimension of the feature vector corresponding to the vector dimension different from the reference dimension to obtain an adjusted target feature vector.

Determining the target feature vector and the feature vector corresponding to the median as a vector to be processed; and determining a target setting vector with the minimum vector distance existing between the target setting vector and the vector to be processed in the set of setting vectors for each vector to be processed.

Determining the number of target vectors to be processed with the minimum vector distance corresponding to each target setting vector; and determining a first running state of the electric vehicle in the running state corresponding to each target setting vector according to the number of the target vectors to be processed with the minimum vector distance corresponding to each target setting vector.

In this embodiment, the set of setting vectors includes a plurality of setting vectors of the electric vehicle in a safe driving state, and the vector dimension of each setting vector is the same.

In the present embodiment, the vector dimension between each vector to be processed and each setting vector is also the same.

In this embodiment, weighting the determined plurality of first driving states to obtain a second driving state may specifically include the following:

and according to the determined time of the target setting vector corresponding to the first running state, distributing a weighted weight to each first running state.

In the present embodiment, in order to ensure the real-time property of the current traveling state detection result, the weighting weight assigned to the first traveling state at the farther timing is determined to be smaller.

For example, the first driving state includes three: a running state t1, a running state t2 and a running state t 3.

Accordingly, the determination times of the target setting vectors corresponding to the driving state z1, the driving state z2, and the driving state z3 are time1, time2, and time3, respectively, and time1 is earlier than time2, and time2 is earlier than time 3.

In the above case, the weighting weight q1 corresponding to the running state t1 is smaller than the weighting weight q2 corresponding to the running state t2, and the weighting weight q2 corresponding to the running state t2 is smaller than the weighting weight corresponding to the running state t 3.

In this way, when determining the current driving state detection result, the first driving state close to the current moment can be considered in an important manner, so that the real-time performance and the accuracy of the current driving state detection result are ensured.

Therefore, the real-time performance and the accuracy of the current driving state detection result can be ensured through the above contents.

On the basis, please refer to fig. 3 in combination, an embodiment of the invention provides a vehicle-mounted detector 300, where the vehicle-mounted detector 300 includes:

the collecting module 3011 is configured to collect operation data, collected by each vehicle-mounted device, in a set time period when the electric vehicle is in a driving state; the data structure and the data display mode of the operation data collected by different vehicle-mounted devices are different.

The conversion module 3012 is configured to convert, according to a preset data conversion list, each set of operating data to obtain vehicle-mounted detection data corresponding to the set of operating data.

The determining module 3013 is configured to determine an identification weight of each piece of vehicle-mounted detection data based on a device class identification of the vehicle-mounted device corresponding to each piece of vehicle-mounted detection data.

A loop module 3014, configured to determine, for every N pieces of vehicle-mounted devices in the plurality of vehicle-mounted devices, a plurality of target driving state detection results corresponding to every N pieces of vehicle-mounted devices according to vehicle-mounted detection data corresponding to each target vehicle-mounted device in every N pieces of vehicle-mounted devices and identification weights corresponding to the vehicle-mounted detection data; wherein N is an integer greater than or equal to 4; enabling the N to be added and returned, and determining a plurality of target driving state detection results corresponding to each N pieces of vehicle-mounted equipment according to vehicle-mounted detection data corresponding to each target vehicle-mounted equipment in each N pieces of vehicle-mounted equipment and identification weights corresponding to the vehicle-mounted detection data; when N reaches a set value after adding one, determining a plurality of target running state detection results corresponding to each N pieces of vehicle-mounted equipment according to vehicle-mounted detection data corresponding to each target vehicle-mounted equipment in each N pieces of vehicle-mounted equipment and identification weights corresponding to the vehicle-mounted detection data; the number of the target running state detection results corresponding to different N is different, and the target running state detection results corresponding to different N form different detection result clusters.

The extracting module 3015 is configured to perform feature extraction on each detection result cluster to obtain a feature vector corresponding to each detection result cluster, and determine a current driving state detection result of the electric vehicle according to each obtained feature vector.

