A cost management system and method for the entire process

Abstract

This specification provides a cost management system and method for the entire process of cost estimation. The system includes an information acquisition module, a cost estimation module, an anomaly analysis module, and an adjustment module. The method includes acquiring basic project information, construction process information, and construction progress information; determining the actual cost based on the basic project information and construction process information; determining the planned cost based on the basic project information and construction progress information; determining the difference value based on the actual cost and the planned cost; determining an actual cost anomaly in response to the difference value exceeding a preset threshold; determining at least one cause of the anomaly and an anomaly probability based on the construction process information meeting preset conditions in response to the actual cost anomaly; and determining at least one project adjustment parameter based on at least one cause of the anomaly and an anomaly probability.

Description

Technical Field

[0001] The present invention relates to the field of engineering technology, and in particular to a cost management system and method for the entire process. Background Art

[0002] There are many factors that affect the construction cost during the construction process of a project, including external factors during the construction process, such as various extreme weather conditions and natural disasters; inadequate preliminary work, design changes, and on-site emergencies can also cause changes in the actual construction cost of the project; for example, the price of raw materials and labor costs may change during the construction process, causing the cost to deviate from the budget. Various uncertainties in different stages of the construction process increase the difficulty of controlling the construction cost.

[0003] Therefore, the present application provides a cost management system and method for the entire process, which can perform cost analysis for different project progress stages, analyze the causes of abnormalities and make targeted adjustments to engineering projects when there are large deviations in actual costs, thereby controlling cost indicators in combination with dynamic changes on site. Summary of the invention

[0004] One or more embodiments of the present specification provide a cost management system for the entire process, including an information acquisition module, a cost estimation module, an abnormality analysis module and an adjustment module: the information acquisition module is configured to acquire basic project information, construction process information and construction progress information; the cost estimation module is configured to determine the actual cost based on the basic project information and the construction process information; and determine the planned cost based on the basic project information and the construction progress information; the abnormality analysis module is configured to determine a difference value based on the actual cost and the planned cost; in response to the difference value being greater than a preset threshold, determine that the actual cost is abnormal, and the preset threshold is related to project specifications and construction difficulty; in response to the actual cost abnormality, determine at least one abnormal cause and abnormal probability based on the construction process information satisfying preset conditions; and the adjustment module is configured to determine at least one project adjustment parameter based on the at least one abnormal cause and the abnormal probability.

[0005] One or more embodiments of the present specification provide a method for managing the entire process of construction cost, including: obtaining basic project information, construction process information, and construction progress information; determining the actual cost based on the basic project information and the construction process information; determining the planned cost based on the basic project information and the construction progress information; determining a difference value based on the actual cost and the planned cost; in response to the difference value being greater than a preset threshold, determining that the actual cost is abnormal, the preset threshold being related to project specifications and construction difficulty; in response to the actual cost abnormality, determining at least one abnormal cause and abnormal probability based on the construction process information satisfying preset conditions; and determining at least one project adjustment parameter based on the at least one abnormal cause and the abnormal probability. BRIEF DESCRIPTION OF THE DRAWINGS

[0006] 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:

[0007] Figure 1 is an exemplary module diagram of the whole process management system of cost management according to some embodiments of this specification;

[0008] Figure 2 is an exemplary flow chart of the whole process management method of cost management according to some embodiments of this specification;

[0009] Figure 3 is an exemplary schematic diagram of a fault prediction model according to some embodiments of this specification;

[0010] Figure 4 is an exemplary schematic diagram of a causal analysis model according to some embodiments of the present specification. DETAILED DESCRIPTION

[0011] 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.

[0012] 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.

[0013] 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.

[0014] 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.

[0015] Figure 1 It is an exemplary module diagram of the whole process management system of cost management according to some embodiments of this specification.

[0016] In some embodiments, Figure 1 As shown, the whole process cost management system 100 includes an information acquisition module 110 , a cost estimation module 120 , an abnormality analysis module 130 and an adjustment module 140 .

[0017] The information acquisition module 110 is a module for acquiring project related information.

[0018] In some embodiments, the information acquisition module 110 is configured to acquire basic project information, construction process information, and construction progress information. The basic project information includes at least project specifications and construction difficulty.

[0019] The cost estimation module 120 is a module for estimating project-related costs.

[0020] In some embodiments, the cost estimation module 120 is configured to: determine the actual cost based on the basic project information and the construction process information; and determine the planned cost based on the basic project information and the construction progress information.

[0021] In some embodiments, the cost estimation module 120 is further configured to: determine the economic cost, labor cost, time cost and operating cost based on the basic project information and construction process information, and the operating cost includes at least the first operating cost; and determine the actual cost based on the economic cost, labor cost, time cost and operating cost by weighting.

[0022] In some embodiments, the operating cost also includes a second operating cost, the construction process information also includes the daily working hours and daily output of each device, and the cost estimation module 120 is further configured to determine the second operating cost based on the daily working hours and daily output of each device.

[0023] In some embodiments, the cost estimation module is further configured to determine the planned cost based on the basic project information, the construction progress information and the maximum tolerance.

[0024] The exception analysis module 130 is a module for analyzing exceptions related to project costs.

[0025] In some embodiments, the anomaly analysis module 130 is configured to: determine a difference value based on actual cost and planned cost; determine an actual cost anomaly in response to the difference value being greater than a preset threshold, wherein the preset threshold is related to project specifications and construction difficulty; and determine at least one cause of the anomaly and an anomaly probability based on construction process information in response to the actual cost anomaly.

[0026] In some embodiments, the abnormality analysis module 130 is further configured to determine at least one abnormality cause and abnormality probability based on the basic project information and the construction process information.

[0027] The adjustment module is a module for determining a project adjustment parameter. The adjustment module 140 is configured to determine at least one project adjustment parameter based on at least one abnormality cause and an abnormality probability.

[0028] For more information on the above description, see Figure 2 Related instructions.

[0029] In some embodiments, the information acquisition module 110, cost estimation module 120, abnormality analysis module 130 and adjustment module 140 of the whole process cost management system 100 can be integrated into a processor. The processor is configured to process information and / or data related to the whole process cost management system 100. The processor can also process data obtained from other devices, such as user terminals. The user terminals may include personal computers, mobile devices, etc.

