Urban environmental health management method and system based on Internet of Things, program product and storage medium

Abstract

The invention provides an urban environmental health management method and system based on the Internet of Things, a program product and a storage medium, and relates to the technical field of urban environmental health management. And areas which are to be cleaned for a short time can be quickly eliminated. When it is found that the space-time entropy value is smaller than the first preset threshold value, a cleaning target mark is directly given in the next period, and if the space-time entropy value is not smaller than the first preset threshold value, whether the activity being carried out in the target area is similar to the known activity needing to be cleaned needs to be further investigated. If the two are similar, it can be deduced that the area needs to be cleaned; and if not, calculating the comprehensive pollution degree. Therefore, the area range in which complex operation needs to be carried out is reduced to the greatest extent, the unnecessary operation amount is reduced from the source, and meanwhile, the pertinence and the flexibility of management are improved.

Description

Technical Field

[0001] The present application relates to the technical field of urban environmental sanitation management, and in particular to an urban environmental sanitation management method, system, program product and storage medium based on the Internet of Things. Background Art

[0002] As cities continue to expand and people's demands for a better living environment continue to rise, urban sanitation management has become a crucial component of urban construction and operations. Good sanitation not only impacts the physical and mental health of residents but is also a key element in projecting a city's image and promoting sustainable development.

[0003] In the related art, one current method is to perform fixed cleaning on each fixed area. However, this method has a relatively rigid process and is not very targeted. Related technologies acquire activity information and then use it to calculate the probability of contamination. Only when the probability reaches a pre-set threshold is the surveillance image retrieved for further processing. While this technology addresses the previously rigid and limited focus of the process, it also introduces new technical challenges and requires a significant amount of unnecessary computation without delivering any real benefits.

[0004] Therefore, there is an urgent need for a technical solution that can reduce unnecessary calculations, be relatively flexible in process, and be highly targeted. Summary of the Invention

[0005] The present application provides an urban environmental sanitation management method, system, program product and storage medium based on the Internet of Things, which is used to minimize the area where complex calculations need to be performed, reduce unnecessary calculations from the source, and improve the targetedness and flexibility of management.

[0006] In the first aspect, the present application provides an urban environmental sanitation management method based on the Internet of Things, including: obtaining the time to be cleaned of the target area by interacting with sanitation vehicle information; judging whether the time to be cleaned is greater than an interval threshold; if the time to be cleaned is greater than the interval threshold, obtaining a historical cleaning target mark sequence of the target area; calculating the spatiotemporal entropy value of the historical cleaning target mark sequence; when the spatiotemporal entropy value is less than a first preset threshold, determining that the target area has periodic pollution characteristics, and assigning a cleaning target mark in the next cycle; when the spatiotemporal entropy value is not less than the first preset threshold, obtaining a monitoring image of the target area during the time to be cleaned, and extracting activity features from the monitoring image; and integrating the activity features with the historical activity feature vector set. Calculate the similarity; and determine whether the similarity between the activity feature and the historical activity feature that causes the clean target mark to be assigned in the historical activity feature vector set is greater than a second preset threshold; if it is greater than the second preset threshold, assign the clean target mark; if it is not greater than the second preset threshold, extract the number of people and the corresponding appearance time from the monitoring image; calculate the person pollution degree based on the number of people and the appearance time; obtain the weather conditions of the target area during the time to be cleaned; multiply the pollution coefficient corresponding to the weather conditions by the person pollution degree, and add the product of the basic pollution parameter corresponding to the weather conditions and the time to be cleaned to obtain the comprehensive pollution degree; determine whether the comprehensive pollution degree is greater than a third preset threshold; if it is greater than the third preset threshold, assign the clean target mark.

[0007] Using this technical solution, the target area's cleaning time is first determined by interacting with sanitation vehicles. For areas with a shorter cleaning time, it's preliminarily determined that they don't require immediate cleaning. Therefore, some areas that don't require cleaning are quickly eliminated, avoiding wasted computing resources. Furthermore, the system analyzes the spatiotemporal entropy of historical cleaning target marker sequences to uncover historical patterns in regional pollution. If the spatiotemporal entropy value falls below a first preset threshold, it indicates that the area exhibits periodic pollution. Based on past patterns, the area can be assigned a cleaning target marker for the next cycle. If the spatiotemporal entropy value is at least the threshold, further investigation is conducted to determine whether the current activities in the target area are similar to those known to require cleaning. If so, it is inferred that the area requires cleaning. If not, the comprehensive pollution level is calculated. This calculation not only considers the pollution level of people but also incorporates the impact of weather conditions on their pollution level, as well as the direct impact of weather conditions themselves, ensuring that the results more accurately reflect the actual pollution situation in the area. Therefore, the area requiring complex calculations is minimized to the greatest extent, reducing unnecessary calculations at the source, while improving the targetedness and flexibility of management.

[0008] In combination with some embodiments of the first aspect, in some embodiments, after the step of obtaining a comprehensive pollution degree by multiplying the pollution coefficient corresponding to the weather conditions by the pollution degree of the people, and adding the product of the basic pollution parameter corresponding to the weather conditions and the time to be cleaned, the method also includes: obtaining a set of adjacent areas of the target area; obtaining the wind direction and wind speed of each adjacent area in the adjacent area set; determining the affected area according to the wind direction and the orientation of each adjacent area in the adjacent area set and the target area; calculating the migration coefficient of the affected area to the target area according to the wind direction and wind speed, wherein: obtaining the position relationship parameter between the affected area and the target area; calculating the wind direction influence factor based on the wind direction; calculating the wind speed influence factor based on the wind speed; multiplying the position relationship parameter, the wind direction influence factor and the wind speed influence factor to obtain the pollutant migration coefficient; multiplying the comprehensive pollution degree of the affected area by the corresponding pollutant migration coefficient to obtain the pollution contribution value of each affected area to the target area; and updating the comprehensive pollution degree of the target area using the pollution contribution value.

[0009] By employing the above technical solution, a set of neighboring regions of a target area is first obtained, defining the scope of surrounding areas that have a correlational impact on the target area. Next, the wind direction and wind speed of each neighboring region in the set are obtained. Wind direction determines the potential direction of pollutant transmission, while wind speed affects the speed and intensity of transmission. The impact region is then determined based on the wind direction and the orientation of each neighboring region in the set relative to the target area, pinpointing which neighboring regions' pollutants may be impacting the target area. Based on this, positional relationship parameters, wind direction influence factors, and wind speed influence factors are further calculated and multiplied together to obtain pollutant migration coefficients. This quantifies the extent to which neighboring regions influence pollutant migration in the target area under different orientations, wind directions, and wind speeds. The comprehensive pollution level of the impacted region is then multiplied by the corresponding pollutant migration coefficient to obtain the pollution contribution value of each impacted region to the target area, thereby measuring the specific contribution of each neighboring region to the pollution situation in the target area. Finally, the pollution contribution value is used to update the comprehensive pollution level of the target area. This ensures that the comprehensive pollution level of the target area no longer relies solely on its own situation but fully considers the influence of surrounding related areas, making the comprehensive pollution level of the target area more realistic.

