A diesel vehicle monitoring data management method, device, medium and equipment

Abstract

The application provides a diesel vehicle monitoring data management method and device, medium and equipment, determines the storage strategy of current monitoring data based on the data value score of the current monitoring data; determines similar monitoring data in the historical monitoring data according to the characteristic identifier of the monitoring data, calculates the comprehensive calling frequency combined with the similar monitoring data and the current monitoring data, to more accurately determine the calling frequency of the same type of monitoring data, and determines the weight according to the calling frequency of each characteristic identifier, and calculates the data value score combined with the weight and the comprehensive calling frequency, to determine the storage strategy of the current monitoring data, which can fully consider the correlation and importance of the monitoring data, and also consider the calling frequency of the characteristic identifier, to improve the accuracy of the data value score, so as to provide a more suitable strategy for the storage of monitoring data, and take into account the storage demand and calling demand of data.

Description

Technical Field

[0001] This application relates to the field of diesel vehicle monitoring technology, specifically to a method, device, medium, and equipment for managing diesel vehicle monitoring data. Background Technology

[0002] Diesel vehicles produce various emissions during operation due to the combustion of diesel fuel. These emissions contribute to air pollution and the greenhouse effect, necessitating emissions monitoring. With the development of intelligent technology and big data, data management has become increasingly important, leading to the application of more and more sensors and other monitoring devices in diesel vehicles to monitor their status. As the types and number of monitoring devices increase and the data accumulates over time, the amount of monitoring data from diesel vehicles grows exponentially. Better management of this monitoring data—ensuring the retention of valid data while compressing or erasing other data—has become a crucial research topic for those skilled in the art. Current storage methods are mostly single-mode storage, which not only results in large storage space requirements but also affects data retrieval efficiency. Therefore, a method that balances storage and retrieval efficiency is needed. Summary of the Invention

[0003] To address the aforementioned technical problems, this application is proposed. Embodiments of this application provide a method, apparatus, medium, and device for managing diesel vehicle monitoring data.

[0004] According to one aspect of this application, a method for managing diesel vehicle monitoring data is provided, comprising: acquiring current monitoring data of a target diesel vehicle; wherein the current monitoring data includes multiple feature identifiers; calculating the similarity between the current monitoring data and historical monitoring data based on the feature identifiers; using historical monitoring data with a similarity greater than a preset similarity threshold as similar monitoring data of the current monitoring data; calculating the comprehensive call frequency of the current monitoring data based on the current monitoring data and the similar monitoring data; calculating the feature weight of each feature identifier based on the call frequency of each feature identifier; calculating the data value score of the current monitoring data based on the feature weights of all feature identifiers and the comprehensive call frequency; and determining the storage strategy of the current monitoring data based on the data value score of the current monitoring data.

[0005] In one embodiment, calculating the similarity between the current monitoring data and the historical monitoring data based on the feature identifier includes: calculating the cosine similarity between the feature identifier of the current monitoring data and the corresponding feature identifier of the historical monitoring data to obtain the similarity.

[0006] In one embodiment, calculating the comprehensive call frequency of the current monitoring data based on the current monitoring data and the similar monitoring data includes: calculating the impact value of the similar monitoring data on the current monitoring data; and calculating the comprehensive call frequency based on the impact value and the call frequency of the current monitoring data.

[0007] In one embodiment, calculating the impact value of the similar monitoring data on the current monitoring data includes: calculating the impact value of the similar monitoring data on the current monitoring data based on the call frequency of the similar monitoring data and the similarity between the current monitoring data and the similar monitoring data.

[0008] In one embodiment, calculating the feature weight of each feature identifier based on its call frequency includes: fitting a linear equation between the call frequency of the feature identifier and the time window based on the call frequency of the feature identifier within multiple time windows; and calculating the feature weight of the feature identifier based on the linear equation.

[0009] In one embodiment, determining the storage strategy for the current monitoring data based on the data value score includes: if the data value score is greater than or equal to a first preset value, storing the current monitoring data on a local server; if the data value score is less than the first preset value but greater than a second preset value, storing the analysis and processing results of the current monitoring data on a local server; wherein the first preset value is greater than the second preset value; and if the data value score is greater than or equal to the second preset value, storing the current monitoring data on a cloud server.

