Land reclamation area supervision method and device, computer equipment and medium
Through the online learning model, the operation plan is adjusted in real time during the land reclamation process, the problem of insufficient efficiency and accuracy of land reclamation supervision in the existing technology has been solved, and efficient and flexible land reclamation supervision has been achieved.
Patent Information
- Application Number
- CN202410986316.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-23
- Publication Date
- 2024-11-12
AI Technical Summary
In the existing technology, the rationality and efficiency of expected plan adjustments in the regional supervision process of land reclamation are poor, and are affected by human subjective factors, resulting in low efficiency and accuracy of land reclamation.
The online learning model is used to obtain the actual and expected progress at the end of each rectification work interval, adjust the follow-up operation plan through adaptiveness, and extend the total duration of rectification work when conditions are not met to optimize the plan to ensure rationality and timeliness.
It has achieved efficient, accurate and flexible supervision of land reclamation, reduced human intervention, discovered problems earlier and adjusted plans in a timely manner, and improved the rationality and efficiency of rectification operations.
Smart Images

Figure CN118941022A_ABST
Abstract
Description
Technical Field
[0001] The present invention is applicable to the field of land supervision technology, and in particular relates to a land consolidation area supervision method, device, computer equipment and medium. Background Art
[0002] Land consolidation includes accelerating the promotion of high-standard farmland, effectively strengthening the protection of arable land quantity and quality, implementing arable land restoration and maintenance, promoting the consolidation of other agricultural land, optimizing the layout of rural construction land, and promoting the consolidation of idle and inefficient rural land. It supervises the implementation of land consolidation tasks so that the implementation of land consolidation can be carried out according to the planned expected progress, which can effectively ensure the efficiency of land consolidation.
[0003] The current process supervision of land consolidation areas usually compares the actual progress completed within a time period with the expected progress that should be completed. When the actual progress completed is less than the expected progress that should be completed, a reminder or early warning message is generated to the supervisory side, and the supervisory side manually adjusts the expected plan.
[0004] The existing method of manually adjusting the expected plan when the progress of land consolidation lags behind is affected by human subjective factors, resulting in poor rationality of the expected plan adjustment and poor timeliness of the manual adjustment, which ultimately leads to poor efficiency and accuracy of the current land consolidation area supervision. Summary of the invention
[0005] In view of this, the embodiments of the present invention provide a land consolidation area supervision method, apparatus, computer equipment and medium to solve the problem of poor rationality and efficiency of expected plan adjustment in the current land consolidation supervision process.
[0006] In a first aspect, a land consolidation area supervision method is provided, the method comprising:
[0007] Set the intervals between land reclamation operations, and use the end time of each of the intervals as the sampling time, obtain the actual progress and expected progress of the land reclamation operation at the current sampling time, input them into the online learning model, and output the optimized progress;
[0008] Determine whether the optimization progress meets the preset conditions. When the optimization progress meets the preset conditions, use the optimization progress as the expected progress to complete the remediation work under the subsequent remediation work intervals. When the optimization progress does not meet the preset conditions, determine whether the number of remediation work intervals is less than the interval number threshold. If so, increase the number of remediation work intervals by one, and update the actual progress and expected progress accordingly, input them into the online learning model to re-acquire the optimization progress, and then return to execute the step of determining whether the optimization progress meets the preset conditions.
[0009] When the optimization progress does not meet the preset conditions and the number of remediation work intervals is not less than the interval number threshold, it is determined that the degree of lag in remediation work progress is uncontrollable and a regulatory warning is issued.
[0010] In a second aspect, a land consolidation area supervision device is provided, the device comprising:
[0011] An update planning acquisition module is used to set the interval of land reclamation operations, and take the end time of each of the intervals as the sampling time, obtain the actual progress and expected progress of the land reclamation operation at the current sampling time, input them into the online learning model, and output the optimized progress;
[0012] The update planning implementation module is used to determine whether the optimization progress meets the preset conditions. When the optimization progress meets the preset conditions, the optimization progress is used as the expected progress to complete the remediation work under the subsequent remediation work interval; when the optimization progress does not meet the preset conditions, it is determined whether the number of remediation work intervals is less than the interval number threshold. If it is less, the number of remediation work intervals is increased by one, and the actual progress and the expected progress are updated accordingly, and then input into the online learning model to re-acquire the optimization progress, and then return to execute the step of determining whether the optimization progress meets the preset conditions;
[0013] The planning update failure warning module is used to determine that the degree of lag in the progress of the remediation work is uncontrollable and issue a regulatory warning when the optimization progress does not meet the preset conditions and the number of the remediation work intervals is not less than the interval number threshold.
