A method and system for monitoring construction cost

Abstract

The embodiments of this specification provide a method and system for monitoring construction cost, the method comprising: acquiring construction image data based on a preset time interval; determining construction information of a construction unit based on the construction image data; determining progress characteristics of the construction unit based on the construction information; determining a matching relationship between progress characteristics and planned information of a construction project based on the progress characteristics; in response to the matching relationship not satisfying a first preset condition, adjusting the construction schedule, including: determining an abnormal unit in the construction unit; and adjusting the unit schedule of the abnormal unit. The method can predict or monitor the construction cost in real time, effectively improving work efficiency and saving resources while reducing costs.

Description

Technical Field

[0001] This specification relates to the field of engineering cost, and in particular to an engineering cost monitoring method and system. Background Art

[0002] With the rapid development of my country's economy, the demand for large-scale decoration projects is growing. These projects are usually large in scale, have a long construction period, and involve many links. Therefore, effective management of construction progress and cost control are particularly important. At present, the Building Information Modeling (BIM) model can be used to manage construction. For example, the initial BIM model is constructed based on the design data, the actual construction information is collected to construct the actual BIM model, the actual BIM model is compared with the initial BIM model, and the actual project progress and project cost are analyzed, so as to conduct further risk assessment or progress adjustment. However, in large-scale projects, frequent BIM construction for comparison and adjustment of project progress based on BIM information are cumbersome and affect efficiency.

[0003] Therefore, it is necessary to provide a project cost monitoring method and system that can periodically determine the cost corresponding to the current construction progress of each construction unit and / or the overall construction project, so as to predict or monitor the project cost in real time, effectively improve work efficiency, save resources and reduce costs. Summary of the invention

[0004] One or more embodiments of the present specification provide a method for monitoring construction cost. The method includes: acquiring construction image data based on a preset time interval; determining construction information of a construction unit based on the construction image data; determining progress characteristics of the construction unit based on the construction information; determining a matching relationship between the progress characteristics and the planned information of the construction project based on the progress characteristics; in response to the matching relationship not satisfying a first preset condition, adjusting the construction progress plan, wherein adjusting the construction progress plan includes: determining an abnormal unit in the construction unit; and adjusting the unit progress plan of the abnormal unit.

[0005] One or more embodiments of the present specification provide a construction cost monitoring system, the system comprising: an acquisition module, configured to acquire construction image data based on a preset time interval; a parameter determination module, configured to determine construction information of a construction unit based on the construction image data; a feature determination module, configured to determine progress features of the construction unit based on the construction information; a matching determination module, configured to determine a matching relationship between the progress features and the planned information of a construction project based on the progress features and the planned information; and an adjustment module, configured to adjust a construction progress plan in response to the matching relationship not satisfying a first preset condition, including: determining abnormal units among the construction units; and adjusting the unit progress plan of the abnormal units among the construction units.

[0006] One or more embodiments of the present specification provide a construction cost monitoring device, which includes at least one processor and at least one memory; the at least one memory is used to store computer instructions; the at least one processor is used to execute at least part of the computer instructions to implement a construction cost monitoring method as described in any embodiment of the present specification.

[0007] One or more embodiments of the present specification provide a computer-readable storage medium, wherein the storage medium stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the engineering cost monitoring method as described in any embodiment of the present specification.

[0008] Some embodiments of the present specification include at least the following beneficial effects: by periodically determining the construction cost corresponding to the current construction progress of each construction unit and / or the overall construction project, the project cost can be predicted or monitored in real time, effectively improving work efficiency, saving resources and reducing costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:

[0010] Figure 1 is an exemplary module diagram of a construction cost monitoring system according to some embodiments of this specification;

[0011] Figure 2 is an exemplary flow chart of a method for monitoring construction cost according to some embodiments of this specification;

[0012] Figure 3 is an exemplary schematic diagram of adjusting a construction schedule according to some embodiments of this specification;

[0013] Figure 4 is an exemplary schematic diagram of a cost model according to some embodiments of the present specification. DETAILED DESCRIPTION

[0014] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of this specification. For ordinary technicians in this field, this specification can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0015] It should be understood that the "system", "device", "unit" and / or "module" used herein are a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

[0016] As shown in this specification and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "comprise" and "include" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0017] Flowcharts are used in this specification to illustrate the operations performed by the system according to the embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed precisely in order. Instead, the steps may be processed in reverse order or simultaneously. At the same time, other operations may also be added to these processes, or one or more operations may be removed from these processes.

[0018] In order to effectively manage and control the costs of construction projects, some embodiments of the present specification provide a project cost monitoring method and system, which can obtain construction image data based on preset time intervals; determine the construction information of the construction unit based on the construction image data; determine the progress characteristics of the construction unit based on the construction information; determine the matching relationship between the progress characteristics and the planned information of the construction project based on the progress characteristics and the planned information; in response to the matching relationship not satisfying a first preset condition, adjust the construction progress plan, thereby predicting or monitoring the project cost in real time, effectively improving work efficiency and saving resources while reducing costs.

[0019] A construction project is a specific project that is prepared for construction or engineering. For example, a construction project can be the construction of a building. Construction projects can include many types. For example, construction projects such as building projects, decoration and renovation projects, installation projects, municipal projects, and landscaping projects. This specification takes a large-scale decoration and renovation project as an example. A large-scale decoration and renovation project refers to a decoration and renovation project for a large building. Large buildings can include office buildings, shopping malls, public buildings (such as libraries), etc. Decoration and renovation projects can include water and electricity renovation, wall, floor, and ceiling construction, and door and window installation.

[0020] Figure 1 It is an exemplary module diagram of a construction cost monitoring system according to some embodiments of this specification.

[0021] In some embodiments of this specification, a construction cost monitoring system is provided. In some embodiments, Figure 1 As shown, the construction cost monitoring system 100 may include an acquisition module 110 , an information determination module 120 , a feature determination module 130 , a matching determination module 140 and an adjustment module 150 .

[0022] The acquisition module 110 may be configured to acquire construction image data based on a preset time interval.

[0023] The information determination module 120 may be configured to determine the construction information of the construction unit based on the construction image data.

[0024] The characteristic determination module 130 may be configured to determine the progress characteristics of the construction unit based on the construction information.

[0025] The matching determination module 140 may be configured to determine a matching relationship between the progress feature and the plan information based on the progress feature and the plan information of the construction project.

[0026] In some embodiments, the matching determination module 140 can be further configured to: determine the unit cost consumption of the construction unit based on the progress characteristics; determine the unit planned cost of the construction unit based on the progress characteristics and the planning information; determine the matching relationship based on the unit cost consumption and the unit planned cost.

[0027] In some embodiments, the matching determination module 140 can be further configured to: determine the allocation ratio of at least one combined material based on progress characteristics; determine the actual material cost of the construction unit based on the allocation ratio and material consumption information; determine the actual labor cost of the construction unit based on progress characteristics and worker attendance information; determine the unit cost consumption of the construction unit based on the actual material cost and the actual labor cost.

[0028] The adjustment module 150 may be configured to adjust the construction schedule in response to the matching relationship not satisfying the first preset condition, including: determining an abnormal unit in the construction unit; and adjusting the unit schedule of the abnormal unit.

[0029] In some embodiments, the adjustment module 150 can be further configured to: in response to the matching relationship satisfying the first preset condition, determine the predicted consumption cost after the preset time period and the predicted planned cost for the preset time period based on the historical progress characteristics and planning information of the construction unit; based on the predicted consumption cost and the predicted planned cost, determine whether to adjust the construction progress plan.

