Big data-based bidding and tendering auxiliary decision-making method and system

Abstract

The invention relates to the technical field of big data risk control, in particular to a bidding and tendering aid decision-making method and system based on big data, comprising a data layer, a core function layer and a user interaction layer, the data layer comprises a big data resource library, an enterprise database and a rule library, the big data resource library is used for storing historical bidding data and industry market prices, and the enterprise database is used for storing enterprise market prices; quotation items are divided into changeable fees and specified fees through labels in a quotation table in the rule base, and the rule base comprises a threshold setting rule and a scoring weight rule. Malicious quotation and abnormal quotation schemes are identified through big data analysis and a machine learning algorithm, risk points are marked, early warning is provided, the multi-dimensional scoring and weight optimization module dynamically adjusts scoring standards according to project types, rationality and competitiveness of the quotation schemes are ensured, the decision process of an enterprise is optimized, and the enterprise quality is improved. The bid winning rate is improved; and the potential risk in project implementation is reduced.

Description

Technical Field

[0001] The present invention relates to the field of big data risk control technology, and in particular to a bidding and tendering decision-making auxiliary method and system based on big data. Background Art

[0002] Bidding is a form of comprehensive economic responsibility system to promote competition in the field of infrastructure construction. Generally, several construction units participate in the project bidding. The bidding unit (construction unit) selects the best candidates. Whoever has a short construction period, low cost, high quality and good reputation will be awarded the project task. The construction unit and the contracting unit sign a contract, which is a one-stop contract to the end and organized in a turnkey manner. The organizational procedures and work links of China's bidding and contracting system mainly include preparing bidding documents, determining the bid price, conducting bidding and signing the project contracting contract.

[0003] Announcement No. CN114066186A A bidding risk early warning system and method based on cloud computing includes a risk assessment system, a bidding management system, an Internet cloud, and a user terminal and a display terminal connected to the risk assessment system and the bidding management system. The present invention obtains first data and second data, performs data analysis on the first data and the second data, obtains and displays risk assessment results, and comprehensively gives early warning information by performing a two-way assessment on investment unit users and design unit users, thereby reducing the risk of bidding.

[0004] The above system conducts a comprehensive evaluation of investment unit users and design unit users through a two-way evaluation mechanism, and combines cloud computing technology to achieve efficient data processing and sharing, thereby effectively reducing the risks in the bidding process. However, the existing system mainly focuses on the evaluation of the design stage and user behavior, but lacks in-depth research on the rationality of bidding quotation schemes, detection of malicious quotations, and dynamic optimization. The existing system does not fully consider the weight distribution requirements of various project types for various costs in the quotation scheme, and cannot dynamically adjust the scoring criteria to adapt to complex bidding scenarios.

[0005] In order to solve the above problems, the present invention proposes a risk warning method and system based on big data, which realizes the automatic generation of bids, the generation and screening of dynamic quotation schemes, the detection of malicious quotations, and multi-dimensional scoring and weight optimization through intelligent technology, thereby significantly improving the efficiency and risk warning capabilities of the bidding process. Summary of the invention

[0006] To achieve the above objectives, the present invention proposes a bidding decision-making auxiliary method and system based on big data, comprising the following steps: Step 1: Preparation of bid documents and classification of quotation items. Combined with the quotation sheet issued by the tenderer and based on its own tendering plan, the bid documents are prepared and classified into modifiable costs and stipulated costs according to the quotation items in the quotation sheet; Step 2: Compare the generation of the bid documents, change the price budget of the proposed bidding plan, adjust the changeable costs on the quotation sheet, set the adjustment range, and make adjustments according to the principle of randomness; Step 3: Comparative bidding screening: According to the type of bidding project, local project costs are collected in combination with big data, and the comparative bidding documents are compared with them and the difference ratio is calculated. By setting the threshold range, the quotation schemes outside the threshold range are screened out, and the remaining quotation schemes are selected, numbered, and randomly screened; Step 4: Score the generated different schemes, combine the bidding quotation content in the big data, generate different quotation systems for different quotation schemes, divide the weights in the quotation schemes according to the bidding items, and score the rationality of the price; Step 5: Provide a comprehensive plan, score the different quotation plans generated, and generate the scores together with the quotation plan.

