Data monitoring methods, devices, electronic equipment and storage media

By using a spin algorithm to update the version number to detect anomalies in park data, the problem of relying on manual calculation for existing park data monitoring has been solved, enabling efficient and accurate data monitoring and emergency response.

CN117668723BActive Publication Date: 2026-11-17GREE ELECTRIC APPLIANCE INC OF ZHUHAI +1
View PDF 1 Cites 0 Cited by

Patent Information

Application Number
CN202311613407.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-11-28
Publication Date
2026-11-17
Estimated Expiration
2043-11-28

AI Technical Summary

Technical Problem

Existing methods for monitoring data in industrial parks rely on manual calculations, resulting in high labor costs, low monitoring efficiency, and weak emergency response capabilities.

Method used

By introducing a spin algorithm to monitor real-time data, updating the version number to determine the probability of abnormal data triggering, and generating alarm information, automated data monitoring and analysis are achieved.

Benefits of technology

It improved data analysis efficiency and emergency response capabilities, reduced labor costs, ensured the accuracy and real-time nature of data analysis, and reduced false alarm rates.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN117668723B_ABST
    Figure CN117668723B_ABST
Patent Text Reader

Abstract

This application provides a data monitoring method, apparatus, electronic device, and storage medium. The method includes: acquiring first data information from the same data collection point, wherein the first data information includes data value information and a first data version parameter; comparing data fluctuations based on the data value information and pre-set reference value information to obtain a first data fluctuation comparison result; updating the first data version parameter when the first data fluctuation comparison result indicates that the data value information differs from the reference value information to obtain a second data version parameter; and performing an anomaly alert operation based on the number of first data information items with the second data version parameter. Because the spin algorithm can determine the probability of data anomaly triggering through the version parameter, it improves the data monitoring effect of the park and enhances the park's emergency response capability.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a data monitoring method, apparatus, electronic device, and storage medium. Background Technology

[0002] A smart park is a vast system integrating software and hardware. It achieves real-time monitoring by collecting and analyzing the massive amounts of data generated within the park every moment. However, existing park data monitoring methods primarily focus on real-time data acquisition and display. Security managers must perform complex and tedious manual calculations based on data collected from various points within the park to summarize data fluctuations, identify anomalies at corresponding data collection points, and initiate emergency responses. This data monitoring method is labor-intensive, inefficient, and weakens the park's emergency response capabilities. Summary of the Invention

[0003] This application provides a data monitoring method, apparatus, electronic device, and readable storage medium. By monitoring the number of times real-time data exceeds a preset threshold and updating the data version number, the probability of abnormal data triggering is determined. When the abnormal probability corresponding to the version number exceeds a pre-set threshold, the data is judged to be abnormal and corresponding alarm information is generated, thus realizing data monitoring and analysis. This solves the problems of existing park data monitoring and analysis relying on security management personnel, resulting in high labor costs, low monitoring efficiency, and weak emergency response capabilities.

[0004] Firstly, this application provides a data monitoring method, which includes:

[0005] Acquire first data information from the same data collection point, wherein the first data information includes data value information and a first data version parameter;

[0006] Based on the data value information and the pre-set reference value information, a data fluctuation comparison is performed to obtain the first data fluctuation comparison result;

[0007] When the first data fluctuation comparison result shows that the data value information is different from the reference value information, the first data version parameter is updated to obtain the second data version parameter;

[0008] An error message is displayed based on the number of first data information entries that have a second data version parameter.

[0009] Optionally, the data monitoring method provided in this application also includes:

[0010] The first data version parameter corresponding to the second data information is determined based on the second data version parameter corresponding to the first data information.

[0011] Based on the data value information corresponding to the second data information and the reference value information, a data fluctuation comparison is performed using a spin algorithm to obtain the second data fluctuation comparison result.

[0012] When the second data fluctuation comparison result is that the data value information corresponding to the second data information is different from the reference value information, the first data version parameter corresponding to the second data information is updated to obtain the second data version parameter corresponding to the second data information.

[0013] Read the second data version parameter of the second data information and perform an error message operation.

[0014] Optionally, the data monitoring method provided in this application also includes:

[0015] The first abnormal data trigger probability of the first data information is obtained based on the number of first data information with a second data version parameter and the number of first data information.

[0016] When the probability of triggering the first abnormal data is greater than the preset first trigger probability threshold, the first data information is determined to be abnormal, and a first data monitoring result is generated.

[0017] Optionally, the data monitoring method provided in this application also includes:

[0018] When the probability of triggering the first abnormal data corresponding to the pedestrian data information is greater than the threshold of the pedestrian data triggering probability, the pedestrian data information is determined to be abnormal, and the first data monitoring result corresponding to the pedestrian data information is generated.

[0019] Optionally, the data monitoring method provided in this application also includes:

[0020] When the probability of triggering the first abnormal data corresponding to the vehicle traffic data information is greater than the vehicle traffic data triggering probability threshold, the vehicle traffic data information is determined to be abnormal, and the first data monitoring result corresponding to the vehicle traffic data information is generated.

[0021] Optionally, the data monitoring method provided in this application also includes:

[0022] When the probability of triggering the first abnormal data corresponding to the device data information is greater than the device data triggering probability threshold, the device data information is determined to be abnormal, and the first data monitoring result corresponding to the device data information is generated.

[0023] Optionally, the data monitoring method provided in this application also includes:

[0024] Based on equipment data information, the cause of equipment failure is determined by a pre-trained equipment failure analysis model, and the result of the equipment failure cause determination is obtained.

[0025] The results of the equipment failure cause determination will be output and displayed.

[0026] Secondly, this application also provides a data monitoring device, comprising:

[0027] The data acquisition module is used to acquire first data information from the same data collection point, wherein the first data information includes data value information and first data version parameters;

[0028] The first data value comparison module is used to compare data fluctuations with the data value information and the preset reference value information to obtain the first data fluctuation comparison result.

