Artificial intelligence service platform

Abstract

The invention discloses an artificial intelligence service platform, which relates to the technical field of information technology and is characterized in that a data storage and extraction module is utilized to receive basic information data of a project and a task from the service platform, and a data processing module is utilized to process the basic information data according to the time appointed by the project and the output completion time of the project. Based on feedback adjustment, project cost, efficiency and feedback adjustment are estimated again, a user interaction module is utilized to provide an interface for a user to input data and check a result, and a data storage and extraction module is utilized to store cyclically fed back data and results. According to the method, accurate estimation, multi-dimensional efficiency evaluation and dynamic feedback adjustment of the project cost are realized, the optimization and innovation not only solve the problems and defects in the prior art, but also improve the efficiency and accuracy of project management, and provide powerful support for sustainable development of enterprises.

Description

Technical Field

[0001] The present invention relates to the field of information technology, and in particular to an artificial intelligence service platform. Background Art

[0002] Machine learning is one of the core driving forces of artificial intelligence. In artificial intelligence service platforms, machine learning technology is used to process and analyze massive amounts of data to discover patterns, predict trends and make decisions. Machine learning algorithms can automatically learn from data and optimize their own performance without the need to manually write complex rules. This autonomous learning ability enables artificial intelligence service platforms to cope with complex and changing scenarios and provide more accurate and personalized services. When building an artificial intelligence service platform, the core technical challenge lies in how to accurately estimate project costs, evaluate service efficiency, and dynamically adjust based on actual performance to optimize resource allocation.

[0003] Traditional cost estimation methods often rely on experience and static data, which makes it difficult to accurately reflect the changes in risks that may occur during project execution, leading to cost overruns and waste of resources. Many existing systems can only provide simple efficiency evaluations, such as completion rate and time utilization rate, but ignore the differentiated impact of different situations, such as early or delayed, on efficiency evaluation, and cannot fully reflect the actual situation of project execution. In addition, the lack of an effective dynamic feedback mechanism makes it difficult for project managers to obtain efficiency evaluation results in a timely manner and make adjustments accordingly, resulting in delayed decision-making and cost out of control. In the adjustment of fixed costs, existing technologies often adopt fixed adjustment ratios and strategies, which cannot be flexibly adjusted according to the actual situation of the project, affecting the refinement and efficiency of cost management. Summary of the invention

[0004] The purpose of the present invention is to provide an artificial intelligence service platform that solves the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solution, and the specific implementation steps are as follows:

[0006] Step S1, using the data storage and extraction module to receive basic information data of projects and tasks from the service platform;

[0007] Step S2-1, using the data processing module, and according to the agreed time of the project and the time of project completion output, make targeted efficiency and feedback adjustments and substitute them into the calculation;

[0008] Step S2-2, based on feedback adjustment, re-estimate project cost, efficiency and feedback adjustment;

[0009] Step S3, using the user interaction module to provide an interface for the user to input data and view results;

[0010] Step S4, using a data storage and extraction module to store the data and results of the loop feedback;

[0011] in;

[0012] The data processing module includes a total cost estimation unit, a project execution efficiency evaluation unit and a feedback adjustment unit;

[0013] The devices used by the data storage and retrieval module include network devices and storage devices;

[0014] The equipment used by the data processing module includes a server;

[0015] The devices used in the user interaction module include computers and smart devices.

[0016] Optionally, the calculation formula of the total cost estimation unit is as follows:

[0017] ZC = CC × (1 + F / 100) × GC;

[0018] in:

[0019] ZC is the cost estimate;

[0020] CC is the material cost, CC is directly used for the material expenses of projects and tasks;

[0021] The calculation of F / 100 converts the percentage into a decimal and multiplies it by the material cost CC to obtain the additional material cost due to the increased risk;

[0022] F is the risk factor;

[0023] GC is fixed cost. GC reflects the costs that do not change with the project scale and material cost CC, including rent and wages.