[0010] In combination with some embodiments of the first aspect, in some embodiments, before the step of multiplying the comprehensive pollution degree of the affected area with the corresponding pollutant migration coefficient to obtain the pollution contribution value of each affected area to the target area, the step also includes: the comprehensive pollution degree of the affected area whose time to be cleaned is greater than the interval threshold is regarded as a null value; the comprehensive pollution degree of the affected area whose spatiotemporal entropy value is less than the first preset threshold is regarded as the third preset threshold multiplied by the quotient of the corresponding time to be cleaned and the corresponding cycle time; the comprehensive pollution degree of the affected area whose similarity is greater than the second preset threshold is regarded as the third preset threshold.

[0011] By adopting the above technical solution, we take into account the reality that in actual urban environmental sanitation management, different areas may not all have complete comprehensive pollution data due to their own unique circumstances and past experiences. Therefore, we have developed specific assignment rules to address this. For impact areas with a time to clean greater than the interval threshold, their comprehensive pollution level is treated as null. This is because such areas may not have yet reached the stage where detailed pollution assessment is required, preventing illicit data from interfering with subsequent calculations. For impact areas with spatiotemporal entropy values ​​less than the first preset threshold, their comprehensive pollution level is treated as the quotient of the third preset threshold multiplied by the corresponding time to clean divided by the corresponding cycle time. This is based on the characteristics of these areas with periodic pollution characteristics, and appropriate temporary data reflecting the actual pollution level is assigned to them through a reasonable calculation method to facilitate subsequent unified analysis and processing. For impact areas with a similarity greater than the second preset threshold, their comprehensive pollution level is treated as the third preset threshold. This is because the ongoing activities are similar to those known to require cleaning, indicating that the impact area is inevitably generating significant pollution. This ensures that the calculation of pollution contribution values ​​from each impact area to the target area and the update of the comprehensive pollution level can be carried out smoothly, maintaining the coherence of the entire environmental sanitation management plan based on regional interaction analysis.

[0012] In combination with some embodiments of the first aspect, in some embodiments, after the step of updating the comprehensive pollution degree of the target area using the pollution contribution value, the method also includes: determining the affected area based on the wind direction and the orientation of each adjacent area in the adjacent area set to the target area; calculating the migration coefficient of each adjacent target area when the target area is used as a pollution source based on the wind direction and wind speed, wherein: obtaining the position relationship parameters of the target area and each adjacent target area; calculating the wind direction influence factor based on the wind direction; calculating the wind speed influence factor based on the wind speed; multiplying the position relationship parameters, wind direction influence factor and wind speed influence factor to obtain the pollutant migration coefficient; multiplying the comprehensive pollution degree of the target area with the corresponding pollutant migration coefficient to obtain the pollution contribution value of the target area to the affected area; and updating the comprehensive pollution degree of the target area using the pollution contribution value.

[0013] By employing this technical solution, the affected areas are determined based on wind direction and the orientation of each adjacent area in the adjacent area set relative to the target area. This step identifies the surrounding areas that the target area, as a pollution source, may affect, broadening the analysis perspective beyond the target area's impact on other areas. By fully considering the fact that regions not only receive but also export pollutants, the entire sanitation management plan can more comprehensively and realistically reflect the complex environmental health interactions between regions, thereby generating more accurate comprehensive pollution data.

[0014] In combination with some embodiments of the first aspect, in some embodiments, after the step of calculating the similarity between the activity feature and the historical activity feature vector set, the method also includes: when the similarity between the activity feature and the historical activity feature in the historical activity feature vector set that does not cause the cleaning target mark to be assigned is greater than a second preset threshold, obtaining the historical end time of the historical activity feature that does not cause the cleaning target mark to be assigned; judging whether the average difference between the historical cleaning time and the historical end time in the historical cleaning target mark sequence is greater than a fourth threshold; if the average difference is not greater than the fourth threshold, assigning the cleaning target mark.

[0015] By adopting the above technical solution, when the similarity between the activity feature and the historical activity feature in the historical activity feature vector set that does not cause the assignment of the cleaning target mark is greater than the second preset threshold, it means that this activity feature will not generate garbage that needs to be directly cleaned. At this time, the historical end time of the historical activity feature that does not cause the assignment of the cleaning target mark is obtained. This historical end time can reflect the actual sanitation maintenance of the area after the previous such activity ended. Then, the average difference between the historical cleaning time and the historical end time in the historical cleaning target mark sequence is determined. By comparing the data difference of these two time dimensions, the time interval pattern between the end of similar activities and the next cleaning of the area can be further analyzed. If the average difference obtained is not greater than the fourth threshold, this situation indicates that although the amount of garbage generated in the current area is not small, it has not yet reached the level that requires immediate direct cleaning. In order to further reduce the amount of calculation and avoid falling into unnecessary complex calculation processes, the comprehensive pollution degree is no longer calculated at this time. Instead, the cleaning target mark is directly assigned based on key information such as the time interval pattern obtained by the previous analysis.

[0016] In combination with some embodiments of the first aspect, in some embodiments, after the step of determining the average difference between the historical cleaning time and the historical end time in the historical cleaning target mark sequence, the method further includes: if the average difference is greater than a fourth threshold, determining whether the time to be cleaned is greater than the average difference; if it is greater than the average difference, executing the step of extracting the number of people and the corresponding appearance time from the monitoring image; if it is not greater than the average difference, ending the hygiene management of the target area.

[0017] By adopting the above technical solution, if the average difference is greater than the fourth threshold, the situation corresponding to the activity feature is judged to have a relatively small amount of garbage generated, and it is further judged whether the time to be cleaned is greater than the average difference. If the time to be cleaned is greater than the average difference, it means that although the amount of garbage generated by the activity feature is small at present, as time goes by, a long time has passed from the current time node to the last cleaning or related reference time. In this case, in order to ensure the accuracy of the judgment of the cleaning needs of the area and avoid the omission of situations such as garbage accumulation due to too long a time, it is still necessary to continue in-depth analysis according to the established process, and potential cleaning needs cannot be easily ignored. If the time to be cleaned is not greater than the average difference, this shows that not only the amount of garbage generated by the current activity feature is small, but also from the time dimension, it has not been too long since the last relevant reference time. The sanitary condition of the area is still relatively good at this stage and does not require immediate cleaning. Therefore, at this time, we directly choose to abandon the subsequent complex analysis process. This approach can, on the one hand, further reduce unnecessary computing power and avoid wasting too much computing resources and management energy in areas that obviously do not need to be cleaned temporarily; on the other hand, it also improves the overall accuracy of cleaning demand judgment, making the entire urban environmental sanitation management process more in line with actual conditions.

[0018] In combination with some embodiments of the first aspect, in some embodiments, activity characteristics include: time characteristics, spatial characteristics and crowd characteristics; time characteristics include start time, end time, periodicity and duration; spatial characteristics include activity location and coverage; crowd characteristics include crowd density, mobility and length of stay.

[0019] By adopting the above technical solution, the activity characteristics are refined into several key dimensions including time characteristics, spatial characteristics and population characteristics, which describe the actual activity situation in the area from different angles and in an all-round way. The characteristics of each dimension cooperate and complement each other, making the entire sanitation management judgment process more reasonable and effectively improving the accuracy of the judgment.

[0020] In the second aspect, the present application provides an urban environmental sanitation management system based on the Internet of Things, which includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and one or more processors call the computer instructions to enable the urban environmental sanitation management system based on the Internet of Things to execute the method described in the first aspect and any possible implementation method of the first aspect.

[0021] In a third aspect, the present application provides a computer program product comprising instructions, which, when run on an urban environmental sanitation management system based on the Internet of Things, enables the urban environmental sanitation management system based on the Internet of Things to execute the method described in the first aspect and any possible implementation method of the first aspect.

