A method and system for calculating engineering cost

Abstract

The present invention relates to the field of engineering cost technology, and specifically to a method and system for calculating engineering cost. The method includes: obtaining risk sequences constructed from historical risk information in historical construction processes, and obtaining multiple initial risk points based on the similarity between risk sequences; constructing risk vectors based on the frequency of occurrence of keywords in the initial risk points; clustering the initial risk points based on the similarity between risk vectors to obtain target clusters, potential risk points, and risk types; obtaining the probability of occurrence of potential risk points based on the triggering causes of the risk types of potential risk points and the total number of risk types; and determining the predicted cost of the current project based on the affected conditions corresponding to the potential risk points in the historical risk information, the overall similarity between the risk vectors in the target cluster where the potential risk points are located, the probability of occurrence, and the initial cost of the current project. The present invention improves the efficiency of calculating the cost of engineering projects and the accuracy of the calculation results.

Description

Technical Field

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

[0002] Project cost estimation refers to the process of detailed estimation and calculation of various project expenses and costs during the construction process. By accurately estimating project costs, the required funds can be determined before project implementation, avoiding budget overruns during project development and ensuring that the project proceeds smoothly within the predetermined funding framework. It can also be used to determine whether the project is progressing, improve overall project efficiency, and mitigate potential cost risks. The analysis of potential risk points has a significant impact on the overall cost estimation results. The more comprehensive the potential risk point analysis, the more accurate the cost estimation results.

[0003] Existing methods for predicting potential risk points typically use methods such as field visits, expert opinion aggregation, and artificial intelligence analysis to aggregate potential risk points, and then use this aggregated data to determine their impact on cost estimates. However, in these potential risk point prediction methods, the aggregated results are often relatively rough. This means that when analyzing the likelihood and impact of a risk, the results are susceptible to bias due to factors such as the evaluator's subjective impressions and the richness of the data. Furthermore, the analysis of potential risk points requires a large amount of data and complex calculations, resulting in a high probability of error in the prediction results, which in turn affects the accuracy of cost estimates. Summary of the Invention

[0004] In order to solve the problem of low accuracy of the calculation results in the process of calculating the cost of engineering projects in the existing methods, the purpose of the present invention is to provide a method and system for calculating the construction cost. The technical solutions adopted are as follows:

[0005] In a first aspect, the present invention provides a method for calculating construction cost, the method comprising the following steps:

[0006] Obtain historical risk information from historical construction processes and construct risk sequences based on this information;

[0007] Based on the similarities between risk sequences, the risk sequences under the same information source are divided into several groups. Risk vectors are constructed based on the frequency of occurrence of keywords in the initial risk points. Each group is an initial risk point. The initial risk points are clustered based on the similarities between risk vectors to obtain several target clusters, potential risk points, and risk types.

[0008] Based on the triggering causes of the risk types of potential risk points and the total number of risk types, the probability of occurrence of potential risk points is obtained. The overall impact weight of potential risk points on the project is obtained by combining the impact conditions corresponding to the potential risk points in historical risk information, the overall similarity between risk vectors within the target cluster where the potential risk points are located, the probability of occurrence, and the initial cost of the current project. The predicted risk cost of the current project is determined using the impact conditions, probability of occurrence, and overall impact weight corresponding to all potential risk points.

[0009] Obtain the predicted cost of the current project based on the initial cost and predicted risk cost of the current project.

[0010] Preferably, the risk sequences under the same information source are divided into several groups according to the similarities between the risk sequences, including:

[0011] For any source:

[0012] Obtaining a similarity between the risk sequences under any information source based on a difference in the number of elements and a DTW distance in the risk sequences under any information source, wherein the difference in the number of elements and the DTW distance are negatively correlated with the similarity;

[0013] A preset number of risk sequences are randomly selected as initial centers, and risk sequences whose similarity to the initial centers is greater than a preset similarity threshold are grouped together.

[0014] Preferably, the step of constructing a risk vector based on the frequency of occurrence of keywords in the initial risk point includes:

[0015] Obtain all keywords within the candidate initial risk points;

[0016] The vector consisting of all keywords in the candidate initial risk point whose occurrence frequency is greater than the preset frequency threshold is used as the risk vector of the candidate initial risk point;

[0017] The candidate initial risk point is any initial risk point.