[0030] In some embodiments, the processor may be configured as a combination of one or more of a central processing unit (CPU), an application specific integrated circuit (ASIC), and the like.

[0031] In some embodiments of the present specification, the whole process cost management system 100 can acquire, transmit and process a large amount of data such as basic project information, construction process information and construction progress information through the information acquisition module 110, the cost estimation module 120, the abnormality analysis module 130 and the adjustment module 140, so as to accurately determine the actual cost in the construction process, adjust the project based on the actual cost abnormality, thereby controlling the loss in time and ensuring that the subsequent cost complies with the cost plan.

[0032] It should be noted that the above description of the cost management 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, they may arbitrarily combine the modules or form a subsystem to connect with other modules without deviating from this principle. In some embodiments, Figure 1 The information acquisition module 110, cost estimation module 120, abnormality analysis module 130 and adjustment module 140 disclosed in the specification can be different modules in a system, or one module can realize the functions of two or more modules. 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.

[0033] Figure 2 is an exemplary flow chart of the whole process management method of cost management according to some embodiments of this specification. Figure 2 As shown, the process 200 includes the following steps 210 to 270. In some embodiments, the process 200 may be executed by a processor.

[0034] Step 210, obtaining basic project information, construction process information and construction progress information.

[0035] Basic project information refers to information related to the project. For example, basic project information may include the initial 3D-BIM model, project specifications, project location, construction difficulty, project work breakdown structure (WBS), project schedule, project cost plan, etc. The project cost plan may include cost budget, time budget, personnel budget, type and quantity of materials required for the project and initial purchase price, unit price of water and electricity and estimated usage, etc.

[0036] Project WBS refers to a tree-like task structure formed by decomposing a project into multiple individual tasks of different levels according to preset principles. For example, the project WBS includes three levels, which can divide the project into multiple first-level tasks, such as underground structure and above-ground structure; each first-level task is then decomposed into multiple second-level tasks, such as underground structure is decomposed into foundation pit, foundation, basement, etc.; each second-level task is decomposed into multiple third-level tasks, such as foundation pit is decomposed into foundation pit dewatering and monitoring, earthwork, foundation pit support, etc.

[0037] The project schedule refers to the planning related to the progress of the project. For example, the project schedule includes the total project volume, various work tasks, construction period, progress nodes and completion time of the project.

[0038] The project cost plan refers to the budget and cost plan for the project. In the early stage, according to the design plan, technical requirements and relevant standards of the project, the project's project quantity, project cost, project progress and other aspects are analyzed and calculated in detail to prepare the project's budget and cost plan.

[0039] Cost budget refers to the total cost of the project. Time budget refers to the estimated time to complete the entire project. Personnel budget refers to the number of personnel with various titles or types of work required to complete the entire project.

[0040] Construction process information refers to the information related to construction every day within the current preset time period. For example, the current progress, weather, the titles and number of construction workers, water consumption, electricity consumption, material information and equipment information. Material information may include the type and quantity of materials used, the actual purchase price and whether they are sufficient. Equipment information may include the type and quantity of equipment currently in use, as well as the type and quantity of equipment that has failed, etc.

[0041] The preset time period can be set manually according to the needs, for example, one week or one month. The preset time period cannot be set too long, otherwise the abnormal causes in the past may no longer be applicable to the current adjustment. The current progress refers to the proportion of all the completed projects to the total project volume.

[0042] Construction progress information refers to information related to the progress, such as the number and type of completed tasks, the number and type of unfinished tasks, and the number and type of ongoing tasks.

[0043] In some embodiments, the processor may obtain basic project information, construction process information, and construction progress information uploaded by the user from the user terminal. The user may be a manager and / or operator of the cost management system 100 .

[0044] In some embodiments, the processor can generate construction progress information in vector form based on the splitting of the project WBS. For example, according to the lowest level of the single task division of the project WBS, such as recording the completed tasks as 1, the unfinished tasks as 0, and the ongoing tasks as 2 in the third level tasks, the construction progress information in vector form is generated.

[0045] Step 220, determining the actual cost based on the basic project information and the construction process information.

[0046] Actual cost refers to the actual cost consumed by the construction to the current progress.

[0047] In some embodiments, the processor can determine the economic cost, time cost and labor cost of the actual cost based on the basic information of the project and the construction process information, and calculate the actual cost based on the economic cost, time cost and labor cost. The economic cost, time cost and labor cost are positively correlated with the actual cost. For example, the processor can calculate the actual cost based on formula (1). Formula (1) is as follows:

[0048] Actual cost = k1 × economic cost + k2 × labor cost + k3 × time cost (1)

[0049] k1, k2 and k3 are coefficients greater than 0 and can be set manually according to requirements. For example, k1, k2 and k3 are all set to 1 / 3.

[0050] The economic cost of the actual cost refers to the amount of money consumed under the current progress. In some embodiments, the processor can determine multiple task items based on the basic information of the project and the construction process information, and take the sum of the amount of money consumed by the multiple task items as the economic cost. The amount of money consumed for each task can be calculated based on the number of each task item and the corresponding unit price, such as the amount of electricity bill is the product of the amount of electricity consumed and the unit price of electricity. It can be understood that the economic cost represents the actual amount consumed, not the actual payment.

[0051] The time cost of the actual cost can refer to the current number of construction days.

[0052] The actual labor cost refers to the cost related to the actual arrangement of construction personnel. The labor cost is related to the number of construction personnel, types of work, professional titles, etc. It is understandable that, when the number of construction personnel is the same, the labor cost of construction personnel with high professional titles is greater than that of construction personnel with low professional titles; the labor cost of construction personnel with high threshold types of work is greater than that of construction personnel with low threshold types of work, such as the labor cost of carpenters is greater than that of plasterers.