[0010] In one embodiment, the diesel vehicle monitoring data management method further includes: inputting relevant information of the current monitoring data into a neural network model to obtain the retrieval probability of the current monitoring data; and determining a storage strategy for the current monitoring data based on the retrieval probability.

[0011] According to another aspect of this application, a diesel vehicle monitoring data management device is provided, comprising: a monitoring data acquisition module for acquiring current monitoring data of a target diesel vehicle; wherein the current monitoring data includes multiple feature identifiers; a similarity calculation module for calculating the similarity between the current monitoring data and historical monitoring data based on the feature identifiers; a similar data determination module for using historical monitoring data with a similarity greater than a preset similarity threshold as similar monitoring data of the current monitoring data; a call frequency calculation module for calculating the comprehensive call frequency of the current monitoring data based on the current monitoring data and the similar monitoring data; a feature weight calculation module for calculating the feature weight of each feature identifier based on the call frequency of each feature identifier; a value score calculation module for calculating the data value score of the current monitoring data based on the feature weights of all feature identifiers and the comprehensive call frequency; and a storage strategy determination module for determining the storage strategy of the current monitoring data based on the data value score of the current monitoring data.

[0012] According to another aspect of this application, a computer-readable storage medium is provided, the storage medium storing a computer program for performing any of the methods described above.

[0013] According to another aspect of this application, an electronic device is provided, comprising: a processor; a memory for storing processor-executable instructions; the processor being configured to perform any of the methods described above.

[0014] This application provides a diesel vehicle monitoring data management method, device, medium, and equipment. The method involves acquiring current monitoring data of a target diesel vehicle, where the current monitoring data includes multiple feature identifiers. Based on these feature identifiers, the method calculates the similarity between the current monitoring data and historical monitoring data. Historical monitoring data with a similarity greater than a preset similarity threshold is used as similar monitoring data for the current monitoring data. Based on the current monitoring data and similar monitoring data, the method calculates the comprehensive call frequency of the current monitoring data. Based on the call frequency of each feature identifier, the method calculates the feature weight of each feature identifier. Based on the feature weights of all feature identifiers and the comprehensive call frequency, the method calculates the data value score of the current monitoring data. Value scoring determines the storage strategy for current monitoring data. Based on the feature identifiers of the monitoring data, similar monitoring data from historical data are identified. The comprehensive call frequency is calculated by combining the similar monitoring data and the current monitoring data to more accurately determine the call frequency of the same type of monitoring data. Furthermore, weights are determined based on the call frequency of each feature identifier. The data value score is calculated by combining the weights and the comprehensive call frequency, thereby determining the storage strategy for the current monitoring data. This approach fully considers the relevance and importance of the monitoring data, as well as the call frequency of feature identifiers, improving the accuracy of the data value score and providing a more suitable storage strategy that balances data storage and retrieval needs. Attached Figure Description

[0015] The above and other objects, features, and advantages of this application will become more apparent from the more detailed description of the embodiments of this application in conjunction with the accompanying drawings. The drawings are provided to further illustrate the embodiments of this application and form part of the specification. They are used together with the embodiments of this application to explain this application and do not constitute a limitation thereof. In the drawings, the same reference numerals generally represent the same components or steps.

[0016] Figure 1 This is a flowchart illustrating a diesel vehicle monitoring data management method provided in an exemplary embodiment of this application.

[0017] Figure 2 This is a schematic diagram of the structure of a diesel vehicle monitoring data management device provided in an exemplary embodiment of this application.

[0018] Figure 3 This is a structural diagram of an electronic device provided in an exemplary embodiment of this application. Detailed Implementation

[0019] Hereinafter, exemplary embodiments according to this application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are merely some embodiments of this application, and not all embodiments of this application. It should be understood that this application is not limited to the exemplary embodiments described herein.

[0020] Figure 1 This is a flowchart illustrating a diesel vehicle monitoring data management method provided in an exemplary embodiment of this application. Figure 1 As shown, the diesel vehicle monitoring data management method includes the following steps:

[0021] Step 110: Obtain the current monitoring data of the target diesel vehicle.

[0022] The current monitoring data includes multiple feature identifiers. Each piece of monitoring data has its own set of data feature identifiers, such as sensor type, vehicle operating status identifier, and engine operating parameters. This application achieves real-time monitoring of the target diesel vehicle, such as emissions monitoring data, by acquiring the current monitoring data of the target diesel vehicle.

