CN111127876A - Information extraction method and device for Internet of vehicles - Google Patents

Abstract

The embodiment of the application provides an information extraction method and device of a vehicle networking system. The information extraction method of the Internet of vehicles comprises the following steps: acquiring information of a component field in a composite field of a driving area of a vehicle, and determining a field function of the composite field of the driving area based on the information of the component field; sampling information of the component fields to obtain sampling data; and determining frequency spectrum information corresponding to the sampling data based on the field function and the sampling data, and extracting abnormal information from the sampling data according to the frequency spectrum information so as to perform traffic early warning on vehicles in the Internet of vehicles. According to the technical scheme of the embodiment of the application, the abnormal information in the composite field of the driving area is extracted through the frequency spectrum information based on the sampling data, so that the accuracy of data acquisition is improved, and meanwhile, the completeness of the acquired data is guaranteed.

Description

Information extraction method and device for Internet of Vehicles

technical field

The present application relates to the field of computer and communication technologies, and in particular, to an information extraction method and device for Internet of Vehicles.

Background technique

In the monitoring process of many compound fields, the prior art often monitors a single component field, and collects the data of the single component field for analysis to obtain the analysis results of all the compound fields. However, in practical applications, if one component field in the compound field changes, other component fields are often triggered to change along with it. Therefore, the desired information may not be extracted from only one component field, or the extracted information may be incomplete, resulting in one-sided data acquisition, which in turn affects the analysis results of the entire composite field.

SUMMARY OF THE INVENTION

The embodiments of the present application provide an information extraction method and device for the Internet of Vehicles, which can improve the accuracy of data collection at least to a certain extent, and at the same time ensure the completeness of the collected data.

Other features and advantages of the present application will become apparent from the following detailed description, or be learned in part by practice of the present application.

According to an aspect of the embodiments of the present application, there is provided a method for extracting abnormal information of the Internet of Vehicles, including: acquiring information of a component field in a composite field of a driving area of a vehicle, and determining the driving area based on the information of the component field The field function of the composite field; sampling the information of the component field to obtain sampled data; based on the field function and the sampled data, determine the spectrum information corresponding to the sampled data, and the spectrum information is used to characterize the The rate of change of the sampled data; according to the spectrum information, abnormal information is extracted from the sampled data, and the abnormal information is used to carry out traffic warning for vehicles in the Internet of Vehicles.

According to an aspect of the embodiments of the present application, there is provided an information extraction device for the Internet of Vehicles, including:

an acquisition unit, configured to acquire the information of the component fields in the driving area compound field of the vehicle, and determine the field function of the driving area compound field based on the information of the component fields;

a sampling unit, used for sampling the information of the component field to obtain sampling data;

a spectrum unit, configured to determine spectrum information corresponding to the sampled data based on the field function and the sampled data, where the spectrum information is used to characterize the change speed of the sampled data;

An extraction unit, configured to extract abnormal information from the sampled data according to the spectrum information, where the abnormal information is used to provide traffic warning to vehicles in the Internet of Vehicles.

In some embodiments of the present application, based on the foregoing solution, the sampled data includes a sample quantity and a sample value; the frequency spectrum unit is configured to: based on the field function, the sample quantity and the sample value, through a multi-dimensional discrete The spectrum information corresponding to the sampled data is determined by means of Fourier transform.

In some embodiments of the present application, based on the foregoing solution, the extraction unit includes: a first identification unit, configured to set the amplitude parameter of the sampled data to be greater than a preset first value in the spectrogram corresponding to the spectrum information The area with the threshold value is identified as the target area; the second identification unit is used to determine the frequency boundary between the target area and the remaining areas from the spectrogram, and identify the extreme value of the frequency corresponding to the frequency boundary is the second threshold; the first extraction unit is configured to extract, according to the spectrum information, the sampling data when the frequency is greater than the second threshold, as the abnormal information.

In some embodiments of the present application, based on the foregoing solution, the first extraction unit includes: setting the second threshold as a preset filtering threshold of the first high-pass filter; inputting the sampled data into the The first high-pass filter obtains the abnormal information.

In some embodiments of the present application, based on the foregoing solution, the sampling unit includes: sampling the information of the component field to obtain preliminary sampling data; passing the preliminary sampling data through a preset second high-pass filter, Filter out low-frequency data in the preliminary sampling data to obtain the sampling data.

In some embodiments of the present application, based on the foregoing solution, the acquiring unit includes: acquiring video data during the driving of the vehicle; identifying objects in the video data, and determining the driving area according to the characteristics of the objects A component field in a composite field; information of the component field is extracted from the video data based on the characteristics of the object.

In some embodiments of the present application, based on the foregoing solution, the field function includes a field strength function; the obtaining unit includes: determining a field strength function of each component field based on the information of the component fields; combining the field strength functions , the field strength function of the composite field in the driving area is obtained.

In some embodiments of the present application, based on the foregoing solution, the information extraction device for the Internet of Vehicles further includes: predicting the driving risk of the vehicle in the driving area compound field according to the abnormal information; When there is a risk, send risk warning information to the vehicle.