In an alternative embodiment, the conversion module 3012 is configured to:

and determining the data type of each group of operation data aiming at each group of operation data.

When the data type of the set of operation data is image data, extracting a plurality of identifiable first boundary image blocks and a first relative position of each first boundary image block in the set of operation data from the set of operation data; determining a plurality of boundary image blocks which are the same as the second boundary image block from the plurality of first boundary image blocks to obtain a plurality of third boundary image blocks, wherein the second boundary image block is a reference boundary image block in a reference image in a data conversion list corresponding to the group of operating data, and the reference image comprises: the image coding method comprises the steps of obtaining a plurality of reference boundary image blocks, a second relative position corresponding to each reference boundary image block and image coding data of each reference boundary image, wherein the second relative position is a two-dimensional coordinate value of each reference boundary image block in a reference image; mapping the third relative positions and the second relative positions of the third boundary image blocks to a data conversion list corresponding to the group of operating data to obtain first target data corresponding to each third boundary image block; intercepting a plurality of second target data corresponding to the image coding data of the reference image from the first target data as vehicle-mounted detection data corresponding to the set of operation data; and the vehicle-mounted detection data corresponding to the group of running data is binary data.

When the data type of the set of operating data is audio data, determining a digital signal extracted based on the analog signal of the set of operating data; for each segment of the digital signals, determining the proportion of the occurrence times of each segment of the signals in a preset time length based on the first occurrence time of each segment of the signals in the preset time length and the second occurrence time of the digital signals in the preset time length; determining a first signal recurrence frequency of each section of signal between two adjacent preset time lengths according to the proportion of the occurrence times of each section of signal in the two adjacent preset time lengths; determining a second signal recurrence frequency of the digital signal in two adjacent preset time lengths according to the proportion of the occurrence times of each section of signal in two adjacent preset time lengths and the occurrence times of the digital signal in each preset time length; determining whether each signal segment is a valid signal based on the first signal reproduction frequency and the second signal reproduction frequency; for each section of signal, if the section of signal is an effective signal, determining vehicle-mounted detection data corresponding to the section of signal from a data conversion list corresponding to the group of operation data; if the segment signal is an invalid signal, the segment signal is discarded.

When the data type of the set of operation data is first numerical data, extracting a three-dimensional coordinate value from the set of operation data; judging whether the three-dimensional coordinate value in the set of operation data is changed relative to the three-dimensional coordinate value in the previous set of operation data of the set of operation data; if so, determining the three-dimensional coordinate value extracted from the set of operation data as a target three-dimensional coordinate value of the set of operation data; otherwise, carrying out weighted sum on the three-dimensional coordinate value extracted from the set of operation data and the three-dimensional coordinate value in the previous set of operation data of the set of operation data, and determining the weighted sum result as the target three-dimensional coordinate value of the set of operation data; and carrying out coordinate transformation on the target three-dimensional coordinate value of the set of operation data according to the data conversion list corresponding to the set of operation data to obtain vehicle-mounted detection data corresponding to the set of operation data.

In an alternative embodiment, the cycle module 3014 is configured to:

In an alternative embodiment, the extracting module 3015 is configured to:

generating a blank vector according to the vector dimension;

In an alternative embodiment, the extracting module 3015 is configured to:

judging whether the vector dimension of each feature vector is the same;

The vehicle-mounted detector comprises a processor and a memory, wherein each functional module and the like in the vehicle-mounted detector are stored in the memory as a program unit, and the processor executes the program unit stored in the memory to realize corresponding functions.

The processor comprises a kernel, and the kernel calls the corresponding program unit from the memory. The kernel can be set to be one or more than one, and the accuracy of the determined current driving state detection result of the electric vehicle is ensured by adjusting the kernel.

The embodiment of the invention provides a readable storage medium, wherein a program is stored on the readable storage medium, and the program realizes the equipment data processing method based on the Internet of things when being executed by a processor.

The embodiment of the invention provides a processor, which is used for running a program, wherein the method for processing the equipment data based on the Internet of things is executed when the program runs.

