CN117874435A - Distributed edge data acquisition method and device, electronic equipment and storage medium - Google Patents
Distributed edge data acquisition method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN117874435A CN117874435A CN202410270545.8A CN202410270545A CN117874435A CN 117874435 A CN117874435 A CN 117874435A CN 202410270545 A CN202410270545 A CN 202410270545A CN 117874435 A CN117874435 A CN 117874435A
- Authority
- CN
- China
- Prior art keywords
- data
- driving data
- target driving
- moment
- acquisition frequency
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 74
- 230000008859 change Effects 0.000 claims abstract description 46
- 238000012545 processing Methods 0.000 claims description 71
- 230000008569 process Effects 0.000 claims description 27
- 238000004140 cleaning Methods 0.000 claims description 11
- 230000002159 abnormal effect Effects 0.000 claims description 10
- 238000013480 data collection Methods 0.000 claims description 10
- 238000006243 chemical reaction Methods 0.000 claims description 9
- 238000000611 regression analysis Methods 0.000 claims description 6
- 238000011282 treatment Methods 0.000 claims description 4
- 238000004891 communication Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 10
- 230000005540 biological transmission Effects 0.000 description 5
- 230000003247 decreasing effect Effects 0.000 description 5
- 238000012544 monitoring process Methods 0.000 description 5
- 230000007613 environmental effect Effects 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000007774 longterm Effects 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 2
- 238000007906 compression Methods 0.000 description 2
- 230000006835 compression Effects 0.000 description 2
- 238000013144 data compression Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000008447 perception Effects 0.000 description 2
- 230000000737 periodic effect Effects 0.000 description 2
- 230000010076 replication Effects 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 230000002123 temporal effect Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 1
- 238000013501 data transformation Methods 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000007620 mathematical function Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000010926 purge Methods 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 238000005406 washing Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Landscapes
- Traffic Control Systems (AREA)
Abstract
The application provides a distributed edge data acquisition method, a distributed edge data acquisition device, electronic equipment and a storage medium, wherein the method comprises the following steps: acquiring target driving data acquired at a plurality of different moments; according to the multiple target driving data, determining the change trend of the target driving data; according to the change trend, determining first prediction data at a first moment, wherein the first moment is the moment after the current moment, and the interval duration between the first moment and the current moment is the acquisition interval duration of target driving data; acquiring first actual data acquired at a first moment, wherein the first actual data and the first predicted data are the same driving data; and judging whether the first predicted data is identical to the first actual data or not, if the first predicted data is identical to the first actual data, determining the adjustment acquisition frequency of the target driving data according to the current acquisition frequency of the target driving data, wherein the adjustment acquisition frequency is smaller than the current acquisition frequency. The distributed edge data acquisition method and device can be used for efficiently acquiring distributed edge data.
Description
Technical Field
The application relates to the technical field of data acquisition, in particular to a distributed edge data acquisition method, a distributed edge data acquisition device, electronic equipment and a storage medium.
Background
Distributed edge data refers to data stored on a plurality of edge computing nodes, which are typically distributed across the edges of a network, near the source of the data generation or end user. Such data is distributed across multiple geographical locations or network edges to meet real-time performance, low latency, and high availability requirements, and it is often necessary to coordinate and manage data synchronization, replication, and sharing among multiple nodes to support the needs of various applications and systems.
Many distributed edge data are involved for intelligent driving, which is critical to real-time decision making and driving assistance systems, including vehicle sensor data, real-time map and navigation data, environmental sensor data, and driver monitoring data, among others. These relevant distributed edge data are key components of intelligent driving systems for vehicle perception, decision making, route planning and driving monitoring. These data need to be processed at the edge nodes of the vehicle itself or nearby to support real-time intelligent driving functions.
During intelligent driving of the vehicle, a large amount of distributed edge data is generated, and most of the data is generated in real time, for example, obstacle detection is performed by the radar system of the vehicle every few microseconds. Collecting and subsequent processing and storage of such large-scale data requires a high hardware infrastructure and high performance computing resources. Therefore, there is a need for a method that enables efficient distributed edge data acquisition.
Disclosure of Invention
The application provides a distributed edge data acquisition method, a distributed edge data acquisition device, electronic equipment and a storage medium, which can be used for efficiently acquiring distributed edge data.
In a first aspect of the present application, there is provided a distributed edge data acquisition method, the method comprising:
acquiring a plurality of target driving data acquired at different moments, wherein the target driving data is any one driving data of a plurality of driving data, and the driving data is data generated by vehicle electronic equipment in a preset vehicle driving process;
determining the change trend of the target driving data according to a plurality of target driving data;
according to the change trend, determining first prediction data at a first moment, wherein the first moment is a moment after the current moment, and the interval duration between the first moment and the current moment is the acquisition interval duration of the target driving data;
acquiring first actual data acquired at the first moment, wherein the first actual data and the first predicted data are the same driving data;
judging whether the first predicted data is identical to the first actual data or not, if the first predicted data is identical to the first actual data, determining an adjustment acquisition frequency of the target driving data according to the current acquisition frequency of the target driving data, wherein the adjustment acquisition frequency is smaller than the current acquisition frequency.
By adopting the technical scheme, various distributed edge data are generated in the running process of the preset vehicle, and the change trend of the target driving data is determined according to the existing target driving data aiming at the target driving data. And then predicting prediction data at a certain time in the future according to the change trend. And acquiring the acquired actual data at the moment, judging whether the predicted data are identical to the actual data, and if so, indicating that the change trend of the target driving data can be predicted. The acquisition frequency of the target driving data can be reduced, the data filling is performed through prediction later, a large amount of data is not required to be acquired through high frequency, and the distributed edge data acquisition can be performed efficiently.
Optionally, the determining the trend of the target driving data according to the plurality of target driving data specifically includes:
determining a time window according to the current acquisition frequency;
placing the time window in the first position so that the starting point of the time window coincides with first target driving data of a plurality of target driving data;
determining a plurality of time sequence data contained when the time window is positioned at the first position in the plurality of target driving data;
Determining a statistical index according to the plurality of time series data, wherein the statistical index is used for reflecting the characteristics of the plurality of time series data;
sequentially sliding the time windows to obtain a plurality of statistical indexes;
and carrying out regression analysis on a plurality of statistical indexes to obtain the variation trend.
