Cost and profit prediction method, device and equipment for construction cost consulting service and medium

Abstract

The application relates to the technical field of order management, in particular to a cost and profit prediction method for construction cost consulting services, which comprises the following steps: constructing a historical engineering database, wherein the historical engineering data comprises structured data of project types, building areas, cost compositions and total construction costs; obtaining new project characteristic parameters, wherein the new project characteristic parameters comprise engineering types, decoration standards, scale parameters and professional compositions, the new project characteristic parameters are split according to the professional compositions, and professional characteristic parameters corresponding to each professional composition are obtained; calculating the similarity between the professional characteristic parameters and historical projects in the historical engineering data, screening matched items, and obtaining to-be-matched historical projects; and generating a cost prediction value and a profit interval evaluation report based on cost elements in actual costs of the to-be-matched historical projects. The application has the effect of improving the accuracy and efficiency of the calculation of the cost and enterprise profit of the engineering construction cost consulting service.

Description

Technical Field

[0001] This application relates to the technical field of order management, and in particular to a method, apparatus, equipment, and storage medium for forecasting the cost and profit of cost consulting services. Background Technology

[0002] In the field of engineering cost consulting services, the assessment of corporate profits and costs is crucial. With the continuous development of the construction industry, engineering projects are becoming increasingly complex, and their characteristics and market fluctuations have a more significant impact on corporate profits and costs. Despite the long history of the construction industry, the technology related to cost and profit forecasting in cost consulting services still needs improvement. While some companies recognize the value of historical project data and have begun to utilize it to support decision-making, the lack of systematic and intelligent analytical methods makes accurate cost and profit assessments still challenging. In typical application scenarios such as cost estimation and profit assessment before undertaking new projects, and dynamic adjustment of cost control strategies in project management, existing technologies are insufficient to meet practical needs.

[0003] Currently, most companies employ two main methods when predicting the costs and profits of engineering cost consulting services. The first relies on the experience and judgment of cost consultants, who subjectively assess the costs and profits of new projects based on their years of experience. The second method supplements this with a rough comparative analysis of a small number of historical projects, simply comparing the new project with some past projects to infer its costs and profits. However, neither of these methods achieves automated matching and quantitative analysis, limiting their efficiency and accuracy in practical applications.

[0004] Existing cost and profit forecasting methods based on personal experience and limited data comparison have significant drawbacks. Over-reliance on experience leads to low standardization, resulting in significant discrepancies in assessments among different consultants, impacting the reliability and consistency of decision-making. Furthermore, the lack of adequate structured processing and intelligent data mining of historical project data limits its potential for data-driven decision-making. Moreover, this approach ignores market fluctuations, such as material price volatility and adjustments to human resource costs, reducing the adaptability and reliability of the forecasting model. In addition, traditional methods are time-consuming and struggle to quickly match highly similar historical cases, affecting decision-making efficiency and accuracy. Summary of the Invention

[0005] In order to improve the accuracy and efficiency of cost and profit calculation for engineering cost consulting services, this application provides a method, apparatus, equipment, and storage medium for predicting the cost and profit of cost consulting services.

[0006] The above-mentioned objective of this application is achieved through the following technical solution: A method for predicting the cost and profit of cost consulting services, the method comprising: Construct a historical engineering database, which includes structured data on project type, building area, cost composition, and total cost; Obtain new project feature parameters, which include project type, decoration standard, scale parameters and professional composition. Decompose the new project feature parameters according to the professional composition to obtain professional feature parameters corresponding to each professional composition. Calculate the similarity between the professional feature parameters and historical projects in the historical engineering data, and filter matching items to obtain the historical projects to be matched; Based on the cost elements in the actual costs of the historical projects to be matched, a cost forecast and profit range assessment report is generated. The cost elements include the quantity of the cost engineering work corresponding to each of the professional characteristic parameters and the completion time of the cost engineering work.

[0007] By adopting the above technical solutions, the accuracy of cost estimation has been improved. Compared with traditional manual experience estimation, the prediction error rate has been reduced, thus improving the accuracy and reliability of cost prediction. An automated data processing and similarity matching process has been designed, reducing the cost assessment work that previously relied on several days of manual work to the hour level, improving work efficiency and enhancing the timeliness of decision-making. The characteristic parameters of new projects are broken down by professional composition, and the similarity matching of each professional characteristic parameter with historical projects is performed. Combined with cost factors such as the number of cost engineers corresponding to each profession and the cost completion time, cost prediction values ​​and profit range assessment reports are generated, making cost and profit predictions more accurate and detailed, closer to the actual situation of the project, and improving the predictive adaptability of projects with different professional compositions.

[0008] In a preferred embodiment, this application can be further configured as follows: calculating the similarity between the feature parameters of the new project and historical projects in the historical engineering data, and filtering matching items to obtain the historical projects to be matched, specifically includes: When the number of historical projects to be matched is lower than a preset threshold, the average direct cost of the target industry is calculated. The average direct cost is corrected using the historical engineering data to obtain the corrected predicted cost.