[0030] In some embodiments, the adjustment module 150 can be further configured to: in response to the need to adjust the construction schedule, update the construction schedule through steps S1 to S4: S1, construct a schedule structure map based on the material procurement plan, the worker arrangement plan, and the construction schedule; S2, generate multiple candidate adjustment plans based on the schedule structure map; S3, based on multiple candidate adjustment plans and the schedule structure map, determine the predicted total progress and predicted total cost of the candidate adjustment plans through a second model, where the prediction model is a machine learning model; in response to the predicted total progress and the predicted total cost satisfying the second preset condition, determine the target adjustment plan based on multiple candidate adjustment plans; or in response to the predicted total progress and the predicted total cost not satisfying the second preset condition, repeat steps S1 to S3.

[0031] For detailed description of each module, see Figure 2~Figure 4 and its related description.

[0032] It should be understood that Figure 1 The system and its modules shown can be implemented in various ways. In some embodiments, the construction cost monitoring system 100 can be implemented by a processor. The processor can process data and / or information obtained from other devices or system components. The processor can execute program instructions based on these data, information and / or processing results to perform one or more functions described in the embodiments of this specification. As an example only, the processor may include a central processing unit (CPU), an application specific integrated circuit (ASIC), etc. or any combination thereof. In some embodiments, the processor may include multiple modules, and different modules may be used to execute different program instructions respectively.

[0033] It should be noted that the above description of the construction cost monitoring system and its modules is only for the convenience of description and cannot limit this specification to the scope of the embodiments. It is understandable that for those skilled in the art, after understanding the principle of the system, it is possible to arbitrarily combine the modules or form a subsystem to connect with other modules without deviating from this principle. In some embodiments, Figure 1The acquisition module 110, information determination module 120, feature determination module 130, matching determination module 140 and adjustment module 150 disclosed in the specification can be different modules in a system, or a module can realize the functions of two or more modules mentioned above. For example, each module can share a storage module, or each module can have its own storage module. Such variations are all within the protection scope of this specification.

[0034] Figure 2 is an exemplary flow chart of a method for monitoring construction cost according to some embodiments of this specification. Figure 2 As shown, the process 200 includes the following steps. In some embodiments, the process 200 can be executed by the construction cost monitoring system 100 or a processor.

[0035] In some embodiments, the construction cost monitoring system 100 or the processor can: acquire construction image data based on preset time intervals; determine construction information of the construction unit based on the construction image data; determine progress characteristics of the construction unit based on the construction information; determine the matching relationship between the progress characteristics and the planned information of the construction project based on the progress characteristics; adjust the construction progress plan in response to the matching relationship not satisfying a first preset condition, and adjusting the construction progress plan includes: determining abnormal units in the construction unit; and adjusting the unit progress plan of the abnormal unit.

[0036] Step 210: Acquire construction image data based on a preset time interval.

[0037] The construction image data is image data related to the construction project. In some embodiments, the construction image data may include multiple construction images. The construction image may be an image taken when the construction personnel report the construction progress. For example, the construction image may be an image of the construction site taken by the construction personnel when they get off work every day. The captured construction image data may be stored in a storage device or uploaded to a server, and the acquisition module 110 may acquire the construction image data from the storage device or the server at a preset time interval.

[0038] The preset time interval is the time interval between two adjacent acquisitions of construction images. The preset time interval may be 1 week, 2 weeks, 1 month, 2 months, etc. The preset time interval may represent the frequency of monitoring the cost of the construction project. For example, the smaller the preset time interval, the higher the frequency of acquiring the construction image data at this time. Accordingly, the frequency of cost monitoring based on the construction image data is higher.

[0039] In some embodiments, the preset time interval can be set manually.

[0040] In some embodiments, the preset time interval may be related to the data volume of the construction image data.

[0041] In some embodiments, the data volume of the construction image data may be determined by the number of construction images in the construction image data, or the total number of pixels in a plurality of construction images.

[0042] In some embodiments, the preset time interval may be negatively correlated to the amount of construction image data. The larger the amount of construction image data, the smaller the preset time interval, and the higher the frequency of acquiring construction image data. For example, the more images of construction image data, the higher the frequency of the processor monitoring the cost of the construction project.

[0043] In the embodiment of the present specification, the more images of the construction image data, the more complete the construction schedule is, the less downtime or idle time there is, and the more accurate the results (e.g., construction information) obtained based on the construction image data are. At this time, the cost monitoring requirements for the construction unit are also higher, and a higher frequency of monitoring can be performed to timely discover the occurrence of cost overruns.

[0044] Step 220: Determine the construction information of the construction unit based on the construction image data.

[0045] A construction unit is a unit obtained by dividing a construction project. When monitoring the cost of a construction project, the construction project can be divided into multiple construction units to monitor the costs of the multiple construction units separately.

[0046] In some embodiments, the information determination module 120 may divide the construction project into at least one construction unit.

[0047] In some embodiments, the information determination module 120 may divide the construction project according to the construction area to obtain at least one construction unit. For example, the construction units obtained by dividing the construction project according to the construction area may include stair construction units, room construction units, etc.

[0048] In some embodiments, the information determination module 120 may divide the construction project according to the construction task to obtain at least one construction unit. For example, the construction task may include water and electricity transformation, wall construction, ground construction, ceiling construction, door and window installation, etc. The construction units obtained according to the construction task division may include water and electricity transformation unit, wall construction unit, ground construction unit, ceiling construction unit, door and window installation unit, etc.

[0049] Construction information is information related to a construction project. In some embodiments, the construction information may include construction progress, reporting time, construction location, etc.

[0050] Construction progress is an indicator used to measure the completion of a construction unit. Construction progress can be expressed in a variety of ways. For example, construction progress can be expressed in a variety of ways such as a Gantt chart and a schedule. The Gantt chart and / or schedule can be used to express the construction plan (e.g., planned start time, planned end time, etc.), actual progress (e.g., real-time completion progress ratio, etc.) of each construction unit. The reporting time refers to the time of reporting the construction progress. The construction location refers to the location corresponding to the construction unit.

[0051] In some embodiments, the information determination module 120 can determine the construction information based on the construction image data through image recognition technology. In some embodiments, the information determination module 120 can identify feature points of the construction image data through image recognition technology. The embodiments of this specification do not specifically limit the image recognition technology, and operations familiar to those skilled in the art can be used. The information determination module 120 can match the identified feature points with the BIM model constructed according to the design data of the current construction project, and determine the successfully matched feature points as target feature points. The information determination module 120 can determine the real-time completion progress ratio based on the target feature points. For example, the ratio of the number of target feature points to the total number of feature points of the construction unit in the BIM model is determined as the real-time completion progress ratio.

[0052] Step 230, based on the construction information, determine the progress characteristics of the construction unit.

[0053] The progress feature is a feature vector that represents the degree of completion of a single construction unit within a unit of time (e.g., one day, three days, one week, two weeks, etc.).

[0054] The degree of completion per unit time refers to the construction progress of the construction unit per unit time. The degree of completion per unit time can be expressed as a percentage.

[0055] In some embodiments, the feature determination module 130 may divide the entire construction area corresponding to a single construction unit into multiple sub-areas, and use the completion degree of each of the multiple sub-areas in a unit time to represent the progress feature of the single construction unit. For example, a single construction unit (e.g., a water and electricity transformation unit) includes n sub-areas, and its progress feature can be represented as {(A1, C1), (A2, C2), (A3, C3), ..., (A n , C n )}. Among them, A n (such as A1, A2, ..., A n ) represents the sub-region number, C n (such as C1, C2, ..., C n ) represents sub-area A n The degree of completion per unit time.