In some embodiments of the present application, based on the foregoing solution, the information extraction device for the Internet of Vehicles further includes: generating a vehicle control instruction according to the abnormal information; sending the control instruction to a control device in the vehicle, to control the vehicle to avoid danger automatically.

According to an aspect of the embodiments of the present application, there is provided a computer-readable medium on which a computer program is stored, and when the computer program is executed by a processor, implements the method for extracting information from the Internet of Vehicles as described in the foregoing embodiments.

According to an aspect of the embodiments of the present application, an electronic device is provided, including: one or more processors; and a storage device for storing one or more programs, when the one or more programs are stored by the one or more programs When executed by multiple processors, the one or more processors are made to implement the method for extracting information from the Internet of Vehicles as described in the foregoing embodiments.

In the technical solutions provided by some embodiments of the present application, the information of the component fields in the driving area compound field of the vehicle is obtained, and the field function of the driving area compound field is determined based on the information of the component fields; the information of the component fields is sampled , obtain the sampled data; based on the field function and the sampled data, determine the spectrum information corresponding to the sampled data, so as to extract abnormal information from the sampled data according to the spectrum information, so as to provide traffic warning to the vehicles in the Internet of Vehicles. The abnormal information in the driving area compound field is extracted based on the spectrum information of the sampled data, which improves the accuracy of data collection and ensures the completeness of the collected data at the same time.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not limiting of the present application.

Description of drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description serve to explain the principles of the application. Obviously, the drawings in the following description are only some embodiments of the present application, and for those of ordinary skill in the art, other drawings can also be obtained from these drawings without creative effort. In the attached image:

FIG. 1 shows a schematic diagram of an exemplary system architecture to which the technical solutions of the embodiments of the present application can be applied;

FIG. 2 schematically shows a schematic diagram of an exemplary system architecture of a technical solution according to an embodiment of the present application;

FIG. 3 schematically shows a flowchart of a method for extracting information from the Internet of Vehicles according to an embodiment of the present application;

FIG. 4 schematically shows a schematic diagram of a driving area compound field of a vehicle according to an embodiment of the present application;

FIG. 5 schematically shows an information flow chart of acquiring a component field in a composite field of a driving area of a vehicle according to an embodiment of the present application;

FIG. 6 schematically shows a flow chart of determining the field function of the driving area composite field based on the information of the component fields according to an embodiment of the present application;

FIG. 7 schematically shows a flowchart of extracting abnormal information from sampling data according to an embodiment of the present application;

FIG. 8 schematically shows a flowchart of a method for extracting abnormal information from a composite field of a driving area based on a multi-dimensional discrete Fourier transform according to an embodiment of the present application;

FIG. 9 schematically shows a flowchart of driving safety field emergency information extraction according to an embodiment of the present application;

FIG. 10 schematically shows a schematic diagram of an application environment of the method for extracting driving information according to an embodiment of the present application;

FIG. 11 schematically shows a block diagram of an information extraction apparatus for the Internet of Vehicles according to an embodiment of the present application;

FIG. 12 shows a schematic structural diagram of a computer system suitable for implementing the electronic device according to the embodiment of the present application.

Detailed ways

Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments, however, can be embodied in various forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this application will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art.

Furthermore, the described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided in order to give a thorough understanding of the embodiments of the present application. However, those skilled in the art will appreciate that the technical solutions of the present application may be practiced without one or more of the specific details, or other methods, components, devices, steps, etc. may be employed. In other instances, well-known methods, devices, implementations, or operations have not been shown or described in detail to avoid obscuring aspects of the present application.

The block diagrams shown in the figures are merely functional entities and do not necessarily necessarily correspond to physically separate entities. That is, these functional entities may be implemented in software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor devices and/or microcontroller devices entity.

The flowcharts shown in the figures are only exemplary illustrations and do not necessarily include all contents and operations/steps, nor do they have to be performed in the order described. For example, some operations/steps can be decomposed, and some operations/steps can be combined or partially combined, so the actual execution order may be changed according to the actual situation.

FIG. 1 shows a schematic diagram of an exemplary system architecture to which the technical solutions of the embodiments of the present application can be applied.

As shown in FIG. 1 , the system architecture may include a collection device, a network 104 and a server 105 . The collection device in this embodiment may be one or more of the terminal device 101 , the vehicle-mounted device 102 and the position sensor 103 . Wherein, the terminal device 101 may include a smart phone, a tablet computer, a computer, etc.; the vehicle-mounted device 102 may include a vehicle-mounted terminal, a vehicle-mounted radar, etc.; . The network 104 is the medium used to provide the communication link between the collection device and the server 105 . The network 104 may include various connection types, such as wired communication links, wireless communication links, and the like.

It should be understood that the numbers of collection devices, networks and servers in FIG. 1 are merely illustrative. According to implementation needs, there can be any number of collection devices, networks and servers. For example, the server 105 may be a server cluster composed of multiple servers, or the like.

The collecting device of this embodiment interacts with the server 105 through the network 104, so that the server 105 obtains the information of the component fields in the driving area compound field of the vehicle, and determines the field function of the driving area compound field based on the information of the component fields; Based on the field function and the sampled data, the spectrum information corresponding to the sampled data is determined, so as to extract abnormal information from the sampled data according to the spectrum information, so as to provide traffic warning to the vehicles in the Internet of Vehicles. The abnormal information in the driving area compound field is extracted based on the spectrum information of the sampled data, which improves the accuracy of data collection and ensures the completeness of the collected data at the same time.