[0022] In a fourth aspect, the present application provides a computer-readable storage medium comprising instructions, which, when executed on an urban environmental sanitation management system based on the Internet of Things, enables the urban environmental sanitation management system based on the Internet of Things to execute the method described in the first aspect and any possible implementation of the first aspect.

[0023] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages: First, the system uses information exchange with sanitation vehicles to determine the target area's cleaning time. For areas with a shorter cleaning time, it's preliminarily determined that they don't require immediate cleaning. Therefore, some areas that don't require cleaning are quickly eliminated to avoid wasting computing resources. Furthermore, the system analyzes the spatiotemporal entropy of historical cleaning target marker sequences to uncover historical patterns of regional pollution. If the spatiotemporal entropy value falls below a first preset threshold, it indicates that the area exhibits periodic pollution. Based on past patterns, the system assigns a cleaning target marker for the next cycle. If the spatiotemporal entropy value is at least the threshold, the system further examines whether the activities currently underway in the target area are similar to those known to require cleaning. If so, it infers that the area requires cleaning. If not, it calculates the comprehensive pollution level. This calculation not only considers the pollution level of individuals but also incorporates the impact of weather conditions on their pollution level, as well as the direct impact of weather conditions themselves, ensuring that the results more accurately reflect the actual pollution situation in the area. Therefore, the area requiring complex calculations is minimized to the greatest extent, reducing unnecessary calculations at the source, while improving the targetedness and flexibility of management.

[0024] 2. Considering the reality that in actual urban environmental sanitation management, different areas may not all have complete comprehensive pollution level data due to their own unique circumstances and past experiences, specific assignment rules have been developed. For impact areas with a time to clean greater than the interval threshold, their comprehensive pollution level is considered null. This is because such areas may not have yet reached the stage where detailed pollution level assessment is required, preventing undesirable data from interfering with subsequent calculations. For impact areas with spatiotemporal entropy values ​​less than the first preset threshold, their comprehensive pollution level is calculated as the quotient of the third preset threshold multiplied by the corresponding time to clean divided by the corresponding cycle time. This is based on the characteristics of these areas with periodic pollution patterns, and appropriate temporary data reflecting the actual pollution level is assigned to them through a reasonable calculation method to facilitate subsequent unified analysis and processing. For impact areas with a similarity greater than the second preset threshold, their comprehensive pollution level is considered the third preset threshold. This is because the ongoing activities are similar to those known to require cleaning, indicating that the impact area is inevitably generating significant pollution. This ensures smooth progress in calculating pollution contribution values ​​from each impact area to the target area and updating the comprehensive pollution level, maintaining the coherence of the entire environmental sanitation management plan based on regional interaction analysis.

[0025] 3. If the average difference is greater than the fourth threshold, the situation corresponding to the activity feature is judged to have a relatively small amount of garbage generated, and it is further judged whether the time to be cleaned is greater than the average difference. If the time to be cleaned is greater than the average difference, it means that although the amount of garbage generated by the activity feature is small at present, as time goes by, a long time has passed from the current time node to the last cleaning or related reference time. In this case, in order to ensure the accuracy of the judgment of the cleaning needs of the area and avoid the omission of situations such as garbage accumulation due to too long a time, it is still necessary to continue in-depth analysis according to the established process, and potential cleaning needs cannot be easily ignored. If the time to be cleaned is not greater than the average difference, this shows that not only the amount of garbage generated by the current activity feature is small, but also from the time dimension, it has not been too long since the last relevant reference time. The sanitary conditions of the area are still relatively good at this stage and do not require immediate cleaning. Therefore, at this time, we directly choose to abandon the subsequent complex analysis process. This approach can, on the one hand, further reduce unnecessary computing power and avoid wasting too much computing resources and management energy in areas that obviously do not need to be cleaned temporarily; on the other hand, it also improves the overall accuracy of cleaning demand judgment, making the entire urban environmental sanitation management process more in line with actual conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 This is a flow chart of the urban environmental sanitation management method based on the Internet of Things in an embodiment of the present application; Figure 2This is another flowchart of the urban environmental sanitation management method based on the Internet of Things in an embodiment of the present application; Figure 3 yes Figure 2 Supplementary flow chart of Figure 4 This is another flowchart of the urban environmental sanitation management method based on the Internet of Things in an embodiment of the present application; Figure 5 This is an exemplary hardware structure diagram of an urban environmental sanitation management system based on the Internet of Things in an embodiment of the present application. DETAILED DESCRIPTION

[0027] The terms used in the following examples of the present application are for the purpose of describing specific embodiments only and are not intended to limit the present application. As used in the specification and appended claims of the present application, the singular expressions "a," "an," "said," "above," "the," and "this" are intended to include plural expressions as well, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used in the present application refers to and encompasses any or all possible combinations of one or more of the listed items.

[0028] In the following, the terms "first" and "second" are used for descriptive purposes only and should not be understood to imply or suggest relative importance or implicitly indicate the number of the technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the embodiments of this application, unless otherwise specified, "plurality" means two or more.

[0029] See also Figure 1 , Figure 1 This is a flow chart of the urban environmental sanitation management method based on the Internet of Things in an embodiment of the present application; S101. Obtaining the cleaning time of the target area by interacting with sanitation vehicle information; Sanitation vehicles are motor vehicles used specifically for urban sanitation work. Time to Clean represents the time elapsed since the last cleaning operation in the target area.

[0030] It should be noted that in actual urban environmental sanitation management application scenarios, it is often necessary to carry out cleaning needs analysis and management work in many areas at the same time. However, in order to facilitate the clear explanation of the relevant processes and principles, the target area is used as an example here for explanation.

[0031] Specifically, the time node when the target area was last cleaned is extracted by using corresponding information interaction means, and then combined with the current time information, the difference between the two is calculated to obtain the time to be cleaned of the target area.

[0032] In some specific embodiments, one can first obtain access to the management system for sanitation vehicles. This management system typically records detailed information such as the work schedule for each vehicle. Next, the cleaning list corresponding to the target area is searched. The cleaning list clearly indicates the specific time each cleaning operation was completed in that area. Based on these records, the target area's last cleaning time can be determined, and the remaining cleaning time can be calculated. This is not limited here.

[0033] In some specific embodiments, the specific time when the target area was last cleaned is obtained by communicating with the staff on the sanitation vehicle, and then the time to be cleaned is calculated based on the current time. This is not limited here.

[0034] In some specific embodiments, the last cleaning time of a target area is determined by analyzing the trajectory of a sanitation vehicle. This is because the trajectory of a sanitation vehicle during cleaning operations is significantly different from that of a normal vehicle or a vehicle in a non-cleaning state. This can be used to determine the time point when the vehicle began cleaning the target area. This is not a limitation here.

[0035] S102, determining whether the cleaning time is greater than the interval threshold; Specifically, the previously obtained cleaning time of the target area is compared with the pre-set interval threshold to determine whether the cleaning time exceeds the established standard limit, and then determine whether a subsequent more in-depth cleaning needs analysis is needed for the area.

[0036] If the calculated time to clean is less than the interval threshold, further analysis of the target area's current cleaning needs can be terminated. This is because the time to clean within the interval threshold means that the area has not been cleaned for a long time and does not currently require cleaning. Therefore, it can be quickly excluded from the current focus and in-depth cleaning needs analysis.

