Method, device, equipment, storage medium and program product for identifying rough road sections

Abstract

The present disclosure provides a method, device, equipment, storage medium and program product for identifying a bumping road section, relates to the technical field of computers, and particularly relates to the technical fields of smart cities, intelligent transportation and electronic maps. A specific implementation scheme is as follows: a vehicle driving data set is acquired, the vehicle driving data set including driving time sequence trajectories collected in a vehicle driving process and audio data, the driving time sequence trajectories and the audio data having a correlation in time sequence; in the audio data, target audio data frames having bumping road section audio features are identified; based on the correlation, target trajectory points associated with the target audio data frames are identified in the driving time sequence trajectories; bumping trajectory points are determined based on the target trajectory points, and a bumping road section is determined based on the bumping trajectory points. The method for identifying a bumping road section provided by the present disclosure can more efficiently find potential road damage.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to technical fields such as smart cities, intelligent transportation, and electronic maps. Background Art

[0002] As the infrastructure of urban construction, roads carry a large amount of traffic activities every day. With the intensification of human activities and the erosion of the natural environment, the condition of roads is suffering varying degrees of damage every day.

[0003] Related technologies provide methods for identifying bumpy roads to identify potential road damage, assisting road construction and maintenance departments in efficiently carrying out road maintenance. Currently, methods for identifying bumpy roads include field surveys, using positioning and gyroscopes to determine vehicle position, acceleration, and attitude data, and predicting bumpy sections based on existing road section information. Summary of the Invention

[0004] The present disclosure provides a method, apparatus, device, storage medium, and program product for identifying bumpy road sections.

[0005] According to one aspect of the present disclosure, a method for identifying a bumpy road section is provided, comprising:

[0006] A vehicle driving data set is obtained, wherein the vehicle driving data set includes a driving time-series trajectory and audio data collected during vehicle driving, and the driving time-series trajectory and the audio data have a temporal correlation relationship; in the audio data, a target audio data frame having audio characteristics of a bumpy road section is identified; based on the correlation relationship, a target trajectory point associated with the target audio data frame is identified in the driving time-series trajectory; a bumpy trajectory point is determined based on the target trajectory point, and a bumpy road section is determined based on the bumpy trajectory point.

[0007] According to another aspect of the present disclosure, there is provided an apparatus for identifying a bumpy road section, comprising:

[0008] An acquisition unit is used to acquire a vehicle driving data set, wherein the vehicle driving data set includes a driving time-series trajectory and audio data collected during the vehicle driving process, and the driving time-series trajectory and the audio data have a temporal correlation relationship; an identification unit is used to identify a target audio data frame having audio features of a bumpy road section in the audio data, and based on the correlation relationship, identify a target trajectory point associated with the target audio data frame in the driving time-series trajectory, determine a bumpy trajectory point based on the target trajectory point, and determine a bumpy road section based on the bumpy trajectory point.

[0009] According to another aspect of the present disclosure, there is provided an electronic device, comprising:

[0010] at least one processor; and a memory communicatively connected to the at least one processor; wherein,

[0011] The memory stores instructions that can be executed by the at least one processor. The instructions are executed by the at least one processor to enable the at least one processor to perform the above-mentioned method.

[0012] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute the above-mentioned method.

[0013] According to another aspect of the present disclosure, a computer program product is provided, comprising a computer program, wherein the computer program implements the above-mentioned method when executed by a processor.

[0014] The method for identifying bumpy road sections provided by the present disclosure can more efficiently discover potential road damage.

[0015] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The accompanying drawings are provided to facilitate a better understanding of the present invention and do not constitute a limitation of the present disclosure.

[0017] Figure 1 is a flow chart of a method for identifying a bumpy road section according to an exemplary embodiment of the present disclosure;

[0018] Figure 2 is a flow chart of a method for identifying a target audio data frame having audio features of a bumpy road section according to an exemplary embodiment of the present disclosure;

[0019] Figure 3 is a flow chart of a method for training a bumpy road audio model according to an exemplary embodiment of the present disclosure;

[0020] Figure 4 is a flow chart of a method for locating a bumpy road according to an exemplary embodiment of the present disclosure;

[0021] Figure 5 is a block diagram of a device for identifying bumpy road sections according to the present disclosure;

[0022] Figure 6 It is a block diagram of an electronic device used to implement the method for identifying bumpy road sections according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0023] The following description of exemplary embodiments of the present disclosure is made in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding. These details should be considered as merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0024] The method for identifying bumpy road sections provided by the present disclosure can be applied to scenarios such as road maintenance in urban construction, electronic maps, route planning, and other navigation information prompts. For example, the present disclosure can be applied to scenarios where bumpy road sections are identified based on a large number of vehicle driving trajectories, and road maintenance is performed based on the identified bumpy road sections.

