Smart community management and control method based on multi-dimensional data monitoring

Abstract

The invention relates to the technical field of data processing, in particular to a smart community management and control method based on multi-dimensional data monitoring, which comprises the following steps: collecting multi-dimensional data in a smart community, and sequentially caching, cleaning, integrating and compressing the multi-dimensional data to output optimized data, training an early warning model by using the optimization data to output an active safety model; monitoring and controlling the smart community through the active security model, giving an alarm when an abnormal condition occurs, and displaying alarm information on a visual interface; determining the management and control stability of the smart community based on the variance of the packet loss rate of the multi-dimensional data; if the management and control stability does not meet the requirement, adjusting the cache size of the multi-dimensional data, or determining the management and control reliability of the smart community based on the early warning missing report rate of the abnormal condition; and if the control reliability does not meet the requirement, adjusting the batch training size of the optimized data. The management and control stability of the smart community is improved.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a smart community management and control method based on multi-dimensional data monitoring. Background Art

[0002] In the existing technology, smart community refers to a new type of community form that uses new-generation information technologies such as the Internet of Things, big data, and artificial intelligence to collect, analyze, and apply multi-dimensional data such as people, places, things, objects, and organizations in the community to achieve intelligent community governance, convenient residents' lives, and precise public services. The traditional community management model mainly relies on manual experience and simple technical means, which can no longer meet the complex and diverse management needs of modern communities. In terms of early warning and control, the existing early warning models are often not accurate and intelligent enough to detect abnormal situations in the community in a timely and accurate manner. Traditional early warning methods are mostly based on simple threshold judgments, which are difficult to effectively identify complex scenarios and potential risks. For example, in the community's fire warning, only based on a single indicator of smoke concentration, it is easy to have false alarms or missed alarms, and it is impossible to detect fire hazards in advance. Moreover, most community management systems lack an effective evaluation and adjustment mechanism for the stability and reliability of control. Once network fluctuations, data anomalies, and other problems occur, the performance of the entire control system will be seriously affected, and the safety and normal operation of the community cannot be guaranteed.

[0003] Chinese Patent Publication No.: CN116228486A discloses an environmental safety management and control system, method and storage medium for a smart community, including a server, a housekeeper terminal, an owner terminal, an interactive platform and a processor, wherein the housekeeper terminal, the owner terminal and the interactive platform are respectively connected to the server, and the interactive platform and the server are respectively connected to the processor; the server is configured to store community information data, and the community information data includes one or more of community building safety inspection data, community personnel access management data, community environment management data and community fire safety management data; the housekeeper terminal is configured for community property personnel to manage The owner terminal is configured to be used by residents to view and upload the community information data; the interactive platform is configured for data interaction and management, the owner terminal uploads and uploads community usage information to the interactive platform, and the owner terminal obtains the community information data through the interactive platform; the housekeeper terminal obtains the community usage information through the interactive platform, and after review, the community usage information is converted into the corresponding community information data, and the housekeeper terminal uploads and uploads the updated community information data to the interactive platform; the community usage information includes one or more of visitor management, property requirements, and environmental feedback. It can be seen that there is a problem that due to the long transmission distance between the data acquisition equipment and the data center, the signal strength gradually decays, resulting in data packet loss, which causes the stability of the management and control of the smart community to decrease. Summary of the invention

[0004] To this end, the present invention provides a smart community management and control method based on multi-dimensional data monitoring, which is used to overcome the problem in the prior art that due to the long transmission distance between the data acquisition equipment and the data center, the signal strength gradually attenuates and causes data packet loss, thereby causing the management and control stability of the smart community to decrease.

[0005] To achieve the above-mentioned objectives, the present invention provides a smart community management and control method based on multidimensional data monitoring, comprising: collecting multidimensional data in the smart community, caching, cleaning, integrating and compressing the multidimensional data in sequence to output optimized data, using the optimized data to train an early warning model to output an active safety model; monitoring and controlling the smart community through the active safety model, issuing an alarm when an abnormal situation occurs and displaying the alarm information on a visual interface; obtaining the packet loss rate of the multidimensional data within a number of collection cycles; determining the management and control stability of the smart community based on the variance of the packet loss rate of the multidimensional data; if the management and control stability does not meet the requirements, adjusting the cache size of the multidimensional data, or determining the management and control reliability of the smart community based on the early warning missed reporting rate of the abnormal situation; if the management and control reliability does not meet the requirements, adjusting the batch training size of the optimized data, or adjusting the compression ratio of the multidimensional data based on the average delay time of the multidimensional data processing.