[0007] In one example, in the calculation of the difference ratio in step 3, F1 represents the price quoted in the comparison bid, and F2 represents the cost in the big data. The calculation formula is If the difference ratio is within the threshold, it is within the range where quotation can be made. If the difference ratio exceeds or is lower than the threshold, it means that the quotation in this aspect is within the unreasonable range.

[0008] In one example, a preliminary screening of data is required before the formula calculation in step three. When the price quoted in the quotation proposal is far lower than the market price, there is suspicion of malicious quotation.

[0009] In one example, the quotation items in the quotation plan in step 4 are divided into the proportion of machinery quotation, the proportion of labor cost quotation and the competitiveness of total price, among which the proportion of machinery quotation and labor cost quotation are combined into the quotation proportion, and weights are assigned according to demand.

[0010] In one example, the mechanical quotation proportion score formula in step 4 is: , the labor cost quotation proportion score formula is: , the total price competitiveness score formula is: , add up the calculated scores to get the final score.

[0011] In one example, a bidding assistance system based on big data includes a data layer, a core function layer and a user interaction layer. The user interaction layer displays the comparison of quotation schemes, the distribution of difference ratios, and the score rankings, and highlights unreasonable cost items.

[0012] In one example, the data layer includes a big data resource library, an enterprise database, and a rule library. The big data resource library is used to store historical bidding data and industry market prices. The rule library divides quotation items into modifiable fees and specified fees through labels in the quotation table, and the rule library includes threshold setting rules and scoring weight rules.

[0013] In one example, the core functional layer includes a tender intelligent generation and classification module, a dynamic quotation scheme generation module, a quotation rationality verification and screening module, and a multi-dimensional scoring and weight optimization module.

[0014] In one example, the intelligent tender generation and classification module uses optical character recognition and natural language processing to extract structured data, the dynamic quotation scheme generation module makes random adjustments to changeable costs and generates random floating values ​​for each adjustable cost item, and the quotation rationality verification and screening module is divided into difference ratio calculation and threshold verification, malicious quotation detection, random screening and grouping.

[0015] In one example, in the multidimensional scoring and weight optimization module, the system needs to integrate business rules, data support and algorithm models to achieve dynamic scoring and weight allocation, data support system, industry benchmark database and project feature library. The project feature library stores different types of scoring weight templates. The computing engine uses Apache Spark to process multidimensional scoring calculations for large-scale quotation solutions and dynamically loads weight templates according to project type or user input.

[0016] The bidding and tendering decision-making assistance method and system based on big data proposed by the present invention can bring the following beneficial effects: 1. The present invention generates bids in an automated and intelligent manner, dynamically adjusts quotation schemes, and combines big data for rationality verification and scoring optimization. The automated process significantly reduces the time and error rate of manual operations. At the same time, a dynamic quotation scheme generation module is used to quickly generate multiple quotation schemes, helping enterprises to complete complex quotation preparation work in a short time and improve bidding efficiency.

[0017] 2. The present invention uses big data analysis and machine learning algorithms to identify malicious quotations and abnormal quotation schemes, mark risk points and provide early warnings. The multi-dimensional scoring and weight optimization module dynamically adjusts the scoring criteria according to the project type to ensure the rationality and competitiveness of the quotation scheme, thereby optimizing the company's decision-making process, improving the winning rate and reducing potential risks in project implementation. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings: Figure 1 A method flow chart of a bidding and tendering decision-making assistance method and system based on big data; Figure 2 This is a schematic diagram of the system architecture of a bidding and tendering decision-making assistance method and system based on big data. DETAILED DESCRIPTION

[0019] In order to more clearly illustrate the overall concept of the present invention, a detailed description is given below in an exemplary manner in conjunction with the accompanying drawings.

[0020] In the description of the present invention, it is necessary to understand that the terms "center", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "axial", "radial", "circumferential" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present invention.