[0014] In a third aspect, an embodiment of the present invention provides a computer device, comprising a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor implements the land reclamation area supervision method as described in the first aspect when executing the computer program.
[0015] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the land consolidation area supervision method as described in the first aspect is implemented.
[0016] Compared with the prior art, the present invention has the following beneficial effects:
[0017] The present invention uses an online learning model to train the actual progress and expected progress of the remediation operation at the end of each remediation operation interval. After each remediation operation interval, the subsequent remediation operation plan is adaptively adjusted in real time based on the previous operation situation. The supervision method does not require human participation, ensuring timely, efficient and reasonable tracking and adjustment of the remediation operation; at the same time, when the adjusted plan does not meet the rationality of the remediation operation, the present invention repeatedly adjusts the output of the online learning model by extending the total duration of the remediation operation under permitted circumstances, so as to increase the possibility that the operation plan output by the online learning model is reasonable and available, and the supervision side is finally notified only when the optimized progress that meets the interval quantity threshold and the preset conditions cannot be generated at the current sampling moment. Compared with conventional supervision methods, the method of the present invention can discover problems earlier and make the implementation of land remediation more flexible, and finally realizes efficient, accurate and flexible supervision of land remediation. BRIEF DESCRIPTION OF THE DRAWINGS
[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.
[0019] Figure 1 This is a schematic diagram of an application environment of a land consolidation area supervision method provided by Embodiment 1 of the present invention;
[0020] Figure 2 It is a flow chart of a land consolidation area supervision method provided in the first embodiment of the present invention;
[0021] Figure 3 It is a structural schematic diagram of a land consolidation area supervision device provided in Embodiment 3 of the present invention;
[0022] Figure 4 It is a structural diagram of a computer device provided in Embodiment 4 of the present invention. DETAILED DESCRIPTION
[0023] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present invention.
[0024] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.
[0025] It should also be understood that the term "and / or" used in the present description and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.
[0026] As used in the present specification and the appended claims, the term "if" may be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" may be interpreted as meaning "upon determination" or "in response to determining" or "upon detection of [described condition or event]" or "in response to detecting [described condition or event]", depending on the context.
[0027] In addition, in the description of the present specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.
[0028] References to "one embodiment" or "some embodiments" etc. described in the present specification mean that one or more embodiments of the present invention include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.
[0029] The embodiments of the present invention can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.
[0030] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.
[0031] It should be understood that the order of execution of the steps in the following embodiments does not imply a precedence of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.
[0032] In order to illustrate the technical solution of the present invention, specific embodiments are provided below for illustration.
[0033] A land consolidation area supervision method provided in the first embodiment of the present invention can be applied in the following aspects: Figure 1 In an application environment, a client communicates with a server. The client includes but is not limited to a PDA, a desktop computer, a laptop computer, an ultra-mobile personal computer (UMPC), a netbook, a cloud terminal device, a personal digital assistant (PDA), and other terminal devices. The server can be implemented by an independent server or a server cluster consisting of multiple servers.
[0034] The above land consolidation area supervision method can be applied to Figure 1 The client in the client, the terminal device corresponding to the client connects to the target database through a preset application programming interface (API). When the target data is driven to execute the corresponding task, a corresponding task log will be generated, and the above task log can be collected through the API. The above land consolidation area supervision method can also be applied to Figure 1 The server in the server, the computer device corresponding to the server is connected to the corresponding database, rule base, etc. to obtain the corresponding data in the database. The above-mentioned computer device can also be connected to the client to collect data and control instructions sent by the client user.
[0035] See also Figure 2 , is a flow chart of a land consolidation area supervision method provided in Embodiment 1 of the present invention. The land consolidation area supervision method may include the following steps:
[0036] S101, setting the interval between land reclamation operations, and taking the end time of each of the intervals as the sampling time, obtaining the actual progress and expected progress of the land reclamation operation at the current sampling time and inputting them into the online learning model, and outputting the optimized progress.
[0037] The essential purpose of land reclamation operation monitoring is to know the progress of the reclamation operation in real time, and to make adaptive adjustments to the subsequent schedule according to the deviation between the actual progress and the expected progress, specifically the lag of the actual progress compared to the expected progress, to ensure that the pre-planned reclamation work volume is completed as much as possible within the expected time.