By adopting the technical scheme, the prediction method based on the time window can capture and quantify the trend of the edge data, whether the trend is short-term fluctuation or long-term trend. This helps to better understand the evolution process of the target driving data, identifying patterns and laws in the data. Meanwhile, the size of the time window and the selection of the step length have flexibility, can be adjusted according to different analysis requirements and data properties, and can adapt to different target driving data types.
Optionally, after determining the adjusted acquisition frequency of the target driving data according to the current acquisition frequency of the target driving data if the first prediction data is determined to be the same as the first actual data, the method further includes:
determining a vacancy number between first driving data and second driving data according to the current acquisition frequency, wherein the first driving data and the second driving data are two adjacent target driving data in a plurality of target driving data acquired based on the adjustment acquisition frequency;
Determining a plurality of filling data between the first driving data and the second driving data according to the change trend, wherein the number of the filling data is the same as the number of the vacant bits;
and sequentially filling a plurality of filling data between the first driving data and the second driving data.
By adopting the technical scheme, after the first actual data of the first predicted data is the same, the calculated data change trend is correct, so that the acquisition frequency can be reduced. After data transmission, the data is filled with the vacant data caused by low-frequency acquisition according to the change trend of the data, so that the data is more complete. The continuity and consistency of the data is ensured and complete data can be provided even at low acquisition frequencies.
Optionally, after the acquiring the target driving data acquired at a plurality of different moments, the method further includes:
acquiring the current acquisition frequency of the driving data;
judging the magnitude relation between the current acquisition frequency and the preset acquisition frequency, if the current acquisition frequency is determined to be smaller than the preset acquisition frequency, removing the third driving data in the third driving data and the fourth driving data or removing the fourth driving data in the third driving data and the fourth driving data, wherein the third driving data and the fourth driving data are two adjacent driving data in a plurality of driving data.
By adopting the technical scheme, if the current acquisition frequency of the driving data is smaller than the preset acquisition frequency, the acquisition frequency of the driving data is smaller, and the real-time requirement of the driving data can be understood to be lower. The amount of data can be further reduced by removing some of the data, thereby saving computation and communication resources.
Optionally, after the determining the magnitude relation between the current acquisition frequency and the preset acquisition frequency, the method further includes:
if the current acquisition frequency is determined to be greater than or equal to the preset acquisition frequency, acquiring the data volume of the target driving data;
grouping the target driving data according to the data amount so that the number of the target driving data of each group is the same;
and compressing the target driving data of each group to obtain a plurality of compressed packets.
By adopting the technical scheme, under the condition that the current acquisition frequency is greater than or equal to the preset acquisition frequency, data transmission is optimized through data compression and grouping processing, resource consumption is reduced, and the efficiency and expandability of data acquisition are improved.
Optionally, before the acquiring the target driving data acquired at a plurality of different moments, the method further includes:
Performing cleaning processing on each driving data to identify and correct error values and abnormal values in the driving data;
converting the driving data after the cleaning treatment to unify a data format;
and carrying out alignment processing on the driving data after conversion processing so as to keep the consistency of a plurality of driving data in the time dimension.
By adopting the technical scheme, the cleaning process is helpful for identifying and correcting the error value and the abnormal value in the driving data. This improves the accuracy and reliability of the data. The alignment process ensures that the driving data collected at a plurality of different times is consistent in the time dimension. This allows the data of different data sources to be aligned on the time axis for comparison and analysis. The conversion process unifies the format of the driving data, making it easier to process and analyze. This helps to eliminate the variability of the data formats, thereby improving the operability of the data.
Optionally, after the determining whether the first predicted data is the same as the first actual data, the method further includes:
if the first predicted data is different from the first actual data, determining second predicted data at a second moment according to the change trend, wherein the second moment is a moment after the first moment, and the interval duration between the second moment and the first moment is the acquisition interval duration;
Acquiring second actual data acquired at the second moment, wherein the second actual data and the second predicted data are the same driving data;
and judging whether the second predicted data is identical to the second actual data or not, and if the second predicted data is identical to the second actual data, removing the first actual data.
By adopting the technical scheme, if the first predicted data is different from the first actual data, the predicted data at the second moment is predicted according to the data change trend, and then the accuracy is verified. If the second predicted data at the second moment is consistent with the second actual data at the moment, further indicating the data change trend, and the first actual data may be abnormal data, removing the abnormal data.
In a second aspect of the present application, a distributed edge data collection device is provided, including an acquisition module, a processing module, and a determination module, where:
the acquisition module is used for acquiring a plurality of target driving data acquired at different moments, wherein the target driving data is any one driving data of a plurality of driving data, and the driving data is data generated by vehicle electronic equipment in the preset vehicle driving process;
The processing module is used for determining the change trend of the target driving data according to a plurality of target driving data;
the processing module is used for determining first prediction data at a first moment according to the change trend, wherein the first moment is a moment after the current moment, and the interval duration between the first moment and the current moment is the acquisition interval duration of the target driving data;
the acquisition module is used for acquiring first actual data acquired at the first moment, wherein the first actual data and the first predicted data are the same driving data;
the judging module is configured to judge whether the first predicted data is the same as the first actual data, and if it is determined that the first predicted data is the same as the first actual data, determine an adjustment acquisition frequency of the target driving data according to a current acquisition frequency of the target driving data, where the adjustment acquisition frequency is smaller than the current acquisition frequency.
Optionally, the processing module is configured to determine a time window according to the current acquisition frequency;
the processing module is used for placing the time window at the first position so that the starting point of the time window coincides with first target driving data of the plurality of target driving data;
The processing module is used for determining a plurality of time sequence data contained when the time window is positioned at the first position in the plurality of target driving data;
the processing module is used for determining a statistical index according to the plurality of time series data, wherein the statistical index is used for reflecting the characteristics of the plurality of time series data;
the processing module is used for sequentially sliding the time windows to obtain a plurality of statistical indexes;
and the processing module is used for carrying out regression analysis on the plurality of statistical indexes to obtain the variation trend.