In the present embodiment, as shown in fig. 4, the in-vehicle detector 300 includes at least one processor 3021, and at least one memory 3022 connected to the processor 3021, a bus; the processor 3021 and the memory 3022 are in communication with each other via a bus 3023; processor 3021 is configured to call program instructions in memory 3022 to implement the in-vehicle detection system described above. The in-vehicle detector 300 herein may be a PC, PAD, cell phone, etc.

In the present embodiment, the method for processing the device data based on the internet of things performed by the in-vehicle detection system 100 is similar to the method for processing the device data based on the internet of things performed by the in-vehicle detector 100, and therefore will not be further described here.

It should be understood that the method for processing device data based on the internet of things may also be applied to other fields of devices of the internet of things, such as smart factories, smart cities, and smart appliances, and when the method is applied to these fields, the corresponding specific data in the method may be adjusted according to the actual field, but the detection logic may be easy to use.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, in-vehicle detectors (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing vehicle mounted detector to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing vehicle mounted detector, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In a typical configuration, the in-vehicle detector includes one or more processors (CPUs), memory, and a bus. The in-vehicle detector may also include an input/output interface, a network interface, and the like.

The memory may include volatile memory in a computer readable medium, Random Access Memory (RAM) and/or nonvolatile memory such as Read Only Memory (ROM) or flash memory (flash RAM), and the memory includes at least one memory chip. The memory is an example of a computer-readable medium.

Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape storage or other magnetic storage vehicle mounted detectors, or any other non-transmission medium that can be used to store information that can be accessed by a computer vehicle mounted detector. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or vehicle-mounted detector that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or vehicle-mounted detector. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or vehicle-mounted detector that comprises the element.

As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The above are merely examples of the present application and are not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. The device data processing method based on the Internet of things is applied to a vehicle-mounted detector, the vehicle-mounted detector is arranged in an electric vehicle, the vehicle-mounted detector is in communication connection with a plurality of vehicle-mounted devices in the electric vehicle, and the vehicle-mounted devices comprise: battery management system, braking equipment, door locking equipment, driving record camera equipment, on-vehicle camera equipment and on-vehicle microphone equipment, the method at least includes:

enabling the N to be added and returned, and determining a plurality of target driving state detection results corresponding to each N pieces of vehicle-mounted equipment according to vehicle-mounted detection data corresponding to each target vehicle-mounted equipment in each N pieces of vehicle-mounted equipment and identification weights corresponding to the vehicle-mounted detection data; wherein the target driving state result includes a plurality of levels:

in the first level, the running state of the electric vehicle is good;

and (3) second grade: the running state of the electric vehicle is abnormal;

and a third stage: the running state of the electric vehicle has slight faults;

fourth stage: the running state of the electric vehicle has serious faults;

and a fifth level: the running state of the electric vehicle is dangerous;

2. The method according to claim 1, wherein the converting the set of operation data according to a preset data conversion list for each set of operation data to obtain vehicle-mounted detection data corresponding to the set of operation data comprises:

3. The method according to claim 2, wherein the determining a plurality of target driving state detection results corresponding to each N vehicle-mounted devices according to the vehicle-mounted detection data corresponding to each target vehicle-mounted device in each N vehicle-mounted device and the identification weight corresponding to the vehicle-mounted detection data comprises:

4. The method of claim 1, wherein the performing feature extraction on each detection result cluster to obtain a feature vector corresponding to each detection result cluster comprises:

generating a blank vector according to the vector dimension;

5. The method according to any one of claims 1 to 4, wherein the determining a current driving state detection result of the electric vehicle according to each obtained feature vector comprises:

judging whether the vector dimension of each feature vector is the same;

6. An on-board detector, comprising a processor, and a memory and a bus connected to the processor; wherein, the processor and the memory complete mutual communication through the bus; the processor is used for calling the program instructions in the memory to execute the data processing method of the internet of things-based equipment according to any one of the claims 1-5.

7. A readable storage medium, on which a program is stored, the program implementing the internet of things based device data processing method of any one of claims 1 to 5 when executed by a processor.