[0025] The bumpy road section identification solutions provided in related technologies mainly include the following methods:

[0026] (1) On-site inspection: Based on the time of road construction and maintenance and road maintenance experience, on-site inspections are conducted at regular intervals and locations to confirm road conditions.

[0027] (2) Positioning + gyroscope equipment: Based on the trajectory of the moving vehicle and the gyroscope equipment, the driving position and the vehicle acceleration, posture and other data at that position are obtained, and the road bumps are calculated and analyzed to confirm the bumpy road sections.

[0028] (3) Bump warning: Based on known bumpy road data, the system warns the vehicle of potential bumpy roads ahead through real-time communication with the vehicle.

[0029] However, method (1) requires manual on-site verification to confirm bumpy road sections, which is labor-intensive. Method (2) requires the use of relatively accurate gyroscope equipment and the establishment of a relatively complex algorithm based on the gyroscope data to analyze potential driving bumps, which places relatively high demands on equipment and algorithms. Method (3) also requires the establishment of a relatively complex algorithm to analyze potential driving bumps, which places relatively high demands on the algorithm.

[0030] Therefore, providing a low-manpower-cost, simple and efficient solution for identifying bumpy road sections is an urgent problem to be solved.

[0031] The present disclosure provides a method for identifying a bumpy road section. In the method for identifying a bumpy road section, the bumpy road section is identified based on a driving time-series trajectory and audio data recorded during driving.

[0032] As an exemplary embodiment, Figure 1 This is a flow chart of a method for identifying bumpy road sections according to an exemplary embodiment of the present disclosure. Figure 1As shown, the method for identifying bumpy road sections provided by the present disclosure includes the following steps S101 to S104.

[0033] In step S101, a vehicle driving data set is obtained, which includes

[0034] Driving time-series trajectory and audio data collected during vehicle driving.

[0035] In this disclosure, the driving time sequence trajectory can be understood as the vehicle's

[0036] The route formed by the corresponding driving position points in the time sequence, in other words, the time sequence trajectory can be formed

[0037] A line is composed of multiple track points that are continuous in time. Audio data can be a vehicle

[0038] The sound generated during driving, the audio data includes multiple audio data frames in time sequence.

[0039] Among them, in the present disclosure, there is a correlation between the driving time sequence trajectory and the audio data.

[0040] In one example, the driving time sequence trajectory and audio data recorded simultaneously during the vehicle driving process can be

[0041] It can be understood as a pair of associated driving time series trajectory and audio data. For example, the same time point will correspond to a trajectory point and an audio data frame.

[0042] The present invention can collect a large number of driving sequence trajectories generated by the same or different vehicles.

[0043] Track and audio data are collected to form a vehicle driving data set.

[0044] In step S102, in the audio data, the audio features of the bumpy road section are identified.

[0045] Target audio data frame.

[0046] Among them, the audio data recorded during vehicle driving will be different for different driving sections.

[0047] Corresponding to different audio features. When a vehicle is driving on a bumpy road, it will produce audio features that match the bumpy road. Therefore, in the present disclosure, the audio data frame with the audio features of the bumpy road can be extracted from the audio data included in the acquired vehicle driving data set, hereinafter referred to as

[0048] The target audio data frame.

[0049] In step S103 , based on the association relationship between the driving time sequence trajectory and the audio data, a target trajectory point associated with the target audio data frame is identified in the driving time sequence trajectory.

[0050] In the present disclosure, when a target audio data frame having a bumpy road audio feature is identified,

[0051] After that, the target track point associated with the target audio data frame can be determined.

[0052] The audio data frame and target trajectory point can be understood as the vehicle in the same

[0053] Data generated at a point in time.

[0054] In the present disclosure, the target trajectory point can be understood as a bumpy trajectory point, which can be determined by clustering multiple trajectory points on the driving time series trajectory.

