CN111625755B

CN111625755B - Data processing method, device, server, terminal and readable storage medium

Info

Publication number: CN111625755B
Application number: CN202010436167.8A
Authority: CN
Inventors: 郭峰; 彭新建; 邓新伟; 毛慧颖; 史量; 钱晨; 蒋弘刚
Original assignee: Beijing Didi Infinity Technology and Development Co Ltd
Current assignee: Beijing Didi Infinity Technology and Development Co Ltd
Priority date: 2020-05-21
Filing date: 2020-05-21
Publication date: 2023-10-31
Anticipated expiration: 2040-05-21
Also published as: CN111625755A

Abstract

The embodiment of the disclosure relates to a data processing method, a data processing device, a server, a terminal and a readable storage medium. The method comprises the following steps: acquiring IMU data of a vehicle reported by a terminal; wherein each sample data in the IMU data has a time attribute; processing the IMU data according to the time attribute of each sampled data to obtain error correction data of the IMU data; wherein the error correction data is related to median data of the IMU data; and correcting each sampling data by adopting the error correction data to obtain corrected IMU data. By adopting the method, the data precision of the IMU data of the vehicle can be improved.

Description

Data processing method, device, server, terminal and readable storage medium

Technical Field

The embodiment of the disclosure relates to the technical field of data processing, in particular to a data processing method, a data processing device, a server, a terminal and a readable storage medium.

Background

An inertial measurement unit (Inertial Measurement Unit, IMU) is a device that measures the attitude angle (or angular rate) and acceleration of an object. Typically, an IMU includes three single axis accelerometers and three single axis gyroscopes for measuring acceleration data and angular velocity data, i.e., IMU data, of an object in three dimensions, respectively.

At present, IMU data are used in large quantities in the projects of automatic driving, navigation systems, driving safety and the like. Taking driving safety as an example, an IMU is arranged in a terminal of a driver, and the terminal measures IMU data of the terminal through the IMU and reports the IMU data to a management background; the management background acquires the IMU data and then carries out data processing, and the gesture of the vehicle is restored, so that whether dangerous driving behaviors such as sudden acceleration, sudden turning, sudden lane change, sudden deceleration and the like exist in the vehicle is detected.

However, the IMU data reported by the terminal has low accuracy, and further in some scenes of applying IMU data, accuracy problems in various applications often occur, for example, when dangerous driving behavior prediction is performed by using IMU data, a situation that prediction accuracy is not high often occurs.

Disclosure of Invention

The embodiment of the disclosure provides a data processing method, a device, a server, a terminal and a readable storage medium, which can be used for improving the data precision of IMU data of a vehicle.

In a first aspect, an embodiment of the present disclosure provides a data processing method, including:

acquiring IMU data of a vehicle reported by a terminal; wherein each sample data in the IMU data has a time attribute;

Processing the IMU data according to the time attribute of each sampled data to obtain error correction data of the IMU data; wherein the error correction data is related to median data of the IMU data;

and correcting each sampling data by adopting the error correction data to obtain corrected IMU data.

In a second aspect, embodiments of the present disclosure provide a data processing method, the method including:

acquiring IMU data of a vehicle, and sending the IMU data to a server; each sampled data in the IMU data has a time attribute;

receiving prompt information issued by the server; the prompt information is related to the driving gesture of the vehicle, and is generated after the server performs data processing on the IMU data by adopting the method described in the first aspect.

In a third aspect, embodiments of the present disclosure provide a data processing apparatus, the apparatus comprising:

the IMU data acquisition module is used for acquiring the IMU data of the traffic tool reported by the terminal; wherein each sample data in the IMU data has a time attribute;

the error correction data acquisition module is used for processing the IMU data according to the time attribute of each sampling data to obtain error correction data of the IMU data; wherein the error correction data is related to median data of the IMU data;

And the error correction module is used for correcting each sampled data by adopting the error correction data to obtain corrected IMU data.

In a fourth aspect, embodiments of the present disclosure provide a data processing apparatus, the apparatus comprising:

the reporting module is used for collecting IMU data of the vehicle and sending the IMU data to the server; each sampled data in the IMU data has a time attribute;

the prompt information receiving module is used for receiving the prompt information issued by the server; the prompt information is related to the driving gesture of the vehicle, and is generated after the server performs data processing on the IMU data by adopting the method described in the first aspect.

In a fifth aspect, an embodiment of the disclosure provides a server, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the method of the first aspect when the processor executes the computer program.

In a sixth aspect, an embodiment of the disclosure provides a terminal, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the method of the second aspect when the processor executes the computer program.

In a seventh aspect, embodiments of the present disclosure provide a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the methods of the first and second aspects described above.

According to the data processing method, the device, the server, the terminal and the readable storage medium, error correction data related to median data of IMU data of a vehicle reported by the terminal are adopted to correct each sampled data in the IMU data, the corrected IMU data are obtained, the IMU data are taken as acceleration data as an example, because the external force applied to an object is the reason that the object generates acceleration, if the terminal is in a static state or a uniform state, the external force applied to the terminal is only gravity and other noises, and when the terminal is in the static state or the uniform state, the acceleration data collected by the terminal are equal to the median data of the IMU data, so that the median data can represent acceleration generated by gravity and other noises, namely, the acceleration data collected by the terminal are interfered by the gravity and other noises. Whereas acceleration data that fluctuates in the vicinity of the median data may also approximate acceleration that characterizes gravity and other noise generation. Therefore, by adopting the error correction data (the error correction data can be the median data of the IMU data or the data fluctuating nearby the median data of the IMU data) related to the median data of the IMU data of the vehicle reported by the terminal, each sampled data in the IMU data is corrected, so that the interference of gravity and other noise in each sampled data can be eliminated, and the data precision of the IMU data of the vehicle is improved. Further, in some scenes of applying IMU data, by adopting the data processing method of the embodiment of the present disclosure, for example, taking a vehicle as an example, in the conventional technology, dangerous driving behavior prediction is generally performed by directly using IMU data of the vehicle reported by the terminal, and because the accuracy of the IMU data of the vehicle reported by the terminal is low, the prediction accuracy of dangerous driving behavior is low, but by adopting the data processing method of the embodiment of the present disclosure, the IMU data of the vehicle reported by the terminal is corrected, so as to obtain corrected IMU data, thereby improving the accuracy of the IMU data of the vehicle, and then dangerous driving behavior prediction is performed on the basis of the corrected IMU data, thereby improving the prediction accuracy of dangerous driving behavior.

Drawings

FIG. 1 is a diagram of an application environment for a data processing method in one embodiment;

FIG. 2 is a flow diagram of a data processing method in one embodiment;

FIG. 3 is a flow chart of a data processing method according to another embodiment;

FIG. 4 is a schematic diagram of the refinement step of step S210 in one embodiment;

FIG. 5 is a schematic diagram of the refinement step of step S212 in one embodiment;

FIG. 6 is a flow chart of a data processing method according to another embodiment;

FIG. 7 is a flow chart of a data processing method according to another embodiment;

FIG. 8 is a flow chart of a data processing method according to another embodiment;

FIG. 9 is a flow chart of a data processing method according to another embodiment;

FIG. 10 is a block diagram of a data processing apparatus in one embodiment;

FIG. 11 is a block diagram showing a structure of a data processing apparatus in another embodiment;

FIG. 12 is a block diagram of a data processing apparatus in another embodiment;

FIG. 13 is a block diagram showing a structure of a data processing apparatus in another embodiment;

FIG. 14 is a block diagram showing the structure of a data processing apparatus in another embodiment;

FIG. 15 is a block diagram showing the structure of a data processing apparatus in another embodiment;

FIG. 16 is a block diagram of a terminal in one embodiment;

FIG. 17 is a block diagram of a server in one embodiment.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present disclosure more apparent, the embodiments of the present disclosure will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the disclosed embodiments and are not intended to limit the disclosed embodiments.