[0021] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0022] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection, an electrical connection, or a communication; it can be a direct connection, or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0023] In the present invention, unless otherwise clearly specified and limited, the first feature "on" or "under" the second feature may be that the first and second features are in direct contact, or the first and second features are in indirect contact through an intermediate medium. In the description of this specification, the description with reference to the terms "one scheme", "some schemes", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the scheme or example are included in at least one scheme or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same scheme or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more schemes or examples in a suitable manner.

[0024] like Figure 1 to Figure 2 As shown, the present invention proposes a bidding decision-making auxiliary method and system based on big data, comprising the following steps: Step 1: Preparation of bids and classification of quotation items. Combined with the quotation sheet issued by the tenderer, the bid is prepared according to its own tendering plan, and the quotation items in the quotation sheet are classified into changeable costs and prescribed costs. Changeable costs are costs that can be adjusted based on the company's own situation, such as project construction costs, material costs, etc. Prescribed costs are items that cannot be changed in the entire process, such as fees and taxes. Taxes are generated by combining various costs through a fixed tax rate and cannot be changed.

[0025] Step 2: Compare the generation of the bid documents, change the price budget of the proposed bidding plan, adjust the changeable costs on the quotation sheet, set the adjustment range, and make adjustments based on the principle of randomness. For example, the adjustment range is between -20% and 20%, where a negative percentage indicates a downward adjustment to the quotation, and a positive percentage indicates an upward adjustment to the quotation. Under the adjustment of price fluctuations, different bidding quotation plans are given.

[0026] Step 3: Compare the selection of bid documents. According to the type of project being bid, collect local project costs in combination with big data, such as the cost of consumables such as steel and wood in construction, compare the bid documents with them and calculate the difference ratio. The calculation formula is: , where F1 represents the price quoted in the bid, F2 represents the cost in the big data, and a threshold is set. The threshold is set to ensure that the difference ratio is within the threshold and belongs to the range where the quotation can be made. If the difference ratio exceeds or is lower than the difference ratio, it means that the quotation in this aspect is unreasonable. Before the formula is calculated, preliminary screening of data is required. For example, in some procurement plans, the purchase price in the quotation plan is much lower than the market price in the big data. At this time, it means that there is a suspicion of malicious quotation. That is, when F1-F2 is a negative number, the larger the calculated difference ratio is, the greater the gap with the existing price in the big data, and the greater the suspicion of malicious quotation; By setting the threshold range, the bidding schemes outside the threshold range are screened out, and the bidding schemes with malicious bids are screened out; Select the remaining quotation proposals, number them, and perform random screening. You can use random screening software to screen and retain the screened quotation proposals. The screening operation can be performed multiple times, and the multiple screening results can be grouped as a preliminary control group.

[0027] Step 4: Score the different generated plans, combine the bidding quotation content in the big data, generate different quotation systems for different quotation plans, divide the weights in the quotation plans according to the bidding projects, and score the reasonableness of the prices. For example, in a construction system with a high degree of mechanization, the weight of the machinery quotation is higher than the weight of labor costs. Therefore, the proportion of machinery quotation in the weight assignment needs to be higher than the proportion of labor costs. In projects that rely on manual construction, such as during construction.

[0028] The quotation items in the quotation plan are divided into the proportion of machinery quotation, the proportion of labor cost quotation and the competitiveness of total price. The proportion of machinery quotation and labor cost quotation are combined into the quotation proportion, and weights are assigned according to the demand. When greater competition is needed in terms of price, the weight of total price competitiveness will be increased. When competition is needed in the quotation proportion, the weight of quotation proportion will be increased. Then, the machinery quotation and labor cost quotation will be weighted according to their bidding projects, so as to set different comparison databases.

[0029] For example, in a bidding project with a high degree of mechanization, the proportion of machinery quotation is assigned to 60%, the proportion of labor cost quotation is assigned to 30%, and the total price competitiveness is assigned to 10. The calculation formulas for each item are: Machinery quotation ratio:

[0030] Labor cost quotation ratio:

[0031] Total price competitiveness:

[0032] Add up the calculated scores to give the final total score.