[0053] In some embodiments, the processor may obtain the number of personnel, types of work, and job titles involved in the construction every day based on the construction process information, and calculate the labor cost based on the number of personnel, types of work, and job titles. For example, the processor may calculate the labor cost based on formula (2). Formula (2) is as follows:

[0054]

[0055] Among them, n represents the number of construction days, k represents the number of workers on the jth day, represents the job title value of the i-th construction worker on the j-th day, Indicates the job type value of the i-th construction worker on the j-th day. The job title value and job type value can be preset. The higher the job title, the higher the job title value. For example, the job title value corresponding to senior engineer is set to 3, the job title value corresponding to intermediate engineer is set to 2, and the job title value corresponding to junior engineer is set to 1. The more difficult the job type, the higher the job type value. For example, the job type value of carpenter is greater than that of plasterer.

[0056] In some embodiments, the processor may determine the economic cost, labor cost, time cost and operating cost based on the basic information of the project and the construction process information; and determine the actual cost by weighting based on the economic cost, labor cost, time cost and operating cost.

[0057] Operating costs refer to the operating costs such as equipment failure and depreciation caused by project operation. The equipment corresponding to operating costs is fixed equipment, such as cranes, concrete mixers, etc.

[0058] In some embodiments, the operating cost includes at least a first operating cost. The first operating cost refers to the cost caused by the failure and / or damage of the construction equipment. In some embodiments, the processor can calculate the first operating cost based on formula (3). Formula (3) is as follows:

[0059]

[0060] Where t represents the number of failed devices. It represents the preset cost value corresponding to device i, which is related to the purchase price, service life and actual usage time of the device when it fails.

[0061] For example, It can be calculated based on formula (4), which is as follows:

[0062]

[0063] Among them, a is the preset coefficient; is the purchase price of equipment i; is the useful life of equipment i; is the actual use time of equipment i. For example, the price of a crane is 200,000 yuan, the service life is 20 years, the crane fails in the 10th year, the preset value a is set to 0.1, and the preset cost value of the crane is calculated to be 10,000 yuan by substituting it into formula (4).

[0064] In some embodiments, the processor may directly use the first operating cost as the operating cost.

[0065] In some embodiments, the processor may calculate the actual cost based on the economic cost, labor cost, time cost, and operating cost. The actual cost is positively correlated with the economic cost, labor cost, time cost, and operating cost. For example, the processor may calculate the actual cost based on formula (5). Formula (5) is as follows:

[0066] Actual cost = k1 × economic cost + k2 × labor cost + k3 × time cost + k4 × operating cost (5)

[0067] Among them, k1, k2, k3, and k4 are weighted weights corresponding to economic cost, labor cost, time cost, and operating cost, which can be preset according to needs.

[0068] Some embodiments of this specification take into account the impact of operating costs on actual costs, so that losses caused by the operation of the project can also be taken into account in the actual costs, such as failure and damage of equipment, so as to make the actual costs more accurate.

[0069] In some embodiments, the weighted weights of economic cost, labor cost, time cost and operation cost are related to project specifications, cost budget, time budget and personnel budget.

[0070] In some embodiments, the processor may construct a feature vector based on project specifications, cost budget, time budget, and personnel budget, search a vector database for a reference vector with the highest similarity to the feature vector, and use the weight combination corresponding to the reference vector as the weighted weight.

[0071] The vector database includes a mapping relationship between multiple reference vectors and weight combinations, where the weight combination is a combination of weighted weights of economic cost, labor cost, time cost and operating cost. The mapping relationship between the reference vector and the weight combination can be determined based on human experience.

[0072] It is understandable that for a project with relatively high specifications, if the time budget is relatively short, the weight of the time cost should be increased when calculating the actual cost; if the cost budget is relatively high, the weight of the economic cost can be reduced when calculating the actual cost. In this way, the weighted weight obtained can be consistent with the project specifications and project budget, making the calculated actual cost more accurate.

[0073] In some embodiments, the operating cost further includes a second operating cost, which refers to the depreciation cost generated by the normal operation of the construction equipment.

[0074] The construction process information also includes the daily working hours and daily output of each device. Daily output refers to the daily workload, such as the weight of concrete mixed by a concrete mixer and the area of ​​land pushed by a bulldozer. Daily working hours refer to the daily operating time of the device. If the device does not work on a certain day, the corresponding daily working hours and daily output are 0.

[0075] In some embodiments, the processor may determine the second operating cost based on the daily working hours and daily output of the equipment. The second operating cost is positively correlated with the daily working hours and daily output. It is understandable that the longer the daily working hours and the higher the daily output, the more fully the equipment is used, and the higher the second operating cost.

[0076] For example, the processor may calculate the second operating cost based on formula (6). Formula (6) is as follows:

[0077]

[0078] Among them, s represents the number of equipment that operates normally without failure, n represents the number of construction days, represents the daily working time of equipment i on day j, Represents the daily output of equipment i on day j.

[0079] In some embodiments, the processor may take the sum of the first operating cost and the second operating cost as the operating cost.

[0080] In some embodiments, the processor may also predict the future failure rate of each device through a failure prediction model based on the device's daily working hours, daily output, sound sequence, vibration sequence, device type, and initial future failure rate; and determine the second operating cost based on the future failure rate. Figure 3 And related instructions.

[0081] When the equipment is operating normally, it will also produce certain losses. Taking the second operating cost into consideration can make the operating cost more in line with the actual operation of the project, thereby making the actual cost more accurate.

[0082] Step 230, determining the planned cost based on the basic project information and the construction progress information.

[0083] The planned cost refers to the cost required to complete the construction to the current progress according to the project schedule and project cost plan.

[0084] In some embodiments, the processor may determine the planned economic cost, planned time cost and planned labor cost based on the basic project information and the construction process information, and calculate the planned cost based on the planned economic cost, planned time cost and planned labor cost.

[0085] In some embodiments, the processor may calculate the planned cost based on a method similar to the actual cost, for example, see formula (1). The corresponding economic cost, time cost, and labor cost are the planned economic cost, planned time cost, and planned labor cost.

[0086] Planned economic cost refers to the amount of money consumed by the current schedule. Planned time cost refers to the time until the current schedule is completed. Planned labor cost refers to the cost related to the planned construction personnel arrangement. The calculation method of planned economic cost and planned labor cost is similar to the economic cost and labor cost of actual cost. The difference is that the parameters obtained are planned. For details, please refer to the relevant instructions above.

[0087] In some embodiments, the processor may determine the planned cost based on basic project information, construction progress information, and maximum tolerance.

