CN114048991A - Sewage treatment sludge cleaning and management method and system - Google Patents

Abstract

The invention provides a method and a system for cleaning and managing sewage and sludge, wherein the method comprises the following steps: step S1: acquiring a preset region set, wherein the region set comprises: a plurality of first regions; step S2: acquiring field data of the first area, and determining whether the first area needs to be cleaned by sewage and sludge based on the field data; step S3: if yes, a proper scheduling strategy is made based on the field data; step S4: and scheduling workers to clean the sewage and sludge in the first area based on a scheduling strategy. According to the method and the system for cleaning and managing the sewage and sludge in the sewage treatment, when the first area needs to be cleaned, an appropriate scheduling strategy is formulated based on the corresponding first field data, and the first area is manually scheduled to be cleaned, so that the problems that cleaning cost is increased due to too many arranged cleaning personnel, cleaning efficiency is reduced due to unreasonable task allocation and the like caused by arrangement of professional cleaning personnel according to experience in the prior art can be effectively solved.

Description

Sewage treatment sludge cleaning and management method and system

Technical Field

The invention relates to the technical field of sewage and sludge cleaning and management, in particular to a sewage and sludge cleaning and management method and system.

Background

Sewage and sludge are often generated in urban underground pipelines and need to be cleaned in time, otherwise, pipeline blockage and sludge precipitation can be caused, and hydrogen sulfide gas is generated to cause environmental pollution and other problems;

at present, when sewage and sludge in a pipeline are cleaned, professional cleaning personnel are arranged for cleaning, but how to reasonably arrange the professional cleaning personnel is determined according to experience, so that the problems that the cleaning cost is increased due to too many arranged people, the cleaning efficiency is reduced due to unreasonable task allocation and the like can be caused;

therefore, a solution is needed.

Disclosure of Invention

One of the objectives of the present invention is to provide a method and a system for managing and cleaning sludge in sewage treatment, wherein when a first area needs to be cleaned, an appropriate scheduling policy is formulated based on corresponding first field data, and a scheduling worker performs the cleaning of the sludge in the first area, so as to effectively avoid the problems of cleaning cost increase caused by too many arranged cleaning workers and cleaning efficiency reduction caused by unreasonable task allocation in the conventional arrangement of professional cleaning workers according to experience.

The embodiment of the invention provides a method for cleaning and managing sewage and sludge, which comprises the following steps:

step S1: acquiring a preset region set, wherein the region set comprises: a plurality of first regions;

step S2: acquiring first field data of the first area, and determining whether the first area needs sewage sludge cleaning or not based on the first field data;

step S3: if yes, an appropriate scheduling strategy is made based on the first field data;

step S4: and scheduling the first region to be manually cleaned of sewage and sludge based on the scheduling strategy.

Preferably, in step S2, the acquiring first field data of the first area includes:

acquiring a plurality of first acquisition nodes corresponding to the first area;

acquiring a first field data item through the first acquisition node;

acquiring a first acquisition range corresponding to the first acquisition node;

acquiring a first area site three-dimensional model corresponding to the first area, determining a first coverage area corresponding to the first acquisition range in the first area site three-dimensional model, and corresponding to the first site data item;

extracting at least one first missing region except the coverage region in the sewage region in the first regional field three-dimensional model;

acquiring position information of the first missing area, wherein the position information comprises: a plurality of position markers;

based on a preset position mark-acquisition information base, attempting to determine acquisition information corresponding to any one of the position marks, wherein the acquisition information comprises: the acquisition party, the second acquisition node and the corresponding second acquisition range;

if the determination is successful, acquiring a credit value of the collector, if the credit value is greater than or equal to a preset credit threshold value, determining a second coverage area corresponding to the second collection range in the first area field three-dimensional model, and simultaneously acquiring a second field data item through a corresponding second collection node;

determining a coinciding zone of the first missing region coinciding with the second coverage zone;

taking the remaining area of the first missing area except the overlapping area as a second missing area, and meanwhile, determining a third field data item corresponding to the overlapping area in the second field data item;

if the determination fails, taking the corresponding first missing region as a second missing region;

determining a first field data item and a third field data item which are associated with the first coverage area and the overlapping area adjacent to the second missing area in the first regional field three-dimensional model and are used as fourth field data items;

acquiring a position relation between the first coverage area adjacent to the second missing area and the overlapping area and the second missing area in the first area field three-dimensional model;

acquiring first attribute information of the second missing region;

acquiring a preset field data prediction model, inputting the fourth field data item, the position relation and the attribute information into the field data prediction model, and acquiring a fifth field data item corresponding to the second missing area;

and integrating the first field data item, the third field data item and the fifth field data item to obtain the first field data of the first area, and finishing the acquisition.

Preferably, the step S2, determining whether the first area needs sewage sludge cleaning based on the first field data, includes:

acquiring a preset sewage and sludge cleaning judgment model, inputting the first field data into the sewage and sludge cleaning judgment model, and acquiring a judgment result, wherein the judgment result comprises: need and not;

when the judgment result is that the sewage sludge is needed, the first area needs to be cleaned;

when the determination result is that the sewage sludge is unnecessary, the first area does not need to be cleaned up.

Preferably, in step S3, based on the field data, a suitable scheduling policy is formulated, which includes:

acquiring a preset sewage sludge cleaning event set, wherein the sewage sludge cleaning event set comprises: a plurality of first sewage sludge clearing events;

performing feature analysis and extraction on the first field data to obtain a plurality of first features;

extracting second field data from the first sewage sludge cleanup event;

performing feature analysis and extraction on the second field data to obtain a plurality of second features;

performing feature matching on the first feature and the second feature, if the first feature and the second feature are matched, taking the first feature matched with the first feature as a first target feature, and simultaneously taking the first feature except the first target feature in the first feature as a second target feature and associating the first feature with a corresponding first sewage sludge cleaning event;

acquiring a first price weight corresponding to the first target characteristic, and associating the first price weight with a corresponding first sewage sludge cleaning event;

acquiring second attribute information of the first area;

performing feature analysis and extraction on the second attribute information to obtain a plurality of third features;

extracting third attribute information in the first sewage sludge cleaning event;

performing feature analysis and extraction on the third attribute information to obtain a plurality of fourth features;

performing feature matching on the third feature and the fourth feature, if the matching is matched, taking the matched third feature as a third target feature, and simultaneously taking the third feature except the third target feature in the third feature as a fourth target feature and associating the third feature with the corresponding first sewage sludge cleaning event;

acquiring a second value weight corresponding to the third target characteristic, and associating the second value weight with the first sewage sludge cleaning event;

summarizing the first and second cost value weights associated with the first sewage sludge cleaning event to obtain a first cost value weight sum;

selecting the maximum first price weight sum as a second price weight sum;

if the second value weight sum is larger than or equal to a preset value weight and a threshold value, extracting a first sewage sludge cleaning process corresponding to the first sewage sludge cleaning event;

generating a scheduling strategy based on the first sewage and sludge cleaning process;

otherwise, sorting the first price weight sums from large to small to obtain a value weight sum sequence;

traversing the first value weight sum from the starting point to the end point of the value weight sum sequence;

taking the traversed first value weight sum as a third value weight sum in each traversal;

extracting the third valence weight and a corresponding second sewage-sludge cleaning course in the first sewage-sludge cleaning event;

setting the second target feature and the fourth target feature associated with the first sewage sludge cleaning event as a fifth target feature;

acquiring a preset problem prediction model, inputting the second sewage and sludge cleaning process and the fifth target characteristic into the problem prediction model, and acquiring at least one problem item, wherein the problem item comprises: a question location, a question type, a first question content, and a corresponding first question value;

acquiring a second area site three-dimensional model corresponding to the first area;

performing sewage rendering configuration on the second area on-site three-dimensional model based on the first on-site data, setting a monitoring point at a virtual position corresponding to the problem position in the second area on-site three-dimensional model, giving a monitoring task corresponding to the problem type to the monitoring point, and obtaining a third area on-site three-dimensional model;

acquiring a preset simulation space, inputting the third area field three-dimensional model into the simulation space, and simulating the second sewage and sludge cleaning process;

acquiring monitoring data returned by the monitoring points at regular time, comparing and analyzing the monitoring data and the problem content, determining whether the monitoring data and the problem content are consistent, and if so, taking the corresponding first problem value as a second problem value;

after the simulation is finished, summarizing the second problem value as a problem value sum, and associating the problem value sum with the corresponding second sewage sludge cleaning process;

after traversing is finished, taking the minimum problem value and the associated second sewage sludge cleaning process as a third sewage sludge cleaning process, and simultaneously taking the first problem content corresponding to the minimum problem value and the second problem value obtained in a summary manner as a second problem content;

and acquiring a preset problem solving model, and inputting the third sewage sludge cleaning process and the second problem content into the problem solving model to acquire a scheduling strategy.