[0056] In some embodiments, the feature determination module 130 may further divide the construction task corresponding to a single construction unit into multiple construction steps, and use the construction progress of each of the multiple construction steps in a unit of time to represent the progress feature of the single construction unit. For example, a single construction unit (e.g., a hydropower transformation unit) includes m construction steps, and its progress feature may be represented as {(S1, D1), (S2, D2), ..., (S m , D m )}, S m (Such as S1, S2, ..., S m ) indicates the number of the construction step, D m (such as D1, D2, ..., D m ) indicates construction step S m The corresponding degree of completion per unit time.

[0057] In some embodiments, the feature determination module 130 can determine the completion degree per unit time of a single construction unit in each sub-area, and combine the completion degrees per unit time of each sub-area to determine the progress characteristics of the construction unit. In some embodiments, the feature determination module 130 can determine the completion degree per unit time of a construction unit in each sub-area according to the construction progress, reporting time, construction location, etc. in the construction information.

[0058] In some embodiments, the feature determination module 130 can determine the completion degree per unit time of a single construction unit in each construction step, and combine the completion degrees per unit time of each construction step to determine the progress characteristics of the construction unit. In some embodiments, the feature determination module 130 can determine the completion degree per unit time of a construction unit in each construction step according to the construction progress, reporting time, construction location, etc. in the construction information.

[0059] Step 240, based on the progress characteristics and the planned information of the construction project, determining the matching relationship between the progress characteristics and the planned information.

[0060] The planning information is the relevant information of the pre-planning of the entire construction project. In some embodiments, the planning information may include the planned cost of at least one construction unit of the construction project. The planned cost may be a cost budget determined before the construction of the construction project begins. In some embodiments, the planning information may include the planned costs of multiple sub-areas or multiple construction steps in the construction unit. In some embodiments, the planning information may also include a construction schedule. The construction schedule is the schedule arrangement of the construction project. For more information about the construction schedule, please refer to the relevant description below.

[0061] In some embodiments, the matching determination module 140 can obtain the planning information of the construction project according to the user's input. For example, the user can upload the planning information of the construction project through the terminal device. The planning information of the construction project can be planned by the staff.

[0062] In some embodiments, the matching determination module 140 can read the plan information of the stored construction project from the storage device. The storage device can be a storage device of the construction cost monitoring system 100, or an external storage device that does not belong to the construction cost monitoring system 100, such as a hard disk, an optical disk, etc. In some embodiments, the storage device stores a large amount of data related to the construction project. For example, the storage device stores the plan information of the construction project pre-entered by the user.

[0063] The matching relationship includes whether the construction costs of multiple construction units match the construction progress. If the construction cost matches the construction progress, it means that the cost consumed by the construction unit is the same as or not much different from the planned cost corresponding to the construction progress, and the construction progress is normal; if the construction cost does not match the construction progress, it means that the cost consumed by the construction unit may exceed the planned cost corresponding to the current construction progress, that is, the cost is over-estimated, and the construction progress may be abnormal.

[0064] In some embodiments, the matching determination module 140 may determine whether the construction cost of a single construction unit matches the planned cost corresponding to the construction progress, so as to determine the matching relationship between the construction cost and the construction progress.

[0065] In some embodiments, the matching determination module 140 can determine the unit cost consumption corresponding to the construction unit according to the progress characteristics of the construction unit; determine the unit planned cost of the construction unit based on the progress characteristics and the planned information of the construction project; and determine the matching relationship between the progress characteristics and the planned information based on the unit cost consumption and the unit planned cost.

[0066] The unit cost consumption is the consumption cost corresponding to the current construction progress of the construction unit. The unit planned cost is the planned cost corresponding to the current construction progress of the construction unit.

[0067] In some embodiments, the matching determination module 140 may determine the unit cost consumption according to the actual cost generated by the progress feature.

[0068] In some embodiments, the matching determination module 140 may determine the planned cost of completing the overall construction process of the construction unit based on the planning information, and determine the unit planned cost of the construction unit based on the planned cost and the progress characteristics of the construction unit. For example, the matching determination module 140 may determine the unit planned cost of the construction unit as the product of the progress characteristics of the construction unit and the planned cost corresponding to the construction unit.

[0069] In some embodiments, the matching determination module 140 may determine the matching relationship based on the respective unit cost consumption and the respective unit planned cost of at least one construction unit.

[0070] In some embodiments, for each construction unit, the matching determination module 140 may determine a first difference based on the unit cost consumption and the unit planned cost of the construction unit, and determine a matching relationship based on the first difference corresponding to at least one construction unit. If the first difference corresponding to at least one construction unit is within the first difference range, the matching determination module 140 may determine that the matching relationship is a match; if there are a preset number (for example, 1) of construction units whose corresponding first difference is outside the first difference range, the matching determination module 140 may determine that the matching relationship is a mismatch.

[0071] In some embodiments, the matching determination module 140 can also determine the current total cost consumption and the total planned cost of at least one construction unit, compare the unit cost consumption of at least one construction unit with the unit planned cost, and compare the current total cost consumption and the total planned cost of at least one construction unit to determine the matching relationship between the progress characteristics and the planning information.

[0072] The current total cost consumption is the sum of the unit cost consumption of all construction units. The planned total cost is the sum of the unit planned costs of all construction units.

[0073] In some embodiments, the matching determination module 140 may determine the second difference based on the current total cost consumption and the total planned cost, and determine the matching relationship based on the first difference and the second difference. If the first difference corresponding to at least one construction unit is within the first difference range, and the second difference is within the second difference range, the matching determination module 140 may determine that the matching relationship is a match; if the first difference corresponding to at least one construction unit is not within the first difference range, or the second difference is outside the second difference range, the matching determination module 140 may determine that the matching relationship is a mismatch.

[0074] The first difference range and the second difference range can be set manually. The second difference range can be larger than the first difference range.

[0075] In some embodiments, the matching determination module 140 may determine the confidence level of the unit cost consumption based on the data volume and time length of the construction image data; and determine whether the unit cost consumption is abnormal based on the confidence level.

[0076] Confidence is a parameter that measures the degree of credibility. In some embodiments, the confidence can be in a numerical range of 0 to 1, where the closer to 0, the lower the credibility, and the closer to 1, the higher the credibility.

[0077] The time length of the construction image data may be a time length between an initial acquisition time and a final acquisition time of the construction image data for determining the unit cost consumption.

[0078] In some embodiments, the confidence level is negatively correlated to the data volume and time length of the construction image data. For example, if the data volume of the construction image data is larger and the time length is longer, the confidence level of the unit cost consumption is closer to 1; if the data volume of the construction image data is smaller and the time length is shorter, the confidence level of the unit cost consumption is closer to 0.

[0079] In some embodiments, the matching determination module 140 may determine the product of the unit cost consumption and the corresponding confidence level as a unit cost correction value, and compare the unit cost correction value with the unit planned cost; in response to the unit planned cost being greater than the unit cost correction value, determine that the unit cost consumption is normal; in response to the unit planned cost being less than or equal to the unit cost correction value, determine that the unit cost consumption is abnormal.

[0080] In some embodiments, in response to abnormal unit cost consumption of at least one construction unit, the matching determination module 140 may determine that the matching relationship is a mismatch; in response to normal unit cost consumption of all construction units, the matching determination module 140 may determine that the matching relationship is a match.

[0081] In the embodiments of this specification, the confidence level is determined by the data volume and time length of the construction image data to judge whether the unit cost consumption is abnormal, thereby judging whether to adjust the construction schedule, and the judgment result is more accurate. The larger the data volume of the construction image data, the more accurate and detailed the grasp of the construction schedule; the longer the time length, the higher the reliability. For example, the longer the time length, some operating costs with a longer cycle can be reflected through materials and labor, and the higher the reliability.