[0024] Optionally, the calculation formula for the evaluation project execution efficiency unit is as follows:

[0025] X1=P1 / (ZC+a×CC);

[0026] X2=[P2×(1+δ)] / (ZC+b×CC);

[0027] X3=[P3×(1-ε)] / (ZC+c×CC);

[0028] in:

[0029] X1 is the efficiency evaluation value within the agreed time;

[0030] X2 is the efficiency evaluation value before the agreed time;

[0031] X3 is the efficiency evaluation value after the agreed time;

[0032] X1, X2 and X3 represent the efficiency evaluation within the agreed time, in advance and in delay of the project respectively;

[0033] P1 is the output within the agreed time;

[0034] P2 is the output before the agreed time;

[0035] P3 is the output after the agreed time;

[0036] P1, P2 and P3 represent the output within the agreed time of the project, in advance and in delay respectively;

[0037] a, b and c are all sensitivity coefficients, and they represent the degree of cost sensitivity within the agreed time, in advance and in delay of the project respectively;

[0038] δ is the reward coefficient, which is used to adjust the efficiency improvement brought by early completion;

[0039] ε is the penalty coefficient, which is used to adjust the efficiency reduction caused by delayed completion.

[0040] Optionally, the sensitivity coefficient a reflects the sensitivity of the cost to the output when the project is carried out completely according to the plan, and is a base coefficient;

[0041] A higher sensitivity coefficient b indicates that the project places great emphasis on time efficiency, while a lower sensitivity coefficient b indicates that the project has extremely high requirements for quality;

[0042] A higher sensitivity coefficient c reflects the negative impact of delayed completion on project costs, including additional overtime expenses, customer dissatisfaction, fines and opportunity costs.

[0043] Optionally, the calculation formula of the feedback adjustment unit is as follows:

[0044] FK1=β 1 ×(1-X1)×ZC;

[0045] FK2=β 2 ×(X2-1)×ZC;

[0046] FK3=β 3 ×(1-X3)×ZC;

[0047] in:

[0048] FK1 is the feedback adjustment value within the agreed time;

[0049] FK2 is the feedback adjustment value before the agreed time;

[0050] FK3 is the feedback adjustment value after the agreed time;

[0051] FK1, FK2 and FK3 represent the feedback adjustment values ​​within the agreed time, in advance and in delay respectively;

[0052] β 1 , β 2 and β 3 They are adjustment coefficients, and respectively represent the intensity of control feedback adjustment within the agreed time of the project, in advance, and in delay.

[0053] Optionally, the calculation formula based on the feedback adjustment value FK1 within the agreed time, the feedback adjustment value FK2 before the agreed time and the feedback adjustment value FK3 after the agreed time fed back to the total cost estimation unit is as follows:

[0054] GC1=GC+ζ×FK1;

[0055] GC2=GC+ζ×FK2;

[0056] GC3=GC+ζ×FK3;

[0057] GC1, GC2 and GC3 are all updated fixed costs;

[0058] ζ is the feedback ratio, which represents the proportion of the feedback adjustment value used to update the fixed cost.

[0059] Optionally, based on the updated fixed cost GC1, GC2 and GC3 are all substituted into the next round of total cost estimation unit for calculation and replace the fixed cost GC. The loop feedback analysis is as follows:

[0060] When the project execution efficiency is high and the risk is low, the updated fixed costs GC1, GC2 and GC3 will decrease, thereby reducing the cost estimate ZC;

[0061] When project execution efficiency is low and risk increases, the updated fixed costs GC1, GC2, and GC3 increase, and the increase will increase the cost estimate ZC.

[0062] Compared with the prior art, the present invention has the following beneficial effects:

[0063] 1. The present invention introduces the dynamic calculation of risk factor F and material cost CC, combined with fixed cost GC, and the artificial intelligence service platform can achieve accurate estimation of project costs. This estimation method not only takes into account direct costs, but also incorporates potential risk factors, thereby improving the accuracy and reliability of cost estimation.