[0037] S103: If the time to be cleaned is greater than the interval threshold, a historical cleaning target mark sequence of the target area is obtained; The historical cleaning target mark sequence refers to the historical cleaning time recorded during multiple cleaning operations on the target area in the past.

[0038] It should be noted that the information exchange with the sanitation vehicle in step S101 can be used to obtain the last cleaning time of the target area. In view of this, in actual operation, the cleaning time data obtained each time can be saved and classified according to key information such as area identification to obtain a historical cleaning target mark sequence.

[0039] S104, calculating the spatiotemporal entropy value of the historical clean target mark sequence; Among them, the spatiotemporal entropy value is used to measure the degree of disorder or regularity presented by this set of time data.

[0040] In some embodiments, the time intervals between adjacent time points are calculated to form a set of time interval data (taking into account the convenience of subsequent frequency calculation, the time intervals within the range can be processed in a certain way, such as rounding each time interval value, or retaining only the first few significant digits, or directly rounding to a suitable precision). The frequency of occurrence of each time interval value is counted, and the frequency of each time interval value in the entire sequence is calculated, that is, the frequency of occurrence of the time interval value is divided by the total number of time intervals to obtain the frequency distribution of the time interval. The information entropy calculation formula is used to calculate the spatiotemporal entropy value. For example, according to the Shannon entropy formula, the calculated frequency of each time interval value is substituted into the formula, and the traversal and summation calculation is performed to finally obtain the spatiotemporal entropy value of the target area based on this set of historical cleaning time data.

[0041] The size of this spatiotemporal entropy value can be used to determine whether there is a pattern in the cleaning time. If the entropy value is small, it means that the time intervals are relatively concentrated and the pattern is obvious; if the entropy value is large, it means that the time intervals are relatively dispersed and the pattern is not obvious.

[0042] S105: When the spatiotemporal entropy value is less than a first preset threshold, the target area is determined to have periodic pollution characteristics, and a clean target mark is assigned in the next cycle; The "cycle" is the average of historical cleaning intervals, and a periodic contamination pattern refers to the recurrence of contamination in a target area over a specific period. Cleaning target markers are used to encourage personnel and vehicles to clean target areas, or to incorporate cleaning target markers into cleaning tasks.

[0043] S106. When the spatiotemporal entropy value is not less than a first preset threshold, obtaining a monitoring image of the target area during the cleaning time, and extracting activity features from the monitoring image; Activity characteristics specifically refer to various activities that are currently taking place or have taken place in the target area, such as setting up stalls, picnics, etc.

[0044] In some embodiments, a deep learning-based behavior recognition algorithm model is integrated. Large amounts of annotated image data of various activities (including annotations covering activity types, key behavioral characteristics, and other information) are collected in advance. This data is used to train the behavior recognition model, enabling it to accurately identify different behavioral activities within surveillance images. Upon receiving surveillance images of the target area, the image data is input into the trained behavior recognition model. The model analyzes and identifies the postures, movements, and relationships between people and objects in the image, and outputs the corresponding activity type. This is not a limitation.

[0045] In some embodiments, it can be reflected in the form of data, for example, activity characteristics include: time characteristics, spatial characteristics and crowd characteristics; time characteristics include start time, end time, periodicity and duration; spatial characteristics include activity location and coverage; crowd characteristics include crowd density, mobility and length of stay.

[0046] It can be seen that breaking down activity characteristics into several key dimensions, including time characteristics, spatial characteristics, and population characteristics, describes the actual activity situation in the area from different angles and in an all-round way. The characteristics of each dimension cooperate and complement each other, making the entire sanitation management judgment process more reasonable and effectively improving the accuracy of the judgment.

[0047] S107, calculating the similarity between the activity feature and the historical activity feature vector set; and determining whether the similarity between the activity feature and the historical activity feature in the historical activity feature vector set that causes the cleaning target to be marked is greater than a second preset threshold; Among them, the historical activity feature vector set refers to a set that has been collected and sorted in the past, covering various activity features that have appeared in the target area and similar areas, and is organized according to a certain data structure.

[0048] Continuing with the previous example, after determining the current activity type, the set of historical activity feature vectors is traversed. For each historical activity feature vector, if the corresponding activity type is exactly the same as the current activity type, for example, both are street stalls, then the similarity between them is determined to be 1. Conversely, if the activity types are different, such as the current activity is street stalls and the historical record is picnics, the similarity is 0.

[0049] Continuing with the previous example, the activity characteristics are expressed in data form and the following calculations are performed: (1) Calculate time overlap: Get the intersection of the time intervals of the two activities as the overlapping time; Get the union of the time intervals of the two activities as the total time range; The time overlap ratio is obtained by calculating the ratio of the overlap time to the total time range; (2) Calculate the duration difference rate: Calculate the difference between the duration of two activities; Divide the difference by the larger duration to get the difference rate; (3) The temporal feature similarity is equal to the weighted sum of the overlap ratio and the duration difference ratio; Spatial feature similarity calculation method: (1) Calculate the location distance similarity: Calculate the straight-line distance between two activities based on their coordinates; Convert distance to similarity: normalize by subtracting the actual distance from the preset maximum allowed distance; (2) Calculate coverage difference: Calculate the difference between the coverage of two activities; Divide the difference by the larger coverage area to get the difference rate; (3) Spatial feature similarity is equal to the weighted sum of location similarity and coverage difference rate; Method for calculating similarity of population characteristics: (1) Calculate the population density difference rate: Calculate the difference between the two activity population densities; Divide the difference by the larger density value to get the difference rate; (2) Calculation of liquidity differential rate: Calculate the difference between the two activity liquidity coefficients; Divide the difference by the larger liquidity value to get the difference rate; (3) Calculate the dwell time difference rate: Calculate the difference between the average dwell times of two activities; Divide the difference by the longer dwell time to get the difference rate; (4) The similarity of population characteristics is equal to the complement of the weighted sum of the three difference rates; Comprehensive similarity calculation method: The temporal feature similarity, spatial feature similarity and population feature similarity are weighted and summed according to the preset weights to obtain the final comprehensive similarity score.

[0050] S108, if it is greater than a second preset threshold, assigning a cleaning target mark; S109: If the number is not greater than a second preset threshold, extract the number of people and the corresponding appearance time from the surveillance image; In some embodiments, an image segmentation algorithm can be used to separate the human area from the background area in the image. The number of segmented human areas can then be counted one by one to determine the number of people. The corresponding appearance time can then be determined based on the image capture time, generating data related to the number of people and appearance time. This data can be integrated into a specialized data structure, such as a two-dimensional array, where one row of data represents the number of people and appearance time at a specific point in time.

[0051] S110, calculating the pollution degree of the characters based on the number of people and appearance time; Among them, the human pollution degree is a quantitative indicator that comprehensively considers the impact of human activities on the environmental sanitation of the target area. It is obtained by performing specific mathematical operations on factors such as the extracted number of people and the corresponding appearance time. The higher the value, the greater the pollution impact of human activities on the area, and the lower the value, the smaller the relative pollution impact.

[0052] In some embodiments, the character pollution degree is the number of people multiplied by the corresponding appearance time.

[0053] S111. Obtaining weather conditions in the target area during the cleaning period; Among them, weather conditions refer to the meteorological conditions present in the target area during the cleaning time, such as weather type (such as sunny, rainy, snowy, etc.).