[0029] The first version update module is used to update the first data version parameter to obtain the second data version parameter when the first data fluctuation comparison result is that the data value information is different from the reference value information.

[0030] The first error message module is used to perform error message operation based on the number of first data information items with second data version parameters.

[0031] Thirdly, this application also provides an electronic device including a processor and a memory, the memory storing a program or instructions executable on the processor, the program or instructions, when executed by the processor, implementing the steps of the data monitoring method as described in the first aspect.

[0032] Fourthly, embodiments of this application provide a readable storage medium on which a program or instructions are stored, which, when executed by a processor, implement the steps of the data monitoring method as described in the first aspect.

[0033] Compared to the inefficient and complex data processing methods where safety management personnel manually perform calculations to summarize data fluctuations at a given data collection point, the technical solution provided in this application only requires the number of first data entries corresponding to the version parameter to determine the overall performance of data fluctuations at the same data collection point and execute corresponding anomaly alerts. This allows for rapid processing of large amounts of data, improving data analysis efficiency while ensuring accuracy and reliability, and enhancing data emergency response capabilities. Furthermore, it reduces the workload of safety management personnel, avoids interference from minor data fluctuations in data monitoring, further improves the real-time nature of data monitoring, and reduces the risk of anomalies in the park.

[0034] The above description is merely an overview of the technical solution provided in this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, specific embodiments of this application are described below. Attached Figure Description

[0035] One or more embodiments are illustrated by way of example with reference numerals in the accompanying drawings. These illustrations do not constitute a limitation on the embodiments. Elements with the same reference numerals in the drawings are denoted as similar elements. Unless otherwise stated, the figures in the drawings are not to be limited by scale.

[0036] Figure 1 This is one of the schematic diagrams of the data monitoring method provided in the embodiments of this application;

[0037] Figure 2 This is a second schematic diagram of the data monitoring method provided in the embodiments of this application;

[0038] Figure 3 This is the third schematic diagram of the data monitoring method provided in the embodiments of this application;

[0039] Figure 4 This is the fourth schematic diagram of the data monitoring method provided in the embodiments of this application;

[0040] Figure 5 This is the fifth schematic diagram of the data monitoring method provided in the embodiments of this application;

[0041] Figure 6 This is the sixth schematic diagram of the data monitoring method provided in the embodiments of this application;

[0042] Figure 7 This is the seventh schematic diagram of the data monitoring method provided in the embodiments of this application;

[0043] Figure 8 This application provides an example of a park data monitoring process;

[0044] Figure 9 This is a schematic diagram of the data monitoring device provided in an embodiment of this application;

[0045] Figure 10 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0046] Exemplary embodiments of the present application will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present application are shown in the drawings, it should be understood that the present application may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this application will be thorough and complete, and will fully convey the scope of the present application to those skilled in the art.

[0047] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such use of data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited; for example, a first object can be one or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0048] A smart park is a vast system integrating software and hardware. It achieves real-time monitoring by collecting and analyzing the massive amounts of data generated within the park every moment. However, existing park data monitoring methods primarily focus on real-time data acquisition and display, with analysis often handled by security management personnel. These personnel perform complex and tedious manual calculations based on data collected from various data collection points within the park to summarize data fluctuations, then determine if any anomalies exist at the data collection points, and initiate emergency responses upon detection of anomalies. This data monitoring method is labor-intensive, inefficient, and weakens the park's emergency response capabilities.

[0049] To address the issue of poor monitoring performance in existing park data monitoring methods, the technical solution provided in this application reduces the pressure on system data storage by dividing and classifying park data for storage. Furthermore, it introduces a spin algorithm to monitor and analyze the collected data, determine whether there are abnormal fluctuations in data increments, and perform data analysis based on the time and source of park data generation. This achieves the purpose of data monitoring, improves the work efficiency of safety management personnel, and enhances the park's emergency response capabilities.

[0050] Specifically, in the technical solution provided in this application, the spin algorithm adds the concept of a version number compared to traditional data monitoring and analysis methods. By monitoring the number of times data exceeds a preset threshold in real-time data, the version number of the data is updated, thereby determining the probability of abnormal data being triggered. The higher the probability of abnormal data being triggered, the greater the danger of the data. When the abnormal probability corresponding to the version number exceeds the preset threshold, the data is judged to be abnormal and corresponding alarm information is generated, thereby realizing the monitoring and analysis of park data.

[0051] Because the spin algorithm used in this application has low computational complexity, it can quickly process large amounts of data, improving the efficiency of park data analysis while ensuring its accuracy and reliability. Furthermore, the spin algorithm can compare real-time collected park data with historical data or pre-set reference values, promptly issuing alarms when abnormal data is detected, further improving the real-time performance of data monitoring and reducing the risk of park anomalies. Moreover, since the data analysis compares real-time data from the same device with historical data or pre-set reference values ​​(i.e., preset thresholds), it can more accurately detect abnormal data, thereby reducing the false alarm rate. In addition, the park data monitoring method provided in this application is applicable to various scenarios within the park, monitoring not only abnormal fluctuations in data generated by devices but also pedestrian and vehicular traffic data, demonstrating broad applicability.

[0052] The following description, in conjunction with the accompanying drawings and taking park data collected from the same data collection point as an example, details the data monitoring method, device, electronic equipment, and non-volatile readable storage medium provided in this application through specific embodiments and application scenarios.

[0053] The first embodiment of this application relates to a data monitoring method, such as... Figure 1 As shown, it includes:

[0054] Step 101: Obtain the first data information from the same data collection point, wherein the first data information includes data value information and a first data version parameter;

[0055] Step 102: Based on the data value information and the preset reference value information, perform data fluctuation comparison to obtain the first data fluctuation comparison result;

[0056] Step 103: When the first data fluctuation comparison result shows that the data value information is different from the reference value information, the first data version parameter is updated to obtain the second data version parameter.