First, before the technical solution of the embodiments of the present disclosure is specifically described, a description is given of a technical background or a technical evolution context on which the embodiments of the present disclosure are based. In general, in the field of vehicles, the current technical background is: IMU data of the vehicle is measured by a terminal placed in the vehicle, and then, based on the measured IMU data, restoration of the vehicle posture, prediction of dangerous driving behavior of the driver, or the like is performed. Based on the background, the applicant finds that the IMU data of the vehicle measured by the terminal is often low in precision through long-term IMU data processing research and development and collection, demonstration and verification of experimental data, so that various problems of low application accuracy can occur in some scenes of applying the IMU data. How to correct the IMU data of the vehicles becomes a current problem to be solved urgently. In addition, the applicant has made a great deal of creative effort in determining how to modify the IMU data of a vehicle and in determining the solutions described in the following embodiments.

The following describes a technical scheme related to an embodiment of the present disclosure in conjunction with a scenario in which the embodiment of the present disclosure is applied.

The data processing method provided by the embodiment of the disclosure can be applied to an application environment as shown in fig. 1. Wherein the terminal 102 communicates with the server 104 via a network. The server 104 acquires IMU data of the vehicles reported by the terminal 102; wherein each sample data in the IMU data has a time attribute; the server 104 processes the IMU data according to the time attribute of each sampled data to obtain error correction data of the IMU data; wherein the error correction data is related to median data of the IMU data; the server 104 corrects each sampled data using the error correction data to obtain corrected IMU data. The terminal 102 may be, but not limited to, various personal computers, notebook computers, smartphones, tablet computers, and portable wearable devices, and the server 104 may be implemented by a stand-alone server or a server cluster composed of a plurality of servers.

In one embodiment, as shown in fig. 2, a data processing method is provided, and the method is applied to the server in fig. 1 for illustration, and includes the following steps:

And step S100, acquiring IMU data of the vehicle reported by the terminal.

Wherein each sample data in the IMU data has a temporal attribute. The IMU (Inertial Measurement Unit ) typically contains an accelerometer and a gyroscope for measuring acceleration data and angular velocity data, respectively, of an object in three-dimensional space. In this embodiment, the IMU data may be IMU acceleration data, and in other embodiments, the IMU data may also be angular velocity data, displacement data, velocity data, and the like, which are not limited herein.

In this embodiment, the terminal may be a terminal of a user using the vehicle, for example, may be a driver terminal, and may be other terminals currently provided in the vehicle. The terminal is internally provided with an IMU, and can measure the IMU data of the vehicle through the IMU and report the measured IMU data of the vehicle to the server.

As an implementation manner, the server may send a report instruction to the terminal, and instruct the terminal to report IMU data of the vehicle periodically according to a time period carried by the report instruction, where the time period may be, for example, 2 minutes or 3 minutes; after receiving the report instruction, the terminal reports the IMU data of the vehicles collected in each time period to the server according to the time period. In other embodiments, the server may also send a data acquisition request to the terminal when the IMU data of the vehicle in a certain period of time needs to be used, and after the terminal receives the data acquisition request, the terminal may report the IMU data of the vehicle in the period of time to the server, or the terminal may also actively report the IMU data of the vehicle collected by the terminal to the server according to a preset time period, and the like, which is not limited herein.

In this embodiment, the IMU data includes sampling data collected by the terminal at different sampling times, where each sampling data has a time attribute, and the time attribute may be a sampling time corresponding to the sampling data.

And step S200, processing the IMU data according to the time attribute of each sampled data to obtain error correction data of the IMU data.

In this embodiment, the error correction data is related to the median data of the IMU data. Taking the IMU data as acceleration data as an example, when the terminal collects acceleration data, the acceleration data collected by the terminal is interfered by external force, so that the acceleration data collected by the terminal is inaccurate.

Because the external force applied to the object is the reason that the object generates acceleration, if the terminal is in a static state or a uniform state, the external force applied to the terminal only has gravity and other noises, and when the terminal is in the static state or the uniform state, the acceleration data collected by the terminal is equal to the median data of the IMU data, so that the median data can represent the acceleration generated by the gravity and other noises, namely the interference of the gravity and other noises on the acceleration data collected by the terminal. Whereas acceleration data that fluctuates in the vicinity of the median data may also approximate acceleration that characterizes gravity and other noise generation.

In this embodiment, the error correction data may be median data of the IMU data, or may be data that fluctuates in the vicinity of the median data of the IMU data, so that the error correction data may represent interference of gravity and other noise on acceleration data collected by the terminal.

In this embodiment, the server processes the IMU data according to the time attribute of each sample data, which may specifically be determining median data of the IMU data, where the median data of the IMU data may be sample data residing in a middle position of the IMU data. The server determines the error correction data of the IMU data according to the median data, specifically, the server may use the median data as the error correction data of the IMU data, or the server may use data in the vicinity of the median data, that is, data having an absolute value of a difference from the median data smaller than a fixed threshold value, as the error correction data of the IMU data.

And step S300, correcting each sampling data by adopting error correction data to obtain corrected IMU data.

And the server corrects each sampled data by adopting error correction data to obtain corrected IMU data. As an implementation manner, the server may subtract the error correction data from each sample data, or the server may assign different weight values to the sample data and the error correction data, and then perform weighted summation on the sample data and the error correction data to obtain corrected sample data corresponding to the sample data, so as to obtain corrected IMU data.

In this embodiment, the sampling data may be three-axis acceleration data, that is, acceleration data of the sampling-time vehicle in an x-axis direction, a y-axis direction, and a z-axis direction, wherein the x-axis direction indicates a front-rear direction when the vehicle is traveling, the y-axis direction indicates a left-right direction when the vehicle is traveling, and the z-axis direction indicates an up-down direction. The server can process the acceleration data of each axis according to the time attribute of the triaxial acceleration data under each sampling time to obtain error correction data corresponding to each axis, wherein the error correction data corresponding to each axis is related to the median data of the acceleration data of the axis. The server then corrects the acceleration data of each axis using the error correction data of each axis, e.g., sampling time t ₁ …t _n Corresponding sampled data, i.e. triaxial acceleration data, respectively (a _1x ,a _1y ,a _1z )…(a _nx ,a _ny ,a _nz ) Error correction data corresponding to the x axis adopts C _x The error correction data corresponding to the y-axis is represented by C _y The error correction data corresponding to the z-axis is represented by C _z The representation is that the server adopts C _x For sampling time t ₁ …t _n A in the corresponding triaxial acceleration data _1x …a _nx Respectively correct by C _y For sampling time t ₁ …t _n A in the corresponding triaxial acceleration data _1y …a _ny Respectively correct by C _z For sampling time t ₁ …t _n A in the corresponding triaxial acceleration data _1z …a _nz And respectively carrying out correction.