It should be noted that the information extraction method of the Internet of Vehicles provided by the embodiments of the present application is generally executed by the server 105 , and accordingly, the information extraction apparatus of the Internet of Vehicles is generally set in the server 105 . However, in other embodiments of the present application, the terminal device may also have similar functions to the server, so as to execute the solution for information extraction of the Internet of Vehicles provided by the embodiments of the present application.

FIG. 2 shows a schematic diagram of an exemplary system architecture to which the technical solutions of the embodiments of the present application can be applied.

As shown in FIG. 2 , the system architecture may include a vehicle 201 , an in-vehicle terminal 202 and/or a vehicle control device 203 . Among them, the on-board terminal 202 in the vehicle 201 can collect the data during the driving of the vehicle, and the on-board terminal here is used to directly or indirectly obtain the road condition data during the driving of the vehicle 201, and the specific road condition data types are not specified here. To make restrictions, such as positioning data, etc., you can also shoot the driving environment video during the driving process of the vehicle in real time, and analyze the driving environment video to obtain road condition data. The in-vehicle terminal 202 acquires the information of the component fields in the driving area composite field of the vehicle, and determines the field function of the driving area composite field based on the information of the component fields; samples the information of the component fields to obtain sampled data; based on the field function and the sampled data , and determine the spectrum information corresponding to the sampled data, so as to extract abnormal information from the sampled data according to the spectrum information, so as to carry out traffic warning for vehicles in the Internet of Vehicles. The abnormal information in the driving area compound field is extracted based on the spectrum information of the sampled data, which improves the accuracy of data collection and ensures the completeness of the collected data at the same time.

During the early warning process, the on-board terminal 202 may issue an alarm notification to notify the driver to pay attention to driving.

In addition, in the application scenario of automatic driving, after the vehicle-mounted terminal 202 extracts abnormal information from the sampled data, it generates a vehicle control command according to the abnormal information, and sends the control command to the vehicle control device 203, so that the vehicle controls The device controls the safe driving of the vehicle based on the control instruction, so as to control the vehicle to automatically avoid danger. By generating control instructions according to the extracted abnormal information, the accuracy of the control instructions is improved, and the stability and safety of automatic driving are more effectively guaranteed.

The implementation details of the technical solutions of the embodiments of the present application are described in detail below:

3 shows a flowchart of a method for extracting information from the Internet of Vehicles according to an embodiment of the present application. The method for extracting information from the Internet of Vehicles can be executed by a server, and the server can be the server shown in FIG. 1; Executed by a terminal device, which may be the vehicle-mounted terminal shown in FIG. 2 . Referring to FIG. 3 , the method for extracting information from the Internet of Vehicles includes at least steps S310 to S340, which are described in detail as follows:

In step S310, the information of the component fields in the driving area compound field of the vehicle is acquired, and the field function of the driving area compound field is determined based on the information of the component fields.

As shown in FIG. 4 , FIG. 4 is a schematic diagram of a driving area compound field of a vehicle provided in an embodiment of the present application. In an embodiment of the present application, the driving area composite field is composed of at least one component field. Because sampling, transmission, calculation, etc. all take time, the burst information of one of the component fields may be triggered within this period of time. The burst information of other component fields, so the burst information may not be extracted from only one type of component field or the extracted information may be incomplete. Therefore, the component fields in this embodiment are the composite results of different types of component fields, such as the composite fields of multiple types of driving areas, that is, the component fields in the actual road are functions of different types of component fields, and then the composition fields of different types of component fields are obtained. Compound results.

Gravitational field theory is used to model the risks posed by non-moving objects that may be involved in a collision (such as a parked vehicle), and spring field theory is used to simulate non-moving objects that are not involved in a collision but can put pressure on the driver ( such as traffic signs), the gravitational field theory incorporating the Doppler effect can simulate the risk brought by moving objects, and the gravitational field theory incorporating the Doppler effect and driver risk factors can simulate the risk caused by driver behavior . These component fields are the component fields, and after they are fused, the driving area composite field is formed. In this embodiment, the field function of the driving area compound field is determined according to the information of the component fields in the driving area compound field of the vehicle.

In an embodiment of the present application, as shown in FIG. 5 , the process of acquiring the information of the component fields in the composite field of the driving area of the vehicle in step S310 includes the following steps S510 to S530, which are described in detail as follows:

In step S510, video data during the running of the vehicle is acquired.

In an embodiment of the present application, in the process of acquiring the information of the component fields in the composite field of the driving area of the vehicle, it can be acquired by means of video information. In this embodiment, the video data during the driving of the vehicle may be acquired by the camera device. For example, video data may be acquired through a vehicle driving recorder, a roadside camera, a road-testing radar, or a vehicle-mounted visual device, which is not limited here.

In step S520, an object in the video data is identified, and a component field in the composite field of the driving area is determined according to the characteristics of the object.