[0057] Step 104: Based on the number of first data information items with second data version parameters, perform an error message operation.

[0058] Specifically, in the park data monitoring method provided in this application, all data within the park is first collected through a server and stored in a database. This park data information carries not only park data value information representing the corresponding numerical values, but also a first park data version parameter indicating the corresponding version. It is important to emphasize that the collected park data information can be assigned identity information and version parameters to each piece of data by pre-setting data attributes. For example, identity information can be assigned to each piece of data using an auto-incrementing ID. The detailed data value information of each piece of data can be assigned based on the specific values ​​collected at the data collection points. Furthermore, the version parameter in each piece of data can be assigned a fixed value, such as 0. Alternatively, a fixed value can be assigned to the version parameter of the first piece of data arranged in chronological order, and subsequent pieces of data can be assigned a second version parameter based on the fixed value of the first piece of data. This application does not impose any restrictions on this approach.

[0059] Subsequently, for the park data information from the same data collection point, it is compared with the pre-set reference value information. When the park data value information carried by the current park data information is different from the reference value information, it is determined that the park data has abnormal fluctuations. The first park data version parameter corresponding to the park data is updated to obtain a new second park data version parameter. Then, based on the number of updated second park data version parameters and the number of park data value information, the probability of abnormal data triggering of park data information is calculated. When the calculated probability of abnormal data triggering is greater than the pre-set triggering probability threshold, the park data is determined to be abnormal data, and the corresponding first park data monitoring result is generated.

[0060] The data analysis and version parameter updates in this application can be implemented through, but are not limited to, a spin algorithm. Specifically, the spin algorithm iteratively compares the park data values ​​carried in the collected park data information with pre-set reference values. In each iteration, multiple park data values ​​are compared with the reference values. When the comparison results differ, the version number of the corresponding park data version parameter is updated. After multiple iterations, abnormal data in the collected park data information is determined based on the version number, and the probability of abnormal data triggering is calculated. By using the spin algorithm for data analysis and version updates, the park data monitoring method provided in this application allows for fluctuations in the collected data and allows for the existence of abnormal data at corresponding collection points. When the proportion of abnormal data in all collected park data information is too high, i.e., the probability of abnormal data triggering is greater than a preset threshold, the status of the corresponding collection point is determined to be abnormal, such as equipment malfunction, and the corresponding park data monitoring results are generated and displayed.

[0061] In addition, to ensure the accuracy of the abnormal data trigger probability calculation results, while calculating the abnormal data trigger probability based on the version number and the number of park data information, it is also necessary to consider influencing factors such as the number of cycles. This application does not impose any restrictions.

[0062] The reference value information pre-set in this application can be the initial information collected for the first time after the equipment is installed and fixed, or it can be the historical information manually set at any time in multiple data collections. For example, for multiple sets of data collected from the same data collection point or the same equipment, an intermediate value can be determined manually or through a pre-defined selection rule as reference information. This application does not impose any restrictions on this.

[0063] For example, when the park data monitoring method provided in this application collects device information of a device through a server, it obtains corresponding park data information. This park data information carries the corresponding data value and version number through methods including, but not limited to, data attributes; for example, the version number is set to 0. Subsequently, the data value is compared with a pre-set reference value. If they match, it indicates that the collected park data information has no data fluctuation, and the version number is not updated. If they do not match, it indicates that the data value of the collected park data information fluctuates compared to the pre-set reference value, and the version number is updated using a spin algorithm, for example, adjusting the version number from 0 to 1. Then, based on the new version number and the number of park data values, an abnormal data trigger probability is calculated, where any version number greater than or equal to 1 is judged as abnormal data. For example, for a park data value with a version number of 1, the abnormal data trigger probability is 100%. The abnormal data trigger probability is then compared with a pre-set trigger probability threshold to generate the corresponding first park data monitoring result.

[0064] When the park data monitoring method provided in this application collects the device information of the same data collection point, such as the same device, in real time through the server, it obtains multiple consecutive park data information. At this time, each park data information includes its own corresponding data value and version number. Moreover, the version number of each park data information is updated by a spin algorithm. Then, based on the number of these park data information and the number of updated version numbers, the abnormal data trigger probability is judged against the pre-set trigger probability threshold to generate the corresponding first park data monitoring result.

[0065] Furthermore, when the source of park data is not limited to a single collection point, different labeling information can be used to distinguish them, avoiding confusion between different park data collected by different devices and affecting the accuracy of park data monitoring and analysis.

[0066] The technical solution provided in this application utilizes a spin algorithm with low computational complexity, enabling rapid processing of large amounts of data. This ensures the accuracy and reliability of park data analysis while improving its efficiency. Furthermore, the spin algorithm compares real-time collected park data with historical data or pre-set reference values. When abnormal data is detected, version parameters are updated. If the probability of abnormal data triggering the version parameters exceeds a preset threshold, a park data alarm is generated. This avoids interference from minor data fluctuations in park data monitoring, further improving the real-time performance of data monitoring and reducing the risk of park anomalies.

[0067] Based on the above implementation methods, such as Figure 2 As shown, the data information from the same data collection point consists of multiple data pieces collected in chronological order. In the data monitoring method provided in this application, after step 103, the following steps are also included:

[0068] Step 131: Determine the first data version parameter corresponding to the second data information based on the second data version parameter corresponding to the first data information;

[0069] Step 132: Based on the data value information corresponding to the second data information and the reference value information, perform data fluctuation comparison using a spin algorithm to obtain the second data fluctuation comparison result;

[0070] Step 133: When the second data fluctuation comparison result is that the data value information corresponding to the second data information is different from the reference value information, the first data version parameter corresponding to the second data information is updated to obtain the second data version parameter corresponding to the second data information.