According to the analysis, as the error correction data can represent the interference of gravity and other noise on the acceleration data collected by the terminal, the server corrects each sampling data by adopting the error correction data, and the interference of gravity and other noise in each triaxial acceleration data can be eliminated by adopting the sampling data such as the triaxial acceleration data. The modified IMU data obtained in this embodiment is IMU data from which the interference of gravity and other noise is eliminated, so that the data accuracy of the IMU data of the vehicle is improved.

In other embodiments, in the case where the IMU data is angular velocity data, displacement data, or velocity data, the IMU data may be corrected by using error correction data related to median data, so as to remove resultant vector errors generated by measurement component noise or errors, which is not particularly limited herein.

As an implementation manner, the data processing method of the present embodiment may be applied to a rectangular cartesian coordinate system, that is, the IMU data of the vehicle reported by the terminal is measured in the rectangular cartesian coordinate system, and it should be noted that the data processing method of the present embodiment may also be applied to any affine coordinate or polar coordinate, which is not limited herein.

In summary, for the IMU acceleration data, since the resultant force applied to the object is the cause of the acceleration generated by the object, if the terminal is in a static state or a constant speed state, the resultant force applied to the terminal is only gravity and other noises, and when the terminal is in the static state or the constant speed state, the acceleration data collected by the terminal is equal to the median data of the IMU data, so that the median data can represent the acceleration generated by gravity and other noises, that is, the interference of gravity and other noises on the acceleration data collected by the terminal. Whereas acceleration data that fluctuates in the vicinity of the median data may also approximate acceleration that characterizes gravity and other noise generation. Therefore, by adopting the error correction data (the error correction data can be the median data of the IMU data or the data fluctuating nearby the median data of the IMU data) related to the median data of the IMU data of the vehicle reported by the terminal, each sampled data in the IMU data is corrected, so that the interference of gravity and other noise in each sampled data can be eliminated, and the data precision of the IMU data of the vehicle is improved. Further, in some scenes of applying IMU data, by adopting the data processing method of the embodiment, for example, taking a vehicle as an example, in the conventional technology, dangerous driving behavior prediction is generally performed by directly using IMU data of the vehicle reported by the terminal, and because the accuracy of the IMU data of the vehicle reported by the terminal is lower, the prediction accuracy of dangerous driving behavior is lower, but by adopting the data processing method of the embodiment, the IMU data of the vehicle reported by the terminal is corrected, so as to obtain corrected IMU data, the accuracy of the IMU data of the vehicle is improved, and dangerous driving behavior prediction is performed by using the corrected IMU data, so that the prediction accuracy of dangerous driving behavior is improved.

The applicant of the disclosed embodiments found during the course of the study that the gravity of the terminal could interfere with the accuracy of the IMU data of the vehicle measured by the terminal when the terminal is placed in the vehicle. In the related art, in order to eliminate the influence of gravity on IMU data, the second norm of the sampled data when the terminal is in a stationary state may be approximated to the local gravitational acceleration, so as to calibrate the IMU data. Specifically, for IMU data of a vehicle reported by a terminal, a server may detect sampling data in a static state of the terminal from a plurality of sampling data included in the IMU data by adopting a static detection algorithm, and then calibrate the IMU data based on a conversion matrix or a six-sided method, so as to eliminate the influence of gravity on the IMU data, however, the method has the following drawbacks: 1) When the server adopts a static detection algorithm to detect the sampling data in the static state of the terminal in a plurality of sampling data included in the IMU data, a threshold value is required to be set manually, and the server determines the sampling data with the two norms of the sampling data smaller than the threshold value as the sampling data in the static state of the terminal, however, the setting of the threshold value is greatly influenced by human subjective factors; 2) The calibration of IMU data only considers the gravity interference factor, but does not consider the interference of other noise; 3) When the IMU data is calibrated, a large number of complex algorithms such as matrix operation, optimization solution and the like are involved, an initial transformation matrix, a state equation, a solution cost function and the like need to be defined in a matrix conversion method, a calibration model, matrix operation and the like need to be built in a six-face method, a logic process is complex, and the calculation complexity is high.

Compared with the method of calibrating the IMU data of the vehicle by adopting the static detection algorithm, the method of calibrating the IMU data of the vehicle does not need to carry out complex matrix operation or matrix transformation, and does not need to manually set a threshold value to detect the static state of the terminal. According to the method, the effect of correcting the IMU data can be achieved by utilizing error correction data related to the median data of the IMU data, the IMU data of the vehicles reported by the terminals at different placement positions can be corrected by adopting the method, complex operations such as filtering and matrix are avoided, and the method is extremely low in calculation complexity and high in practicality.

In one embodiment, based on the embodiment shown in fig. 2 and shown in fig. 3, this embodiment relates to a process how the server obtains error correction data according to the time attribute of each sample data, and corrects each sample data. Specifically, the embodiment includes the following steps:

and step S100, acquiring IMU data of the vehicle reported by the terminal.

Wherein each sample data in the IMU data has a temporal attribute. Specifically, the specific process of this step S100 may be referred to the description of the above embodiment, and will not be repeated here.

Step S210, calculating median data corresponding to the IMU data according to the time attribute of each sampling data, and determining the median data as error correction data.

In this embodiment, specifically, after the server obtains the IMU data of the vehicle reported by the terminal, median data corresponding to the IMU data is calculated according to the time attribute of each sampled data, where the median data is error correction data of the IMU data.

The server calculates median data corresponding to the IMU data according to the time attribute of each sampling data, specifically, the IMU data comprises sampling data acquired by the terminal at different sampling times, namely, the IMU data comprises a plurality of sampling data, and the server calculates the median data of the plurality of sampling data to obtain the median data corresponding to the IMU data.

And step S310, subtracting the median data from each sampling data to obtain corrected IMU data.

In this embodiment, specifically, the server subtracts the median data from each sample data included in the IMU data, to obtain corrected IMU data.

For example, the sampled data may be triaxial acceleration data, and the IMU data may be the sampling time t ₁ …t _n Corresponding triaxial acceleration data (a _1x ,a _1y ,a _1z )…(a _nx ,a _ny ,a _nz ) The median data (error correction data) corresponding to the x-axis adopts C _x The median data (error correction data) corresponding to the y-axis is represented by C _y The median data (error correction data) corresponding to the z-axis is represented by C _z In this embodiment, the server subtracts the median data from each sample data, specifically, the value of a _1x L a _nx Respectively subtract C _x Pair a _1y L a _ny Respectively subtract C _y Pair a _1z L a _nz Respectively subtract C _z The corrected IMU data obtained is: (a) _1x -C _x ,a _1y -C _y ,a _1z -C _z )L(a _nx -C _x ,a _ny -C _y ,a _nz -C _z ) Wherein (a) _1x -C _x ,a _1y -C _y ,a _1z -C _z ) For the sampling time t ₁ Corresponding corrected triaxial acceleration data, (a) _nx -C _x ,a _ny -C _y ,a _nz -C _z ) For the sampling time t _n Corresponding corrected triaxial acceleration data.

