JP2022526509A - Operational data analysis methods, equipment, electronic devices and computer storage media - Google Patents

Abstract

The present invention discloses a method for analyzing driving data, an apparatus, an electronic device, and a computer storage medium, wherein the method is to receive an analysis request for driver data, and the analysis request for driver data is analyzed. (101) and the database to determine the driver's facial features that match the facial features, the database includes the driver's facial features and driving. The correspondence with the data is stored (102), the driving data corresponding to the determined facial features of the driver in the database is acquired (103), and the acquired driving data is analyzed. The driver's evaluation result corresponding to the driver's facial features is acquired (104). [Selection diagram] Fig. 1

Description

This application is submitted based on a Chinese patent application with an application number of 201910945671.8 filed with the Chinese Patent Office on September 30, 2019, claiming the priority of the Chinese patent application. The entire contents of the Chinese patent application are incorporated herein by reference.

The present invention relates to a vehicle system data analysis technique, and more particularly to a driving data analysis method, an apparatus, an electronic device, and a computer storage medium.

Vehicle travel is very popular in our lives. Whether it is a company-operated fleet or a fleet for general passenger transportation services, multiple drivers are usually involved and quasi-personal management is carried out on the drivers to ensure traffic safety and quality of service. There is a need to. In addition, it is necessary to evaluate and report each driver in order to determine the corresponding insurance strategy for industries such as insurance other than the transportation industry.

The embodiments of the present invention seek to provide a technical solution for operating data analysis.

An embodiment of the present invention provides a method of analyzing driving data, wherein the method receives a request for analysis of driver data, and the request for analysis of the driver data is required to be analyzed. Including the facial features and determining the driver's facial features that match the facial features in the database, the database stores the correspondence between the driver's facial features and the driving data. And, the driver's evaluation result corresponding to the driver's facial feature is obtained by acquiring the driving data corresponding to the determined driver's facial feature in the database and analyzing the acquired driving data. To get and include.

An embodiment of the present invention further provides an operating data analyzer comprising a receiving module, a first processing module, an acquisition module and a second processing module, wherein the receiving module requests analysis of driver data. The driver data analysis request includes the facial features requested to be analyzed, and the first processing module contains the driver's facial features that match the facial features in the database. The database is configured to determine, the correspondence between the driver's facial features and the driving data is stored, and the acquisition module is the driving data corresponding to the determined driver's facial features in the database. The second processing module is configured to analyze the acquired operation data and acquire the driver evaluation result corresponding to the facial features of the driver.

An embodiment of the invention further provides an electronic device comprising a processor and a memory configured to store a computer program that can be executed by the processor, wherein the processor executes the computer program. Then, it is configured to execute the analysis method of any one of the above-mentioned operation data.

The embodiments of the present invention further provide a computer storage medium for storing a computer program, which realizes any one of the methods of analyzing operating data described above when executed by a processor.

The embodiments of the present invention further provide computer program products, including computer program instructions, such that the computer program instructions realize a method of analyzing any one of the above operating data when executed by a computer. To.

In the driving data analysis method, apparatus, electronic device and computer storage medium proposed by the embodiments of the present invention, the driver data analysis request is received, and the driver data analysis request is requested to be analyzed. The driver's facial features that include the facial features and match the facial features are determined in the database, and the correspondence between the driver's facial features and the driving data is stored in the database and determined in the database. The driving data corresponding to the facial features of the driver is acquired, the acquired driving data is analyzed, and the driver evaluation result corresponding to the facial features of the driver is acquired. In this way, in the embodiment of the present invention, the driving data corresponding to the driver's facial features can be determined according to the driver's facial features, and the data analysis can be performed, and the driving can be performed at the driver's angle. It is possible to analyze driving data related to the driver, realize accurate evaluation of the driving behavior of the driver, and obtain more accurate driver evaluation data by application scenarios such as driver management, fleet management, insurance management, etc. Can be provided.

It should be understood that the general description described above and the detailed description described below are merely examples and explanations and do not limit the present invention.

The drawings herein are incorporated herein to constitute a portion thereof, and these drawings show examples consistent with the present invention, and together with the specification, technical solutions to the embodiments of the present invention. Used to explain the strategy.
It is an exemplary flowchart of the analysis method of the operation data of the Example of this invention. It is a schematic diagram of the alarm data statistical result of the Example of this invention. It is an exemplary structural diagram of one application scenario of the embodiment of the present invention. It is an exemplary structural diagram of the configuration of the operation data analyzer of the embodiment of the present invention. It is an exemplary structural diagram of the electronic device of the Example of this invention.

Hereinafter, examples of the present invention will be described in more detail with reference to the drawings and examples. It should be understood that the examples provided herein are used only to illustrate the embodiments of the invention and are not limiting the embodiments of the invention. In addition, the examples provided below are used to implement partial embodiments of the invention and are not provided to implement all embodiments of the invention, without conflict. , The technical solutions described in the examples of the present invention can be implemented by any combination method.