[0006] Furthermore, determining the control stability of the smart community includes: Comparing the variance of the packet loss rate of the multidimensional data with a preset first variance; If the variance of the packet loss rate of the multi-dimensional data is greater than the preset first variance, it is determined that the management and control stability of the smart community does not meet the requirements.

[0007] Furthermore, determining the control reliability of the smart community includes: Comparing the variance of the packet loss rate of the multidimensional data with the preset first variance and the preset second variance respectively; If the variance of the packet loss rate of the multidimensional data is greater than the preset first variance and less than or equal to the preset second variance, it is preliminarily determined that the management and control reliability of the smart community does not meet the requirements, and whether the management and control reliability of the smart community meets the requirements is determined based on the warning omission rate of abnormal situations.

[0008] Furthermore, adjusting the cache size of the multidimensional data includes: Comparing the variance of the packet loss rate of the multidimensional data with the preset second variance; If the variance of the packet loss rate of the multi-dimensional data is greater than a preset second variance, the cache size of the multi-dimensional data is increased.

[0009] Furthermore, the increase range of the cache size of the multi-dimensional data is determined by the difference between the variance of the packet loss rate of the multi-dimensional data and a preset second variance.

[0010] Further, adjusting the batch training size of the optimization data includes: Compare the warning missed alarm rate of the abnormal situation with the preset first missed alarm rate and the preset second missed alarm rate respectively; If the warning missed alarm rate of the abnormal situation is greater than the preset first missed alarm rate, it is determined that the control reliability of the smart community does not meet the requirements; If the warning missed alarm rate of the abnormal situation is greater than the preset first missed alarm rate and less than or equal to the preset second missed alarm rate, reducing the batch training size of the optimization data; If the warning missed alarm rate of the abnormal situation is greater than the preset second missed alarm rate, it is preliminarily determined that the storage validity of the multidimensional data does not meet the requirements, and whether the storage validity of the multidimensional data meets the requirements is determined based on the average delay time of the multidimensional data processing.

[0011] Furthermore, the reduction extent of the batch training size of the optimization data is determined by the difference between the warning missed alarm rate of the abnormal situation and a preset first missed alarm rate.

[0012] Furthermore, the compression ratio of the multidimensional data is adjusted, including: Compare the average delay time of multidimensional data processing with the preset delay time; If the average delay time of the multidimensional data processing is greater than the preset delay time, it is determined that the storage validity of the multidimensional data does not meet the requirements, and the compression ratio of the multidimensional data is increased.

[0013] Furthermore, the average delay duration of the multidimensional data processing is a ratio of a total delay duration of the multidimensional data processing in a number of processing cycles to the number of processing cycles.

[0014] Furthermore, the increase range of the compression ratio of the multidimensional data is determined by the difference between an average delay time of multidimensional data processing and a preset delay time.

[0015] Compared with the prior art, the beneficial effect of the present invention lies in that the method of the present invention adjusts the cache size of multidimensional data according to the variance of the packet loss rate of the multidimensional data. Since there may be a long transmission distance between the data acquisition device and the data center, the signal strength gradually decays, causing data packet loss. By increasing the cache size of the multidimensional data, more data can be temporarily stored on the data acquisition device or the nodes in the transmission path to avoid data loss due to temporary signal interruption or slow transmission. The batch training size of the optimized data is adjusted according to the early warning omission rate of abnormal situations. Since the model does not have enough data to learn the overall characteristics and laws of the data during training, it is easy to over-rely on the existing small amount of data, and learn some noise or special cases in the data as universal laws, which leads to overfitting, and for a certain For some events with low probability of occurrence, the small number of samples leads to no warning when the event occurs. By reducing the batch training size of the optimization data, the model parameters can be updated more frequently, and the step size of each update is relatively small, making the model training process smoother and able to better learn the overall characteristics and laws in the data. The compression ratio of multidimensional data is adjusted according to the average delay time of multidimensional data processing. Since the collected data may have quality problems such as noise, errors, and duplications, it takes up additional storage resources, causes errors in the storage and processing process, and reduces the effectiveness of data storage. By increasing the compression ratio of multidimensional data, the storage space occupied by data can be reduced, the pressure on storage resources can be alleviated, and the transmission speed can be increased, thereby improving the efficiency of data processing and improving the management and control stability of the smart community.