[0071] Step 134: Read the second data version parameter of the second data information and perform an error message operation.

[0072] Specifically, the park data monitoring method provided in this application also offers a different method for updating park data version parameters. Specifically, in the multiple park data pieces collected in real time by this application, the data value in the second park data version parameter of each park data piece is determined based on the number of park data pieces preceding it in chronological order that have updated their park data version parameters. For example, if 10 park data pieces are collected in chronological order, and the first park data piece does not exceed a preset value, its corresponding park data version parameter is set to 0. The second park data piece exceeds the preset value, and its corresponding park data version parameter is set to 1. The third park data piece also exceeds the preset value, and its corresponding park data version parameter is increased by 1 based on the version parameter of the second park data piece, resulting in 2, which is used as the park data version parameter for the third park data piece. That is, the park data version parameter in each park data piece is updated or unchanged based on the judgment result, resulting in a new park data version parameter.

[0073] When the version parameters of each park data are increased or remain unchanged based on the previous data version parameters, the second abnormal data trigger probability is calculated based on the data value corresponding to the second park data version parameter of the last park data and the number of park data value information. When the calculated abnormal data trigger probability is greater than the preset trigger probability threshold, the group of park data is judged as abnormal data, and the corresponding second park data monitoring result is generated.

[0074] It should be emphasized that the action of providing an anomaly prompt based on the second data information mentioned in this application applies to scenarios where only the first and second data information arranged in sequence are collected. When more than two data information are collected, the second data version parameter of the last second data information in the time sequence is read, and an anomaly prompt action is performed.

[0075] For example, when the park data monitoring method provided in this application collects device information of a device in real time through a server, it obtains multiple consecutive park data information. Each park data information includes its own data value and version number, and the version number of each park data information is updated based on the previous version number using a spin algorithm. Therefore, by obtaining the version number of the last park data information, the number of anomalies in all the real-time collected park data can be determined. The probability of anomaly triggering for the device can be calculated based on the number of anomalies and the total number of collected data, thereby generating the corresponding park data monitoring result.

[0076] Based on the above implementation, the technical solution provided in this application can also accumulate version numbers by updating version parameters through a spin algorithm. It is not necessary to count the total number of abnormal data corresponding to the version parameters. It is only necessary to obtain the total number of abnormal data in all collected park data information based on the last version number of multiple data collected in chronological order, and quickly calculate the corresponding abnormal data trigger probability, which further improves the efficiency of park data monitoring and analysis.

[0077] Based on the above implementation method, the data fluctuation comparison result includes the data size comparison result. In the data monitoring method provided in this application, step 102 includes:

[0078] Step 121: Compare the data value information with the reference value information using the spin algorithm to obtain the data size comparison result.

[0079] Specifically, in the data monitoring method provided in this application, comparing data fluctuations using the spin algorithm can be done by judging the magnitude of the fluctuations based on the data size. That is, when the magnitude of the data value information and the reference value information are different, it can be determined that the first data information corresponding to the data value information is different from the reference value information, and the spin algorithm is used to update it. When acquiring multiple data information from the same data acquisition point in real time, this application can also compare the data size with the reference data information by the average value of the multiple data information arranged in chronological order and the difference between each data information, to obtain the data size comparison result.

[0080] In addition, data fluctuations can also be judged by variance, standard deviation, etc., and corresponding version parameters can be updated accordingly. This application does not impose any restrictions.

[0081] Based on the above implementation methods, the technical solution provided by this application can quickly determine the fluctuation of the collected data information by comparing the data size, which improves the efficiency of data fluctuation judgment and further ensures the data emergency response capability of this application.

[0082] Based on the above implementation methods, such as Figure 3 As shown, in the data monitoring method provided in this application, step 104 includes:

[0083] Step 141: Obtain the first abnormal data trigger probability of the first data information based on the number of first data information with the second data version parameter and the number of first data information.

[0084] Step 142: When the probability of triggering the first abnormal data is greater than the preset first trigger probability threshold, the first data information is determined to be abnormal, and a first data monitoring result is generated.

[0085] Specifically, in the data monitoring method provided in this application, the probability of abnormal data triggering in the first data information can be calculated by the number of first data information pieces with a human data version parameter and the total number of first data information pieces. Based on the probability of abnormal data triggering and a preset first triggering probability threshold, data anomaly judgment is performed, and corresponding monitoring results are generated and displayed. Since only the first data information pieces judged as abnormal data will have their version parameters updated, it is only necessary to count the number of first data information pieces with a second version parameter to obtain the number of anomalies in the first data information, thereby determining the probability of abnormal data triggering in the first data information.

[0086] Similarly, when using the method of accumulating version parameters, and updating the version parameters of the next data information arranged in chronological order based on the previous data information, this application can also determine the number of all abnormal data in this set of data information by the value of the version parameter after the last data information is updated, thereby calculating the corresponding abnormal data trigger probability, and judging the abnormality of data information based on the abnormal data trigger probability and the trigger probability threshold.

[0087] Furthermore, the data monitoring method provided in this application is not limited to judging data anomalies by the probability of abnormal data triggering; it can also directly monitor and analyze data by the value of version parameters and the pre-set version parameter threshold.

[0088] For example, in a scenario where each piece of data is accumulated based on the initial first version parameter, the number of first data pieces with a second data version parameter is directly compared with a pre-set version threshold. If the number of first data pieces with a second data version parameter exceeds the version threshold, the data is identified as abnormal and an alarm is triggered.

[0089] As for the method of accumulating version parameters, it is only necessary to compare the version parameter of the last data information arranged in chronological order with the version threshold. As long as the version parameter exceeds the version threshold, the data is identified as abnormal and an alarm is triggered.