[0009] By adopting the above technical solution, the prediction problem when historical data is insufficient is solved. When the matched historical data is limited or of low quality, the average direct cost of the target industry is calculated and Bayesian correction is performed using historical engineering data to obtain a more realistic predicted cost, thereby improving the reliability of the prediction.

[0010] In a preferred embodiment, this application can be further configured such that: calculating the similarity between the feature parameters of the new project and historical projects in the historical engineering data specifically includes: The feature weight data of the new project's feature parameters are obtained through the user interface. The similarity calculation parameters are adjusted based on the feature weight data, and the similarity between the target project and the historical engineering data is calculated.

[0011] By adopting the above technical solutions, after constructing a historical project database and obtaining the feature parameters of new projects, feature weight data can be obtained through the user interface and similarity calculation parameters can be adjusted. This allows for more accurate matching of historical data, improves the personalization of cost prediction, meets the refined management needs of different scenarios, and makes cost and profit predictions more closely aligned with the actual operating conditions of enterprises. This achieves more accurate cost estimation, reduces the prediction error rate, and improves the accuracy and reliability of cost prediction.

[0012] In a preferred embodiment, this application can be further configured as follows: adjusting the similarity calculation parameters based on the feature weight data and calculating the similarity between the target project and the historical engineering data specifically includes: The difference in feature vectors between the target project and the historical engineering data is calculated using a weighted Euclidean distance algorithm. Alternatively, the cosine of the angle between the feature vectors of the target project and the historical engineering data can be calculated using a cosine similarity algorithm.

[0013] By adopting the above technical solution, after constructing a historical project database and obtaining the feature parameters of new projects, the similarity calculation parameters are adjusted using the feature weight data obtained from the user interface. The difference between the feature vectors of the target project and the historical project data is calculated by the weighted Euclidean distance algorithm, or the cosine value of the angle between the feature vectors is calculated by the cosine similarity algorithm. This allows for more accurate matching of historical data, improves the personalization level of cost prediction, achieves more accurate cost estimation, reduces the prediction error rate, and improves the accuracy and reliability of cost prediction.

[0014] In a preferred embodiment, this application can be further configured to: generate a cost forecast and profit range assessment report based on the actual cost of the historical project to be matched, combined with real-time updated material price indices, regional adjustment coefficients, and the company's indirect cost ratio, specifically including: Real-time access to building material price indices, regional adjustment coefficients, and labor cost fluctuation parameters; The weight coefficients of the market dynamic factors are dynamically adjusted based on the parameters, and the calculation parameters of the cost prediction model are updated.

[0015] By adopting the above technical solutions, a historical project database is constructed, new project characteristic parameters are obtained, similarity is calculated, and matching items are screened. Combined with the real-time obtained building material price index, regional adjustment coefficient, and labor cost fluctuation parameters, the weight coefficients of market dynamic factors are dynamically adjusted and the calculation parameters of the cost prediction model are updated. This generates cost prediction values ​​and profit range assessment reports, making profit assessments closer to the actual situation, improving the reliability and accuracy of decision-making, and avoiding prediction deviations caused by market fluctuations.

[0016] The second objective of this invention is achieved through the following technical solution: A cost and profit forecasting device for cost consulting services, the device comprising: The database construction module is used to build a historical project database, which includes structured data such as project type, building area, cost composition, and total cost. The project feature extraction module is used to obtain new project feature parameters, which include project type, decoration standard, scale parameters and professional composition. The new project feature parameters are split according to the professional composition to obtain professional feature parameters corresponding to each professional composition. The project matching module is used to calculate the similarity between the professional feature parameters and historical projects in the historical engineering data, and to filter matching items to obtain the historical projects to be matched. The profit analysis module is used to generate a cost forecast and profit range assessment report based on the cost elements in the actual cost of the historical project to be matched. The cost elements include the quantity of the cost engineering project corresponding to each professional characteristic parameter and the completion time of the cost engineering project.

[0017] By adopting the above technical solutions, the accuracy of cost estimation has been improved. Compared with traditional manual experience estimation, the prediction error rate has been reduced, thus improving the accuracy and reliability of cost prediction. An automated data processing and similarity matching process has been designed, reducing the cost assessment work that previously relied on several days of manual work to the hour level, improving work efficiency and enhancing the timeliness of decision-making. The profit model is adjusted by combining market dynamic factors and introducing real-time changing parameters, making the profit assessment closer to the actual situation, improving the reliability and accuracy of decision-making, and avoiding prediction deviations caused by market fluctuations. Continuous iteration and optimization of the historical database ensures the stability and efficiency of the cost prediction model, adapting it to various types of engineering projects and enhancing the model's adaptability and prediction accuracy.

[0018] The above-mentioned objective three of this application is achieved through the following technical solution: A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-described method for predicting the cost and profit of cost consulting services.

[0019] The fourth objective of this application is achieved through the following technical solution: A computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described method for predicting the cost and profit of cost consulting services.