[0016] Furthermore, the method of the present invention adjusts the cache size of multidimensional data by setting a preset first variance and a preset second variance. Since there may be a long transmission distance between the data acquisition device and the data center, the signal strength gradually decays, resulting in data packet loss. By increasing the cache size of the multidimensional data, more data can be temporarily stored on the data acquisition device or the nodes in the transmission path, avoiding data loss due to temporary signal interruption or slow transmission, and further improving the management and control stability of the smart community.

[0017] Furthermore, the method of the present invention adjusts the batch training size of the optimized data by setting a preset first false negative rate and a preset second false negative rate. Since the model does not have enough data to learn the overall characteristics and laws of the data during training, it is easy to over-rely on the existing small amount of data, and learn some noise or special cases in the data as general laws, which leads to overfitting. For some events with a low probability of occurrence, the small number of samples leads to no warning when the event occurs. By reducing the batch training size of the optimized data, the model parameters can be updated more frequently, and the step size of each update is relatively small, so that the training process of the model is smoother, and the overall characteristics and laws in the data can be better learned, further improving the management and control stability of the smart community.

[0018] Furthermore, the method of the present invention adjusts the compression ratio of multidimensional data by setting a preset delay time. Since the collected data may have quality problems such as noise, errors, and duplications, which result in the occupation of additional storage resources and induce errors during storage and processing, resulting in a decrease in the effectiveness of data storage, by increasing the compression ratio of multidimensional data, the storage space occupied by the data can be reduced, the pressure on storage resources can be alleviated, and the transmission speed can be increased, thereby improving the efficiency of data processing and further improving the management and control stability of the smart community. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 This is an overall flow chart of a smart community management and control method based on multi-dimensional data monitoring according to an embodiment of the present invention; Figure 2 It is a logic flow chart of a smart community management and control method based on multi-dimensional data monitoring according to an embodiment of the present invention; Figure 3 A specific flow chart of a process for adjusting the cache size of multidimensional data in a smart community management and control method based on multidimensional data monitoring according to an embodiment of the present invention; Figure 4 This is a specific flow chart of the process of adjusting the batch training size of optimized data in the smart community management and control method based on multi-dimensional data monitoring in an embodiment of the present invention. DETAILED DESCRIPTION

[0020] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0021] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0022] See also Figure 1 , Figure 2 , Figure 3 as well as Figure 4 As shown, they are respectively an overall flow chart of a smart community management and control method based on multidimensional data monitoring, a logical flow chart, a specific flow chart of a process for adjusting the cache size of multidimensional data, and a specific flow chart of a process for adjusting the batch training size of optimized data in an embodiment of the present invention. A smart community management and control method based on multidimensional data monitoring of the present invention comprises: Step S1, collecting multidimensional data in the smart community, caching, cleaning, integrating and compressing the multidimensional data in sequence to output optimized data, and using the optimized data to train an early warning model to output an active safety model; Step S2, monitoring and controlling the smart community through the active safety model, issuing an alarm when an abnormal situation occurs and displaying the alarm information on a visual interface; Step S3, obtaining the packet loss rate of multidimensional data in several collection cycles; Step S4, determining the management and control stability of the smart community based on the variance of the packet loss rate of the multi-dimensional data; Step S5: if the control stability does not meet the requirements, the cache size of the multidimensional data is adjusted, or the control reliability of the smart community is determined based on the warning missed rate of abnormal situations; Step S6: If the control reliability does not meet the requirements, the batch training size of the optimized data is adjusted, or the compression ratio of the multidimensional data is adjusted based on the average delay time of the multidimensional data processing.

[0023] Specifically, the multidimensional data includes the name of the resident, the address of the house, and the time of video surveillance.

[0024] Specifically, data optimization includes removing duplicate resident information, completing missing video surveillance information, and integrating resident distribution information.

[0025] Specifically, the active safety models are random forest models, convolutional neural network models, and digital twin models.

[0026] Specifically, abnormal situations include elevator malfunctions within the community, house fires, and fallen trees within the community.