[0064] 2. The present invention designs different efficiency evaluation formulas for the three situations of within the agreed time, ahead of schedule and delayed. This multi-dimensional evaluation method can comprehensively reflect the efficiency performance of the project at different execution stages and provide project managers with more detailed and accurate decision-making basis.

[0065] 3. The feedback adjustment unit of the present invention enables the platform to automatically generate feedback adjustment values ​​FK1, FK2 and FK3 based on the efficiency evaluation results, and selects appropriate adjustment strategies to update the fixed costs GC1, GC2 and GC3 according to the actual situation of the project. This dynamic feedback mechanism enables project managers to obtain efficiency evaluation results in a timely manner and make adjustments accordingly, thereby optimizing resource allocation and improving project execution efficiency.

[0066] 4. The present invention adjusts the coefficient β through the sensitivity coefficients a, b and c 1 , β 2 and β 3 The setting of the feedback ratio ζ enables the artificial intelligence service platform to be flexibly adjusted according to the characteristics and needs of different projects. This flexibility not only improves the level of refinement of cost management, but also enhances the adaptability and scalability of the platform to different projects. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] Figure 1 A method flow chart of the service platform for this artificial intelligence;

[0068] Figure 2 It is a structural schematic diagram of the data processing module of the present invention;

[0069] Figure 3 Schematic diagram of the loop structure for feedback adjustment of the service platform of this artificial intelligence. DETAILED DESCRIPTION

[0070] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0071] Regarding this artificial intelligence service platform, it is different from the existing artificial intelligence service platforms. The traditional cost estimation methods in the existing artificial intelligence service platforms often rely on experience judgment and static data, which makes it difficult to accurately reflect the risk changes that will occur during the project execution process. It also ignores the differentiated impact of different situations, such as advance or delay, on efficiency evaluation. It lacks an effective dynamic feedback mechanism and cannot be flexibly adjusted according to the actual situation of the project. This algorithm unit realizes accurate estimation of project costs, multi-dimensional efficiency evaluation and dynamic feedback adjustment. These optimizations and innovations not only solve the problems and shortcomings of existing technologies, but also improve the efficiency and accuracy of project management, providing strong support for the sustainable development of enterprises.

[0072] For examples, see Figures 1 to 3 , this implementation provides an artificial intelligence service platform, and the specific implementation steps are as follows:

[0073] Step S1, using the data storage and extraction module to receive basic information data of projects and tasks from the service platform;

[0074] Step S2-1, using the data processing module, and according to the agreed time of the project and the time of project completion output, make targeted efficiency and feedback adjustments and substitute them into the calculation;

[0075] Step S2-2, based on feedback adjustment, re-estimate project cost, efficiency and feedback adjustment;

[0076] Step S3, using the user interaction module to provide an interface for the user to input data and view results;

[0077] Step S4, using a data storage and extraction module to store the data and results of the loop feedback;

[0078] in;

[0079] The data processing module includes a total cost estimation unit, a project execution efficiency evaluation unit and a feedback adjustment unit;

[0080] The equipment used in the data storage and retrieval module includes network equipment and storage equipment;

[0081] The equipment used in the data processing module includes servers;

[0082] The devices used in the user interaction module include computers and smart devices.

[0083] In this embodiment, the system not only improves the accuracy and reliability of cost estimation, promotes the refinement and multidimensionality of efficiency evaluation, and strengthens the flexibility and dynamism of cost control through the mutual cooperation of three algorithm units, combined with the three operation results of ZC, one of the results of X1, X2 and X3, and one of the results of FK1, FK2 and FK3, but more importantly, they form a complete project management closed-loop mechanism through their close connection and circular influence. ZC is the cost estimate value. Through this result, the project manager can have a preliminary understanding of the total cost required for the project, providing a basis for subsequent budget allocation and cost control. X1 is the efficiency evaluation value within the agreed time, X2 is the efficiency evaluation value before the agreed time, and X3 is the efficiency evaluation value after the agreed time. It is refined into the efficiency within the agreed time, in advance, and delayed. The purpose is to help project managers understand the efficiency of project execution. FK1 is the feedback adjustment value within the agreed time, FK2 is the feedback adjustment value before the agreed time, and FK3 is the feedback adjustment value after the agreed time. It reflects the feedback adjustment in different situations according to the efficiency of the three situations: within the agreed time, in advance, and delayed. The purpose is to make the cost estimate closer to the actual execution of the project by dynamically adjusting the fixed cost, thereby improving the accuracy and flexibility of cost management. The calculation result of one of the results of FK1, FK2 and FK3 is integrated into the fixed cost GC through the feedback ratio ζ to obtain the updated fixed cost, which in turn affects the calculation of one of the results of ZC, X1, X2 and X3, so that the three algorithms of this system have a high correlation and entanglement, so that the overall algorithm system can perform automatic feedback and optimization according to the actual situation to be closer to reality.