[0033] Step 5: Provide a comprehensive plan, score the different quotation plans generated, and generate the scores together with the quotation plan for the quotation party to review, so that the quotation party can modify the unreasonable aspects of the quotation plan.

[0034] The big data risk early warning system includes data layer, core function layer and user interaction layer.

[0035] The data layer includes a big data resource library, an enterprise database, and a rule library. The big data resource library is used to store historical bidding data, industry market prices, such as the prices of consumables such as steel, wood, and machinery, and regional economic indicators. Regional economic indicators mainly store human resource wages within the region, tax policies, which are used to calculate taxes and fees in quotations, and a rule library. The rule library divides quotation items into modifiable fees and specified fees through labels in the quotation table, and the rule library includes threshold setting rules and scoring weight rules.

[0036] The core functional layer includes the intelligent tender generation and classification module, the dynamic quotation scheme generation module, the quotation rationality verification and screening module, and the multi-dimensional scoring and weight optimization module.

[0037] The intelligent tender document generation and classification module uses optical character recognition and natural language processing to extract structured data (such as cost item name, unit, and quantity), identify key fields (such as "fees", "taxes", and "construction costs"), mark them as prescribed costs or changeable costs, match historical templates based on the rule engine, fill in the current bidding data, automatically generate a draft tender document, mark adjustable cost items (such as material costs and labor costs), and provide a visual interface that allows users to manually adjust the cost item classification (such as changing a "prescribed cost" to "changeable").

[0038] The dynamic quotation scheme generation module makes random adjustments to the changeable costs and generates a random floating value for each adjustable cost item. The formula is: , supporting tiered adjustments such as "material cost reduction ≤10%, labor cost increase ≤15%".

[0039] The quotation rationality verification and screening module is divided into difference ratio calculation and threshold verification, malicious quotation detection, random screening and grouping. The difference ratio formula is used in the difference ratio calculation: The difference ratio is calculated and a dynamic threshold is set. Solutions that exceed the threshold are marked as abnormal.

[0040] Malicious quotation detection calculates the deviation ratio between the bid price and the market benchmark price, sets a threshold to determine anomalies, and uses isolation forest or Z-Score analysis. Isolation forest quickly separates abnormal points by constructing "isolated trees" (abnormal points are easy to be isolated because they are rare and have large differences). The quotation difference ratio, historical quotation volatility, etc. are used as features, and the isolation forest model is trained using historical normal quotation data to output anomaly scores (0~1). The closer the score is to 1, the higher the possibility of anomaly. Quotations that are significantly lower than the market price are identified. The quotation for a certain material is 40% lower than the market average price, and the system prompts "risk of malicious low pricing."

[0041] Random screening and grouping, using a pseudo-random number algorithm (such as the Mersenne Twister algorithm), randomly sample the verified solutions (such as selecting 20%) to generate multiple groups of preliminary control groups (Groups A / B / C).

[0042] In the multi-dimensional scoring and weight optimization module, the system needs to integrate business rules, data support and algorithm models to achieve dynamic scoring and weight allocation, data support system, industry benchmark database and project feature library. The project feature library stores different types of scoring weight templates. The calculation engine uses Apache Spark to process multi-dimensional scoring calculations for large-scale quotation solutions and dynamically loads weight templates according to project type or user input.

[0043] The user interaction layer displays the comparison of quotation schemes, distribution of difference ratios, and rating rankings, highlights unreasonable cost items, and uses ECharts or D3.js to generate interactive bar charts and radar charts to compare the total price, sub-item costs (machinery, labor, materials), difference ratios, ratings, etc. of multiple quotation schemes side by side. It supports drag-and-drop sorting, sorting by total price / rating / difference ratio, and clicking on the scheme card to expand details (such as a comparison chart of sub-item quotations and industry benchmarks).

[0044] The degree of deviation between each sub-item quotation and the market price is displayed with a color gradient (red means too high, green means reasonable, and blue means too low). For example, if the quotation for a certain material is 25% lower than the market price → the dark blue block is highlighted and marked with "Risk: suspected malicious low price".

[0045] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0046] The above description is only an embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent substitution, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of the claims of the present invention.