Preferably, the method for cleaning and managing sewage sludge further comprises the following steps:

step S5: and dynamically tracking the first area to carry out the sewage sludge cleaning process.

The embodiment of the invention provides a sewage treatment sludge cleaning and management system, which comprises:

an obtaining module, configured to obtain a preset region set, where the region set includes: a plurality of first regions;

the determining module is used for acquiring first field data of the first area and determining whether the first area needs to be cleaned by sewage and sludge or not based on the first field data;

the formulating module is used for formulating a proper scheduling strategy based on the first field data if the first field data exists;

and the scheduling module is used for scheduling manpower to clean the sewage and sludge in the first area based on the scheduling strategy.

Preferably, the determining module performs the following operations:

acquiring a plurality of first acquisition nodes corresponding to the first area;

acquiring a first field data item through the first acquisition node;

acquiring a first acquisition range corresponding to the first acquisition node;

acquiring a first area site three-dimensional model corresponding to the first area, determining a first coverage area corresponding to the first acquisition range in the first area site three-dimensional model, and corresponding to the first site data item;

extracting at least one first missing region except the coverage region in the sewage region in the first regional field three-dimensional model;

acquiring position information of the first missing area, wherein the position information comprises: a plurality of position markers;

based on a preset position mark-acquisition information base, attempting to determine acquisition information corresponding to any one of the position marks, wherein the acquisition information comprises: the acquisition party, the second acquisition node and the corresponding second acquisition range;

if the determination is successful, acquiring a credit value of the collector, if the credit value is greater than or equal to a preset credit threshold value, determining a second coverage area corresponding to the second collection range in the first area field three-dimensional model, and simultaneously acquiring a second field data item through a corresponding second collection node;

determining a coinciding zone of the first missing region coinciding with the second coverage zone;

taking the remaining area of the first missing area except the overlapping area as a second missing area, and meanwhile, determining a third field data item corresponding to the overlapping area in the second field data item;

if the determination fails, taking the corresponding first missing region as a second missing region;

determining a first field data item and a third field data item which are associated with the first coverage area and the overlapping area adjacent to the second missing area in the first regional field three-dimensional model and are used as fourth field data items;

acquiring a position relation between the first coverage area adjacent to the second missing area and the overlapping area and the second missing area in the first area field three-dimensional model;

acquiring first attribute information of the second missing region;

acquiring a preset field data prediction model, inputting the fourth field data item, the position relation and the attribute information into the field data prediction model, and acquiring a fifth field data item corresponding to the second missing area;

and integrating the first field data item, the third field data item and the fifth field data item to obtain the first field data of the first area, and finishing the acquisition.

Preferably, the determining module performs the following operations:

acquiring a preset sewage and sludge cleaning judgment model, inputting the first field data into the sewage and sludge cleaning judgment model, and acquiring a judgment result, wherein the judgment result comprises: need and not;

when the judgment result is that the sewage sludge is needed, the first area needs to be cleaned;

when the determination result is that the sewage sludge is unnecessary, the first area does not need to be cleaned up.

Preferably, the formulation module performs the following operations:

acquiring a preset sewage sludge cleaning event set, wherein the sewage sludge cleaning event set comprises: a plurality of first sewage sludge clearing events;

performing feature analysis and extraction on the first field data to obtain a plurality of first features;

extracting second field data from the first sewage sludge cleanup event;

performing feature analysis and extraction on the second field data to obtain a plurality of second features;

performing feature matching on the first feature and the second feature, if the first feature and the second feature are matched, taking the first feature matched with the first feature as a first target feature, and simultaneously taking the first feature except the first target feature in the first feature as a second target feature and associating the first feature with a corresponding first sewage sludge cleaning event;

acquiring a first price weight corresponding to the first target characteristic, and associating the first price weight with a corresponding first sewage sludge cleaning event;

acquiring second attribute information of the first area;

performing feature analysis and extraction on the second attribute information to obtain a plurality of third features;

extracting third attribute information in the first sewage sludge cleaning event;

performing feature analysis and extraction on the third attribute information to obtain a plurality of fourth features;

performing feature matching on the third feature and the fourth feature, if the matching is matched, taking the matched third feature as a third target feature, and simultaneously taking the third feature except the third target feature in the third feature as a fourth target feature and associating the third feature with the corresponding first sewage sludge cleaning event;

acquiring a second value weight corresponding to the third target characteristic, and associating the second value weight with the first sewage sludge cleaning event;

summarizing the first and second cost value weights associated with the first sewage sludge cleaning event to obtain a first cost value weight sum;

selecting the maximum first price weight sum as a second price weight sum;

if the second value weight sum is larger than or equal to a preset value weight and a threshold value, extracting a first sewage sludge cleaning process corresponding to the first sewage sludge cleaning event;

generating a scheduling strategy based on the first sewage and sludge cleaning process;

otherwise, sorting the first price weight sums from large to small to obtain a value weight sum sequence;

traversing the first value weight sum from the starting point to the end point of the value weight sum sequence;

taking the traversed first value weight sum as a third value weight sum in each traversal;

extracting the third valence weight and a corresponding second sewage-sludge cleaning course in the first sewage-sludge cleaning event;

setting the second target feature and the fourth target feature associated with the first sewage sludge cleaning event as a fifth target feature;

acquiring a preset problem prediction model, inputting the second sewage and sludge cleaning process and the fifth target characteristic into the problem prediction model, and acquiring at least one problem item, wherein the problem item comprises: a question location, a question type, a first question content, and a corresponding first question value;

acquiring a second area site three-dimensional model corresponding to the first area;

performing sewage rendering configuration on the second area on-site three-dimensional model based on the first on-site data, setting a monitoring point at a virtual position corresponding to the problem position in the second area on-site three-dimensional model, giving a monitoring task corresponding to the problem type to the monitoring point, and obtaining a third area on-site three-dimensional model;

acquiring a preset simulation space, inputting the third area field three-dimensional model into the simulation space, and simulating the second sewage and sludge cleaning process;

acquiring monitoring data returned by the monitoring points at regular time, comparing and analyzing the monitoring data and the problem content, determining whether the monitoring data and the problem content are consistent, and if so, taking the corresponding first problem value as a second problem value;

after the simulation is finished, summarizing the second problem value as a problem value sum, and associating the problem value sum with the corresponding second sewage sludge cleaning process;

after traversing is finished, taking the minimum problem value and the associated second sewage sludge cleaning process as a third sewage sludge cleaning process, and simultaneously taking the first problem content corresponding to the minimum problem value and the second problem value obtained in a summary manner as a second problem content;

and acquiring a preset problem solving model, and inputting the third sewage sludge cleaning process and the second problem content into the problem solving model to acquire a scheduling strategy.

Preferably, the sewage treatment sludge cleaning and management system further comprises:

and the tracking module is used for dynamically tracking the process of cleaning the sewage and the sludge in the first area.

Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.

The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.

Drawings

The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:

FIG. 1 is a flow chart of a method for cleaning and managing sludge from sewage treatment according to an embodiment of the present invention;

FIG. 2 is a flow chart of another method for cleaning and managing sewage sludge according to an embodiment of the present invention;

FIG. 3 is a schematic view of another sewage sludge disposal and management system according to an embodiment of the present invention.

Detailed Description

The preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, and it will be understood that they are described herein for the purpose of illustration and explanation and not limitation.

The embodiment of the invention provides a method for cleaning and managing sludge in sewage treatment, which comprises the following steps of:

step S1: acquiring a preset region set, wherein the region set comprises: a plurality of first regions;

step S2: acquiring first field data of the first area, and determining whether the first area needs sewage sludge cleaning or not based on the first field data;

step S3: if yes, an appropriate scheduling strategy is made based on the first field data;

step S4: and scheduling the first region to be manually cleaned of sewage and sludge based on the scheduling strategy.