[0018] Preferably, clustering the initial risk points according to the similarity between the risk vectors to obtain several target clusters, potential risk points and risk types includes:

[0019] A hierarchical clustering algorithm is used to cluster all initial risk points, and the average value of the similarities between all risk vectors in each cluster is used as the similarity level corresponding to each cluster;

[0020] The layer with the largest degree of discreteness of similarity corresponding to all clusters is taken as the final clustering result, and each target cluster in the final clustering result is obtained, and each target cluster is regarded as a potential risk point;

[0021] The next layer of the final clustering result is used as the risk type corresponding to each target cluster.

[0022] Preferably, obtaining the occurrence probability of the potential risk point according to the triggering cause of the risk type of the potential risk point and the total number of risk types includes:

[0023] For any potential risk point:

[0024] Determining a first occurrence probability of a risk type of any potential risk point according to the total number of risk types;

[0025] Determining a second occurrence probability of any potential risk point within the corresponding risk type according to the number of triggering causes of any potential risk point;

[0026] The first occurrence probability and the second occurrence probability are combined to determine the occurrence probability of any potential risk point.

[0027] Preferably, the overall impact weight of the potential risk point on the project is obtained by combining the impact situation corresponding to the potential risk point in the historical risk information, the overall similarity between the risk vectors in the target cluster where the potential risk point is located, the probability of occurrence, and the initial cost of the current project, including:

[0028] For any potential risk point:

[0029] Calculate the average impact amount of all historical risks associated with the potential risk point, and record it as the average impact amount; the impact amount is the difference between the final project cost and the initial estimated cost;

[0030] calculating a first ratio between the average impact amount and the initial cost of the current project;

[0031] The normalized result of the product of the similarity degree corresponding to any potential risk point, the average impact amount and the first ratio is determined as the overall impact weight of any potential risk point on the project.

[0032] Preferably, the method of determining the predicted risk cost of the current project by utilizing the impact conditions, occurrence probabilities, and overall impact weights corresponding to all potential risk points includes:

[0033] For any potential risk point: the maximum impact value of any potential risk point is obtained by combining the average impact amount corresponding to the potential risk point, the probability of occurrence of the potential risk point, and the overall impact weight of the potential risk point on the project;

[0034] The cumulative sum of the maximum impact values ​​of all potential risk points is taken as the predicted risk cost of the current project.

[0035] Preferably, obtaining the predicted cost of the current project based on the initial cost and predicted risk cost of the current project includes:

[0036] The sum of the initial cost of the current project and the predicted risk cost is determined as the predicted cost of the current project.

[0037] Preferably, obtaining the discrete degree of the similarity degrees corresponding to all clusters includes: taking the variance of the similarity degrees corresponding to all clusters as the discrete degree.

[0038] In a second aspect, the present invention provides a system for calculating construction cost, the system comprising:

[0039] The data collection module is used to obtain historical risk information during the historical construction process and construct various risk sequences based on the historical risk information;

[0040] The first processing module is used to divide risk sequences under the same information source into several groups based on the similarities between risk sequences; construct risk vectors based on the frequency of occurrence of keywords in the initial risk points; each group is an initial risk point; and cluster the initial risk points based on the similarities between risk vectors to obtain several target clusters, potential risk points, and risk types;

[0041] The second processing module is used to obtain the probability of occurrence of potential risk points based on the triggering cause of the risk type of the potential risk point and the total number of risk types; combine the impact of the potential risk point corresponding to the historical risk information, the overall similarity between the risk vectors in the target cluster where the potential risk point is located, the probability of occurrence, and the initial cost of the current project to obtain the overall impact weight of the potential risk point on the project; and use the impact, probability of occurrence, and overall impact weight corresponding to all potential risk points to determine the predicted risk cost of the current project;

[0042] The prediction module is used to obtain the predicted cost of the current project based on the initial cost and predicted risk cost of the current project.