In this embodiment, median data corresponding to IMU data is calculated according to a time attribute of each sample data, the median data is used as error correction data of the IMU data, if a sample time terminal corresponding to the median data is in a constant speed state or a static state, acceleration generated by gravity and other noise can be represented by the median data, that is, interference of gravity and other noise on acceleration data collected by the terminal, if a sample time terminal corresponding to the median data is not in a constant speed state or a static state, acceleration generated by gravity and other noise can be represented by the median data approximately, and therefore, interference generated by gravity and other noise in each sample data can be eliminated by subtracting the median data from each sample data, and effects of reducing calculation complexity and improving practicality can be achieved.

In one embodiment, based on the embodiment shown in fig. 3, as shown in fig. 4, this embodiment relates to how the server calculates the median data process corresponding to the IMU data according to the time attribute of each sample data. In this embodiment, the step S210 may include step S211 and step S212:

step S211, sequencing each sampled data according to the sequence of sampling time of each sampled data to obtain an IMU data sequence.

Specifically, each sample data in the IMU data has a time attribute, and as an implementation manner, the IMU data may include a sample time corresponding to each sample data, for example, the sample time may be a sample timestamp, and the server may sort each sample data according to the order of the sample timestamp of each sample data from small to large, so as to obtain an IMU data sequence, thereby ensuring that each sample data in the IMU data sequence is generated according to the time sequence of the actual driving behavior of the vehicle.

In other embodiments, the server may also sort the sampled data according to the order of the sampling time stamps from the big to the small of the sampled data to obtain the IMU data sequence, which is not limited herein.

Step S212, according to the number of sampling data in the IMU data sequence, determining the median data corresponding to the IMU data.

Median, also known as median, is the number in the middle of a set of data in a sequential order. In this embodiment, the server sorts the sampled data according to the sequence of the sampling time of the sampled data to obtain an IMU data sequence, and then determines median data corresponding to the IMU data according to the number of sampled data in the IMU data sequence. For example, the server may determine the sample data at a middle position of the IMU data sequence as median data corresponding to the IMU data, and determine the median data as error correction data.

According to the method and the device, the situation that the median data determined by the server have deviation due to the fact that all sampling data are not strictly arranged according to the sequence of sampling time in the IMU data reported by the terminal is avoided, and the accuracy of the median data of the IMU data is improved.

In a possible implementation manner of step S212, for step S212, the server may directly determine median data according to the number of sampled data in the determined IMU data sequence, that is, step S212 may include: if the number of the sampling data in the IMU data sequence is an odd number, determining the sampling data at the middle position of the IMU data sequence as median data; if the number of the sampling data in the IMU data sequence is even, determining the average value of two adjacent sampling data positioned in the middle of the IMU data sequence as median data.

Specifically, if the number of sampling data in the IMU data sequence is an odd number, the server determines the sampling data at the middle position of the IMU data sequence as median data. For example, the number of sample data in the IMU data sequence is 9, and the server starts counting from the head or tail of the IMU data sequence, and determines the 5 th sample data as median data. Further, if the number of sampling data in the IMU data sequence is even, it may be understood that the number of sampling data in the middle position of the IMU data sequence is two, for example, the number of sampling data in the IMU data sequence is 10, the server counts from the head or tail of the IMU data sequence, determines the 5 th sampling data and the 6 th sampling data, calculates the average value of the 5 th sampling data and the 6 th sampling data, and determines the average value of two adjacent sampling data in the middle position of the IMU data sequence as median data.

Therefore, the server determines the median data corresponding to the IMU data according to the number of the sampled data in the IMU data sequence, specifically distinguishes whether the number of the sampled data in the IMU data sequence is odd or even, and processes the situations of the odd number and the even number in a corresponding mode, so that the accuracy of the median data of the IMU data is improved.

In another possible implementation manner of step S212, for step S212, the server may segment the IMU data sequence according to a preset time division window, and then calculate median data corresponding to each IMU data sequence segment. Referring to fig. 5, fig. 5 is a schematic diagram of a refinement step of step S212. As shown in fig. 5, the step S212 may include the steps of:

step S2121, segmenting the IMU data sequence according to a preset time division window to obtain a plurality of IMU data sequence fragments.

In this embodiment, after sequencing each sampled data according to the sequence of sampling time of each sampled data to obtain an IMU data sequence, the server segments the IMU data sequence according to a preset time division window to obtain a plurality of IMU data sequence segments.

For example, the IMU data sequence is a plurality of sampling data collected by the terminal within 3 minutes, and the terminal collects sampling data every 0.02 seconds, then the IMU data sequence includes 9000 sampling data, the time division window is for example 10 seconds, then the server segments the IMU data sequence according to 10 seconds, so as to obtain 18 IMU data sequence segments, and each IMU data sequence segment includes 500 sampling data.

In one embodiment, if the remaining segments of the IMU data sequence are less than the single division after the server segments the IMU data sequence, the server merges the remaining segments into the last time division window. For example, continuing to take the IMU data sequence including 9000 sample data as an example, the time division window is 8 seconds, the server divides the 9000 sample data into 22 IMU data sequence segments, and then remaining 200 sample data, and the server merges the remaining 200 sample data into the last time division window, that is, the server finally divides the IMU data sequence into 22 IMU data sequence segments, the first 21 IMU data sequence segments each include 400 sample data, and the last IMU data sequence segment includes 600 sample data. Therefore, omission of the sampling data in the segmentation process of the IMU data sequence can be avoided through merging the residual sampling data.

In step S2122, median data corresponding to each IMU data sequence segment is calculated according to the number of sampling data in each IMU data sequence segment.

And the server calculates the median data corresponding to each IMU data sequence fragment according to the number of the sampling data in each IMU data sequence fragment.

Specifically, if the number of sampling data in one IMU data sequence segment is an odd number, determining the sampling data at the middle position of the IMU data sequence segment as median data corresponding to the IMU data sequence segment. If the number of the sampling data in one IMU data sequence segment is even, determining the average value of two adjacent sampling data in the middle position of the IMU data sequence segment as the median data corresponding to the IMU data sequence segment.

In the present embodiment, the setting of the time division window is not particularly limited. However, the time division window should not be too small, if the time division window is too small, the number of sampling data included in the time division window is small, so that median data corresponding to the IMU data sequence segments cannot well correct the sampling data, for example, after the IMU data sequence is segmented by the set time division window, the number of sampling data in each IMU data sequence segment may be at least not less than 100, which, of course, does not limit the application of the embodiment.

Based on the embodiment shown in fig. 5, correspondingly, for step S300, the server may specifically subtract the median data corresponding to the IMU data sequence segment from each sample data in the IMU data sequence segment, to obtain corrected IMU data.

And for each IMU data sequence segment, the server respectively subtracts the median data corresponding to the IMU data sequence segment from each sampling data in the IMU data sequence segment to obtain a corrected IMU data sequence segment corresponding to the IMU data sequence segment. Each sampled data in the modified IMU data sequence segment is sampled data modified by the server by adopting median data corresponding to the IMU data sequence segment, so that interference of gravity and other noise to each sampled data in the time division window is eliminated, a plurality of modified IMU data sequence segments corresponding to the IMU data sequence, namely modified IMU data, are obtained, and the accuracy of the IMU data is improved.