[0082] In some embodiments, the matching determination module 140 can determine the allocation ratio of at least one combined material based on the progress characteristics of the construction unit; determine the actual material cost of the construction unit based on the allocation ratio and material consumption information; determine the actual labor cost of the construction unit based on the progress characteristics and worker attendance information; and determine the unit cost consumption of the construction unit based on the actual material cost and the actual labor cost.

[0083] Joint materials are raw materials that are used by two or more construction units. Each construction unit uses specific raw materials when performing construction tasks. For example, raw materials such as cement and lime (putty) are used in multiple construction units such as wall construction units, ceiling construction units, floor construction units, and even door and window installation units. Therefore, joint materials for construction units such as wall construction units, ceiling construction units, floor construction units, and door and window installation units may include cement, lime, etc.

[0084] The allocation ratio of combined materials is the proportion of combined materials used by different construction units.

[0085] The allocation ratio of combined materials can allocate the lost combined materials to each current construction unit according to the allocation ratio and the current progress, which is conducive to better controlling the cost of combined materials and monitoring whether the combined material loss is abnormal. For example, 10 bags of cement cannot be used due to moisture at the current progress. Although the wall construction unit U1 and the ground construction unit U2 have not actually used these 10 bags of cement, these 10 bags of cement have also been consumed; the 10 bags of cement are allocated to the wall construction unit U1 and the ground construction unit U2 at the current progress according to the allocation ratio, and abnormal losses can be discovered in time (for example, the actual material cost at the current progress can be used to reversely infer whether there is abnormal loss).

[0086] In some embodiments, for each combination material, the matching determination module 140 can determine, based on the construction schedule, the theoretical consumption ratio of at least two construction units that apply the combination material at the current progress and the total planned usage of the combination material by at least two construction units; determine the theoretical total consumption of the at least two construction units that apply the combination material at the current progress based on the total planned usage, the theoretical consumption ratio and the progress characteristics of the at least two construction units that apply the combination material; determine the actual total consumption of a combination material used by at least two construction units that apply the combination material at the current progress based on the construction schedule and the progress characteristics; determine the distribution ratio of the combination material in at least two construction units based on the actual total consumption of a combination material used by at least two construction units at the current progress, the progress characteristics, the theoretical total consumption and the theoretical consumption ratio.

[0087] In some embodiments, the construction schedule may include unit schedules corresponding to multiple construction units. A unit schedule is a schedule arrangement for a single construction unit. In some embodiments, the construction schedule may include the start and end times of multiple construction units or construction steps, the construction sequence of the construction steps, etc.

[0088] The theoretical consumption ratio is the ratio of the combined material that at least one construction unit theoretically needs to consume. In some embodiments, the matching determination module 140 can determine the theoretical consumption ratio of at least one construction unit based on the construction schedule and historical data.

[0089] The theoretical total consumption is the amount of the combined material consumed by all construction units under the current progress characteristics. In some embodiments, the matching determination module 140 can determine the unit theoretical consumption of each construction unit, and determine the sum of the unit theoretical consumption of multiple construction units as the theoretical total consumption. The matching determination module 140 can determine the product result of the progress characteristics corresponding to the construction unit and the unit planned usage of a certain combined material used by the construction unit as the unit theoretical consumption of the construction unit using this combined material. The matching determination module 140 can determine the product of the total planned usage of the combined material used by at least two construction units and the theoretical consumption ratio of a certain construction unit as the unit planned usage of the construction unit.

[0090] In some embodiments, the matching determination module 140 may determine the actual total consumption by adding the theoretical total consumption to the loss. The loss may be preset by the system or manually.

[0091] In some embodiments, for each combined material, the matching determination module 140 may process the actual total consumption, progress characteristics, and theoretical consumption ratio of the combined material used by at least two construction units at the current progress based on a preset algorithm to determine the allocation ratio of the combined material in the at least two construction units. For example, for n construction units (n>2), the preset algorithm may be: Allocation ratio of construction unit 1 = [theoretical unit consumption of construction unit 1 / theoretical total consumption] The actual total consumption of a combined material used by n construction units at the current progress; the allocation ratio of construction unit 2 = [theoretical unit consumption of construction unit 2 / theoretical total consumption] The actual total consumption of a combined material used by n construction units at the current progress; ...; the allocation ratio of construction unit n = [theoretical unit consumption of construction unit n / theoretical total consumption] The actual total consumption of a combined material used by n construction units at the current progress.

[0092] The material consumption information includes the total quantity of various types of raw materials actually consumed and the corresponding total cost of the raw materials.

[0093] The actual material cost is the material consumption cost corresponding to the current construction progress of the construction unit.

[0094] In some embodiments, the matching determination module 140 may multiply the material consumption information (e.g., the total cost of raw materials) by the allocation ratio of a single construction unit to obtain the actual consumption of the construction unit, and multiply the actual consumption by the material unit cost to obtain the actual material cost of the construction unit. The material unit cost is the average cost of the raw materials, which can be calculated by dividing the total cost of multiple purchases by the total quantity of multiple purchases.

[0095] As an example, if the material consumption information is 170 bags (including 10 bags of loss), the actual material cost of construction unit U1 = 170 The allocation ratio of this construction unit Cost per piece of material.

[0096] In some embodiments, the matching determination module 140 may determine the batch allocation ratio of at least one combined material based on the historical progress characteristics and procurement characteristics of the construction unit; and determine the actual material cost based on the batch allocation ratio.

[0097] The historical progress feature is the progress feature of a single construction unit determined in the historical report. For example, the matching determination module 140 can determine the progress feature of the construction unit according to the reported construction progress after each construction worker reports the construction progress.

[0098] During the construction process, the joint materials may be purchased multiple times, and the unit cost of each purchase may be different. The purchase characteristics are related features of multiple purchases. In some embodiments, the purchase characteristics may include the type of materials purchased multiple times, the purchase time, the purchase cost, the purchase unit, etc.

[0099] In some embodiments, the matching determination module 140 may divide the multiple historical progress features into multiple sets according to the purchase time of the purchase feature. Each set corresponds to a construction period, and the construction duration of each construction period is the same. For example, if a certain joint material is purchased once every month, the multiple historical progress features may be divided into multiple sets by month.

[0100] When using combined materials, you can give priority to materials purchased earlier. Using the earliest purchased materials first can reduce the storage cost of materials.

[0101] The batch usage ratio refers to the proportion of a certain combined material in the purchase volume corresponding to different purchase batches that can be provided for the actual total consumption of the combined material.

[0102] For one of the at least one combination of materials, the matching determination module 140 may determine the batch usage ratio of the combination of materials in different purchase batches according to the order of purchase time of the purchase batches.

[0103] Just as an example, if the allocation ratio of the combined material X used by the three construction units (such as r1, r2, and r3) in February (i.e., the construction period corresponding to the historical progress feature set of February) is determined to be r1:r2:r3=100:50:10 according to the historical progress feature set of February, 170 bags (including 10 bags of loss) are actually consumed; if the allocation ratio of the combined material X used by the three construction units in March (i.e., the construction period corresponding to the historical progress feature set of March) is determined to be r1:r2:r3=50:50:0 according to the historical progress feature set of March, 100 bags (no loss) are actually consumed. 220 bags were purchased in February (170 bags of which were provided for construction in February and the remaining 50 bags of which were provided for construction in March), and 200 bags were purchased in March (50 bags of which were provided for construction in March). For the combined material X consumed in February, the batch usage ratio of the purchase batch in February is 170 / 170=100%, and the batch usage ratio of the purchase batch in March is 0 / 170=0%; for the combined material X consumed in March, the batch usage ratio of the purchase batch in February is 50 / 100=50%, and the batch usage ratio of the purchase batch in March is 50 / 100=50%.