[0038] In order to know the progress of the operation, it is necessary to collect and obtain the progress of the remediation operation. Therefore, this embodiment sets the remediation operation interval, and uses the end time of the remediation operation interval as the sampling time. The remediation operation interval is the time period of a remediation operation. For example, the duration of the remediation operation interval can be set to one hour, or one day. Considering that the workload of the remediation operation is large, this embodiment preferably sets the duration of the remediation operation interval to one day, and uses the end time of each day as the sampling time corresponding to each remediation operation interval. The duration of the remediation operation interval is usually related to the total duration of the overall remediation operation. The reason why this embodiment preferably sets the duration of the remediation operation interval to one day is also considered that the total duration of the remediation operation is often set in days.
[0039] After clarifying the remediation operation interval and the corresponding sampling time, based on the optimization of this embodiment, sampling can be performed at the end time of each remediation operation interval, that is, at the end time of each day, to obtain the actual progress of the remediation operation after the end of the day and the original expected progress.
[0040] It is easy to understand that the total duration of the remediation operation should be several days, and one remediation operation interval is one day. Before the formal remediation operation, each remediation operation interval, that is, the sub-progress that needs to be completed every day, will be specified, and it is guaranteed that the operation progress will be 100% completed after the total duration of the remediation operation. Therefore, it can be seen that the expected progress is actually the planned progress, which contains the specific sub-progress that needs to be completed every day, and the actual progress is the progress that is updated in real time as the remediation operation is implemented, which is specifically the sub-progress that is actually completed every day before the current sampling time.
[0041] After completing the remediation work on the same day, that is, after a remediation work interval, at the end of the day, the sampling time can be used to collect information to determine the specific sub-progress values completed each day from the beginning of the remediation work to the end of today, and thus form the actual progress information. After comparing the actual progress with the expected progress, the deviation between the actual completed sub-progress and the expected sub-progress can be completed in each remediation work interval during the previous operation time, that is, each day, and it can be determined whether adaptive adjustments need to be made to the subsequent expected progress content.
[0042] Considering that the progress of the remediation work is a process that changes with the number of days, and the expected progress also needs to be adjusted once a day according to the actual progress after the end of each day, this embodiment preferably uses an online learning model to complete the above deviation comparison and adaptive adjustment. Specifically, after obtaining the corresponding actual progress and expected progress at the current sampling time, the obtained actual progress and expected progress are input into the online learning model. The online learning model needs to perform a training process each time it receives a new input, so as to obtain the output corresponding to the input after the training process is completed. That is, after the training process converges, the output of the converged online learning model is used as the optimization progress.
[0043] The training of the online learning model requires setting constraints. The specific setting basis can be that, considering the limited capacity of the remediation operation, a sub-progress peak threshold for each day's operation can be set to constrain the sub-progress value of each day in the optimization progress. In addition, the remediation operation must be 100% completed after the total duration of the remediation operation. Therefore, the sum of the sub-progress values of each day can be set to 1 to constrain the sub-progress value of each day in the optimization progress, and so on.
[0044] The so-called convergence of the online learning model is easy to understand, which means that the sum of all constraints decreases by less than the set reduction threshold after a set number of consecutive training times. At this time, it indicates that as the training progresses, the sum of the constraints basically no longer decreases, and the training end point has been reached.
[0045] S102, judging whether the optimization progress meets the preset conditions. When the optimization progress meets the preset conditions, taking the optimization progress as the expected progress, completing the remediation work under the subsequent remediation work intervals; when the optimization progress does not meet the preset conditions, judging whether the number of remediation work intervals is less than the interval number threshold, if so, adding one to the number of remediation work intervals, and correspondingly updating the actual progress and the expected progress, inputting them into the online learning model to re-acquire the optimization progress, and then returning to execute the step of judging whether the optimization progress meets the preset conditions.
[0046] Although the online learning model is often trained to converge after step S101 and the output result of the converged online learning model can be used as the optimization progress, it is easy to understand that the optimization progress may not meet the actual requirements of the expected progress. This actual requirement as the preset progress is recorded as the preset condition.
[0047] If the optimized progress is to be truly used as the expected progress, that is, as an available subsequent progress plan, it should satisfy the requirement that the sum of the sub-progress values corresponding to each remediation operation interval (that is, every day) is 1, so as to ensure that the remediation operation is completed just after the total duration of the remediation operation, and as described in step S101, the remediation operation capacity of the remediation operation within a remediation operation interval is limited, so it is also necessary to ensure that the sub-progress value corresponding to each remediation operation interval (that is, every day) in the optimized progress is not greater than the sub-progress peak threshold. Therefore, this embodiment sets the preset condition that the sum of the sub-progress values corresponding to each remediation operation interval in the optimized progress is 1 and each sub-progress value is not greater than the preset sub-progress peak threshold.