[0084] See also Figures 1 to 3 , the calculation formula of the total cost estimation unit is as follows:

[0085] ZC = CC × (1 + F / 100) × GC;

[0086] in:

[0087] ZC is the cost estimate;

[0088] CC is the material cost, CC is directly used for the material expenses of projects and tasks;

[0089] The calculation of F / 100 converts the percentage into a decimal and multiplies it by the material cost CC to obtain the additional material cost due to the increased risk;

[0090] F is the risk factor;

[0091] GC is fixed cost. GC reflects the costs that do not change with the project scale and material cost CC, including rent and wages.

[0092] In this embodiment: First, by introducing the risk factor F, the algorithm unit enables the total cost estimation unit to quantify the risks that the project may face and incorporate it into the cost estimation, thereby improving the accuracy and reliability of the estimation, which helps project managers better understand project costs and avoid cost overruns;

[0093] The fixed cost GC in the total cost estimation unit does not change with the project scale and material cost, but can adapt to the risk level of different projects by adjusting the risk factor F. This design makes the total cost estimation unit highly adaptable and applicable to various types of artificial intelligence service projects. The calculation result of the risk factor F helps project managers to more comprehensively evaluate the risk status of the project during the decision-making process, thereby formulating more scientific and reasonable risk management strategies and response measures. Moreover, through continuous monitoring and adjustment of the risk factor F, project managers can timely discover and respond to potential risk factors, thereby enhancing the risk management and risk resistance capabilities of the project.

[0094] In addition, through cost estimation, project managers can more clearly understand the risks that the project may face and its cost impact, so as to formulate targeted risk management measures and reduce project risks.

[0095] See also Figures 1 to 3 , the calculation formula for evaluating the project execution efficiency unit is as follows:

[0096] X1=P1 / (ZC+a×CC);

[0097] X2=[P2×(1+δ)] / (ZC+b×CC);

[0098] X3=[P3×(1-ε)] / (ZC+c×CC);

[0099] in:

[0100] X1 is the efficiency evaluation value within the agreed time;

[0101] X2 is the efficiency evaluation value before the agreed time;

[0102] X3 is the efficiency evaluation value after the agreed time;

[0103] X1, X2 and X3 represent the efficiency evaluation within the agreed time, in advance and in delay of the project respectively;

[0104] P1 is the output within the agreed time;

[0105] P2 is the output before the agreed time;

[0106] P3 is the output after the agreed time;

[0107] P1, P2 and P3 represent the output within the agreed time of the project, in advance and in delay respectively;

[0108] a, b and c are all sensitivity coefficients, and they represent the degree of cost sensitivity within the agreed time, in advance and in delay of the project respectively;

[0109] δ is the reward coefficient, which is used to adjust the efficiency improvement brought by early completion;

[0110] ε is the penalty coefficient, which is used to adjust the efficiency reduction caused by delayed completion.

[0111] In this embodiment, the algorithm unit provides a multi-dimensional efficiency evaluation method by evaluating the project execution efficiency unit, which can comprehensively reflect the efficiency performance of the project at different execution stages, which helps project managers to understand the project execution status more accurately, find problems in time and take corresponding measures;

[0112] For projects completed ahead of schedule, the project execution efficiency evaluation unit gives positive incentives by introducing a reward coefficient δ, while for projects completed late, a penalty coefficient ε is used to constrain them. This design helps to stimulate the enthusiasm of the project team while constraining them to complete the project on time.