In this embodiment, the median data in each time division window is used as the interference of gravity and other noise received by the terminal on each sampling data in the time division window, and each sampling data in the IMU data sequence segment is corrected. The IMU data sequence is segmented to obtain a plurality of IMU data sequence fragments, and then the sampled data of each IMU data sequence fragment is corrected respectively, so that the server can process each IMU data sequence fragment in parallel, and the correction efficiency of the sampled data is improved.

In one embodiment, based on the embodiment shown in fig. 2 and described above, as shown in fig. 6, this embodiment relates to a process how the server performs linear interpolation preprocessing on IMU data. In this embodiment, the method includes the following steps:

and step S100, acquiring IMU data of the vehicle reported by the terminal.

And step S400, performing linear interpolation processing on missing sampling data in the IMU data to obtain IMU data after the linear interpolation processing.

In this embodiment, after the server obtains the IMU data of the vehicle reported by the terminal, linear interpolation processing is performed on missing sampling data in the IMU data. It can be appreciated that in the process of transmitting IMU data of a vehicle, there may be a situation that sampling data is lost, and the server performs linear interpolation processing on missing sampling data in the IMU data, so as to repair the missing sampling data in the IMU data.

Linear interpolation is the estimation of a value from two data points adjacent to each other to the left and right of a point in a one-dimensional data sequence that needs interpolation. In this embodiment, as an embodiment, the server may calculate an average value of two sample data adjacent to the left and right of the missing sample data, and use the average value as the value of the missing sample data.

And step S220, processing the IMU data subjected to linear interpolation processing according to the time attribute of each sampling data to obtain error correction data.

The server processes the IMU data after the linear interpolation processing according to the time attribute of each sampled data, and the specific process of obtaining the error correction data can be referred to the description of the above embodiment, which is not repeated herein.

The server corrects each sampled data by using the error correction data, and the specific process of obtaining the corrected IMU data may be referred to the description of the above embodiment, which is not repeated herein.

According to the method, the integrity and the accuracy of the IMU data are improved by performing linear interpolation processing on the missing sampling data in the IMU data, and the server processes the IMU data subjected to linear interpolation processing according to the time attribute of each sampling data to obtain error correction data, so that the data accuracy of the error correction data is improved.

In one embodiment, based on the embodiment shown in fig. 2 and shown in fig. 7, the present embodiment relates to a process of how the server predicts the driving gesture of the vehicle according to the corrected IMU data. In this embodiment, after the server obtains the corrected IMU data, the method further includes step S510 and step S520:

Step S510, calculating the comprehensive acceleration data corresponding to the sampling time of each sampling data according to the corrected IMU data. Wherein, each comprehensive acceleration data is obtained after calculating the two norms of the corresponding sampling data.

As an implementation manner, the IMU data in this embodiment may be IMU acceleration data, and the corrected IMU data may be corrected acceleration data of the vehicle at each sampling time, specifically corrected triaxial acceleration data. For example, the corrected triaxial acceleration data corresponding to the sampling time T is (a) _Tx ,a _Ty ,a _Tz ) Wherein a is _Tx For the corrected acceleration data corresponding to the x-axis, a _Ty For the corrected acceleration data corresponding to the y-axis, a _Tz For the corrected acceleration data corresponding to the z axis, the server calculates the comprehensive acceleration data A corresponding to the sampling time T _T Can be calculated by equation 1:

by the method, the server can calculate the comprehensive acceleration data corresponding to the sampling time of each sampling data.

Step S520, predicting the driving posture of the vehicle by using the integrated acceleration data.

The server predicts the driving posture of the vehicle by using the comprehensive acceleration data. The comprehensive acceleration data of each sampling time represents the corresponding sampling time, the stress condition of the terminal after the influence of gravity and other noise is eliminated, namely the influence of the gravity and other noise on the sampling data due to the difference of the placement positions of the terminal is eliminated, and the prediction of the running gesture of the vehicle is performed based on each comprehensive acceleration data, for example, whether dangerous driving behaviors such as sudden acceleration, sharp turning, sharp lane change, sudden deceleration and the like exist in the vehicle or not is predicted, so that the prediction accuracy of the running gesture prediction can be improved.

Further, if the predicted result obtained by the server is that the vehicle has dangerous driving, the server sends prompt information to the terminal, wherein the prompt information is used for prompting the driver to drive safely, so that the drive safety of the driver is supervised, and the prompt information can be voice prompt information or text prompt information, and is not particularly limited.

An embodiment of the present disclosure is described below in conjunction with a specific travel scenario, with specific reference to fig. 8, the method comprising the steps of:

and step S100, acquiring IMU data of the vehicle reported by the terminal.

Wherein each sample data in the IMU data has a temporal attribute. In this embodiment, the IMU data includes sampling data collected by the terminal at different sampling times, where each sampling data has a time attribute, and the time attribute may be a sampling time corresponding to the sampling data.

The IMU data in this embodiment may be IMU acceleration data, and the sample data corresponding to each sample time included in the IMU data may be acceleration data of the vehicle at each sample time, specifically, triaxial acceleration data.

In this embodiment, the server may perform linear interpolation processing on missing sample data in the acquired IMU data, so as to repair the missing sample data.

Specifically, each sample data in the IMU data has a time attribute, and as an implementation manner, the IMU data may include a sample time corresponding to each sample data, for example, the sample time may be a sample timestamp, and the server may sort each sample data according to the order of the sample timestamp of each sample data from small to large to obtain an IMU data sequence, so as to ensure that each sample data in the IMU data sequence is generated according to the time sequence of the actual driving behavior of the vehicle.

For example, the IMU data includes a sampling time t ₁ …t _n (n is an integer greater than 1) respectively corresponding to the sampling data (a _1x ,a _1y ,a _1z )…(a _nx ,a _ny ,a _nz ) However, sampling time t ₁ …t _n The corresponding sampled data does not necessarily follow exactly t ₁ 、t ₂ 、t ₃ 、t ₄ 、…、t _n-1 、t _n The server orders the sampling data according to the sequence of the sampling time of the sampling data to obtain an IMU data sequence as follows:

(a _1x ,a _1y ,a _1z )(a _2x ,a _2y ,a _2z )(a _3x ,a _3y ,a _3z )(a _4x ,a _4y ,a _4z )…(a _n-1x ,a _n-1y ,a _n-1z )(a _nx ,a _ny ,a _nz )

If the server segments the IMU data sequence and the remaining segments of the IMU data sequence are less than the single division, the server merges the remaining segments into the last time division window. For example, continuing to take the IMU data sequence including 9000 sample data as an example, the time division window is 8 seconds, the server divides the 9000 sample data into 22 IMU data sequence segments, and then remaining 200 sample data, and the server merges the remaining 200 sample data into the last time division window, that is, the server finally divides the IMU data sequence into 22 IMU data sequence segments, the first 21 IMU data sequence segments each include 400 sample data, and the last IMU data sequence segment includes 600 sample data. Therefore, omission of the sampling data in the segmentation process of the IMU data sequence can be avoided through merging the residual sampling data.

For example, the number of sample data in the first IMU data sequence segment is 101, and the server then sends the 51 th sample data (a _mx ,a _my ,a _mz ) And the m is a positive integer smaller than n as the median data corresponding to the IMU data sequence fragment.