The working principle and the beneficial effects of the technical scheme are as follows:

the preset area set comprises a plurality of first areas (such as underground pipelines of a certain street) needing sewage sludge management; the method comprises the steps of obtaining first field data (the sludge thickness of each area of the underground pipeline; arranging a camera and a laser transmitting device in the underground pipeline, transmitting laser to a sewage surface by the laser transmitting device to generate light spots on the sewage surface, collecting light spot images by the camera, analyzing the light spot images to obtain the sludge thickness; collecting the images of the sewage surface only by the camera, comparing the images with the images obtained after previous sludge cleaning to determine the sludge thickness); determining whether the first area needs sewage sludge cleaning based on the first field data; if so, based on the first field data, making a proper scheduling strategy (for example, determining the total sludge amount, scheduling a reasonable number of cleaning personnel and sewage suction trucks to clean, allocating proper cleaning tasks for different cleaning personnel, determining proper placement places for sucked sludge and the like); based on a scheduling strategy, scheduling manpower to clean sewage and sludge;

according to the embodiment of the invention, when the first area needs to be cleaned, an appropriate scheduling strategy is formulated based on the corresponding first field data, and the first area is manually scheduled to be cleaned, so that the problems that cleaning cost is increased due to too many cleaning personnel, cleaning efficiency is reduced due to unreasonable task allocation and the like caused by the fact that the traditional method arranges professional cleaning personnel according to experience can be effectively avoided.

The embodiment of the present invention provides a method for cleaning and managing sewage and sludge, in step S2, acquiring first field data of the first area, including:

acquiring a plurality of first acquisition nodes corresponding to the first area;

acquiring a first field data item through the first acquisition node;

acquiring a first acquisition range corresponding to the first acquisition node;

acquiring a first area site three-dimensional model corresponding to the first area, determining a first coverage area corresponding to the first acquisition range in the first area site three-dimensional model, and corresponding to the first site data item;

extracting at least one first missing region except the coverage region in the sewage region in the first regional field three-dimensional model;

acquiring position information of the first missing area, wherein the position information comprises: a plurality of position markers;

based on a preset position mark-acquisition information base, attempting to determine acquisition information corresponding to any one of the position marks, wherein the acquisition information comprises: the acquisition party, the second acquisition node and the corresponding second acquisition range;

if the determination is successful, acquiring a credit value of the collector, if the credit value is greater than or equal to a preset credit threshold value, determining a second coverage area corresponding to the second collection range in the first area field three-dimensional model, and simultaneously acquiring a second field data item through a corresponding second collection node;

determining a coinciding zone of the first missing region coinciding with the second coverage zone;

taking the remaining area of the first missing area except the overlapping area as a second missing area, and meanwhile, determining a third field data item corresponding to the overlapping area in the second field data item;

if the determination fails, taking the corresponding first missing region as a second missing region;

determining a first field data item and a third field data item which are associated with the first coverage area and the overlapping area adjacent to the second missing area in the first regional field three-dimensional model and are used as fourth field data items;

acquiring a position relation between the first coverage area adjacent to the second missing area and the overlapping area and the second missing area in the first area field three-dimensional model;

acquiring first attribute information of the second missing region;

acquiring a preset field data prediction model, inputting the fourth field data item, the position relation and the attribute information into the field data prediction model, and acquiring a fifth field data item corresponding to the second missing area;

and integrating the first field data item, the third field data item and the fifth field data item to obtain the first field data of the first area, and finishing the acquisition.

The working principle and the beneficial effects of the technical scheme are as follows:

when first field data is acquired, acquiring a corresponding first acquisition node (a network node which is in butt joint with a plurality of acquisition devices in a first area), and determining the acquisition range of the first acquisition node (the acquisition range of the acquisition devices is which area in an underground pipeline and can be recorded during device installation); acquiring a first area site three-dimensional model (underground pipeline three-dimensional model) and determining a first coverage area; extracting a first missing area (the sludge data in the area cannot be acquired) except the first covering area in a sewage area (preset) in a first area on-site three-dimensional model; acquiring position information of the first missing area, wherein the position information comprises a plurality of position marks; determining the collected information based on a preset position mark-collected information base (a database containing the collected information corresponding to different position marks can be obtained from the Internet based on a big data technology); the acquisition information comprises an acquisition party (such as a certain company), a second acquisition node (a network node which is in butt joint with acquisition equipment in an area corresponding to the acquisition position mark) and a second acquisition range; determining a second coverage area, and simultaneously determining an overlapping area; however, a second missing region which cannot be acquired still exists in the first missing region, and a fifth field data item of the second missing region is predicted by a preset field data prediction model (a model generated by learning a record of large amount of manual sludge amount prediction by using a machine learning algorithm) based on a fourth field data item corresponding to the adjacent first covering region and the overlapping region, the position relation of the fourth field data item and the first attribute information (such as sewage flow direction); integrating the first field data item, the third field data item and the fifth field data item to obtain first field data and finish obtaining;

in practical application, when sludge monitoring is carried out on an underground pipeline of a region, related permission needs to be received; however, underground pipelines in different areas may have a problem of intercommunication, and the area near the junction of the underground pipeline in the area and the underground pipeline in other areas needs to be monitored when monitoring is to be comprehensive, but the monitoring area is not always allowed; when more and more sludge cleaning companies are added, monitoring data of a missing area (generally an area near a joint) monitored by the other party can be acquired by the other party; the embodiment of the invention sets a credit value (determined based on the authenticity of the provided data) for the acquisition party as a judgment standard, realizes data sharing on the premise of ensuring acquisition accuracy, and is more reasonable in setting and capable of acquiring monitoring data corresponding to a missing area; in addition, even if monitoring data shared by other parties cannot be acquired, prediction can be carried out, and the response capability of the system is improved.

The embodiment of the invention provides a sewage treatment sludge cleaning and management method, which is used for acquiring a credit value of a collector and comprises the following steps:

obtaining a credit record of the acquirer, the credit record including: a plurality of first entries;

analyzing the first record item to obtain a first credit evaluation value;

if the first credit evaluation value is larger than a preset credit evaluation threshold value, taking the corresponding first credit evaluation value as a second credit evaluation value;

if the first credit evaluation value is less than or equal to the credit evaluation threshold value, taking the corresponding first credit evaluation value as a third credit evaluation value, and simultaneously taking the corresponding first record item as a second record item;

acquiring the credibility of the second record item;

calculating a credit value based on the second credit evaluation value, the third credit evaluation value and the credibility, wherein the calculation formula is as follows:

wherein cre is the credit value, α_iIs the ith second credit evaluation value, m is the total number of the second credit evaluation values, σ is the credit evaluation threshold value, μ₁And mu₂Is a preset first weight value, beta_tIs the t-th third credit evaluation value, gamma_tThe credibility of the second record item corresponding to the tth third credit evaluation value, n is the total number of the third credit evaluation values, mu₃And mu₄Is a preset second weight value.

The working principle and the beneficial effects of the technical scheme are as follows:

acquiring credit records of the acquirer (for example, records of data sharing with different companies, records of credit evaluation of different companies and the like); analyzing the first record item to obtain a first credit evaluation value (the higher the first credit evaluation value is, the better the credit expression is); when the first credit evaluation value is less than or equal to a preset credit evaluation threshold (for example: 90), the evaluation is low, and in order to prevent malicious evaluation, the credibility of the second record item needs to be acquired (which can be determined based on the normal degree of the historical evaluation record of the evaluator); comprehensively calculating a credit value based on the second credit evaluation value, the third credit evaluation value and the credibility, finishing acquisition and improving the working efficiency of the system;

in the formula, the second credit evaluation value, the third credit evaluation value and the reliability are positively correlated with the credit value, the ratio of the second credit evaluation value to the credit evaluation threshold is also positively correlated with the credit value, the ratio of the third credit evaluation value to the credit evaluation threshold is also positively correlated with the credit value, different weight values are given for comprehensive calculation, and the setting is reasonable.

An embodiment of the present invention provides a method for managing and cleaning sewage and sludge, in step S2, determining whether the first area needs to be cleaned by sewage and sludge based on the first field data, including:

acquiring a preset sewage and sludge cleaning judgment model, inputting the first field data into the sewage and sludge cleaning judgment model, and acquiring a judgment result, wherein the judgment result comprises: need and not;

when the judgment result is that the sewage sludge is needed, the first area needs to be cleaned;

when the determination result is that the sewage sludge is unnecessary, the first area does not need to be cleaned up.