[0027] In implementation, the method of the present invention adjusts the cache size of multidimensional data according to the variance of the packet loss rate of the multidimensional data. Since there may be a long transmission distance between the data acquisition device and the data center, the signal strength gradually decays, resulting in data packet loss. By increasing the cache size of the multidimensional data, more data can be temporarily stored on the data acquisition device or the nodes in the transmission path to avoid data loss due to temporary signal interruption or slow transmission. The batch training size of the optimized data is adjusted according to the warning omission rate of abnormal situations. Since the model does not have enough data to learn the overall characteristics and laws of the data during training, it is easy to over-rely on the existing small amount of data, and learn some noise or special cases in the data as general laws, which leads to overfitting, and for some low probability of occurrence The small number of samples leads to no warning when encountering the event. By reducing the batch training size of the optimization data, the model parameters can be updated more frequently, and the step size of each update is relatively small, making the model training process smoother and able to better learn the overall characteristics and laws in the data. The compression ratio of the multidimensional data is adjusted according to the average delay time of the multidimensional data processing. Since the collected data may have quality problems such as noise, errors, and duplications, it takes up additional storage resources and causes errors during the storage and processing process, resulting in a decrease in the effectiveness of data storage. By increasing the compression ratio of multidimensional data, the storage space occupied by the data can be reduced, the pressure on storage resources can be alleviated, and the transmission speed can be increased, thereby improving the efficiency of data processing and improving the management and control stability of the smart community.

[0028] Specifically, determining the control stability of the smart community includes: Obtaining the packet loss rate of the multidimensional data in several acquisition cycles, and calculating the variance of the packet loss rate of the multidimensional data; Comparing the variance of the packet loss rate of the multidimensional data with a preset first variance; If the variance of the packet loss rate of the multi-dimensional data is greater than the preset first variance, it is determined that the management and control stability of the smart community does not meet the requirements.

[0029] Specifically, determining the control reliability of the smart community includes: Comparing the variance of the packet loss rate of the multidimensional data with the preset first variance and the preset second variance respectively; If the variance of the packet loss rate of the multidimensional data is greater than the preset first variance and less than or equal to the preset second variance, it is preliminarily determined that the management and control reliability of the smart community does not meet the requirements, and whether the management and control reliability of the smart community meets the requirements is determined based on the warning omission rate of abnormal situations.

[0030] It can be understood that the three intervals divided by the preset first variance and the preset second variance correspond to three situations respectively: The first interval is that the variance of the packet loss rate of the multidimensional data is less than or equal to the preset first variance, and the corresponding situation is: it is determined that the control stability of the smart community meets the requirements; The second interval is when the variance of the packet loss rate of the multidimensional data is greater than the preset first variance and less than or equal to the preset second variance. The corresponding situation is: since the model does not have enough data to learn the overall characteristics and rules of the data during training, it is easy to over-rely on the existing small amount of data and learn some noise or special cases in the data as universal rules, which leads to overfitting. For some events with low probability of occurrence, the small number of samples leads to no warning when the event occurs; The third interval is when the variance of the packet loss rate of the multidimensional data is greater than the preset second variance. The corresponding situation is: since there may be a long transmission distance between the data acquisition device and the data center, the signal strength gradually decays, causing data packet loss.

[0031] In practice, the preset first variance is generally selected in the range of [0.03, 0.05], and the preset second variance is generally selected in the range of [0.06, 0.08].

[0032] Preferably, the preferred embodiment of the preset first variance is 0.04, and the preferred embodiment of the preset second variance is 0.07.

[0033] Specifically, the variance of the packet loss rate of multidimensional data is the variance of the packet loss rate of the multidimensional data within several acquisition cycles. The calculation method of the variance of the packet loss rate of multidimensional data is a conventional technical means well known to technical personnel in this field. Therefore, the calculation process of the variance of the packet loss rate of multidimensional data will not be repeated here.

[0034] In implementation, the method of the present invention determines the management and control stability of the smart community by setting a preset first variance and a preset second variance, thereby reducing the impact of the decrease in the management and control accuracy of the smart community due to inaccurate determination of the management and control stability of the smart community, and further improving the management and control stability of the smart community.