In an embodiment of the present application, the component fields in the driving area composite field are identified in real time. For example, traffic participants, such as vehicles, pedestrians, etc.; can identify in real time what traffic elements are on the road, including non-moving objects that may be involved in a collision, such as parked vehicles; not involved in a collision but will Non-moving objects such as traffic signs, moving objects, etc., where the operator exerts pressure.

In an embodiment of the present application, by identifying objects in the video data, according to the characteristics of the objects, it is determined how many kinds of component fields the target area has, that is, how many kinds of component fields constitute the driving area composite field of the target area, and the types of the component fields are recorded. The number is d, and E1, E2,...,E _d are used to represent d component fields respectively;

In addition, after the roadside camera is identified, the identification information can be uploaded to the traffic management platform, so that other vehicles can obtain the component field information in real time from the traffic management platform.

In an embodiment of the present application, although identification is also mentioned here, because the identification effect is not always completely credible, it cannot completely identify burst information, and this embodiment can obtain abnormal information by processing data. The extraction of burst information in this embodiment may be based only on component field data. For example, through the data of the component field, the sudden information can be analyzed from it, and then the judgment of the traffic accident can be guided.

In step S530, the information of the component field is extracted from the video data based on the feature of the object.

In an embodiment of the present application, after the component fields in the driving area composite field are identified, according to the component fields in the driving area composite field, the information of the component fields is extracted from the video data based on the characteristics of the object, that is, in the video The information of a component field is separated from the data.

In an embodiment of the present application, as shown in FIG. 6 , the process of determining the field function of the driving area composite field based on the information of the component field in step S310 includes the following steps S610 to S620, which are described in detail as follows:

In step S610, the field strength function of each component field is determined based on the information of the component fields.

In an embodiment of the present application, the vehicle driving area is regarded as a physical field, and a vehicle running in this field may have a potential risk of being collided by other vehicles. In this embodiment, the information of each component field is represented by a field strength function. In this embodiment, the field strength function E of each component field is determined according to the information of the component fields. Let's take an electric or magnetic field as an example. The driving safety field is similar to an electric or magnetic field, and its strength is similar to that of an electric or magnetic field. Therefore, the field strength of the driving safety field is similar to the electric field strength and the magnetic field strength, so it is also denoted by E.

Specifically, in the process of determining the field strength function, the vehicle information, such as the relative speed of the vehicle, the angle of the driving wind direction between the vehicles, the vehicle mass, the viscosity of the surface, the curvature, etc., are brought into the gravitational field theory model in the field of physics, The spring potential energy model and the Doppler effect model are used to calculate the potential collision strength between vehicles, which is the field strength for the safe and smooth driving. The field strength of the driving safety field is obtained by measurement or other methods. For example, by sampling a certain driving safety field, the field strength of its driving safety field is 100N/V (ox/car), that is, the average collision force brought by each vehicle is 100N.

In step S620, the field strength functions are combined to obtain a field strength function of the composite field of the driving area.

In an embodiment of the present application, there is sudden information in the component field, that is, there is sudden information in the actual traffic road or geographical area, such as a vehicle suddenly changing lanes, a vehicle braking suddenly, a pedestrian suddenly entering , this information has a great impact on vehicle safety. In a road or a certain area, there are often different types of safety fields, and each field affects each other. Therefore, burst information may not be extracted from only one type of security field or the extracted burst information may be incomplete.

In this embodiment, the information is extracted from different types of safety fields, that is, the burst information extraction of the driving area composite field, the field strength function of the component fields is obtained, and the field strength functions of all the component fields are combined to obtain the driving area composite field. Field strength function of the field.

Exemplarily, in this embodiment, the field strength function of the driving area composite field is obtained by summing the field strength functions of all the component fields in the driving area composite field, or weighted summation, etc.

In step S320, the information of the component field is sampled to obtain sampled data.

In an embodiment of the present application, after the component field of the composite field in the driving area is determined, the information of the component field in the driving process of the vehicle is sampled, that is, according to the data characteristics in the component field, the information of the component field in the driving process of the vehicle is collected. The environmental data or driving data corresponding to the data features are obtained to obtain sampling data.

In an embodiment of the present application, the sampling data in this embodiment may be field strength data, vehicle speed, obstacle data, etc., which are not limited here.

In an embodiment of the present application, the process of sampling the information of the component field in step S320 to obtain the sampled data includes the following steps:

Sampling the information of the component field to obtain preliminary sampling data;

Passing the preliminary sampling data through a preset second high-pass filter to filter out low-frequency data in the preliminary sampling data to obtain the sampling data.

Specifically, in an embodiment of the present application, preliminary sampling data is obtained by sampling the component field information. The preliminary sampling data in this embodiment is complete data, and there is a large amount of redundant data in these data. Therefore, the preliminary sampling data needs to be filtered to obtain relatively accurate data.

In an embodiment of the present application, after the preliminary sampling data is obtained, the preliminary sampling data is passed through a preset second high-pass filter to obtain sampling information with a higher frequency. Specifically, the preliminary sampling information is passed through the second high-pass filter, and the frequency threshold of the second high-pass filter can be selected to be lower. The sampling information of the threshold value cannot pass through the filter, and the sampling information higher than the threshold value can obtain the sampling data of higher frequency.