[0090] Based on the above implementation methods, the technical solution provided in this application measures whether the data is abnormal by calculating the probability of abnormal data triggering, which further improves the efficiency of park data monitoring and analysis.

[0091] Based on the above implementation methods, such as Figure 4 As shown, the park data information includes pedestrian data information after being processed by segmentation and classification, and the trigger probability threshold includes pedestrian data trigger probability threshold. In the park data monitoring method provided in this application, step 142 includes:

[0092] Step 151: When the probability of triggering the first abnormal data corresponding to the pedestrian data information is greater than the threshold of the pedestrian data triggering probability, the pedestrian data information is judged to be abnormal, and the first park data monitoring result corresponding to the pedestrian data information is generated.

[0093] Specifically, the park data monitoring method provided in this application can monitor and analyze pedestrian data information after it has been processed into blocks and categories. When the technical solution provided in this application collects all data within the park through a server, it first needs to classify and store the data according to its type to reduce the server's data storage pressure while extracting pedestrian data information, such as pedestrian flow in various passages within the park and the number of users of public facilities like elevators. Information representing pedestrian flow can be obtained through methods including, but not limited to, camera capture and recognition, and calculation of the number of times people swipe their cards; this application does not impose any restrictions.

[0094] Taking the monitored pedestrian flow of a channel as an example, after collecting multiple sets of pedestrian flow data for each channel in real time, the technical solution provided in this application compares the pedestrian flow data for each channel with a pre-set initial pedestrian flow data. If the pedestrian flow data for a channel is greater than the pre-set initial pedestrian flow data, it indicates that the pedestrian flow data for that channel is abnormal at the current moment. A spin algorithm is used to update the version number corresponding to the pedestrian flow data. Once the version numbers corresponding to all pedestrian flow data collected for that channel have been updated, the probability of triggering abnormal data for the pedestrian flow data is calculated based on the number of pedestrian flow data with changed version numbers and the total number of pedestrian flow data collected for that channel. Alternatively, multiple pedestrian flow data can be collected sequentially over time using an accumulation method, with the version number of each subsequent pedestrian flow data point updated based on the previous one. The probability of triggering abnormal data for the pedestrian flow data is determined based on the version number of the last pedestrian flow data point and the total number of pedestrian flow data points.

[0095] When the probability of triggering abnormal data corresponding to the flow of people in a passage is greater than the preset threshold for the flow of people, it means that the flow of people in the passage is greater than the designed carrying capacity of the passage. The corresponding park data monitoring results are generated and output for display, so that safety management personnel can organize the diversion and realize the park emergency response function when the flow of people in the passage is too large.

[0096] Based on the above implementation methods, since the park data monitoring method provided in this application can monitor and analyze pedestrian data in park data, it is applicable to the monitoring, analysis and alarm response of park pedestrian flow, thus expanding the application scope of this application.

[0097] Based on the above implementation methods, such as Figure 5As shown, the park data information includes vehicle traffic data information after block classification processing, and the trigger probability threshold includes the vehicle traffic data trigger probability threshold. In the park data monitoring method provided in this application, step 142 includes:

[0098] Step 152: When the probability of triggering the first abnormal data corresponding to the vehicle traffic data information is greater than the threshold of the vehicle traffic data triggering probability, the vehicle traffic data information is judged to be abnormal, and the first park data monitoring result corresponding to the vehicle traffic data information is generated.

[0099] Specifically, the park data monitoring method provided in this application can monitor and analyze vehicle traffic data after it has been processed into blocks and categories. After the technical solution provided in this application collects all data within the park through a server, it first needs to classify and store the data according to its type to reduce the server's data storage pressure while extracting vehicle traffic data, such as traffic flow in various lanes within the park and vehicle occupancy rates in parking lots. Information representing traffic flow can be obtained through methods including, but not limited to, camera capture and recognition, and calculation of vehicle entry and exit parking lot card swiping records; this application does not impose any restrictions.

[0100] Taking monitored traffic flow as an example, after collecting multiple sets of traffic flow data for each channel in real time, the technical solution provided in this application compares the traffic flow for each channel with a pre-set initial traffic flow. If the traffic flow for a channel is greater than the pre-set initial traffic flow, it indicates that the traffic flow for that channel is abnormal data at the current moment. A spin algorithm is used to update the version number corresponding to the traffic flow. Once the version numbers for all traffic flow data collected for that channel have been updated, the probability of triggering abnormal data for the traffic flow is calculated based on the number of traffic flow data with changed version numbers and the total number of traffic flow data collected for that channel. Alternatively, multiple traffic flow data collected in chronological order can be accumulated, with the version number of the later traffic flow data updated based on the previous traffic flow data. The probability of triggering abnormal data for the traffic flow is determined based on the version number of the last traffic flow data and the total number of traffic flow data.

[0101] When the probability of triggering abnormal data corresponding to the traffic flow of a channel is greater than the preset traffic flow trigger probability threshold, it indicates that the traffic flow of the channel is greater than the channel's designed carrying capacity. The corresponding park data monitoring results are generated and output for display, so that safety management personnel can organize traffic diversion and realize the park's emergency response function when the traffic flow of the channel is too large.

[0102] Based on the above implementation methods, since the park data monitoring method provided in this application can monitor and analyze vehicle traffic data in the park data, it is applicable to the monitoring, analysis and alarm response of park traffic flow, thus expanding the application scope of this application.

[0103] Based on the above implementation methods, such as Figure 6 As shown, the park data information includes equipment data information after being processed by block classification, and the trigger probability threshold includes equipment data trigger probability threshold. In the park data monitoring method provided in this application, step 142 includes:

[0104] Step 153: When the probability of triggering the first abnormal data corresponding to the device data information is greater than the device data trigger probability threshold, the device data information is judged to be abnormal, and the first campus data monitoring result corresponding to the device data information is generated.