The working principle and the beneficial effects of the technical scheme are as follows:

the first field data are input into a preset sewage and sludge cleaning judgment model (a model generated after learning a record of whether a large amount of manual work needs sewage and sludge cleaning or not by using a machine learning algorithm), a judgment result is obtained, whether the first area needs sewage and sludge cleaning or not can be determined based on the judgment result, and the working efficiency of the system can be effectively improved.

The embodiment of the invention provides a method for cleaning and managing sludge in sewage treatment, wherein in the step S3, based on the field data, a proper scheduling strategy is formulated, and the method comprises the following steps:

acquiring a preset sewage sludge cleaning event set, wherein the sewage sludge cleaning event set comprises: a plurality of first sewage sludge clearing events;

performing feature analysis and extraction on the first field data to obtain a plurality of first features;

extracting second field data from the first sewage sludge cleanup event;

performing feature analysis and extraction on the second field data to obtain a plurality of second features;

performing feature matching on the first feature and the second feature, if the first feature and the second feature are matched, taking the first feature matched with the first feature as a first target feature, and simultaneously taking the first feature except the first target feature in the first feature as a second target feature and associating the first feature with a corresponding first sewage sludge cleaning event;

acquiring a first price weight corresponding to the first target characteristic, and associating the first price weight with a corresponding first sewage sludge cleaning event;

acquiring second attribute information of the first area;

performing feature analysis and extraction on the second attribute information to obtain a plurality of third features;

extracting third attribute information in the first sewage sludge cleaning event;

performing feature analysis and extraction on the third attribute information to obtain a plurality of fourth features;

performing feature matching on the third feature and the fourth feature, if the matching is matched, taking the matched third feature as a third target feature, and simultaneously taking the third feature except the third target feature in the third feature as a fourth target feature and associating the third feature with the corresponding first sewage sludge cleaning event;

acquiring a second value weight corresponding to the third target characteristic, and associating the second value weight with the first sewage sludge cleaning event;

summarizing the first and second cost value weights associated with the first sewage sludge cleaning event to obtain a first cost value weight sum;

selecting the maximum first price weight sum as a second price weight sum;

if the second value weight sum is larger than or equal to a preset value weight and a threshold value, extracting a first sewage sludge cleaning process corresponding to the first sewage sludge cleaning event;

generating a scheduling strategy based on the first sewage and sludge cleaning process;

otherwise, sorting the first price weight sums from large to small to obtain a value weight sum sequence;

traversing the first value weight sum from the starting point to the end point of the value weight sum sequence;

taking the traversed first value weight sum as a third value weight sum in each traversal;

extracting the third valence weight and a corresponding second sewage-sludge cleaning course in the first sewage-sludge cleaning event;

setting the second target feature and the fourth target feature associated with the first sewage sludge cleaning event as a fifth target feature;

acquiring a preset problem prediction model, inputting the second sewage and sludge cleaning process and the fifth target characteristic into the problem prediction model, and acquiring at least one problem item, wherein the problem item comprises: a question location, a question type, a first question content, and a corresponding first question value;

acquiring a second area site three-dimensional model corresponding to the first area;

performing sewage rendering configuration on the second area on-site three-dimensional model based on the first on-site data, setting a monitoring point at a virtual position corresponding to the problem position in the second area on-site three-dimensional model, giving a monitoring task corresponding to the problem type to the monitoring point, and obtaining a third area on-site three-dimensional model;

acquiring a preset simulation space, inputting the third area field three-dimensional model into the simulation space, and simulating the second sewage and sludge cleaning process;

acquiring monitoring data returned by the monitoring points at regular time, comparing and analyzing the monitoring data and the problem content, determining whether the monitoring data and the problem content are consistent, and if so, taking the corresponding first problem value as a second problem value;

after the simulation is finished, summarizing the second problem value as a problem value sum, and associating the problem value sum with the corresponding second sewage sludge cleaning process;

after traversing is finished, taking the minimum problem value and the associated second sewage sludge cleaning process as a third sewage sludge cleaning process, and simultaneously taking the first problem content corresponding to the minimum problem value and the second problem value obtained in a summary manner as a second problem content;

and acquiring a preset problem solving model, and inputting the third sewage sludge cleaning process and the second problem content into the problem solving model to acquire a scheduling strategy.

The working principle and the beneficial effects of the technical scheme are as follows:

when a scheduling strategy is formulated, a plurality of first sewage sludge cleaning events (event records for successfully and efficiently cleaning underground pipeline sewage sludge in different areas historically) are obtained; the scheduling strategy is required to be formulated based on the first sewage and sludge cleaning event, and the adaptation condition of the first sewage and sludge cleaning event and the current area sewage and sludge cleaning needs to be considered; therefore, the first field data and the second field data (the sludge amount of each region of the underground pipeline which is historically cleaned by sewage and sludge) are respectively subjected to characteristic analysis and extraction, characteristic matching is carried out after extraction, the first characteristics which are matched and matched are taken as first target characteristics, and the rest first characteristics are taken as second target characteristics; acquiring a first value weight corresponding to the first target feature (if the first target feature is matched with the first target feature, the usability of a sewage and sludge cleaning process in a corresponding sewage and sludge cleaning event can be considered to be in positive correlation); acquiring second attribute information (length, size, pipeline distribution, service life and the like of an underground pipeline) of the first area, extracting third attribute information (the length, size, pipeline distribution, service life and the like of the underground pipeline which is historically cleaned by sewage and sludge) in a first sewage and sludge cleaning event, respectively performing characteristic analysis and extraction, performing characteristic matching after extraction, and taking the third characteristic which is matched with the third characteristic as a third target characteristic and taking the rest of the third characteristics as a fourth target characteristic; acquiring a second value weight corresponding to the third target feature (if the third target feature is matched with the third target feature, the usability of the sewage and sludge cleaning process in the corresponding sewage and sludge cleaning event can be considered to be in positive correlation); summarizing (summing) the first price weight and the second price weight to obtain a first price weight sum; if the maximum value (the second value weight sum) of the first value weight sum is greater than the preset value weight sum threshold (for example, 85), which indicates that the suitability is high, the scheduling strategy can be generated by directly using the first sewage sludge cleaning process (how many people are allocated, what kind of work is allocated, what equipment is needed, and the like) in the first sewage sludge cleaning event for reference; otherwise, the overall adaptation degree is low, the depth is required to be screened, and the third weight sum is traversed; extracting corresponding second sewage sludge cleaning process; acquiring a preset problem prediction model (a model generated after learning records of problems possibly existing under the condition that certain different applicable scenes exist in the implementation scheme of a large number of other parties through a machine learning algorithm), inputting a second sewage and sludge cleaning process and a fifth target characteristic into the problem prediction model, predicting problems possibly existing if different fifth target characteristics exist in the second sewage and sludge cleaning process, and outputting a problem item, wherein the problem item comprises a problem position (for example, the size of an underground pipeline is not matched, the problem position is sewage suction equipment), a problem type (equipment type), first problem content (the power of the sewage suction equipment is small) and a corresponding first problem value (the problem value is positively correlated with the severity of the problem content); acquiring a second area site three-dimensional model, performing sewage rendering configuration (setting virtual sewage) on the second area site three-dimensional model based on first site data, setting a monitoring point corresponding to a virtual position of the problem position in the second area site three-dimensional model (for example, setting a monitoring point at a device setting position), and giving a monitoring task (monitoring device power) corresponding to the problem type; simulating a second sewage and sludge cleaning process (setting virtual workers, virtual equipment for sewage suction and the like) in a preset simulation space, acquiring monitoring data returned by monitoring points, matching the monitoring data with corresponding problem contents, and if the monitoring data are consistent with the corresponding problem contents, generating a problem, wherein the corresponding first problem value is effective and serves as a second problem value; after traversing, determining the minimum problem value and a related third sewage sludge cleaning process, and meanwhile, collecting second problem content; inputting the third sewage and sludge cleaning process and the second problem content into a preset problem solving model (a model generated after learning a large number of manual problem solving processes by using a machine learning algorithm and simultaneously making a record of a scheduling strategy based on the sewage and sludge cleaning process), and obtaining a scheduling strategy;

when the scheduling strategy is formulated in the embodiment of the invention, firstly, whether the scheduling strategy can be generated by fully using the first sewage and sludge cleaning process in the first sewage and sludge cleaning event is considered, if the scheduling strategy cannot be generated by deeply screening, using the third sewage and sludge cleaning process and solving the second problem content is considered, the generation accuracy of the scheduling strategy can be ensured, and the coping capability of the system for different conditions is further improved; when a scheduling strategy is generated by using a first sewage sludge cleaning process in a first sewage sludge cleaning event for reference, the characteristics of respective field data and attribute information are extracted and matched, and the setting is reasonable; when carrying out the degree of depth screening and borrowing the reference third sewage silt cleaning process and solving second problem content and generating the scheduling strategy, carry out the problem prediction based on the fifth target characteristic that matches nonconformity, save problem analysis resources, simultaneously, simulate in the simulation space, can fully carry out the feasibility to second sewage silt cleaning process and verify, promote screening efficiency.