Step S320, subtracting the median data corresponding to the IMU data sequence fragments from each sample data in the IMU data sequence fragments to obtain corrected IMU data.

And for each IMU data sequence segment, the server respectively subtracts the median data corresponding to the IMU data sequence segment from each sampling data in the IMU data sequence segment to obtain a corrected IMU data sequence segment corresponding to the IMU data sequence segment. For example, continuing with the above example, the first IMU data sequence fragment is: (a) _1x ,a _1y ,a _1z )(a _2x ,a _2y ,a _2z ) …, a total of 101 sample data, the server subtracting the median data of the first IMU data sequence segment from the 101 sample data, i.e., the 51 th sample data (a _mx ,a _my ,a _mz ) Obtaining a corrected first IMU data sequence fragment: (a) _1x -a _mx ,a _1y -a _my ,a _1z -a _mz )(a _2x -a _mx ,a _2y -a _my ,a _2z -a _mz )…。

And carrying out the same processing on each IMU data sequence segment to obtain a plurality of modified IMU data sequence segments, namely modified IMU data.

For example, for the first IMU data sequence segment after the correction, the sampling time t ₁ The corresponding corrected triaxial acceleration data is (a) _1x -a _mx ,a _1y -a _my ,a _1z -a _mz ) The server samples the time t ₁ Substituting the corresponding corrected triaxial acceleration data into the above formula 1, and calculating to obtain the sampling time t ₁ The corresponding comprehensive acceleration data is

The server predicts the driving posture of the vehicle by using the comprehensive acceleration data. The comprehensive acceleration data of each sampling time represents the corresponding sampling time, the terminal eliminates the stress condition after the influence of gravity and other noise, namely eliminates the influence of gravity and other noise on the sampling data due to the difference of the placement positions of the terminal, and the prediction of the running gesture of the vehicle is performed based on each comprehensive acceleration data, for example, whether dangerous driving behaviors such as sudden acceleration, sharp turning, sharp lane change, sudden deceleration and the like exist in the vehicle is predicted, so that the prediction accuracy of the running gesture prediction can be improved.

According to the method, error correction data related to median data of IMU data of a vehicle reported by a terminal are adopted to correct each sampling data in the IMU data, the IMU data are corrected, and the IMU data are taken as acceleration data as an example. Whereas acceleration data that fluctuates in the vicinity of the median data may also approximate acceleration that characterizes gravity and other noise generation. Therefore, by adopting the error correction data (the error correction data can be the median data of the IMU data or the data fluctuating nearby the median data of the IMU data) related to the median data of the IMU data of the vehicle reported by the terminal, each sampled data in the IMU data is corrected, so that the interference of gravity and other noise in each sampled data can be eliminated, and the data precision of the IMU data of the vehicle is improved.

Further, in some scenes of applying IMU data, by adopting the data processing method of the embodiment, for example, taking a vehicle as an example, in the conventional technology, dangerous driving behavior prediction is generally performed by directly using IMU data of the vehicle reported by the terminal, and because the accuracy of the IMU data of the vehicle reported by the terminal is lower, the prediction accuracy of dangerous driving behavior is lower, but by adopting the data processing method of the embodiment, the IMU data of the vehicle reported by the terminal is corrected, so as to obtain corrected IMU data, the accuracy of the IMU data of the vehicle is improved, and dangerous driving behavior prediction is performed by using the corrected IMU data, so that the prediction accuracy of dangerous driving behavior is improved.

In one embodiment, as shown in fig. 9, a data processing method is provided, and the method is applied to the terminal in fig. 1 for illustration, and includes the following steps:

step S10, acquiring IMU data of the vehicle, and sending the IMU data to a server.

Each sample data in the IMU data has a temporal attribute. As an embodiment, the terminal may collect IMU data of the vehicle at preset sampling intervals, for example, the terminal may collect IMU data of the terminal every 0.02 seconds.

In this embodiment, the server may send a report instruction to the terminal, instruct the terminal to report the IMU data of the vehicle periodically according to a time period carried by the report instruction, where the time period may be, for example, 2 minutes or 3 minutes, and after the terminal receives the report instruction, report the IMU data of the vehicle collected by the terminal according to the sampling interval in the current time period to the server according to the time period.

Step S20, receiving prompt information issued by the server.

The prompt information is related to the driving gesture of the vehicle, and the prompt information is generated after the server processes the IMU data by adopting any one of the embodiments shown in fig. 2-9.

In this embodiment, the prompt information may be used to prompt the driver to drive safely, and the prompt information may be a voice prompt information or a text prompt information, which is not limited herein.

Therefore, the terminal in the embodiment can monitor and remind the driving behavior of the driver by collecting the IMU data of the vehicle, sending the IMU data to the server and receiving the prompt information issued by the server, so that the driving safety of the vehicle is improved.

It should be understood that, although the steps in the flowcharts of fig. 2-9 are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in fig. 2-9 may include multiple steps or stages that are not necessarily performed at the same time, but may be performed at different times, nor does the order in which the steps or stages are performed necessarily performed in sequence, but may be performed alternately or alternately with at least a portion of the steps or stages in other steps or other steps.

In one embodiment, as shown in FIG. 10, there is provided a data processing apparatus comprising:

the IMU data acquisition module 10 is used for acquiring the IMU data of the traffic tool reported by the terminal; wherein each sample data in the IMU data has a time attribute;

the error correction data obtaining module 20 is configured to process the IMU data according to the time attribute of each sampled data, so as to obtain error correction data of the IMU data; wherein the error correction data is related to median data of the IMU data;

And the error correction module 30 is configured to correct the respective sampled data by using the error correction data, so as to obtain corrected IMU data.

In one embodiment, based on the embodiment shown in fig. 10, as shown in fig. 11, the error correction data obtaining module 20 includes: a median data calculating unit 201, configured to calculate median data corresponding to the IMU data according to the time attribute of each sample data, and determine the median data as the error correction data; the error correction module 30 is specifically configured to subtract the median data from each of the sampled data to obtain the corrected IMU data.

In one embodiment, on the basis of the embodiment shown in fig. 11, as shown in fig. 12, the median data calculation unit 201 includes: a sorting subunit 2011, configured to sort the respective sample data according to the sequence of the sampling times of the respective sample data, so as to obtain an IMU data sequence; the median data determining subunit 2012 is configured to determine median data corresponding to the IMU data according to the number of sampled data in the IMU data sequence.

Optionally, the median data determination subunit 2012 is specifically configured to: if the number of the sampling data in the IMU data sequence is an odd number, determining the sampling data at the middle position of the IMU data sequence as the median data; and if the number of the sampling data in the IMU data sequence is even, determining the average value of two adjacent sampling data positioned in the middle of the IMU data sequence as the median data.

Optionally, the median data determining subunit 2012 is specifically configured to segment the IMU data sequence according to a preset time division window to obtain a plurality of IMU data sequence segments, and calculate median data corresponding to each IMU data sequence segment according to the number of sampling data in each IMU data sequence segment.

Optionally, the error correction module 30 is specifically configured to subtract the median data corresponding to the IMU data sequence segment from each sample data in the IMU data sequence segment, so as to obtain corrected IMU data.