[0054] In some embodiments, the management system will connect with the meteorological department's professional meteorological data interface, or call a third-party meteorological data service that has been connected, and obtain the corresponding weather condition data of the area during the cleaning time according to the geographic location information of the target area, in preparation for the subsequent calculation of the comprehensive pollution degree.

[0055] S112, obtaining a comprehensive pollution degree by multiplying the pollution coefficient corresponding to the weather condition by the pollution degree of the person, and adding the product of the basic pollution parameter corresponding to the weather condition and the time to be cleaned; Specifically, the pollution coefficient and basic pollution parameter values ​​corresponding to the current weather conditions will be found from the pre-configured table of correspondence between weather conditions, pollution coefficients, and basic pollution parameters. Then, according to the established calculation formula (multiplying the pollution coefficient corresponding to the weather conditions by the pollution level of the people, and then multiplying the basic pollution parameter corresponding to the weather conditions by the time to be cleaned), the relevant values ​​will be substituted into the calculation to finally obtain the comprehensive pollution level value of the target area.

[0056] It's important to note that weather conditions can affect the degree of pollution caused by people's daily activities. For example, on rainy days, rainwater wets the ground and any garbage stored outdoors, making the existing garbage even more messy and increasing its impact on the environment, leading to a corresponding increase in human pollution. Furthermore, weather conditions themselves can introduce new garbage. For example, on a rainy day, the scouring effect of rainwater can wash debris previously accumulated on rooftops, in ditches, and elsewhere onto the ground, creating new garbage and adding a new cleaning burden to the regional environment.

[0057] S113, determining whether the comprehensive pollution level is greater than a third preset threshold; S114: If the value is greater than a third preset threshold, assign a cleaning target mark.

[0058] As can be seen, the system first uses information exchange with sanitation vehicles to determine the target area's cleaning time. For areas with a shorter cleaning time, it is initially determined that they do not require immediate cleaning. Therefore, some areas that do not require cleaning are quickly eliminated to avoid wasting computing resources. Furthermore, the system further analyzes the spatiotemporal entropy of historical cleaning target marker sequences to uncover historical patterns in regional pollution. If the spatiotemporal entropy value is found to be below a first preset threshold, it indicates that the area exhibits periodic pollution. Based on past patterns, the system can then assign a cleaning target marker for the next period. If the spatiotemporal entropy value is above the first preset threshold, further investigation is required to determine whether the activities currently underway in the target area are similar to those known to require cleaning. If so, it is inferred that the area requires cleaning. If not, the comprehensive pollution level is calculated. This calculation not only considers the pollution level of people but also incorporates the impact of weather conditions on their pollution level, as well as the direct impact of weather conditions themselves, ensuring that the results more accurately reflect the actual pollution situation in the area. Therefore, the area requiring complex calculations is minimized to the greatest extent, reducing unnecessary calculations at the source, while improving the targetedness and flexibility of management.

[0059] The above embodiment reduces unnecessary computational complexity and improves management relevance and flexibility. However, when calculating the comprehensive pollution level, the target area is calculated as an independent area. However, in actual use, the target area is not independent.

[0060] See also Figure 2 , Figure 2 This is another flowchart of the urban environmental sanitation management method based on the Internet of Things in an embodiment of the present application; Therefore, in some embodiments, after step S112, the method further includes: S201, obtaining a set of adjacent areas of a target area; Among them, the adjacent area set refers to a set of areas that are directly adjacent to or very close to the target area in geographical space and may have mutual influence on environmental factors (such as pollutant diffusion).

[0061] Since the target area doesn't exist independently in reality and is influenced by surrounding areas, a set of adjacent areas must be obtained. Specifically, this is done using a pre-defined geographic information database that details the geographic boundaries and location relationships of each area. Based on the target area's geographic boundary information, the system searches and filters the database to identify all areas spatially adjacent to the target area. These areas are then consolidated into a set to facilitate further analysis and processing of the relevant information about these adjacent areas.

[0062] S202, obtaining the wind direction and wind speed of each adjacent area in the adjacent area set; Specifically, the system establishes a connection with a meteorological monitoring device or a meteorological data service provider. For each adjacent area in the set of adjacent areas, the management system sends a data request to the corresponding meteorological monitoring device based on its geographic location, or queries the meteorological data service provider's database for the current wind direction and speed data for that area. The system then records this data for subsequent use in operations such as determining the impact area and calculating migration coefficients.

[0063] S203, determining the affected area according to the wind direction and the orientation of each adjacent area in the adjacent area set and the target area; In some embodiments, an azimuth coordinate system centered on the target area is established, and the position information of each adjacent area in the set of adjacent areas is converted into this coordinate system. The wind direction vector direction of each adjacent area is determined based on the wind direction information. By comparing the wind direction vector direction of the adjacent area with the azimuth vector direction of the adjacent area relative to the target area, if the wind direction vector direction points to the azimuth range of the target area, the adjacent area is determined to be an affected area.

[0064] S204. Calculate the migration coefficient of the impact area to the target area based on the wind direction and wind speed; Among them, the migration coefficient is used to quantify the possibility of pollutants in the impact area migrating to the target area.

[0065] S2041. Obtain positional relationship parameters between the impact area and the target area; The position relationship parameter represents a quantitative indicator of the specific position relationship between the impact area and the target area in geographic space, such as the distance between the two.

[0066] S2042. Calculate wind direction influence factor based on wind direction; In some embodiments, the direction of the line connecting the impact area and the target area is determined as a reference direction. The angle between the wind direction and the reference direction is calculated. Based on the magnitude of the angle, a wind direction influence factor is calculated using a preset function (e.g., a linear function, a piecewise function, etc.). For example, the smaller the angle, the greater the wind direction influence factor.

[0067] S2043. Calculate wind speed impact factor based on wind speed; In some embodiments, the wind speed impact factor is calculated using a mathematical model or empirical formula based on wind speed and the propagation characteristics of pollutants at different wind speeds. Generally speaking, the greater the wind speed, the faster the pollutants spread, the wider the spread, the greater the potential impact on the target area, and the larger the wind speed impact factor. Conversely, the lower the wind speed, the smaller the wind speed impact factor.

[0068] S2044. Multiply the position relationship parameter, the wind direction influence factor, and the wind speed influence factor to obtain a pollutant migration coefficient; S205. Multiply the comprehensive pollution degree of the affected area by the corresponding pollutant migration coefficient to obtain the pollution contribution value of each affected area to the target area; It should be noted that in the entire process covered by steps S101 to S114, there is a situation where the target area only generates comprehensive pollution level data in the embodiment of steps S109 to S114. However, in the process of steps S101 to S108, the target area does not yet have comprehensive pollution level data.

[0069] See also Figure 3 , Figure 3 yes Figure 2 Supplementary flow chart of Therefore, in some embodiments, before step S205, the method further includes: S301: The comprehensive contamination degree of the affected area where the cleaning time is greater than the interval threshold is considered as a null value; Specifically, for those affected areas whose cleaning time is greater than the interval threshold, these areas may have just exceeded the time limit of the initial judgment, but have not yet entered the detailed stage of fully considering their pollution level. More information or further analysis may be needed to determine their comprehensive pollution level. If an inaccurate value is rashly assigned, it will interfere with subsequent operations such as calculating the pollution contribution value to the target area based on the comprehensive pollution level of each affected area. Therefore, the comprehensive pollution level of such affected areas is regarded as a null value, so that they can be identified as areas whose actual pollution level has not yet been determined in subsequent related processes, waiting for more appropriate subsequent processing or calculation to improve this data.