[0023] Step 120: Calculate the similarity between the current monitoring data and the historical monitoring data based on the feature identifier.

[0024] This application calculates the similarity between current monitoring data and historical monitoring data based on the feature identifiers of current monitoring data, in order to filter out monitoring data in historical monitoring data that are the same as or similar to current monitoring data.

[0025] Step 130: Use historical monitoring data with a similarity greater than the preset similarity threshold as similar monitoring data for the current monitoring data.

[0026] By calculating the similarity between current monitoring data and historical monitoring data, and selecting historical monitoring data with a similarity greater than a similarity threshold as similar monitoring data for the current monitoring data, the importance and frequency of use of the current monitoring data can be comprehensively determined.

[0027] Step 140: Calculate the overall call frequency of the current monitoring data based on the current monitoring data and similar monitoring data.

[0028] This application combines current monitoring data and similar monitoring data to comprehensively calculate the overall call frequency of current monitoring data.

[0029] Step 150: Calculate the feature weight of each feature identifier based on the call frequency of each feature identifier.

[0030] The importance of each feature identifier is determined based on its call frequency, and the feature weight of that feature identifier is then calculated.

[0031] Step 160: Calculate the data value score of the current monitoring data based on the feature weights of all feature identifiers and the comprehensive call frequency.

[0032] By combining the feature weights of all feature identifiers and the overall call frequency, the data value score of the current monitoring data is calculated, thereby determining the importance of the current monitoring data.

[0033] Step 170: Determine the storage strategy for the current monitoring data based on the data value score of the current monitoring data.

[0034] This application uses the data value score of the current monitoring data to rationally arrange the storage and retrieval of the current monitoring data between local servers and cloud servers, so as to achieve efficient data management and use.

[0035] This application provides a diesel vehicle monitoring data management method, which involves acquiring current monitoring data of a target diesel vehicle; wherein the current monitoring data includes multiple feature identifiers; calculating the similarity between the current monitoring data and historical monitoring data based on the feature identifiers; using historical monitoring data with a similarity greater than a preset similarity threshold as similar monitoring data of the current monitoring data; calculating the comprehensive call frequency of the current monitoring data based on the current monitoring data and the similar monitoring data; calculating the feature weight of each feature identifier based on the call frequency of each feature identifier; calculating the data value score of the current monitoring data based on the feature weights of all feature identifiers and the comprehensive call frequency; and calculating the data value score of the current monitoring data based on the data value score of the current monitoring data. The process involves determining the storage strategy for the current monitoring data; identifying similar monitoring data from historical data based on the feature identifiers of the monitoring data; calculating the comprehensive call frequency by combining the similar monitoring data and the current monitoring data to more accurately determine the call frequency of the same type of monitoring data; determining the weight based on the call frequency of each feature identifier; and calculating the data value score by combining the weight and the comprehensive call frequency. This approach determines the storage strategy for the current monitoring data, fully considering both the relevance and importance of the monitoring data, as well as the call frequency of the feature identifiers, to improve the accuracy of the data value score. This provides a more suitable strategy for storing monitoring data, balancing both storage and retrieval needs.

[0036] In one embodiment, step 120 can be implemented by calculating the cosine similarity between the feature identifier of the current monitoring data and the corresponding feature identifier of the historical monitoring data to obtain the similarity.

[0037] Specifically, regarding the current monitoring data Let its feature identifier set be . ,in, For the i-th feature identifier, For historical monitoring data Denote its feature identifier set Constructing a cosine similarity function The similarity between data feature identifiers of two monitoring data sets is calculated based on the cosine similarity function. ,when When the similarity threshold is reached, historical monitoring data is considered acceptable. and Sufficient similarity will have an effect on The value assessment is affected, and historical monitoring data is selected at this time. For similar monitoring data.

[0038] In one embodiment, step 140 can be implemented by: calculating the impact value of similar monitoring data on the current monitoring data; and calculating the comprehensive call frequency based on the impact value and the call frequency of the current monitoring data.

[0039] This application calculates the impact value of similar monitoring data on current monitoring data to determine the value assessment of the current monitoring data, and calculates the comprehensive call frequency by combining the impact value of similar monitoring data on the current monitoring data and the call frequency of the current monitoring data.

[0040] In one embodiment, step 140 can be implemented by calculating the impact value of similar monitoring data on the current monitoring data based on the frequency of similar monitoring data calls and the similarity between the current monitoring data and similar monitoring data.

[0041] This application uses statistical analysis of current monitoring data. The number of calls within a certain time period, and the calculation of current monitoring data. Self-call frequency For similar monitoring data Calculate its impact on current monitoring data Impact value ,in, The calculation formula is:

[0042] ;

[0043] in, yes The frequency of calls within a certain time period.

[0044] Taking into account both the current monitoring data's own calling frequency and the impact of similar monitoring data on the current monitoring data, the comprehensive calling frequency is calculated using the following formula. :

[0045] .

[0046] In one embodiment, step 150 can be implemented as follows: based on the call frequency of the feature identifier within multiple time windows, a linear equation between the call frequency of the feature identifier and the time window is fitted; based on the linear equation, the feature weight of the feature identifier is calculated.

[0047] Specifically, the call records are divided into multiple time windows according to the time sequence. For each data feature identifier Statistical analysis of its call frequency within each time window. And map the time window to the independent variable. (like Mapped to Mapping to level 2), call frequency as the dependent variable. Fitting a straight line using the least squares method Feature weights Based on the slope The calculation yielded: .when When, it indicates that the feature identifier Its importance increases over time; when When, it indicates that the feature identifier Its importance is decreasing; when When, it indicates that the feature identifier Its importance is relatively stable.

[0048] In one embodiment, the specific implementation of step 170 above may be as follows: if the data value score is greater than or equal to a first preset value, the current monitoring data is stored on a local server; if the data value score is less than the first preset value but greater than a second preset value, the analysis and processing results of the current monitoring data are stored on a local server; wherein, the first preset value is greater than the second preset value; if the data value score is greater than or equal to the second preset value, the current monitoring data is stored on a cloud server.

[0049] This application calculates the data value score of the current monitoring data based on the feature weights of all feature identifiers and the comprehensive call frequency. The formula for calculating the data value score is as follows:

[0050] ;

[0051] in, The data value scoring formula comprehensively considers the feature weights of the monitoring data's feature identifiers and the overall call frequency, providing a comprehensive indicator to measure the value of each monitoring data.

[0052] when When the (first preset value) is reached, the current monitoring data is directly stored on the local server to ensure that high-value data can be quickly accessed locally, thereby improving the system response speed.

[0053] when At that time, the system analyzes and processes the monitoring data cluster to which the current monitoring data belongs, and stores the processed results on the local server. For example, for a speed monitoring data cluster, statistical characteristics such as the average speed, standard deviation of speed, maximum speed, and minimum speed over a certain period of time can be calculated as the results of the analysis and processing, aiming to preserve key information of the data with minimal storage cost.

[0054] when At this time, the current monitoring data is not stored on the local server, but is only retrieved from the cloud server when necessary, saving storage resources on the local server.

[0055] In one embodiment, the above-mentioned diesel vehicle monitoring data management method may further include: inputting relevant information of the current monitoring data into a neural network model to obtain the retrieval probability of the current monitoring data; and determining the storage strategy of the current monitoring data based on the retrieval probability.

[0056] This application constructs a neural network model to predict the probability of accessing current monitoring data. The input to the neural network model includes multiple data feature labels of the monitoring data (such as sensor type, vehicle operating status identifier, engine operating parameters, etc.), data generation timestamps (extracting time series features, such as hour, day, week, etc.), historical access records (including access frequency over a past period, last access time interval, etc.), and feature weights of the data feature identifiers. These rich input features provide the neural network model with more comprehensive information, helping it to better understand the characteristics and calling patterns of the data. The hidden layers of this neural network model can use Long Short-Term Memory (LSTM) networks or Gated Recurrent Units (GRUs) as their basic structure. These recurrent neural networks are advantageous in processing time-series data, automatically capturing long-term dependencies of time-series features, such as the changing trend of calling frequency of data feature identifiers over time. The number of neurons and layers can be adjusted according to actual needs. The output layer uses the sigmoid function to map the output value between 0 and 1, representing the probability that the monitored data will be called within a future period. .

[0057] During model training, the collected historical monitoring data and its call records are divided into training and test sets, according to... For training, The proportion used for testing, and the cross-entropy loss function with L2 regularization:

[0058] Loss ,

[0059] in, The number of training samples. For the first The actual call label for each sample (1 for called, 0 for not called). The model predicts the first The probability of calling a sample, It is the regularization coefficient. It is the first Layer weights, It refers to the number of network layers.

[0060] Through multiple iterations of training, the weights and biases of the neural network model are continuously adjusted to ensure that the performance metrics (such as accuracy and recall) of the neural network model on the test set reach a satisfactory level.

[0061] In actual operation, the relevant features of the newly generated current monitoring data are input into the trained neural network model to obtain the probability of calling the current monitoring data. .

[0062] Based on a pre-set probability threshold Determine the storage strategy:

[0063] when In this case, the monitoring data or its related data cluster can be cached from the cloud server to the local server in advance to improve the data retrieval speed.

[0064] when At that time, based on the data value score of the current monitoring data calculated above, a decision is made on whether to store the monitoring data to the local server, thereby realizing intelligent decision-making for the storage and retrieval of monitoring data.

[0065] Figure 2 This is a schematic diagram of the structure of a diesel vehicle monitoring data management device provided in an exemplary embodiment of this application. Figure 2As shown, the diesel vehicle monitoring data management device 20 includes: a monitoring data acquisition module 21, used to acquire current monitoring data of the target diesel vehicle; wherein, the current monitoring data includes multiple feature identifiers; a similarity calculation module 22, used to calculate the similarity between the current monitoring data and historical monitoring data based on the feature identifiers; a similar data determination module 23, used to use historical monitoring data with a similarity greater than a preset similarity threshold as similar monitoring data of the current monitoring data; a call frequency calculation module 24, used to calculate the comprehensive call frequency of the current monitoring data based on the current monitoring data and similar monitoring data; a feature weight calculation module 25, used to calculate the feature weight of each feature identifier based on the call frequency of each feature identifier; a value score calculation module 26, used to calculate the data value score of the current monitoring data based on the feature weights of all feature identifiers and the comprehensive call frequency; and a storage strategy determination module 27, used to determine the storage strategy of the current monitoring data based on the data value score of the current monitoring data.

[0066] This application provides a diesel vehicle monitoring data management device, which acquires current monitoring data of a target diesel vehicle through a monitoring data acquisition module 21. The current monitoring data includes multiple feature identifiers. A similarity calculation module 22 calculates the similarity between the current monitoring data and historical monitoring data based on the feature identifiers. A similarity data determination module 23 uses historical monitoring data with a similarity greater than a preset similarity threshold as similar monitoring data for the current monitoring data. A call frequency calculation module 24 calculates the comprehensive call frequency of the current monitoring data based on the current monitoring data and similar monitoring data. A feature weight calculation module 25 calculates the feature weight of each feature identifier based on its call frequency. A value scoring module 26 calculates the current monitoring data based on the feature weights of all feature identifiers and the comprehensive call frequency. Based on the data value score of the current monitoring data, the storage strategy determination module 27 determines the storage strategy for the current monitoring data; it identifies similar monitoring data in historical monitoring data based on the feature identifiers of the monitoring data, calculates the comprehensive call frequency by combining the similar monitoring data and the current monitoring data, so as to more accurately determine the call frequency of the same type of monitoring data, and determines the weight based on the call frequency of each feature identifier, and calculates the data value score by combining the weight and the comprehensive call frequency, thereby determining the storage strategy for the current monitoring data. This approach can fully consider the relevance and importance of the monitoring data, as well as the call frequency of the feature identifiers, to improve the accuracy of the data value score, thus providing a more suitable strategy for the storage of monitoring data, taking into account both the data storage needs and the call needs.

[0067] In one embodiment, the similarity calculation module 22 can be further configured to: calculate the cosine similarity between the feature identifier of the current monitoring data and the corresponding feature identifier of the historical monitoring data to obtain the similarity.

[0068] In one embodiment, the call frequency calculation module 24 can be further configured to: calculate the impact value of similar monitoring data on the current monitoring data; and calculate the comprehensive call frequency based on the impact value and the call frequency of the current monitoring data.

[0069] In one embodiment, the call frequency calculation module 24 can be further configured to: calculate the impact value of similar monitoring data on the current monitoring data based on the call frequency of similar monitoring data and the similarity between the current monitoring data and similar monitoring data.

[0070] In one embodiment, the feature weight calculation module 25 can be further configured to: fit a linear equation between the call frequency of the feature identifier and the time window based on the call frequency of the feature identifier in multiple time windows; and calculate the feature weight of the feature identifier based on the linear equation.

[0071] In one embodiment, the storage strategy determination module 27 can be further configured to: if the data value score is greater than or equal to a first preset value, store the current monitoring data on a local server; if the data value score is less than the first preset value but greater than a second preset value, store the analysis and processing results of the current monitoring data on a local server; wherein the first preset value is greater than the second preset value; if the data value score is greater than or equal to the second preset value, store the current monitoring data on a cloud server.

[0072] In one embodiment, the diesel vehicle monitoring data management device 20 can be further configured to: input relevant information of the current monitoring data into a neural network model to obtain the calling probability of the current monitoring data; and determine the storage strategy of the current monitoring data based on the calling probability.

[0073] Below, for reference Figure 3 This application describes an electronic device according to embodiments thereof. The electronic device may be either or both of a first device and a second device, or a standalone device independent of them, which may communicate with the first device and the second device to receive acquired input signals from them.

[0074] Figure 3 A block diagram of an electronic device according to an embodiment of this application is illustrated.

[0075] like Figure 3 As shown, the electronic device 10 includes one or more processors 11 and memory 12.

[0076] The processor 11 may be a central processing unit (CPU) or other form of processing unit with data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 10 to perform desired functions.

[0077] The memory 12 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 11 may execute the program instructions to implement the methods of the various embodiments of this application described above and / or other desired functions. Various contents such as input signals, signal components, and noise components may also be stored in the computer-readable storage medium.

[0078] In one example, the electronic device 10 may also include an input device 13 and an output device 14, which are interconnected via a bus system and / or other forms of connection mechanism (not shown).

[0079] When the electronic device is a standalone device, the input device 13 can be a communication network connector for receiving the collected input signals from the first device and the second device.

[0080] In addition, the input device 13 may also include, for example, a keyboard, a mouse, etc.

[0081] The output device 14 can output various information to the outside, including determined distance information, direction information, etc. The output device 14 may include, for example, a display, a speaker, a printer, and a communication network and its connected remote output devices, etc.

[0082] Of course, for the sake of simplicity, Figure 3 Only some of the components of the electronic device 10 relevant to this application are shown in this illustration; components such as buses, input / output interfaces, etc., are omitted. In addition, the electronic device 10 may include any other suitable components depending on the specific application.

[0083] In addition to the methods and apparatus described above, embodiments of this application may also be computer program products, which include computer program instructions that, when executed by a processor, cause the processor to perform the steps in the methods according to various embodiments of this application described in the "Exemplary Methods" section above.

[0084] The computer program product can be written in any combination of one or more programming languages ​​to perform the operations of the embodiments of this application. The programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0085] Furthermore, embodiments of this application may also be computer-readable storage media storing computer program instructions thereon, which, when executed by a processor, cause the processor to perform the steps in the methods according to various embodiments of this application described in the "Exemplary Methods" section above.

[0086] The computer-readable storage medium may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof.

[0087] The basic principles of this application have been described above with reference to specific embodiments. However, it should be noted that the advantages, benefits, and effects mentioned in this application are merely examples and not limitations, and should not be considered as essential features of each embodiment of this application. Furthermore, the specific details disclosed above are for illustrative and facilitative purposes only, and are not limitations. These details do not limit the application to the necessity of employing the aforementioned specific details for implementation.

[0088] The block diagrams of devices, apparatuses, devices, and systems involved in this application are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, devices, and systems can be connected, arranged, and configured in any manner. Words such as “comprising,” “including,” “having,” etc., are open-ended terms meaning “including but not limited to,” and are used interchangeably with them. The terms “or” and “and” as used herein refer to the terms “and / or,” and are used interchangeably with them unless the context clearly indicates otherwise. The term “such as” as used herein refers to the phrase “such as but not limited to,” and is used interchangeably with it.

[0089] It should also be noted that in the apparatus, equipment, and methods of this application, the components or steps can be disassembled and / or recombined. These disassemblies and / or recombinations should be considered as equivalent solutions of this application.

[0090] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use this application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of this application. Therefore, this application is not intended to be limited to the aspects shown herein, but rather to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0091] The above description has been given for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of this application to the forms disclosed herein. Although numerous exemplary aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations thereof.

Claims

1. A method for managing diesel vehicle monitoring data, characterized in that, include: Acquire current monitoring data of the target diesel vehicle; wherein, the current monitoring data includes multiple feature identifiers; Based on the feature identifier, the similarity between the current monitoring data and the historical monitoring data is calculated; Historical monitoring data with a similarity greater than a preset similarity threshold are used as similar monitoring data for the current monitoring data; Based on the current monitoring data and the similar monitoring data, calculate the comprehensive call frequency of the current monitoring data; Calculate the feature weight of each feature identifier based on the frequency of its call; Based on the feature weights of all the aforementioned feature identifiers and the comprehensive call frequency, the data value score of the current monitoring data is calculated; Based on the data value score of the current monitoring data, a storage strategy for the current monitoring data is determined.

2. The diesel vehicle monitoring data management method according to claim 1, characterized in that, The step of calculating the similarity between the current monitoring data and the historical monitoring data based on the feature identifier includes: The cosine similarity between the feature identifier of the current monitoring data and the corresponding feature identifier of the historical monitoring data is calculated to obtain the similarity.

3. The diesel vehicle monitoring data management method according to claim 1, characterized in that, The calculation of the comprehensive call frequency of the current monitoring data based on the current monitoring data and the similar monitoring data includes: Calculate the impact value of the similar monitoring data on the current monitoring data; The comprehensive call frequency is calculated based on the impact value and the call frequency of the current monitoring data.

4. The diesel vehicle monitoring data management method according to claim 3, characterized in that, The calculation of the impact value of the similar monitoring data on the current monitoring data includes: Based on the frequency of access to the similar monitoring data and the similarity between the current monitoring data and the similar monitoring data, the impact value of the similar monitoring data on the current monitoring data is calculated.

5. The diesel vehicle monitoring data management method according to claim 1, characterized in that, The calculation of the feature weight of each feature identifier based on the call frequency of each feature identifier includes: Based on the call frequency of the feature identifier within multiple time windows, a linear equation between the call frequency of the feature identifier and the time window is fitted. Based on the linear equation, the feature weights of the feature identifiers are calculated.

6. The diesel vehicle monitoring data management method according to claim 1, characterized in that, The process of determining the storage strategy for the current monitoring data based on the data value score includes: If the data value score is greater than or equal to the first preset value, the currently monitored data will be stored on the local server. If the data value score is less than the first preset value but greater than the second preset value, the analysis and processing result of the current monitoring data is stored on the local server; wherein the first preset value is greater than the second preset value. If the data value score is greater than or equal to the second preset value, the current monitoring data will be stored on the cloud server.

7. The diesel vehicle monitoring data management method according to claim 1, characterized in that, The diesel vehicle monitoring data management method also includes: The relevant information of the current monitoring data is input into the neural network model to obtain the probability of calling the current monitoring data; Based on the call probability, the storage strategy for the current monitoring data is determined.

8. A diesel vehicle monitoring data management device, characterized in that, include: The monitoring data acquisition module is used to acquire the current monitoring data of the target diesel vehicle; wherein, the current monitoring data includes multiple feature identifiers; The similarity calculation module is used to calculate the similarity between the current monitoring data and the historical monitoring data based on the feature identifier; A similar data determination module is used to identify historical monitoring data with a similarity greater than a preset similarity threshold as similar monitoring data to the current monitoring data. The call frequency calculation module is used to calculate the comprehensive call frequency of the current monitoring data based on the current monitoring data and the similar monitoring data; The feature weight calculation module is used to calculate the feature weight of each feature identifier based on the frequency of its call. The value scoring calculation module is used to calculate the data value score of the current monitoring data based on the feature weights of all the feature identifiers and the comprehensive call frequency; The storage strategy determination module is used to determine the storage strategy for the current monitoring data based on the data value score of the current monitoring data.

9. A computer-readable storage medium, characterized in that, The storage medium stores a computer program for performing the method described in any one of claims 1-7.

10. An electronic device, characterized in that, include: processor; Memory used to store the processor's executable instructions; The processor is used to execute the method described in any one of claims 1-7.

Images