[0105] Specifically, the park data monitoring method provided in this application can monitor and analyze vehicle traffic data after it has been processed into blocks and categories. When the technical solution provided in this application collects all data within the park through a server, it first needs to classify and store the data according to its type. This reduces the server's data storage pressure while extracting equipment data, such as the operational data of various equipment and facilities within the park, and data collected by various cameras, gates, and other machines. The equipment and facility data can be obtained through, but is not limited to, IoT transmission methods; this application does not impose any restrictions.

[0106] Taking equipment operation data as an example, after collecting the operation data of all equipment in the park in real time, the technical solution provided in this application compares the equipment operation data corresponding to each device with the pre-set initial equipment operation data. When the equipment operation data corresponding to a device is greater than the pre-set initial equipment operation data, it indicates that the device is operating abnormally at the current moment. The version number corresponding to the equipment operation data is updated through a spin algorithm. After the version numbers corresponding to all equipment operation data collected by that device have been updated, the probability of triggering abnormal data corresponding to the equipment operation data is calculated based on the number of equipment operation data with changed version numbers and the total number of equipment operation data corresponding to that device collected. Alternatively, multiple equipment operation data collected in chronological order can be accumulated, with the version number of the later equipment operation data updated based on the previous equipment operation data. The probability of triggering abnormal data corresponding to the equipment operation data is determined based on the version number of the last equipment operation data and the number of multiple equipment operation data.

[0107] When the probability of triggering abnormal data corresponding to the device's operating data exceeds the preset threshold for triggering device operating data, it indicates that the device is in an abnormal operating state. The corresponding park data monitoring results are generated and displayed, allowing security management personnel to notify equipment maintenance personnel for repair or to notify security personnel to sound an alarm, thus realizing the park's emergency response function when the device is operating abnormally.

[0108] For example, the standard data setting for the temperature acquisition devices installed in the park is 0 degrees Celsius. When the temperature exceeds 100 degrees Celsius, the equipment will be damaged. To avoid excessive fluctuations and high frequencies in the temperature acquisition data, which could easily damage the devices, this application uses a spin algorithm to monitor and analyze the data detected by the temperature acquisition devices in real time.

[0109] When the temperature fluctuation threshold is set to 50 degrees Celsius, the temperature data logger collects multiple data points in real time. The first data point, arranged chronologically, is 10 degrees Celsius, falling within the range of 0 to 50 degrees Celsius. This is considered normal data and does not trigger a version number update. The second data point is 56 degrees Celsius, exceeding the preset 50-degree threshold, and is considered abnormal data, triggering a spin algorithm. For example, it checks historical data to see if any data has triggered the algorithm before, and increments the version number accordingly. Finally, based on the version number and the total data volume, the abnormal data trigger probability of the temperature data logger is generated. When the abnormal data trigger probability exceeds the threshold, an alarm is triggered, alerting safety management personnel to take appropriate measures.

[0110] Based on the above implementation methods, since the park data monitoring method provided in this application can monitor and analyze the equipment data in the park data, it is applicable to the monitoring, analysis and alarm response of park equipment operation and data collection, thus expanding the application scope of this application.

[0111] Based on the above implementation methods, such as Figure 7 As shown, in the park data monitoring method provided in this application, after step 104, it further includes:

[0112] Step 106: Based on the equipment data information, use a pre-trained equipment fault analysis model to determine the cause of equipment faults and obtain the result of the equipment fault cause determination.

[0113] Step 107: Output and display the results of the equipment failure cause determination.

[0114] Specifically, the park data monitoring method provided in this application can, after collecting equipment data information, also determine the cause of equipment failure based on abnormal data and output the determination result for safety management personnel to handle in subsequent steps.

[0115] For example, after generating the first campus data monitoring results corresponding to the equipment data information, a preliminary determination of the cause of equipment failure is first performed on the abnormal data in the equipment data information. For example, a pre-trained equipment failure analysis model is used to make a preliminary determination of the cause of failure based on the equipment data information, such as simply distinguishing between equipment failure and human sabotage. The equipment failure analysis model is only used to match and determine the cause of failure based on abnormal data and pre-trained common failures. For example, if a match is found, it is classified as equipment failure and corresponding display content is generated; if a match is not found, it is classified as human sabotage and corresponding display content is also generated. This application does not impose any limitations.

[0116] In addition, abnormal data and its corresponding device location, name, model, and other information can be directly sent to safety management personnel, who can then make their own judgments on the data anomalies and take subsequent actions. For example, if the safety management personnel determine that the anomaly is caused by a device malfunction, they will notify the device maintenance personnel to repair it. If the safety management personnel determine that the anomaly is caused by human sabotage, they will notify the security personnel to handle the situation and call the alarm.

[0117] Based on the above implementation method, the park data monitoring method provided in this application can perform preliminary equipment fault analysis on equipment data information while generating park data monitoring results, and output and display the preliminary judgment results of equipment fault causes and park data monitoring results, for example, transmit them to the monitoring room where the safety management personnel are located, so that the safety management personnel can identify the cause of the fault and respond to the abnormal situation, thereby ensuring the safety and stability of the park.

[0118] Based on the above implementation methods, such as Figure 8 As shown, this application also provides an example of a park data monitoring process:

[0119] like Figure 8 As shown, the park data monitoring process provided in this application first transmits all data within the park to the server, such as pedestrian data, vehicle data, and equipment data, and stores them in the database in blocks and categories. Finally, for each type of park data information, multiple park data information corresponding to each device are subjected to anomaly detection through a spin algorithm, and the detection results are output and displayed.

[0120] The process begins with collecting data as a pre-set reference value, which is assumed to be normal data and set to version number 0. Next, a test of the park's data monitoring and analysis is conducted. If the test fails, it indicates a problem with the equipment installation; for example, the equipment may not be installed correctly, or it may malfunction immediately after installation. Only data that passes the test can be used as the reference value.

