Intelligent current bid evaluation project system and method based on multi-level scoring logic

Abstract

The invention provides an intelligent current bid evaluation project system and method based on multi-level scoring logic, and belongs to the technical field of intelligent bidding, the system comprises a layering module, a logic module, an adjustment updating module and a prediction module, and through systematic top-to-bottom classification and in combination with data analysis and market trends, a bid evaluation result is obtained. A current bid evaluation project standard can be objectively quantified, the interference of subjective judgment is reduced, meanwhile, a dynamic adjustment mechanism ensures that the scoring model adapts to a changing market environment, so that the scoring model is more flexible and applicable and has the capability of predicting the bidding success probability and the potential risk, a bid invitation organization is helped to make a more intelligent decision, and the bid invitation efficiency is improved. Therefore, the bidding success rate and the effectiveness of project implementation are improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent bidding technology, and in particular to an intelligent current bidding evaluation project system and method based on multi-level scoring logic. Background Art

[0002] In the current bidding and procurement process, the current bid evaluation project is a key step, which directly affects the fairness, transparency and efficiency of the bidding. The traditional current bid evaluation project method often relies on the subjective judgment of the expert review team, which is not only time-consuming, but also may lead to inconsistency in the evaluation results due to human factors. At the same time, with the development of information technology, especially the advancement of data analysis and machine learning technology, more and more bidding organizations are beginning to seek automated and intelligent current bid evaluation project solutions. However, these solutions usually lack sufficient flexibility and adaptability, and it is difficult to cope with the complex and changing bidding environment and the diverse current bid evaluation project standards. In addition, they are rarely able to predict the probability and potential risks of successful bidding, or dynamically adjust the current bid evaluation project standards based on market trends and historical data.

[0003] Therefore, the present invention provides an intelligent current bidding evaluation project system and method based on multi-level scoring logic. Summary of the invention

[0004] The present invention provides an intelligent current bid evaluation project system and method based on multi-level scoring logic. Through systematic top-to-bottom level classification and combined with data analysis and market trends, it can objectively quantify the current bid evaluation project standards and reduce the interference of subjective judgment. At the same time, the dynamic adjustment mechanism ensures that the scoring model adapts to the changing market environment, making it more flexible and applicable. The ability to predict the probability of successful bidding and potential risks helps bidding organizations make more informed decisions, thereby improving the success rate of bidding and the effectiveness of project implementation.

[0005] The present invention provides an intelligent current bid evaluation project system based on multi-level scoring logic, comprising:

[0006] Hierarchical module: Analyze application scenarios and target users, and define the top-level classification, middle-level classification, and bottom-level classification of the current bid evaluation project based on the analysis results;

[0007] Logical module: conducts an overall analysis of the current bid evaluation project, obtains the overall goal and the basic vector of the project, sets the scoring logic and aggregation logic for the bottom-level classification, middle-level classification and top-level classification based on the overall goal and the basic vector of the project, and then constructs a scoring model;

[0008] Adjustment and update module: setting adjustment conditions according to the project basic vector, and adjusting and updating the scoring model based on the adjustment conditions;

[0009] Prediction module: Based on the historical bidding data and market trend analysis, predict the future bidding success probability of the current evaluation project, and formulate a bidding strategy based on the adjusted and updated scoring model and the future bidding success probability.

[0010] The present invention provides an intelligent current bid evaluation project system based on multi-level scoring logic, a hierarchical module, including:

[0011] Scenario analysis unit: collects industry information, determines the scoring standards for each industry based on the industry information, and at the same time, collects market information, determines the hot spots and pain points of the current bid evaluation project in the bidding based on the market information, and determines the scenario requirements according to the scoring standards and the hot spots and pain points;

[0012] User analysis unit: clarifies the bidding roles, performs role background analysis on the bidding roles, and determines role requirements based on the background analysis results;

[0013] Classification determination unit: Analyze the scenario requirements and role requirements, determine the main current bid evaluation project areas and key concerns, form a top-level classification, refine the top-level classification to obtain a middle-level classification, and refine each middle-level classification to obtain a bottom-level classification.

[0014] The present invention provides an intelligent current bid evaluation project system based on multi-level scoring logic, a classification determination unit, comprising:

[0015] Demand analysis subunit: Analyze the relationship and demand priority between the scenario requirements and role requirements, identify the core requirements and secondary requirements, and determine the commonalities between the scenario requirements and role requirements;

[0016] Field determination subunit: Determine the demand characteristics corresponding to the core demand and the secondary demand based on the common points of the demand, and determine the current bid evaluation project field according to the demand characteristics, determine the field importance of the current bid evaluation project field from the project field table, combine the field importance with the demand priority, classify the current bid evaluation project field, and then determine the main current bid evaluation project field.

[0017] The present invention provides an intelligent current bid evaluation project system based on multi-level scoring logic, a classification determination unit, and further includes:

[0018] Framework subunit: refine the main current bid evaluation project areas to determine the key concerns, and design a classification framework based on the main current bid evaluation project areas and key concerns;

[0019] Hierarchical classification subunit: Determine the scoring target of the top-level classification based on the classification framework, and determine the top-level classification according to the scoring target, subdivide the scoring target based on the classification framework to obtain scoring factors, determine the middle-level classification according to the scoring factors, obtain scoring indicators based on the subdivision of the scoring factors, and determine the bottom-level classification according to the scoring indicators.