[0048] When the optimization progress meets the preset conditions, it means that it can truly be used as the expected progress. At this time, the optimization progress output when the online learning model converges can be used as the expected progress. The expected progress after replacing the optimization progress is the planned progress arrangement after adaptively adjusting the planned content after the current sampling moment according to the specific deviation between the actual progress before the current sampling moment and the previous expected progress.
[0049] When the optimization progress does not meet the preset conditions, it is very likely that there is not much remaining remediation work time after the current sampling moment, resulting in a sub-progress value of a certain day in the optimization progress output by the online learning model exceeding the sub-progress peak threshold representing the upper limit of the remediation work capacity for a single day, or the sum of all sub-progress values cannot be guaranteed to be 1 after the remaining remediation work time after the current sampling moment, that is, it cannot be guaranteed that the remediation work volume will be 100% completed after the total remediation work time.
[0050] To this end, the total duration of the remediation operation can be extended to increase the available possibility of optimizing the progress. This embodiment accordingly sets an interval number threshold for comparison with the number of remediation operation intervals. It is easy to understand that since this embodiment is to increase the total duration of the remediation operation by increasing the number of remediation operation intervals, the interval number threshold must first be no less than the initial number of remediation operation intervals, and its specific value can be set according to the extendibility of the total duration of the remediation operation. If the extendibility is large, the interval number threshold is set accordingly large, and if the extendibility is small, the interval number threshold is set accordingly small; in particular, when the total duration of the remediation operation cannot be extended, that is, the number of remediation operation intervals cannot be increased, the value of the interval number threshold is set to the initial number of remediation operation intervals.
[0051] After setting the interval number threshold, for the above-mentioned situation when the optimization progress does not meet the preset conditions, the number of remediation operation intervals is increased by one. At this time, since the number of remediation operation intervals is increased by one, the actual progress and expected progress at the current sampling time will both have one more remediation operation interval at the end, and the corresponding sub-progress values corresponding to the increased remediation operation intervals in the actual progress and expected progress are both 0 because the corresponding sub-progress has not actually been carried out and has not been planned in advance.
[0052] After increasing the number of remediation work intervals by one and adding the sub-progress corresponding to the increased remediation work interval to the actual progress and expected progress, the update of the actual progress and the expected progress is completed, the updated actual progress and expected progress are re-input into the online learning model, and the optimization progress is re-output after the training converges, and the re-output optimization progress is used to judge again whether it meets the preset conditions.
[0053] That is, after adding one to the number of remediation operation intervals, the online learning model actually outputs the optimization progress based on the actual progress and expected progress of the input, and judges whether it meets the preset conditions based on the optimization progress. When the optimization progress obtained after adding one to the number of remediation operation intervals meets the preset conditions, the optimization progress can be used as the expected progress.
[0054] S103, when the optimization progress does not meet the preset conditions and the number of the remediation operation intervals is not less than the interval number threshold, it is determined that the degree of lag in the remediation operation progress is uncontrollable and a regulatory warning is issued.
[0055] However, when the operation of adding one to the number of remediation work intervals reaches the threshold number of intervals, the corresponding optimization progress after each addition operation does not meet the preset conditions. This means that even if the total duration of the remediation operation is extended to the maximum allowed extent, it cannot make up for the lagging work volume of the current actual progress. Therefore, at the current sampling time, it can be determined that the degree of lag in the remediation work progress is uncontrollable, and a regulatory warning is issued.
[0056] This embodiment uses an online learning model to train the actual progress and expected progress of the remediation work at the end of each remediation work interval. After each remediation work interval, the subsequent expected progress, that is, the remediation work plan, is adaptively adjusted in real time based on the previous work situation. When the adjusted plan cannot meet the reasonable requirements of the actual remediation work, the total duration of the remediation work is extended under permitted circumstances to optimize the output of the online learning model, thereby increasing the possibility that the work plan output by the online learning model meets the reasonable requirements of the actual remediation work. This supervision method of this embodiment does not require human participation, ensuring timely, efficient and reasonable tracking and adjustment of the remediation work. At the same time, this embodiment notifies the supervision side only when the optimization progress that meets the interval quantity threshold and preset conditions cannot be generated at the current sampling moment. Compared with conventional supervision methods, problems can be discovered earlier, and land remediation implementation can be made more flexible, ultimately achieving efficient, accurate and flexible supervision of land remediation.