[0070] S302: The comprehensive contamination degree of the affected area whose spatiotemporal entropy value is less than the first preset threshold is regarded as the quotient of the third preset threshold multiplied by the corresponding cleaning time and the corresponding cycle time; For those affected areas whose spatiotemporal entropy values ​​are less than the first preset threshold after analysis, it means that they have periodic pollution characteristics. However, since it is still in the early process stage, the complete comprehensive pollution degree calculation process may not have been carried out yet. In order to be able to give such areas with special rules a relatively reasonable temporary data that can reflect their actual pollution level in subsequent unified analysis of the impact of each affected area on the target area, this calculation method is used to determine their comprehensive pollution level. Specifically, according to the time to be cleaned and the corresponding cycle time of the area, the comprehensive pollution level is calculated by multiplying the third preset threshold by the quotient of the corresponding time to be cleaned and the corresponding cycle time. In this way, based on the periodic characteristics of the area and the time from the current time to the last cleaning and other factors, its current pollution level can be roughly measured, which is convenient for subsequent consideration of the pollution contribution of each affected area to the target area.

[0071] S303: The comprehensive pollution degree of the affected area whose similarity is greater than the second preset threshold is regarded as the third preset threshold.

[0072] If the similarity between the activity characteristics of an impact area and the historical activity characteristics that resulted in the clean target labeling in the historical activity feature vectors is greater than the second preset threshold, it means that the activities currently taking place in the area are similar to those known to require cleaning. Based on past experience, it can be inferred that the area is likely to have generated a lot of pollution, and the pollution level is high enough to meet the standard for cleaning. Therefore, in order to ensure the smooth progress of subsequent calculations of the pollution contribution of each impact area to the target area and the update of the target area's comprehensive pollution level, the comprehensive pollution level of such impact areas is treated as the third preset threshold, that is, it is temporarily assigned a value based on the established pollution level standard that reflects the need for cleaning.

[0073] As can be seen, in the actual urban environmental sanitation management, different areas may not all have complete comprehensive pollution data due to their own unique circumstances and past experiences. Therefore, specific assignment rules have been developed to address this reality. For impact areas with a time to clean greater than the interval threshold, their comprehensive pollution level is treated as null. This is because such areas may not have yet entered the stage where detailed pollution assessment is required, preventing illogical data from interfering with subsequent calculations. For impact areas with spatiotemporal entropy values ​​less than the first preset threshold, their comprehensive pollution level is treated as the quotient of the third preset threshold multiplied by the corresponding time to clean divided by the corresponding cycle time. This is based on the characteristics of these areas with periodic pollution characteristics, and appropriate temporary data reflecting the actual pollution level is assigned to them through a reasonable calculation method to facilitate subsequent unified analysis and processing. For impact areas with a similarity greater than the second preset threshold, their comprehensive pollution level is treated as the third preset threshold. This is because the ongoing activities are similar to those known to require cleaning, indicating that the impact area is inevitably generating significant pollution. This ensures that the calculation of pollution contribution values ​​from each impact area to the target area and the update of the comprehensive pollution level can proceed smoothly, maintaining the coherence of the entire environmental sanitation management plan based on regional interaction analysis.

[0074] S206: Update the comprehensive pollution degree of the target area using the pollution contribution value.

[0075] As can be seen, the first step is to obtain a set of neighboring areas of the target area, defining the scope of surrounding areas that have a correlation with the target area. Next, the wind direction and wind speed of each neighboring area in the neighboring area set are obtained. Wind direction determines the possible direction of pollutant transmission, while wind speed affects the speed and intensity of transmission. The impact area is then determined based on the wind direction and the orientation of each neighboring area in the neighboring area set relative to the target area, locating which neighboring areas' pollutants may have an impact on the target area. Based on this, the positional relationship parameters, wind direction influence factors, and wind speed influence factors are further calculated and multiplied to obtain the pollutant migration coefficient. This quantifies the degree of influence of neighboring areas on pollutant migration in the target area under different orientations, wind directions, and wind speeds. The comprehensive pollution level of the impacted area is then multiplied by the corresponding pollutant migration coefficient to obtain the pollution contribution value of each impacted area to the target area, thereby measuring the specific contribution of each neighboring area to the pollution situation in the target area. Finally, the pollution contribution value is used to update the comprehensive pollution level of the target area. This ensures that the comprehensive pollution level of the target area no longer relies solely on its own situation but fully considers the influence of surrounding areas, making the comprehensive pollution level of the target area more realistic.

[0076] In the above embodiment, the comprehensive pollution degree of the target area is no longer solely dependent on its own situation, but the influence of the surrounding related areas is fully considered to make the comprehensive pollution degree of the target area more in line with the actual situation. However, in actual use, the calculation results often have deviations. In fact, the pollution degree of the target area will also be reduced accordingly.

[0077] Therefore, in some embodiments, after step S206, the method further includes: S207, determining the affected area according to the wind direction and the orientation of each adjacent area in the adjacent area set and the target area; It should be noted that the principle and process of this step are similar to those of step S203. For the relevant principle and process, reference may be made to step S203 and no limitation is given here.

[0078] S208. Calculate the migration coefficient of each adjacent target area when the target area is used as a pollution source based on wind direction and wind speed: It should be noted that the principle and process of this step are similar to those of step S204. For the relevant principle and process, reference may be made to step S204 and no limitation is made here.

[0079] S2081. Obtain positional relationship parameters between the target area and each adjacent target area; It should be noted that the principle and process of this step are similar to those of step S2041. For the relevant principles and processes, reference may be made to step S2041 and are not limited here.

[0080] S2082. Calculate wind direction influence factor based on wind direction; It should be noted that the principle and process of this step are similar to those of step S2042. For related principles and processes, please refer to step S2042 and are not limited here.

[0081] S2083. Calculate wind speed impact factor based on wind speed; It should be noted that the principle and process of this step are similar to those of step S2043. For related principles and processes, reference may be made to step S2043 and are not limited here.

[0082] S2084. Multiply the position relationship parameter, the wind direction influence factor, and the wind speed influence factor to obtain a pollutant migration coefficient; It should be noted that the principle and process of this step are similar to those of step S2044. For related principles and processes, reference may be made to step S2044 and are not limited here.

[0083] S209: Multiply the comprehensive pollution degree of the target area by the corresponding pollutant migration coefficient to obtain the pollution contribution value of the target area to the affected area; It should be noted that the principle and process of this step are similar to those of step S205. For the relevant principle and process, reference may be made to step S205 and no limitation is made here.

[0084] S210: Update the comprehensive pollution degree of the target area using the pollution contribution value.

[0085] It should be noted that the principle and process of this step are similar to those of step S206. For the relevant principle and process, reference may be made to step S206 and no limitation is given here.

[0086] Determining the affected area based on wind direction and the orientation of each adjacent area in the set of adjacent areas relative to the target area identifies the surrounding areas that the target area, as a pollution source, may impact. This broadens the analytical perspective, moving beyond the consideration of the impact of other areas on the target area. By fully accounting for the fact that regions not only receive but also export pollutants, the overall sanitation management plan can more comprehensively and realistically reflect the complex environmental health interactions between regions, thereby generating more accurate comprehensive pollution data.