In step S330, based on the field function and the sampled data, spectrum information corresponding to the sampled data is determined, where the spectrum information is used to characterize the change speed of the sampled data.

In an embodiment of the present application, after obtaining the field function and the sampled data, spectrum information corresponding to the sampled data is determined, so as to represent the change speed of the sampled data through the spectrum information.

In an embodiment of the present application, the sampled data includes the number of samples and the sampled value; in step S330, based on the field function and the sampled data, the process of determining the spectrum information corresponding to the sampled data includes the following steps:

Based on the field function, the number of samples and the sample value, the spectral information corresponding to the sampled data is determined by means of multi-dimensional discrete Fourier transform.

表示对E_i∈{E₁,E₂,...,E_d}进行采样得到的第j_i∈{1,2,...,n_i}个采样值；用f(E₁,E₂,...,E_d)表示行驶区域复合场的场函数，对该场函数进行多维离散傅里叶变换，得到行驶区域复合场的采样数据对应的频谱信息：Specifically, in an embodiment of the present application, the component fields obtained by sampling the driving safety field are respectively E ₁ , E ₂ ,...,E _d , respectively denoted by n ₁ ,n ₂ ,...,n _d The number of sampled values obtained by sampling E ₁ , E ₂ ,...,E _d , use

represents the j _i ∈ {1,2,...,n _i } sampled value obtained by sampling E _i ∈{E ₁ ,E ₂ ,...,E _d }; use f(E ₁ ,E ₂ ,...,E _d ) represents the field function of the composite field in the driving area, and multi-dimensional discrete Fourier transform is performed on the field function to obtain the spectral information corresponding to the sampled data of the composite field in the driving area:

in,

In step S340, according to the spectrum information, abnormal information is extracted from the sampled data, and the abnormal information is used to carry out traffic warning for vehicles in the Internet of Vehicles.

In an embodiment of the present application, after obtaining the spectrum information corresponding to the sampled data of the composite field of the driving area, abnormal information is extracted from the sampled data according to the spectrum information, so as to provide traffic warning to the vehicles in the vehicle network.

In an embodiment of the present application, the abnormal information in this embodiment includes burst data, and sampling data with a relatively high frequency can be identified as burst data.

In an embodiment of the present application, as shown in FIG. 7 , the process of extracting abnormal information from the sampled data according to the spectrum information in step S340 includes the following steps S710 to S730, which are described in detail as follows:

In step S710, in the spectrogram corresponding to the spectrum information, a region where the amplitude parameter of the sampled data is greater than a preset first threshold is identified as a target region.

In an embodiment of the present application, Fourier transform is performed on the obtained sampling data with higher frequency to obtain a spectrum of information with higher frequency, and a region with high frequency and large amplitude is found from the spectrum as the target region. Among them, the amplitude represents the large field strength of the driving safety field generated by the sampling information of this frequency, which brings great danger to the traffic participants.

Specifically, if the sum of the amplitude of u ₁ of a certain sampled data (referred to as u ₁ ) divided by the amplitude of the sampling information corresponding to all frequencies (referred to as u ₁ , u ₂ ,..., _un ) exceeds If a certain threshold is reached, then the sampled data corresponding to the amplitude u ₁ is abnormal data or burst information. That is, if u ₁ /(u ₁ +u ₂ +... ₊ un )≥p, where p represents the first threshold, then the information whose amplitude is u ₁ is burst information; if in addition to u ₁ , there are The amplitude u _i of other frequencies also satisfies this condition, then the information whose amplitude is u ₁ and u _i are all burst information, that is, the area in the spectrogram corresponding to these data is the target area.

It should be noted that the selection of the threshold p in the above scheme is determined in advance. If you attach great importance to the security risks brought by burst information, then p is set smaller, that is, set more conservatively, so that more burst information will be obtained; otherwise, p can be set larger, so as to obtain Emergent information will be less.

In step S720, a frequency boundary between the target area and the remaining areas is determined from the spectrogram, and an extreme value of the frequency corresponding to the frequency boundary is identified as a second threshold.

In an embodiment of the present application, the frequency boundary between the target area and the remaining areas is continuously found from the frequency spectrum, and the frequency value corresponding to the boundary is obtained as the second threshold, that is, the filtering threshold of the first high-pass filter.

It should be noted that the frequency corresponding to the frequency boundary in this embodiment has a maximum value and a minimum value. In this embodiment, the extreme value of the frequency corresponding to the frequency boundary is identified as the second threshold.

In step S730, according to the spectrum information, the sampling data when the frequency is greater than the second threshold is extracted as the abnormality information.

In an embodiment of the present application, after the second threshold is obtained, the sampling data when the frequency is greater than the second threshold is extracted according to the spectrum information obtained by the previous calculation, as abnormal information or burst information.

In an embodiment of the present application, the sampling data includes the number of samples and the sampling value; in step S730, according to the spectrum information, the sampling data when the frequency is greater than the second threshold is extracted as the process of the abnormal information, It includes the following steps:

Setting the second threshold as a preset filtering threshold of the first high-pass filter;

Inputting the sampled data into the first high-pass filter to obtain the abnormality information.