[0104] In some embodiments, for a single construction unit, the matching determination module 140 can determine the actual material cost of the construction unit in different construction periods based on the consumption of a certain combined material used by the construction unit in different construction periods, the allocation ratio of a certain combined material used by multiple construction units in different construction periods, the unit cost of materials in the purchase batches corresponding to different construction periods, and the batch usage ratio.

[0105] Continuing with the above example, for unit r1 of the three construction units above, the actual material cost of unit r1 in February = the total consumption of the combined material X in February The proportion of combined material X used in r1 unit within 2 months Cost of materials per piece in February The proportion of combined materials consumed in February that were purchased in February = 170 (100 / 160) Cost of materials per piece in February 100%; Actual material cost of unit r1 in March = Total consumption of joint material X in March Distribution ratio of combined material X used in r1 unit within 3 months (Material cost per piece in February The proportion of materials consumed in March that were purchased in February + the cost of each piece of material in March The proportion of materials consumed in March that were purchased in March) = 110 (50 / 100) (Material cost per piece in February 50% + 3 months material cost per piece 50%).

[0106] In the embodiments of this specification, since the combined materials may be purchased multiple times and the unit cost of each purchase may be different, the batch allocation ratio of each batch of combined materials can be determined in combination with the historical progress characteristics, so that the calculated material consumption cost is more accurate.

[0107] Worker attendance information refers to the actual attendance of the worker. In some embodiments, the worker attendance information can be obtained through a clock-in machine or a worker's entry and exit record sheet.

[0108] The actual labor cost refers to the labor cost corresponding to the current construction progress of the construction unit.

[0109] In some embodiments, the matching determination module 140 can determine the actual labor cost based on the workload or the number of workers. In some embodiments, the matching determination module 140 can determine the actual labor cost by dividing the workload corresponding to the construction unit at the current construction progress by the total workload, and then multiplying it by the total labor cost corresponding to the total workload. The workload of the construction unit at the current progress can be determined based on the unit progress characteristics and the worker attendance information. The total workload can be obtained from the planning information.

[0110] In some embodiments, the matching determination module 140 may determine the sum of the actual material cost and the actual labor cost corresponding to a single construction unit as the unit cost consumption of the construction unit.

[0111] In some embodiments, the unit cost consumption may also include actual operating costs, that is, the unit cost consumption is equal to the sum of actual material costs, actual labor costs, and actual operating costs corresponding to a single construction unit.

[0112] The actual operating cost refers to the operating cost corresponding to the current construction progress of the construction unit. In some embodiments, the operating cost may include one or more of capital cost, equipment depreciation cost, equipment rental cost, water and electricity usage, safety and labor protection item cost, etc. In some embodiments, the operating cost can be calculated by the equipment rental duration, equipment rental cost, water and electricity usage, the number of safety and labor protection items, etc.

[0113] In some embodiments, the matching determination module 140 may obtain the actual operating cost through cost model prediction based on the actual material cost, the actual labor cost and the progress characteristics.

[0114] In some embodiments, the cost model may be a machine learning model. For example, the cost model may be a convolutional neural network (CNN) model, a deep neural network (DNN) model, etc. The cost model may also be a machine learning model of other structures, such as a neural network model, a recurrent neural network model, etc.

[0115] like Figure 4 As shown, inputs of the cost model 440 may include actual material costs 410 , actual labor costs 420 , and schedule characteristics 430 , and outputs may include actual operating costs 450 .

[0116] In some embodiments, the matching determination module 140 may obtain a plurality of first training samples with a first label to form a first training sample set, and obtain the cost model through training with the first training sample set. The first training sample may be obtained from historical data corresponding to historically calculated projects, and the historical data may include completed projects or unfinished but calculated projects.

[0117] In some embodiments, the first training sample may include sample actual material cost, sample actual labor cost, and sample progress characteristics of historical completed projects. The first label may be the actual operating cost corresponding to the first training sample, which is the actual operating cost of the historical completed project after accounting in a construction phase.

[0118] In some embodiments, the matching determination module 140 may input the first training sample set into the initial cost model to perform multiple rounds of iterations. Each round of iteration includes: selecting one or more first training samples from the first training sample set, inputting one or more first training samples into the initial cost model, and obtaining the model prediction output corresponding to the one or more first training samples; substituting the model prediction output corresponding to the one or more first training samples and the first labels of the one or more first training samples into the formula of the predefined loss function to calculate the value of the loss function; and updating the model parameters in the initial cost model in reverse according to the value of the loss function. When the iteration end condition is met, the iteration ends and the trained cost model is obtained. Among them, the iteration end condition may be that the loss function converges, the number of iterations reaches a threshold, etc.

[0119] In the embodiments of this specification, the actual operating cost is determined through a cost model. The self-learning ability of the machine learning model can be used to find patterns from a large amount of historical data, obtain the relationship between actual material cost, actual labor cost, progress characteristics and actual operating cost, etc., thereby improving the accuracy and efficiency of determining the actual operating cost.

[0120] In some embodiments, the matching determination module 140 may divide the plurality of first training samples into a plurality of first training sample subsets based on the actual material cost of the historical data, and perform alternate training on different first training sample subsets according to their sizes. The size refers to the number of training samples in the first training sample subsets.

[0121] In some embodiments, the matching determination module 140 may divide the first training sample corresponding to the historical data whose actual material cost is greater than the consumption threshold into a large-scale training sample subset, and divide the first training sample corresponding to the historical data whose actual material cost is less than the consumption threshold into a small-scale training sample subset, and perform alternating training using the divided large-scale training sample subset and the small-scale training sample subset to obtain a cost model. The consumption threshold can be set manually.

[0122] The actual material cost reflects the scale of the construction project to a certain extent. The actual operating costs of different project scales may have different patterns (for example, when the scale of the construction project is large, the number of safety and labor protection items is greater and the cost of each item is lower). Dividing the first training sample by the actual material cost can enable the model to learn this pattern more quickly.

[0123] In some embodiments, different training sample subsets have different learning rates during the training process, and the learning rates may be determined based on training sample characteristics.

[0124] The learning rate is an important parameter of the model, which represents the step size of the gradient moving toward the optimal solution of the loss function in each iteration. The size of the learning rate can affect the speed of neural network learning.

[0125] The training sample feature refers to the characteristics of the first training sample itself. In some embodiments, the training sample feature may include the time length of the first training sample and the reliability of the first training sample.

[0126] The time length of the first training sample refers to the time length of the sample progress feature corresponding to the first training sample. For example, one day, one week, etc. The time lengths corresponding to different first training samples may be different. In some embodiments, the matching determination module 140 may determine the learning rate of the first training sample subset based on the average time length of multiple first training samples in the first training sample subset. For the first training sample subset with a long average time length, the matching determination module 140 may set the learning rate of the first training sample subset to a larger value. This is because samples under short time scales may have greater accidental factors and it is more difficult to learn the "laws of operating costs", while samples under long time scales can more comprehensively reflect the "laws of operating costs".

[0127] The reliability of the first training sample is a parameter for measuring the training effect of the first training sample. In some embodiments, the matching determination module 140 can determine the reliability of the first training sample by label consistency. If the first labels corresponding to multiple identical or similar first training samples are consistent or mostly consistent, the reliability is high and the training effect is good; if the first labels corresponding to multiple identical or similar first training samples are greatly different, the reliability is low and the training effect may be poor. For first training samples of the same category, the first labels should be consistent.

[0128] In some embodiments, the matching determination module 140 may determine the learning rate of the first training sample subset based on the average reliability of multiple first training samples in the first training sample subset. For a first training sample subset with a higher average reliability, the matching determination module 140 may set the learning rate of the first training sample subset to a larger value.