The embodiment of the invention provides a method for cleaning and managing sludge in sewage treatment, which comprises the following steps of:

step S5: and dynamically tracking the first area to carry out the sewage sludge cleaning process.

The working principle and the beneficial effects of the technical scheme are as follows:

when the first area is cleaned by sewage and sludge, the cleaning process is dynamically tracked (for example, corresponding manual field conditions are inquired), and the supervision and promotion effect is played.

An embodiment of the present invention provides a sewage treatment sludge cleaning and management system, as shown in fig. 3, including:

an obtaining module 1, configured to obtain a preset region set, where the region set includes: a plurality of first regions;

the determining module 2 is used for acquiring first field data of the first area and determining whether the first area needs sewage sludge cleaning or not based on the first field data;

the formulating module 3 is used for formulating a proper scheduling strategy based on the first field data if the first field data exists;

and the scheduling module 4 is used for scheduling manual sewage and sludge cleaning to the first area based on the scheduling strategy.

The working principle and the beneficial effects of the technical scheme are as follows:

the preset area set comprises a plurality of first areas (such as underground pipelines of a certain street) needing sewage sludge management; the method comprises the steps of obtaining first field data (the sludge thickness of each area of the underground pipeline; arranging a camera and a laser transmitting device in the underground pipeline, transmitting laser to a sewage surface by the laser transmitting device to generate light spots on the sewage surface, collecting light spot images by the camera, analyzing the light spot images to obtain the sludge thickness; collecting the images of the sewage surface only by the camera, comparing the images with the images obtained after previous sludge cleaning to determine the sludge thickness); determining whether the first area needs sewage sludge cleaning based on the first field data; if so, based on the first field data, making a proper scheduling strategy (for example, determining the total sludge amount, scheduling a reasonable number of cleaning personnel and sewage suction trucks to clean, allocating proper cleaning tasks for different cleaning personnel, determining proper placement places for sucked sludge and the like); based on a scheduling strategy, scheduling manpower to clean sewage and sludge;

according to the embodiment of the invention, when the first area needs to be cleaned, an appropriate scheduling strategy is formulated based on the corresponding first field data, and the first area is manually scheduled to be cleaned, so that the problems that cleaning cost is increased due to too many cleaning personnel, cleaning efficiency is reduced due to unreasonable task allocation and the like caused by the fact that the traditional method arranges professional cleaning personnel according to experience can be effectively avoided.

The embodiment of the invention provides a sewage treatment sludge cleaning and management system, wherein a determining module 2 executes the following operations:

acquiring a plurality of first acquisition nodes corresponding to the first area;

acquiring a first field data item through the first acquisition node;

acquiring a first acquisition range corresponding to the first acquisition node;

acquiring a first area site three-dimensional model corresponding to the first area, determining a first coverage area corresponding to the first acquisition range in the first area site three-dimensional model, and corresponding to the first site data item;

extracting at least one first missing region except the coverage region in the sewage region in the first regional field three-dimensional model;

acquiring position information of the first missing area, wherein the position information comprises: a plurality of position markers;

based on a preset position mark-acquisition information base, attempting to determine acquisition information corresponding to any one of the position marks, wherein the acquisition information comprises: the acquisition party, the second acquisition node and the corresponding second acquisition range;

if the determination is successful, acquiring a credit value of the collector, if the credit value is greater than or equal to a preset credit threshold value, determining a second coverage area corresponding to the second collection range in the first area field three-dimensional model, and simultaneously acquiring a second field data item through a corresponding second collection node;

determining a coinciding zone of the first missing region coinciding with the second coverage zone;

taking the remaining area of the first missing area except the overlapping area as a second missing area, and meanwhile, determining a third field data item corresponding to the overlapping area in the second field data item;

if the determination fails, taking the corresponding first missing region as a second missing region;

determining a first field data item and a third field data item which are associated with the first coverage area and the overlapping area adjacent to the second missing area in the first regional field three-dimensional model and are used as fourth field data items;

acquiring a position relation between the first coverage area adjacent to the second missing area and the overlapping area and the second missing area in the first area field three-dimensional model;

acquiring first attribute information of the second missing region;

acquiring a preset field data prediction model, inputting the fourth field data item, the position relation and the attribute information into the field data prediction model, and acquiring a fifth field data item corresponding to the second missing area;

and integrating the first field data item, the third field data item and the fifth field data item to obtain the first field data of the first area, and finishing the acquisition.

The working principle and the beneficial effects of the technical scheme are as follows:

when first field data is acquired, acquiring a corresponding first acquisition node (a network node which is in butt joint with a plurality of acquisition devices in a first area), and determining the acquisition range of the first acquisition node (the acquisition range of the acquisition devices is which area in an underground pipeline and can be recorded during device installation); acquiring a first area site three-dimensional model (underground pipeline three-dimensional model) and determining a first coverage area; extracting a first missing area (the sludge data in the area cannot be acquired) except the first covering area in a sewage area (preset) in a first area on-site three-dimensional model; acquiring position information of the first missing area, wherein the position information comprises a plurality of position marks; determining the collected information based on a preset position mark-collected information base (a database containing the collected information corresponding to different position marks can be obtained from the Internet based on a big data technology); the acquisition information comprises an acquisition party (such as a certain company), a second acquisition node (a network node which is in butt joint with acquisition equipment in an area corresponding to the acquisition position mark) and a second acquisition range; determining a second coverage area, and simultaneously determining an overlapping area; however, a second missing region which cannot be acquired still exists in the first missing region, and a fifth field data item of the second missing region is predicted by a preset field data prediction model (a model generated by learning a record of large amount of manual sludge amount prediction by using a machine learning algorithm) based on a fourth field data item corresponding to the adjacent first covering region and the overlapping region, the position relation of the fourth field data item and the first attribute information (such as sewage flow direction); integrating the first field data item, the third field data item and the fifth field data item to obtain first field data and finish obtaining;

in practical application, when sludge monitoring is carried out on an underground pipeline of a region, related permission needs to be received; however, underground pipelines in different areas may have a problem of intercommunication, and the area near the junction of the underground pipeline in the area and the underground pipeline in other areas needs to be monitored when monitoring is to be comprehensive, but the monitoring area is not always allowed; when more and more sludge cleaning companies are added, monitoring data of a missing area (generally an area near a joint) monitored by the other party can be acquired by the other party; the embodiment of the invention sets a credit value (determined based on the authenticity of the provided data) for the acquisition party as a judgment standard, realizes data sharing on the premise of ensuring acquisition accuracy, and is more reasonable in setting and capable of acquiring monitoring data corresponding to a missing area; in addition, even if monitoring data shared by other parties cannot be acquired, prediction can be carried out, and the response capability of the system is improved.

The embodiment of the invention provides a sewage treatment sludge cleaning and management system, wherein a determining module 2 executes the following operations:

obtaining a credit record of the acquirer, the credit record including: a plurality of first entries;

analyzing the first record item to obtain a first credit evaluation value;

if the first credit evaluation value is larger than a preset credit evaluation threshold value, taking the corresponding first credit evaluation value as a second credit evaluation value;

if the first credit evaluation value is less than or equal to the credit evaluation threshold value, taking the corresponding first credit evaluation value as a third credit evaluation value, and simultaneously taking the corresponding first record item as a second record item;

acquiring the credibility of the second record item;

calculating a credit value based on the second credit evaluation value, the third credit evaluation value and the credibility, wherein the calculation formula is as follows:

wherein cre is the credit value, α_iIs the ith second credit evaluation value, m is the total number of the second credit evaluation values, σ is the credit evaluation threshold value, μ₁And mu₂Is a preset first weight value, beta_tIs the t-th third credit evaluation value, gamma_tIs as followsthe credibility of the second record items corresponding to the t third credit evaluation values, n is the total number of the third credit evaluation values, mu₃And mu₄Is a preset second weight value.