In one embodiment, on the basis of the embodiment shown in fig. 10, as shown in fig. 13, the data processing apparatus further includes: the interpolation module 40 is configured to perform linear interpolation processing on the missing sample data in the IMU data, so as to obtain IMU data after the linear interpolation processing; the error correction data obtaining module 20 is specifically configured to process the IMU data after the linear interpolation processing according to the time attribute of each sample data, so as to obtain the error correction data.

The error correction module 30 is specifically configured to subtract the median data from each of the sampled data to obtain the corrected IMU data.

Optionally, the IMU data is IMU acceleration data.

In one embodiment, on the basis of the embodiment shown in fig. 10, as shown in fig. 14, the data processing apparatus further includes:

the comprehensive acceleration acquisition module 50 is configured to calculate, according to the corrected IMU data, comprehensive acceleration data corresponding to sampling times of the respective sampling data; each comprehensive acceleration data is obtained after calculating the two norms of the corresponding sampling data;

the driving posture prediction module 60 is configured to predict the driving posture of the vehicle using the integrated acceleration data.

Optionally, the system further comprises a prompt message sending module 70, configured to send a prompt message to the terminal if the predicted result obtained by prediction is that dangerous driving exists in the vehicle; the prompt information is used for prompting the driver to drive safely.

In one embodiment, as shown in fig. 15, there is provided a data processing apparatus including:

the reporting module 100 is configured to collect IMU data of a vehicle and send the IMU data to a server; each sampled data in the IMU data has a time attribute;

the prompt message receiving module 200 is configured to receive a prompt message sent by the server; the prompt information is related to the driving gesture of the vehicle, and is generated after the server processes the IMU data by adopting any one of the embodiments shown in fig. 2-9.

For specific limitations of the data processing apparatus, reference may be made to the above limitations of the data processing method, and no further description is given here. Each of the modules in the above-described data processing apparatus may be implemented in whole or in part by software, hardware, and combinations thereof. The above modules may be embedded in hardware or may be independent of a processor in a server or a terminal, or may be stored in software in a memory in the server or the terminal, so that the processor may call and execute operations corresponding to the above modules.

Fig. 16 is a block diagram of a terminal 1300 according to an exemplary embodiment. For example, terminal 1300 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, an exercise device, a personal digital assistant, and the like.

Referring to fig. 16, a terminal 1300 may include one or more of the following components: a processing component 1302, a memory 1304, a power component 1306, a multimedia component 1308, an audio component 1310, an input/output (I/O) interface 1312, a sensor component 1314, and a communication component 1316. Wherein the memory has stored thereon a computer program or instructions that run on the processor.

The processing component 1302 generally controls overall operation of the terminal 1300, such as operations associated with display, telephone call, data communication, camera operation, and recording operation. The processing component 1302 may include one or more processors 1320 to execute instructions to perform all or part of the steps of the methods described above. Further, the processing component 1302 can include one or more modules that facilitate interactions between the processing component 1302 and other components. For example, the processing component 1302 may include a multimedia module to facilitate interaction between the multimedia component 1308 and the processing component 1302.

The memory 1304 is configured to store various types of data to support operations at the terminal 1300. Examples of such data include instructions for any application or method operating on terminal 1300, contact data, phonebook data, messages, pictures, videos, and the like. The memory 1304 may be implemented by any type or combination of volatile or nonvolatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disk.

The power supply assembly 1306 provides power to the various components of the terminal 1300. Power components 1306 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for terminal 1300.

The multimedia component 1308 includes a touch-sensitive display screen between the terminal 1300 and the user that provides an output interface. In some embodiments, the touch display screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensor may sense not only the boundary of a touch or slide action, but also the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 1308 includes a front-facing camera and/or a rear-facing camera. When the terminal 1300 is in an operation mode, such as a photographing mode or a video mode, the front camera and/or the rear camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have focal length and optical zoom capabilities.

The audio component 1310 is configured to output and/or input audio signals. For example, the audio component 1310 includes a Microphone (MIC) configured to receive external audio signals when the terminal 1300 is in an operation mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals may be further stored in the memory 1304 or transmitted via the communication component 1316. In some embodiments, the audio component 1310 also includes a speaker for outputting audio signals.

The I/O interface 1312 provides an interface between the processing component 1302 and peripheral interface modules, which may be a keyboard, click wheel, buttons, etc. These buttons may include, but are not limited to: homepage button, volume button, start button, and lock button.

The sensor assembly 1314 includes one or more sensors for providing status assessment of various aspects of the terminal 1300. For example, sensor assembly 1314 may detect the on/off state of terminal 1300, the relative positioning of the components, such as the display and keypad of terminal 1300, sensor assembly 1314 may also detect a change in position of terminal 1300 or a component of terminal 1300, the presence or absence of user contact with terminal 1300, terminal 1300 orientation or acceleration/deceleration, and temperature change of terminal 1300. The sensor assembly 1314 may include a proximity sensor configured to detect the presence of nearby objects in the absence of any physical contact. The sensor assembly 1314 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 1314 may also include an acceleration sensor, a gyroscopic sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

The communication component 1316 is configured to facilitate communication between the terminal 1300 and other devices, either wired or wireless. Terminal 1300 may access a wireless network based on a communication standard, such as WiFi,2G, or 3G, or a combination thereof. In one exemplary embodiment, the communication component 1316 receives broadcast signals or broadcast related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 1316 further includes a Near Field Communication (NFC) module to facilitate short range communications. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, ultra Wideband (UWB) technology, bluetooth (BT) technology, and other technologies.

In an exemplary embodiment, the terminal 1300 may be implemented by one or more Application Specific Integrated Circuits (ASICs), digital Signal Processors (DSPs), digital Signal Processing Devices (DSPDs), programmable Logic Devices (PLDs), field Programmable Gate Arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic elements for executing the data processing method shown in fig. 9, described above.

Fig. 17 is a block diagram of a server 1400 shown in accordance with an exemplary embodiment. With reference to fig. 17, the server 1400 includes a processing component 1420 that further includes one or more processors and memory resources represented by a memory 1422 for storing instructions or computer programs, such as application programs, executable by the processing component 1420. The application programs stored in memory 1422 can include one or more modules, each corresponding to a set of instructions. Further, the processing component 1420 is configured to execute instructions to perform the data processing methods illustrated in fig. 2-8 described above.

The server 1400 may also include a power component 1424 configured to perform power management of the device, a wired or wireless network interface 1426 configured to connect the device to a network, and an input/output (I/O) interface 1428. The server 1400 may operate an operating system based on storage 1422, such as Window14 14erverTM,Mac O14 XTM,UnixTM,LinuxTM,FreeB14DTM or the like.

In an exemplary embodiment, a storage medium is also provided that includes instructions, such as memory 1422 including instructions, that can be executed by a processor of server 1400 to perform the above-described methods. The storage medium may be a non-transitory computer readable storage medium, which may be, for example, ROM, random Access Memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, etc.

Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in embodiments provided by the present disclosure may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, or the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like.

The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.

The above examples merely represent a few implementations of the disclosed examples, which are described in more detail and are not to be construed as limiting the scope of the invention. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made to the disclosed embodiments without departing from the spirit of the disclosed embodiments. Accordingly, the protection scope of the disclosed embodiment patent should be subject to the appended claims.