[0020] In summary, this application includes at least one of the following beneficial technical effects: 1. By employing an intelligent matching algorithm based on historical data, systematically analyzing and utilizing historical engineering data, the cost estimation is made more accurate, the prediction error rate is reduced, and the accuracy and reliability of cost prediction are improved; 2. The innovative design of automated data processing and similarity matching processes improves work efficiency, enabling enterprises to obtain preliminary cost forecasts for new projects in a shorter time and enhancing the timeliness of decision-making; 3. Adjust the profit model by incorporating dynamic market factors and introducing real-time changing parameters to make profit assessment more closely reflect reality, improve the reliability and accuracy of decision-making, and avoid prediction deviations caused by market fluctuations. Attached Figure Description

[0021] Figure 1 This is a flowchart of a method for predicting the cost and profit of cost consulting services in one embodiment of this application; Figure 2 This is a schematic diagram of a cost and profit forecasting system for cost consulting services according to one embodiment of this application; Figure 3 This is a schematic diagram of a device according to one embodiment of this application. Detailed Implementation

[0022] The present application will be further described in detail below with reference to the accompanying drawings.

[0023] In one embodiment, such as Figure 1 As shown, this application discloses a method for predicting the cost and profit of cost consulting services, which specifically includes the following steps: S10: Construct a historical project database, which includes structured data on project type, building area, cost composition, and total cost.

[0024] Specifically, after collecting the raw data, it needs to be cleaned and normalized. Data cleaning aims to remove erroneous, duplicate, and incomplete data. Erroneous data may be due to entry errors or measurement mistakes; if left untreated, it will affect subsequent analysis and prediction results. Duplicate data increases database redundancy and reduces data processing efficiency. Incomplete data may lead to missing information, affecting a comprehensive understanding of the project. Normalization unifies data from different sources and in different formats into a standard format, making the data comparable. For example, building area data expressed in different units needs to be converted to the same unit for accurate subsequent analysis and comparison.

[0025] After cleaning and normalization, the data is structured and stored according to dimensions such as project type, building area, cost composition, and total cost. Project type can be classified according to the nature and purpose of the project, such as residential, commercial, and industrial buildings. Building area is an important indicator for measuring the scale of a project; accurately recording the building area helps in analyzing the costs and profits of projects of different sizes. Cost composition includes direct costs such as labor costs and material costs, and indirect costs such as management fees and taxes. Total cost is the final expenditure of the entire project, which is a comprehensive reflection of costs and profits. Structured storage facilitates subsequent data querying, analysis, and use.

[0026] S20: Obtain new project feature parameters, which include project type, decoration standard, scale parameters and professional composition. Decompose the new project feature parameters according to the professional composition to obtain professional feature parameters corresponding to each professional composition.

[0027] Specifically, when acquiring the characteristic parameters of a new project, information is obtained from relevant documents such as the project's brief and tender documents. For the project type, it is accurately classified according to its nature and purpose, such as commercial buildings, residential buildings, and industrial buildings. The decoration standards are evaluated based on the project's design requirements and expected effects, and are categorized into different levels such as simple decoration, medium decoration, and luxury decoration. Scale parameters are mainly determined based on indicators such as building area, number of floors, and land area. The professional composition involves a detailed analysis of the various professional fields involved in the project, such as architecture, structural engineering, electrical engineering, and water supply and drainage. After acquiring these characteristic parameters, they are broken down according to the professional composition. For example, for a comprehensive commercial building project, it is broken down into architectural characteristic parameters, electrical characteristic parameters, etc. Architectural characteristic parameters are further refined into specific details such as wall structure and roof form; electrical characteristic parameters include aspects such as power load and lighting systems. This breakdown allows for more precise analysis and matching of each professional field.

[0028] S30: Calculate the similarity between the professional feature parameters and historical projects in the historical engineering data, and filter matching items to obtain the historical projects to be matched.

[0029] Specifically, a scientific algorithm is used to calculate the similarity between professional feature parameters and historical projects in historical engineering data. First, feature vectors are extracted from both the professional feature parameters and historical projects; these feature vectors contain numerical information for each feature. Then, a weighted Euclidean distance algorithm or a cosine similarity algorithm is used to calculate the similarity between the two. The weighted Euclidean distance algorithm considers the weight of each feature, assigning higher weights to features that have a greater impact on cost and profit. For example, when calculating the similarity of construction projects, the weights of building area and decoration standards may be relatively high. By calculating the distance between the professional feature parameters and the feature vectors of historical projects, a smaller distance indicates a higher similarity. For example, feature parameters that have a greater impact on cost, such as building area and material costs, can be assigned higher weights; while feature parameters that have a smaller impact on cost can be assigned lower weights.

[0030] Cosine similarity algorithm measures similarity by calculating the cosine of the angle between two vectors; the closer the cosine is to 1, the higher the similarity. This algorithm is suitable for processing high-dimensional data and can more accurately reflect the similarity between data. After calculating the similarity, the most matching historical items are selected as potential historical items for matching based on a set similarity threshold. The similarity threshold needs to be adjusted according to the actual situation. If the threshold is set too high, it may result in too few historical items being selected for matching, failing to provide sufficient reference information; if the threshold is set too low, it may select some historical items with low similarity, affecting the accuracy of the prediction.