The working principle and the beneficial effects of the technical scheme are as follows:

acquiring credit records of the acquirer (for example, records of data sharing with different companies, records of credit evaluation of different companies and the like); analyzing the first record item to obtain a first credit evaluation value (the higher the first credit evaluation value is, the better the credit expression is); when the first credit evaluation value is less than or equal to a preset credit evaluation threshold (for example: 90), the evaluation is low, and in order to prevent malicious evaluation, the credibility of the second record item needs to be acquired (which can be determined based on the normal degree of the historical evaluation record of the evaluator); comprehensively calculating a credit value based on the second credit evaluation value, the third credit evaluation value and the credibility, finishing acquisition and improving the working efficiency of the system;

in the formula, the second credit evaluation value, the third credit evaluation value and the reliability are positively correlated with the credit value, the ratio of the second credit evaluation value to the credit evaluation threshold is also positively correlated with the credit value, the ratio of the third credit evaluation value to the credit evaluation threshold is also positively correlated with the credit value, different weight values are given for comprehensive calculation, and the setting is reasonable.

The embodiment of the invention provides a sewage treatment sludge cleaning and management system, wherein a determining module 2 executes the following operations:

acquiring a preset sewage and sludge cleaning judgment model, inputting the first field data into the sewage and sludge cleaning judgment model, and acquiring a judgment result, wherein the judgment result comprises: need and not;

when the judgment result is that the sewage sludge is needed, the first area needs to be cleaned;

when the determination result is that the sewage sludge is unnecessary, the first area does not need to be cleaned up.

The working principle and the beneficial effects of the technical scheme are as follows:

the first field data are input into a preset sewage and sludge cleaning judgment model (a model generated after learning a record of whether a large amount of manual work needs sewage and sludge cleaning or not by using a machine learning algorithm), a judgment result is obtained, whether the first area needs sewage and sludge cleaning or not can be determined based on the judgment result, and the working efficiency of the system can be effectively improved.

The embodiment of the invention provides a sewage treatment sludge cleaning and management system, wherein a formulation module 3 executes the following operations:

acquiring a preset sewage sludge cleaning event set, wherein the sewage sludge cleaning event set comprises: a plurality of first sewage sludge clearing events;

performing feature analysis and extraction on the first field data to obtain a plurality of first features;

extracting second field data from the first sewage sludge cleanup event;

performing feature analysis and extraction on the second field data to obtain a plurality of second features;

performing feature matching on the first feature and the second feature, if the first feature and the second feature are matched, taking the first feature matched with the first feature as a first target feature, and simultaneously taking the first feature except the first target feature in the first feature as a second target feature and associating the first feature with a corresponding first sewage sludge cleaning event;

acquiring a first price weight corresponding to the first target characteristic, and associating the first price weight with a corresponding first sewage sludge cleaning event;

acquiring second attribute information of the first area;

performing feature analysis and extraction on the second attribute information to obtain a plurality of third features;

extracting third attribute information in the first sewage sludge cleaning event;

performing feature analysis and extraction on the third attribute information to obtain a plurality of fourth features;

performing feature matching on the third feature and the fourth feature, if the matching is matched, taking the matched third feature as a third target feature, and simultaneously taking the third feature except the third target feature in the third feature as a fourth target feature and associating the third feature with the corresponding first sewage sludge cleaning event;

acquiring a second value weight corresponding to the third target characteristic, and associating the second value weight with the first sewage sludge cleaning event;

summarizing the first and second cost value weights associated with the first sewage sludge cleaning event to obtain a first cost value weight sum;

selecting the maximum first price weight sum as a second price weight sum;

if the second value weight sum is larger than or equal to a preset value weight and a threshold value, extracting a first sewage sludge cleaning process corresponding to the first sewage sludge cleaning event;

generating a scheduling strategy based on the first sewage and sludge cleaning process;

otherwise, sorting the first price weight sums from large to small to obtain a value weight sum sequence;

traversing the first value weight sum from the starting point to the end point of the value weight sum sequence;

taking the traversed first value weight sum as a third value weight sum in each traversal;

extracting the third valence weight and a corresponding second sewage-sludge cleaning course in the first sewage-sludge cleaning event;

setting the second target feature and the fourth target feature associated with the first sewage sludge cleaning event as a fifth target feature;

acquiring a preset problem prediction model, inputting the second sewage and sludge cleaning process and the fifth target characteristic into the problem prediction model, and acquiring at least one problem item, wherein the problem item comprises: a question location, a question type, a first question content, and a corresponding first question value;

acquiring a second area site three-dimensional model corresponding to the first area;

performing sewage rendering configuration on the second area on-site three-dimensional model based on the first on-site data, setting a monitoring point at a virtual position corresponding to the problem position in the second area on-site three-dimensional model, giving a monitoring task corresponding to the problem type to the monitoring point, and obtaining a third area on-site three-dimensional model;

acquiring a preset simulation space, inputting the third area field three-dimensional model into the simulation space, and simulating the second sewage and sludge cleaning process;

acquiring monitoring data returned by the monitoring points at regular time, comparing and analyzing the monitoring data and the problem content, determining whether the monitoring data and the problem content are consistent, and if so, taking the corresponding first problem value as a second problem value;

after the simulation is finished, summarizing the second problem value as a problem value sum, and associating the problem value sum with the corresponding second sewage sludge cleaning process;

after traversing is finished, taking the minimum problem value and the associated second sewage sludge cleaning process as a third sewage sludge cleaning process, and simultaneously taking the first problem content corresponding to the minimum problem value and the second problem value obtained in a summary manner as a second problem content;

and acquiring a preset problem solving model, and inputting the third sewage sludge cleaning process and the second problem content into the problem solving model to acquire a scheduling strategy.

The working principle and the beneficial effects of the technical scheme are as follows:

when a scheduling strategy is formulated, a plurality of first sewage sludge cleaning events (event records for successfully and efficiently cleaning underground pipeline sewage sludge in different areas historically) are obtained; the scheduling strategy is required to be formulated based on the first sewage and sludge cleaning event, and the adaptation condition of the first sewage and sludge cleaning event and the current area sewage and sludge cleaning needs to be considered; therefore, the first field data and the second field data (the sludge amount of each region of the underground pipeline which is historically cleaned by sewage and sludge) are respectively subjected to characteristic analysis and extraction, characteristic matching is carried out after extraction, the first characteristics which are matched and matched are taken as first target characteristics, and the rest first characteristics are taken as second target characteristics; acquiring a first value weight corresponding to the first target feature (if the first target feature is matched with the first target feature, the usability of a sewage and sludge cleaning process in a corresponding sewage and sludge cleaning event can be considered to be in positive correlation); acquiring second attribute information (length, size, pipeline distribution, service life and the like of an underground pipeline) of the first area, extracting third attribute information (the length, size, pipeline distribution, service life and the like of the underground pipeline which is historically cleaned by sewage and sludge) in a first sewage and sludge cleaning event, respectively performing characteristic analysis and extraction, performing characteristic matching after extraction, and taking the third characteristic which is matched with the third characteristic as a third target characteristic and taking the rest of the third characteristics as a fourth target characteristic; acquiring a second value weight corresponding to the third target feature (if the third target feature is matched with the third target feature, the usability of the sewage and sludge cleaning process in the corresponding sewage and sludge cleaning event can be considered to be in positive correlation); summarizing (summing) the first price weight and the second price weight to obtain a first price weight sum; if the maximum value (the second value weight sum) of the first value weight sum is greater than the preset value weight sum threshold (for example, 85), which indicates that the suitability is high, the scheduling strategy can be generated by directly using the first sewage sludge cleaning process (how many people are allocated, what kind of work is allocated, what equipment is needed, and the like) in the first sewage sludge cleaning event for reference; otherwise, the overall adaptation degree is low, the depth is required to be screened, and the third weight sum is traversed; extracting corresponding second sewage sludge cleaning process; acquiring a preset problem prediction model (a model generated after learning records of problems possibly existing under the condition that certain different applicable scenes exist in the implementation scheme of a large number of other parties through a machine learning algorithm), inputting a second sewage and sludge cleaning process and a fifth target characteristic into the problem prediction model, predicting problems possibly existing if different fifth target characteristics exist in the second sewage and sludge cleaning process, and outputting a problem item, wherein the problem item comprises a problem position (for example, the size of an underground pipeline is not matched, the problem position is sewage suction equipment), a problem type (equipment type), first problem content (the power of the sewage suction equipment is small) and a corresponding first problem value (the problem value is positively correlated with the severity of the problem content); acquiring a second area site three-dimensional model, performing sewage rendering configuration (setting virtual sewage) on the second area site three-dimensional model based on first site data, setting a monitoring point corresponding to a virtual position of the problem position in the second area site three-dimensional model (for example, setting a monitoring point at a device setting position), and giving a monitoring task (monitoring device power) corresponding to the problem type; simulating a second sewage and sludge cleaning process (setting virtual workers, virtual equipment for sewage suction and the like) in a preset simulation space, acquiring monitoring data returned by monitoring points, matching the monitoring data with corresponding problem contents, and if the monitoring data are consistent with the corresponding problem contents, generating a problem, wherein the corresponding first problem value is effective and serves as a second problem value; after traversing, determining the minimum problem value and a related third sewage sludge cleaning process, and meanwhile, collecting second problem content; inputting the third sewage and sludge cleaning process and the second problem content into a preset problem solving model (a model generated after learning a large number of manual problem solving processes by using a machine learning algorithm and simultaneously making a record of a scheduling strategy based on the sewage and sludge cleaning process), and obtaining a scheduling strategy;