Claims

1. A method of data processing, the method comprising:

acquiring Inertial Measurement Unit (IMU) data of a vehicle reported by a terminal; wherein each sample data in the IMU data has a time attribute;

processing the IMU data according to the time attribute of each sampled data to obtain error correction data of the IMU data; wherein the error correction data is median data of the IMU data, or the error correction data is data having an absolute value of a difference value from the median data smaller than a fixed threshold; the IMU data comprises sampling data acquired by the terminal at different sampling times, the median data are obtained by sequencing the sampling data according to the sequence of the sampling times of the sampling data, and the sampling data at the middle position of the IMU data sequence are determined to be the median data; the terminal is in a constant speed state or a static state at the sampling time corresponding to the median data;

2. The method of claim 1, wherein processing the IMU data according to the time attribute of each sample data to obtain error correction data of the IMU data comprises:

calculating median data corresponding to the IMU data according to the time attribute of each sampling data;

correspondingly, the correcting the sampling data by adopting the error correction data to obtain corrected IMU data comprises the following steps:

and subtracting the median data from each sampling data to obtain the corrected IMU data.

3. The method of claim 2, wherein the calculating the median data corresponding to the IMU data according to the time attribute of each sample data comprises:

sequencing the sampling data according to the sequence of the sampling time of the sampling data to obtain an IMU data sequence;

and determining the median data corresponding to the IMU data according to the number of the sampling data in the IMU data sequence.

4. A method according to claim 3, wherein the determining median data corresponding to the IMU data according to the number of sample data in the IMU data sequence comprises:

If the number of the sampling data in the IMU data sequence is an odd number, determining the sampling data at the middle position of the IMU data sequence as the median data;

and if the number of the sampling data in the IMU data sequence is even, determining the average value of two adjacent sampling data positioned in the middle of the IMU data sequence as the median data.

5. A method according to claim 3, wherein the determining median data corresponding to the IMU data according to the number of sample data in the IMU data sequence comprises:

segmenting the IMU data sequence according to a preset time division window to obtain a plurality of IMU data sequence fragments;

and calculating the median data corresponding to each IMU data sequence fragment according to the number of sampling data in each IMU data sequence fragment.

6. The method of claim 5, wherein subtracting the median data from each of the sample data to obtain the modified IMU data comprises:

and subtracting the median data corresponding to the IMU data sequence fragments from each sampling data in the IMU data sequence fragments respectively to obtain corrected IMU data.

7. The method of claim 1, wherein after the acquiring the inertial measurement unit IMU data of the vehicle reported by the terminal, further comprises:

performing linear interpolation processing on the missing sampling data in the IMU data to obtain IMU data after the linear interpolation processing;

correspondingly, the processing the IMU data according to the time attribute of each sampled data to obtain error correction data of the IMU data includes:

and processing the IMU data after the linear interpolation processing according to the time attribute of each sampling data to obtain the error correction data.

8. The method of any of claims 1-7, wherein the IMU data is IMU acceleration data.

9. The method according to any one of claims 1-7, wherein said correcting said respective sampled data using said error correction data, after obtaining corrected IMU data, further comprises:

according to the corrected IMU data, calculating comprehensive acceleration data corresponding to the sampling time of each sampling data respectively; each comprehensive acceleration data is obtained after calculating the two norms of the corresponding sampling data;

And predicting the running gesture of the vehicle by utilizing the comprehensive acceleration data.

10. The method according to claim 9, wherein the method further comprises:

if the predicted result obtained by prediction is that dangerous driving exists in the transportation means, prompt information is sent to the terminal; the prompt information is used for prompting the driver to drive safely.

11. A method of data processing, the method comprising:

receiving prompt information issued by the server; the prompt information is related to the driving gesture of the vehicle, and is generated after the server processes the IMU data by the method according to any one of claims 1 to 10.

12. A data processing apparatus, the apparatus comprising:

the error correction data acquisition module is used for processing the IMU data according to the time attribute of each sampling data to obtain error correction data of the IMU data; wherein the error correction data is median data of the IMU data, or the error correction data is data having an absolute value of a difference value from the median data smaller than a fixed threshold; the IMU data comprises sampling data acquired by the terminal at different sampling times, the median data are obtained by sequencing the sampling data according to the sequence of the sampling times of the sampling data, and the sampling data at the middle position of the IMU data sequence are determined to be the median data; the terminal is in a constant speed state or a static state at the sampling time corresponding to the median data;

13. The apparatus of claim 12, wherein the error correction data acquisition module comprises:

the median data calculation unit is used for calculating median data corresponding to the IMU data according to the time attribute of each sampling data;

correspondingly, the error correction module is specifically configured to subtract the median data from each sampling data to obtain the corrected IMU data.

14. The apparatus according to claim 13, wherein the median data calculation unit includes:

the sequencing subunit is used for sequencing each sampled data according to the sequence of the sampling time of each sampled data to obtain an IMU data sequence;

and the median data determining subunit is used for determining median data corresponding to the IMU data according to the number of the sampling data in the IMU data sequence.

15. The apparatus of claim 14, wherein the median data determination subunit is specifically configured to:

16. The apparatus of claim 14, wherein the median data determining subunit is specifically configured to segment the IMU data sequence according to a preset time division window to obtain a plurality of IMU data sequence segments, and calculate median data corresponding to each IMU data sequence segment according to the number of sampled data in each IMU data sequence segment.

17. The apparatus of claim 16, wherein the error correction module is specifically configured to subtract median data corresponding to the IMU data sequence segment from each sample data in the IMU data sequence segment to obtain corrected IMU data.

18. The apparatus of claim 12, wherein the apparatus further comprises:

the interpolation module is used for carrying out linear interpolation processing on the missing sampling data in the IMU data to obtain IMU data after the linear interpolation processing;

correspondingly, the error correction data acquisition module is specifically configured to process the IMU data after the linear interpolation processing according to the time attribute of each sampling data, so as to obtain the error correction data.

19. The apparatus of any of claims 12-18, wherein the IMU data is IMU acceleration data.

20. The apparatus according to any one of claims 12-18, wherein the apparatus further comprises:

the comprehensive acceleration acquisition module is used for calculating comprehensive acceleration data corresponding to the sampling time of each sampling data according to the corrected IMU data; each comprehensive acceleration data is obtained after calculating the two norms of the corresponding sampling data;

and the driving gesture prediction module is used for predicting the driving gesture of the vehicle by utilizing the comprehensive acceleration data.

21. The apparatus of claim 20, wherein the apparatus further comprises:

the prompt information sending module is used for sending prompt information to the terminal if the predicted result obtained by prediction is that dangerous driving exists in the vehicle; the prompt information is used for prompting the driver to drive safely.

22. A data processing apparatus, the apparatus comprising:

The prompt information receiving module is used for receiving the prompt information issued by the server; the prompt information is related to the driving gesture of the vehicle, and is generated after the server processes the IMU data by the method according to any one of claims 1 to 10.

23. A server comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the method according to any one of claims 1 to 10 when the computer program is executed.

24. A terminal comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the method of claim 11 when executing the computer program.

25. A storage medium having stored thereon a computer program, which when executed by a processor, implements the steps of the method of any of claims 1 to 11.