Optionally, the processing module is configured to determine, according to the current acquisition frequency, a number of vacancies between first driving data and second driving data, where the first driving data and the second driving data are two adjacent target driving data among the plurality of target driving data acquired based on the adjustment acquisition frequency;
the judging module is used for determining a plurality of filling data between the first driving data and the second driving data according to the change trend, wherein the filling data are the same as the vacancy number;
the processing module is used for sequentially filling the plurality of filling data between the first driving data and the second driving data.
Optionally, the acquiring module is configured to acquire a current acquisition frequency of the driving data;
the judging module is configured to judge a magnitude relation between the current acquisition frequency and a preset acquisition frequency, and if it is determined that the current acquisition frequency is smaller than the preset acquisition frequency, remove the third driving data from the third driving data and the fourth driving data, or remove the fourth driving data from the third driving data and the fourth driving data, where the third driving data and the fourth driving data are two adjacent driving data from the plurality of driving data.
Optionally, the acquiring module is configured to acquire a data amount of the target driving data if the current acquisition frequency is determined to be greater than or equal to the preset acquisition frequency;
the processing module is used for grouping the target driving data according to the data quantity so that the quantity of the target driving data of each group is the same;
and the processing module is used for compressing each group of target driving data to obtain a plurality of compressed packets.
Optionally, the processing module is used for performing cleaning processing on each driving data so as to identify and correct an error value and an abnormal value in the driving data;
The processing module is used for converting the driving data after the cleaning processing to unify the data format;
and the processing module is used for carrying out alignment processing on the driving data after conversion processing so as to keep the consistency of a plurality of driving data in the time dimension.
Optionally, the processing module is configured to determine, if the first predicted data is determined to be different from the first actual data, second predicted data at a second time according to the change trend, where the second time is a time subsequent to the first time, and an interval duration with the first time is the acquisition interval duration;
the acquisition module is used for acquiring second actual data acquired at the second moment, wherein the second actual data and the second predicted data are the same driving data;
the judging module is configured to judge whether the second predicted data is identical to the second actual data, and if it is determined that the second predicted data is identical to the second actual data, remove the first actual data.
In a third aspect the present application provides an electronic device comprising a processor, a memory for storing instructions, a user interface and a network interface, both for communicating with other devices, the processor being for executing the instructions stored in the memory to cause the electronic device to perform a method as claimed in any one of the preceding claims.
In a fourth aspect of the present application, there is provided a computer readable storage medium storing instructions that, when executed, perform a method as claimed in any one of the preceding claims.
In summary, one or more technical solutions provided in the embodiments of the present application at least have the following technical effects or advantages:
1. and generating various distributed edge data in the running process of the preset vehicle, and determining the change trend of the target driving data according to the existing target driving data aiming at the target driving data. And then predicting prediction data at a certain time in the future according to the change trend. And acquiring the acquired actual data at the moment, judging whether the predicted data are identical to the actual data, and if so, indicating that the change trend of the target driving data can be predicted. The acquisition frequency of the target driving data can be reduced, the data filling is performed through prediction later, a large amount of data is not required to be acquired through high frequency, and the distributed edge data acquisition can be performed efficiently.
2. The temporal window based prediction method is capable of capturing and quantifying trends in edge data, whether short term fluctuations or long term trends. This helps to better understand the evolution process of the target driving data, identifying patterns and laws in the data. Meanwhile, the size of the time window and the selection of the step length have flexibility, can be adjusted according to different analysis requirements and data properties, and can adapt to different target driving data types.
3. After the fact that the first actual data of the first predicted data are the same is determined, the calculated data change trend is correct, and then the acquisition frequency can be reduced. After data transmission, the data is filled with the vacant data caused by low-frequency acquisition according to the change trend of the data, so that the data is more complete. The continuity and consistency of the data is ensured and complete data can be provided even at low acquisition frequencies.
Drawings
Fig. 1 is a schematic flow chart of a distributed edge data collection method disclosed in an embodiment of the present application;
FIG. 2 is a schematic diagram of a time window sliding disclosed in an embodiment of the present application;
fig. 3 is a schematic structural diagram of a distributed edge data collection device according to an embodiment of the present disclosure;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Reference numerals illustrate: 301. an acquisition module; 302. a processing module; 303. a judging module; 401. a processor; 402. a communication bus; 403. a user interface; 404. a network interface; 405. a memory.
Detailed Description
In order to make those skilled in the art better understand the technical solutions in the present specification, the technical solutions in the embodiments of the present specification will be clearly and completely described below with reference to the drawings in the embodiments of the present specification, and it is obvious that the described embodiments are only some embodiments of the present application, but not all embodiments.
In the description of embodiments of the present application, words such as "for example" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described herein as "such as" or "for example" should not be construed as preferred or advantageous over other embodiments or designs. Rather, the use of words such as "or" for example "is intended to present related concepts in a concrete fashion.
In the description of the embodiments of the present application, the term "plurality" means two or more. For example, a plurality of systems means two or more systems, and a plurality of screen terminals means two or more screen terminals. Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating an indicated technical feature. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless expressly specified otherwise.
Distributed edge data refers to data stored on a plurality of edge computing nodes, which are typically distributed across the edges of a network, near the source of the data generation or end user. Such data is distributed across multiple geographical locations or network edges to meet real-time performance, low latency, and high availability requirements, and it is often necessary to coordinate and manage data synchronization, replication, and sharing among multiple nodes to support the needs of various applications and systems.
Many distributed edge data are involved for intelligent driving, which is critical to real-time decision making and driving assistance systems, including vehicle sensor data, real-time map and navigation data, environmental sensor data, and driver monitoring data, among others. These relevant distributed edge data are key components of intelligent driving systems for vehicle perception, decision making, route planning and driving monitoring. These data need to be processed at the edge nodes of the vehicle itself or nearby to support real-time intelligent driving functions.
During intelligent driving of the vehicle, a large amount of distributed edge data is generated, and most of the data is generated in real time, for example, obstacle detection is performed by the radar system of the vehicle every few microseconds. Collecting and subsequent processing and storage of such large-scale data requires a high hardware infrastructure and high performance computing resources. Therefore, there is a need for a method that enables efficient distributed edge data acquisition.
The embodiment discloses a distributed edge data acquisition method, referring to fig. 1, comprising the following steps:
s110, acquiring a plurality of target driving data acquired at different moments.