[0088] The maximum tolerance refers to the maximum value that the cost may deviate from the cost plan. In some embodiments, the maximum tolerance can be set based on experience.

[0089] In some embodiments, the processor may determine the initial planned cost based on the basic project information and the construction progress information, and determine the sum of the initial planned cost and the maximum tolerance as the planned cost. The initial planned cost is the planned cost determined based on the basic project information and the construction progress information, and the determination method can refer to the relevant description above.

[0090] In the actual implementation of the project, there may be certain unexpected situations or differences between the implementation and the plan, so designing a maximum tolerance can make the planned cost more tolerant and more accurate.

[0091] In some implementations, the processor can determine the maximum tolerance based on historical anomaly causes and basic project information.

[0092] The historical abnormality cause refers to the main reason for the cost abnormality in the history of the engineering project. The historical abnormality cause can be determined based on historical data. For example, the processor can construct a feature vector based on at least one of the project specifications, project location, and construction difficulty of the current project, and search for at least one historical abnormality cause corresponding to a reference vector whose similarity with the feature vector is greater than a preset threshold based on the vector database, and use the historical abnormality cause with the most occurrences as the target historical abnormality cause.

[0093] The vector database includes a plurality of reference vectors and corresponding historical anomaly causes, and the reference vectors may be constructed based on at least one of historical project specifications, historical project locations, and historical construction difficulties in the historical data.

[0094] In some embodiments, the processor may determine the maximum tolerance based on each item in the historical data that has the target abnormal cause. For example, the processor may calculate multiple differences between the historical actual costs and the historical planned costs of multiple items corresponding to the target abnormal cause in the historical data, and use the differences as cost differences; multiply the multiple cost differences by the abnormal probability corresponding to the target abnormal cause as the consumption cost; and round the median of the multiple consumption costs to obtain the maximum tolerance. For more information about the abnormal causes and the corresponding abnormal probabilities, please refer to the following text and Figure 4 Related instructions.

[0095] In some embodiments of the present specification, the maximum tolerance is determined based on the historical abnormal causes and basic project information, so that the maximum tolerance can be made consistent with the historical cost abnormalities, thereby making the obtained maximum tolerance more accurate.

[0096] Step 240 , determining a variance value based on the actual cost and the planned cost.

[0097] The variance value reflects the difference between actual cost and planned cost.

[0098] In some embodiments, the processor may calculate the difference value based on the actual cost and the planned cost. For example, the processor may calculate the difference value based on formula (7). Formula (7) is as follows:

[0099] Variance value = (actual cost - planned cost) / planned cost (7)

[0100] Step 250 , in response to the difference value being greater than a preset threshold, determining that the actual cost is abnormal.

[0101] The preset threshold is a critical value of the difference value, which can be preset manually. In some embodiments, the preset threshold is related to the basic information of the project. For example, the preset threshold is positively correlated with the project specifications and construction difficulty in the basic information of the project. The higher the project specifications, the more uncontrollable factors there are, so the range of actual cost differences allowed is larger; the greater the construction difficulty, the more construction problems encountered, so the range of actual cost differences allowed is also larger.

[0102] Step 260 , in response to the actual cost exception, based on the construction process information satisfying a preset condition, determining at least one exception cause and an exception probability.

[0103] The abnormal cause is the reason for the actual cost abnormality. For example, the abnormal cause may include abnormal weather, construction speed, material price changes, construction personnel changes, equipment problems, insufficient material storage, etc.

[0104] In some embodiments, the processor may, in response to the actual cost anomaly, sequentially compare the elements in the construction process information to see if they meet the preset conditions, and determine at least one element that meets the preset conditions as the cause of the anomaly. The elements in the construction process information may include weather, construction progress, actual purchase price of materials and whether the materials are sufficient, actual construction personnel, the number of equipment that has failed, etc. The preset conditions may be set based on experience and actual conditions.

[0105] For example, the preset condition may be that the proportion of weather anomalies exceeds a first preset value, and the processor may search for weather in the construction process information, and determine weather as an abnormal cause based on the proportion of weather anomalies exceeding the first preset value. Weather anomalies may include abnormal weather such as rainy days, snowy days, and hail. Exemplarily, the first preset value may be 30%, and there are 30 days of construction process information, of which 15 days are rainy, and weather is determined as an abnormal cause.

[0106] For another example, the preset condition may be that the proportion of abnormal construction speed is lower than a second preset value, and the processor may determine the speed as an abnormal cause based on the proportion of abnormal construction speed being lower than the second preset value. The abnormal construction speed may include a construction progress being less than a preset progress, such as a construction progress being less than 0.5%. Exemplarily, the second preset value may be set to 20%. If there is 30 days of construction process information, and there are 3 days with a construction progress of less than 0.5%, then the speed is not an abnormal cause; if there are 10 days with a construction progress of less than 0.5%, then the speed is determined to be an abnormal cause.

[0107] The determination of abnormal causes such as changes in construction personnel, equipment problems, changes in material prices, insufficient material storage, etc. is similar to the above. For example, the processor can regard construction personnel as an abnormal cause based on the fact that the proportion of personnel changes is greater than the third preset value. For another example, the processor can regard equipment as an abnormal cause based on the fact that the proportion of equipment failures is greater than the fourth preset value. The third preset value and the fourth preset value can be considered as settings, for example, the third preset value and the fourth preset value are set to 10% and 5% respectively.

[0108] The anomaly probability is the probability corresponding to the cause of the anomaly.

[0109] In some embodiments, the processor may determine the abnormal probability based on the abnormal cause. For example, if there is only one abnormal cause, the abnormal probability corresponding to the abnormal cause is 100%; if there are multiple abnormal causes, the abnormal degree corresponding to each abnormal cause is calculated, and the ratio of each abnormal degree to the sum of all abnormal degrees is used as the corresponding abnormal probability. For example, if there are three abnormal causes, and the abnormal degrees of the abnormal causes are 30%, 30%, and 60%, respectively, then the abnormal probabilities corresponding to the abnormal causes are 25%, 25%, and 50%, respectively.