[0057] The second embodiment of the present invention provides a method for supervising a land consolidation area. The embodiment further clarifies the expression forms of the implementation progress, the expected progress and the optimization progress, and clarifies the specific working mode of the online learning model based on the expression forms:
[0058] As in the above embodiment, since the workload of the remediation operation is large and generally measured in days, the present embodiment also preferably sets the duration of the remediation operation interval to one day. Then, the actual progress and expected progress obtained at the end of the remediation operation interval as the sampling time can be set to a one-dimensional vector of 1*M, where M is the number of remediation operation intervals, which is specifically the total number of days for the remediation operation in the present embodiment. Each column in the vector represents each operation day, and the elements of each column represent the sub-progress value under the corresponding operation day. The present embodiment preferably normalizes all sub-progress values in the vector. Accordingly, it can be seen that in order to ensure that the remediation operation is completed after the total duration of the remediation operation ends, the sum of each sub-progress value in the expected progress should be 1.
[0059] It should be noted that in this embodiment, the progress of the land reclamation task is quantifiable as prior information. For example, the ratio of the area of the area where land reclamation is completed within a certain number of working days and the area of the area to be reclaimed in the overall plan can be used as the sub-progress value corresponding to the number of working days.
[0060] Corresponding to the actual progress and expected progress input to the online learning model, the optimized progress output by the online learning model is also a one-dimensional vector of 1*M. The optimized progress represents the scheduling plan content after the original expected progress is optimized after the online learning model training. This kind of optimization of the original expected progress can only change the plan content after the current sampling time, but cannot change the historical work progress before the current sampling time. Therefore, in the optimized progress, the sub-progress values corresponding to the days before the current sampling time should be completely consistent with the sub-progress values corresponding to the days before the current sampling time in the actual progress.
[0061] The training process of the online learning model requires setting constraints. Whether the constraints are set reasonably or not directly affects the rationality and accuracy of the adjustment of the optimization progress obtained after the training converges to the expected progress. In this embodiment, the constraints for training the online learning model are set in four parts, namely, sub-progress peak constraints, total progress constraints, trend constraints, and historical progress constraints, in combination with the usage scenarios and training purposes of the online learning model.
[0062] The sub-progress peak constraint is:
[0063]
[0064] Among them, e represents a natural constant, a m represents the mth element of the M elements in the output vector obtained during the training of the online learning model, max(a m ) represents the maximum element among the M elements in the output vector obtained by the online learning model during training, and r1 represents the preset sub-progress peak threshold.
[0065] The natural constant e is taken as the base and max(a m )-r1 is used as an exponent to form a sub-progress peak constraint. It can be seen that when the sub-progress peak value in the output vector obtained during online learning model training exceeds the preset sub-progress peak threshold, the more serious the exceeding phenomenon is, the greater the increase rate of the sub-progress peak constraint, that is, the exponential mapping result. Compared with the method of linearly characterizing the output vector exceeding the preset threshold and constraining it, this method of constraining the sub-progress peak value of the output vector in an exponential form can more effectively make the sub-progress value of the output vector as small as possible as small as possible, thereby improving training efficiency.
[0066] The overall progress constraint is:
[0067]
[0068] Wherein, M represents the total number of element values in the output vector obtained during training of the online learning model.
[0069] It is easy to understand that the output vector output by the online learning model after convergence, that is, the optimization progress to be output in the end, is a sub-progress plan for each day under the total duration of the entire remediation operation after optimization and update. Therefore, the sum of the element values in each column, that is, the sum of the sub-progress corresponding to each day, should be maintained at 100% progress, that is, maintained at 1.
[0070] The trend constraint is:
[0071] cos(B2,C2)
[0072] Among them, B2 represents the sub-vector composed of the n+1th to Mth elements in the output vector obtained during training of the online learning model, C2 represents the sub-vector composed of the n+1th to Mth elements in the expected progress input to the online learning model, n represents the number of the remediation operation intervals before the current sampling moment, and cos(B2,C2) represents the cosine similarity between the sub-vector B2 and the sub-vector C2.
[0073] It should be noted that, since the current sampling moment is the moment when the current remediation operation interval ends, the number n of the remediation operation intervals before the current sampling moment includes the current remediation operation interval.
[0074] The reason why the above trend constraint is constructed to constrain the similarity between each remediation operation interval, that is, the daily sub-progress, and the original expected progress, that is, the originally planned daily sub-progress in the output vector after the current sampling moment during the online learning model training is because the initial expected progress is set manually, and its setting process usually refers to various prior information, that is, the initial expected progress is usually considered in the process of manual setting. The actual allowable conditions of the operation at different stages within the total duration of the remediation operation are different, such as personnel deployment, material arrival time, etc. Therefore, through this trend constraint, it can be ensured as much as possible that the specific size of each remediation operation interval, that is, the daily sub-progress value in the subsequent optimization progress is consistent with the prior information, further improving the rationality of land remediation supervision.