[0031] S40: Based on the cost elements in the actual cost of the historical project to be matched, generate a cost forecast and profit range assessment report, wherein the cost elements include the quantity of the cost engineering project corresponding to each of the professional characteristic parameters and the cost completion time.

[0032] Specifically, cost forecasts and profit range assessment reports are generated based on cost elements from the actual costs of the historical projects to be matched. Cost elements include the quantity of cost-related works and the completion time for each professional characteristic parameter. The quantity of cost-related works is precisely calculated based on the professional characteristic parameters. For example, in electrical engineering, the length of cables laid and the number of distribution boxes are counted. The completion time is comprehensively assessed by combining the actual construction period of historical projects and the progress requirements of the current project. When generating cost forecasts, adjustments are made based on the actual costs of the historical projects to be matched, combined with dynamic factors of the current market. Market dynamic factors include material price indices and regional adjustment coefficients. If current market material prices rise, the cost forecast will be increased accordingly. Simultaneously, the company's indirect cost ratio is considered and incorporated into the cost forecast calculation. When generating the profit range assessment report, profits are calculated based on the cost forecasts and the project's expected revenue. Expected revenue is estimated based on factors such as project scale and market conditions. By calculating profit values ​​under different scenarios, a reasonable profit range is determined. For example, considering market uncertainties, profit values ​​under optimistic, normal, and pessimistic scenarios are calculated, providing enterprises with a comprehensive profit assessment reference. The resulting cost forecasts and profit range assessment reports provide accurate decision-making basis for enterprises in cost consulting services, helping them better control costs, assess profits, and improve their economic efficiency and competitiveness. Moreover, with the continuous updating and improvement of historical project databases and the ongoing optimization of algorithms, the accuracy and reliability of this cost and profit forecasting method will continuously improve, better adapting to market changes and the development needs of enterprises. In practical applications, this method can be used for effective cost and profit forecasting for different types of projects, such as large public building projects and small residential projects, providing strong support for enterprise decision-making in different scenarios. Simultaneously, this method can promote the effective utilization of historical project data, uncover the potential value behind the data, and drive innovation and development in the field of cost consulting services. It helps enterprises break away from traditional cost and profit forecasting methods that rely on personal experience, achieving standardized and intelligent forecasting, and improving operational efficiency and management level. Furthermore, a detailed analysis and consideration of cost elements allows for a more accurate grasp of a project's cost structure and profit sources, providing a basis for enterprises to formulate reasonable pricing strategies and cost control measures. In an increasingly competitive market environment, this accurate cost and profit forecasting method enables enterprises to gain an advantage in project bidding and cost management, enhancing their market competitiveness and sustainable development capabilities. Moreover, with continuous technological advancements and data accumulation, this method has significant room for improvement and expansion, and can be further integrated with technologies such as artificial intelligence and big data analytics to achieve even more accurate and efficient cost and profit forecasting.

[0033] In one embodiment, step S30, which involves calculating the similarity between the professional feature parameters and historical projects in the historical engineering data, and filtering matching items to obtain the historical projects to be matched, specifically includes: S31: When the number of historical projects to be matched is lower than a preset threshold, calculate the average direct cost of the target industry.

[0034] Specifically, the system calculates the average direct cost of the target industry. In practice, the system collects data from a large number of relevant projects within the target industry. These data come from various sources, including statistical information released by industry associations, publicly available market research reports, and some project data accumulated by the companies themselves. After collection, the data undergoes rigorous screening and processing to remove outliers and inaccurate data, ensuring data quality. Next, the data is categorized according to certain classification criteria, such as by project type or size. For each category of data, the system uses an appropriate statistical method to calculate the average direct cost. Commonly used statistical methods include the arithmetic mean and the weighted average. The arithmetic mean is simple and direct; it adds up all the direct costs in that category and then divides by the number of projects to obtain the average direct cost. The weighted average, on the other hand, assigns different weights to each project based on its importance or representativeness, and then calculates a weighted average direct cost, thus more accurately reflecting the actual situation of the industry.

[0035] S32: Correct the average direct cost using historical engineering data to obtain the corrected predicted cost.

[0036] Specifically, the average direct cost is corrected using historical engineering data. The system performs in-depth mining and analysis of historical engineering data to extract key information relevant to the current new project, such as the project's specific characteristics and cost composition ratios. Using Bayesian statistical methods, combined with existing limited historical data and prior knowledge, the average direct cost is corrected. The core of the Bayesian method is to update the prior probability (i.e., average direct cost) based on new evidence (i.e., historical engineering data), thereby obtaining the posterior probability, which is the corrected predicted cost. In this process, the system reasonably determines the prior distribution and likelihood function based on the characteristics and distribution of historical data. The prior distribution reflects the cost estimate in the absence of new evidence, while the likelihood function describes the relationship between new evidence and different cost assumptions. Through continuous iteration and optimization, the corrected predicted cost becomes closer to reality.