[0035] Specifically, adjusting the cache size of the multidimensional data includes: Comparing the variance of the packet loss rate of the multidimensional data with the preset second variance; If the variance of the packet loss rate of the multi-dimensional data is greater than a preset second variance, the cache size of the multi-dimensional data is increased.

[0036] Specifically, the increase range of the cache size of the multi-dimensional data is determined by the difference between the variance of the packet loss rate of the multi-dimensional data and a preset second variance.

[0037] Specifically, when the difference between the variance of the packet loss rate of the multidimensional data and the preset second variance is within 0.02, the cache size of the multidimensional data is increased to 1.1 times of the original size; when the difference between the variance of the packet loss rate of the multidimensional data and the preset second variance exceeds 0.02, on the basis of being increased to 1.1 times of the original size, the cache size of the multidimensional data is increased by 50MB for every 0.02 exceeding it. For example, the difference between the variance of the packet loss rate of the multidimensional data and the preset second variance is 0.06, the current cache size of the multidimensional data is 500MB, and the increased cache size of the multidimensional data is 500×1.1+50×2=650MB.

[0038] In implementation, the method of the present invention adjusts the cache size of multidimensional data by setting a preset first variance and a preset second variance. Since there may be a long transmission distance between the data acquisition device and the data center, the signal strength gradually decays, resulting in data packet loss. By increasing the cache size of the multidimensional data, more data can be temporarily stored on the data acquisition device or the nodes in the transmission path, avoiding data loss due to temporary signal interruption or slow transmission, and further improving the management and control stability of the smart community.

[0039] Specifically, adjusting the batch training size of the optimization data includes: The number of missed warnings of abnormal situations and the total number of abnormal situations are obtained respectively, and the missed warning rate of abnormal situations is calculated; Comparing the warning missed alarm rate of the abnormal situation with the preset first missed alarm rate and the preset second missed alarm rate respectively; If the warning missed alarm rate of the abnormal situation is greater than the preset first missed alarm rate, it is determined that the control reliability of the smart community does not meet the requirements; If the warning missed alarm rate of the abnormal situation is greater than the preset first missed alarm rate and less than or equal to the preset second missed alarm rate, reducing the batch training size of the optimization data; If the warning missed alarm rate of the abnormal situation is greater than the preset second missed alarm rate, it is preliminarily determined that the storage validity of the multidimensional data does not meet the requirements, and whether the storage validity of the multidimensional data meets the requirements is determined based on the average delay time of the multidimensional data processing.

[0040] It can be understood that the three intervals divided by the preset first false negative rate and the preset second false negative rate correspond to three situations respectively: The first interval is that the warning missed alarm rate of abnormal situations is less than or equal to the preset first missed alarm rate, and the corresponding situation is: it is determined that the control reliability of the smart community meets the requirements; The second interval is when the warning missed rate of abnormal situations is greater than the preset first missed rate and less than or equal to the preset second missed rate. The corresponding situation is: since the model does not have enough data to learn the overall characteristics and laws of the data during training, it is easy to over-rely on the existing small amount of data and learn some noise or special cases in the data as universal laws, which leads to overfitting. For some events with low probability of occurrence, there are few samples, resulting in no warning when encountering the event; The third interval is that the warning missed alarm rate of abnormal situations is greater than the preset second missed alarm rate. The corresponding situation is: because the collected data may have quality problems such as noise, errors, and duplications, it takes up additional storage resources, causes errors in the storage and processing process, and reduces the effectiveness of data storage.

[0041] In practice, the preset first false negative rate is generally selected in the range of [0.02, 0.04], and the preset second false negative rate is generally selected in the range of [0.05, 0.07].

[0042] Preferably, the preferred embodiment of the preset first false negative rate is 0.03, and the preferred embodiment of the preset second false negative rate is 0.06.

[0043] Specifically, the warning omission rate of abnormal situations is the ratio of the number of warning omissions of abnormal situations to the total number of abnormal situations.

[0044] In implementation, the method of the present invention determines the management and control reliability of the smart community by setting a preset first false negative rate and a preset second false negative rate, thereby reducing the impact of the decline in the management and control stability of the smart community due to inaccurate determination of the management and control reliability of the smart community, and further improving the management and control stability of the smart community.

[0045] Specifically, the reduction extent of the batch training size of the optimization data is determined by the difference between the warning missed alarm rate of the abnormal situation and the preset first missed alarm rate.