[0121] The real-time collected data (data) is then compared with the reference value information (data0). Each piece of real-time collected data (data) has its own data attributes, such as a unique identifier (id) generated by the system database, the data value (number), and the version number (version). Subsequently, multiple real-time collected data are compared with the data values ​​corresponding to the pre-set initial value information in a loop. When the results differ, the version number of the corresponding real-time collected data is updated using a spin algorithm. After repeating this loop multiple times, the probability of abnormal data triggering is calculated based on the version number and the total number of data, and the corresponding data monitoring results are generated.

[0122] In addition, to ensure the stability and accuracy of the technical solution provided in this application, factors such as database capacity, data acquisition and transmission latency, and spin algorithm computational efficiency also need to be considered in actual application to park management and monitoring. This application does not impose any restrictions on these factors.

[0123] The second embodiment of this application relates to a data monitoring device, such as... Figure 9 As shown, it includes:

[0124] The data acquisition module 201 is used to acquire first data information from the same data collection point, wherein the first data information includes data value information and first data version parameters;

[0125] The first data value comparison module 202 is used to compare data fluctuations based on the data value information and the preset reference value information to obtain the first data fluctuation comparison result.

[0126] The first version update module 203 is used to update the first data version parameter to obtain the second data version parameter when the first data fluctuation comparison result is that the data value information is different from the reference value information.

[0127] The first anomaly notification module 204 is used to perform anomaly notification operations based on the number of first data information items with second data version parameters.

[0128] Based on the above embodiments, the data monitoring device provided in this application further includes:

[0129] The version value determination module is used to determine the first data version parameter corresponding to the second data information based on the second data version parameter corresponding to the first data information.

[0130] The second data value comparison module is used to determine the first data version parameter corresponding to the second data information based on the second data version parameter corresponding to the first data information.

[0131] The second version update module is used to update the first data version parameter corresponding to the second data information when the second data fluctuation comparison result is that the data value information corresponding to the second data information is different from the reference value information, so as to obtain the second data version parameter corresponding to the second data information.

[0132] The second error message module is used to perform error message operation based on the value of the second data version parameter corresponding to the second data information.

[0133] Based on the above embodiments, the first data value comparison module 202 in the data monitoring device provided in this application includes:

[0134] The size comparison unit is used to compare the data value information with the reference value information using the spin algorithm to obtain the data size comparison result.

[0135] Based on the above implementation method, the park data information includes pedestrian data information after being processed by block classification. In the data monitoring device provided in this application, the first monitoring result generation module 205 includes:

[0136] The pedestrian data monitoring unit is used to determine that the pedestrian data information is abnormal and generate the first data monitoring result corresponding to the pedestrian data information when the probability of triggering the first abnormal data corresponding to the pedestrian data information is greater than the threshold of the pedestrian data triggering probability.

[0137] Based on the above implementation method, the first error notification module 204 includes:

[0138] An anomaly probability calculation unit is used to obtain the first anomaly data trigger probability of the first data information based on the number of first data information with a second data version parameter and the number of the first data information.

[0139] The first data monitoring unit is used to determine that the first data information is abnormal and generate a first data monitoring result when the probability of triggering the first abnormal data is greater than a preset first trigger probability threshold.

[0140] Based on the above implementation method, the park data information includes vehicle traffic data information after block classification processing. In the data monitoring device provided in this application, the first monitoring result generation module 205 includes:

[0141] The vehicle traffic data monitoring unit is used to determine that the vehicle traffic data information is abnormal and generate the first data monitoring result corresponding to the vehicle traffic data information when the probability of triggering the first abnormal data corresponding to the vehicle traffic data information is greater than the vehicle traffic data triggering probability threshold.

[0142] Based on the above implementation method, the park data information includes equipment data information after block classification processing. In the data monitoring device provided in this application, the first monitoring result generation module 205 includes:

[0143] The device data monitoring unit is used to determine that the device data information is abnormal when the probability of triggering the first abnormal data corresponding to the device data information is greater than the device data triggering probability threshold, and to generate the first data monitoring result corresponding to the device data information.

[0144] Based on the above embodiments, the data monitoring device provided in this application further includes:

[0145] The equipment failure analysis module is used to determine the cause of equipment failure based on equipment data information and a pre-trained equipment failure analysis model, and obtain the result of the equipment failure cause determination.

[0146] The fault analysis result display module is used to output and display the results of the equipment fault cause judgment.

[0147] The third embodiment of this application relates to an electronic device, such as... Figure 10 As shown, it includes:

[0148] At least one processor 301;

[0149] And a memory 302 communicatively connected to the at least one processor 301;

[0150] The memory 302 stores instructions that can be executed by the at least one processor. The instructions are executed by the at least one processor 301 to enable the at least one processor 301 to implement the data monitoring method described in the first embodiment of this application.

[0151] The memory and processor are connected via a bus, which can include any number of interconnecting buses and bridges, connecting various circuits of one or more processors and memories. The bus can also connect various other circuits, such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and will not be described further herein. The bus interface provides an interface between the bus and the transceiver. The transceiver can be a single element or multiple elements, such as multiple receivers and transmitters, providing a unit for communicating with various other devices over a transmission medium. Data processed by the processor is transmitted over the wireless medium via an antenna, which further receives data and transmits it to the processor.

[0152] The processor manages the bus and general processing, and also provides various functions, including timing, peripheral interfaces, voltage regulation, power management, and other control functions. Memory is used to store data used by the processor during operation.

[0153] The fourth embodiment of this application relates to a non-volatile computer-readable storage medium storing a computer program. When executed by a processor, the computer program implements the data monitoring method described in the first embodiment of this application.