[0043] The present invention has at least the following beneficial effects:

[0044] The present invention first divides the risk sequences under the same information source into multiple groups based on the similarities between risk sequences in historical risk information during historical construction processes. Each group is regarded as an initial risk point. A risk vector is constructed based on the frequency of occurrence of keywords in the initial risk points. The initial risk points are clustered into multiple target clusters based on the similarities between the risk vectors, and potential risk points are determined. These risk points are potential risk points that may be encountered in the current project. Through grouping and clustering, the potential patterns and associations in the data are mined, the historical risk information is summarized, and the accuracy of identifying potential risk points is improved. Furthermore, the risk cost of the current project is predicted by combining the triggering causes of the risk types of the potential risk points, the total number of risk types, the corresponding affected conditions of the potential risk points in the historical risk information, and the initial cost of the current project. The predicted cost of the current project is then determined based on the initial cost of the current project. By constructing a risk database for each potential risk point, the present invention can quickly and accurately output the probability of occurrence of the potential risk point and the impact on the current project by simply matching the project type and content when conducting potential risk analysis, thereby improving the efficiency and accuracy of project cost estimation. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0046] Figure 1 A flowchart of a method for calculating construction cost provided by an embodiment of the present invention;

[0047] Figure 2 This is a structural block diagram of a construction cost calculation system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0048] In order to further illustrate the technical means and effects adopted by the present invention to achieve the predetermined purpose of the invention, the following is a detailed description of a method and system for calculating the construction cost proposed in accordance with the present invention in combination with the accompanying drawings and preferred embodiments.

[0049] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0050] The following describes in detail a method and system for calculating construction cost provided by the present invention with reference to the accompanying drawings.

[0051] An embodiment of a method for calculating construction cost:

[0052] The specific scenario targeted by this embodiment is: in the process of calculating the cost of an engineering project, in order to ensure the accuracy of the calculation results, it is necessary to determine the potential risk points of the engineering project, and estimate the impact of the potential risk points based on the potential risk points, and then obtain the cost amount of the engineering project.

[0053] This embodiment proposes a method for calculating the construction cost. Figure 1 As shown, a method for calculating construction cost in this embodiment includes the following steps:

[0054] Step S1: Obtain historical risk information during historical construction processes, and construct risk sequences based on the historical risk information.

[0055] First, obtain project documents from all projects under construction during the historical time period, including design drawings, contract documents, and technical specifications. Then, based on the design drawings and technical specifications, determine the material prices of the required raw materials, labor costs, and prices of various instruments and equipment. Furthermore, understand relevant policies in the region where the project is located, including tax policies and environmental protection requirements. Simultaneously, conduct an on-site survey of the construction site to obtain site information, including construction site conditions, project volume, and potential problems during construction. Subsequently, summarize historical risks for the company's own historical projects, its clients' historical projects, and other similar projects. It should be noted that this summarized historical risk information is extracted using artificial intelligence algorithm models, such as the BERT model, to extract key information, such as distributor A and the price fluctuations of each material. Implementers set the historical time period based on their specific circumstances, and this will not be elaborated on here.

[0056] It should be noted that the data and information collected by this application are obtained with full consent and authorization, and the collection, use and processing of relevant information must comply with relevant regulations.

[0057] This embodiment uses the historical risk information collected through the historical construction process as a reference to calculate the cost of the current project.

[0058] Furthermore, for any historical risk, all keywords in the historical risk are extracted, such as: dealer A, price fluctuation range of each material, equipment price fluctuation range, etc., and these keywords are used to construct a risk sequence. Specifically, all keywords in the historical risk are converted into word vectors, and then the word vectors corresponding to the historical risk constitute the risk sequence.

[0059] So far, this embodiment has obtained multiple risk sequences in the historical construction process.

[0060] Step S2: Divide the risk sequences under the same information source into several groups based on the similarities between risk sequences; construct risk vectors based on the frequency of occurrence of keywords in the initial risk points; each group is an initial risk point; cluster the initial risk points based on the similarities between risk vectors to obtain several target clusters, potential risk points and risk types.