Claims

1. A bidding decision-making assistance method based on big data, characterized by: The following steps are involved: Step 1: Preparation of bid documents and classification of quotation items. Combined with the quotation sheet issued by the tenderer and based on its own tendering plan, the bid documents are prepared and classified into modifiable costs and stipulated costs according to the quotation items in the quotation sheet; Step 2: Compare the generation of the bid documents, change the price budget of the proposed bidding plan, adjust the changeable costs on the quotation sheet, set the adjustment range, and make adjustments according to the principle of randomness; Step 3: Comparative bidding screening: According to the type of bidding project, local project costs are collected in combination with big data, and the comparative bidding documents are compared with them and the difference ratio is calculated. By setting the threshold range, the quotation schemes outside the threshold range are screened out, and the remaining quotation schemes are selected, numbered, and randomly screened; Step 4: Score the generated different schemes, combine the bidding quotation content in the big data, generate different quotation systems for different quotation schemes, divide the weights in the quotation schemes according to the bidding items, and score the rationality of the price; Step 5: Provide a comprehensive plan, score the different quotation plans generated, and generate the scores together with the quotation plan.

2. The bidding and tendering decision-making auxiliary method based on big data according to claim 1 is characterized by: In the calculation of the difference ratio in step 3, F1 represents the price quoted in the comparison bid, and F2 represents the cost in the big data. The calculation formula is If the difference ratio is within the threshold, it belongs to the reasonable quotation range. If the difference ratio exceeds or is lower than the threshold, it means that the quotation in this aspect is within the unreasonable range.

3. The bidding and tendering decision-making auxiliary method based on big data according to claim 2 is characterized by: Before calculating the formula in step three, a preliminary screening of data is required. When the price quoted in the quotation proposal is lower than the market price, there is suspicion of malicious quotation.

4. The bidding and tendering decision-making auxiliary method based on big data according to claim 1 is characterized by: The quotation items in the quotation plan in step 4 are divided into the proportion of machinery quotation, the proportion of labor cost quotation and the competitiveness of total price, among which the proportion of machinery quotation and labor cost quotation are combined into the quotation proportion, and weights are assigned according to demand.

5. The bidding and tendering decision-making auxiliary method based on big data according to claim 4 is characterized by: The mechanical quotation proportion score formula in step 4 is: , the labor cost quotation proportion score formula is: , the total price competitiveness score formula is: , add up the calculated scores to get the final score.

6. A bidding and tendering auxiliary system based on big data for executing 1 to 5, characterized in that: It includes data layer, core function layer and user interaction layer. The user interaction layer displays quotation scheme comparison, difference ratio distribution, score ranking, and highlights unreasonable cost items.

7. The bidding and tendering auxiliary system based on big data according to claim 6 is characterized by: The data layer includes a big data resource library, an enterprise database and a rule library. The big data resource library is used to store historical bidding data and industry market prices. The rule library divides the quotation items into modifiable fees and specified fees through labels in the quotation table, and the rule library includes threshold setting rules and scoring weight rules.

8. The bidding and tendering auxiliary system based on big data according to claim 6 is characterized by: The core functional layer includes a tender intelligent generation and classification module, a dynamic quotation scheme generation module, a quotation rationality verification and screening module, and a multi-dimensional scoring and weight optimization module.

9. The bidding and tendering auxiliary system based on big data according to claim 8 is characterized in that: The intelligent tender generation and classification module uses optical character recognition and natural language processing to extract structured data. The dynamic quotation scheme generation module makes random adjustments to changeable costs and generates random floating values ​​for each adjustable cost item. The quotation rationality verification and screening module is divided into difference ratio calculation and threshold verification, malicious quotation detection, random screening and grouping.

10. The bidding and tendering auxiliary system based on big data according to claim 8, characterized in that: In the multidimensional scoring and weight optimization module, the system needs to integrate business rules, data support and algorithm models to achieve dynamic scoring and weight allocation, data support system, industry benchmark database and project feature library. The project feature library stores different types of scoring weight templates. The computing engine uses Apache Spark to process multidimensional scoring calculations for large-scale quotation solutions and dynamically loads weight templates according to project types.

Images