[0037] Furthermore, this method yields more accurate cost forecasts that better reflect reality. The revised cost forecast comprehensively considers the average level of the target industry and the characteristics of historical engineering data, avoiding biases caused by relying solely on average costs or limited historical data. Compared to traditional methods, this approach more accurately reflects the actual cost of new projects. In practical applications, for some emerging fields or special types of projects, traditional cost forecasting methods often struggle to provide accurate results due to limited historical data. This revised method, however, utilizes existing historical data and industry average information to provide more reliable cost forecasts, helping companies make more informed decisions. Simultaneously, as historical engineering data accumulates and is updated, the revised cost forecast becomes even more precise, further improving the accuracy and reliability of cost forecasting and providing strong support for cost control and profit assessment.

[0038] In one embodiment, step S30, which calculates the similarity between the professional feature parameters and historical projects in the historical engineering data, specifically includes: S33: Obtain feature weight data of new project feature parameters through the user interface.

[0039] Specifically, when a user opens the interactive interface, the system will provide a default set of initial feature weight data. This data is based on a large amount of historical project data and industry experience, and has certain reference value. However, users can modify it according to the specific circumstances of a project. For example, for a project with extremely high requirements for decoration standards, users can increase the weight of the decoration standard feature parameter using the slider or input box, while appropriately decreasing the weight of other feature parameters. During the adjustment process, the interface will display the adjusted weight values ​​in real time, allowing users to clearly understand the results of their operations. At the same time, to avoid user errors or unreasonable weight settings, the system will perform a validity check on the input weight data. If the weight data entered by the user exceeds the reasonable range, the system will pop up a prompt box reminding the user to re-enter it, ensuring the accuracy and validity of the weight data.

[0040] S34: Adjust the similarity calculation parameters based on feature weight data, and calculate the similarity between the target project and historical engineering data.

[0041] Furthermore, the similarity calculation parameters are adjusted based on the acquired feature weight data. The system incorporates feature weight data into the calculation process according to different similarity calculation algorithms. Taking the weighted Euclidean distance algorithm as an example, this algorithm is used to calculate the feature vector difference between the target project and historical engineering data. In traditional Euclidean distance calculation, each feature parameter has the same weight, but in this technical solution, each feature parameter is weighted according to the feature weight data input by the user. Specifically, the system multiplies the value of each feature parameter by its corresponding weight, and then performs calculations such as square and square root. In this way, feature parameters with higher weights will have a larger proportion in the calculation, thus better reflecting the impact of that feature parameter on project similarity.

[0042] The cosine similarity algorithm also adjusts based on feature weight data. It measures similarity by calculating the cosine of the angle between the feature vectors of the target project and historical project data. During the calculation, the value of each feature parameter is multiplied by its corresponding weight, followed by vector dot product and modulus calculations. This approach more accurately reflects the contribution of different feature parameters to project similarity.

[0043] After adjusting the similarity calculation parameters, the system calculates the similarity between the target project and historical project data. The system iterates through each historical project in the historical project database, calculating the similarity between the target project's feature vector and the feature vectors of the historical projects. After calculation, the system sorts the historical projects according to their similarity scores, selecting those with higher similarity as potential matching projects. These potential matching projects will serve as important references for subsequent cost prediction and profit assessment.

[0044] This approach enables more accurate matching of historical data, enhancing the personalization of cost forecasting. Different projects have different characteristics and needs; by allowing users to customize feature weights, cost and profit forecasts can be more closely aligned with the company's actual operational status. For certain special types of projects, such as large commercial complexes, users can adjust the weights of different feature parameters based on the project's priorities and concerns, resulting in more realistic cost and profit forecasts. This personalized forecasting capability meets the refined management needs of different scenarios, enabling companies to make more accurate and reliable project decisions. Simultaneously, this similarity calculation method based on user interaction and feature weight adjustment also improves the accuracy and reliability of forecasts, avoiding the prediction bias caused by fixed weights in traditional methods, and providing more effective support for companies' project cost and profit forecasting.

[0045] In one embodiment, step S34, which involves adjusting the similarity calculation parameters based on the feature weight data and calculating the similarity between the target project and historical engineering data, specifically includes: S341: Calculate the feature vector difference between the target project and historical engineering data using a weighted Euclidean distance algorithm.

[0046] Specifically, the first step in using this algorithm is to extract feature vectors. Feature vectors for each historical project are extracted from the historical project database. These feature vectors contain structured data such as project type, building area, cost composition, and total cost. Simultaneously, corresponding feature vectors are extracted from new projects, such as project type, decoration standards, scale parameters, and professional composition. This step is like creating a unique "portrait" for each project, and these feature vectors are the key elements of that "portrait."