In the embodiments of the present invention, the terms "comprising", "including" or any other variation thereof are intended to cover non-exclusive implications, whereby a method or apparatus comprising a set of elements. It should be noted that, in addition to including the elements explicitly described, it also contains other elements not explicitly listed, or specific elements for implementing the method or device. Without more limitation, an element limited by the sentence "contains one ..." is an example of a method or device comprising said element and another related element (eg, a step in the method or a unit in the device). Units do not preclude the presence of (which can be a partial circuit, a partial processor, a partial program, or software, etc.).

For example, the method for analyzing operation data according to the embodiment of the present invention includes a series of steps, but the method for analyzing operation data according to the embodiment of the present invention is not limited to the steps described, and similarly, the present invention is used. The device for analyzing operating data according to an embodiment includes a series of modules, but the device according to the embodiment of the present invention is not limited to including the modules explicitly described, and further, in order to obtain relevant information. , Or an informational module that needs to be configured for processing.

The term "and / or" herein is merely an association that describes an associated object, indicating that there may be three types of relationships, eg, A and / or B, where A is independent. 3 cases are displayed, such as the case where A and B exist at the same time, and the case where B exists independently. Further, the term "at least one" as used herein refers to any combination of one or more of the plurality, including, for example, at least one of A, B, C. This indicates that it contains any one or more elements selected from the set consisting of A, B and C.

The application scenario of the embodiments of the present invention can be a computer system combined with an in-vehicle device and a cloud platform and can be operated with many other general purpose or dedicated computing system environments or configurations. Illustratively, the in-vehicle device can be a vehicle-mounted driver monitoring system (DMS), an advanced driving support system (ADAS) or other device, and the cloud platform is small. It can be a computer system or a distributed cloud computing technology environment that includes a large computer system.

In-vehicle devices, cloud platforms, etc. can be described in the general context of computer system executable instructions (program modules, etc.) executed by a computer system. Program modules can typically include routines, programs, target programs, components, logic, data structures, etc., which either perform a particular task or implement a particular abstract data category. On cloud platforms, tasks are performed by remote processing devices that make up a communication network link. In a cloud platform, program modules can be located on a local or remote computing system storage medium with storage equipment.

In this embodiment, the in-vehicle device can communicate with the vehicle sensor, the positioning device, and the like, and the in-vehicle device includes data collected by the vehicle sensor via the communication connection, geolocation information reported by the positioning device, and the like. Can be obtained. Illustratively, a vehicle's sensor can be at least one of devices such as millimeter-wave radar, laser radar, and cameras, and the positioning device is a Global Positioning System (GPS), Hokuto satellite navigation system. Alternatively, it may be a device that provides a positioning service based on at least one positioning system among the Galileo satellite navigation systems.

In some embodiments of the present invention, a method for analyzing driving data is proposed, and the embodiments of the present invention may be applied to fields such as driving behavior analysis, vehicle operation management, driver management, and business behavior analysis. can. The operation data analysis method of the embodiment of the present invention can be applied to a cloud platform that forms a communication connection with an in-vehicle device. FIG. 1 is an exemplary flow chart of a method for analyzing operating data according to an embodiment of the present invention, and as shown in FIG. 1, the process may include the following steps.

In step 101, an analysis request for driver data is received, and the analysis request for driver data includes facial features requested to be analyzed.

In the embodiments of the present invention, the facial features required to be analyzed can be features extracted from the image of the driver's face. In practical application, the vehicle-mounted device or a third-party device can take the driver's facial features from the driver's face image using a face recognition algorithm after acquiring the driver's face image. The third party device may be an external device that provides a third party service, the external device may be communicatively connected to the cloud platform, and exemplary, the external device may be an electronic device such as a computer. The embodiments of the present invention are not limited to the type of third party service, and by way of example, the third party service can be a business analysis service, a school bus service or another third party service. It should be noted that the embodiments of the present invention are not limited to the type of face recognition algorithm.

In a practical application, an in-vehicle device or a third party device can generate a driver data analysis request and send the driver data analysis request to a cloud platform after acquiring the driver's facial features.

In step 102, the driver's facial features that match the facial features are determined in the database, and the correspondence between the driver's facial features and the driving data is stored in the database.

In this embodiment, the database can be pre-established on a cloud platform. In practical applications, the in-vehicle device installed in the vehicle can transmit driving data and driver's facial features to the cloud platform, which is the driving data and driver transmitted by the received in-vehicle device. According to the facial features of, the correspondence between the received facial features of the driver and the driving data can be established in the database. Since it is not easy to forge a driver's facial features, establishing a relationship between it and the driving data being analyzed based on the driver's facial features will improve the accuracy of the analysis results and prevent tampering. Useful for.

In actual application, after establishing the correspondence between the driver's facial features and driving data in the database, if the cloud platform receives the facial features required to be analyzed, it will be in the database via feature comparison. It is possible to determine the driver's facial features that match the facial features required to be analyzed.

In step 103, the database acquires driving data corresponding to the determined facial features of the driver.

In an actual application, after determining the facial features of the driver, it is possible to acquire driving data corresponding to the determined facial features of the driver according to the correspondence stored in the database.

In step 104, the acquired driving data is analyzed to acquire the driver evaluation result corresponding to the facial features of the driver.

In this embodiment, the analysis for driving data may be to analyze the safety of driver driving behavior. Illustratively, the acquired driver evaluation results can represent the safety of the driver's driving behavior. Although the above content has been exemplified only for driving data analysis, it should be noted that in the embodiments of the present invention, the content of driving data analysis is not limited thereto.