[0061] Since the historical risk information summarized in the preliminary preparations comes from different engineering projects, there are certain differences between different historical risk information, that is, there are differences in the participating parties and project locations, among which the participating parties include contractors, managers and suppliers.

[0062] However, by clustering historical risk information, classifying it into different potential risk points and constructing corresponding potential risk point sets, it is possible to associate the historical risks of different engineering projects, thereby improving the accuracy of potential risk point analysis and the difficulty of obtaining them.

[0063] Therefore, this embodiment will group the risk sequences so that the similarity of all risk sequences in the same group is higher, and the similarity of risk sequences between different groups is lower. The similarity between different risk sequences can be characterized by the dynamic time warping distance. The larger the dynamic time warping distance between two sequences, the lower the degree of matching between the two sequences, that is, the less similar the fluctuations of the two sequences are. In addition, considering that there may be length differences between two risk sequences, and the dynamic time warping distance cannot intuitively reflect the length differences between different risk sequences, this embodiment will combine the dynamic time warping distance between different risk sequences and the length differences between different risk sequences to evaluate the similarity between each pair of sequences, and divide different risk sequences based on the evaluation results.

[0064] In this embodiment, one participant is regarded as an information source. Next, this embodiment is described using one information source as an example. The risk sequences of other information sources can be processed using the method provided in this embodiment.

[0065] For any source:

[0066] The dynamic time warping (DTW) distance between each pair of risk sequences under the information source is calculated. The similarity between each pair of risk sequences under the information source is obtained based on the difference in the number of elements in the pair of risk sequences under the information source and the DTW distance. The difference in the number of elements and the DTW distance are negatively correlated with the similarity.

[0067] Among them, the negative correlation relationship means that the dependent variable will decrease as the independent variable increases, and the dependent variable will increase as the independent variable decreases. It can be a subtraction relationship, a division relationship, etc., which is determined by actual application.

[0068] In this embodiment, a specific calculation formula for the similarity between risk sequences is given. The similarity between the i-th risk sequence and the j-th risk sequence can be expressed as:

[0069]

[0070] in, represents the similarity between the i-th risk sequence and the j-th risk sequence, represents the number of elements in the ith risk sequence, represents the number of elements in the j-th risk sequence, represents the DTW distance between the i-th risk sequence and the j-th risk sequence, Indicates the absolute value sign, Represents the normalization function.

[0071] In this embodiment, the constant 1 is added to the denominator of the similarity calculation formula to prevent the denominator from being 0. In specific applications, the implementer can set it according to specific circumstances. Represents the difference in the number of elements between the i-th risk sequence and the j-th risk sequence. The larger the value, the greater the length difference between the two sequences. The larger the DTW distance between the i-th risk sequence and the j-th risk sequence, the lower the degree of match between the two, that is, the lower the similarity. When the difference in the number of elements between the i-th risk sequence and the j-th risk sequence is smaller, and the DTW distance between the i-th risk sequence and the j-th risk sequence is also smaller, it means that the i-th risk sequence and the j-th risk sequence are more similar, that is, the greater the similarity between the i-th risk sequence and the j-th risk sequence.

[0072] By adopting the above method, the similarity between any two risk sequences under the information source can be obtained. A preset number of risk sequences are randomly selected as the initial centers, and the risk sequences whose similarity with each initial center is greater than the preset similarity threshold are grouped together, that is, the risk sequences under the information source are divided into multiple groups, and each group is taken as an initial risk point, that is, multiple initial risk points are obtained. It should be noted that if the similarity between a certain risk sequence and all the initial sequences is less than or equal to the preset similarity threshold, it means that the risk sequence may have information collection errors or other situations during data collection, and will not be analyzed subsequently. In this embodiment, the preset number is 10, and the preset similarity threshold is 0.5. In specific applications, the implementer can set the preset number and preset similarity threshold according to the specific situation.

[0073] Next, this embodiment is described using an initial risk point as an example. Other initial risk points can be processed using the method provided in this embodiment.