[0113] Through the efficiency evaluation results, project managers can make decisions more quickly, such as adjusting resource allocation and optimizing project plans, thereby improving project execution efficiency.

[0114] See also Figures 1 to 3 , the calculation formula of the feedback adjustment unit is as follows:

[0115] FK1=β 1 ×(1-X1)×ZC;

[0116] FK2=β 2 ×(X2-1)×ZC;

[0117] FK3=β 3 ×(1-X3)×ZC;

[0118] in:

[0119] FK1 is the feedback adjustment value within the agreed time;

[0120] FK2 is the feedback adjustment value before the agreed time;

[0121] FK3 is the feedback adjustment value after the agreed time;

[0122] FK1, FK2 and FK3 represent the feedback adjustment values ​​within the agreed time, in advance and in delay respectively;

[0123] β 1 , β 2 and β 3 They are adjustment coefficients, and respectively represent the intensity of control feedback adjustment within the agreed time of the project, in advance, and in delay.

[0124] In this embodiment, the algorithm unit first calculates the cost estimate ZC obtained by the total cost estimation unit, and the efficiency evaluation value X1 within the agreed time, the efficiency evaluation value X2 before the agreed time, and the efficiency evaluation value X3 after the agreed time obtained by the project execution efficiency evaluation unit, combined with the adjustment coefficient β 1 , β 2 and β 3 , thus obtaining feedback adjustment values ​​reflecting different completion efficiencies;

[0125] Among them, the adjustment coefficient β 1 It reflects the baseline intensity of the impact of feedback adjustment on fixed costs when the project is completed within the agreed time. It is a relatively stable value unless there is a major change in project strategy.

[0126] Adjustment coefficient β 2 It will vary depending on the project's reward mechanism. If the project encourages early completion, the adjustment coefficient β 2 It will be set high to give a large positive feedback adjustment when completing ahead of schedule, which helps motivate the project team to be more efficient and may result in additional cost savings;

[0127] Adjustment coefficient β 3 It is usually set high to reflect the harsh attitude towards delayed completion, which will lead to serious consequences such as customer loss and reputation damage, so the adjustment coefficient β 3 The increase is intended to penalize delays through financial means and motivate project teams to work harder to complete projects on time;

[0128] It is worth noting that the feedback adjustment unit can be understood as a comprehensive application and further expansion of the above-mentioned efficiency evaluation. By automatically collecting and analyzing data during project execution, the artificial intelligence service platform can update the efficiency evaluation results in real time and quickly feedback to project managers. This real-time information feedback mechanism helps managers to find problems and adjust strategies in a timely manner, thereby improving the overall efficiency of project management. Efficiency evaluation is not only used for the evaluation of current projects, but also can be used as a reference for future project planning and improvement. By comprehensively analyzing the efficiency evaluation results of multiple projects, the artificial intelligence service platform can identify the key factors affecting efficiency and potential improvement points, and provide strong support for future project management and optimization. For customer-oriented artificial intelligence service platforms, efficient project execution and accurate cost estimation can significantly improve customer trust and satisfaction. By using these efficiency evaluations, the platform can demonstrate its professionalism and reliability to customers, thereby enhancing market competitiveness.

[0129] The feedback adjustment mechanism in this algorithm unit enables the feedback adjustment unit to dynamically optimize the fixed cost GC according to the actual execution of the project, which helps project managers to better control project costs and avoid unnecessary waste. Feedback adjustment is not only a cost optimization for the current project, but also a continuous improvement for future projects. By continuously accumulating and adjusting feedback adjustment values, project managers can gradually improve cost estimation and efficiency evaluation models and improve the overall management level of the project.