In actual application, steps 101 to 104 can be realized based on a processor of a cloud platform or the like, and the processor is an integrated circuit (ASIC) for specific applications, a digital signal processor (DSP), or a digital signal processor (DSP). : Digital Signal Processor (DSPD), Digital Signal Processing Device (DSPD), Programmable Logic Device (PLD), Field Programmable Gate Array (FPGA: Field Program Central Processor) It can be at least one of a unit), a controller, a microprocessor, and a microprocessor.

As can be seen, in the embodiment of the present invention, according to the driver's facial features, the driving data corresponding to the driver's facial features can be determined and the data analysis can be performed, and the driving can be performed at the driver's angle. It is possible to analyze driving data related to the driver, realize accurate evaluation of the driving behavior of the driver, and obtain more accurate driver evaluation data by application scenarios such as driver management, fleet management, insurance management, etc. Can be provided.

In this embodiment, when the in-vehicle device transmits an analysis request for driver data to the cloud platform, the facial features required to be analyzed are features extracted from the driver's facial image taken by the in-vehicle camera. Yes, so it is possible to acquire and analyze driving data based on the facial features required to be analyzed and perform an accurate behavioral assessment on the actual driver of the vehicle, i.e. analyze. The obtained driver evaluation result can reflect the driving behavior of the current driver of the vehicle.

In some alternative embodiments of the invention, the driving data may include driver behavior data and / or vehicle progress data, where the driver behavior data is stretch, phone call, drinking, smoking, makeup, driver. Vehicle progress data, including at least one of not being in the driving position, includes lane departure warning, forward collision warning, speed violation warning, pedestrian appearance in front of the vehicle, rear collision warning, obstacle warning in front of the vehicle. Includes at least one of them. That is, the driver behavior data and / or the vehicle progress data can be warning data. It should be noted that the above content exemplifies only the driver behavior data and the vehicle progress data, and the contents of the driver behavior data and the vehicle progress data are not limited thereto in the embodiment of the present invention.

In the actual application, the DMS can acquire the driver behavior data and then transmit the driver behavior data to the cloud platform, and the ADAS acquires the vehicle progress data and then transmits the vehicle progress data to the cloud platform. can do. Here, the DMS can be installed in the vehicle, the DMS includes the in-vehicle camera, the image collection direction of the in-vehicle camera is directed toward the inside of the cabin, and the DMS analyzes the driver image obtained by the in-vehicle camera. Then, if it is determined that the driver behavior is an behavior to be warned according to the analysis result, the above-mentioned driver behavior data can be generated. The driver behavior data indicates a behavior to be alerted, and may be an inattentive driving behavior such as yawning, calling a telephone, drinking water, smoking, or makeup. The ADAS can be installed in the vehicle, the ADAS can include a camera, the camera is mounted on the vehicle but the image collection direction is towards the outside of the vehicle, and the ADAS is an environmental image of the outside of the vehicle collected by the camera. If the vehicle progress behavior is determined to be an action to be alerted according to the analysis result, the above-mentioned vehicle progress data is generated, and the vehicle progress data indicates the vehicle progress behavior to be warned, for example, lane deviation. , Forward collision, speed violation, pedestrians appearing in front of the vehicle, etc.

As a matter of course, since the driver's facial features reflect one driver's unique biological feature, in the embodiment of the present invention, by establishing a correspondence relationship between the driver's facial features and the driving data. The same driver's driver behavior data and / or vehicle progress data can be screened and the same driver's driver behavior data and / or vehicle progress data can be analyzed, i.e., data separately for each driver. Perform analysis to help understand each driver's driving behavior. Further, when the in-vehicle device sends an analysis request for driver data to the cloud platform, the facial features required to be analyzed are facial features extracted from the driver's facial image taken by the in-vehicle camera. Therefore, it is possible to acquire and analyze driver behavior data and / or vehicle progress data based on the facial features required to be analyzed to perform accurate behavioral assessments for the actual driver of the vehicle. That is, the driver evaluation results obtained by analysis can reflect the current driver's driving behavior of the vehicle.

When the driving data includes driver behavior data and vehicle progress data, the same driver's behavior and vehicle progress data are comprehensively considered, and the same driver's behavior is comprehensively analyzed. Can be more objective and correct.

In some alternative embodiments, the in-vehicle device can transmit both driving data and the driver's facial features to the cloud platform. Illustratively, the DMS can transmit both the driver data and the driver's facial features to the cloud platform, and the ADAS can transmit both the vehicle data and the driver's facial features to the cloud platform. Here, the driver data may include driver behavior data, and the vehicle data may include vehicle progress data.

In one example, the cloud platform receives driver behavior data and driver facial features transmitted by DMS, vehicle progress data and driver facial features transmitted by ADAS, and is transmitted by DMS and ADAS. It is possible to obtain driving data of driver behavior data and vehicle progress data by comparing the facial features of the drivers and associating the driver behavior data and the vehicle progress data corresponding to the driver's facial features of the successful comparison. can.

In another example, the driver data further comprises a DMS first device identifier and the vehicle data further comprises an ADAS second device identifier. Here, the first device identifier of the DMS can be the ID of the DMS or other identifier information of the DMS, the first device identifier is used only to identify the DMS, and the second device identifier of the ADAS is. It can be the ID of the ADAS or other identifier information of the ADAS, and the second device identifier is used only to identify the ADAS.

After receiving the driver data and the vehicle data, the cloud platform assigns the vehicle identifier corresponding to the first device identifier and the second device identifier, respectively, according to the first mapping relationship between the device identifier and the vehicle identifier established in the database. Can be decided.

In an embodiment of the invention, the vehicle identifier can be the vehicle license plate number or other identifier information, and when the DMS transmits driver data to the cloud platform, the vehicle identifier may also be transmitted to the cloud platform. Yes, and correspondingly, when ADAS sends vehicle data to the cloud platform, it can also send the vehicle identifier to the cloud platform.

In practical application, the cloud platform receives the data transmitted by DMS and ADAS, and then according to the vehicle identifier carried to the data transmitted by DMS and the vehicle identifier carried to the data transmitted by ADAS. The correspondence between the device identifier and the vehicle identifier can be established in the database, and here, the correspondence between the device identifier and the vehicle identifier is the correspondence between the first device identifier and the vehicle identifier, and the second device identifier. It may include a correspondence with a vehicle identifier.

Obviously, when the first device identifier and the second device identifier are received after establishing the correspondence between the device identifier and the vehicle identifier in the database, the first device identifier and the second device identifier are used in the database according to the correspondence. The corresponding vehicle identifier can be searched for, and in response to the first device identifier and the second device identifier corresponding to the same vehicle identifier, the received driver behavior data and vehicle progress data are transferred to the same vehicle. You can decide to respond. In this case, the received driver behavior data and the vehicle progress data can be associated with each other to acquire driving data including the driver behavior data and the vehicle progress data.

In the embodiment of the present invention, the cloud platform receives the driving data and the driver's facial features transmitted by the in-vehicle device, and then corresponds to the received driver's facial features and the received driving data in the database. A relationship can be established, or the database can establish a correspondence between the driver's facial features that match the received driver's facial features and the received driving data, exemplary. First, from the driver's facial features stored in the database, the driver's facial features that match the received driver's facial features are determined, and then the database matches the received driver's facial features. It is possible to establish a correspondence between the driver's facial features and the received driving data.

By establishing a correspondence between the driver's facial features and the driving data in the database, it is easy to determine the driving data corresponding to the driver's facial features after receiving the subsequent driver's facial features, and further. From the driver's angle, it is useful to analyze driving data related to the driver, and it can be understood that an accurate evaluation of the driver's driving behavior can be realized.

As an example, the realization method for acquiring the evaluation result of the driver for the driving data obtained by the analysis is to determine the risk level of the driving behavior according to the driving data, and to determine the risk level and the evaluation weight in advance. Acquiring the evaluation weight corresponding to the determined danger level according to the mapping relationship with, and determining the driver evaluation result corresponding to the driver's facial feature according to the determined danger level and the corresponding evaluation weight. It can include things.

Illustratively, multiple risk levels of driving behavior can be predivided and corresponding rating weights can be set for each risk level, with rating weights corresponding to each risk level set according to actual needs. The rating weights corresponding to different risk levels are different. For example, for severe risky behavior, the rating weight can be -10, for moderate risky behavior, the rating weight can be -5, and for mild risky behavior, the rating weight can be -5. , -2, and if there is no risky behavior in a unit period, the rating weight can be 2.

In an embodiment of the invention, after determining the driving data in the database, various driving behaviors represented by the driving data can be determined, further, the risk level corresponding to each driving behavior is scored, and then the risk level is scored. The driver evaluation result can be obtained by adding the scores corresponding to the driving behavior. In practical applications, driver assessment results can be used as the basis for unit or individual performance management. In one example, the higher the value of the driver evaluation result, the safer the driver driving behavior.

Not surprisingly, the risk levels of various driving behaviors can be set according to the actual application needs, so that the method of determining the driver evaluation results according to the driving behavior risk level is an accurate driver evaluation. It helps to obtain results and can accurately evaluate the safety of driver driving behavior.

For the implementation method that determines the risk level of driving behavior according to the driving data, the reliability of the driving data is determined and the driving data or the reliability determined to be reliable driving data is set as an example. Includes determining the risk level of driving behavior according to driving data above the threshold.

In this embodiment, the setting threshold can be set according to the actual application needs. When actually implementing, after determining the reliability of the driving data, according to the reliability of the driving data, whether the driving data is reliable driving data, or whether the reliability of the driving data exceeds the set threshold. If the driving data is reliable driving data or the reliability of the driving data exceeds the set threshold, the risk level of driving behavior is determined according to the driving data, and the driving data is unreliable driving data. If the reliability of the driving data does not exceed the set threshold, the risk level of driving behavior is not determined.

As a matter of course, in the embodiment of the present invention, it is not possible to determine the risk level of driving behavior based on the driving data being reliable driving data or the reliability of the driving data exceeding the set threshold. Alternatively, unreliable operating data can be excluded. Specifically, when the operation data is alarm data, by introducing a reconfirmation processing mechanism for the alarm data, the probability that the in-vehicle device will make an erroneous alarm or erroneous report will be reduced to some extent, and the analysis result for the alarm data will be more. By making it objective and reliable, and by excluding unreliable or unreliable alarm data, it helps to accurately assess the driver's driving behavior and accurately assess the risk level of driving behavior. Useful for.

In some alternative embodiments of the invention, the driving data includes vehicle progress data, the vehicle progress data includes geographic location information of vehicle progress and time information of vehicle progress, and the realization determines the reliability of the driving data. Regarding the method, in one example, acquisition of weather condition information and / or traffic condition information corresponding to vehicle progress time information and vehicle progress geographic location information, and according to weather condition information and / or traffic condition information, driving data It may include determining reliability.

In embodiments of the invention, the vehicle travel geolocation is used to indicate the vehicle's current geolocation, and the vehicle travel geolocation is in the form of latitude and longitude data or other types of geolocation data. Can be expressed. In practical application, the ADAS can acquire the geolocation information of the vehicle progress from the vehicle positioning device. The vehicle progress time information indicates a time point at which the vehicle progress data is transmitted. After ADAS sends the vehicle progress data to the cloud platform, the cloud platform can acquire the time information of the vehicle progress and the geolocation information of the vehicle progress.

In this example, the weather information includes, but is not limited to, rain, snow, sunny, night, cloudy, etc., and the traffic information includes uphill, downhill, corner, road leveling, road unevenness, obstacles, etc. Includes, but is not limited to, empty roads, traffic jams, car accidents, etc.

As a matter of course, the weather information and / or the traffic information is an important factor that influences the driver's behavior. Therefore, by introducing a reconfirmation processing mechanism for the alarm data, the in-vehicle device can make a false alarm or an error. Reduce the probability of reporting to some extent and make the analysis results for the alarm data more objective and reliable, for example, determine the reliability of the driving data according to the weather information and / or the traffic information, and the reliability of the driving data. When determining the risk level of driving behavior according to, excluding unreliable or unreliable alarm data helps to accurately assess the driving behavior of the driver and accurately assess the risk level of driving behavior. Useful for.

In an embodiment of the invention, if the driver behavior data is alarm data and / or the vehicle progress data is alarm data, the DMS and / or ADAS may transmit the alarm data to the cloud platform. Yes, the cloud platform can verify and statistically analyze the alarm data when it receives the alarm data, see FIG. 2, which is a schematic diagram of the alarm data statistical results of the embodiments of the present invention.

In some alternative embodiments of the invention, the cloud platform can validate the alarm data according to the weather information and / or the traffic information when receiving the alarm data. In the first specific example, if the warning data indicates a speed violation of the vehicle and the traffic information indicates that congestion will occur at the current position where the vehicle is traveling, the warning data is unreliable data. Can be decided. In the second specific example, if the warning data indicates that a vehicle accident has occurred in front of the vehicle, and the traffic conditions information indicates that no vehicle accident has occurred at the current position where the vehicle is traveling. The alarm data can be determined to be unreliable data. In the third specific example, if the warning data indicates a lane deviation, the traffic condition information determines that the warning data is unreliable if there is traffic regulation in the area of the current position where the vehicle is traveling. For example, the reliability of the alarm data can be set to a reliability value lower than the set value. By introducing a reconfirmation processing mechanism for alarm data, the probability of false alarms and false reports by in-vehicle devices will be reduced to some extent, and the analysis results for alarm data will be more objective and reliable.

FIG. 3 is an exemplary structural diagram of an application scenario of an embodiment of the present invention, and with reference to FIG. 3, acquisition of time information of vehicle progress and weather condition information corresponding to geolocation information of vehicle progress 1 One implementation method is that the cloud platform sends the first query request to the first server that provides the weather service after receiving the vehicle progress time information and the vehicle progress geolocation information transmitted by the in-vehicle device. 1 The query request is used to query the weather information corresponding to the time information of the vehicle progress and the geolocation information of the vehicle progress, and the weather information is the time point corresponding to the time information of the vehicle progress, and the vehicle progresses. It is to represent the weather condition corresponding to the geolocation information of. After receiving the first query request, the first server queries according to the first query request, acquires the corresponding weather condition information, and transmits the weather condition information to the cloud platform. In this way, the cloud platform can receive the weather information transmitted by the first server.

Referring to FIG. 3, one implementation method of acquiring the traffic condition information corresponding to the vehicle progress time information and the vehicle progress geographic position information is that the cloud platform uses the vehicle progress time information and the vehicle transmitted by the in-vehicle device. After receiving the geographic location information of the progress, the second query request is sent to the second server that provides the traffic condition information, and the second query request is the traffic corresponding to the time information of the vehicle progress and the geographic position information of the vehicle progress. Used to query the state information, the traffic state information is a time point corresponding to the time information of the vehicle progress, and represents the traffic state corresponding to the geographic position information of the vehicle progress. After receiving the second query request, the second server queries according to the second query request, acquires the corresponding traffic condition information, and transmits the traffic condition information to the cloud platform. In this way, the cloud platform can receive the traffic information transmitted by the second server.

In some alternative embodiments of the present invention, the driving data includes the driver behavior data and the corresponding driver image when the driver behavior data is acquired, and the implementation method for determining the reliability of the driving data is different. One example may include determining the reliability of the driver behavior data according to the driver image.

In the actual application, the DMS can collect the driver image in real time, and if it decides to send the alarm data, it will send the alarm data and the corresponding driver image to the cloud platform when acquiring the alarm data. be able to.

As a matter of course, the driver image transmitted by the DMS of the in-vehicle device reflects the true driver state. Therefore, by introducing a reconfirmation processing mechanism of the alarm data, the in-vehicle device makes an erroneous alarm and reports erroneously. The probability is reduced to some extent, the analysis result for the warning data is made more objective and reliable, and specifically, the reliability of the warning data is determined according to the driver image to reduce the misjudgment rate of the driver behavior data. However, it can help to accurately determine the risk level of driving behavior. For example, the warning data reported by the in-vehicle device indicates that the driver has a fatigued driving condition, and according to the analysis of the driver image at the time when the in-vehicle device was reported together with the warning data, the driver at that time was missing. If not, the alarm data can be determined to be unreliable operating data, or the alarm data can be determined to be unreliable, and unreliable or unreliable alarm data. Exclusions help to accurately assess the driver's driving behavior and, in addition, help accurately assess the risk level of driving behavior.

In some alternative embodiments of the invention, the database is pre-established with a mapping relationship between the driver's facial features and the fleet identifier, and correspondingly at least 2 corresponding to the same fleet identifier according to the mapping relationship. The facial features of one driver can be determined, and the fleet evaluation results can be obtained according to the driver evaluation results corresponding to the facial features of each driver among the facial features of at least two drivers.

In practice applications, the same in-vehicle device can upload the driver's facial features and the identifier of the fleet to which the vehicle belongs to the cloud platform, thus the cloud platform is the driver transmitted by the same in-vehicle device. According to the facial features and fleet identifiers of, the mapping relationship between the driver's facial features and the fleet identifiers can be established in the database.

In the embodiment of the present invention, by establishing the mapping relationship in the database, it is possible to determine the facial features of all the drivers of the same fleet, and further, the driver evaluation results corresponding to the facial features of each driver. You can get the driver evaluation results for all drivers in the same fleet, and you can also evaluate each driver in each fleet separately, the driver in each fleet. Understand that it helps to understand the action.

Those skilled in the art will appreciate that in the above method of the specific embodiment, the writing order of the steps is a strict execution order and does not limit the implementation process, and the specific execution order of each step is its function and possibility. Can be understood that it should be based on.

Based on the method of analyzing operating data submitted by the above embodiment, the embodiments of the present invention propose an analytical device for operating data. FIG. 4 is an exemplary structural diagram of the configuration of the operation data analysis device according to the embodiment of the present invention, and as shown in FIG. 4, the device includes a receiving module 401, a first processing module 402, and acquisition. A module 403 and a second processing module 404 are provided, wherein the receiving module 401 is configured to receive a driver data analysis request, and the driver data analysis request is requested to be analyzed. The first processing module 402 including the face feature is configured to determine the driver's face feature that matches the face feature in the database, and the database corresponds to the driver's face feature and the driving data. The relationship is stored, the acquisition module 403 is configured to acquire operation data corresponding to the determined driver's facial features in the database, and the second processing module 404 acquires the operation data. Is configured to analyze and obtain a driver evaluation result corresponding to the driver's facial features.

In some alternative embodiments of the present invention, the second processing module 404 determines the risk level of driving behavior according to the operating data and is determined according to the mapping relationship between the predetermined risk level and the evaluation weight. It is configured to acquire the evaluation weight corresponding to the danger level and determine the driver evaluation result corresponding to the facial feature of the driver according to the determined danger level and the corresponding evaluation weight.

In some alternative embodiments of the invention, the driving data includes driver behavior data and / or vehicle progress data, and the driver behavior data includes stretch, telephone call, drinking water, smoking, makeup, driver. The vehicle progress data includes lane departure warning, forward collision warning, speed violation warning, pedestrian appearance in front of the vehicle, rear collision warning, obstacle in front of the vehicle, including at least one of the fact that the vehicle is not in the driving position. Includes at least one of the alarms.

In some alternative embodiments of the invention, the first processing module 402 further receives driving data and driver's facial features transmitted by an in-vehicle device installed in the vehicle and receives the driver's facial features. The correspondence between the facial features and the received driving data is established in the database, or the correspondence between the driver's facial features that match the driver's facial features received in the database and the received driving data is established. Configured to establish.

In some alternative embodiments of the present invention, the second processing module 404 determines the reliability of the operation data, and the operation data or the reliability determined to be reliable operation data is set. It is configured to determine the risk level of the driving behavior according to the driving data exceeding the threshold.

In some alternative embodiments of the present invention, the driving data includes vehicle progress data, the vehicle progress data includes geographic location information of vehicle progress and time information of vehicle progress, and the second processing module 404 , The weather condition information and / or the traffic condition information corresponding to the vehicle progress time information and the vehicle travel geographic location information are acquired, and the reliability of the driving data is obtained according to the weather condition information and / or the traffic condition information. Is configured to determine.

In some alternative embodiments of the invention, the second processing module 404 sends a first query request to a first server that provides weather services, the first query request being the time information of the vehicle progress and the vehicle progress. It is used to query the weather information of the geolocation information of the vehicle progress, and is configured to receive the weather information transmitted by the first server.

In some alternative embodiments of the present invention, the second processing module 404 sends a second query request to a second server that provides traffic information, and the second query request is time information of the vehicle progress. And used to query the traffic information of the geographic location information of the vehicle progress, and configured to receive the traffic information transmitted by the second server.

In some alternative embodiments of the invention, the driving data includes driver behavior data and a corresponding driver image when the driver behavior data is acquired, and the second processing module 404 is the driver. It is configured to determine the reliability of the driver behavior data according to the image.

In some alternative embodiments of the invention, the driver's facial features are features extracted from the driver's facial image.

In some alternative embodiments of the invention, the database is further pre-established with a mapping relationship with the driver's facial feature sum fleet identifier, and the second processing module 404 further follows the mapping relationship. , At least two driver facial features corresponding to the same fleet identifier are determined, and the fleet evaluation result is determined according to the driver evaluation result corresponding to each driver's facial feature among the at least two driver facial features. Configured to get.

In a practical application, the receive module 401, the first processing module 402, the acquisition module 403 and the second processing module 404 can all be realized by a processor in an in-vehicle data terminal or a cloud platform, and the processor is an ASIC. , DSP, DSPD, PLD, FPGA, CPU, controller, microcontroller, microprocessor can be at least one.

Further, each functional module in this embodiment can be integrated into one processing unit, and each unit can exist physically separately, and two or more units are integrated into one unit. be able to. The integrated unit can be implemented using the form of hardware and can also be implemented using the form of software function modules.

Based on this understanding, the integrated unit can be stored in one computer-readable storage medium if it is implemented in the form of a software functional module and is not sold or used as a stand-alone product. The technical solution of an embodiment may be embodied in the form of a software product, either in essence or in part that contributes to the prior art, or in whole or in part, in the form of a computer software product. Is stored in one storage medium, and one computer device (which may be a personal computer, server, or network device, etc.) or processor is all or part of the steps of the method described in this embodiment. Includes some instructions to execute. The storage medium described above can store program codes such as a U disk, a mobile hard disk, a read-only memory (ROM: Read Only Memory), a random access memory (RAM: Random Access Memory), a magnetic disk, or an optical disk. Includes medium.

Specifically, the computer program instruction corresponding to the operation data analysis method in the present embodiment can be stored in a storage medium such as an optical disk, a hard disk, or a U disk, and analysis of one operation data in the storage medium. When the computer program instruction corresponding to the method is read or executed by an electronic device, it realizes a method for analyzing any one operation data of the above embodiment.

Based on the same technical concept as in the above embodiment, with reference to FIG. 5, the electronic device 50 according to the embodiment of the present invention can be shown, which may include a memory 51 and a processor 52, wherein the memory 51 is a computer program. And configured to store data, the processor 52 is configured to execute a computer program stored in the memory to implement any one data analysis method of the above embodiment.

In actual application, the memory 51 may be a volatile memory such as RAM, or a ROM, flash memory, hard disk (HDD: Hard Disk Drive) or solid state hard disk (SSD:). It can be a non-volatile memory such as a Solid-State Drive, or a combination of the above categories of memory, providing instructions and data to the processor 52.

The processor 52 may be at least one of an ASIC, DSP, DSPD, PLD, FPGA, CPU, controller, microcontroller, microprocessor. It should be understood that the electronic devices used to realize the functionality of the processor for different devices may be other and the embodiments of the present invention are not specifically limited.

In some embodiments, the features or modules included in the apparatus according to the embodiments of the present invention may be used to perform the methods described in the embodiments of the above methods, a particular realization of the above methods. The description in the examples can be referred to and will not be described again here for brevity.

The embodiments of the present invention further provide a computer storage medium for storing a computer program, any one of the operational data analyzes described in the embodiments of the present invention when the computer program is executed by a processor. Realize the method.

Embodiments of the invention further provide computer program products, including computer program instructions, which, when executed by a computer, analyze any one of the operational data described in the embodiments of the invention. Try to realize the method.

The description for each of the above embodiments tends to emphasize the differences between the embodiments, and the same or similarities can be referred to each other and are not described again herein for brevity.

The methods disclosed in the examples of each method according to the present invention can be arbitrarily combined without conflict to obtain examples of new methods.

The features disclosed in the examples of each product according to the present invention can be arbitrarily combined without conflict to obtain examples of new products.

The features disclosed in the embodiments of the methods or devices according to the invention can be arbitrarily combined without conflict to obtain examples of new methods or devices.

Through the description of the above embodiments, those skilled in the art can realize that the method of the above embodiment is realized not only in the form of software and a required general-purpose hardware platform, but also by hardware. It is clearly understandable that it can be done, but in many cases the former is the more preferred embodiment. Based on this understanding, substantive parts of the technical solution of the invention, or parts that contribute to the current art, can be implemented in the form of software products, said computer software products. The method described in each embodiment of the present application is executed on a storage medium (for example, ROM / RAM, magnetic disk, optical disk, etc.) and a terminal device (which may be a mobile phone, computer, server, network device, etc.). Includes some instructions to get it done.

The above has been described for embodiments of the present invention with reference to the drawings, but the present invention is not limited to the above-mentioned specific embodiments, and the above-mentioned specific embodiments are exemplary. Only, and not limiting, one of ordinary skill in the art can make many forms under the enlightenment of the invention without departing from the scope of protection of the object of the invention and the claims. , All of which are within the scope of the protection of the present invention.

Claims (15)

It is a method of analyzing driving data.
Receiving an analysis request for driver data, said analysis request for driver data includes facial features required to be analyzed.
The database determines the facial features of the driver that match the facial features, and the database stores the correspondence between the facial features of the driver and the driving data.
Acquiring driving data corresponding to the determined facial features of the driver in the database,
A method for analyzing driving data, including analyzing the acquired driving data and acquiring a driver evaluation result corresponding to the facial features of the driver. Analyzing the acquired operation data and acquiring the evaluation result of the driver is not possible.
Determining the risk level of driving behavior according to the driving data,
To obtain the evaluation weight corresponding to the determined danger level according to the mapping relationship between the predetermined danger level and the evaluation weight,
Including determining the driver evaluation result corresponding to the driver's facial features according to the determined risk level and the corresponding evaluation weight.
The method for analyzing operation data according to claim 1. The driving data includes driver behavior data and / or vehicle progress data, and the driver behavior data includes at least one of stretch, telephone call, drinking water, smoking, makeup, and the driver not being in the driving position. The vehicle progress data includes at least one of lane departure warning, forward collision warning, speed violation warning, pedestrian appearance in front of the vehicle, rear collision warning, and obstacle warning in front of the vehicle.
The method for analyzing operation data according to claim 1. Before acquiring the driving data corresponding to the determined facial features of the driver in the database,
Receiving driving data and driver's facial features transmitted by in-vehicle devices installed in the vehicle,
The driver's facial features that match the received driver's facial features with the received driver's facial features and the received driving data are established in the database. Establishing a correspondence in the database, including further,
The method for analyzing operation data according to claim 3. Determining the risk level of driving behavior according to the driving data
Determining the reliability of the operation data
The driving data determined to be reliable driving data or the reliability determines the risk level of the driving behavior according to the driving data exceeding a set threshold.
The method for analyzing operation data according to any one of claims 2 to 4. The driving data includes vehicle progress data, and the vehicle progress data includes geolocation information of vehicle progress and time information of vehicle progress.
Determining the reliability of the operation data is
Acquiring the weather information and / or the traffic information corresponding to the time information of the vehicle progress and the geolocation information of the vehicle progress, and
Including determining the reliability of the driving data according to the weather information and / or the traffic information.
The method for analyzing operation data according to claim 5. Acquiring the weather information corresponding to the time information of the vehicle progress and the geolocation information of the vehicle progress is possible.
The first query request is sent to the first server that provides the weather service, and the first query request is for querying the time information of the vehicle progress and the weather condition information of the geolocation information of the vehicle progress. To be used in
Including receiving the weather information transmitted by the first server.
The method for analyzing operation data according to claim 6. Acquiring the traffic condition information corresponding to the time information of the vehicle progress and the geolocation information of the vehicle progress is possible.
The second query request is transmitted to the second server that provides the traffic condition information, and the second query request queries the traffic condition information of the vehicle progress time information and the vehicle progress geolocation information. To be used for
Including receiving the traffic condition information transmitted by the second server.
The method for analyzing operation data according to claim 6. The driving data includes the driver behavior data and the corresponding driver image when the driver behavior data is acquired.
Determining the reliability of the driving data includes determining the reliability of the driver behavior data according to the driver image.
The method for analyzing operation data according to claim 5. The driver's facial feature is a feature extracted from the driver's facial image.
The method for analyzing operating data according to any one of claims 1 to 9. In the database, the mapping relationship between the driver's facial features and the fleet identifier is established in advance, and the method for analyzing the driving data is as follows.
Determining at least two driver facial features that correspond to the same fleet identifier according to the mapping relationship.
Further including acquiring a fleet evaluation result according to a driver evaluation result corresponding to each driver's facial feature among the at least two driver's facial features.
The method for analyzing operation data according to any one of claims 1 to 10. An operation data analyzer including a receiving module, a first processing module, an acquisition module, and a second processing module.
The receiving module is configured to receive an analysis request for driver data, the analysis request for driver data including facial features required to be analyzed.
The first processing module is configured to determine a driver's facial feature that matches the facial feature in a database, and the database stores a correspondence between the driver's facial feature and driving data.
The acquisition module is configured to acquire driving data corresponding to the determined facial features of the driver in the database.
The second processing module is an operation data analysis device configured to analyze the acquired operation data and acquire a driver evaluation result corresponding to the facial features of the driver. An electronic device comprising a processor and a memory configured to store a computer program that can be executed by the processor.
The processor is an electronic device that executes the computer program to execute the method for analyzing operation data according to any one of claims 1 to 11. A computer storage medium that stores computer programs
The computer program is a computer storage medium that, when executed by a processor, realizes the method for analyzing operating data according to any one of claims 1 to 11. A computer program product comprising a computer program instruction, wherein the computer program instruction causes a computer to execute the method for analyzing operation data according to any one of claims 1 to 11.

Images