[0020] The present invention provides an intelligent current bidding evaluation project system based on multi-level scoring logic, and a logic module includes:

[0021] Overall target determination unit: performs overall analysis on the current bid evaluation project, generates a project basic vector, and obtains the overall target based on the project basic vector;

[0022] Model unit: determining the relevant variables of the underlying classification according to the overall goal, obtaining the domain knowledge of the field to which the current bid evaluation project belongs, and defining the dependency relationship between the relevant variables based on the project basic vector;

[0023] Scoring logic unit: collects underlying historical data related to the underlying classification, determines the prior probability of each relevant variable based on the underlying historical data, and determines the likelihood probability of each relevant variable based on the dependency relationship between the relevant variables, determines the posterior probability of the corresponding relevant variable based on the prior probability and the likelihood probability, converts the posterior probability into the score of the corresponding relevant variable, and uses the maximum score among the relevant variables as the corresponding underlying classification score. Similarly, obtains the scores of each middle-level classification and top-level classification;

[0024] Aggregation logic unit: construct a bottom-level score distribution according to the bottom-level classification scores, set a first threshold based on the bottom-level score distribution, filter the bottom-level classification scores higher than the first threshold from the bottom-level classification, obtain the bottom-level screening results, aggregate the bottom-level screening results to the middle-level classification, similarly, set a second threshold to obtain the middle-level screening results, aggregate the middle-level screening results to the top-level classification, set a third threshold to obtain the top-level screening results, and aggregate the top-level screening results into the current bid evaluation project score;

[0025] Scoring model unit: integrates the contents of the scoring logic unit and the aggregation logic unit to build a scoring model.

[0026] The present invention provides an intelligent current bid evaluation project system based on multi-level scoring logic, an adjustment and update module, including:

[0027] Direction determination unit: determine the project characteristics according to the project basic vector, identify the first condition affecting the scoring model in combination with the overall goal and the project characteristics, classify the first condition based on the project characteristics, and extract the project history data of the same type of project as the current evaluation project to analyze the potential impact of the first condition, and obtain the possible adjustment direction of the first condition;

[0028] An updating unit: derives an adjustment condition based on the first condition and the possible adjustment direction, and adjusts and updates the scoring model.

[0029] The present invention provides an intelligent current bid evaluation project system based on multi-level scoring logic, a prediction module, including:

[0030] Factor extraction unit: collects relevant historical bidding data and market trend information related to bidding, analyzes historical bidding data, and extracts key factors for success and failure;

[0031] Prediction determination unit: evaluates the first impact of different key factors on the bidding results, and at the same time, identifies the second impact of market trends on the success of the bidding, combines the first impact and the second impact to obtain the bidding success rate, uses machine learning algorithms to build a prediction model, and quantitatively evaluates the bidding success rate based on the prediction model, thereby predicting the future bidding success rate;

[0032] Strategy determination unit: Combine the future bidding success rate with the adjusted and updated scoring model to form a comprehensive evaluation framework, use the comprehensive evaluation framework to evaluate the pros and cons of different bidding schemes for the current evaluation project, and determine the bidding strategy.

[0033] The present invention provides an intelligent current bid evaluation project method based on multi-level scoring logic, comprising:

[0034] Step 1: Analyze the application scenarios and target users, and define the top-level, middle-level, and bottom-level categories of the current bid evaluation project based on the analysis results;

[0035] Step 2: Conduct an overall analysis of the current bid evaluation project to obtain the overall goal and project basic vector, and set scoring logic and aggregation logic for the bottom-level classification, middle-level classification, and top-level classification based on the overall goal and project basic vector, and then build a scoring model;

[0036] Step 3: setting adjustment conditions according to the project basic vector, and adjusting and updating the scoring model based on the adjustment conditions;

[0037] Step 4: Based on the historical bidding data and market trend analysis, predict the future bidding success probability of the current evaluation project, and formulate a bidding strategy based on the adjusted and updated scoring model and the future bidding success probability.

[0038] Compared with the prior art, the beneficial effects of this application are as follows: through systematic top-to-bottom classification, combined with data analysis and market trends, it is possible to objectively quantify the current bid evaluation project standards and reduce the interference of subjective judgment. At the same time, the dynamic adjustment mechanism ensures that the scoring model adapts to the changing market environment, making it more flexible and applicable. The ability to predict the probability of successful bidding and potential risks helps bidding organizations make more informed decisions, thereby improving the success rate of bidding and the effectiveness of project implementation.

[0039] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0040] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0042] Figure 1 It is a structural diagram of an intelligent current bidding evaluation project system based on multi-level scoring logic provided by an embodiment of the present invention;

[0043] Figure 2 It is a flowchart of an intelligent current bid evaluation project method based on multi-level scoring logic provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0044] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0045] Embodiment 1:

[0046] The embodiment of the present invention provides an intelligent current bidding project system based on multi-level scoring logic, such as Figure 1 As shown, including:

[0047] Hierarchical module: Analyze application scenarios and target users, and define the top-level classification, middle-level classification, and bottom-level classification of the current bid evaluation project based on the analysis results;

[0048] Logical module: conducts an overall analysis of the current bid evaluation project, obtains the overall goal and the basic vector of the project, sets the scoring logic and aggregation logic for the bottom-level classification, middle-level classification and top-level classification based on the overall goal and the basic vector of the project, and then constructs a scoring model;

[0049] Adjustment and update module: setting adjustment conditions according to the project basic vector, and adjusting and updating the scoring model based on the adjustment conditions;

[0050] Prediction module: Based on the historical bidding data and market trend analysis, predict the future bidding success probability of the current evaluation project, and formulate a bidding strategy based on the adjusted and updated scoring model and the future bidding success probability.