[0074] Specifically, any initial risk point is designated as a candidate initial risk point, and all keywords within the candidate initial risk point are obtained. The frequency of occurrence of each keyword within the candidate initial risk point is calculated. A vector consisting of keywords within the candidate initial risk point whose frequency of occurrence exceeds a preset frequency threshold is used as the risk vector for the candidate initial risk point. This means that keywords with lower frequency of occurrence are eliminated, and the risk vector is composed of keywords with higher frequency of occurrence. In this embodiment, the preset frequency threshold is 0.4; in specific applications, the implementer can set this threshold based on specific circumstances.

[0075] Next, this example uses a hierarchical clustering algorithm to cluster all initial risk points across all information sources, generating clustering results at varying levels of precision. This facilitates the aggregation and consolidation of potential risk points across different information sources. It should be noted that risk types include market risk, technical risk, and management risk, and triggering factors include material price fluctuations (market risk), changes in technical standards (technical risk), and delayed delivery and substandard quality (management risk).

[0076] Specifically, a hierarchical clustering algorithm is used to perform agglomerative hierarchical clustering on all initial risk points. Each sample begins as an independent class, and the classes with the highest similarity are gradually merged until all samples are merged into one class. For each layer of the hierarchical clustering results, the average similarity between all risk vectors within each cluster is calculated and recorded as the degree of similarity corresponding to each cluster. The greater the dispersion of the similarity between different clusters within the same layer, the better the clustering effect. In this embodiment, variance is used to characterize the degree of dispersion. The variance of the similarity corresponding to all clusters within the same layer is used as the degree of dispersion for that layer. The greater the variance, the greater the dispersion, i.e., the better the clustering effect for that layer. The clustering result of the layer with the largest degree of dispersion is used as the final clustering result. Each cluster in the final clustering result is obtained and recorded as a target cluster. Each target cluster is used as a potential risk point, thus obtaining multiple potential risk points. These potential risk points are potential risk points for the current project. The next layer of the final clustering result is used as the risk type corresponding to each target cluster, thus obtaining multiple risk types. The hierarchical clustering algorithm is a state-of-the-art technique and will not be described in detail here.

[0077] In step S3, the occurrence probability of the potential risk point is obtained based on the triggering cause of the risk type of the potential risk point and the total number of risk types; the overall impact weight of the potential risk point on the project is obtained by combining the affected conditions corresponding to the potential risk point in the historical risk information, the overall similarity between the risk vectors in the target cluster where the potential risk point is located, the occurrence probability and the initial cost of the current project; the predicted risk cost of the current project is determined using the affected conditions, occurrence probability and overall impact weight corresponding to all potential risk points.

[0078] Furthermore, the probability of occurrence of each potential risk point is evaluated based on the triggering cause of the risk type of the potential risk point and the number of risk types. The predicted risk cost of the current project is determined by combining the affected conditions corresponding to the potential risk points in the historical risk information, the overall similarity between the risk vectors in the target cluster where the potential risk points are located, and the initial cost of the current project.

[0079] This embodiment will be described below using a potential risk point as an example. Other potential risk points can be processed using the method provided in this embodiment.

[0080] Specifically, for any potential risk point: calculate the inverse of the total number of risk types, and record this inverse as the first occurrence probability. The first occurrence probability is used to characterize the frequency of occurrence of the risk type of the potential risk point; calculate the inverse of the number of triggering causes for the potential risk point, and record this inverse as the second occurrence probability. The second occurrence probability is used to characterize the probability of the potential risk point appearing within the corresponding risk type; and multiply the first and second occurrence probabilities as the occurrence probability of the potential risk point. It should be noted that one potential risk point corresponds to one risk triggering cause, so the number of triggering causes is the number of potential risk points under that risk type.

[0081] For any potential risk point: calculate the average of the impact amounts corresponding to all historical risks of the potential risk point, and record it as the average impact amount; wherein the impact amount is the difference between the final cost of the project and the initial estimated cost; it should be noted that the initial estimated cost is the estimated cost when no risk is considered. The ratio between the average impact amount and the initial cost of the current project is recorded as the first ratio; the normalized result of the product of the similarity corresponding to the potential risk point, the average impact amount and the first ratio is determined as the overall impact weight of the potential risk point on the project. It should be noted that there are many methods for normalizing data. This embodiment adopts the maximum and minimum normalization method to normalize the product of the similarity, the average impact amount and the first ratio. The maximum and minimum normalization method is an existing technology and will not be described in detail here. It should be noted that the initial cost of the current project is determined before the construction of the current project. The initial cost is the risk-free cost, that is, the cost determined when various risks are not considered.