[0047] Further, the corresponding weights are determined. Different features have varying degrees of impact on project similarity. For example, in some cases, building area may have a greater impact on cost and profit, thus requiring a higher weight to this feature. Through the user interface, users can customize the weights of these features according to specific project needs. This step is akin to assigning different levels of importance to each element on a "portrait."

[0048] Then, a weighted calculation is performed. For each feature, its value is multiplied by its corresponding weight. The purpose of this is to highlight the influence of important features and weaken the influence of unimportant features. For example, if the weight of building area is 0.6 and the weight of decoration standard is 0.3, then the difference in building area will have a greater impact on the final result when calculating similarity.

[0049] Next, the eigenvector differences are calculated. The weighted eigenvectors are then interpolated to obtain the difference value for each feature. These difference values ​​are then squared, summed, and the square root is taken to obtain the weighted Euclidean distance between the target project and historical project data. The smaller this distance value, the more similar the target project is to the historical projects.

[0050] S342: Alternatively, calculate the cosine of the angle between the feature vectors of the target project and the historical engineering data using the cosine similarity algorithm.

[0051] Specifically, a cosine similarity algorithm can also be used. Similarly, the first step is to extract feature vectors from both historical project data and the new project. Then, the vector dot product is calculated. The feature vector of the target project is multiplied by the feature vector of the historical project data. The result of the dot product reflects the similarity of the two vectors in direction. The closer the directions of the two vectors are, the larger the value of the dot product. Next, the vector magnitudes are calculated. The magnitudes of the feature vectors of the target project and the historical project data are calculated separately. The magnitude of a vector represents its length, reflecting its size. Finally, the cosine of the angle between the two vectors is calculated. Dividing the result of the dot product by the product of the magnitudes of the two vectors yields the cosine of the angle between the feature vectors of the target project and the historical project data. The closer the cosine value is to 1, the closer the directions of the two vectors are, meaning the target project is more similar to the historical project.

[0052] These two algorithms allow for more precise filtering of historical projects that best match the target project. In practical applications, when historical data is abundant and feature distribution is relatively uniform, the weighted Euclidean distance algorithm better considers the weights and numerical differences of features, thus more accurately reflecting the similarity between projects. When focusing more on the directional similarity of feature vectors, the cosine similarity algorithm is more suitable. The combined use of these two algorithms provides a more scientific and accurate basis for cost and profit forecasting in cost consulting services, making the forecast results closer to reality. This effectively improves the accuracy and reliability of cost forecasting, while also enhancing the timeliness and effectiveness of decision-making. It allows companies to obtain preliminary cost forecasts for new projects in a shorter time, better responding to market changes and project needs.

[0053] In one embodiment, in step S40, a cost forecast and profit range assessment report is generated based on the cost elements in the actual cost of the historical project to be matched. The cost elements include the quantity and completion time of the engineering work corresponding to each professional characteristic parameter, specifically including: S41: Real-time acquisition of building material price index, regional adjustment coefficient and labor cost fluctuation parameters.

[0054] Specifically, in obtaining real-time building material price indices, data can be collected through multiple channels. Firstly, partnerships can be established with authoritative building material industry data platforms. These platforms typically update price information for various building materials regularly, covering different brands and specifications. Through interface integration, automatic data acquisition and real-time synchronization can be achieved. Secondly, dedicated personnel can conduct on-site surveys of local building material markets to understand actual price fluctuations. Survey personnel can visit major building material markets and dealers, recording price changes over different time periods. Furthermore, attention can be paid to building material price reports released by industry associations, which are often highly authoritative and accurate. Simultaneously, web scraping technology can be used to capture and analyze price data from major building material e-commerce platforms to obtain broader market price information. By collecting and integrating data from multiple channels, a comprehensive and accurate building material price index can be obtained.

[0055] S42: Based on the parameters, dynamically adjust the weight coefficients of market dynamic factors and update the calculation parameters of the cost prediction model.

[0056] Specifically, obtaining the regional adjustment coefficient requires considering factors such as the economic development level, price level, and geographical environment of different regions. Regional economic data released by the National Bureau of Statistics, such as regional GDP and the Consumer Price Index, can be referenced to determine the economic differences between regions. Simultaneously, the impact of local construction industry market conditions, such as local construction costs and labor costs, on project costs should be understood. Communication with local construction industry associations and relevant government departments is essential to obtain their suggestions and guidance on the regional adjustment coefficient. Furthermore, analyzing historical project cost data in different regions can identify patterns in the impact of regional differences on project costs, thereby determining a reasonable regional adjustment coefficient.

[0057] Obtaining parameters for labor cost fluctuations requires monitoring the dynamic changes in the labor market. Collaborating with relevant human resources agencies allows for the acquisition of information on labor supply and demand, wage levels, and other relevant data. Regularly collecting local construction worker wage data, including wages for different job types and skill levels, is crucial. Simultaneously, monitoring national and local government labor policies and minimum wage standards is essential, as policy changes directly impact labor costs. Furthermore, surveys and interviews can be used to understand construction companies' expectations and actual payments regarding labor costs. Additionally, analyzing historical labor cost data within the industry can identify patterns of fluctuation and provide a reference for predicting future labor costs.