[0075] The historical progress constraint is:
[0076] dis(B1,D1)
[0077] Among them, B1 represents a sub-vector composed of the 1st to nth elements in the output vector obtained by the online learning model during training, D1 represents a sub-vector composed of the 1st to nth elements in the actual progress, and dis(B1,D1) represents the Euclidean distance between B1 and D1.
[0078] It is easy to understand that since the status of the completed remediation work is a given and cannot be changed, the output vector output by the online learning model during the training process must ensure that the daily sub-progress before the current sampling time is consistent with the status of the completed remediation work, so as to serve as a guiding basis for subsequent plans to ensure the rationality and accuracy of subsequent plans, so it is necessary to construct the above-mentioned historical progress constraint.
[0079] It should be noted that, during the training of the online learning model, the above four constraints can correspond to weights of different sizes respectively. In the present embodiment, the weight corresponding to the historical progress constraint is preferably the largest, followed by the weights corresponding to the peak constraint and the total value constraint respectively, and the weight corresponding to the trend constraint is the smallest. In this way, it can be achieved that, in the final optimization progress, the sub-progress values corresponding to the days before the current sampling time are consistent with the sub-progress values corresponding to the days in the actual progress.
[0080] This embodiment makes specific limitations on the constraints in the online learning model training process. In addition, in the process of constructing the constraints, in addition to establishing a historical progress constraint to ensure that the sub-progress information before the current moment in the optimization progress is consistent with the actual situation, and establishing a total progress constraint to ensure that the sum of each sub-progress of the optimization progress is 1 (that is, 100%), a sub-progress peak constraint that considers the upper limit of the operating capacity of a single remediation operation interval is specially constructed, as well as a trend constraint that makes the optimization progress more consistent with the prior information, further improving the rationality and output speed of the optimization progress finally obtained by the online learning model.
[0081] Corresponding to the method of the above embodiment, Figure 3 The structural block diagram of the land consolidation area supervision device provided in the third embodiment of the present invention is shown. The above-mentioned supervision device is applied to a computer device, and the computer device is connected to the target database through a preset application program interface. When the target database is driven to execute a corresponding task, a corresponding task log is generated, and the above-mentioned task log can be collected through the API. For the convenience of explanation, only the part related to the embodiment of the present invention is shown.
[0082] See also Figure 3 , the supervision device comprises:
[0083] The update planning acquisition module 31 is used to set the interval of land reclamation operations, and take the end time of each of the intervals of land reclamation operations as the sampling time, obtain the actual progress and expected progress of the land reclamation operations at the current sampling time, input them into the online learning model, and output the optimized progress;
[0084] The update planning implementation module 32 is used to determine whether the optimization progress meets the preset conditions. When the optimization progress meets the preset conditions, the optimization progress is used as the expected progress to complete the remediation work under the subsequent remediation work interval; when the optimization progress does not meet the preset conditions, it is determined whether the number of remediation work intervals is less than the interval number threshold. If it is less, the number of remediation work intervals is increased by one, and the actual progress and the expected progress are updated accordingly, and then input into the online learning model to re-acquire the optimization progress, and then return to execute the step of determining whether the optimization progress meets the preset conditions;
[0085] The planning update failure warning module 33 is used to determine that the degree of lag in the progress of the remediation work is uncontrollable and issue a regulatory warning when the optimization progress does not meet the preset conditions and the number of the remediation work intervals is not less than the interval number threshold.
[0086] Optionally, the update plan acquisition module 31 includes:
[0087] The progress representation form limiting unit is used to limit the actual progress, expected progress and optimized progress to be one-dimensional vectors of 1*M, where M represents the number of remediation operation intervals, and the value of the elements in each column of the vector represents the sub-progress value corresponding to each remediation operation interval.
[0088] Optionally, the update plan acquisition module 31 further includes:
[0089] The optimization progress acquisition unit is used for the online learning model to perform training with constraint conditions after receiving the input actual progress and expected progress. When the training process converges, the output result of the converged online learning model is output as the optimization progress; the constraint conditions include sub-progress peak constraint, total progress constraint, trend constraint and historical progress constraint.