[0110] In some embodiments, the processor may calculate the degree of abnormality corresponding to the abnormal cause based on the actual abnormal ratio and the preset ratio. For example, the processor may calculate the degree of abnormality corresponding to the abnormal cause based on formula (8). Formula (8) is as follows:

[0111] Abnormality degree = (actual abnormality ratio - preset ratio) / preset ratio (8)

[0112] The actual abnormality ratio is the ratio of the number of days with abnormalities to the total number of days in the current progress. The preset ratio is the preset value corresponding to the cause of the abnormality. Please refer to the description of the cause of the abnormality above.

[0113] For example, the cause of the anomaly includes the weather. For the degree of weather anomaly, the corresponding actual anomaly ratio is the ratio of weather anomaly, and the preset ratio is the first preset value corresponding to the weather. For example, the preset ratio is 30%, and it rains on 15 out of 30 days. Then, the actual anomaly ratio is 50%. Substituting into formula (8), the degree of weather anomaly is calculated to be 66.7%.

[0114] In some embodiments, the processor may determine at least one abnormality cause and abnormality probability based on the basic project information and the construction process information.

[0115] It is understandable that when the basic information of the project is different, such as when the project is located in different geographical locations, the criteria for determining the cause of the anomaly will also be different.

[0116] In some embodiments, the processor can construct a feature vector based on at least one of the project specifications, project location, and construction difficulty in the project process information, search a preset table to determine a reference vector with the highest similarity to the feature vector, and use the reference judgment standard corresponding to the reference vector as the abnormality judgment standard. The preset table includes a mapping relationship between the reference vector and the reference judgment standard, and the preset table can be set manually based on experience. The abnormality judgment standard is a condition used to determine the cause. For example, for ordinary areas, the proportion of weather anomalies is determined to be more than 30% of rainy days; for areas prone to rain, the standard for determining weather anomalies should be higher, such as determining weather anomalies when more than 50% of rainy days are rainy.

[0117] In some embodiments, the processor may determine at least one abnormal cause and abnormal probability based on the construction process information and the abnormality determination criteria. For example, the processor may determine the element in the construction process information that meets the abnormality determination criteria as the abnormal cause; if there is only one abnormal cause, the abnormal probability corresponding to the abnormal cause is determined to be 100%; if there are multiple abnormal causes, the abnormal degree corresponding to each abnormal cause is calculated, and the ratio of each abnormal degree to the sum of all abnormal degrees is used as the abnormal probability corresponding to each abnormal cause. The method for determining the abnormal probability based on the abnormal degree is similar to the above, and the details can be referred to the above and related instructions.

[0118] Adding basic project information as a judgment criterion takes into account the actual situation of the project itself, so that the causes and probabilities of anomalies are more in line with the actual situation of the project itself, and can be applied to anomaly analysis of different projects.

[0119] Step 270, determining at least one project adjustment parameter based on at least one abnormality cause and abnormality probability.

[0120] The project adjustment parameter is an adjustment parameter for adjusting the project parameters of the engineering project. In some embodiments, the project adjustment parameter includes at least one of the task level, task scope, task sequence, and resource allocation parameter.

[0121] Task level refers to the hierarchical structure of tasks in WBS. Adjusting task level includes increasing or decreasing task level, merging or splitting tasks, etc. Task scope refers to the specific scope and work content of tasks. Adjusting task scope can ensure that each task is clearly defined in the project WBS. Adjusting task sequence can ensure that the execution sequence of tasks is reasonable and avoid conflicts and overlaps between tasks. Resource allocation parameters include the allocation of resources such as manpower, equipment, and materials in each task.

[0122] One abnormal cause can correspond to multiple project adjustment parameters, and one project parameter can also correspond to multiple abnormal causes.

[0123] In some embodiments, the processor may use the abnormal probability corresponding to the abnormal cause as the sub-weight of the project adjustment parameter corresponding to the abnormal cause; calculate the sum of the sub-weights corresponding to the same project adjustment parameters corresponding to different abnormal causes, and use the sum of the sub-weights as the weight corresponding to the project adjustment parameter; and select at least one project adjustment parameter with the highest weight as the target project adjustment parameter. For the abnormal cause and the corresponding abnormal probability, please refer to the relevant description above.

[0124] For example, abnormal cause A corresponds to parameters ①②, and the abnormal probability of abnormal cause A is 40%; abnormal cause B corresponds to parameters ②③, and the abnormal probability of abnormal cause B is 50%. Then the sub-weights of parameter ② are 40% and 50% respectively, and the weight of parameter ② is 90%.

[0125] The correspondence between the abnormal cause and the project adjustment parameters can be determined based on historical data or human experience. For example, if the weather is abnormal, the task scope and task sequence will be adjusted, such as handling outdoor work on sunny days and indoor work on rainy days; if the construction progress is abnormal, the task level and task sequence will be adjusted.

[0126] Selecting the highest-weighted abnormal causes for adjustment instead of adjusting all of them can avoid making too large adjustments to the project at one time, which can lead to overlapping or missing tasks, duplication or waste of resources, and delays in the overall progress and completion time of the project.

[0127] Figure 3 is an exemplary schematic diagram of a fault prediction model according to some embodiments of the present specification.

[0128] In some embodiments, Figure 3 As shown, the processor can predict the future failure rate 330 of the equipment through a fault prediction model 320 based on the equipment's daily working hours 311, daily output 312, sound sequence 313, vibration sequence 314, equipment type 315 and initial future failure rate 316; and determine the second operating cost 340 based on the future failure rate 330.

[0129] The sound sequence 313 is a sequence related to the sound of equipment in the construction project. For example, the sound sequence can be a loudness sequence.

[0130] The vibration sequence 314 refers to an amplitude sequence and / or frequency sequence of the vibration sound of the equipment during the construction project.

[0131] In some embodiments, the processor may obtain a sound sequence and a vibration sequence corresponding to each device based on a sound sensor on each device.

[0132] To save resources, the processor can collect sound sequences and vibration sequences during a preset time period every day. The preset time period can be set according to needs, such as 8:00-10:00, etc.

[0133] The equipment type 315 refers to the type of equipment used in the construction project, such as an excavator, a concrete mixer, a crane, etc. The processor may obtain the equipment type uploaded by the user based on the user terminal.