[0082] By using the above method, the overall impact weight of each potential risk point on the project can be obtained.

[0083] After obtaining the overall impact weight of each potential risk point on the project, the risk cost of the current project is predicted by combining the average impact amount, occurrence probability and overall impact weight corresponding to all potential risk points.

[0084] Specifically, for any potential risk point, the product of the average impact amount, the probability of occurrence, and the overall impact weight corresponding to that potential risk point is calculated, and this product is used as the maximum impact value of that potential risk point. Using this method, the maximum impact value of each potential risk point can be obtained, and the cumulative sum of the maximum impact values ​​of all potential risk points is used as the predicted risk cost of the current project.

[0085] So far, this embodiment has determined the predicted risk cost of the current project.

[0086] Step S4: Obtain the predicted cost of the current project based on the initial cost and the predicted risk cost of the current project.

[0087] After determining the predicted risk cost of the current project, the sum of the initial cost of the current project and the predicted risk cost is used as the predicted risk cost of the current project, which completes the cost estimation of the current project.

[0088] This embodiment first divides risk sequences from the same information source into multiple groups based on the similarities between risk sequences in historical risk information during historical construction. Each group is considered an initial risk point. Risk vectors are constructed based on the frequency of occurrence of keywords in the initial risk points. The initial risk points are clustered into multiple target clusters based on the similarities between the risk vectors, and potential risk points are identified. These risk points are potential risk points that may be encountered in the current project. Through grouping and clustering, potential patterns and associations in the data are mined, historical risk information is aggregated, and the accuracy of identifying potential risk points is improved. Furthermore, the risk cost of the current project is predicted based on the triggering cause of the risk type of the potential risk point, the total number of risk types, the impact corresponding to the potential risk point in the historical risk information, and the initial cost of the current project. The predicted cost of the current project is then determined based on the initial cost of the current project. By constructing a risk database for each potential risk point, this embodiment can quickly and accurately output the probability of occurrence of the potential risk point and its impact on the current project by simply matching the project type and content during potential risk analysis, thereby improving the efficiency and accuracy of project cost estimation.

[0089] An embodiment of a system for calculating construction cost:

[0090] See Figure 2 , which shows a structural block diagram of a construction cost estimation system provided by an embodiment of the present invention. The system may include a data acquisition module, a first processing module, a second processing module and a prediction module.

[0091] Among them, the data acquisition module is used to obtain historical risk information during the historical construction process and construct various risk sequences based on the historical risk information;

[0092] The first processing module is used to divide risk sequences under the same information source into several groups based on the similarities between risk sequences; construct risk vectors based on the frequency of occurrence of keywords in the initial risk points; each group is an initial risk point; and cluster the initial risk points based on the similarities between risk vectors to obtain several target clusters, potential risk points, and risk types;

[0093] The second processing module is used to obtain the probability of occurrence of potential risk points based on the triggering cause of the risk type of the potential risk point and the total number of risk types; combine the impact of the potential risk point corresponding to the historical risk information, the overall similarity between the risk vectors in the target cluster where the potential risk point is located, the probability of occurrence, and the initial cost of the current project to obtain the overall impact weight of the potential risk point on the project; and use the impact, probability of occurrence, and overall impact weight corresponding to all potential risk points to determine the predicted risk cost of the current project;

[0094] The prediction module is used to obtain the predicted cost of the current project based on the initial cost and predicted risk cost of the current project.