[0130] See also Figures 1 to 3 The calculation formula based on the feedback adjustment value FK1 within the agreed time, the feedback adjustment value FK2 before the agreed time and the feedback adjustment value FK3 after the agreed time fed back to the total cost estimation unit is as follows:

[0131] GC1=GC+ζ×FK1;

[0132] GC2=GC+ζ×FK2;

[0133] GC3=GC+ζ×FK3;

[0134] GC1, GC2 and GC3 are all updated fixed costs;

[0135] ζ is the feedback ratio, which represents the proportion of the feedback adjustment value used to update the fixed cost

[0136] Based on the updated fixed cost GC1, GC2 and GC3 will be substituted into the next round of total cost estimation unit for calculation and replace the fixed cost GC. The loop feedback analysis is as follows:

[0137] When the project execution efficiency is high and the risk is low, the updated fixed costs GC1, GC2 and GC3 will decrease, thereby reducing the cost estimate ZC;

[0138] When project execution efficiency is low and risk increases, the updated fixed costs GC1, GC2, and GC3 increase, and the increase will increase the cost estimate ZC.

[0139] In this embodiment, the algorithm unit uses a feedback adjustment mechanism to enable the updated fixed costs GC1, GC2 and GC3 to dynamically reflect the efficiency changes and risk situations during the project execution process. This flexibility makes the cost estimation closer to the actual project, which helps project managers to better control costs. The updated fixed costs GC1, GC2 and GC3 provide project managers with more accurate cost information, which helps them make more scientific and reasonable decisions. For example, in terms of project budget allocation, resource allocation, risk response strategy formulation, etc., the changes in the updated fixed costs GC1, GC2 and GC3 can serve as an important reference. By comprehensively considering the changing trends and reasons of FC', project managers can more accurately grasp the changing laws of project costs, thereby formulating more effective cost control measures.

[0140] The update of the updated fixed costs GC1, GC2 and GC3 also involves the re-evaluation of the risk factor F. In the total cost estimation unit, the risk factor F is one of the important factors affecting the total cost estimation. When new risk factors appear during the project execution and the original risk factors change, the value of the risk factor F will be adjusted accordingly. This adjustment will further affect the calculation results of the updated fixed costs GC1, GC2 and GC3, and will eventually be reflected in the total cost estimate ZC. Therefore, by paying attention to the changes in the updated fixed costs GC1, GC2 and GC3, project managers can promptly discover and respond to potential risk factors and reduce the risk of project failure;

[0141] The feedback adjustment mechanism itself is a continuous improvement process. By continuously collecting data and information during the project execution process and updating and adjusting the updated fixed costs GC1, GC2 and GC3, project managers can gradually optimize the cost estimation model and improve the accuracy and reliability of cost estimation. This continuous improvement process helps project managers better understand the changing rules of project costs and provide more accurate cost estimation support for future projects.

[0142] In summary, the updated fixed costs GC1, GC2 and GC3 with different results have a multi-faceted and far-reaching impact on the total cost estimation unit. It not only improves the flexibility and accuracy of cost control, but also provides project managers with more scientific decision-making support and risk management tools. At the same time, through the process of continuous improvement, project managers can continuously optimize the cost estimation model and improve the overall level and efficiency of project management.

[0143] In addition, through the feedback adjustment mechanism of the feedback adjustment unit, the fixed cost GC is dynamically optimized. The optimized updated fixed costs GC1, GC2 and GC3 will be used as one of the input parameters for the next round of cost estimation, thereby affecting the new cost estimation results. This cyclical impact makes the cost estimation closer to the actual project situation and improves the accuracy and reliability of the estimation. With the continuous execution of the project and the continuous feedback adjustment, the project manager can gradually accumulate and adjust the feedback adjustment value and the correlation coefficient. These adjustments will continuously improve the cost estimation model to make it more in line with the actual needs and management strategies of the project. This continuous improvement process helps project managers better grasp the project cost and improve the overall management level of the project.