The distributed edge data acquisition method disclosed by the embodiment of the application is applied to a vehicle-mounted computing platform. An on-board computing platform is a computing platform of a preset vehicle (typically a vehicle-mounted computer) for processing and analyzing data from sensors, cameras and other data sources. In-vehicle computing platforms are often equipped with high performance processors and Graphics Processing Units (GPUs) for real-time data processing and decision-making.
In the running process of the preset vehicle, the related sensor and the electronic equipment acquire data according to the existing control instruction. For example, including vehicle sensor data, modern automobiles are equipped with various sensors, such as radar, cameras, ultrasonic sensors, and LiDAR (LiDAR), for sensing the environment surrounding the vehicle. The data generated by these sensors includes information such as obstacle detection, distance measurement, speed, direction, and object identification. Real-time map and navigation data, the intelligent driving system needs real-time map data, including roads, traffic signs, road conditions, road construction and navigation information. These data typically need to be stored and updated at the edge nodes to provide accurate navigation and route planning. Environmental sensor data, the intelligent driving vehicle can collect environmental data such as temperature, humidity, air pressure, visibility and the like so as to adapt to different meteorological conditions and road conditions.
Since intelligent driving involves many distributed edge data, i.e. driving data. However, some of these data are important to real-time decision making and driving assistance systems, while some do not participate in intelligent driving. For example, driver monitoring data, some intelligent driving systems use cameras and sensors to monitor the status of the driver, such as fatigue, distraction, and posture. This portion of data does not affect intelligent driving, and if this portion of data is collected, transmitted, and processed in real time, it may result in waste of hardware facilities and computing resources.
And after the related equipment collects driving data, transmitting the driving data to the vehicle-mounted computing platform. First, a large number of different driving data needs to be preprocessed, which includes at least a washing process, a conversion process, and an alignment process. And firstly, cleaning the driving data, and deleting or repairing errors, inconsistencies or missing values in the data. This may involve deleting duplicate data, filling in missing values, correcting data format errors, etc. Outliers are identified and processed that may affect the analysis results. Statistical methods or machine learning algorithms may be employed to detect outliers and select appropriate treatments, such as deletion, substitution or adjustment.
And then converting the driving data after the cleaning treatment, wherein the data conversion comprises converting the original data to change the measurement unit of the data, normalize the data or apply mathematical functions to improve analysis. Common data transformations include logarithmic transformation, normalization, and the like. While ensuring that the data is stored and presented in a proper format for analysis. This may involve converting the data to a standard format, such as CSV, JSON, or database format.
Finally, an alignment process is performed, and if the driving data is from different sources or has different time stamps, the data alignment needs to be performed to ensure that the data is consistent in the time dimension for subsequent analysis. The purge process helps to identify and correct erroneous and outliers in the driving data. This improves the accuracy and reliability of the data. The alignment process ensures that the driving data collected at a plurality of different times is consistent in the time dimension. This allows the data of different data sources to be aligned on the time axis for comparison and analysis. The conversion process unifies the format of the driving data, making it easier to process and analyze. This helps to eliminate the variability of the data formats, thereby improving the operability of the data.
After preprocessing various driving data, the vehicle-mounted computing platform calculates the current acquisition frequency of the driving data according to the data acquisition quantity and the acquisition time. And then judging the magnitude relation between the current acquisition frequency and the preset acquisition frequency, wherein for the preset acquisition frequency, different embodiments can be adjusted according to actual conditions to be used as a speed judgment standard of the driving data acquisition frequency. If the current acquisition frequency of the driving data is smaller than the preset acquisition frequency, the acquisition frequency of the driving data can be understood to be smaller, and the real-time requirement of the data is not high.
If the current acquisition frequency is greater than or equal to the preset acquisition frequency, acquiring the data size of the target driving data corresponding to the current acquisition frequency, namely, how many data the driving data have. Then, the target driving data are grouped according to the data quantity, and the group number is determined according to the data quantity so as to ensure that the number of the target driving data of each group is the same. And then compressing each group of target driving data to obtain a plurality of compressed packets, and finally sending the compressed packets to data processing equipment to complete data acquisition. Under the condition that the current acquisition frequency is greater than or equal to the preset acquisition frequency, data transmission is optimized through data compression and grouping processing, resource consumption is reduced, and data acquisition efficiency and expandability are improved.
Further, when the acquisition frequency of the driving data is smaller than the preset acquisition frequency, the driving data is sampled. One driving data is removed every interval, and any two driving data adjacent to each other in the driving data are taken as an example, the third driving data and the fourth driving data. The removal processing is performed on the third driving data of the third driving data and the fourth driving data, or the removal processing is performed on the fourth driving data of the third driving data and the fourth driving data. If the current acquisition frequency of the driving data is smaller than the preset acquisition frequency, the acquisition frequency of the driving data is smaller, and the real-time requirement of the driving data is lower. The amount of data can be further reduced by removing some of the data, thereby saving computation and communication resources.
S120, determining the change trend of the target driving data according to the plurality of target driving data.
Specifically, the time window size, i.e. the time span of the data within the window, is determined according to the previously determined current acquisition frequency of the target driving data. In general, the current acquisition frequency and the time window are in an inverse proportion relationship, and the specific proportion relationship between the current acquisition frequency and the time window can be freely adjusted according to the actual situation, and the embodiment is not particularly limited. The selected time window is then placed in the first position so that its starting point coincides with the first data point of the target driving data, ensuring that the analysis starts from the beginning of the data sequence. From a plurality of target driving data, it is determined which data are included in the first time window, which data are to be used for calculating statistical indicators and trends. For example, referring to fig. 2, the current acquisition frequency of the target driving data is to acquire data once every two seconds, resulting in data a, b, c, d, e, f, g, h … …. And the size of the time window is 16 seconds. The time window a is placed in the first place and contains the first 9 target driving data. The data within the selected time window is then used to calculate a statistical indicator. These statistical indicators may include mean, variance, standard deviation, maximum, minimum, etc. for reflecting the characteristics of the data. These indices are calculated for trend analysis. And then sliding the time window in turn to cover the entire target driving data sequence. Referring to fig. 2, the sliding interval may be 1 data, sequentially obtaining a time window B and a time window C. Repeating the above steps within each window calculates a statistical indicator, which will provide a statistical indicator over a series of time windows. Finally, regression analysis is performed on these statistical indicators. Regression analysis is a statistical method used to identify and quantify trends in data. Linear regression, polynomial regression, or other regression models may be used to find the relationship of the statistical indicators to time, thereby analyzing the trend of the target driving data.