[0087] In actual use, in step S107, it is simply determined whether the similarity between the activity feature and the historical activity feature vector that caused the cleaning target to be assigned is greater than or equal to the second preset threshold. However, other situations are not considered.

[0088] See also Figure 4 , Figure 4 This is another flowchart of the urban environmental sanitation management method based on the Internet of Things in an embodiment of the present application; Therefore, in some embodiments, after step S107, the method further includes: S401: when the similarity between the activity feature and the historical activity feature in the historical activity feature vector set that does not cause the cleaning target mark to be assigned is greater than a second preset threshold, obtaining the historical end time of the historical activity feature that does not cause the cleaning target mark to be assigned; It should be noted that in the process involved in this embodiment, based on the matching of activity features with historical activity features, three different judgment results are generated. First, the activity feature cannot match the historical activity feature. In this case, step S108 will be executed. Second, the activity feature can match the historical activity feature, but the matching historical activity feature is not assigned a cleaning target mark. In this case, step S401 will be executed. Third, the activity feature can also match the historical activity feature, and the matching historical activity feature is assigned a cleaning target mark. In this case, step S409 will be executed.

[0089] Among them, the historical end time refers to the specific time point when the historical activity ends, which can reflect the end of the activity in the time dimension.

[0090] S402: Determine whether the average difference between the historical cleaning time and the historical end time in the historical cleaning target mark sequence is greater than a fourth threshold; By determining the average difference between the historical cleaning time and the historical end time in the historical cleaning target marker sequence, we can gain a deeper understanding of how long it typically takes to clean the area after similar activities. This average difference reflects the area's ability to maintain hygiene under the influence of such activities and the regularity of its cleaning cycles, providing a more scientific basis for subsequent judgments on whether the current area needs cleaning.

[0091] S403: If the average difference is not greater than a fourth threshold, assign a cleaning target mark.

[0092] Specifically, when the average difference is not greater than the fourth threshold, it means that the time interval between the end of similar activities and cleaning of the area is short, which means that the current area may have accumulated a certain amount of garbage. Although it has not reached the level of immediate cleaning, in order to ensure the environmental sanitation of the area, a cleaning target mark is directly assigned at this time to avoid further complex comprehensive pollution calculations and improve the efficiency of cleaning management.

[0093] It can be seen that when the similarity between the activity feature and the historical activity feature in the historical activity feature vector set that does not cause the assignment of the cleaning target mark is greater than the second preset threshold, it means that this activity feature will not generate garbage that needs to be directly cleaned. At this time, the historical end time of the historical activity feature that does not cause the assignment of the cleaning target mark is obtained. This historical end time can reflect the actual sanitation maintenance of the area after the previous such activity ended. Then, the average difference between the historical cleaning time and the historical end time in the historical cleaning target mark sequence is determined. By comparing the data difference of these two time dimensions, the time interval pattern between the end of similar activities and the next cleaning of the area can be further analyzed. If the average difference obtained is not greater than the fourth threshold, this situation indicates that although the amount of garbage generated in the current area is not small, it has not yet reached the level that requires immediate direct cleaning. In order to further reduce the amount of calculation and avoid falling into unnecessary complex calculation processes, the comprehensive pollution degree is no longer calculated at this time. Instead, the cleaning target mark is directly assigned based on the key information such as the time interval pattern obtained from the previous analysis.

[0094] S404: If the average difference is greater than the fourth threshold, determine whether the time to be cleaned is greater than the average difference; If the current activity is similar to past activities that did not result in a cleaning mark, it is known that the time interval between the end of similar activities and cleaning in this area is relatively long. At this time, it is necessary to further combine the current waiting time to clean to comprehensively judge the need for cleaning. Specifically, determining whether the waiting time to clean is greater than the average difference means considering whether the average time interval between the end of similar activities and cleaning is longer, but from the current time dimension, the time since the last cleaning has exceeded this average interval. This can further determine whether the area currently needs cleaning more urgently and provide a basis for subsequent handling decisions.

[0095] S405: If the difference is greater than the average difference, the step of extracting the number of people and the corresponding appearance time from the surveillance image is executed; The previous analysis revealed that although the current activity characteristics originally generated relatively little garbage (because the average difference was greater than the fourth threshold, indicating that cleaning intervals after similar activities were long), the time since the last cleaning has now exceeded this average interval, resulting in a significant time span. It's possible that garbage has accumulated during this period, necessitating a deeper understanding of the impact of human activity in the current area on environmental sanitation. Specifically, extracting the number of people and their corresponding appearance times from surveillance images utilizes surveillance images, a data source that intuitively reflects the actual conditions in the area, to analyze information related to human activity. This is because factors such as the number of people and the regularity of their appearance times can significantly influence the sanitation of the area. This extracted data can then be used to further calculate indicators such as human contamination, allowing for more accurate assessment of cleaning needs.

[0096] S406: If it is not greater than the average difference, then end the health management of the target area.

[0097] When analyzing the similarities between the current activity and past activities that did not result in a clean mark, it was found that not only did the current activity characteristics generate less garbage, but also, from a temporal perspective, not too long had passed since the last relevant reference time. The sanitation condition of the area is still relatively good at this stage and does not require immediate cleaning. Specifically, ending sanitation management in the target area is based on the previous judgment results, avoiding further investment of computing resources and management effort in this area that does not currently require cleaning, reducing unnecessary operational processes, and allowing the entire city's environmental sanitation management work to focus on areas with greater cleaning needs, thereby improving management efficiency. At the same time, it also ensures the accuracy of cleaning needs judgments, making resource allocation more reasonable.

[0098] It can be seen that if the average difference is greater than the fourth threshold, the situation corresponding to the activity feature is judged to have a relatively small amount of garbage generated, and it is further judged whether the time to be cleaned is greater than the average difference. If the time to be cleaned is greater than the average difference, it means that although the amount of garbage generated by the activity feature is small at present, as time goes by, a long time has passed from the current time node to the last cleaning or related reference time. In this case, in order to ensure the accuracy of the judgment of the cleaning needs of the area and avoid the omission of situations such as garbage accumulation due to too long a time, it is still necessary to continue in-depth analysis according to the established process, and potential cleaning needs cannot be easily ignored. If the time to be cleaned is not greater than the average difference, this shows that not only the amount of garbage generated by the current activity feature is small, but also from the time dimension, it has not been too long since the last relevant reference time. The sanitary conditions of the area are still relatively good at this stage and do not require immediate cleaning. Therefore, at this time, we directly choose to abandon the subsequent complex analysis process. This approach can, on the one hand, further reduce unnecessary computing power and avoid wasting too much computing resources and management energy in areas that obviously do not need to be cleaned temporarily; on the other hand, it also improves the overall accuracy of cleaning demand judgment, making the entire urban environmental sanitation management process more in line with actual conditions.

[0099] The following describes an exemplary IoT-based urban environmental sanitation management system provided in an embodiment of the present application. Figure 5 This is a schematic diagram of an exemplary hardware structure of an urban environmental sanitation management system based on the Internet of Things provided in an embodiment of the present application.

[0100] In some embodiments, the urban environmental sanitation management system based on the Internet of Things is a computer device or the urban environmental sanitation management system based on the Internet of Things includes a computer device. The computer device includes a processor, a memory and a network interface connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store data. The network interface of the computer device is used to communicate with other external terminals or servers via a network connection. In some embodiments, the network interface can be a wired network interface, and in some embodiments, the network interface can also be a wireless network interface. When the computer program is executed by the processor, the method in the embodiment of the present application is implemented.