[0046] Specifically, when the difference between the warning omission rate of abnormal situations and the preset first omission rate is within 0.03, the batch training size of the optimized data is reduced to 0.9 times of the original; when the difference between the warning omission rate of abnormal situations and the preset first omission rate exceeds 0.03, on the basis of being reduced to 0.9 times of the original, the batch training size of the optimized data is reduced by 10 for every 0.01 that exceeds it. For example, when the difference between the warning omission rate of abnormal situations and the preset first omission rate is 0.05, the current batch training size of the optimized data is 500, and the reduced batch training size of the optimized data is 500×0.9-10×2=430.

[0047] In implementation, the method of the present invention adjusts the batch training size of the optimized data by setting a preset first false negative rate and a preset second false negative rate. Since the model does not have enough data to learn the overall characteristics and laws of the data during training, it is easy to over-rely on the existing small amount of data, and learn some noise or special cases in the data as general laws, which leads to overfitting. For some events with a low probability of occurrence, the small number of samples leads to no warning when the event occurs. By reducing the batch training size of the optimized data, the model parameters can be updated more frequently, and the step size of each update is relatively small, which makes the training process of the model smoother, and can better learn the overall characteristics and laws in the data, further improving the management and control stability of the smart community.

[0048] Specifically, adjusting the compression ratio of the multidimensional data includes: Obtaining the delay time of multidimensional data processing in several processing cycles, and calculating the average delay time of the multidimensional data processing; Comparing the average delay time of the multidimensional data processing with a preset delay time; If the average delay time of the multidimensional data processing is greater than the preset delay time, it is determined that the storage validity of the multidimensional data does not meet the requirements, and the compression ratio of the multidimensional data is increased.

[0049] It can be understood that the two intervals divided by the preset delay time correspond to two situations: The first interval is that the average delay time of multidimensional data processing is less than or equal to the preset delay time, and the corresponding situation is: determining that the storage validity of the multidimensional data meets the requirements; The second interval is when the average delay time of multidimensional data processing is greater than the preset delay time. The corresponding situation is: because the collected data may have quality problems such as noise, errors, and duplications, it takes up additional storage resources, causes errors in the storage and processing process, and reduces the effectiveness of data storage.

[0050] In practice, the preset delay time is generally selected in the range of [2s, 4s].

[0051] Preferably, the preferred embodiment of the preset delay time length is 3s.

[0052] In implementation, the method of the present invention determines the storage validity of multidimensional data by setting a preset delay period, thereby reducing the impact of the decline in the management and control stability of the smart community due to inaccurate determination of the storage validity of the multidimensional data, and further improving the management and control stability of the smart community.

[0053] Specifically, the average delay duration of the multidimensional data processing is the ratio of the total delay duration of the multidimensional data processing in a number of processing cycles to the number of processing cycles.

[0054] Specifically, the increase range of the compression ratio of the multi-dimensional data is determined by the difference between the average delay time of multi-dimensional data processing and the preset delay time.

[0055] Specifically, when the difference between the average delay time of multidimensional data processing and the preset delay time is within 2s, the compression ratio of the multidimensional data is increased to 1.2 times of the original value; when the difference between the average delay time of multidimensional data processing and the preset delay time exceeds 2s, on the basis of being increased to 1.2 times of the original value, the compression ratio of the multidimensional data increases by 3% for every 1s exceeding it. For example, the difference between the average delay time of multidimensional data processing and the preset delay time is 4s, the current compression ratio of the multidimensional data is 50%, and the compression ratio of the increased multidimensional data is 50×1.2+3×2=66%.

[0056] Specifically, the compression ratio of the multidimensional data is the ratio of the compressed portion of the multidimensional data to the total amount of the original multidimensional data.

[0057] In implementation, the method of the present invention adjusts the compression ratio of multidimensional data by setting a preset delay time. Since the collected data may have quality problems such as noise, errors, and duplications, additional storage resources are occupied, errors are caused during storage and processing, and the effectiveness of data storage is reduced. By increasing the compression ratio of multidimensional data, the storage space occupied by the data can be reduced, the pressure on storage resources can be alleviated, and the transmission speed can be increased, thereby improving the efficiency of data processing and further improving the management and control stability of the smart community.