[0051] In this embodiment, a systematic current bid evaluation project framework is constructed through comprehensive scenario analysis, user demand identification and hierarchical classification, industry and market information is collected, hot spots and pain points are accurately identified, and clear scoring criteria are formed in combination with role requirements.

[0052] In this embodiment, the overall goal is the overall outcome and effect that the project hopes to achieve during execution, which is extracted from the project background and basic vectors. For example, the overall goal of an IT system development project may be "developing a user-friendly, scalable and highly secure online trading platform."

[0053] In this embodiment, an overall analysis is performed on the current bid evaluation project, a project basic vector is generated to establish the overall goal, a model is established to determine the relevant variables of the underlying classification, and the dependencies between these variables are defined. The prior and likelihood probabilities are calculated through the underlying historical data to obtain the posterior probabilities, which are then converted into scores. Aggregation logic is used to perform threshold screening and hierarchical aggregation on the scores, and ultimately a comprehensive scoring model is constructed.

[0054] In this embodiment, scoring logic refers to the systematic rules and methods for evaluating and scoring each underlying classification and its related variables during the bid evaluation process; aggregation logic refers to the rules and methods for integrating and summarizing the scores of each underlying classification during the bid evaluation process to obtain comprehensive evaluation results for the middle-level classification and top-level classification.

[0055] In this embodiment, the adjustment condition refers to the specific parameters or standards that actually need to be changed after the possible adjustment direction is determined. For example, for "technical implementation capability", the adjustment condition is to modify the technical standard and promote the use of the latest development framework.

[0056] In this embodiment, by conducting an overall analysis of the project, determining the project characteristics and combining them with the overall goals, identifying the first condition that affects the scoring model, and classifying the first condition. By extracting historical project data of similar projects to analyze the potential impact, possible adjustment directions are obtained, and specific adjustment conditions are generated based on these adjustment directions, and the scoring model is further updated as necessary.

[0057] In this embodiment, the historical bidding data refers to specific data related to the bidding process and results, and involves all information on the submission, review and decision results of the bidding proposal.

[0058] In this embodiment, the bidding strategy is a specific action plan formulated based on the analysis of evaluation results and market information. It clarifies the bidding objectives (such as winning specific projects or customers), uses a comprehensive evaluation framework to analyze the advantages and disadvantages of different bidding schemes, adjusts services or prices in light of market changes, identifies possible risk factors (such as backward technology, budget overruns, etc.), formulates relevant response measures, and invests more resources in areas with strong competitiveness to enhance strength. For example, if the comprehensive evaluation results show that technological innovation is the key factor for successful bidding, the bidding strategy may be to strengthen technological research and development, emphasize innovative solutions as selling points in the bidding documents, and adjust prices appropriately to improve cost-effectiveness.

[0059] The working principle and beneficial effects of the above technical solution are: by applying modular analysis, scoring logic construction, dynamic adjustment and risk prediction, it aims to improve the fairness, transparency and efficiency of the current bidding evaluation project process. Through systematic top-to-bottom classification, combined with data analysis and market trends, it can objectively quantify the current bidding evaluation project standards and reduce the interference of subjective judgment. At the same time, the dynamic adjustment mechanism ensures that the scoring model adapts to the changing market environment, making it more flexible and applicable. The ability to predict the probability of successful bidding and potential risks will help bidding organizations make more informed decisions, thereby improving the success rate of bidding and the effectiveness of project implementation.

[0060] Embodiment 2:

[0061] The embodiment of the present invention provides an intelligent current bid evaluation project system based on multi-level scoring logic, a hierarchical module, including:

[0062] Scenario analysis unit: collects industry information, determines the scoring standards for each industry based on the industry information, and at the same time, collects market information, determines the hot spots and pain points of the current bid evaluation project in the bidding based on the market information, and determines the scenario requirements according to the scoring standards and the hot spots and pain points;

[0063] User analysis unit: clarifies the bidding roles, performs role background analysis on the bidding roles, and determines role requirements based on the background analysis results;

[0064] Classification determination unit: Analyze the scenario requirements and role requirements, determine the main current bid evaluation project areas and key concerns, form a top-level classification, refine the top-level classification to obtain a middle-level classification, and refine each middle-level classification to obtain a bottom-level classification.

[0065] In this embodiment, industry information refers to various data and knowledge related to a specific industry, including market trends, competitive environment, regulations and policies, industry standards, best practices, technological advances, customer needs, etc. For example, trend reports on the IT service market, including the development of technologies such as cloud computing and artificial intelligence.

[0066] In this embodiment, the scoring criteria are a set of specific indicators used to score various project characteristics, which are usually set based on multiple aspects such as industry best practices, customer needs, and regulatory requirements. For example, if a bidder provides an advanced technical solution and demonstrates its effectiveness and reliability, the score may be 4 points. If the bidder has received customer complaints in past contracts and has not effectively resolved them, the review may give 3 points. If the bidder's quotation is lower than the market average and has corresponding guarantees in terms of technical capabilities and service quality, it can get 4 points.

[0067] In this embodiment, market information refers to data and dynamics related to a specific market, including consumer behavior, demand changes, competitor analysis, pricing strategies, market share, etc. Industry information is usually broader and focuses on the entire industry and its trends, while market information focuses on dynamics and changes within a specific market.

[0068] In this embodiment, hot spots refer to topics or issues that are popular and widely concerned in the current market or industry; and pain points refer to difficulties and challenges encountered by users or customers when using a product or service.

[0069] In this embodiment, the step of determining scenario requirements is to understand current industry trends and market hotspots, identify the problems faced by target users through user feedback, market research, etc., summarize and conclude using a pre-set scoring criteria framework, and clarify the priority and influence of the requirements.