[0134] For more information about daily working hours and daily output, please refer to Figure 2 And related instructions.

[0135] The future failure rate 330 refers to the possibility that the device will fail within a preset time period in the future. The initial future failure rate 316 refers to the probability that the device will fail initially. The initial future failure rate can be set manually or based on historical data. For example, the initial future failure rate can be the historical failure rate in the historical data corresponding to the time closest to the current time. For another example, the initial future failure rate can be set manually based on experience, and the initial future failure rate is positively correlated with the service life of the device.

[0136] The fault prediction model 320 is a model for predicting the future failure rate of a device. In some embodiments, the fault prediction model is a machine learning model, such as a deep neural network (DNN) model, a neural network (NN) model, or at least one of other models.

[0137] In some embodiments, the fault prediction model can be obtained by training a large number of first training samples and first labels corresponding to the first training samples. In some embodiments, a plurality of first training samples with first labels can be input into the initial fault prediction model, a loss function can be constructed by the first labels and the results of the initial fault prediction model, and the parameters of the initial fault prediction model can be iteratively updated based on the loss function by gradient descent or other methods. When the preset conditions are met, the model training is completed and a trained fault prediction model is obtained. The preset conditions can be that the loss function converges, the number of iterations reaches a threshold, etc.

[0138] Each group of training samples in the first training samples may include sample daily working hours, sample daily output, sample sound sequence, sample vibration sequence, sample equipment type and sample initial future failure rate in the sample data. The first training samples may be obtained based on equipment related data that has failed in historical data.

[0139] The first label corresponding to the first training sample is the future failure rate of the sample corresponding to each group of training samples. The first label can be obtained by manual labeling or automatic labeling. For example, the future failure rate refers to the possibility of failure in the future period. The possibility of failure in the corresponding future period in the past time can be obtained based on historical data as the first label, and the failure is marked as 1 and the failure is marked as 0.

[0140] Exemplarily, the future time period may be within the next month, if device A fails on March 5, sample 1 is the relevant data of device A on and before January 5, because device A did not fail from January 5 to February 5, the first label corresponding to sample 1 is marked as 0; sample 2 is the relevant data of device A on and before March 1, because device A failed on March 5, which is a recent failure, so the corresponding first label of sample 2 is marked as 1; sample 3 is the relevant data of device A on and before February 7, and sample 3 also fails in the next month, but compared with sample 2, the failure of sample 3 occurs later, and the first label corresponding to the sample can be appropriately attenuated, such as marked as 0.8.

[0141] In some embodiments, the second operating cost 340 is positively correlated with the future failure rate 330. The processor may determine the second operating cost 340 by calculation based on the future failure rate 330. For example, the processor may calculate the second operating cost by formula (9). Formula (9) is as follows:

[0142]

[0143] Among them, s is the number of devices operating normally. represents the future failure rate of equipment i on the last day of construction, represents the future failure rate of equipment i on the first day of construction; α is the preset amplification factor, due to The second operating cost values ​​obtained by decimal calculation are too small. The calculated values ​​can be amplified by using a preset magnification coefficient α to make the obtained second operating cost more accurate.

[0144] In some embodiments of the present specification, a fault prediction model is used to predict the future failure rate, thereby determining the second operating cost based on the future failure rate. This can improve the accuracy of the prediction of the future failure rate, reduce the error rate of manual judgment, and thus improve the reliability of the subsequently determined second operating cost.

[0145] The fault prediction model includes multiple prediction sub-models, and the multiple prediction sub-models output future failure rates in different future time periods. For example, the prediction sub-model may include predicting the future failure rate in the next month, the future failure rate in the next two months, the future failure rate in the next three months, etc. The training method of the prediction sub-model is similar to the training method of the fault prediction model. The training samples of the prediction sub-model are sample day working hours, sample day output, sample sound sequence, sample vibration sequence, sample equipment type, and sample initial future failure rates in different future time periods. The corresponding training label can be determined based on whether a fault occurs in the future time period corresponding to the training sample in the historical data. If a fault occurs, the training label corresponding to the training sample is marked as 1. If no fault occurs, the training label corresponding to the training sample is marked as 0.

[0146] In some embodiments, the processor may determine the second operating cost by weighting based on the future failure rates of the device in different future time periods. The weighted weights of the future failure rates in different future time periods are related to the time distance between each future time period and the current moment. The weighted weights of the future failure rates in different future time periods are negatively correlated with the time distance between each future time period and the current moment, and the second operating cost is positively correlated with the weighted weights.

[0147] For example, the processor may calculate the second operating cost by using formula (10). Formula (10) is as follows:

[0148]

[0149] Where t represents the total number of different future time periods; represents the future failure rate of device i in the last day corresponding to the jth future time period, represents the future failure rate of device i on the first day corresponding to the jth future time period, It represents the weighted weight of the future failure rate in the jth future time period. The closer the jth future time period is to the current moment, the greater the weighted weight.

[0150] The closer the predicted future failure rate is to the current time, the higher the prediction accuracy is, the higher the corresponding weight is, and the more accurate the weighted determination of the second operating cost is.

[0151] In some embodiments, the processor may determine the importance of the equipment based on a preset cost value of the equipment, project participation, and the number of the same type; and determine a second operating cost based on the importance and future failure rate.

[0152] Project participation refers to the proportion of equipment planned to participate in the entire project. For example, if a mixer is always needed, the project participation is 100%; a tower crane is used when building high floors, but is generally not needed when building basements and low floors, so the project participation can be set to 60%.

[0153] The project participation of the equipment is related to the construction process information. For example, the processor can determine the number of days each equipment is used based on the construction process information, and use the number of days used and the total number of construction days as the project participation of the equipment.

[0154] The number of the same type refers to the number of devices with the same function. It is understandable that the more devices with the same function there are, the smaller the impact of a single device failure, and the lower the operating cost.

[0155] For a description of the preset cost values, see Figure 2 .

[0156] Importance refers to the importance of equipment in the construction process. Importance is positively correlated with the preset cost value and project participation, and negatively correlated with the number of the same type.

[0157] In some embodiments, the processor may normalize the preset cost value, project participation, and number of the same type of the device, respectively, and use the average of the normalized preset cost value, project participation, and number of the same type as the importance of the device.