[0058] To dynamically adjust the weighting coefficients of market dynamic factors based on the aforementioned parameters, a scientific weighting adjustment model needs to be established. First, a quantitative analysis should be conducted on the building material price index, regional adjustment coefficient, and labor cost fluctuation parameters to determine their relative importance within the market dynamic factors. Methods such as the analytic hierarchy process (AHP) can be used to evaluate and determine the weights of each parameter. Then, the weighting coefficients should be dynamically adjusted based on real-time parameter changes. For example, when the building material price index fluctuates significantly, its weight in the market dynamic factors should be appropriately increased; when the regional adjustment coefficient changes significantly, its weight should be adjusted accordingly. Simultaneously, the interrelationships between the parameters should be considered to avoid unreasonable weight allocation. When adjusting the weighting coefficients, verification and optimization should be conducted using historical data and actual project conditions to ensure the rationality and accuracy of the weighting coefficients.

[0059] Updating the calculation parameters of the cost prediction model is a crucial step in ensuring prediction accuracy. After obtaining real-time parameters and adjusting weighting coefficients, this information needs to be promptly updated into the cost prediction model. First, the cost prediction model should be retrained and optimized, using the newly acquired data to adjust the model's parameters. Machine learning algorithms, such as neural networks and decision trees, can be used to train the model and improve its predictive capabilities. Then, the updated model should be validated and tested by comparing it with actual project cost data to evaluate its accuracy and reliability. If deviations are found, the model should be adjusted and improved promptly. Simultaneously, a model update mechanism should be established to regularly update and maintain the model, ensuring it adapts to market changes and project needs.

[0060] Through the above series of operations, it is possible to obtain building material price indices, regional adjustment coefficients, and labor cost fluctuation parameters in real time. Based on these parameters, the weight coefficients of market dynamic factors are dynamically adjusted, and the calculation parameters of the cost prediction model are updated, thereby making the cost and profit prediction of cost consulting services more accurate and reliable, and providing strong support for enterprise decision-making.

[0061] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0062] In one embodiment, a cost and profit forecasting device for cost consulting services is provided, which corresponds one-to-one with the cost and profit forecasting methods for cost consulting services described in the above embodiments. For example... Figure 2 As shown, this cost and profit forecasting device for cost consulting services includes a database construction module, a project feature extraction module, a project matching module, and a profit analysis module. Detailed descriptions of each functional module are as follows: The database construction module is used to build a historical project database, which includes structured data such as project type, building area, cost composition, and total cost. The project feature extraction module is used to obtain the feature parameters of the new project. The feature parameters of the new project include the project type, decoration standard, scale parameters and professional composition. The feature parameters of the new project are broken down according to the professional composition to obtain the professional feature parameters corresponding to each professional composition. The project matching module is used to calculate the similarity between professional feature parameters and historical projects in historical engineering data, and to filter matching items to obtain historical projects to be matched. The profit analysis module is used to generate cost forecasts and profit range assessment reports based on cost elements in the actual costs of historical projects to be matched. The cost elements include the quantity of cost engineering works corresponding to each professional characteristic parameter and the completion time of the cost engineering works.

[0063] Optionally, the project matching module includes: The cost calculation sub-module is used to calculate the average direct cost of the target industry when the number of historical projects to be matched is lower than a preset threshold. The cost correction submodule is used to correct the average direct cost using historical engineering data to obtain the corrected predicted cost.

[0064] Optionally, the project matching module includes: The weight acquisition submodule is used to obtain feature weight data of new project feature parameters through the user interface. The similarity calculation submodule is used to adjust the similarity calculation parameters based on feature weight data and calculate the similarity between the target project and historical engineering data.

[0065] Optionally, the similarity calculation submodule includes: The first calculation unit is used to calculate the feature vector difference between the target project and historical engineering data using a weighted Euclidean distance algorithm. Alternatively, the second calculation unit is used to calculate the cosine value of the angle between the feature vectors of the target project and the historical engineering data using a cosine similarity algorithm.

[0066] Optional, the profit analysis module includes: The fluctuation data acquisition submodule is used to acquire building material price index, regional adjustment coefficient and labor cost fluctuation parameters in real time; The model update submodule is used to dynamically adjust the weight coefficients of market dynamic factors based on parameters and update the calculation parameters of the cost prediction model.

[0067] Specific limitations regarding the cost and profit forecasting device for cost consulting services can be found in the limitations on cost and profit forecasting methods for cost consulting services mentioned above, and will not be repeated here. Each module in the aforementioned cost and profit forecasting device for cost consulting services can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0068] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 3 As shown, the computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and database. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The network interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a method for cost and profit forecasting in cost consulting services.