[0101] Those skilled in the art will understand that Figure 5The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0102] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

[0103] As used in the above embodiments, the term “when” may be interpreted to mean “if” or “after” or “in response to determining that” or “in response to detecting that”, depending on the context. Similarly, the phrases “upon determining that” or “if (stated condition or event) is detected” may be interpreted to mean “if determining that” or “in response to determining that” or “upon detecting (stated condition or event)” or “in response to detecting (stated condition or event)”, depending on the context.

[0104] In the above embodiments, all or part of the embodiments can be implemented using software, hardware, firmware, or any combination thereof. When implemented using software, all or part of the embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of this application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, optical fiber, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer, or a data storage device such as a server or data center that integrates one or more available media. The available medium can be magnetic media (e.g., floppy disk, hard disk, tape), optical media (e.g., DVD), or semiconductor media (e.g., solid-state drive).

[0105] Those skilled in the art will appreciate that all or part of the process steps in the above-described method embodiments can be implemented by a computer program instructing the relevant hardware. The program can be stored in a computer-readable storage medium, and when executed, the program can include the process steps in the above-described method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM or random access memory (RAM), magnetic disks, or optical disks.

Claims

1. A method for urban environmental sanitation management based on the Internet of Things, characterized in that: include: By interacting with sanitation vehicle information, the cleaning time of the target area can be obtained; Determine whether the cleaning time is greater than an interval threshold; If the time to be cleaned is greater than the interval threshold, obtaining a historical cleaning target mark sequence of the target area; Calculating the spatiotemporal entropy value of the historical cleaning target mark sequence; When the spatiotemporal entropy value is less than a first preset threshold, the target area is determined to have periodic pollution characteristics, and a cleaning target mark is assigned in the next cycle; When the spatiotemporal entropy value is not less than a first preset threshold, obtaining a monitoring image of the target area during the time to be cleaned, and extracting activity features from the monitoring image; Calculating similarity between the activity feature and the historical activity feature vector set; and determining whether the similarity between the activity feature and the historical activity feature that caused the cleaning target mark to be assigned in the historical activity feature vector set is greater than a second preset threshold; If it is greater than a second preset threshold, a cleaning target mark is assigned; If it is not greater than a second preset threshold, extracting the number of people and the corresponding appearance time from the surveillance image; Calculating character pollution levels based on the number of people and the appearance time; Obtaining the weather conditions of the target area during the cleaning time; The comprehensive pollution degree is obtained by multiplying the pollution coefficient corresponding to the weather condition by the pollution degree of the person, and adding the product of the basic pollution parameter corresponding to the weather condition and the time to be cleaned; Determining whether the comprehensive pollution level is greater than a third preset threshold; If it is greater than the third preset threshold, a cleaning target mark is assigned.

2. The method according to claim 1, characterized in that After the step of obtaining the comprehensive pollution degree by multiplying the pollution coefficient corresponding to the weather condition by the pollution degree of the person, and adding the product of the basic pollution parameter corresponding to the weather condition and the time to be cleaned, the method further includes: Acquire a set of adjacent areas of the target area; Get the wind direction and wind speed of each adjacent area in the adjacent area set; Determine an affected area based on the wind direction and the orientation of each adjacent area in the set of adjacent areas to the target area; Calculating a migration coefficient of the impact area to the target area according to the wind direction and the wind speed, wherein: obtaining positional relationship parameters between the impact area and the target area; Calculating a wind direction influence factor based on the wind direction; calculating a wind speed impact factor based on the wind speed; Multiplying the position relationship parameter, the wind direction influence factor, and the wind speed influence factor to obtain the pollutant migration coefficient; Multiplying the comprehensive pollution degree of the affected area by the corresponding pollutant migration coefficient to obtain the pollution contribution value of each affected area to the target area; The comprehensive pollution degree of the target area is updated using the pollution contribution value.

3. The method according to claim 2, characterized in that Before the step of multiplying the comprehensive pollution degree of the affected area by the corresponding pollutant migration coefficient to obtain the pollution contribution value of each affected area to the target area, the step further includes: The comprehensive contamination degree of the affected area whose time to be cleaned is greater than the interval threshold is considered as a null value; The comprehensive contamination degree of the affected area whose spatiotemporal entropy value is less than the first preset threshold is regarded as the quotient of the third preset threshold multiplied by the corresponding time to be cleaned and the corresponding cycle time; The comprehensive pollution degree of the affected area whose similarity is greater than the second preset threshold is regarded as the third preset threshold.

4. The method according to claim 2, characterized in that After the step of updating the comprehensive pollution degree of the target area using the pollution contribution value, the method further includes: Determining an affected area based on the wind direction and the orientation of each adjacent area in the set of adjacent areas to the target area; The migration coefficient of each of the adjacent target areas when the target area is used as a pollution source is calculated according to the wind direction and the wind speed, wherein: Obtaining positional relationship parameters between the target area and each of the adjacent target areas; Calculating a wind direction influence factor based on the wind direction; calculating a wind speed impact factor based on the wind speed; Multiplying the position relationship parameter, the wind direction influence factor, and the wind speed influence factor to obtain the pollutant migration coefficient; Multiplying the comprehensive pollution degree of the target area by the corresponding pollutant migration coefficient to obtain the pollution contribution value of the target area to the affected area; The comprehensive pollution degree of the target area is updated using the pollution contribution value.

5. The method according to claim 1, wherein After the step of calculating the similarity between the activity feature and the historical activity feature vector set, the method further includes: When the similarity between the activity feature and the historical activity feature that does not cause the cleaning target mark to be assigned in the historical activity feature vector set is greater than the second preset threshold, obtaining the historical end time of the historical activity feature that does not cause the cleaning target mark to be assigned; Determining whether an average difference between a historical cleaning time and a historical end time in a historical cleaning target mark sequence is greater than a fourth threshold; If the average difference is not greater than a fourth threshold, a cleaning target mark is assigned.

6. The method according to claim 5, characterized in that After the step of determining the average difference between the historical cleaning time and the historical end time in the historical cleaning target mark sequence, the method further includes: If the average difference is greater than a fourth threshold, determining whether the time to be cleaned is greater than the average difference; If it is greater than the average difference, executing the step of extracting the number of people and the corresponding appearance time from the surveillance image; If it is not greater than the average difference, the health management of the target area is terminated.

7. The method according to claim 1, characterized in that The activity characteristics include: time characteristics, spatial characteristics and crowd characteristics; the time characteristics include start time, end time, periodicity and duration; the spatial characteristics include activity location and coverage; the crowd characteristics include crowd density, mobility and length of stay.

8. An urban environmental sanitation management system based on the Internet of Things, characterized in that: The urban environmental sanitation management system based on the Internet of Things includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the urban environmental sanitation management system based on the Internet of Things to execute the method described in any one of claims 1 to 7.

9. A computer program product comprising instructions, characterized in that When the computer program product is run on an urban environmental sanitation management system based on the Internet of Things, the urban environmental sanitation management system based on the Internet of Things executes the method according to any one of claims 1 to 7.

10. A computer-readable storage medium comprising instructions, characterized in that: When the instruction is executed on an urban environmental sanitation management system based on the Internet of Things, the urban environmental sanitation management system based on the Internet of Things executes the method according to any one of claims 1 to 7.

Images