[0158] Normalization of preset cost values ​​means that the minimum value of all preset cost values ​​of all devices is normalized to 0, the maximum value is normalized to 1, and the preset cost values ​​of other devices are normalized to [0,1] according to a linear relationship. The normalization of project participation is the same. Normalization of the same type of quantity means that the maximum value of the same type of quantity of all devices is normalized to 0, the minimum value is normalized to 1, and the same type of quantity of other devices is normalized to [0,1] according to a linear relationship.

[0159] In some embodiments, the processor may determine the second operating cost by calculation based on the importance and the future failure rate. The second operating cost is positively correlated with the importance and the future failure rate.

[0160] For example, the processor may calculate the second operating cost based on formula (11). Formula (11) is as follows:

[0161]

[0162] Among them, Z i It represents the importance of device i. The meanings of other parameters are the same as those in formula (9). Please refer to the previous description for details.

[0163] For the same type of equipment, the corresponding operating costs may be different due to different costs, involvement and the number of equipment of the same type. The second operating cost is determined based on importance and future failure rate, taking into account the differences in the usage of each device, thereby making the calculated second operating cost more accurate.

[0164] Figure 4 is an exemplary schematic diagram of a causal analysis model according to some embodiments of the present specification.

[0165] In some embodiments, the processor may determine at least one abnormal cause and abnormal probability based on the basic project information, construction progress information, and construction process information through a cause analysis model.

[0166] The cause analysis model is a model used to determine the cause of an abnormality and the probability of an abnormality. In some embodiments, the cause analysis model is a machine learning model, for example, at least one of a recurrent neural network (RNN) model, a neural network (NN) model, or other models.

[0167] In some embodiments, Figure 4As shown, the cause analysis model 401 includes a first prediction layer 420 and a second prediction layer 430. In some embodiments, the processor can determine the ideal process information 430 through the first prediction layer 420 based on the project basic information 411 and the construction progress information 412; and determine at least one abnormal cause 451 and abnormal probability 452 through the second prediction layer 440 based on the construction process information 413 and the ideal process information 430.

[0168] The ideal process information 430 refers to the process information of each day under the predicted plan state. The ideal process information can roughly reflect the overall situation of the construction process of the project. For example, for the weather, the ratio of sunny days to rainy days reflected by the ideal process information is consistent with the plan state. In some embodiments, the ideal process information includes weather, construction personnel, progress, types and quantities of materials used, actual purchase prices and whether they are sufficient, types and quantities of equipment used on the day, and types and quantities of equipment that have failed.

[0169] The first prediction layer 420 is a model structure for predicting ideal process information. In some embodiments, the first prediction layer is a machine learning model, such as a RNN model.

[0170] In some embodiments, the first prediction layer can be trained by a large number of second training samples and second labels corresponding to the second training samples. The training method is similar to the fault prediction model, and can be specifically referred to in Figure 3 And related instructions.

[0171] Each group of training samples in the second training samples may include sample project basic information and sample construction progress information in the sample data. The second training samples may be obtained based on historical related data of engineering projects with no abnormal actual costs in historical data. The historical construction process information corresponding to the second training samples is used as the second label.

[0172] The second prediction layer 430 is a model structure for predicting abnormal causes and abnormal probabilities. In some embodiments, the second prediction layer is a machine learning model, such as a NN model.

[0173] In some embodiments, the second prediction layer can be obtained by training a large number of third training samples and third labels corresponding to the third training samples. The training method is similar to the fault prediction model, and can be specifically referred to in Figure 3 And related instructions.

[0174] Each group of training samples in the third training samples may include construction process information with actual cost anomalies in historical data and ideal process information predicted by the first prediction layer. The third label may be obtained by manual annotation.

[0175] For example, the difference between the two sets of data is manually analyzed, and the construction process information that does not conform to the ideal process information is marked as the abnormal cause in the third label, and the proportion of the occurrence of a certain abnormal cause to the total occurrence of all abnormal causes is marked as the abnormal probability of the abnormal cause in the third label. For example, in the ideal process information, it rained for 2 days and the equipment did not fail. In the actual construction process information, it rained for 6 days and a certain equipment failed for 6 days. Among them, 4 days of rain and 6 days of equipment failure are abnormal. The abnormal probability of the abnormal cause being weather is 40%, and the abnormal probability of being equipment failure is 60%.

[0176] In some embodiments, the input of the cause analysis model also includes the first operating cost and the second operating cost. The processor can determine at least one abnormal cause and abnormal probability through the cause analysis model based on the basic project information, construction progress information, construction process information, the first operating cost and the second operating cost.

[0177] In some embodiments, the first operating cost and the second operating cost can be used as inputs of the second prediction layer. The processor can determine at least one abnormal cause and abnormal probability through the second prediction layer based on the construction process information, the ideal process information, the first operating cost and the second operating cost. Each group of training samples in the third training samples can include the construction process information of the engineering project with abnormal actual cost in the historical data, the ideal process information predicted by the first prediction layer, and the historical first operating cost and the historical second operating cost corresponding to the engineering project with abnormal actual cost in the historical data.

[0178] The first operating cost and the second operating cost can reflect the impact of equipment usage during the construction process on the actual cost of the project. As the input of the cause analysis model, they can more accurately determine the abnormal causes related to equipment operation problems.

[0179] 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.

[0180] 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. In addition, some features, structures or characteristics in one or more embodiments of this specification can be appropriately combined.

[0181] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences, the use of alphanumeric characters, or the use of other names described in this specification are not intended to limit the order of the processes and methods of this specification. 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.

[0182] 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.

[0183] In some embodiments, numerical parameters should consider the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their ranges in some embodiments of this specification are approximate values, in specific embodiments, the settings of such numerical values ​​are as accurate as possible within the feasible range.