The change trend comprises an increasing trend, a decreasing trend and a periodic fluctuation trend. The increasing trend means that the data exhibits a gradual or increasing character, but is not necessarily linear. The decreasing trend indicates that the data is decreasing or gradually decreasing, reflecting the trend of decreasing. The periodic fluctuation trend indicates that the data undergoes rapid fluctuation in a short time. The trend of the data is also more known, and is not listed here. The random variation trend of the data does not belong to the scope of the discussion of the application, and when the data authority randomly varies, the data can be understood as not carrying out subsequent processing or not calculating the variation trend.
The temporal window based prediction method is capable of capturing and quantifying trends in edge data, whether short term fluctuations or long term trends. This helps to better understand the evolution process of the target driving data, identifying patterns and laws in the data. Meanwhile, the size of the time window and the selection of the step length have flexibility, can be adjusted according to different analysis requirements and data properties, and can adapt to different target driving data types.
S130, determining first prediction data at a first moment according to the change trend.
After the change trend of the target driving data is determined, the numerical value of the target driving data at different moments can be calculated. As a simple example, a set of target driving data sampled once every second is "2.2,4.2,6.2,8.2, 10.2, 12.2, 14.2 … …", from which it can be seen that this set of data exhibits an increasing trend, and each increment is 2, it can be predicted that the data immediately following 14.2 should be 16.2. Similarly, the first predicted data at the first moment can be determined according to the change trend, the first moment is the moment after the current moment, and the interval duration between the first moment and the current moment is the acquisition interval duration of the target driving data.
S140, acquiring first actual data acquired at a first moment.
Since the first prediction data obtained in step S130 is predicted by the data change trend, there may be a case where there is a prediction error, and thus further verification is required. Namely, at a first moment, acquired first actual data is acquired, and the first actual data and the first predicted data belong to the same driving data. For example, at the current time, the first predicted data of the predicted first time is the in-vehicle temperature data, and then the first actual data should also be the in-vehicle temperature data, and is the in-vehicle temperature data collected at the first time.
S150, judging whether the first predicted data is identical to the first actual data, if so, determining the adjustment acquisition frequency of the target driving data according to the current acquisition frequency of the target driving data.
At a first moment, after acquiring the acquired first actual data, verifying whether the predicted first predicted data is correct. Namely, whether the first predicted data is the same as the first actual data or not is judged, if the first predicted data is the same as the first actual data, the result of prediction through the change trend of the target driving data is correct, and the acquisition frequency of the target driving data can be reduced. And determining an adjustment acquisition frequency according to the current acquisition frequency, wherein the adjustment acquisition frequency is smaller than the current acquisition frequency.
By adopting the technical scheme, various distributed edge data are generated in the running process of the preset vehicle, and the change trend of the target driving data is determined according to the existing target driving data aiming at the target driving data. And then predicting prediction data at a certain time in the future according to the change trend. And acquiring the acquired actual data at the moment, judging whether the predicted data are identical to the actual data, and if so, indicating that the change trend of the target driving data can be predicted. The acquisition frequency of the target driving data can be reduced, the data filling is performed through prediction later, a large amount of data is not required to be acquired through high frequency, and the distributed edge data acquisition can be performed efficiently.
Further, after the frequency of collecting the target driving data is reduced, the number of the collected target driving data is reduced, so that filling processing needs to be performed on the vacant target driving data for the accuracy of subsequent analysis. Taking any two adjacent target driving data in the plurality of target driving data acquired after the acquisition frequency is adjusted, the first driving data and the second driving data as examples. Firstly, according to the current acquisition frequency, namely, the acquisition frequency before adjustment, the vacancy number between the first driving data and the second driving data is determined. For example, if the first driving data and the second driving data are sampled every 8 seconds after the adjustment and sampled every 2 seconds before the adjustment, three driving data should be further included between the first driving data and the second driving data, and the number of vacancies is 3.
And then determining filling data between the first driving data and the second driving data according to the predicted change trend, wherein the number of the filling data is the same as the number of the vacant bits. And finally, sequentially filling the plurality of filling data between the first driving data and the second driving data. By adopting the technical scheme, after the first actual data of the first predicted data is the same, the calculated data change trend is correct, so that the acquisition frequency can be reduced. After data transmission, the data is filled with the vacant data caused by low-frequency acquisition according to the change trend of the data, so that the data is more complete. The continuity and consistency of the data is ensured and complete data can be provided even at low acquisition frequencies.
If the first predicted data is different from the first actual data, to verify whether the first actual data collected is abnormal data. And continuously determining second predicted data at a second moment according to the change trend, wherein the second moment is the later moment than the first moment, and the interval duration between the second moment and the first moment is the acquisition interval duration. And acquiring second actual data acquired at a second moment, wherein the second actual data and the second predicted data are the same driving data, and the second actual data, the second predicted data, the first actual data and the first predicted data are the same driving data. And finally judging whether the second predicted data is identical to the second actual data or not, and if the second predicted data is identical to the second actual data, indicating that the first actual data is possibly abnormal data, removing the first actual data and adopting the first predicted data.
If the first predicted data is different from the first actual data, predicting the predicted data at the second moment according to the data change trend, and then verifying the accuracy of the predicted data. If the second predicted data at the second moment is consistent with the second actual data at the moment, further indicating the data change trend, and the first actual data may be abnormal data, removing the abnormal data.
The embodiment also discloses a distributed edge data acquisition device, referring to fig. 3, including an acquisition module 301, a processing module 302, and a judgment module 303, where:
the acquiring module 301 is configured to acquire target driving data acquired at a plurality of different times, where the target driving data is any one driving data of a plurality of driving data, and the driving data is data generated by an electronic device of a vehicle during a preset vehicle driving process.
The processing module 302 is configured to determine a trend of the target driving data according to the plurality of target driving data.
The processing module 302 is configured to determine, according to the change trend, first predicted data at a first time, where the first time is a time subsequent to the current time, and an interval duration with the current time is an acquisition interval duration of the target driving data.