[0070] In this embodiment, role background analysis is to identify various relevant roles (such as buyers, sellers, review experts, etc.) in the bidding process, collect role-related data through questionnaires, interviews or document research, including the role's responsibilities, powers, experience, decision-making basis, etc., summarize and summarize the collected information, and extract the influencing factors and needs of each role. For example, the head of the department may have higher expectations in terms of technical capabilities and support services, while the procurement department is more concerned about price.

[0071] In this embodiment, role requirements refer to the specific requirements and expectations of each role for the project during the bidding process, including technical requirements, service levels, budget ranges, etc., including product or service features required to meet role expectations.

[0072] In this embodiment, by analyzing scenario requirements and role requirements, identifying core and secondary requirements, and determining commonalities in requirements, the current evaluation project areas are defined based on the characteristics of the requirements and combined with importance and priority to divide the current evaluation project levels. Then, the main current evaluation project areas are refined, a classification framework is designed, the scoring targets of the top-level classification are clarified, subdivided into scoring factors, and the middle-level classification and bottom-level classification are further determined.

[0073] The working principle and beneficial effects of the above technical solution are: through comprehensive scenario analysis, user demand identification and hierarchical classification, a systematic current bid evaluation project framework is constructed to collect industry and market information, accurately identify hot spots and pain points, and combine role requirements to form clear scoring standards. By setting a dynamic adjustment mechanism, it can adapt to the ever-changing bidding environment, making the current bid evaluation project process more flexible, reducing the deviation of subjective judgment, and improving the transparency and consistency of the current bid evaluation project.

[0074] Embodiment 3:

[0075] The embodiment of the present invention provides an intelligent current bid evaluation project system based on multi-level scoring logic, and a classification determination unit, including:

[0076] Demand analysis subunit: Analyze the relationship and demand priority between the scenario requirements and role requirements, identify the core requirements and secondary requirements, and determine the commonalities between the scenario requirements and role requirements;

[0077] Field determination subunit: Determine the demand characteristics corresponding to the core demand and the secondary demand based on the common points of the demand, and determine the current bid evaluation project field according to the demand characteristics, determine the field importance of the current bid evaluation project field from the project field table, combine the field importance with the demand priority, classify the current bid evaluation project field, and then determine the main current bid evaluation project field.

[0078] In this embodiment, scenario requirements refer to specific requirements that a project or service needs to meet in a specific situation, which are usually guided by business goals. Role requirements refer to the specific expectations and requirements of participants (such as customers, users, and suppliers) for scenario requirements. Role requirements are developed on the basis of scenario requirements. Since different roles have different understandings and expectations of scenario requirements, role requirements are usually interrelated with scenario requirements, but may have different emphases. For example, in an IT project, the scenario requirement may be "providing high-availability cloud services", while role requirements may include "the IT department wants to achieve availability 95% of the time" and "the finance department requires cost control."

[0079] In this embodiment, demand priority refers to sorting the importance of various requirements according to business goals and user expectations. Low-priority requirements can be temporarily abandoned or postponed when resources are limited or time is tight. Core requirements (high priority): The system needs to support two-factor authentication to enhance security. Secondary requirements (low priority): The user interface color of the system should comply with the company's brand standards.

[0080] In this embodiment, the commonality of requirements is the consistent part between the scenario requirements and the role requirements, which may be "all participants want to improve project efficiency" or "all roles are concerned about data security."

[0081] In this embodiment, core requirements are requirements that are critical to the success of the project and usually have a high priority. Secondary requirements are requirements that are less important to the project and have a lower priority than core requirements. For example, the core requirement: the system must be able to handle requests from 10,000 concurrent users, and the secondary requirement: provide easily customizable user interface theme options.

[0082] In this embodiment, the current evaluation project field is a plurality of dimensions that need to be considered in the evaluation process, involving various aspects of the demand, usually involving key performance indicators (KPIs) or required characteristics. For example, in the bidding process, the current evaluation project field may include technical capabilities, project management capabilities, after-sales service quality, cost-effectiveness, etc.

[0083] In this embodiment, domain importance refers to the importance of a current evaluation project domain to the overall project success, which determines the attention that needs to be given to this domain during the evaluation process. For example, for a hospital information system tender, technical capabilities may be considered the most important domain importance, while service support may be a secondary important domain.

[0084] In this embodiment, the project domain table includes the names, descriptions, and roles or importance of different domains in the project. For example, the domain name is technical capability, the domain description is to evaluate the bidder's ability and innovation in the project's technical solution, the domain importance is high, and the evaluation criteria are the effectiveness of the solution, the technical complexity of the implementation, scalability, etc.

[0085] In this embodiment, the current evaluation project fields are graded based on the domain importance and demand priority, and the comparison between the importance and demand priority of each current evaluation project field is determined. For example, the domain importance of technical capabilities is first identified, and its practicality is judged based on the priority of core requirements. The specific steps of grading are to grade the fields based on the domain importance and demand priority of each current evaluation project field, which are usually divided into: key areas: extremely important and priority areas (such as technical capabilities); important areas: areas that require attention but are not the highest priority (such as support capabilities); secondary areas: relatively less important areas (such as other additional functions).

[0086] The working principle and beneficial effects of the above technical solution are: by analyzing the relationship between scenario requirements and role requirements, identifying core requirements and secondary requirements, and extracting common points of requirements, forming the current evaluation project field, combining the project field table with the demand priority, and dividing the current evaluation project field into importance levels, so as to ensure that the current evaluation project standards are scientific, reasonable and systematic, improve the accuracy and effectiveness of the current evaluation project, ensure that the current evaluation project standards meet actual needs, and reduce deviations.