[0184] 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 cost management system for the entire process, including an information acquisition module, a cost estimation module, an abnormality analysis module and an adjustment module: The information acquisition module is configured to acquire basic project information, construction process information and construction progress information; The cost estimation module is configured to: Determine the actual cost based on the basic project information and the construction process information; Determine the planned cost based on the basic project information and the construction progress information; The abnormality analysis module is configured as follows: Determine a variance value based on the actual cost and the planned cost; In response to the difference value being greater than a preset threshold, determining that the actual cost is abnormal, the preset threshold being related to project specifications and construction difficulty; In response to the actual cost anomaly, determining at least one anomaly cause and an anomaly probability based on the construction process information satisfying a preset condition; The abnormal cause and the abnormal probability are obtained through a cause analysis model based on the basic information of the project, the construction progress information, the construction process information, the first operating cost and the second operating cost; the cause analysis model is a machine learning model; The cause analysis model includes a first prediction layer and a second prediction layer; the first operating cost refers to the cost caused by the failure and / or damage of the construction equipment, and the second operating cost refers to the depreciation cost caused by the normal operation of the construction equipment; The first prediction layer is used to determine the ideal process information based on the basic information of the project and the construction progress information; the second prediction layer is used to determine the at least one abnormal cause and the abnormal probability based on the construction process information, the ideal process information, the first operating cost and the second operating cost; the element in the construction process information that meets the abnormality determination standard is determined as the abnormal cause, and in response to the existence of only one abnormal cause, the abnormal probability corresponding to the abnormal cause is determined to be 100%; in response to the existence of multiple abnormal causes, the abnormal degree corresponding to each abnormal cause is calculated, and the ratio of each abnormal degree to the sum of all abnormal degrees is used as the corresponding abnormal probability; wherein the calculation formula of the abnormal degree is: abnormal degree = (actual abnormal proportion - preset proportion) / preset proportion; The adjustment module is configured to determine at least one project adjustment parameter based on the at least one abnormal cause and the abnormal probability, wherein one abnormal cause corresponds to a plurality of project adjustment parameters, and one project adjustment parameter corresponds to a plurality of abnormal causes; the determining at least one project adjustment parameter based on the at least one abnormal cause and the abnormal probability comprises: Determine the abnormal probability corresponding to the abnormal cause as a sub-weight of the project adjustment parameter corresponding to the abnormal cause; Determine the sum of the sub-weights corresponding to the same item adjustment parameters corresponding to different abnormal causes as the weight corresponding to the same item adjustment parameters; At least one of the project adjustment parameters with the highest weight is selected as the target project adjustment parameter.

2. The system according to claim 1, characterized in that: The cost estimation module is further configured to: Based on the basic information of the project and the construction process information, determine economic cost, labor cost, time cost and operation cost, wherein the operation cost at least includes the first operation cost; The actual cost is determined by weighting based on the economic cost, the labor cost, the time cost and the operating cost.

3. The system according to claim 2, characterized in that: The operating cost also includes a second operating cost, the construction process information also includes the daily working hours and daily output of the equipment, and the cost estimation module is further configured as follows: The second running cost is determined based on the daily operating hours and the daily output of the equipment.

4. The system according to claim 1, characterized in that: The cost estimation module is further configured to determine the planned cost based on the basic project information, the construction progress information and the maximum tolerance.

5. A method for managing the entire cost process, comprising: Obtain basic project information, construction process information and construction progress information; Determine the actual cost based on the basic project information and the construction process information; Determine the planned cost based on the basic project information and the construction progress information; Determine a variance value based on the actual cost and the planned cost; In response to the difference value being greater than a preset threshold, determining that the actual cost is abnormal, the preset threshold being related to project specifications and construction difficulty; In response to the actual cost anomaly, determining at least one anomaly cause and an anomaly probability based on the construction process information satisfying a preset condition; The abnormal cause and the abnormal probability are obtained through a cause analysis model based on the basic information of the project, the construction progress information, the construction process information, the first operating cost and the second operating cost; the cause analysis model is a machine learning model; The cause analysis model includes a first prediction layer and a second prediction layer; the first operating cost refers to the cost caused by the failure and / or damage of the construction equipment, and the second operating cost refers to the depreciation cost caused by the normal operation of the construction equipment; The first prediction layer is used to determine the ideal process information based on the basic information of the project and the construction progress information; the second prediction layer is used to determine the at least one abnormal cause and the abnormal probability based on the construction process information, the ideal process information, the first operating cost and the second operating cost; the element in the construction process information that meets the abnormality determination standard is determined as the abnormal cause, and in response to the existence of only one abnormal cause, the abnormal probability corresponding to the abnormal cause is 100%; in response to the existence of multiple abnormal causes, the abnormal degree corresponding to each abnormal cause is calculated, and the ratio of each abnormal degree to the sum of all abnormal degrees is used as the corresponding abnormal probability; wherein the calculation formula of the abnormal degree is: abnormal degree = (actual abnormal proportion-preset proportion) / preset proportion; based on the at least one abnormal cause and the abnormal probability, at least one project adjustment parameter is determined, wherein one abnormal cause corresponds to multiple project adjustment parameters, and one project adjustment parameter corresponds to multiple abnormal causes; the determination of at least one project adjustment parameter based on the at least one abnormal cause and the abnormal probability includes: Determine the abnormal probability corresponding to the abnormal cause as a sub-weight of the project adjustment parameter corresponding to the abnormal cause; Determine the sum of the sub-weights corresponding to the same item adjustment parameters corresponding to different abnormal causes as the weight corresponding to the same item adjustment parameters; The at least one item adjustment parameter with the highest weight is selected as the target item adjustment parameter.

6. The method according to claim 5, characterized in that The determining of the actual cost based on the basic project information and the construction process information includes: Based on the basic information of the project and the construction process information, determine economic cost, labor cost, time cost and operation cost, wherein the operation cost at least includes the first operation cost; The actual cost is determined by weighting based on the economic cost, the labor cost, the time cost and the operating cost.

7. The method according to claim 6, characterized in that: The operating cost also includes a second operating cost, the construction process information also includes the daily working hours and daily output of the equipment, and the economic cost, labor cost, time cost and operating cost determined based on the basic project information and the construction process information include: The second running cost is determined based on the daily operating hours and the daily output of the equipment.

8. The method according to claim 5, characterized in that: Determining the planned cost based on the basic project information and the construction progress information includes: The planned cost is determined based on the basic project information, the construction progress information and the maximum tolerance.

Images