[0090] Optionally, the update plan acquisition module 31 further includes:
[0091] The constraint condition limiting unit is used to limit the sub-progress peak constraint, the total progress constraint, the trend constraint and the historical progress constraint respectively:
[0092] The sub-progress peak constraint is:
[0093]
[0094] Among them, e represents a natural constant, a m represents the mth element of the M elements in the output vector obtained during the training of the online learning model, max(a m) represents the maximum element among the M elements in the output vector obtained by the online learning model during training, and r1 represents a preset sub-progress peak threshold;
[0095] The overall progress constraint is:
[0096]
[0097] Wherein, M represents the total number of element values in the output vector obtained by the online learning model during training;
[0098] The trend constraint is:
[0099] cos(B2,C2)
[0100] Wherein, B2 represents a sub-vector composed of the n+1th to Mth elements in the output vector obtained by the online learning model during training, C2 represents a sub-vector composed of the n+1th to Mth elements in the expected progress input to the online learning model, n represents the number of the remediation operation intervals before the current sampling time, and cos(B2, C2) represents the cosine similarity between the sub-vector B2 and the sub-vector C2;
[0101] The historical progress constraint is:
[0102] dis(B1,D1)
[0103] Among them, B1 represents a sub-vector composed of the 1st to nth elements in the output vector obtained by the online learning model during training, D1 represents a sub-vector composed of the 1st to nth elements in the actual progress, and dis(B1,D1) represents the Euclidean distance between B1 and D1.
[0104] Optionally, the update planning implementation module 32 includes:
[0105] The preset condition limiting unit is used to limit the preset condition to mean that the sum of the sub-progress values corresponding to each remediation operation interval in the optimization progress is 1 and each sub-progress value is not greater than a preset sub-progress peak threshold.
[0106] Optionally, the update plan implementation module 32 further includes:
[0107] The progress update mode limiting unit is used to limit the actual progress and expected progress of the update in the following ways:
[0108] After the number of the remediation operation intervals is increased by one, the sub-progress value corresponding to the newly added remediation operation interval is added to the actual progress and the expected progress.
[0109] Optionally, the monitoring device further includes:
[0110] The limiting module 34 is used to limit the sub-progress values corresponding to the remediation operation intervals before the current sampling time in the optimization progress to be the same as the sub-progress values corresponding to the remediation operation intervals before the current sampling time in the actual progress; and the interval number threshold is not less than the initial remediation operation interval number.
[0111] It should be noted that the information interaction, execution process and other contents between the above modules are based on the same concept as the embodiment of the method of the present invention. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.
[0112] Figure 4 This is a schematic diagram of the structure of a computer device provided in Embodiment 4 of the present invention. Figure 4 As shown, the computer device of this embodiment includes: at least one processor ( Figure 4 Only one is shown), a memory, and a computer program stored in the memory and executable on at least one processor, wherein when the processor executes the computer program, the steps in any of the above-mentioned land reclamation area supervision method embodiments are implemented.
[0113] The computer device may include, but is not limited to, a processor and a memory. Those skilled in the art will appreciate that Figure 4 This is merely an example of a computer device and does not constitute a limitation on the computer device. The computer device may include more or fewer components than those shown in the figure, or a combination of certain components, or different components. For example, it may also include a network interface, a display screen, and an input device.
[0114] The processor may be a CPU, or other general-purpose processors, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.
[0115] The memory includes a readable storage medium, an internal memory, etc., wherein the internal memory may be the memory of a computer device, and the internal memory provides an environment for the operation of an operating system and computer-readable instructions in the readable storage medium. The readable storage medium may be a hard disk of a computer device, and in other embodiments may also be an external storage device of a computer device, for example, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on a computer device. Further, the memory may also include both an internal storage unit of a computer device and an external storage device. The memory is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as program codes of computer programs, etc. The memory may also be used to temporarily store data that has been output or is to be output.
[0116] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention. The specific working process of the units and modules in the above-mentioned device can refer to the corresponding process in the above-mentioned method embodiment, which will not be repeated here. If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned method embodiment can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may at least include: any entity or device capable of carrying computer program code, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.
[0117] The present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by a computer program product. When the computer program product runs on a computer device, the computer device can implement the steps in the above-mentioned method embodiment when executing.
[0118] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0119] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.
[0120] In the embodiments provided by the present invention, it should be understood that the disclosed devices / computer equipment and methods can be implemented in other ways. For example, the device / computer equipment embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0121] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0122] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.
Claims
1. A land consolidation area supervision method, characterized in that: The method comprises: Set the intervals between land reclamation operations, and use the end time of each of the intervals as the sampling time, obtain the actual progress and expected progress of the land reclamation operation at the current sampling time, input them into the online learning model, and output the optimized progress; Determine whether the optimization progress meets the preset conditions. When the optimization progress meets the preset conditions, use the optimization progress as the expected progress to complete the remediation work under the subsequent remediation work intervals. When the optimization progress does not meet the preset conditions, determine whether the number of remediation work intervals is less than the interval number threshold. If so, increase the number of remediation work intervals by one, and update the actual progress and expected progress accordingly, input them into the online learning model to re-acquire the optimization progress, and then return to execute the step of determining whether the optimization progress meets the preset conditions. When the optimization progress does not meet the preset conditions and the number of remediation work intervals is not less than the interval number threshold, it is determined that the degree of lag in remediation work progress is uncontrollable and a regulatory warning is issued.