[0087] Embodiment 4:

[0088] The embodiment of the present invention provides an intelligent current bid evaluation project system based on multi-level scoring logic, the classification determination unit also includes:

[0089] Framework subunit: refine the main current bid evaluation project areas to determine the key concerns, and design a classification framework based on the main current bid evaluation project areas and key concerns;

[0090] Hierarchical classification subunit: Determine the scoring target of the top-level classification based on the classification framework, and determine the top-level classification according to the scoring target, subdivide the scoring target based on the classification framework to obtain scoring factors, determine the middle-level classification according to the scoring factors, obtain scoring indicators based on the subdivision of the scoring factors, and determine the bottom-level classification according to the scoring indicators.

[0091] In this embodiment, the scoring target is to define the top-level classification of the current bid evaluation project, such as technical capabilities, commercial quotations, etc.; the scoring factors are to define more specific evaluation criteria under the scoring items, such as the innovation of the technical solution, the rationality of the quotation, etc.; the scoring indicators are further refined into quantifiable evaluation dimensions for the scoring factors, such as the innovation of the technical solution can be refined into technological advancement, practicality, etc.

[0092] In this embodiment, key concerns refer to specific aspects or features that require special attention when evaluating the main current bid evaluation project area. They are factors that have a greater impact on the results of the current bid evaluation project and are directly related to core needs. For example, in the current bid evaluation project area of ​​"technical capabilities", key concerns may include the innovation, adaptability, and scalability of the technology.

[0093] In this embodiment, the classification framework is a structured tool for organizing review dimensions and elements and classifying the elements in the entire current bid evaluation project process, thereby simplifying complexity and clarifying the relationship between each level.

[0094] In this embodiment, the top-level classification is the most extensive classification in the current bid evaluation project field, usually focusing on key decision-making areas or evaluation dimensions, and directly affecting the key factors of project success. In the bidding of IT projects, the top-level classification includes: technical capabilities, project management capabilities, cost-effectiveness, risk management, and after-sales support; the middle-level classification is a further refinement of the top-level classification, usually focusing on the key concerns in each top-level classification to form more specific evaluation dimensions or characteristics. Taking "technical capabilities" as an example, the middle-level classification includes: technical innovation capabilities, technical implementation plans, suspension or non-suitability of technical standards; the bottom-level classification is the most specific evaluation dimension, usually subdivided according to specific scoring indicators. For the middle-level classification "technical innovation capabilities", the bottom-level classification may include: the quality of technical documents provided (scoring range 1-5), the uniqueness and innovation of the solution (scoring range 1-5), and the number of successful cases of similar projects in the past (scoring range 1-5).

[0095] The working principle and beneficial effects of the above technical solution are: by refining the main current bid evaluation project areas, determining key concerns, and designing a classification framework to establish a systematic evaluation structure, according to the classification framework, determine the scoring targets of the top-level classification, and further subdivide it into middle-level classification and bottom-level classification. Through hierarchical classification, the consistency of various indicators and scoring targets is ensured, which reduces the subjectivity in traditional current bid evaluation projects, improves the transparency and efficiency of the current bid evaluation project process, and flexibly adjusts according to changes in demand to meet the requirements of a complex bidding environment.

[0096] Embodiment 5:

[0097] The embodiment of the present invention provides an intelligent current bidding project system based on multi-level scoring logic, and the logic module includes:

[0098] Overall target determination unit: performs overall analysis on the current bid evaluation project, generates a project basic vector, and obtains the overall target based on the project basic vector;

[0099] Model unit: determining the relevant variables of the underlying classification according to the overall goal, obtaining the domain knowledge of the field to which the current bid evaluation project belongs, and defining the dependency relationship between the relevant variables based on the project basic vector;

[0100] Scoring logic unit: collects underlying historical data related to the underlying classification, determines the prior probability of each relevant variable based on the underlying historical data, and determines the likelihood probability of each relevant variable based on the dependency relationship between the relevant variables, determines the posterior probability of the corresponding relevant variable based on the prior probability and the likelihood probability, converts the posterior probability into the score of the corresponding relevant variable, and uses the maximum score among the relevant variables as the corresponding underlying classification score. Similarly, obtains the scores of each middle-level classification and top-level classification;

[0101] Aggregation logic unit: construct a bottom-level score distribution according to the bottom-level classification scores, set a first threshold based on the bottom-level score distribution, filter the bottom-level classification scores higher than the first threshold from the bottom-level classification, obtain the bottom-level screening results, aggregate the bottom-level screening results to the middle-level classification, similarly, set a second threshold to obtain the middle-level screening results, aggregate the middle-level screening results to the top-level classification, set a third threshold to obtain the top-level screening results, and aggregate the top-level screening results into the current bid evaluation project score;

[0102] Scoring model unit: integrates the contents of the scoring logic unit and the aggregation logic unit to build a scoring model.

[0103] In this embodiment, the project basic vector is a vector that describes the key characteristics and parameters of the project, and is usually used to define and analyze various aspects of the project, such as project scale: such as project budget, construction period, resource requirements, etc.; project goals: such as improving efficiency, reducing costs, enhancing security, etc.; project types: such as IT projects, construction projects, R&D projects, etc.; access standards: such as technical requirements, compliance requirements, etc.

[0104] In this embodiment, the relevant variables refer to key factors or parameters that have an impact on achieving the overall goal, and are usually used to analyze project progress or evaluate results. For example, in an IT project, the relevant variables may include: technical quality, team collaboration efficiency, and budget compliance.