[0154] That is, those skilled in the art will understand that all or part of the steps in the methods of the above embodiments can be implemented by a program instructing related hardware. This program is stored in a storage medium and includes several instructions to cause a device (which may be a microcontroller, chip, etc.) or processor to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0155] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the application disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this application are indicated by the following claims.

[0156] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A data monitoring method, characterized in that, The method includes: Acquire first data information from the same data collection point, wherein the first data information includes data value information and first data version parameters; Based on the data value information and the pre-set reference value information, a data fluctuation comparison is performed to obtain the first data fluctuation comparison result; When the first data fluctuation comparison result shows that the data value information is different from the reference value information, the first data version parameter is updated to obtain the second data version parameter; An error message is displayed based on the number of first data information items that have a second data version parameter. The data information from the same data collection point also includes second data information arranged chronologically after the first data information. After updating the first data version parameter to obtain the second data version parameter when the first data fluctuation comparison result indicates that the data value information differs from the reference value information, the process further includes: The first data version parameter corresponding to the second data information is determined based on the second data version parameter corresponding to the first data information. The second data fluctuation comparison result is obtained by comparing the data value information corresponding to the second data information with the reference value information through a spin algorithm. The spin algorithm includes: comparing the collected multiple data information with the pre-set reference value information in a loop; in each loop, when the data information is different from the reference value information, updating the version number of the data version parameter corresponding to the data information; after multiple loop comparisons, determining whether the data information is different from the reference value information based on the updated version number. When the second data fluctuation comparison result is that the data value information corresponding to the second data information is different from the reference value information, the first data version parameter corresponding to the second data information is updated to obtain the second data version parameter corresponding to the second data information. Read the second data version parameter of the second data information and perform an error message operation.

2. The method according to claim 1, characterized in that, The step of providing an anomaly alert based on the number of first data information items with a second data version parameter includes: The first abnormal data trigger probability of the first data information is obtained based on the number of first data information with a second data version parameter and the number of first data information. When the probability of triggering the first abnormal data is greater than the preset first trigger probability threshold, the first data information is determined to be abnormal, and a first data monitoring result is generated.

3. The method according to claim 2, characterized in that, The data information includes pedestrian data information after block classification processing, and the trigger probability threshold includes a pedestrian data trigger probability threshold. The step of determining the first data information as abnormal and generating a first data monitoring result when the trigger probability of the first abnormal data is greater than a preset first trigger probability threshold includes: When the probability of triggering the first abnormal data corresponding to the pedestrian data information is greater than the threshold of the pedestrian data triggering probability, the pedestrian data information is determined to be abnormal, and the first data monitoring result corresponding to the pedestrian data information is generated.

4. The method according to claim 2, characterized in that, The data information includes vehicle traffic data information after block classification processing, the trigger probability threshold includes a vehicle traffic data trigger probability threshold, and the step of determining that the first data information is abnormal and generating a first data monitoring result when the trigger probability of the first abnormal data is greater than the preset first trigger probability threshold includes: When the probability of triggering the first abnormal data corresponding to the vehicle traffic data information is greater than the vehicle traffic data triggering probability threshold, the vehicle traffic data information is determined to be abnormal, and the first data monitoring result corresponding to the vehicle traffic data information is generated.

5. The method according to claim 2, characterized in that, The data information includes device data information after block classification processing, the trigger probability threshold includes a device data trigger probability threshold, and the step of determining that the first data information is abnormal and generating a first data monitoring result when the trigger probability of the first abnormal data is greater than the preset first trigger probability threshold includes: When the probability of triggering the first abnormal data corresponding to the device data information is greater than the device data triggering probability threshold, the device data information is determined to be abnormal, and the first data monitoring result corresponding to the device data information is generated.

6. The method according to claim 5, characterized in that, After determining that the device data information is abnormal and generating the first data monitoring result corresponding to the device data information when the probability of triggering the first abnormal data corresponding to the device data information is greater than the device data triggering probability threshold, the method further includes: Based on the equipment data information, the cause of equipment failure is determined by a pre-trained equipment failure analysis model, and the result of the equipment failure cause determination is obtained. The results of the fault diagnosis will be output and displayed.

7. A data monitoring device, characterized in that, include: The data acquisition module is used to acquire first data information from the same data collection point, wherein the first data information includes data value information and first data version parameters; The first data value comparison module is used to compare data fluctuations with the data value information and the preset reference value information to obtain the first data fluctuation comparison result. The first version update module is used to update the first data version parameter to obtain the second data version parameter when the first data fluctuation comparison result is that the data value information is different from the reference value information. The first anomaly alert module is used to perform anomaly alert operations based on the number of first data information items with second data version parameters. The data information of the same data collection point also includes second data information arranged in chronological order after the first data information. The first version update module is also used to determine the first data version parameter corresponding to the second data information based on the second data version parameter corresponding to the first data information. The second data fluctuation comparison result is obtained by comparing the data value information corresponding to the second data information with the reference value information through a spin algorithm. The spin algorithm includes: comparing the collected multiple data information with the pre-set reference value information in a loop; in each loop, when the data information is different from the reference value information, updating the version number of the data version parameter corresponding to the data information; after multiple loop comparisons, determining whether the data information is different from the reference value information based on the updated version number. When the second data fluctuation comparison result is that the data value information corresponding to the second data information is different from the reference value information, the first data version parameter corresponding to the second data information is updated to obtain the second data version parameter corresponding to the second data information. Read the second data version parameter of the second data information and perform an error message operation.

8. An electronic device, characterized in that, It includes a processor and a memory, the memory storing a program or instructions that can run on the processor, the program or instructions being executed by the processor to implement the steps of the data monitoring method as described in any one of claims 1-6.

9. A readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the data monitoring method as described in any one of claims 1-6.

Citation Information

Patent Citations

  • Data-driven park management service Qos monitoring method and system

    CN116383751A