[0069] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to perform the following steps: Construct a historical engineering database, which includes structured data on project type, building area, cost composition, and total cost. Obtain the characteristic parameters of the new project, which include project type, decoration standards, scale parameters, and professional composition; Calculate the similarity between the feature parameters of the new project and the historical projects in the historical engineering data, and filter the matching items to obtain the historical projects to be matched; Based on the actual costs of the historical projects to be matched, combined with real-time updated material price indices, regional adjustment coefficients, and the company's indirect cost ratios, a cost forecast and profit range assessment report is generated.

[0070] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor: Construct a historical engineering database, which includes structured data on project type, building area, cost composition, and total cost. Obtain the characteristic parameters of the new project, which include project type, decoration standards, scale parameters, and professional composition; Calculate the similarity between the feature parameters of the new project and the historical projects in the historical engineering data, and filter the matching items to obtain the historical projects to be matched; Based on the actual costs of the historical projects to be matched, combined with real-time updated material price indices, regional adjustment coefficients, and the company's indirect cost ratios, a cost forecast and profit range assessment report is generated.

[0071] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0072] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is used as an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0073] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for predicting the cost and profit of cost consulting services, characterized in that, The methods for predicting the cost and profit of the cost consulting service include: Construct a historical engineering database, which includes structured data on project type, building area, cost composition, and total cost; Obtain new project feature parameters, which include project type, decoration standard, scale parameters and professional composition. Decompose the new project feature parameters according to the professional composition to obtain professional feature parameters corresponding to each professional composition. Calculate the similarity between the professional feature parameters and historical projects in the historical engineering data, and filter matching items to obtain the historical projects to be matched; Based on the cost elements in the actual costs of the historical projects to be matched, a cost forecast and profit range assessment report is generated. The cost elements include the quantity of the cost engineering work corresponding to each of the professional characteristic parameters and the completion time of the cost engineering work.

2. The method for cost and profit forecasting in cost consulting services according to claim 1, characterized in that, The calculation of the similarity between the professional feature parameters and historical projects in the historical engineering data, and the filtering of matching items to obtain the historical projects to be matched, specifically includes: When the number of historical projects to be matched is lower than a preset threshold, the average direct cost of the target industry is calculated. The average direct cost is corrected using the historical engineering data to obtain the corrected predicted cost.

3. The method for predicting costs and profits in cost consulting services according to claim 1, characterized in that, The calculation of the similarity between the professional feature parameters and historical projects in the historical engineering data specifically includes: The feature weight data of the new project's feature parameters are obtained through the user interface. The similarity calculation parameters are adjusted based on the feature weight data, and the similarity between the target project and the historical engineering data is calculated.

4. The method for predicting costs and profits in cost consulting services according to claim 3, characterized in that, The step of adjusting the similarity calculation parameters based on the feature weight data and calculating the similarity between the target project and the historical engineering data specifically includes: The difference in feature vectors between the target project and the historical engineering data is calculated using a weighted Euclidean distance algorithm. Alternatively, the cosine of the angle between the feature vectors of the target project and the historical engineering data can be calculated using a cosine similarity algorithm.

5. The method for cost and profit forecasting in cost consulting services according to claim 1, characterized in that, The process generates a cost forecast and profit range assessment report based on the cost elements in the actual costs of the historical projects to be matched. The cost elements include the quantity and completion time of the engineering work corresponding to each professional characteristic parameter, specifically including: Real-time acquisition of labor cost fluctuation parameters; The weight coefficients of the market dynamic factors are dynamically adjusted based on the parameters, and the calculation parameters of the cost prediction model are updated.

6. A cost and profit forecasting device for cost consulting services, characterized in that, The cost and profit forecasting device for cost consulting services includes: The database construction module is used to build a historical project database, which includes structured data such as project type, building area, cost composition, and total cost. The project feature extraction module is used to obtain new project feature parameters, which include project type, decoration standard, scale parameters and professional composition. The new project feature parameters are split according to the professional composition to obtain professional feature parameters corresponding to each professional composition. The project matching module is used to calculate the similarity between the professional feature parameters and historical projects in the historical engineering data, and to filter matching items to obtain the historical projects to be matched. The profit analysis module is used to generate a cost forecast and profit range assessment report based on the cost elements in the actual cost of the historical project to be matched. The cost elements include the quantity of the cost engineering project corresponding to each professional characteristic parameter and the completion time of the cost engineering project.

7. The cost and profit forecasting device for cost consulting services according to claim 6, characterized in that, The project matching module includes: The cost calculation submodule is used to calculate the average direct cost of the target industry when the number of historical projects to be matched is lower than a preset threshold. The cost correction submodule is used to correct the average direct cost using the historical engineering data to obtain the corrected predicted cost.

8. The cost and profit forecasting device for cost consulting services according to claim 6, characterized in that, The project matching module includes: The weight acquisition submodule is used to acquire the feature weight data of the feature parameters of the new project through the user interface. The similarity calculation submodule is used to adjust the similarity calculation parameters based on the feature weight data and calculate the similarity between the target project and the historical engineering data.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the cost and profit forecasting method for cost consulting services as described in any one of claims 1 to 5.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the cost and profit forecasting method for cost consulting services as described in any one of claims 1 to 5.

Images