The acquiring module 301 is configured to acquire first actual data acquired at a first time, where the first actual data and the first predicted data are the same driving data.
The judging module 303 is configured to judge whether the first predicted data is the same as the first actual data, and if it is determined that the first predicted data is the same as the first actual data, determine an adjusted acquisition frequency of the target driving data according to the current acquisition frequency of the target driving data, where the adjusted acquisition frequency is less than the current acquisition frequency.
In a possible implementation, the processing module 302 is configured to determine the time window according to the current acquisition frequency.
The processing module 302 is configured to place the time window in a first position, so that a start point of the time window coincides with a first target driving data of the plurality of target driving data.
The processing module 302 is configured to determine a plurality of time series data included when the time window is located at the first position from the plurality of target driving data.
The processing module 302 is configured to determine a statistical indicator according to the plurality of time series data, where the statistical indicator is used to reflect characteristics of the plurality of time series data.
The processing module 302 is configured to sequentially slide the time window to obtain a plurality of statistical indexes.
And the processing module 302 is configured to perform regression analysis on the plurality of statistical indexes to obtain a variation trend.
In a possible implementation manner, the processing module 302 is configured to determine, according to the current acquisition frequency, a number of vacancies between the first driving data and the second driving data, where the first driving data and the second driving data are two adjacent target driving data among the plurality of target driving data acquired based on the adjustment acquisition frequency.
The judging module 303 is configured to determine, according to the change trend, a plurality of filling data between the first driving data and the second driving data, where the plurality of filling data is the same as the number of vacant bits.
The processing module 302 is configured to sequentially fill the plurality of filling data between the first driving data and the second driving data.
In one possible implementation, the acquiring module 301 is configured to acquire a current acquisition frequency of driving data.
The judging module 303 is configured to judge a magnitude relation between the current collection frequency and the preset collection frequency, and if it is determined that the current collection frequency is smaller than the preset collection frequency, remove the third driving data of the third driving data and the fourth driving data, or remove the fourth driving data of the third driving data and the fourth driving data, where the third driving data and the fourth driving data are two adjacent driving data of the plurality of driving data.
In one possible implementation, the acquiring module 301 is configured to acquire the data amount of the target driving data if it is determined that the current acquisition frequency is greater than or equal to the preset acquisition frequency.
The processing module 302 is configured to group the target driving data according to the data amount, so that the number of the target driving data in each group is the same.
The processing module 302 is configured to perform compression processing on each set of target driving data to obtain a plurality of compression packets.
In one possible implementation, the processing module 302 is configured to perform a cleaning process on each driving data to identify and correct erroneous and outliers in the driving data.
The processing module 302 is configured to perform conversion processing on the driving data after the cleaning processing, so as to unify a data format.
And the processing module 302 is configured to perform alignment processing on the driving data after the conversion processing, so as to keep the consistency of multiple driving data in the time dimension.
In a possible implementation manner, the processing module 302 is configured to determine, if it is determined that the first predicted data is different from the first actual data, second predicted data at a second time according to the change trend, where the second time is a time subsequent to the first time, and an interval duration with the first time is an acquisition interval duration.
The acquiring module 301 is configured to acquire second actual data acquired at a second moment, where the second actual data and the second predicted data are the same driving data.
The judging module 303 is configured to judge whether the second predicted data is identical to the second actual data, and if it is determined that the second predicted data is identical to the second actual data, remove the first actual data.
It should be noted that: in the device provided in the above embodiment, when implementing the functions thereof, only the division of the above functional modules is used as an example, in practical application, the above functional allocation may be implemented by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules, so as to implement all or part of the functions described above. In addition, the embodiments of the apparatus and the method provided in the foregoing embodiments belong to the same concept, and specific implementation processes of the embodiments of the method are detailed in the method embodiments, which are not repeated herein.
The embodiment also discloses an electronic device, referring to fig. 4, the electronic device may include: at least one processor 401, at least one communication bus 402, a user interface 403, a network interface 404, at least one memory 405.
Wherein communication bus 402 is used to enable connected communications between these components.
The user interface 403 may include a Display screen (Display) and a Camera (Camera), and the optional user interface 403 may further include a standard wired interface and a standard wireless interface.
The network interface 404 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface), among others.
Wherein the processor 401 may include one or more processing cores. The processor 401 connects the various parts within the entire server using various interfaces and lines, performs various functions of the server and processes data by executing or executing instructions, programs, code sets, or instruction sets stored in the memory 405, and invoking data stored in the memory 405. Alternatively, the processor 401 may be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), programmable logic array (Programmable Logic Array, PLA). The processor 401 may integrate one or a combination of several of a central processor 401 (Central Processing Unit, CPU), an image processor 401 (Graphics Processing Unit, GPU), a modem, etc. The CPU mainly processes an operating system, a user interface, an application program and the like; the GPU is used for rendering and drawing the content required to be displayed by the display screen; the modem is used to handle wireless communications. It will be appreciated that the modem may not be integrated into the processor 401 and may be implemented by a single chip.
The Memory 405 may include a random access Memory 405 (Random Access Memory, RAM) or a Read-Only Memory 405 (Read-Only Memory). Optionally, the memory 405 includes a non-transitory computer readable medium (non-transitory computer-readable storage medium). Memory 405 may be used to store instructions, programs, code sets, or instruction sets. The memory 405 may include a stored program area and a stored data area, wherein the stored program area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playing function, an image playing function, etc.), instructions for implementing the above-described various method embodiments, etc.; the storage data area may store data or the like involved in the above respective method embodiments. The memory 405 may also optionally be at least one storage device located remotely from the aforementioned processor 401. As shown, an operating system, network communication module, user interface 403 module, and application programs for the distributed edge data collection method may be included in memory 405, which is a computer storage medium.
In the electronic device shown in fig. 4, the user interface 403 is mainly used for providing an input interface for a user, and acquiring data input by the user; and the processor 401 may be used to invoke an application in the memory 405 that stores the distributed edge data collection method, which when executed by the one or more processors 401, causes the electronic device to perform the method as in one or more of the embodiments described above.