[0144] In summary, in the specific implementation process, the total cost estimation unit, the project execution efficiency evaluation unit and the feedback adjustment unit play a vital role in the artificial intelligence service platform. They not only improve the accuracy and reliability of cost estimation, promote the refinement and multidimensionality of efficiency evaluation, and strengthen the flexibility and dynamism of cost control, but more importantly, they form a complete project management closed-loop mechanism through their close connection and circular influence. This mechanism helps project managers to fully and accurately grasp the project situation and formulate scientific and reasonable project management strategies and measures. At the same time, it also helps the project team to continuously accumulate experience and knowledge and improve the level and ability of project management. Therefore, it can be said that the total cost estimation unit, the project execution efficiency evaluation unit and the feedback adjustment unit and their circular influence on each other are important guarantees for the successful operation of the artificial intelligence service platform.

[0145] For example 2, please refer to Figures 1 to 3 , the sensitivity coefficient a reflects the sensitivity of cost to output when the project is carried out completely according to plan, and is the benchmark coefficient;

[0146] A higher sensitivity coefficient b indicates that the project places great emphasis on time efficiency, while a lower sensitivity coefficient b indicates that the project has extremely high requirements for quality;

[0147] A higher sensitivity coefficient c reflects the negative impact of delayed completion on project costs, including additional overtime expenses, customer dissatisfaction, fines and opportunity costs.

[0148] In this embodiment, by setting different cost sensitivity coefficients for different situations, including within the agreed time, ahead of schedule, and delayed completion, the cost of the project under different execution conditions can be estimated more accurately. This segmented processing method helps project managers better understand the laws and trends of cost changes.

[0149] When the coefficient of sensitivity coefficient b is set high, the project team will be financially motivated to work harder to improve work efficiency and strive to complete the project ahead of schedule. This positive incentive mechanism helps to improve the team's cohesion and execution. The coefficient of sensitivity coefficient c is set high, which can reflect the serious negative impact of delayed completion on project costs. This setting method helps project managers pay more attention to time management and reduce additional costs and potential risks caused by delays.

[0150] By analyzing the changes in the cost sensitivity coefficient, project managers can formulate resource allocation plans more scientifically. For example, when it is expected that the project may be completed ahead of schedule, resource investment can be appropriately reduced to avoid waste. When it is expected that the project may be delayed, resource investment needs to be increased in a timely manner to ensure that the project can be completed on time.

[0151] Different settings of cost sensitivity coefficients can provide project managers with more comprehensive and in-depth cost information, which helps managers consider various factors more comprehensively in the decision-making process and make more scientific and reasonable decisions.

[0152] The setting and adjustment of cost sensitivity coefficients is an ongoing process. With the accumulation of project experience and data, project managers can continuously optimize the setting of these coefficients to improve the efficiency and accuracy of cost control. This continuous improvement mechanism helps project teams continuously improve their competitiveness and adaptability.

[0153] In summary, different settings of cost sensitivity coefficients have many beneficial effects on project management and cost control. By setting these coefficients scientifically and reasonably, project managers can more accurately estimate costs, motivate teams, control risks, optimize resource allocation, improve decision-making quality and promote continuous improvement.

[0154] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations can be made to the embodiments without departing from the principles and spirit of the present invention, and the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An artificial intelligence service platform, characterized in that: The specific implementation steps are as follows: Step S1, using the data storage and extraction module to receive basic information data of projects and tasks from the service platform; Step S2-1, using the data processing module, and according to the agreed time of the project and the time of project completion output, make targeted efficiency and feedback adjustments and substitute them into the calculation; Step S2-2, based on feedback adjustment, re-estimate project cost, efficiency and feedback adjustment; Step S3, using the user interaction module to provide an interface for the user to input data and view results; Step S4, using a data storage and extraction module to store the data and results of the loop feedback; in; The data processing module includes a total cost estimation unit, a project execution efficiency evaluation unit and a feedback adjustment unit.

2. The artificial intelligence service platform according to claim 1, characterized in that: The devices used by the data storage and retrieval module include network devices and storage devices; The equipment used by the data processing module includes a server; The devices used in the user interaction module include computers and smart devices.