when the scheduling strategy is formulated in the embodiment of the invention, firstly, whether the scheduling strategy can be generated by fully using the first sewage and sludge cleaning process in the first sewage and sludge cleaning event is considered, if the scheduling strategy cannot be generated by deeply screening, using the third sewage and sludge cleaning process and solving the second problem content is considered, the generation accuracy of the scheduling strategy can be ensured, and the coping capability of the system for different conditions is further improved; when a scheduling strategy is generated by using a first sewage sludge cleaning process in a first sewage sludge cleaning event for reference, the characteristics of respective field data and attribute information are extracted and matched, and the setting is reasonable; when carrying out the degree of depth screening and borrowing the reference third sewage silt cleaning process and solving second problem content and generating the scheduling strategy, carry out the problem prediction based on the fifth target characteristic that matches nonconformity, save problem analysis resources, simultaneously, simulate in the simulation space, can fully carry out the feasibility to second sewage silt cleaning process and verify, promote screening efficiency.

The embodiment of the invention provides a sewage treatment sludge cleaning and management system, which further comprises:

and the tracking module is used for dynamically tracking the process of cleaning the sewage and the sludge in the first area.

The working principle and the beneficial effects of the technical scheme are as follows:

when the first area is cleaned by sewage and sludge, the cleaning process is dynamically tracked (for example, corresponding manual field conditions are inquired), and the supervision and promotion effect is played.

It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.

Claims (10)

1. A method for cleaning and managing sludge in sewage treatment is characterized by comprising the following steps:

step S1: acquiring a preset region set, wherein the region set comprises: a plurality of first regions;

step S2: acquiring first field data of the first area, and determining whether the first area needs sewage sludge cleaning or not based on the first field data;

step S3: if yes, an appropriate scheduling strategy is made based on the first field data;

step S4: and scheduling the first region to be manually cleaned of sewage and sludge based on the scheduling strategy.

2. The wastewater treatment sludge cleaning management method of claim 1, wherein the step S2 of obtaining first field data of the first area comprises:

acquiring a plurality of first acquisition nodes corresponding to the first area;

acquiring a first field data item through the first acquisition node;

acquiring a first acquisition range corresponding to the first acquisition node;

acquiring a first area site three-dimensional model corresponding to the first area, determining a first coverage area corresponding to the first acquisition range in the first area site three-dimensional model, and corresponding to the first site data item;

extracting at least one first missing region except the coverage region in the sewage region in the first regional field three-dimensional model;

acquiring position information of the first missing area, wherein the position information comprises: a plurality of position markers;

based on a preset position mark-acquisition information base, attempting to determine acquisition information corresponding to any one of the position marks, wherein the acquisition information comprises: the acquisition party, the second acquisition node and the corresponding second acquisition range;

if the determination is successful, acquiring a credit value of the collector, if the credit value is greater than or equal to a preset credit threshold value, determining a second coverage area corresponding to the second collection range in the first area field three-dimensional model, and simultaneously acquiring a second field data item through a corresponding second collection node;

determining a coinciding zone of the first missing region coinciding with the second coverage zone;

taking the remaining area of the first missing area except the overlapping area as a second missing area, and meanwhile, determining a third field data item corresponding to the overlapping area in the second field data item;

if the determination fails, taking the corresponding first missing region as a second missing region;

determining a first field data item and a third field data item which are associated with the first coverage area and the overlapping area adjacent to the second missing area in the first regional field three-dimensional model and are used as fourth field data items;

acquiring a position relation between the first coverage area adjacent to the second missing area and the overlapping area and the second missing area in the first area field three-dimensional model;

acquiring first attribute information of the second missing region;

acquiring a preset field data prediction model, inputting the fourth field data item, the position relation and the attribute information into the field data prediction model, and acquiring a fifth field data item corresponding to the second missing area;

and integrating the first field data item, the third field data item and the fifth field data item to obtain the first field data of the first area, and finishing the acquisition.

3. The sewage sludge disposal management method of claim 1 wherein the step S2 of determining whether the first area requires sewage sludge disposal based on the first field data comprises:

acquiring a preset sewage and sludge cleaning judgment model, inputting the first field data into the sewage and sludge cleaning judgment model, and acquiring a judgment result, wherein the judgment result comprises: need and not;

when the judgment result is that the sewage sludge is needed, the first area needs to be cleaned;

when the determination result is that the sewage sludge is unnecessary, the first area does not need to be cleaned up.

4. The method of claim 1, wherein the step S3 of formulating an appropriate scheduling strategy based on the field data comprises:

acquiring a preset sewage sludge cleaning event set, wherein the sewage sludge cleaning event set comprises: a plurality of first sewage sludge clearing events;

performing feature analysis and extraction on the first field data to obtain a plurality of first features;

extracting second field data from the first sewage sludge cleanup event;

performing feature analysis and extraction on the second field data to obtain a plurality of second features;

performing feature matching on the first feature and the second feature, if the first feature and the second feature are matched, taking the first feature matched with the first feature as a first target feature, and simultaneously taking the first feature except the first target feature in the first feature as a second target feature and associating the first feature with a corresponding first sewage sludge cleaning event;

acquiring a first price weight corresponding to the first target characteristic, and associating the first price weight with a corresponding first sewage sludge cleaning event;

acquiring second attribute information of the first area;

performing feature analysis and extraction on the second attribute information to obtain a plurality of third features;

extracting third attribute information in the first sewage sludge cleaning event;

performing feature analysis and extraction on the third attribute information to obtain a plurality of fourth features;

performing feature matching on the third feature and the fourth feature, if the matching is matched, taking the matched third feature as a third target feature, and simultaneously taking the third feature except the third target feature in the third feature as a fourth target feature and associating the third feature with the corresponding first sewage sludge cleaning event;

acquiring a second value weight corresponding to the third target characteristic, and associating the second value weight with the first sewage sludge cleaning event;

summarizing the first and second cost value weights associated with the first sewage sludge cleaning event to obtain a first cost value weight sum;

selecting the maximum first price weight sum as a second price weight sum;

if the second value weight sum is larger than or equal to a preset value weight and a threshold value, extracting a first sewage sludge cleaning process corresponding to the first sewage sludge cleaning event;

generating a scheduling strategy based on the first sewage and sludge cleaning process;

otherwise, sorting the first price weight sums from large to small to obtain a value weight sum sequence;

traversing the first value weight sum from the starting point to the end point of the value weight sum sequence;

taking the traversed first value weight sum as a third value weight sum in each traversal;

extracting the third valence weight and a corresponding second sewage-sludge cleaning course in the first sewage-sludge cleaning event;

setting the second target feature and the fourth target feature associated with the first sewage sludge cleaning event as a fifth target feature;