It should be noted that, for simplicity of description, the foregoing method embodiments are all expressed as a series of action combinations, but it should be understood by those skilled in the art that the present application is not limited by the order of actions described, as some steps may be performed in other order or simultaneously in accordance with the present application. Further, those skilled in the art will also appreciate that the embodiments described in the specification are all preferred embodiments, and that the acts and modules referred to are not necessarily required in the present application.
In the foregoing embodiments, the descriptions of the embodiments are emphasized, and for parts of one embodiment that are not described in detail, reference may be made to related descriptions of other embodiments.
In the several embodiments provided herein, it should be understood that the disclosed apparatus may be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative, such as a division of units, merely a division of logic functions, and there may be additional divisions in actual implementation, such as multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some service interface, device or unit indirect coupling or communication connection, electrical or otherwise.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable memory 405. Based on such understanding, the technical solution of the present application may be embodied in essence or a part contributing to the prior art or all or part of the technical solution in the form of a software product stored in a memory 405, including several instructions for causing a computer device (which may be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the methods of the embodiments of the present application. And the aforementioned memory 405 includes: various media capable of storing program codes, such as a U disk, a mobile hard disk, a magnetic disk or an optical disk.
The foregoing is merely exemplary embodiments of the present disclosure and is not intended to limit the scope of the present disclosure. That is, equivalent changes and modifications are contemplated by the teachings of this disclosure, which fall within the scope of the present disclosure. Other embodiments of the present disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure. This application is intended to cover any adaptations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a scope and spirit of the disclosure being indicated by the claims.
Claims (10)
1. The distributed edge data acquisition method is characterized by comprising the following steps of:
acquiring a plurality of target driving data acquired at different moments, wherein the target driving data is any one driving data of a plurality of driving data, and the driving data is data generated by vehicle electronic equipment in a preset vehicle driving process;
determining the change trend of the target driving data according to a plurality of target driving data;
According to the change trend, determining first prediction data at a first moment, wherein the first moment is a moment after the current moment, and the interval duration between the first moment and the current moment is the acquisition interval duration of the target driving data;
acquiring first actual data acquired at the first moment, wherein the first actual data and the first predicted data are the same driving data;
judging whether the first predicted data is identical to the first actual data or not, if the first predicted data is identical to the first actual data, determining an adjustment acquisition frequency of the target driving data according to the current acquisition frequency of the target driving data, wherein the adjustment acquisition frequency is smaller than the current acquisition frequency.
2. The distributed edge data collection method according to claim 1, wherein the determining the trend of the target driving data according to the plurality of target driving data specifically includes:
determining a time window according to the current acquisition frequency;
placing the time window in the first position so that the starting point of the time window coincides with first target driving data of a plurality of target driving data;
Determining a plurality of time sequence data contained when the time window is positioned at the first position in the plurality of target driving data;
determining a statistical index according to the plurality of time series data, wherein the statistical index is used for reflecting the characteristics of the plurality of time series data;
sequentially sliding the time windows to obtain a plurality of statistical indexes;
and carrying out regression analysis on a plurality of statistical indexes to obtain the variation trend.
3. The distributed edge data collection method according to claim 1, wherein after the determining the adjusted collection frequency of the target driving data according to the current collection frequency of the target driving data if the first prediction data is the same as the first actual data, the method further comprises:
determining a vacancy number between first driving data and second driving data according to the current acquisition frequency, wherein the first driving data and the second driving data are two adjacent target driving data in a plurality of target driving data acquired based on the adjustment acquisition frequency;
determining a plurality of filling data between the first driving data and the second driving data according to the change trend, wherein the number of the filling data is the same as the number of the vacant bits;
And sequentially filling a plurality of filling data between the first driving data and the second driving data.
4. The distributed edge data collection method of claim 1, wherein after the obtaining the target driving data collected at a plurality of different times, the method further comprises:
acquiring the current acquisition frequency of the driving data;
judging the magnitude relation between the current acquisition frequency and the preset acquisition frequency, if the current acquisition frequency is determined to be smaller than the preset acquisition frequency, removing the third driving data in the third driving data and the fourth driving data or removing the fourth driving data in the third driving data and the fourth driving data, wherein the third driving data and the fourth driving data are two adjacent driving data in a plurality of driving data.
5. The method of claim 4, further comprising, after said determining the magnitude relation between the current acquisition frequency and a preset acquisition frequency:
if the current acquisition frequency is determined to be greater than or equal to the preset acquisition frequency, acquiring the data volume of the target driving data;
Grouping the target driving data according to the data amount so that the number of the target driving data of each group is the same;
and compressing the target driving data of each group to obtain a plurality of compressed packets.
6. The distributed edge data collection method of claim 1, wherein prior to the obtaining the target driving data collected at the plurality of different times, the method further comprises:
performing cleaning processing on each driving data to identify and correct error values and abnormal values in the driving data;
converting the driving data after the cleaning treatment to unify a data format;
and carrying out alignment processing on the driving data after conversion processing so as to keep the consistency of a plurality of driving data in the time dimension.
7. The distributed edge data collection method of claim 1, wherein after the determining whether the first predicted data is the same as the first actual data, the method further comprises:
if the first predicted data is different from the first actual data, determining second predicted data at a second moment according to the change trend, wherein the second moment is a moment after the first moment, and the interval duration between the second moment and the first moment is the acquisition interval duration;
Acquiring second actual data acquired at the second moment, wherein the second actual data and the second predicted data are the same driving data;
and judging whether the second predicted data is identical to the second actual data or not, and if the second predicted data is identical to the second actual data, removing the first actual data.
8. The distributed edge data acquisition device is characterized by comprising an acquisition module (301), a processing module (302) and a judging module (303), wherein:
the acquiring module (301) is configured to acquire target driving data acquired at a plurality of different times, where the target driving data is any one driving data of a plurality of driving data, and the driving data is data generated by vehicle electronic equipment during a preset vehicle driving process;
the processing module (302) is configured to determine a trend of the target driving data according to a plurality of target driving data;
the processing module (302) is configured to determine, according to the variation trend, first prediction data at a first time, where the first time is a time subsequent to a current time, and an interval duration between the first time and the current time is an acquisition interval duration of the target driving data;
The acquiring module (301) is configured to acquire first actual data acquired at the first moment, where the first actual data and the first predicted data are the same driving data;
the judging module (303) is configured to judge whether the first predicted data is the same as the first actual data, and if it is determined that the first predicted data is the same as the first actual data, determine an adjusted acquisition frequency of the target driving data according to a current acquisition frequency of the target driving data, where the adjusted acquisition frequency is smaller than the current acquisition frequency.