[0055] For example, the present disclosure can cluster the track points on the driving time series trajectory and determine the regions formed by the clustered track points of the same category. The present disclosure also determines the number of track points within each region. If the number of track points within a region is greater than a threshold, the geometric center of the region can be determined as the target track point.

[0056] In step S104 , a bumpy trajectory point is determined based on the target trajectory point, and a bumpy road section is determined based on the bumpy trajectory point.

[0057] In the present disclosure, since the target audio data frame is audio data having audio characteristics of a bumpy road section, the target trajectory point associated with the target audio data frame can theoretically be understood as a location point on the bumpy road section (bumpy trajectory point). Therefore, based on the target trajectory point, the bumpy trajectory point can be determined, and based on the determined bumpy trajectory point, the bumpy road section can be determined.

[0058] Since the driving time-series trajectory can be acquired by a device with a positioning function, and the audio data can be acquired by a device with an audio recording function, positioning function devices and audio recording devices are generally equipped on vehicles compared to gyroscope devices. In addition, the vehicle is always accompanied by fixed audio, so it is relatively easy to collect audio data during the vehicle's driving. Therefore, in the present disclosure, by recording the audio data generated during the vehicle's driving, the audio data with the audio characteristics of the bumpy road section is identified, and the bumpy road section can be identified by combining the driving time-series trajectory that generates the audio data. The method of identifying bumpy road sections based on driving time-series trajectory and driving audio data provided by the present disclosure has low labor costs, and can simply and efficiently obtain data for identifying bumpy road sections, thereby improving the effectiveness of bumpy road section identification.

[0059] The driving time-series trajectory involved in the embodiments of the present disclosure is collected by a device with a positioning function in the vehicle. The audio data is collected by a device with an audio recording function in the vehicle. Specifically, the driving time-series trajectory and audio data in the present disclosure can be collected by the same device or by different devices. In order to improve data accuracy in the present disclosure, a device with both a positioning function and an audio recording function can be used to collect the driving time-series trajectory and audio data. For example, the driving time-series trajectory and audio data can be collected by a smart rearview mirror with a positioning function in the vehicle, a driving recorder, or other GPS devices.

[0060] In an exemplary embodiment of the present disclosure, a bumpy road section audio model for extracting audio features of bumpy road sections can be pre-trained. When performing bumpy road section audio data recognition, recognition can be performed based on the pre-trained bumpy road section audio model.

[0061] As an exemplary embodiment, Figure 2 This is a flow chart of a method for identifying a target audio data frame with audio features of a bumpy road section according to an exemplary embodiment of the present disclosure. Figure 2 As shown, the method for identifying target audio data frames having bumpy road audio features provided by the present disclosure includes the following steps S201 to S203.

[0062] In step S201, a bumpy road section audio model is called, the input of the bumpy road section audio model is audio data, and the output is bumpy road section audio features.

[0063] In step S202 , the audio data is input into a pre-trained bumpy road audio model.

[0064] In step S203, based on the output result of the bumpy road audio model, a target audio data frame having the bumpy road audio feature is determined.

[0065] In the present disclosure, a pre-trained bumpy road section audio model is called to identify the audio features of the bumpy road section. The target audio data frame with the bumpy road section audio features can be directly determined based on the output results of the bumpy road section audio model, and the target audio data frame with the bumpy road section audio features can be identified relatively quickly.

[0066] In practical applications, different vehicle attributes may produce different audio characteristics on the same bumpy road section. For example, when vehicles of different weights and sound insulation are traveling at different speeds on the same bumpy road, the audio characteristics of the collected audio data may differ. Therefore, in an exemplary embodiment of the present disclosure, a bumpy road audio model can be pre-trained to match different vehicle attributes.

[0067] In an exemplary embodiment of the present disclosure, when identifying a target audio data frame having a bumpy road audio feature and calling a bumpy road audio model, the attributes of the vehicle that generates the audio data included in the vehicle driving data set can be determined, and a bumpy road audio model that matches the vehicle attributes can be called. The target audio data frame can be identified based on the bumpy road audio model that matches the vehicle attributes, thereby further improving the accuracy of identifying the audio data frame having the bumpy road audio feature.

[0068] The following embodiment of the present disclosure describes the training process of the bumpy road audio model.

[0069] As an exemplary embodiment, Figure 3 This is a flow chart of a method for training a bumpy road audio model according to an exemplary embodiment of the present disclosure. Figure 3 As shown, the method for training a bumpy road audio model provided by the present disclosure includes the following steps S301 to S303.

[0070] In step S301 , audio samples generated by vehicles with different vehicle attributes driving on different bumpy road sections are collected.

[0071] In this disclosure, to improve the comprehensiveness of audio sample coverage and the accuracy of model training, audio sample data can be collected based on different dimensions, such as vehicle model, interior sound insulation, bumps, and vehicle speed. In other words, different vehicle attributes in this disclosure include at least one of the following: vehicle model, interior sound insulation, and vehicle speed.

[0072] In the present disclosure, car models of different weights and different sound insulation can be selected, and they can be driven at different speeds on a road with known bumpy locations, and a certain amount of driving audio data can be collected. The audio data at the bumpy locations can be extracted as audio samples to perform sample training data for subsequent audio sample model training. In one example, the sample collection has the following dimensions: car model (sedan, mid-sized car, large truck), in-car sound insulation (no sound insulation, general sound insulation, quiet), bumpy conditions (small bumps, medium bumps, large bumps), and vehicle speed (20-40, 40-60, 60-80+). It can be understood that in the embodiments of the present disclosure, directional adjustments can be made to support specific situations based on the characteristics and needs of specific areas.

[0073] In step S302, a bumpy road audio model is established based on the audio samples.

[0074] In this disclosure, when training an audio model, a bumpy road audio model can be established using machine learning methods based on collected audio sample data. The bumpy road audio model takes audio data as input and outputs audio features common to bumpy road sections, referred to as bumpy road audio features in this disclosure.

[0075] In step S303 , a bumpy road audio model matching different vehicle attributes is obtained through training.

[0076] In this disclosure, because different vehicle attributes correspond to different audio features of bumpy road sections, when training a bumpy road section audio model, based on machine learning and optimization algorithms, separate bumpy road section audio models are trained for vehicles with different attributes to obtain bumpy road section audio models that match different vehicle attributes. The bumpy road section audio models that match different vehicle attributes can be understood as bumpy road section audio models with different standards corresponding to different vehicle attributes.

[0077] Among them, different vehicle attributes can be understood as one or more differences among vehicle type, interior sound insulation, vehicle speed, etc.

[0078] In the present disclosure, collecting audio samples generated by vehicles with different attributes traveling on different bumpy roads ensures diversity and comprehensiveness of the sample data. Furthermore, based on the audio samples, the present disclosure conducts training for vehicles with different attributes, and trains a bumpy road audio model that matches the vehicle attributes. This allows subsequent recognition of bumpy road audio features to utilize the bumpy road audio model that matches the vehicle attributes, thereby improving the accuracy of identifying audio data frames with bumpy road audio features.

[0079] In the present disclosure, when identifying audio data frames having the audio characteristics of a bumpy road section, the audio data from the acquired vehicle travel dataset can be input into a called bumpy road section audio model, and target audio data frames having the audio characteristics of a bumpy road section can be identified based on the output of the bumpy road section audio model. It will be understood that the vehicle travel dataset in the present disclosure includes a large amount of audio data, and all of this large amount of audio data can be input into the called bumpy road section audio model to determine target audio data frames having the audio characteristics of a bumpy road section from the entire audio data. These target audio data frames can form a target audio data frame set.

[0080] In the present disclosure, each target audio data frame identified in the audio data of the vehicle driving dataset may be associated with multiple different driving time-series trajectories. In the present disclosure, it is necessary to determine the bumpy track points associated with the target audio data frames on each of the multiple different driving time-series trajectories, and then determine the bumpy road section based on the bumpy track points.

[0081] In the present disclosure, the target trajectory points associated with the identified target audio data frame belong to multiple driving time series trajectories in the vehicle driving data set.

[0082] Furthermore, due to the many uncertainties inherent in driving, the collected audio data may be noisy and interfered with. The bumpy track points identified based on the target audio data frame identified from the interfered audio data may be inaccurate. Therefore, the present disclosure eliminates errors by cross-comparing the calculation results of a large number of tracks.

[0083] As an exemplary embodiment, when determining a bumpy track point based on a target track point, the embodiment of the present disclosure may determine the number of tracks that the target track point belongs to in different driving time series tracks. If the number of tracks is greater than a threshold, the target track point is determined to be a bumpy track point.

[0084] In the disclosed embodiments, bumpy track points are identified by determining the number of track points that belong to different time-series tracks. This can, to a certain extent, eliminate errors caused by interfered audio data and improve the accuracy of bumpy track point identification. For example, if a location on a road is marked as bumpy by the driving tracks and audio of a large number of different vehicles, there is a high probability that bumpy conditions exist at that location.

[0085] The method for identifying bumpy road sections provided by this disclosure can quickly identify bumpy road sections with low labor costs, thereby discovering a wide range of potential road damage and assisting in road maintenance and navigation using bumpy road sections. For example, it can effectively assist road maintenance departments in carrying out road maintenance work efficiently.

[0086] Among them, in order to use bumpy road sections for road maintenance and navigation, it is necessary to locate the bumpy roads.

[0087] In an exemplary embodiment of the present disclosure, after a bumpy trajectory point is determined, road network data can be retrieved to locate a bumpy road that matches a bumpy road segment corresponding to the bumpy trajectory point, thereby facilitating subsequent road maintenance, navigation prediction, and the like for the bumpy road.

[0088] As an exemplary embodiment, Figure 4 FIG. 1 is a flow chart of a method for locating a bumpy road according to an exemplary embodiment of the present disclosure. Figure 4As shown, devices for bumpy road recognition, such as map data engines, can collect a large amount of vehicle driving data. The collected vehicle driving data includes driving time-series trajectories based on global positioning function (GPS) positioning, and audio data obtained by driving recording. Based on the audio data, a bumpy road section audio model that matches the vehicle attributes is called to extract the bumpy road section audio data frame. According to the time corresponding to the extracted bumpy road section audio data frame, the bumpy trajectory points and bumpy road sections existing in the driving time-series trajectories in the vehicle driving data set are deduced. And for the determined bumpy trajectory points, a large number of cross-comparison results can be used to filter out interference such as audio clutter to obtain bumpy trajectory points with relatively high accuracy. Based on the road network matching method, the bumpy trajectory points in the driving time-series trajectory are matched with the road network to locate the bumpy road corresponding to the bumpy trajectory point, and then the bumpiness of the bumpy road is determined.

[0089] The method disclosed herein for identifying bumpy road sections using driving recordings and vehicle trajectory positioning information can identify bumpy road sections using a simple algorithm. Furthermore, driving recordings and vehicle trajectory positioning information can be acquired using relatively common equipment with relatively low precision requirements, making it relatively easy to promote and apply. For example, the bumpy road section identification method provided herein can be applied in the following scenarios:

[0090] (1) In the construction of smart cities, it can help urban road maintenance departments quickly find bumpy sections and improve the efficiency of problem detection.

[0091] (2) In electronic map navigation products, users can be informed of potential bumpy conditions on the road ahead based on the collected and analyzed bumpy information.

[0092] (3) In truck navigation products, the collected and analyzed bumpy information can be used to plan and guide trucks transporting fragile goods to a smoother route.

[0093] Based on this, the method for identifying bumpy road sections provided by the present disclosure can quickly identify bumpy road sections with low labor costs, thereby discovering a wide range of potential road damage and assisting in road maintenance and navigation using bumpy road sections. For example, it can effectively assist road maintenance departments in carrying out road maintenance work efficiently.

[0094] Based on the same concept, an embodiment of the present disclosure also provides a device for identifying bumpy road sections.

[0095] It is understandable that the device for identifying bumpy road sections provided by the embodiment of the present disclosure includes hardware structures and / or software modules corresponding to the execution of each function in order to achieve the above functions. In combination with the units and algorithm steps of the various examples disclosed in the embodiment of the present disclosure, the embodiment of the present disclosure can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the technical solution of the embodiment of the present disclosure.

[0096] As an exemplary embodiment, Figure 5 This is a block diagram of a device for identifying bumpy road sections according to the present disclosure. Figure 5 As shown, the apparatus 500 for identifying bumpy road sections provided by the present disclosure includes an acquisition unit 501 and an identification unit 502 .

[0097] The acquisition unit 501 is configured to acquire a vehicle driving dataset, wherein the vehicle driving dataset includes a time-series driving trajectory and audio data collected during vehicle driving, wherein the time-series driving trajectory and the audio data are temporally correlated. The identification unit 502 is configured to identify target audio data frames having audio features of a bumpy road section in the audio data, identify target trajectory points associated with the target audio data frames in the time-series driving trajectory based on the correlation, determine bumpy trajectory points based on the target trajectory points, and determine a bumpy road section based on the bumpy trajectory points.

[0098] The identification unit 502 identifies the target audio data frame having the bumpy road section audio feature in the audio data in the following manner:

[0099] Call the bumpy road section audio model, the input of the bumpy road section audio model is audio data, and the output is bumpy road section audio features; input the audio data into the pre-trained bumpy road section audio model, and based on the output result of the bumpy road section audio model, determine the target audio data frame with bumpy road section audio features.

[0100] The recognition unit 502 calls the bumpy road section audio model in the following manner: determining the attributes of the vehicle that generates the audio data included in the vehicle driving data set; and calling the bumpy road section audio model that matches the vehicle attributes.

[0101] The apparatus 500 for identifying bumpy road sections further includes a training unit 503, which is configured to pre-train a bumpy road section audio model using the following method:

[0102] Audio samples generated by vehicles with different vehicle attributes driving on different bumpy roads are collected, where the different vehicle attributes include at least one of the following attributes: vehicle model, interior sound insulation, and vehicle speed. Based on the audio samples, training is performed on vehicles with different vehicle attributes to obtain a bumpy road audio model that matches the vehicle attributes.

[0103] Among them, the target trajectory points associated with the target audio data frame belong to multiple driving time series trajectories in the vehicle driving data set; the identification unit 502 determines the bumpy trajectory point based on the target trajectory point in the following manner: determine the number of trajectories to which the target trajectory point belongs to different driving time series trajectories; if the number of trajectories is greater than the quantity threshold, the target trajectory point is determined as a bumpy trajectory point.

[0104] The device 500 for identifying bumpy road sections further includes a positioning unit 504, which is used to: call the road network data corresponding to the bumpy trajectory point; and locate the bumpy road of the bumpy road section corresponding to the bumpy trajectory point in the road network data.

[0105] Among them, the driving time sequence trajectory is collected by a device with positioning function in the vehicle, and the audio data is collected by a device with audio recording function in the vehicle.

[0106] Regarding the above-mentioned device involved in the present disclosure, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0107] In the technical solutions disclosed herein, the acquisition, storage, and application of user personal information involved comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0108] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0109] Figure 6 A schematic block diagram of an example electronic device 600 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are provided as examples only and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0110] like Figure 6As shown, the device 600 includes a computing unit 601, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 602 or a computer program loaded from a storage unit 608 into a random access memory (RAM) 603. Various programs and data required for the operation of the device 600 can also be stored in the RAM 603. The computing unit 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0111] Various components in device 600 are connected to I / O interface 605, including an input unit 606, such as a keyboard, mouse, etc.; an output unit 607, such as various types of displays, speakers, etc.; a storage unit 608, such as a magnetic disk, optical disk, etc.; and a communication unit 609, such as a network card, modem, wireless communication transceiver, etc. The communication unit 609 allows device 600 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0112] The computing unit 601 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 601 performs the various methods and processes described above, such as the method for identifying bumpy roads. For example, in some embodiments, the method for identifying bumpy roads can be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 608. In some embodiments, part or all of the computer program can be loaded and / or installed onto the device 600 via the ROM 602 and / or the communication unit 609. When the computer program is loaded into the RAM 603 and executed by the computing unit 601, one or more steps of the method for identifying bumpy roads described above can be performed. Alternatively, in other embodiments, the computing unit 601 can be configured to perform the method for identifying bumpy roads by any other suitable means (e.g., via firmware).

[0113] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0114] The program code for implementing the method of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0115] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0116] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0117] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0118] A computer system may include a client and a server. The client and server are generally remote from each other and typically interact through a communication network. The client-server relationship arises through computer programs running on the respective computers and having a client-server relationship with each other. The server may be a cloud server, a server in a distributed system, or a server integrated with a blockchain.

[0119] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved. This is not a limitation herein.

[0120] The above specific embodiments do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the scope of protection of this disclosure.

Claims

1. A method for identifying a bumpy road section, comprising: Acquire a vehicle driving data set, wherein the vehicle driving data set includes a driving time-series trajectory and audio data collected during the vehicle driving process, and the driving time-series trajectory and the audio data have a temporal correlation relationship; Determining vehicle attributes that generate the audio data included in the vehicle driving dataset, calling a bumpy road section audio model that matches the vehicle attributes, and identifying target audio data frames having bumpy road section audio features in the audio data based on the bumpy road section audio model, wherein the vehicle attributes include at least any one of the following: vehicle model, interior sound insulation, and vehicle speed; Based on the association relationship, identifying a target trajectory point associated with the target audio data frame in the driving time series trajectory, where the target trajectory point associated with the target audio data frame belongs to a plurality of driving time series trajectories in the vehicle driving dataset; determining the number of trajectories of the target trajectory point belonging to different driving time series trajectories, and if the number of trajectories is greater than a quantity threshold, determining the target trajectory point as a bumpy trajectory point; A bumpy road section is determined based on the bumpy trajectory points.

2. The method according to claim 1, wherein The step of identifying a target audio data frame having a bumpy road section audio feature in the audio data comprises: The audio data is input into a pre-trained bumpy road audio model, and based on the output result of the bumpy road audio model, a target audio data frame having bumpy road audio features is determined.

3. The method according to claim 1, wherein The bumpy road audio model is pre-trained in the following way: Collecting audio samples generated by vehicles with different vehicle attributes driving on different bumpy road sections, wherein the different vehicle attributes include at least one of the following attributes: vehicle model, interior sound insulation, and vehicle speed; Based on the audio samples, training is performed for vehicles with different vehicle attributes to obtain a bumpy road section audio model that matches the vehicle attributes.

4. The method according to claim 1, further comprising: Call road network data; In the road network data, a bumpy road that matches the bumpy road section corresponding to the bumpy trajectory point is located.

5. The method according to any one of claims 1 to 4, wherein: The driving time sequence trajectory is collected by a device with a positioning function in the vehicle, and the audio data is collected by a device with an audio recording function in the vehicle.

6. A device for identifying bumpy road sections, comprising: an acquisition unit, configured to acquire a vehicle driving data set, wherein the vehicle driving data set includes a driving time-series trajectory and audio data collected during the vehicle driving process, wherein the driving time-series trajectory and the audio data are temporally correlated; an identification unit, for determining a vehicle attribute that generates the audio data included in the vehicle driving data set, calling a bumpy road section audio model that matches the vehicle attribute, identifying a target audio data frame having a bumpy road section audio feature in the audio data based on the bumpy road section audio model, identifying a target trajectory point associated with the target audio data frame in the driving time series trajectory based on the association relationship, and determining the number of trajectories of the target trajectory point belonging to different driving time series trajectories; if the number of trajectories is greater than a quantity threshold, determining the target trajectory point as a bumpy trajectory point, and determining a bumpy road section based on the bumpy trajectory point. The vehicle attributes include at least one of the following: vehicle type, interior sound insulation, and vehicle speed. The target trajectory points associated with the target audio data frame belong to multiple driving time series trajectories in the vehicle driving data set.

7. The device according to claim 6, wherein The recognition unit recognizes the target audio data frame having the bumpy road section audio feature in the audio data in the following manner: The audio data is input into a pre-trained bumpy road audio model, and based on the output result of the bumpy road audio model, a target audio data frame having bumpy road audio features is determined.

8. The apparatus according to claim 6, further comprising a training unit, wherein the training unit is configured to pre-train the bumpy road section audio model in the following manner: Collecting audio samples generated by vehicles with different vehicle attributes driving on different bumpy road sections, wherein the different vehicle attributes include at least one of the following attributes: vehicle model, interior sound insulation, and vehicle speed; Based on the audio samples, training is performed for vehicles with different vehicle attributes to obtain a bumpy road section audio model that matches the vehicle attributes.

9. The device according to claim 8, further comprising a positioning unit, wherein the positioning unit is configured to: Calling the road network data corresponding to the bumpy trajectory point; In the road network data, a bumpy road of a bumpy road section corresponding to the bumpy trajectory point is located.

10. The device according to any one of claims 6 to 9, wherein: The driving time sequence trajectory is collected by a device with a positioning function in the vehicle, and the audio data is collected by a device with an audio recording function in the vehicle.

11. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 5.

12. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1 to 5.

13. A computer program product comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 5.

Images