In an embodiment of the present application, the constant information is obtained by setting the second threshold as the filtering threshold of the first high-pass filter, so as to input the sampled data into the first high-pass filter.

As shown in FIG. 8 , FIG. 8 is a flowchart of a method for extracting abnormal information from a composite field of a driving area based on a multi-dimensional discrete Fourier transform provided by an embodiment of the present application. In FIG. 8, in step S810, determine the driving safety field of the target area, that is, the type of component field, which may include one or more component fields; in step S820, determine the composite driving safety field (ie, the driving area composite field) ) and the functional relationship between each component field; in step S830, each driving safety field is sampled; in step S840, discrete Fourier transform is performed on the driving safety field to determine the value of the sampled data in the driving safety field. Spectrum information; in step S850, extract information with a high frequency of change according to the spectrum information of the sampled data.

Exemplarily, as shown in FIG. 9 , FIG. 9 is a flowchart of driving safety field emergency information extraction provided by an embodiment of the present application. In FIG. 9, in step S910, the sampling data of the driving safety field is obtained first; in step S920, multi-dimensional discrete Fourier transform is performed on the sampled data to determine the spectral information of the sampled data; in step S930, according to the spectral information, Pass the sampled data through a high-pass filter to obtain the burst information of the driving safety field in step S940.

In an embodiment of the present application, in step S340, according to the spectrum information, abnormal information is extracted from the sampled data, and after the abnormal information is used in the process of performing traffic warning on vehicles in the Internet of Vehicles, the process further includes: Follow the steps below:

predicting the driving risk of the vehicle in the driving area compound field according to the abnormal information;

When the driving risk is predicted, risk warning information is sent to the vehicle.

As shown in FIG. 10 , FIG. 10 is a schematic diagram of an application environment of the driving information extraction method provided by the embodiment of the present application. In an embodiment of the present application, the multi-dimensional discrete Fourier transform module 1001 and the high-pass filtering module 1002 jointly extract abnormal data in the driving safety field; the shared data module 1003 mainly provides various types of existing road condition information; the collaborative perception module 1004 It is mainly composed of information sending units including vehicle sensors and is used to sample the driving safety field. The temperature acquisition function module is written in C in the vehicle sensor of the collaborative sensing part, the data analysis and statistics module of traffic data and parking lot data is written in python in the shared data part, and MATLAB is used in the multi-dimensional discrete Fourier transform module and the high-pass filter module. Write; determine how many driving safety fields there are in the target area to form the composite driving safety field of the target area (that is, the driving area composite field), determine the functional relationship between the composite driving safety field and each component field, sample the driving safety field, record the sampling values The number of samples of each driving safety field, the multi-dimensional discrete Fourier transform is used to separate the information with higher changing frequency and the information with lower changing frequency, and the low-pass filter is used to extract the high-frequency information, which is the burst information.

In the actual application process of the method in this embodiment, if there is a sudden factor in the driving safety field and it is extracted, it is judged that the extraction is correct. Based on this method, we obtained statistics on the winning rate of extracting abnormal information by the method in this embodiment, as shown in the following table:

Table 1 The correct rate of burst information extraction in the prior art and the technology in this embodiment

To sum up, the method in this embodiment takes time for sampling, transmission, calculation, etc., so the sudden information of one type of driving safety field may trigger the sudden information of other types of driving safety field during this period. Only from one type of component field may not extract burst information or the extracted information is incomplete. Therefore, the present embodiment considers the extraction of burst information from many different types of driving safety fields.

The following describes the device embodiments of the present application, which can be used to execute the method for extracting information from the Internet of Vehicles in the above-mentioned embodiments of the present application. For details not disclosed in the device embodiments of the present application, please refer to the above-mentioned embodiments of the information extraction method for the Internet of Vehicles in the present application.

FIG. 11 shows a block diagram of an information extraction apparatus for the Internet of Vehicles according to an embodiment of the present application.

Referring to FIG. 11 , an information extraction apparatus 1100 for the Internet of Vehicles according to an embodiment of the present application includes:

an obtaining unit 1110, configured to obtain the information of the component fields in the driving area composite field of the vehicle, and determine the field function of the driving area composite field based on the information of the component fields;

a sampling unit 1120, configured to sample the information of the component field to obtain sampled data;

a spectrum unit 1130, configured to determine spectrum information corresponding to the sampled data based on the field function and the sampled data, where the spectrum information is used to characterize the change speed of the sampled data;

The extraction unit 1140 is configured to extract abnormal information from the sampled data according to the spectrum information, where the abnormal information is used to perform traffic warning for vehicles in the Internet of Vehicles.

In some embodiments of the present application, based on the foregoing solution, the sampled data includes a sample quantity and a sample value; the frequency spectrum unit is configured to: based on the field function, the sample quantity and the sample value, through a multi-dimensional discrete The spectrum information corresponding to the sampled data is determined by means of Fourier transform.