9. An electronic device comprising a processor (401), a memory (405), a user interface (403) and a network interface (404), the memory (405) being configured to store instructions, the user interface (403) and the network interface (404) being configured to communicate with other devices, the processor (401) being configured to execute the instructions stored in the memory (405) to cause the electronic device to perform the method of any of claims 1-7.
10. A computer readable storage medium storing instructions which, when executed, perform the method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410270545.8A CN117874435B (en) | 2024-03-11 | 2024-03-11 | Distributed edge data acquisition method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410270545.8A CN117874435B (en) | 2024-03-11 | 2024-03-11 | Distributed edge data acquisition method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117874435A true CN117874435A (en) | 2024-04-12 |
| CN117874435B CN117874435B (en) | 2024-06-25 |
Family
ID=90581579
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410270545.8A Active CN117874435B (en) | 2024-03-11 | 2024-03-11 | Distributed edge data acquisition method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117874435B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021159359A1 (en) * | 2020-02-12 | 2021-08-19 | 深圳元戎启行科技有限公司 | Data collection method and device for operating system of unmanned vehicle |
| CN113672467A (en) * | 2021-08-24 | 2021-11-19 | 中国电信股份有限公司 | Operation and maintenance early warning method and device, electronic equipment and storage medium |
| CN115269573A (en) * | 2022-07-20 | 2022-11-01 | 重庆长安汽车股份有限公司 | Method and device for complementing missing vehicle data, vehicle and storage medium |
| US11487273B1 (en) * | 2021-04-30 | 2022-11-01 | Dalian University Of Technology | Distributed industrial energy operation optimization platform automatically constructing intelligent models and algorithms |
| CN115685949A (en) * | 2022-12-29 | 2023-02-03 | 深圳市信润富联数字科技有限公司 | Method and device for adjusting data sampling frequency in discrete machining production process |
| US20230359542A1 (en) * | 2022-05-05 | 2023-11-09 | International Business Machines Corporation | Handling data gaps in sequential data |
| CN117370033A (en) * | 2023-12-07 | 2024-01-09 | 杭州义益钛迪信息技术有限公司 | Cloud edge cooperative resource optimization method and device, electronic equipment and storage medium |
| CN117423224A (en) * | 2023-09-27 | 2024-01-19 | 深圳市地质环境研究院有限公司 | Data acquisition method of slope monitoring internet of things equipment |
-
2024
- 2024-03-11 CN CN202410270545.8A patent/CN117874435B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021159359A1 (en) * | 2020-02-12 | 2021-08-19 | 深圳元戎启行科技有限公司 | Data collection method and device for operating system of unmanned vehicle |
| US11487273B1 (en) * | 2021-04-30 | 2022-11-01 | Dalian University Of Technology | Distributed industrial energy operation optimization platform automatically constructing intelligent models and algorithms |
| CN113672467A (en) * | 2021-08-24 | 2021-11-19 | 中国电信股份有限公司 | Operation and maintenance early warning method and device, electronic equipment and storage medium |
| US20230359542A1 (en) * | 2022-05-05 | 2023-11-09 | International Business Machines Corporation | Handling data gaps in sequential data |
| CN115269573A (en) * | 2022-07-20 | 2022-11-01 | 重庆长安汽车股份有限公司 | Method and device for complementing missing vehicle data, vehicle and storage medium |
| CN115685949A (en) * | 2022-12-29 | 2023-02-03 | 深圳市信润富联数字科技有限公司 | Method and device for adjusting data sampling frequency in discrete machining production process |
| CN117423224A (en) * | 2023-09-27 | 2024-01-19 | 深圳市地质环境研究院有限公司 | Data acquisition method of slope monitoring internet of things equipment |
| CN117370033A (en) * | 2023-12-07 | 2024-01-09 | 杭州义益钛迪信息技术有限公司 | Cloud edge cooperative resource optimization method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117874435B (en) | 2024-06-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109844666A (en) | System and method for interior predictive fault detection | |
| CN101999101B (en) | The defining method of system cloud gray model prediction | |
| CN111613059B (en) | Data processing method and device | |
| CN113723338B (en) | Sensor abnormality detection method, device and computer-readable storage medium | |
| CN112874530A (en) | Vehicle diagnosis method and device, electronic equipment and storage medium | |
| CN114490161A (en) | Fault diagnosis method and device, vehicle and storage medium | |
| CN110490132B (en) | Data processing method and device | |
| CN110266774B (en) | Method, device and equipment for inspecting data quality of Internet of vehicles and storage medium | |
| US20210390802A1 (en) | Method, Computer Program And Device For Processing Signals | |
| CN117874435B (en) | Distributed edge data acquisition method and device, electronic equipment and storage medium | |
| EP2847676B1 (en) | System and method of distributed procesing for machine-vision analysis | |
| CN110853364B (en) | Data monitoring method and device | |
| CN112232326A (en) | Driving information generation method and device, electronic equipment and computer readable medium | |
| CN114416441A (en) | Real-time database automatic testing method and system, electronic equipment and storage medium | |
| CN115293735A (en) | Unmanned factory industrial internet platform monitoring management method and system | |
| CN114136342A (en) | Mileage tampering judgment method and system | |
| CN111275847B (en) | Method and device for detecting shunting vehicle | |
| CN114034972A (en) | Intelligent cable fault determination method and device based on image data | |
| CN113379285A (en) | Building environment monitoring method, building environment monitoring device, building environment monitoring equipment, storage medium and program product | |
| CN111798591A (en) | Method and device for determining total mileage of vehicle, computer equipment and storage medium | |
| CN114608639B (en) | Instrument algorithm calibration method, device, terminal, storage medium and system | |
| CN115292146B (en) | System capacity estimation method, system, equipment and storage medium | |
| CN116176579B (en) | Automatic driving following distance measuring and calculating device and method | |
| CN111835830B (en) | Data perception system, method and device | |
| CN114399355B (en) | Information pushing method and device based on user conversion rate and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |