A method, system, device and storage medium for automatic coding of data center equipment monitoring

Abstract

The present invention discloses a method for automatic encoding of data center equipment monitoring, comprising: collecting and acquiring historical monitoring data and real-time monitoring data of each monitoring device through data center equipment; performing data preprocessing on the historical monitoring data and the real-time monitoring data to obtain a training sample set; extracting a feature set based on the training sample set; constructing and training a machine learning model based on the feature set; and automatically encoding input real-time monitoring video data using the trained machine learning model. The method for automatic encoding of data center equipment monitoring of the present invention can effectively enhance the overall effect of automatic encoding of video data using the trained machine learning model by combining real-time monitoring data and historical monitoring data and performing various appropriate data preprocessing on the data.

Description

Technical Field

[0001] The present invention relates to the field of monitoring coding technology, and in particular to a method, system, device and storage medium for automatic coding of data center equipment monitoring. Background Art

[0002] In the video surveillance system of data center equipment, using appropriate encoding methods for the collected videos is beneficial to saving hard disk storage space and extending recording time while ensuring monitoring quality.

[0003] In existing technologies, surveillance video encoding often relies on manual selection and modification, which is time-consuming and labor-intensive. Some methods that use training models for automatic encoding often rely on large amounts of historical video data as training samples. However, this approach can also lead to poor overall automatic encoding results due to significant differences between the data and the real-time surveillance video. Summary of the Invention

[0004] The present invention proposes a method, system, device and storage medium for automatic coding of data center equipment monitoring, which can realize automatic coding of monitoring videos and effectively improve the comprehensive effect after automatic coding.

[0005] In order to achieve the above object, the present invention provides the following technical solutions:

[0006] A data center equipment monitoring automatic coding method, comprising:

[0007] Collect and obtain historical and real-time monitoring data from each monitoring device through data center equipment;

[0008] Performing data preprocessing on the historical monitoring data and the real-time monitoring data to obtain a training sample set;

[0009] Extracting a feature set based on the training sample set;

[0010] Building and training a machine learning model based on the feature set;

[0011] The input real-time monitoring video data is automatically encoded through the trained machine learning model.

[0012] Optionally, priorities are set for the historical monitoring data and the real-time monitoring data according to information of each monitoring device.

[0013] Optionally, the data preprocessing includes:

[0014] The historical monitoring data and the real-time monitoring data are grouped according to preset condition rules.

[0015] Optionally, the preset condition rules include time rules and location rules.

[0016] Optionally, the data preprocessing includes:

[0017] Abnormal data in the historical monitoring data and the real-time monitoring data are eliminated.

[0018] Optionally, the extracting a feature set based on the training sample set:

[0019] A feature matching rule based on a clustering algorithm is established to perform correlation clustering grouping on the training sample set.

[0020] Optionally, after the input real-time monitoring image data is automatically encoded by the trained machine learning model, the automatically encoded information data is collected and obtained and visualized.

[0021] Optionally, a data center equipment monitoring automatic coding system includes:

[0022] The data acquisition module is used to collect and obtain historical monitoring data and real-time monitoring data of each monitoring device through data center equipment;

[0023] Data preprocessing module, used to preprocess the historical monitoring data and the real-time monitoring data to obtain a training sample set

[0024] A feature extraction module, configured to extract a feature set based on the training sample set;

[0025] Constructing a training model module for constructing and training a machine learning model based on the feature set;

[0026] The automatic encoding module automatically encodes the input real-time monitoring image data through the trained machine learning model.

[0027] Optionally, an electronic device is provided, characterized in that the electronic device includes:

[0028] at least one processor; and,

[0029] a memory communicatively coupled to the at least one processor;

[0030] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the above-mentioned method for automatic coding of data center equipment monitoring.

[0031] Optionally, a computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, the method for automatic coding of data center equipment monitoring described above is implemented.

[0032] Compared with the prior art, the present invention has the following beneficial effects:

[0033] By simultaneously collecting and obtaining the real-time monitoring data and historical monitoring data of each monitor as the basis of the training sample set, and performing various data preprocessing on the training sample set, it is convenient to extract the feature values ​​of the training sample set, and then train and construct the automatic encoding machine learning model through the extracted feature set, which can effectively enhance the comprehensive effect of the automatic encoding model after automatic encoding of the real-time monitoring video data. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 A flowchart of a method for automatic coding of data center equipment monitoring provided by the present invention.

[0035] Figure 2 This is a module diagram of a data center equipment monitoring automatic coding system provided by the present invention.

[0036] Figure 3 A schematic diagram of the internal structure of an electronic device for automatic coding of data center equipment monitoring provided by the present invention. DETAILED DESCRIPTION

[0037] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0038] See also Figure 1 The flowchart of the method for automatic coding of data center equipment monitoring provided by the present invention includes the following steps:

[0039] S1. Collect and obtain historical monitoring data and real-time monitoring data of each monitoring device through data center equipment;

[0040] Among them, the data center equipment is connected to multiple monitoring devices for data at the same time, so the historical monitoring data and real-time monitoring data of each monitoring device can be collected and obtained at the same time through the data center equipment.

[0041] Specifically, the historical monitoring data and real-time monitoring data collected from each monitoring device include encoding format, monitoring video resolution, specific image video storage size, etc., which facilitates the subsequent judgment of whether the current monitoring video encoding method is appropriate based on the relationship between monitoring video quality and monitoring video storage size.

[0042] By collecting a large amount of historical monitoring data, we can prevent the one-sided loss of the trained automatic encoding model. By collecting real-time monitoring data, we can obtain the latest data that is more in line with the current reality in real time, which is conducive to updating, optimizing or adjusting the automatic encoding model based on the changing real-time monitoring data.

[0043] S2. Preprocess the historical monitoring data and real-time monitoring data to obtain a training sample set;

[0044] In an optional embodiment, data preprocessing includes:

[0045] Prioritize historical and real-time monitoring data based on information from each monitoring device.

[0046] Among them, the information of each monitoring device may include information such as the monitoring location. For example, the historical monitoring data and real-time monitoring data in each monitoring device can be prioritized according to the importance of each monitoring device, which is conducive to the subsequent training of the machine learning model to set the weights of different parameters according to the priority.

[0047] In an optional embodiment, data preprocessing further includes:

[0048] Group historical monitoring data and real-time monitoring data according to preset condition rules;

[0049] Specifically, the preset condition rules may include time rules and location rules, such as grouping historical monitoring data and real-time monitoring data at similar monitoring locations into one group, or grouping historical monitoring data and real-time monitoring data at similar monitoring time periods into one group.

[0050] In an optional embodiment, data preprocessing further includes:

[0051] Eliminate abnormal data from historical monitoring data and real-time monitoring data.

[0052] Among them, abnormal data in historical monitoring data and real-time monitoring data include abnormal monitoring image data such as snow-like monitoring images when the signal is lost or incomplete and poor-quality image frames of the monitoring images.

[0053] Afterwards, data preprocessing may further include clustering the data using a K-means clustering algorithm and correcting the data using the first relationship to obtain more accurate data.

[0054] S3, extracting a feature set based on the training sample set;

[0055] In an optional embodiment, the process of extracting a feature set based on a training sample set includes:

[0056] Establish feature matching rules based on clustering algorithm and perform correlation clustering grouping on the training sample set.

[0057] S4. Build and train a machine learning model based on the feature set;

[0058] Among them, the machine learning model can be an existing machine learning model such as Lightgbm, Catboost, XGBoost, Random Forest, etc.

[0059] Specifically, feature sets are used as input to build and train machine learning models. Furthermore, various optimization techniques can be used to tune hyperparameters, which can further improve the prediction accuracy of each model.

[0060] S5. Automatically encode the input real-time monitoring video data through the trained machine learning model.

[0061] Specifically, after the machine learning model is trained, the machine learning model is used to automatically encode the input real-time monitoring video data.

[0062] Furthermore, after automatic encoding, the automatic encoding information data is collected and obtained and visualized. By visually displaying the automatic encoding information data, the comprehensive results after automatic encoding can be presented more intuitively and clearly, which facilitates the adjustment of relevant parameters when training the machine learning model based on the comprehensive results to optimize the machine learning model, thereby helping to further enhance the comprehensive effect of automatic encoding.

[0063] Among them, the comprehensive effect after automatic encoding of the surveillance video refers to ensuring the video quality of the surveillance video after automatic encoding, including picture quality, resolution, brightness, etc., so that the human eye can also observe it easily, while saving the hard disk storage space of the surveillance video as much as possible, thereby also facilitating the comprehensive effect of extending the surveillance recording time.

[0064] To sum up, the trained machine learning model in the technical solution of the present application can accurately and appropriately automatically encode the input real-time monitoring video data, and can save the storage space of the monitoring video as much as possible while ensuring the video quality of the monitoring video after automatic encoding, that is, it has a good comprehensive effect of automatic encoding, and after automatic encoding, the relevant information after automatic encoding is visualized, which is convenient for adjusting the machine learning model parameters for optimization. At the same time, by comprehensively adopting the real-time operation data and historical operation data of the vehicle and battery, the comprehensive effect of automatic encoding of the monitoring video can also be enhanced.

[0065] like Figure 2 FIG. 1 is a functional module diagram of a data center equipment monitoring automatic coding system according to the present invention.

[0066] The data center equipment monitoring and automatic encoding system 100 of the present invention can be installed in an electronic device. Depending on the functionality implemented, the data center equipment monitoring and automatic encoding system can include a data acquisition module 101, a data preprocessing module 102, a feature extraction module 103, a training model construction module 104, and an automatic encoding module 105. The modules described in this solution, also referred to as units, are a series of computer program segments that can be executed by an electronic device processor and perform a fixed function, and are stored in the electronic device's memory.

[0067] In detail, each module in the data center equipment monitoring automatic coding system 100 according to the embodiment of the present invention adopts the same Figure 1 The method for automatic coding of data center equipment monitoring described in the preceding text is the same technical means and can produce the same technical effects, so I will not go into details here.

[0068] like Figure 3 FIG. 1 is a schematic diagram of the structure of an electronic device for realizing automatic coding of data center equipment monitoring according to the present invention.

[0069] The electronic device may include a processor 10, a memory 11, a communication bus 12 and a communication interface 13, and may also include a computer program stored in the memory 11 and executable on the processor 10, such as an evaluation program for automatic coding of data center equipment monitoring.

[0070] The data center equipment monitoring automatic coding program stored in the memory 11 of the electronic device is a combination of multiple computer programs. When running in the processor 10, it can achieve:

[0071] Collect and obtain historical and real-time monitoring data from each monitoring device through data center equipment;

[0072] Perform data preprocessing on historical monitoring data and real-time monitoring data to obtain a training sample set;

[0073] Extract feature sets based on training sample sets;

[0074] Build and train machine learning models based on feature sets;

[0075] The input real-time monitoring video data is automatically encoded through the trained machine learning model.

[0076] Specifically, the specific implementation method of the processor 10 for the above computer program can refer to Figure 1 The description of the relevant steps in the corresponding embodiments will not be repeated here.

[0077] An embodiment of the present invention may further provide a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program. When the computer program is executed by a processor of an electronic device, the computer program may implement:

[0078] Collect and obtain historical and real-time monitoring data from each monitoring device through data center equipment;

[0079] Perform data preprocessing on historical monitoring data and real-time monitoring data to obtain a training sample set;

[0080] Extract feature sets based on training sample sets;

[0081] Build and train machine learning models based on feature sets;

[0082] The input real-time monitoring video data is automatically encoded through the trained machine learning model.

[0083] Furthermore, the computer-usable storage medium may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function, etc.; the data storage area may store data created according to the use of the blockchain node, etc.

[0084] The above description is only a preferred specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any technician familiar with the technical field, within the technical scope disclosed by the present invention, who makes equivalent replacements or changes based on the technical solution and inventive concept of the present invention, should be covered by the scope of protection of the present invention.

Claims

1. A method for automatic coding of data center equipment monitoring, characterized in that: include: Collect and obtain historical and real-time monitoring data from each monitoring device through data center equipment; Performing data preprocessing on the historical monitoring data and the real-time monitoring data to obtain a training sample set; Extracting a feature set based on the training sample set; Building and training a machine learning model based on the feature set; The input real-time monitoring video data is automatically encoded through the trained machine learning model.

2. The method according to claim 1, wherein: The data preprocessing includes: Priorities are set for the historical monitoring data and the real-time monitoring data according to information of each monitoring device.

3. The method according to claim 1, wherein: The data preprocessing includes: The historical monitoring data and the real-time monitoring data are grouped according to preset condition rules.

4. The method according to claim 3, wherein: The preset condition rules include time rules and location rules.

5. The method according to claim 1, wherein: The data preprocessing includes: Abnormal data in the historical monitoring data and the real-time monitoring data are eliminated.

6. The method according to claim 1, wherein: The feature set is extracted based on the training sample set: A feature matching rule based on a clustering algorithm is established to perform correlation clustering grouping on the training sample set.

7. The method according to claim 1, wherein: After the input real-time monitoring image data is automatically encoded by the trained machine learning model, the automatically encoded information data is collected and obtained and visualized.

8. A data center equipment monitoring automatic coding system, characterized in that: include: The data acquisition module is used to collect and obtain historical monitoring data and real-time monitoring data of each monitoring device through data center equipment; Data preprocessing module, used to preprocess the historical monitoring data and the real-time monitoring data to obtain a training sample set A feature extraction module, configured to extract a feature set based on the training sample set; Constructing a training model module for constructing and training a machine learning model based on the feature set; The automatic encoding module automatically encodes the input real-time monitoring image data through the trained machine learning model.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and, a memory communicatively coupled to the at least one processor; The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to perform the method for automatic coding of data center equipment monitoring according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method for automatic coding of monitoring data center equipment according to any one of claims 1 to 7 is implemented.

Images