[0105] In this embodiment, domain knowledge refers to expertise about the industry or field to which the project belongs, which helps to understand the background and potential problems of the project, including industry standards and best practices, competitor analysis, customer needs and market dynamics.

[0106] In this embodiment, dependency refers to how one variable affects or is affected by other variables. In an IT project, code quality (variable A) may depend on the experience of team members (variable B), that is, "the richer the team experience, the higher the code quality."

[0107] In this embodiment, the underlying historical data refers to data specific to the underlying classification, which is used to evaluate and analyze the performance of specific factors, variables or conditions in the success or failure of a project.

[0108] In this embodiment, the prior probability is a preliminary estimated probability of an event occurring based on underlying historical data and experience, without considering any new evidence. For example, in past projects, 80% of the time they were successfully implemented under specific conditions, so the prior probability of success can be preliminarily determined to be 0.8.

[0109] In this embodiment, likelihood probability refers to the probability of observing certain data under given conditions, which is used for parameter estimation and model evaluation. For example, if a certain project technology is given as A, and the underlying historical data shows that the success rate under this technology is 70%, then the likelihood probability of success for this technology can be expressed as 0.7.

[0110] In this embodiment, Where P(H|D) represents the posterior probability of observing that the relevant variable D is true when the relevant variable D is true; P(D|H) represents the likelihood probability of observing that the relevant variable D is true when the relevant variable H is true; P(H) represents the prior probability that the relevant variable H is true; It represents the likelihood of observing that the relevant variable D is true when the relevant variable H is false; represents the prior probability that the dependent variable H is false.

[0111] In this embodiment, the first threshold is set based on the underlying score distribution, and is used to screen out the underlying classifications with good performance and analyze the distribution of the underlying scores. For example, by drawing a histogram or calculating quantiles, a specific threshold (such as the 75% quantile) is set according to business needs or data distribution, indicating that classification scores above this value will be considered qualified.

[0112] In this embodiment, the bottom-level screening results are the bottom-level categories with scores higher than the threshold. For example, if the scores in the bottom-level categories are 90, 80, 85, and 60, and the threshold is set to 75, the screening results are 90, 80, and 85.

[0113] In this embodiment, the second threshold is used to screen the middle-level scores, evaluate the distribution of the middle-level classification scores and select the relevant threshold (such as using the 70% quantile). The middle-level screening results are the middle-level classification scores screened by the second threshold, indicating that the standards for further review are met. If the set middle-level scores (such as 80, 75, and 82) and the threshold is 78, the results are 80 and 82; the third threshold is used to screen the top-level scores, evaluate the distribution of the top-level classification scores, and set the corresponding threshold (such as using the 85% quantile). The top-level screening results are the top-level classification scores that are finally screened out, and their scores are higher than the preset third threshold. If the top-level classification scores are 90 and 83, and the set threshold is 85, the final result is 90.

[0114] In this embodiment, the scoring model is constructed by integrating the above processes and data to construct a scoring model including all scoring logics and screening logics, and a comprehensive scoring model is established by integrating the scoring results and screening results of each level of classification.

[0115] The working principle and beneficial effects of the above technical solution are: through an overall analysis of the current bid evaluation project, a project basic vector is generated to establish the overall goal, a model is established to determine the relevant variables of the underlying classification, and the dependencies between these variables are defined, the prior and likelihood probabilities are calculated through the underlying historical data, and the posterior probabilities are obtained, which are then converted into scores. Aggregation logic is used to perform threshold screening and hierarchical aggregation on the scores, and finally a comprehensive scoring model is constructed to realize automated processes to reduce manual intervention, accelerate the progress of the current bid evaluation project, and significantly save time, especially in the case of large-scale bidding, to achieve scientific and efficient current bid evaluation projects.

[0116] Embodiment 6:

[0117] The embodiment of the present invention provides an intelligent current bid evaluation project system based on multi-level scoring logic, an adjustment and update module, including:

[0118] Direction determination unit: determine the project characteristics according to the project basic vector, identify the first condition affecting the scoring model in combination with the overall goal and the project characteristics, classify the first condition based on the project characteristics, and extract the project history data of the same type of project as the current evaluation project to analyze the potential impact of the first condition, and obtain the possible adjustment direction of the first condition;

[0119] An updating unit: derives an adjustment condition based on the first condition and the possible adjustment direction, and adjusts and updates the scoring model.

[0120] In this embodiment, project characteristics refer to key information and features displayed during the project implementation process, usually including the project's scale, complexity, technical requirements, industry, resource allocation, time frame, etc. For example, the characteristics of an IT system implementation project may include: scale: involving multiple departments, and expected to take 10 months to complete; complexity: integrating multiple technology platforms, such as cloud computing and mobile applications; technical requirements: requiring the use of specific programming languages ​​and tools; industry: healthcare industry, with high requirements for data security and compliance.

[0121] In this embodiment, the first condition is considered to be a key factor affecting the scoring model during the evaluation process, and is directly related to the realization of project goals and the quality of scoring results. For example, in an IT project, the first condition may be "technical implementation capability."

[0122] In this embodiment, the project history data is comprehensive data related to a specific project, including the entire life cycle information of the project, including data of the planning, execution, monitoring and closing stages.

[0123] In this embodiment, possible adjustment directions are based on the analysis of the first condition, identifying areas or methods that can be improved or optimized. If the first condition is "technical implementation capability", possible adjustment directions may be to introduce new technologies or frameworks to improve system performance.