In some embodiments of the present application, based on the foregoing solution, the extracting unit 1140 includes: a first identifying unit, configured to set the amplitude parameter of the sampled data to be greater than a preset first identification unit in the spectrogram corresponding to the spectrum information An area with a threshold is identified as a target area; a second identification unit is used to determine the frequency boundary between the target area and the rest of the areas from the spectrogram, and determine the extreme value of the frequency corresponding to the frequency boundary It is identified as the second threshold; the first extraction unit is configured to extract, according to the spectrum information, the sampling data when the frequency is greater than the second threshold, as the abnormal information.

In some embodiments of the present application, based on the foregoing solution, the first extraction unit includes: setting the second threshold as a preset filtering threshold of the first high-pass filter; inputting the sampled data into the The first high-pass filter obtains the abnormal information.

In some embodiments of the present application, based on the foregoing solution, the sampling unit 1120 includes: sampling the information of the component field to obtain preliminary sampling data; passing the preliminary sampling data through a preset second high-pass filter , filtering out low-frequency data in the preliminary sampling data to obtain the sampling data.

In some embodiments of the present application, based on the foregoing solution, the acquiring unit 1110 includes: acquiring video data during the driving of the vehicle; identifying objects in the video data, and determining the driving according to the characteristics of the objects A component field in a regional composite field; the information of the component field is extracted from the video data based on the characteristics of the object.

In some embodiments of the present application, based on the foregoing solution, the field function includes a field strength function; the obtaining unit 1110 includes: determining the field strength function of each component field based on the information of the component fields; combining the field strengths function to obtain the field strength function of the composite field in the driving area.

In some embodiments of the present application, based on the foregoing solution, the information extraction apparatus 1100 for the Internet of Vehicles further includes: predicting the driving risk of vehicles in the driving area compound field according to the abnormal information; When driving is risky, send risk warning information to the vehicle.

In some embodiments of the present application, based on the foregoing solution, the information extraction device 1100 for the Internet of Vehicles further includes: generating a vehicle control instruction according to the abnormal information; sending the control instruction to a control device in the vehicle , to control the vehicle to avoid danger automatically.

FIG. 12 shows a schematic structural diagram of a computer system suitable for implementing the electronic device according to the embodiment of the present application.

It should be noted that the computer system 1200 of the electronic device shown in FIG. 12 is only an example, and should not impose any limitations on the functions and scope of use of the embodiments of the present application.

As shown in FIG. 12, the computer system 1200 includes a central processing unit (Central Processing Unit, CPU) 1201, which can be loaded into a random device according to a program stored in a read-only memory (Read-Only Memory, ROM) 1202 or from a storage part 1208 A program in a memory (Random Access Memory, RAM) 1203 is accessed to perform various appropriate actions and processes, for example, the methods described in the above embodiments are performed. In the RAM 1203, various programs and data necessary for system operation are also stored. The CPU 1201 , the ROM 1202 , and the RAM 1203 are connected to each other through a bus 1204 . An Input/Output (I/O) interface 1205 is also connected to the bus 1204 .

The following components are connected to the I/O interface 1205: an input section 1206 including a keyboard, a mouse, etc.; an output section 1207 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc. ; a storage section 1208 including a hard disk and the like; and a communication section 1209 including a network interface card such as a LAN (Local Area Network) card, a modem, and the like. The communication section 1209 performs communication processing via a network such as the Internet. Drivers 1210 are also connected to I/O interface 1205 as needed. A removable medium 1211, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is mounted on the drive 1210 as needed so that a computer program read therefrom is installed into the storage section 1208 as needed.

In particular, according to embodiments of the present application, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising a computer program for performing the method illustrated in the flowchart. In such an embodiment, the computer program may be downloaded and installed from the network via the communication portion 1209, and/or installed from the removable medium 1211. When the computer program is executed by the central processing unit (CPU) 1201, various functions defined in the system of the present application are executed.

It should be noted that the computer-readable medium shown in the embodiments of the present application may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the above two. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or a combination of any of the above. More specific examples of computer readable storage media may include, but are not limited to, electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), erasable Erasable Programmable Read Only Memory (EPROM), flash memory, optical fiber, portable Compact Disc Read-Only Memory (CD-ROM), optical storage device, magnetic storage device, or any suitable of the above The combination. In this application, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this application, however, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying a computer-readable computer program therein. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device . A computer program embodied on a computer-readable medium may be transmitted using any suitable medium, including but not limited to: wireless, wired, etc., or any suitable combination of the foregoing.

The flowchart and block diagrams in the Figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. Wherein, each block in the flowchart or block diagram may represent a module, program segment, or part of code, and the above-mentioned module, program segment, or part of code contains one or more executables for realizing the specified logical function instruction. It should also be noted that, in some alternative implementations, the functions noted in the blocks may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It is also noted that each block of the block diagrams or flowchart illustrations, and combinations of blocks in the block diagrams or flowchart illustrations, can be implemented in special purpose hardware-based systems that perform the specified functions or operations, or can be implemented using A combination of dedicated hardware and computer instructions is implemented.

The units involved in the embodiments of the present application may be implemented in software or hardware, and the described units may also be provided in a processor. Among them, the names of these units do not constitute a limitation on the unit itself under certain circumstances.