2. The land consolidation area supervision method according to claim 1, characterized in that: The actual progress, expected progress and optimized progress are all one-dimensional vectors of 1*M, where M represents the number of remediation operation intervals, and the values of the elements in each column of the vector represent the sub-progress values corresponding to each remediation operation interval.
3. The land consolidation area supervision method according to claim 2, characterized in that: The actual progress and expected progress of the land consolidation operation at the current sampling time are obtained and input into the online learning model, and the optimization progress is output, including: After receiving the input actual progress and expected progress, the online learning model is trained with constraint conditions, and when the training process converges, the output result of the converged online learning model is output as the optimization progress; The constraint conditions include sub-progress peak constraint, total progress constraint, trend constraint and historical progress constraint.
4. The land consolidation area supervision method according to claim 3 is characterized in that: The sub-progress peak constraint, total progress constraint, trend constraint and historical progress constraint are respectively: The sub-progress peak constraint is: Among them, e represents a natural constant, a m represents the mth element of the M elements in the output vector obtained during the training of the online learning model, max(a m ) represents the maximum element among the M elements in the output vector obtained by the online learning model during training, and r1 represents a preset sub-progress peak threshold; The overall progress constraint is: Wherein, M represents the total number of element values in the output vector obtained by the online learning model during training; The trend constraint is: cos(B2,C2) Wherein, B2 represents a sub-vector composed of the n+1th to Mth elements in the output vector obtained by the online learning model during training, C2 represents a sub-vector composed of the n+1th to Mth elements in the expected progress input to the online learning model, n represents the number of the remediation operation intervals before the current sampling time, and cos(B2, C2) represents the cosine similarity between the sub-vector B2 and the sub-vector C2; The historical progress constraint is: dis(B1,D1) Among them, B1 represents a sub-vector composed of the 1st to nth elements in the output vector obtained by the online learning model during training, D1 represents a sub-vector composed of the 1st to nth elements in the actual progress, and dis(B1,D1) represents the Euclidean distance between B1 and D1.
5. The land consolidation area supervision method according to claim 1, characterized in that: The preset condition means that the sum of the sub-progress values corresponding to each remediation operation interval in the optimization progress is 1 and each sub-progress value is not greater than a preset sub-progress peak threshold.
6. The land consolidation area supervision method according to claim 1, characterized in that: The method for updating the actual progress and expected progress is: After the number of the remediation operation intervals is increased by one, the sub-progress value corresponding to the newly added remediation operation interval is added to the actual progress and the expected progress.
7. The land consolidation area supervision method according to claim 1, characterized in that: In the optimized progress, the sub-progress values corresponding to the remediation operation intervals before the current sampling time are the same as the sub-progress values corresponding to the remediation operation intervals before the current sampling time in the actual progress; The interval number threshold is not less than the initial remediation operation interval number.
8. A land consolidation area supervision device, characterized in that: The monitoring device comprises: An update planning acquisition module is used to set the interval of land reclamation operations, and take the end time of each of the intervals as the sampling time, obtain the actual progress and expected progress of the land reclamation operation at the current sampling time, input them into the online learning model, and output the optimized progress; The update planning implementation module is used to determine whether the optimization progress meets the preset conditions. When the optimization progress meets the preset conditions, the optimization progress is used as the expected progress to complete the remediation work under the subsequent remediation work interval; when the optimization progress does not meet the preset conditions, it is determined whether the number of remediation work intervals is less than the interval number threshold. If it is less, the number of remediation work intervals is increased by one, and the actual progress and the expected progress are updated accordingly, and then input into the online learning model to re-acquire the optimization progress, and then return to execute the step of determining whether the optimization progress meets the preset conditions; The planning update failure warning module is used to determine that the degree of lag in the progress of the remediation work is uncontrollable and issue a regulatory warning when the optimization progress does not meet the preset conditions and the number of the remediation work intervals is not less than the interval number threshold.
9. A computer device, characterized in that: The computer device includes a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the land reclamation area supervision method according to any one of claims 1 to 7 is implemented.
10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the land reclamation area supervision method according to any one of claims 1 to 7 is implemented.