acquiring a preset problem prediction model, inputting the second sewage and sludge cleaning process and the fifth target characteristic into the problem prediction model, and acquiring at least one problem item, wherein the problem item comprises: a question location, a question type, a first question content, and a corresponding first question value;

acquiring a second area site three-dimensional model corresponding to the first area;

performing sewage rendering configuration on the second area on-site three-dimensional model based on the first on-site data, setting a monitoring point at a virtual position corresponding to the problem position in the second area on-site three-dimensional model, giving a monitoring task corresponding to the problem type to the monitoring point, and obtaining a third area on-site three-dimensional model;

acquiring a preset simulation space, inputting the third area field three-dimensional model into the simulation space, and simulating the second sewage and sludge cleaning process;

acquiring monitoring data returned by the monitoring points at regular time, comparing and analyzing the monitoring data and the problem content, determining whether the monitoring data and the problem content are consistent, and if so, taking the corresponding first problem value as a second problem value;

after the simulation is finished, summarizing the second problem value as a problem value sum, and associating the problem value sum with the corresponding second sewage sludge cleaning process;

after traversing is finished, taking the minimum problem value and the associated second sewage sludge cleaning process as a third sewage sludge cleaning process, and simultaneously taking the first problem content corresponding to the minimum problem value and the second problem value obtained in a summary manner as a second problem content;

and acquiring a preset problem solving model, and inputting the third sewage sludge cleaning process and the second problem content into the problem solving model to acquire a scheduling strategy.

5. The method of claim 1, further comprising:

step S5: and dynamically tracking the first area to carry out the sewage sludge cleaning process.

6. The utility model provides a sewage treatment silt clearance management system which characterized in that includes:

an obtaining module, configured to obtain a preset region set, where the region set includes: a plurality of first regions;

the determining module is used for acquiring first field data of the first area and determining whether the first area needs to be cleaned by sewage and sludge or not based on the first field data;

the formulating module is used for formulating a proper scheduling strategy based on the first field data if the first field data exists;

and the scheduling module is used for scheduling manpower to clean the sewage and sludge in the first area based on the scheduling strategy.

7. The sewage treatment sludge cleaning management system of claim 6 wherein the determination module performs the following operations:

acquiring a plurality of first acquisition nodes corresponding to the first area;

acquiring a first field data item through the first acquisition node;

acquiring a first acquisition range corresponding to the first acquisition node;

acquiring a first area site three-dimensional model corresponding to the first area, determining a first coverage area corresponding to the first acquisition range in the first area site three-dimensional model, and corresponding to the first site data item;

extracting at least one first missing region except the coverage region in the sewage region in the first regional field three-dimensional model;

acquiring position information of the first missing area, wherein the position information comprises: a plurality of position markers;

based on a preset position mark-acquisition information base, attempting to determine acquisition information corresponding to any one of the position marks, wherein the acquisition information comprises: the acquisition party, the second acquisition node and the corresponding second acquisition range;

if the determination is successful, acquiring a credit value of the collector, if the credit value is greater than or equal to a preset credit threshold value, determining a second coverage area corresponding to the second collection range in the first area field three-dimensional model, and simultaneously acquiring a second field data item through a corresponding second collection node;

determining a coinciding zone of the first missing region coinciding with the second coverage zone;

taking the remaining area of the first missing area except the overlapping area as a second missing area, and meanwhile, determining a third field data item corresponding to the overlapping area in the second field data item;

if the determination fails, taking the corresponding first missing region as a second missing region;

determining a first field data item and a third field data item which are associated with the first coverage area and the overlapping area adjacent to the second missing area in the first regional field three-dimensional model and are used as fourth field data items;

acquiring a position relation between the first coverage area adjacent to the second missing area and the overlapping area and the second missing area in the first area field three-dimensional model;

acquiring first attribute information of the second missing region;

acquiring a preset field data prediction model, inputting the fourth field data item, the position relation and the attribute information into the field data prediction model, and acquiring a fifth field data item corresponding to the second missing area;

and integrating the first field data item, the third field data item and the fifth field data item to obtain the first field data of the first area, and finishing the acquisition.

8. The sewage treatment sludge cleaning management system of claim 6 wherein the determination module performs the following operations:

acquiring a preset sewage and sludge cleaning judgment model, inputting the first field data into the sewage and sludge cleaning judgment model, and acquiring a judgment result, wherein the judgment result comprises: need and not;

when the judgment result is that the sewage sludge is needed, the first area needs to be cleaned;

when the determination result is that the sewage sludge is unnecessary, the first area does not need to be cleaned up.

9. The sewage treatment sludge disposal management system of claim 6 wherein said formulation module performs the following operations:

acquiring a preset sewage sludge cleaning event set, wherein the sewage sludge cleaning event set comprises: a plurality of first sewage sludge clearing events;

performing feature analysis and extraction on the first field data to obtain a plurality of first features;

extracting second field data from the first sewage sludge cleanup event;

performing feature analysis and extraction on the second field data to obtain a plurality of second features;

performing feature matching on the first feature and the second feature, if the first feature and the second feature are matched, taking the first feature matched with the first feature as a first target feature, and simultaneously taking the first feature except the first target feature in the first feature as a second target feature and associating the first feature with a corresponding first sewage sludge cleaning event;

acquiring a first price weight corresponding to the first target characteristic, and associating the first price weight with a corresponding first sewage sludge cleaning event;

acquiring second attribute information of the first area;

performing feature analysis and extraction on the second attribute information to obtain a plurality of third features;

extracting third attribute information in the first sewage sludge cleaning event;

performing feature analysis and extraction on the third attribute information to obtain a plurality of fourth features;

performing feature matching on the third feature and the fourth feature, if the matching is matched, taking the matched third feature as a third target feature, and simultaneously taking the third feature except the third target feature in the third feature as a fourth target feature and associating the third feature with the corresponding first sewage sludge cleaning event;

acquiring a second value weight corresponding to the third target characteristic, and associating the second value weight with the first sewage sludge cleaning event;

summarizing the first and second cost value weights associated with the first sewage sludge cleaning event to obtain a first cost value weight sum;

selecting the maximum first price weight sum as a second price weight sum;

if the second value weight sum is larger than or equal to a preset value weight and a threshold value, extracting a first sewage sludge cleaning process corresponding to the first sewage sludge cleaning event;

generating a scheduling strategy based on the first sewage and sludge cleaning process;

otherwise, sorting the first price weight sums from large to small to obtain a value weight sum sequence;

traversing the first value weight sum from the starting point to the end point of the value weight sum sequence;

taking the traversed first value weight sum as a third value weight sum in each traversal;

extracting the third valence weight and a corresponding second sewage-sludge cleaning course in the first sewage-sludge cleaning event;

setting the second target feature and the fourth target feature associated with the first sewage sludge cleaning event as a fifth target feature;

acquiring a preset problem prediction model, inputting the second sewage and sludge cleaning process and the fifth target characteristic into the problem prediction model, and acquiring at least one problem item, wherein the problem item comprises: a question location, a question type, a first question content, and a corresponding first question value;

acquiring a second area site three-dimensional model corresponding to the first area;

performing sewage rendering configuration on the second area on-site three-dimensional model based on the first on-site data, setting a monitoring point at a virtual position corresponding to the problem position in the second area on-site three-dimensional model, giving a monitoring task corresponding to the problem type to the monitoring point, and obtaining a third area on-site three-dimensional model;

acquiring a preset simulation space, inputting the third area field three-dimensional model into the simulation space, and simulating the second sewage and sludge cleaning process;

acquiring monitoring data returned by the monitoring points at regular time, comparing and analyzing the monitoring data and the problem content, determining whether the monitoring data and the problem content are consistent, and if so, taking the corresponding first problem value as a second problem value;

after the simulation is finished, summarizing the second problem value as a problem value sum, and associating the problem value sum with the corresponding second sewage sludge cleaning process;

after traversing is finished, taking the minimum problem value and the associated second sewage sludge cleaning process as a third sewage sludge cleaning process, and simultaneously taking the first problem content corresponding to the minimum problem value and the second problem value obtained in a summary manner as a second problem content;

and acquiring a preset problem solving model, and inputting the third sewage sludge cleaning process and the second problem content into the problem solving model to acquire a scheduling strategy.

10. The sewage treatment sludge disposal and management system of claim 6 further comprising:

and the tracking module is used for dynamically tracking the process of cleaning the sewage and the sludge in the first area.

Images