As another aspect, the present application also provides a computer-readable medium. The computer-readable medium may be included in the electronic device described in the above embodiments; it may also exist alone without being assembled into the electronic device. middle. The above-mentioned computer-readable medium carries one or more programs, and when the above-mentioned one or more programs are executed by an electronic device, enables the electronic device to implement the methods described in the above-mentioned embodiments.

It should be noted that although several modules or units of the apparatus for action performance are mentioned in the above detailed description, this division is not mandatory. Indeed, according to embodiments of the present application, the features and functions of two or more modules or units described above may be embodied in one module or unit. Conversely, the features and functions of one module or unit described above may be further divided into multiple modules or units to be embodied.

From the description of the above embodiments, those skilled in the art can easily understand that the exemplary embodiments described herein may be implemented by software, or may be implemented by software combined with necessary hardware. Therefore, the technical solutions according to the embodiments of the present application may be embodied in the form of software products, and the software products may be stored in a non-volatile storage medium (which may be CD-ROM, U disk, mobile hard disk, etc.) or on the network , which includes several instructions to cause a computing device (which may be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the embodiments of the present application.

Other embodiments of the present application will readily occur to those skilled in the art upon consideration of the specification and practice of the embodiments disclosed herein. This application is intended to cover any variations, uses or adaptations of this application that follow the general principles of this application and include common knowledge or conventional techniques in the technical field not disclosed in this application .

It is to be understood that the present application is not limited to the precise structures described above and illustrated in the accompanying drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the application is limited only by the appended claims.

Claims (10)

1. an abnormal information extraction method of Internet of Vehicles, is characterized in that, comprises: acquiring information of a component field in the driving area compound field of the vehicle, and determining a field function of the driving area compound field based on the information of the component field; Sampling the information of the component field to obtain sampling data; determining, based on the field function and the sampled data, spectrum information corresponding to the sampled data, where the spectrum information is used to characterize the change speed of the sampled data; According to the spectrum information, abnormal information is extracted from the sampled data, and the abnormal information is used to carry out traffic warning for vehicles in the Internet of Vehicles. 2. method according to claim 1, is characterized in that, described sampling data comprises sampling quantity and sampling value; Based on the field function and the sampled data, determining the spectrum information corresponding to the sampled data, including: Based on the field function, the number of samples and the sample value, the spectral information corresponding to the sampled data is determined by means of multi-dimensional discrete Fourier transform. 3. The method according to claim 1, wherein, according to the spectrum information, extracting abnormal information from the sampled data, comprising: In the spectrogram corresponding to the spectrum information, the area where the amplitude parameter of the sampled data is greater than the preset first threshold is identified as the target area; Determine the frequency boundary between the target area and the remaining areas from the spectrogram, and identify the extreme value of the frequency corresponding to the frequency boundary as the second threshold; According to the spectrum information, sampling data when the frequency is greater than the second threshold is extracted as the abnormal information. 4. The method according to claim 3, wherein, according to the spectrum information, extracting the sampling data when the frequency is greater than the second threshold, as the abnormal information, comprising: Setting the second threshold as a preset filtering threshold of the first high-pass filter; Inputting the sampled data into the first high-pass filter to obtain the abnormality information. 5. The method according to claim 1, wherein the information of the component field is sampled to obtain sampled data, comprising: Sampling the information of the component field to obtain preliminary sampling data; Passing the preliminary sampling data through a preset second high-pass filter to filter out low-frequency data in the preliminary sampling data to obtain the sampling data. 6. The method according to claim 1, wherein acquiring the information of the component field in the composite field of the driving area of the vehicle comprises: acquiring video data during the driving of the vehicle; Identifying objects in the video data, and determining a component field in the composite field of the driving area according to the characteristics of the objects; The information of the component field is extracted from the video data based on the characteristics of the object. 7. The method according to claim 1, wherein the field function comprises a field strength function; and determining the field function of the driving area composite field based on the information of the component fields, comprising: Determine the field strength function of each component field based on the information of the component field; The field strength functions are combined to obtain the field strength function of the composite field of the driving area. 8. The method according to claim 1, wherein, after extracting abnormal information from the sampled data according to the spectrum information, the method further comprises: predicting the driving risk of the vehicle in the driving area compound field according to the abnormal information; When the driving risk is predicted, risk warning information is sent to the vehicle. 9. The method according to any one of claims 1-8, wherein, after extracting abnormal information from the sampled data according to the spectrum information, the method further comprises: generating vehicle control instructions according to the abnormal information; The control command is sent to a control device in the vehicle to control the vehicle to automatically avoid danger. 10. An information extraction device for Internet of Vehicles, characterized in that it comprises: an acquisition unit, configured to acquire the information of the component fields in the driving area compound field of the vehicle, and determine the field function of the driving area compound field based on the information of the component fields; a sampling unit, used for sampling the information of the component field to obtain sampling data; a spectrum unit, configured to determine spectrum information corresponding to the sampled data based on the field function and the sampled data, where the spectrum information is used to characterize the change speed of the sampled data; An extraction unit, configured to extract abnormal information from the sampled data according to the spectrum information, where the abnormal information is used to provide traffic warning to vehicles in the Internet of Vehicles.

Images