3. The artificial intelligence service platform according to claim 2, characterized in that: The calculation formula of the total cost estimation unit is as follows: ZC = CC × (1 + F / 100) × GC; in: ZC is the cost estimate; CC is the material cost, CC is directly used for the material expenses of projects and tasks; The calculation of F / 100 converts the percentage into a decimal and multiplies it by the material cost CC to obtain the additional material cost due to the increased risk; F is the risk factor; GC is fixed cost. GC reflects the costs that do not change with the project scale and material cost CC, including rent and wages.

4. The artificial intelligence service platform according to claim 3, characterized in that: The calculation formula for the evaluation project execution efficiency unit is as follows: X1=P1 / (ZC+a×CC); X2=[P2×(1+δ)] / (ZC+b×CC); X3=[P3×(1-ε)] / (ZC+c×CC); in: X1 is the efficiency evaluation value within the agreed time; X2 is the efficiency evaluation value before the agreed time; X3 is the efficiency evaluation value after the agreed time; X1, X2 and X3 represent the efficiency evaluation within the agreed time, in advance and in delay of the project respectively; P1 is the output within the agreed time; P2 is the output before the agreed time; P3 is the output after the agreed time; P1, P2 and P3 represent the output within the agreed time of the project, in advance and in delay respectively; a, b and c are all sensitivity coefficients, and they represent the degree of cost sensitivity within the agreed time, in advance and in delay of the project respectively; δ is the reward coefficient, which is used to adjust the efficiency improvement brought by early completion; ε is the penalty coefficient, which is used to adjust the efficiency reduction caused by delayed completion.

5. The artificial intelligence service platform according to claim 4, characterized in that: The sensitivity coefficient a reflects the sensitivity of cost to output when the project is carried out completely according to plan, and is the base coefficient; A high sensitivity coefficient b indicates that the project places great emphasis on time efficiency, while a low sensitivity coefficient b indicates that the project has extremely high requirements for quality; A high sensitivity coefficient c reflects the negative impact of delayed completion on project costs, including additional overtime expenses, customer dissatisfaction, fines and opportunity costs.

6. The artificial intelligence service platform according to claim 5, characterized in that: The calculation formula of the feedback adjustment unit is as follows: FK1=β 1 ×(1-X1)×ZC; FK2=β 2 ×(X2-1)×ZC; FK3=β 3 ×(1-X3)×ZC; in: FK1 is the feedback adjustment value within the agreed time; FK2 is the feedback adjustment value before the agreed time; FK3 is the feedback adjustment value after the agreed time; FK1, FK2 and FK3 represent the feedback adjustment values ​​within the agreed time, in advance and in delay respectively; β 1 , β 2 and β 3 They are adjustment coefficients, and respectively represent the intensity of control feedback adjustment within the agreed time of the project, in advance, and in delay.

7. The artificial intelligence service platform according to claim 6, characterized in that: The calculation formula based on the feedback adjustment value FK1 within the agreed time, the feedback adjustment value FK2 before the agreed time and the feedback adjustment value FK3 after the agreed time fed back to the total cost estimation unit is as follows: GC1=GC+ζ×FK1; GC2=GC+ζ×FK2; GC3=GC+ζ×FK3; GC1, GC2 and GC3 are all updated fixed costs; ζ is the feedback ratio, which represents the proportion of the feedback adjustment value used to update the fixed cost.

8. The artificial intelligence service platform according to claim 7, characterized in that: Based on the updated fixed costs GC1, GC2 and GC3 are all substituted into the next round of total cost estimation unit for calculation and replace the fixed cost GC. The loop feedback analysis is as follows: When the project execution efficiency is high and the risk is low, the updated fixed costs GC1, GC2 and GC3 will decrease, thereby reducing the cost estimate ZC; When project execution efficiency is low and risk increases, the updated fixed costs GC1, GC2, and GC3 increase, and the increase will increase the cost estimate ZC.

Images