[0058] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

Claims

1. A smart community management and control method based on multi-dimensional data monitoring, characterized in that: include: Collect multidimensional data in the smart community, cache, clean, integrate and compress the multidimensional data in sequence to output optimized data, and use the optimized data to train the early warning model to output an active safety model; The active safety model is used to monitor and control the smart community, and an alarm is issued when an abnormal situation occurs and the alarm information is displayed on a visual interface; Obtain the packet loss rate of multi-dimensional data in several collection cycles; Determine the control stability of smart communities based on the variance of packet loss rate of multi-dimensional data; If the control stability does not meet the requirements, the cache size of the multidimensional data is adjusted, or the control reliability of the smart community is determined based on the warning omission rate of abnormal situations; If the control reliability does not meet the requirements, the batch training size of the optimized data is adjusted, or the compression ratio of the multidimensional data is adjusted based on the average delay time of the multidimensional data processing.

2. The smart community management and control method based on multi-dimensional data monitoring according to claim 1 is characterized in that: Determine the control stability of the smart community, including: Comparing the variance of the packet loss rate of the multidimensional data with a preset first variance; If the variance of the packet loss rate of the multi-dimensional data is greater than the preset first variance, it is determined that the management and control stability of the smart community does not meet the requirements.

3. The smart community management and control method based on multi-dimensional data monitoring according to claim 2 is characterized in that: Determine the control reliability of the smart community, including: Comparing the variance of the packet loss rate of the multidimensional data with the preset first variance and the preset second variance respectively; If the variance of the packet loss rate of the multidimensional data is greater than the preset first variance and less than or equal to the preset second variance, it is preliminarily determined that the management and control reliability of the smart community does not meet the requirements, and whether the management and control reliability of the smart community meets the requirements is determined based on the warning omission rate of abnormal situations.

4. The smart community management and control method based on multi-dimensional data monitoring according to claim 3 is characterized in that: Adjusting the cache size of the multidimensional data includes: Comparing the variance of the packet loss rate of the multidimensional data with the preset second variance; If the variance of the packet loss rate of the multi-dimensional data is greater than a preset second variance, the cache size of the multi-dimensional data is increased.

5. The smart community management and control method based on multi-dimensional data monitoring according to claim 4 is characterized in that: The increase range of the cache size of the multi-dimensional data is determined by the difference between the variance of the packet loss rate of the multi-dimensional data and a preset second variance.

6. The smart community management and control method based on multi-dimensional data monitoring according to claim 5 is characterized in that: The batch training size of the optimization data is adjusted, including: Compare the warning missed alarm rate of the abnormal situation with the preset first missed alarm rate and the preset second missed alarm rate respectively; If the warning missed alarm rate of the abnormal situation is greater than the preset first missed alarm rate, it is determined that the control reliability of the smart community does not meet the requirements; If the warning missed alarm rate of the abnormal situation is greater than the preset first missed alarm rate and less than or equal to the preset second missed alarm rate, reducing the batch training size of the optimization data; If the warning missed alarm rate of the abnormal situation is greater than the preset second missed alarm rate, it is preliminarily determined that the storage validity of the multidimensional data does not meet the requirements, and whether the storage validity of the multidimensional data meets the requirements is determined based on the average delay time of the multidimensional data processing.

7. The smart community management and control method based on multi-dimensional data monitoring according to claim 6 is characterized in that: The reduction extent of the batch training size of the optimization data is determined by the difference between the warning missed alarm rate of the abnormal situation and the preset first missed alarm rate.

8. The smart community management and control method based on multi-dimensional data monitoring according to claim 7 is characterized in that: Adjusting the compression ratio of the multidimensional data includes: Compare the average delay time of multidimensional data processing with the preset delay time; If the average delay time of the multidimensional data processing is greater than the preset delay time, it is determined that the storage validity of the multidimensional data does not meet the requirements, and the compression ratio of the multidimensional data is increased.

9. The smart community management and control method based on multi-dimensional data monitoring according to claim 8 is characterized in that: The average delay duration of the multidimensional data processing is a ratio of the total delay duration of the multidimensional data processing in a number of processing cycles to the number of processing cycles.

10. The smart community management and control method based on multi-dimensional data monitoring according to claim 9 is characterized in that: The increase range of the compression ratio of the multi-dimensional data is determined by the difference between the average delay time of the multi-dimensional data processing and the preset delay time.

Images