[0129] In some embodiments, the matching determination module 140 can determine the learning rate of the training samples in different training sample sets through the vector database based on the training sample features. The learning rate can be a single value or sequence data. The vector database may include the material corresponding to the sample, the proportion of the number of training sample sets in all training sample sets, the reliability of the training samples, etc.

[0130] In the embodiment of the present specification, different training sample subsets are determined through actual material costs of historical data for alternating training, which can improve the accuracy of the trained cost model under different construction project scales.

[0131] In the embodiments of this specification, it is necessary not only to compare the total cost, but also to compare the unit cost consumption and the unit planned cost of each construction unit. Compared with the result obtained by evaluating only the total cost, it is more accurate and more convenient to adjust the construction schedule. In this way, it is possible to monitor whether the unit cost consumption matches the unit planned cost. For example, even if the total cost and the planned information match, but the unit cost consumption and the unit planned cost of one construction unit do not match, then the construction unit may have occupied the cost budget of other construction units, and the construction schedule needs to be adjusted.

[0132] Step 250: In response to the matching relationship not satisfying the first preset condition, adjusting the construction schedule.

[0133] In some embodiments, the first preset condition may include that the matching relationship is not matched. At this time, the adjustment module 150 may adjust the construction schedule.

[0134] In some embodiments, the adjustment module can adjust the construction schedule according to a preset rule. In some embodiments, the adjustment module 150 can determine abnormal units in the construction unit and adjust the unit schedule of the abnormal unit. The preset rule can be to reduce the construction speed of the construction unit with excessive cost.

[0135] An abnormal unit may be a construction unit whose unit cost consumption exceeds the unit planned cost. In some embodiments, if the unit cost consumption of a construction unit exceeds the unit planned cost, the construction unit may be determined as an abnormal unit, and the construction speed corresponding to the construction unit may be reduced. For example, if the unit cost consumption of a wall construction unit exceeds the unit planned cost, the progress of the wall construction unit may be adjusted (for example, the construction speed may be reduced).

[0136] In some embodiments, in response to the matching relationship satisfying the first preset condition, the adjustment module 150 may further determine whether the construction schedule needs to be adjusted according to the predicted consumption cost and the predicted planned cost. For more information on how to determine whether the construction schedule needs to be adjusted according to the predicted consumption cost and the predicted planned cost, please refer to Figure 3 and related instructions.

[0137] In the embodiments of the present specification, the matching relationship between the progress characteristics and the planned information is determined based on a preset time interval, and it is determined whether the construction progress plan needs to be adjusted. The cost corresponding to the current construction progress can be confirmed in stages and compared with the planned cost, so as to adjust the construction progress and realize real-time monitoring of the project cost, thereby effectively improving work efficiency, saving resources and reducing costs.

[0138] It should be noted that the above description of the process 200 is only for example and illustration, and does not limit the scope of application of this specification. For those skilled in the art, various modifications and changes can be made to the process 200 under the guidance of this specification. However, these modifications and changes are still within the scope of this specification.

[0139] Figure 3 It is an exemplary schematic diagram of adjusting the construction schedule according to some embodiments of this specification.

[0140] In some embodiments, Figure 3 As shown, in response to the matching relationship satisfying the first preset condition 310, the adjustment module 150 can determine the predicted consumption cost 321 for the preset time period and the predicted planned cost 322 for the preset time period based on the historical progress characteristics 323 and plan information 324 of multiple construction units; based on the predicted consumption cost 321 and the predicted planned cost 322, determine whether to adjust the construction progress plan 330.

[0141] For more information about historical schedule features and planning information, see Figure 2 and its related description.

[0142] The preset time period is a time period after the current moment. The preset time period can be set manually. In some embodiments, the preset time period can be 1 week, 2 weeks, one month, two months, one quarter, etc. after the current moment.

[0143] The predicted consumption cost is the consumption cost under the predicted progress corresponding to the preset time period. In some embodiments, the predicted consumption cost may include the material cost and labor cost under the predicted progress corresponding to the preset time period. In some embodiments, the predicted consumption cost may also include the material cost, labor cost and operating cost under the construction progress corresponding to the preset time period.

[0144] Predicted progress refers to the progress characteristics of a construction unit within a preset time period.

[0145] In some embodiments, the adjustment module 150 may use the average progress of at least one historical progress feature of the construction unit as the predicted progress for a preset time period.

[0146] In some embodiments, the adjustment module 150 may calculate the predicted consumption cost for the preset time period according to the predicted progress of the preset time period. The adjustment module 150 may determine the predicted consumption cost of the construction unit based on the unit planned cost of the construction unit and the predicted progress of the construction unit. For example, the adjustment module 150 may determine the predicted consumption cost of the construction unit by multiplying the predicted progress of the construction unit by the unit planned cost corresponding to the construction unit. For more information about the unit planned cost, see Figure 2 and its related description.

[0147] In some embodiments, the adjustment module 150 can obtain the predicted consumption cost through cost model prediction based on historical progress characteristics, planning information and preset time period. For more information about cost model, please refer to Figure 2 and its related description.

[0148] In some embodiments, the input of the cost model may further include at least one historical progress feature of the construction unit, plan information, and the length of a preset time period, and the output of the cost model may further include the predicted consumption cost. In some embodiments, the first training sample of the cost model may further include at least one sample historical progress feature of the sample construction unit, sample plan information, and the length of a sample preset time period, and the first label may further include the actual cost of the first training sample in the sample preset time period.

[0149] In some embodiments, the adjustment module 150 may determine the predicted plan cost for a preset time period based on the historical progress characteristics and the plan information. Figure 2 The method for determining the planned cost of the medium unit is similar. For more information, see Figure 2 .

[0150] In some embodiments, the adjustment module 150 can determine whether the predicted consumption cost and the predicted planned cost match to determine whether the construction schedule needs to be adjusted. The method of determining whether the match is the same as the method of determining whether the unit cost consumption and the unit planned cost match. In response to the predicted consumption cost and the predicted planned cost matching, there is no need to adjust the construction schedule; in response to the predicted consumption cost and the predicted planned cost not matching, the construction schedule needs to be adjusted.

[0151] In the embodiment of the present specification, by determining the predicted consumption cost and the predicted planned cost, the construction schedule can be adjusted in advance when the cost plan is not exceeded at present but may be exceeded in the future.

[0152] In some embodiments, in response to the need to adjust the construction schedule, the adjustment module 150 may adjust the construction schedule based on the procurement information of the raw materials.

[0153] The procurement information may include the market price of each raw material, for example, the market price of each raw material in different regions or different manufacturers, the market price at multiple historical times, etc.

[0154] In some embodiments, the adjustment module 150 can adjust the construction sequence of each construction unit and the purchase time of each raw material. For example, the adjustment module 150 can adjust the purchase time of the raw materials to after the period of time when the market quotation is low, so as to buy the raw materials at a lower market price as much as possible. For another example, after the purchase time when the raw materials are purchased at a low price, the construction steps that need to use the raw materials are screened, and for the construction steps whose order can be adjusted, the construction steps are arranged to be performed first.

[0155] In this manual, by adjusting the construction schedule based on procurement information, raw materials can be purchased when the market price is low, thereby reducing costs.