[0124] The working principle and beneficial effects of the above technical solution are: through an overall analysis of the current bid evaluation project, determining the project characteristics and combining them with the overall goals, identifying the first condition that affects the scoring model, and classifying the first condition, and analyzing the potential impact by extracting historical project data of similar projects, and deriving possible adjustment directions, generating specific adjustment conditions based on these adjustment directions, and further making necessary updates to the scoring model, thereby improving the scientificity and flexibility of the scoring model and better adapting to the complex and changing bidding environment.

[0125] Embodiment 7:

[0126] The embodiment of the present invention provides an intelligent current bid evaluation project system based on multi-level scoring logic, a prediction module, including:

[0127] Factor extraction unit: collects relevant historical bidding data and market trend information related to bidding, analyzes historical bidding data, and extracts key factors for success and failure;

[0128] Prediction determination unit: evaluates the first impact of different key factors on the bidding results, and at the same time, identifies the second impact of market trends on the success of the bidding, combines the first impact and the second impact to obtain the bidding success rate, uses machine learning algorithms to build a prediction model, and quantitatively evaluates the bidding success rate based on the prediction model, thereby predicting the future bidding success rate;

[0129] Strategy determination unit: Combine the future bidding success rate with the adjusted and updated scoring model to form a comprehensive evaluation framework, use the comprehensive evaluation framework to evaluate the pros and cons of different bidding schemes for the current evaluation project, and determine the bidding strategy.

[0130] In this embodiment, market trend information refers to data and analysis results that reflect market changes, consumer behavior, technological progress, competitive dynamics, etc., including changes in industry growth rates and market capacity consumer preferences, especially demands in the technology field (such as preference for cloud services).

[0131] In this embodiment, key factors refer to the main variables and conditions that affect success or failure in the bidding process. By identifying these factors, the competitiveness of the bidding proposal can be enhanced, including the technical advantages of the bidding proposal (such as innovative technical solutions).

[0132] In this embodiment, the first impact usually refers to the key factor that most directly and significantly affects the bidding results, such as the impact of differences in technical capabilities: if the technology provided by a bidding proposal far exceeds that of other bidders, this factor may be the key to winning the bid (such as using the latest technology).

[0133] In this embodiment, the second influence refers to a relatively minor factor, but it is also particularly important in affecting the bidding results, such as the impact of market trends. Economic uncertainty causes customers to prefer stable suppliers, which may indirectly affect the success rate of the bid.

[0134] In this embodiment, the comprehensive evaluation framework is a structured methodology or tool that aims to analyze and compare different bidding proposals by combining multiple evaluation dimensions, including evaluation of key factors, scoring models, and success rates. For example, the framework may include key success factors, market analysis, risk assessment, technical quality, etc.

[0135] The working principle and beneficial effects of the above technical solution are: by collecting and analyzing historical bidding data and market trends, identifying the key factors of success and failure, and the potential impact of market changes on bidding results, using statistical and machine learning algorithms to build a prediction model, quantitatively evaluate the probability of successful bidding, and identify risk factors, update the scoring model based on the prediction results and historical project data, and form a comprehensive evaluation framework to evaluate the pros and cons of different bidding schemes, thereby optimizing bidding strategies and ensuring the relevance and timeliness of current bid evaluation project standards.

[0136] Embodiment 8:

[0137] The embodiment of the present invention provides an intelligent current bid evaluation project method based on multi-level scoring logic, such as Figure 2 As shown, including:

[0138] Step 1: Analyze the application scenarios and target users, and define the top-level, middle-level, and bottom-level categories of the current bid evaluation project based on the analysis results;

[0139] Step 2: Conduct an overall analysis of the current bid evaluation project to obtain the overall goal and project basic vector, and set scoring logic and aggregation logic for the bottom-level classification, middle-level classification, and top-level classification based on the overall goal and project basic vector, and then build a scoring model;

[0140] Step 3: setting adjustment conditions according to the project basic vector, and adjusting and updating the scoring model based on the adjustment conditions;

[0141] Step 4: Based on the historical bidding data and market trend analysis, predict the future bidding success probability of the current evaluation project, and formulate a bidding strategy based on the adjusted and updated scoring model and the future bidding success probability.

[0142] The working principle and beneficial effects of the above technical solution are: through systematic top-to-bottom classification, combined with data analysis and market trends, it is possible to objectively quantify the current bid evaluation project standards and reduce the interference of subjective judgment. At the same time, the dynamic adjustment mechanism ensures that the scoring model adapts to the changing market environment, making it more flexible and applicable. The ability to predict the probability of successful bidding and potential risks will help bidding organizations make more informed decisions, thereby improving the success rate of bidding and the effectiveness of project implementation.

[0143] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An intelligent current bidding project evaluation system based on multi-level scoring logic, characterized in that: include: Hierarchical module: Analyze application scenarios and target users, and define the top-level classification, middle-level classification, and bottom-level classification of the current bid evaluation project based on the analysis results; Logical module: conducts an overall analysis of the current bid evaluation project, obtains the overall goal and the basic vector of the project, sets the scoring logic and aggregation logic for the bottom-level classification, middle-level classification and top-level classification based on the overall goal and the basic vector of the project, and then constructs a scoring model; Adjustment and update module: setting adjustment conditions according to the project basic vector, and adjusting and updating the scoring model based on the adjustment conditions; Prediction module: Based on the historical bidding data and market trend analysis, predict the future bidding success probability of the current evaluation project, and formulate a bidding strategy based on the adjusted and updated scoring model and the future bidding success probability.

2. According to claim 1, an intelligent current bidding project system based on multi-level scoring logic is characterized in that: Layered modules, including: Scenario analysis unit: collects industry information, determines the scoring standards for each industry based on the industry information, and at the same time, collects market information, determines the hot spots and pain points of the current bid evaluation project in the bidding based on the market information, and determines the scenario requirements according to the scoring standards and the hot spots and pain points; User analysis unit: clarifies the bidding roles, performs role background analysis on the bidding roles, and determines role requirements based on the background analysis results; Classification determination unit: Analyze the scenario requirements and role requirements, determine the main current bid evaluation project areas and key concerns, form a top-level classification, refine the top-level classification to obtain a middle-level classification, and refine each middle-level classification to obtain a bottom-level classification.

3. According to claim 2, an intelligent current bidding project evaluation system based on multi-level scoring logic is characterized in that: Classification determination unit, including: Demand analysis subunit: Analyze the relationship and demand priority between the scenario requirements and role requirements, identify the core requirements and secondary requirements, and determine the commonalities between the scenario requirements and role requirements; Field determination subunit: Determine the demand characteristics corresponding to the core demand and the secondary demand based on the common points of the demand, and determine the current bid evaluation project field according to the demand characteristics, determine the field importance of the current bid evaluation project field from the project field table, combine the field importance with the demand priority, classify the current bid evaluation project field, and then determine the main current bid evaluation project field.

4. According to claim 3, an intelligent current bidding evaluation project system based on multi-level scoring logic is characterized in that: The classification determination unit further includes: Framework subunit: refine the main current bid evaluation project areas to determine the key concerns, and design a classification framework based on the main current bid evaluation project areas and key concerns; Hierarchical classification subunit: Determine the scoring target of the top-level classification based on the classification framework, and determine the top-level classification according to the scoring target, subdivide the scoring target based on the classification framework to obtain scoring factors, determine the middle-level classification according to the scoring factors, obtain scoring indicators based on the subdivision of the scoring factors, and determine the bottom-level classification according to the scoring indicators.

5. According to claim 1, the intelligent current bidding evaluation project system based on multi-level scoring logic is characterized in that: Logic module, including: Overall target determination unit: performs overall analysis on the current bid evaluation project, generates a project basic vector, and obtains the overall target based on the project basic vector; Model unit: determining the relevant variables of the underlying classification according to the overall goal, obtaining the domain knowledge of the field to which the current bid evaluation project belongs, and defining the dependency relationship between the relevant variables based on the project basic vector; Scoring logic unit: collects underlying historical data related to the underlying classification, determines the prior probability of each relevant variable based on the underlying historical data, and determines the likelihood probability of each relevant variable based on the dependency relationship between the relevant variables, determines the posterior probability of the corresponding relevant variable based on the prior probability and the likelihood probability, converts the posterior probability into the score of the corresponding relevant variable, and uses the maximum score among the relevant variables as the corresponding underlying classification score. Similarly, obtains the scores of each middle-level classification and top-level classification; Aggregation logic unit: construct a bottom-level score distribution according to the bottom-level classification scores, set a first threshold based on the bottom-level score distribution, filter the bottom-level classification scores higher than the first threshold from the bottom-level classification, obtain the bottom-level screening results, aggregate the bottom-level screening results to the middle-level classification, similarly, set a second threshold to obtain the middle-level screening results, aggregate the middle-level screening results to the top-level classification, set a third threshold to obtain the top-level screening results, and aggregate the top-level screening results into the current bid evaluation project score; Scoring model unit: integrates the contents of the scoring logic unit and the aggregation logic unit to build a scoring model.

6. According to claim 4, an intelligent current bidding evaluation project system based on multi-level scoring logic is characterized in that: Adjust the update module, including: Direction determination unit: determine the project characteristics according to the project basic vector, identify the first condition affecting the scoring model in combination with the overall goal and the project characteristics, classify the first condition based on the project characteristics, and extract the project history data of the same type of project as the current evaluation project to analyze the potential impact of the first condition, and obtain the possible adjustment direction of the first condition; An updating unit: derives an adjustment condition based on the first condition and the possible adjustment direction, and adjusts and updates the scoring model.

7. The intelligent current bidding evaluation project system based on multi-level scoring logic according to claim 6 is characterized in that: Prediction module, including: Factor extraction unit: collects relevant historical bidding data and market trend information related to bidding, analyzes historical bidding data, and extracts key factors for success and failure; Prediction determination unit: evaluates the first impact of different key factors on the bidding results, and at the same time, identifies the second impact of market trends on the success of the bidding, combines the first impact and the second impact to obtain the bidding success rate, uses machine learning algorithms to build a prediction model, and quantitatively evaluates the bidding success rate based on the prediction model, thereby predicting the future bidding success rate; Strategy determination unit: Combine the future bidding success rate with the adjusted and updated scoring model to form a comprehensive evaluation framework, use the comprehensive evaluation framework to evaluate the pros and cons of different bidding schemes for the current evaluation project, and determine the bidding strategy.

8. An intelligent current bid evaluation project method based on multi-level scoring logic, characterized in that: include: Step 1: Analyze the application scenarios and target users, and define the top-level, middle-level, and bottom-level categories of the current bid evaluation project based on the analysis results; Step 2: Conduct an overall analysis of the current bid evaluation project to obtain the overall goal and project basic vector, and set scoring logic and aggregation logic for the bottom-level classification, middle-level classification, and top-level classification based on the overall goal and project basic vector, and then build a scoring model; Step 3: setting adjustment conditions according to the project basic vector, and adjusting and updating the scoring model based on the adjustment conditions; Step 4: Based on the historical bidding data and market trend analysis, predict the future bidding success probability of the current evaluation project, and formulate a bidding strategy based on the adjusted and updated scoring model and the future bidding success probability.

Images