[0095] It should be understood that Figure 2 The structural block diagram of a construction cost estimation system and its modules shown can be implemented in various ways. For example, in some embodiments, the system and its modules can be implemented using hardware, software, or a combination of software and hardware. The hardware portion can be implemented using dedicated logic, while the software portion can be stored in memory and executed by an appropriate instruction execution system, such as a microprocessor or specially designed hardware. Those skilled in the art will appreciate that the above-described methods and systems can be implemented using computer-executable instructions and / or contained in processor control code, such as provided on a carrier medium such as a disk, CD, or DVD-ROM, a programmable memory such as read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The systems and their modules described herein can be implemented not only using hardware circuits such as very large-scale integrated circuits or gate arrays, semiconductors such as logic chips or transistors, or programmable hardware devices such as field programmable gate arrays or programmable logic devices, but can also be implemented using software executed by various types of processors, or a combination of such hardware circuits and software (e.g., firmware).

[0096] For more details about the above modules, please refer to other places in this manual and will not be repeated here.

[0097] In other embodiments, a device for calculating project cost is provided, comprising a memory and a processor. The memory is used to store executable program code, and the processor is used to retrieve and execute the executable program code from the memory, causing the device to perform the aforementioned method for calculating project cost. The device can be a chip, component, or module. The chip may include a processor and memory connected together. The memory is used to store instructions. When the processor retrieves and executes the instructions, the chip can perform the method for calculating project cost provided in the aforementioned embodiment.

[0098] In other embodiments, a computer program product is also provided. When the computer program product runs on a computer, it enables the computer to execute the above-mentioned related steps to implement a method for calculating the construction cost provided in the above-mentioned embodiment.

[0099] In other embodiments, a computer-readable storage medium is also provided, in which computer program code is stored. When the computer program code is run on a computer, the computer executes the above-mentioned related method steps to implement a method for calculating engineering cost provided in the above-mentioned embodiment.

[0100] Among them, the provided systems, electronic devices, computer program products, and computer-readable storage media are all used to execute the corresponding methods provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding methods provided above, and will not be repeated here.

[0101] It should be noted that the above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for calculating construction cost, characterized in that: The method comprises the following steps: Obtain historical risk information from historical construction processes and construct risk sequences based on this information; Based on the similarities between risk sequences, the risk sequences under the same information source are divided into several groups. Risk vectors are constructed based on the frequency of occurrence of keywords in the initial risk points. Each group is an initial risk point. The initial risk points are clustered based on the similarities between risk vectors to obtain several target clusters, potential risk points, and risk types. Based on the triggering causes of the risk types of potential risk points and the total number of risk types, the probability of occurrence of potential risk points is obtained. The overall impact weight of potential risk points on the project is obtained by combining the impact conditions corresponding to the potential risk points in historical risk information, the overall similarity between risk vectors within the target cluster where the potential risk points are located, the probability of occurrence, and the initial cost of the current project. The predicted risk cost of the current project is determined using the impact conditions, probability of occurrence, and overall impact weight corresponding to all potential risk points. Obtain the predicted cost of the current project based on the initial cost and predicted risk cost of the current project; The similarity between the risk sequences satisfies the following formula: in, represents the similarity between the i-th risk sequence and the j-th risk sequence, represents the number of elements in the ith risk sequence, represents the number of elements in the j-th risk sequence, represents the DTW distance between the i-th risk sequence and the j-th risk sequence, Indicates the absolute value sign, Represents the normalization function.

2. A method for calculating construction cost according to claim 1, characterized in that: According to the similarities between risk sequences, the risk sequences under the same information source are divided into several groups, including: For any source: Obtaining a similarity between the risk sequences under any information source based on a difference in the number of elements and a DTW distance in the risk sequences under any information source, wherein the difference in the number of elements and the DTW distance are negatively correlated with the similarity; A preset number of risk sequences are randomly selected as initial centers, and risk sequences whose similarity to the initial centers is greater than a preset similarity threshold are grouped together.

3. The method for calculating construction cost according to claim 1, wherein: The step of constructing a risk vector based on the frequency of occurrence of keywords in the initial risk point includes: Obtain all keywords within the candidate initial risk points; The vector consisting of all keywords in the candidate initial risk point whose occurrence frequency is greater than the preset frequency threshold is used as the risk vector of the candidate initial risk point; The candidate initial risk point is any initial risk point.