[0156] In some embodiments, Figure 3As shown, in response to the need to adjust the construction schedule 330, the adjustment module 150 can update the construction schedule 330 through steps S1 to S4, including: S1, constructing a schedule structure map 340 based on the material procurement plan, the worker arrangement plan, and the construction schedule; S2, generating multiple candidate adjustment plans 350 based on the schedule structure map 340; S3, based on the multiple candidate adjustment plans 350 and the schedule structure map 340, determining the predicted total progress 361 and the predicted total cost 362 of the candidate adjustment plans through a prediction model; S4, in response to the predicted total progress 361 and the predicted total cost 362 satisfying the second preset condition 370, determining a target adjustment plan 380 based on the multiple candidate adjustment plans 350; or in response to the predicted total progress 361 and the predicted total cost 362 not satisfying the second preset condition 370, repeating steps S1 to S3.

[0157] The material purchase plan is a planned purchase arrangement for raw materials. In some embodiments, the material purchase plan may include material type, material purchase quantity, material purchase time, etc.

[0158] The worker arrangement plan is a planned work arrangement of workers. In some embodiments, the worker arrangement plan may include the amount of workers and the working hours of workers, etc.

[0159] The progress structure graph is a graph that reflects the causal relationship between multiple construction units and construction steps. The progress structure graph is a data structure composed of nodes and edges, where the edges connect the nodes and the nodes and edges may have attribute characteristics.

[0160] Construction steps are the steps in the execution process of the construction unit. Some construction steps may have a contextual relationship, for example, floor tiles, doors and windows can only be laid after the water and electricity renovation is completed. Some construction steps have no contextual relationship, which means that these construction steps can be carried out at the same time.

[0161] In some embodiments, the nodes in the progress structure map represent each construction step in the construction schedule. The node features can represent the materials and labor arrangements (eg, number of workers, type of work, etc.) required for each construction step.

[0162] In some embodiments, the edge in the progress structure graph represents the contextual relationship between two construction steps. The contextual relationship between two construction steps means that the previous construction step (i.e., the preceding construction step) must be completed before the next construction step (i.e., the subsequent construction step) can be performed. The edge is a directed edge, pointing from the preceding construction step to the subsequent construction step, indicating that the subsequent construction step can only be started after the preceding construction step is completed.

[0163] In some embodiments, the edge feature of the progress structure graph may include the waiting time between two construction steps. For example, in a certain construction unit, after pouring cement, it is necessary to wait for a period of time until the cement is completely dry before proceeding to the next step.

[0164] In the embodiment of this specification, if two construction steps require a certain time interval, it will obviously extend the construction period and incur additional costs. Therefore, using the waiting time between two construction steps as an edge feature of the progress structure graph can make the prediction of the total progress and the total cost more accurate.

[0165] The candidate adjustment plan is an alternative plan for adjusting the construction schedule. In some embodiments, the candidate adjustment plan may include an adjusted material procurement plan, an adjusted worker arrangement plan, and the like.

[0166] In some embodiments, the adjustment module 150 can randomly generate multiple candidate adjustment plans based on the progress structure map. The adjustment module 150 can randomly generate multiple candidate adjustment plans in two ways. The first random generation method is to randomly adjust the construction order of the nodes to generate multiple candidate adjustment plans. For example, other construction steps that have no previous and next correlation can be brought forward. The second random generation method is to randomly adjust the material procurement plan or the worker scheduling plan to generate multiple candidate adjustment plans. For example, adjust the material procurement quantity and material procurement time in the material procurement plan, or the number of workers and worker working hours in the worker scheduling plan.

[0167] In some embodiments, the adjustment module 150 can set a probability value, generate a random number in the interval [0,1], and determine whether to execute the first random generation method or the second random generation method according to the random number and the probability value. If the random number is less than or equal to the set probability value, the first random generation method is executed, otherwise the second random generation method can be executed.

[0168] In some embodiments, the adjustment module 150 may use a pseudo-random number generator to generate a random number.

[0169] In some embodiments, the size of the set probability value may be negatively correlated to the number of edges in the progress structure graph. That is, the more logical relationships there are between the construction steps (the more edges there are), the smaller the set probability value is. This is because the more logical relationships there are between the construction steps, the more difficult it is to adjust the construction sequence.

[0170] In some embodiments, for the second random generation method, the adjustment range of the material procurement plan or the worker arrangement plan (for example, the adjustment range of the material procurement quantity) and the number of candidate adjustment plans generated are both positively correlated with the difference when the forecast cost is abnormal. For example, the larger the difference when the forecast cost is abnormal, the larger the adjustment range in the generated candidate adjustment plan; the larger the difference when the forecast cost is abnormal, the more candidate adjustment plans are generated in a single time. The difference when the forecast cost is abnormal is the difference between the planned cost and the forecast cost correction value when the forecast cost is abnormal.

[0171] This is because when the difference in the predicted cost anomaly is small, only a small adjustment may be needed to meet the required adjustment purpose. When the difference in the predicted cost anomaly is large, generating more candidate adjustment plans at a time is more conducive to finding an adjustment plan that meets the conditions.

[0172] In some embodiments, the prediction model may be a machine learning model. For example, the prediction model may be a graph neural network (GNN) model. The prediction model may also be a machine learning model of other structures, such as a neural network model, a recurrent neural network model, etc.

[0173] In some embodiments, the input of the prediction model may include multiple candidate adjustment plans, a schedule structure map, and schedule characteristics of all construction units, and the output may include the predicted total schedule and predicted total cost corresponding to the candidate adjustment plans.

[0174] In some embodiments, the adjustment module 150 may obtain a plurality of second training samples with second labels to form a second training sample set, and obtain a prediction model through training with the second training sample set. The second training samples may be obtained through historical data.

[0175] In some embodiments, the second training sample may include a sample candidate adjustment plan, a sample progress structure map, and sample progress characteristics of all construction units. The second label may be the actual total progress and actual total cost corresponding to the second training sample. The training process of the prediction model is similar to the training process of the cost model, which will not be repeated here.

[0176] In some embodiments, the forecasting module may include a schedule forecasting layer and a cost forecasting layer.

[0177] The input of the progress prediction layer may include multiple candidate adjustment plans, progress structure maps, and progress characteristics of all construction units, and the output of the progress prediction layer may include predicted total progress. The progress prediction layer may be a GNN model. The input of the cost prediction layer may include candidate adjustment plans, and the output may include predicted total cost.

[0178] In some embodiments, the trained cost model can be directly used as a cost prediction layer and the candidate adjustment plan can be input into the cost model as a historical progress feature, thereby outputting a predicted cost, that is, a predicted total cost.

[0179] In the embodiments of the present specification, the predicted total progress and predicted total cost are determined by the prediction model. The self-learning ability of the machine learning model can be used to find patterns from a large amount of historical data, obtain the relationship between material consumption cost, labor cost, predicted total progress and predicted total cost, etc., thereby improving the accuracy and efficiency of determining the predicted total progress and predicted total cost, thereby determining a more appropriate target adjustment plan.

[0180] The second preset condition may include: the predicted total progress reaches the early completion ratio of the target total progress, and the predicted total cost meets the savings ratio of the target total cost. For example, when the predicted total progress is greater than the product of the target total progress and the corresponding early completion ratio, and the predicted total cost is greater than the product of the target total cost and the savings ratio, it can be determined that the predicted total progress and the predicted total cost meet the second preset condition.

[0181] Among them, the target total progress refers to the time condition that the total progress of the construction project in the plan information needs to meet. The early completion ratio refers to the ratio of the predicted total progress to the target total progress. The target total cost refers to the cost value that the total cost of the construction project in the plan information needs to meet. The savings ratio refers to the ratio of the predicted total cost to the target total cost.

[0182] As an example, the target total progress is 1 year to complete, and the target total cost is 3 million. The early completion rate is 90%, and the savings rate is 95%. The second preset condition can be that the predicted total progress is greater than the total progress of 365 days. 90%, the predicted total cost is greater than the target total cost of 3 million 95%. The target total progress, target total cost, early completion ratio and savings ratio can be obtained through manual input.

[0183] In some embodiments, the adjustment module 150 may determine the target adjustment plan based on the candidate adjustment plan with the highest overall ranking of predicted total progress and predicted total cost among multiple candidate adjustment plans. The adjustment module 150 may sort the predicted total progress from high to low, and sort the predicted total cost from low to high, and then perform weighted summation on the sorted results of the predicted total progress and predicted total cost to obtain the overall ranking of the candidate adjustment plans. The higher the overall ranking corresponding to the candidate adjustment plan, the better the effect after adjustment. The weights of the sorting results of the predicted total progress and predicted total cost of different construction projects may be different. For example, for construction projects that can obtain more early progress rewards by progressing ahead of schedule, the weight of the sorting results of the predicted total progress can be set higher. The weight of the sorting result is obtained through manual input.

[0184] In the embodiment of the present specification, when the predicted total progress and the predicted total cost meet the second preset condition, the candidate adjustment plan is confirmed as the target adjustment plan, which can make the target adjustment plan approach the ideal situation of being completed ahead of schedule and at a lower cost.

[0185] One or more embodiments of the present specification also provide a multi-source ocean observation data fusion device, which includes at least one processor and at least one memory; the at least one memory is used to store computer instructions; the at least one processor is used to execute at least part of the computer instructions to implement a construction cost monitoring method as described in any embodiment of the present specification.

[0186] One or more embodiments of the present specification also provide a computer-readable storage medium, wherein the storage medium stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the engineering cost monitoring method as described in any embodiment of the present specification.

[0187] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements and corrections to this specification. Such modifications, improvements and corrections are suggested in this specification, so such modifications, improvements and corrections still belong to the spirit and scope of the exemplary embodiments of this specification.

[0188] At the same time, this specification uses specific words to describe the embodiments of this specification. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures or characteristics in one or more embodiments of this specification can be appropriately combined.

[0189] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences described in this specification, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some invention embodiments that are currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0190] Similarly, it should be noted that in order to simplify the description disclosed in this specification and thus help understand one or more embodiments of the invention, in the above description of the embodiments of this specification, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the subject matter of this specification are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0191] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise specified, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may change according to the required features of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining the digits. Although the numerical domains and parameters used to confirm the breadth of the range in some embodiments of this specification are approximate values, in specific embodiments, the setting of such numerical values ​​is as accurate as possible within the feasible range.

[0192] Each patent, patent application, patent application publication, and other materials, such as articles, books, specifications, publications, documents, etc., cited in this specification is hereby incorporated by reference in its entirety. Except for application history documents that are inconsistent with or conflicting with the contents of this specification, documents that limit the broadest scope of the claims of this specification (currently or later attached to this specification) are also excluded. It should be noted that if the descriptions, definitions, and / or use of terms in the materials attached to this specification are inconsistent or conflicting with the contents described in this specification, the descriptions, definitions, and / or use of terms in this specification shall prevail.

[0193] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A method for monitoring construction cost, characterized in that: include: Acquiring construction image data based on a preset time interval; Determining construction information of a construction unit based on the construction image data; Based on the construction information, determining progress characteristics of the construction unit; Based on the progress characteristics and the planned information of the construction project, determining a matching relationship between the progress characteristics and the planned information; In response to the matching relationship not satisfying the first preset condition, adjusting the construction schedule, wherein the adjusting the construction schedule includes: determining abnormal units in the construction units; Adjusting the unit schedule of the abnormal unit; In response to the matching relationship satisfying the first preset condition, Determining the predicted consumption cost for a preset time period and the predicted planned cost for the preset time period based on the historical progress characteristics of the construction unit and the plan information; Determining whether to adjust the construction schedule based on the predicted consumption cost and the predicted planned cost; In response to the need to adjust the construction schedule, the construction schedule is updated through steps S1 to S4: S1, constructing a progress structure map based on the material procurement plan, the worker arrangement plan, and the construction progress plan; S2, generating a plurality of candidate adjustment plans based on the progress structure map; S3, based on the multiple candidate adjustment plans and the progress structure map, determining the predicted total progress and predicted total cost of the candidate adjustment plans through a prediction model, wherein the prediction model is a machine learning model; S4, in response to the predicted total progress and the predicted total cost satisfying the second preset condition, determining a target adjustment plan based on the multiple candidate adjustment plans; or in response to the predicted total progress and the predicted total cost not satisfying the second preset condition, repeating steps S1 to S3.

2. A method for monitoring construction cost according to claim 1, characterized in that: The determining, based on the progress feature and the planned information of the construction project, a matching relationship between the progress feature and the planned information includes: Based on the progress characteristics, determining the unit cost consumption of the construction unit; Determining a unit planned cost of the construction unit based on the progress characteristics and the planned information; The matching relationship is determined based on the unit cost consumption and the unit planned cost.

3. A method for monitoring construction cost according to claim 2, characterized in that: The determining the unit cost consumption of the construction unit based on the progress characteristics includes: determining, based on the progress characteristics, a distribution ratio of at least one combined material; Determining the actual material cost of the construction unit based on the allocation ratio and material consumption information; Determining the actual labor cost of the construction unit based on the progress characteristics and worker attendance information; Based on the actual material cost and the actual labor cost, the unit cost consumption of the construction unit is determined.

4. A construction cost monitoring system, characterized in that: The system comprises: An acquisition module, configured to acquire construction image data based on a preset time interval; an information determination module, configured to determine the construction information of the construction unit based on the construction image data; a characteristic determination module, configured to determine a progress characteristic of the construction unit based on the construction information; a matching determination module configured to determine a matching relationship between the progress feature and the plan information based on the progress feature and the plan information of the construction project; and The adjustment module is configured to adjust the construction schedule in response to the matching relationship not satisfying the first preset condition, including: determining abnormal units in the construction units; Adjusting the unit schedule of the abnormal unit; The adjustment module is further configured to: In response to the matching relationship satisfying the first preset condition, Determining the predicted consumption cost for a preset time period and the predicted planned cost for the preset time period based on the historical progress characteristics of the construction unit and the plan information; Determining whether to adjust the construction schedule based on the predicted consumption cost and the predicted planned cost; In response to the need to adjust the construction schedule, the construction schedule is updated through steps S1 to S4: S1, constructing a progress structure map based on the material procurement plan, the worker arrangement plan, and the construction progress plan; S2, generating a plurality of candidate adjustment plans based on the progress structure map; S3, based on the multiple candidate adjustment plans and the progress structure map, determining the predicted total progress and predicted total cost of the candidate adjustment plans through a prediction model, wherein the prediction model is a machine learning model; S4, in response to the predicted total progress and the predicted total cost satisfying the second preset condition, determining a target adjustment plan based on the multiple candidate adjustment plans; or in response to the predicted total progress and the predicted total cost not satisfying the second preset condition, repeating steps S1 to S3.

5. A construction cost monitoring system according to claim 4, characterized in that: The matching determination module is further configured to: Based on the progress characteristics, determining the unit cost consumption of the construction unit; Determining a unit planned cost of the construction unit based on the progress characteristics and the planned information; The matching relationship is determined based on the unit cost consumption and the unit planned cost.

6. A construction cost monitoring device, characterized in that: The apparatus comprises at least one processor and at least one memory; The at least one memory is used to store computer instructions; The at least one processor is used to execute at least part of the computer instructions to implement a construction cost monitoring method as described in any one of claims 1 to 3.

7. A computer-readable storage medium storing computer instructions, characterized in that: After the computer reads the computer instructions in the storage medium, the computer executes a construction cost monitoring method as described in any one of claims 1 to 3.

Images