4. The method for calculating construction cost according to claim 1, wherein: The initial risk points are clustered according to the similarities between the risk vectors to obtain several target clusters, potential risk points and risk types, including: A hierarchical clustering algorithm is used to cluster all initial risk points, and the average value of the similarities between all risk vectors in each cluster is used as the similarity level corresponding to each cluster; The layer with the largest degree of discreteness of similarity corresponding to all clusters is taken as the final clustering result, and each target cluster in the final clustering result is obtained, and each target cluster is regarded as a potential risk point; The next layer of the final clustering result is used as the risk type corresponding to each target cluster.

5. The method for calculating construction cost according to claim 1, wherein: Obtaining the probability of occurrence of a potential risk point based on the triggering cause of the risk type of the potential risk point and the total number of risk types includes: For any potential risk point: Determining a first occurrence probability of a risk type of any potential risk point according to the total number of risk types; Determining a second occurrence probability of any potential risk point within the corresponding risk type according to the number of triggering causes of any potential risk point; The first occurrence probability and the second occurrence probability are combined to determine the occurrence probability of any potential risk point.

6. A method for calculating construction cost according to claim 4, characterized in that: The overall impact weight of the potential risk point on the project is obtained by combining the impact of the potential risk point corresponding to the historical risk information, the overall similarity between the risk vectors in the target cluster where the potential risk point is located, the probability of occurrence, and the initial cost of the current project, including: For any potential risk point: Calculate the average impact amount of all historical risks associated with the potential risk point, and record it as the average impact amount; the impact amount is the difference between the final project cost and the initial estimated cost; calculating a first ratio between the average impact amount and the initial cost of the current project; The normalized result of the product of the similarity degree corresponding to any potential risk point, the average impact amount and the first ratio is determined as the overall impact weight of any potential risk point on the project.

7. A method for calculating construction cost according to claim 6, characterized in that: The predicted risk cost of the current project is determined by using the impact conditions, occurrence probability and overall impact weights corresponding to all potential risk points, including: For any potential risk point: the maximum impact value of any potential risk point is obtained by combining the average impact amount corresponding to the potential risk point, the probability of occurrence of the potential risk point, and the overall impact weight of the potential risk point on the project; The cumulative sum of the maximum impact values ​​of all potential risk points is taken as the predicted risk cost of the current project.

8. The method for calculating construction cost according to claim 1, wherein: The method of obtaining the predicted cost of the current project based on the initial cost and predicted risk cost of the current project includes: The sum of the initial cost of the current project and the predicted risk cost is determined as the predicted cost of the current project.

9. A method for calculating construction cost according to claim 4, characterized in that: The obtaining of the discrete degree of the similarity degrees corresponding to all clusters includes: taking the variance of the similarity degrees corresponding to all clusters as the discrete degree.

10. A system for calculating construction cost, characterized in that: The system includes: The data collection module is used to obtain historical risk information during the historical construction process and construct various risk sequences based on the historical risk information; The first processing module is used to divide risk sequences under the same information source into several groups based on the similarities between risk sequences; construct risk vectors based on the frequency of occurrence of keywords in the initial risk points; each group is an initial risk point; and cluster the initial risk points based on the similarities between risk vectors to obtain several target clusters, potential risk points, and risk types; The second processing module is used to obtain the probability of occurrence of potential risk points based on the triggering cause of the risk type of the potential risk point and the total number of risk types; combine the impact of the potential risk point corresponding to the historical risk information, the overall similarity between the risk vectors in the target cluster where the potential risk point is located, the probability of occurrence, and the initial cost of the current project to obtain the overall impact weight of the potential risk point on the project; and use the impact, probability of occurrence, and overall impact weight corresponding to all potential risk points to determine the predicted risk cost of the current project; The prediction module is used to obtain the predicted cost of the current project based on the initial cost and predicted risk cost of the current project; The similarity between the risk sequences satisfies the following formula: in, represents the similarity between the i-th risk sequence and the j-th risk sequence, represents the number of elements in the ith risk sequence, represents the number of elements in the j-th risk sequence, represents the DTW distance between the i-th risk sequence and the j-th risk sequence, Indicates the absolute value sign, Represents the normalization function.

Images