Intelligent bid evaluation method and device based on big data analysis

Abstract

The invention discloses an intelligent bid evaluation method and device based on big data analysis. The method comprises the steps of obtaining a bid invitation demand information set and a bidding scheme index set; the bid invitation demand information set comprises a priority value, an index type value, an index demand value, a standard value and a lower limit value of each demand index; the bidding scheme index set comprises bidding scheme information; the bidding scheme information comprises a capability value of each technical index and an index importance ranking vector; the element of the index importance ranking vector is the serial number of the technical index; preprocessing the bid invitation demand information set and the bidding scheme index set to obtain a to-be-evaluated bid information set; and performing bid evaluation processing on the information set to be subjected to bid evaluation to obtain optimal bid scheme information.

Description

Technical Field

[0001] The present invention relates to the fields of bidding and procurement technology and data processing, and in particular to an intelligent bid evaluation method and device based on big data analysis. Background Art

[0002] In today's business activities and project construction, bidding is a common and important way to allocate resources and select cooperation. With the continuous expansion of the scale of various projects, the increasing complexity of technical requirements, and the gradual increase in the number of entities participating in bidding, traditional bid evaluation methods face many challenges. On the one hand, bidding requirements often cover indicators in multiple dimensions. These indicators not only differ in importance, but also have different types (such as technical indicators, service indicators, cost indicators, etc.). Traditional methods are difficult to accurately quantify and consider these complex and diverse indicators in a comprehensive and reasonable manner. On the other hand, there are a large number of bidding proposals. When manually screening, evaluating and comparing them, the workload is huge and easily affected by subjective factors. As a result, the evaluation results may not be objective and fair. It is also difficult to efficiently and accurately locate the optimal solution that truly meets the core needs of the tenderer and performs well in all aspects from the massive number of solutions.

[0003] Data analytics technology has developed rapidly in recent years, with various industries actively exploring how to leverage big data analytics to unlock the value behind data and drive more scientific and rational business decisions. However, in the bidding and tendering sector, the full integration of data analytics into the bid evaluation process to achieve intelligent, efficient, and accurate bid evaluation remains a challenge and has yet to be fully implemented or widely adopted.

[0004] Based on the above background, there is an urgent need for an intelligent bid evaluation method that can leverage the advantages of big data analysis to comprehensively, objectively and efficiently evaluate and screen bidding proposals, thereby accurately finding the optimal bidding proposal to meet the needs of increasingly complex bidding activities. Summary of the Invention

[0005] The present invention mainly solves the problem of how to comprehensively, objectively and efficiently evaluate and screen bidding proposals based on the advantages of big data analysis, so as to accurately find the optimal bidding proposal through an intelligent bidding evaluation method. The present invention discloses an intelligent bidding evaluation method and device based on big data analysis.

[0006] In a first aspect, an embodiment of the present invention discloses an intelligent bid evaluation method based on big data analysis, comprising:

[0007] S1, obtaining a set of bidding requirement information and a set of bidding scheme indicators; the bidding requirement information set includes a priority value, indicator type value, indicator requirement value, standard value, and lower limit value of each requirement indicator; the bidding scheme indicator set includes bidding scheme information; the bidding scheme information includes an indicator importance ranking vector and a capability value of each technical indicator; the elements of the indicator importance ranking vector are serial numbers of the technical indicators;

[0008] S2, pre-processing the bidding requirement information set and the bidding scheme indicator set to obtain a bid evaluation information set;

[0009] S3, performing bid evaluation on the set of information to be evaluated to obtain the optimal bidding solution information.

[0010] The pre-processing of the bidding requirement information set and the bidding scheme indicator set to obtain the information set to be evaluated includes:

[0011] S21, performing data cleaning processing on the bidding requirement information set and the bidding scheme indicator set to obtain a first data set;

[0012] S22, performing category discrimination processing on the first data set to obtain a second data set;

[0013] S23: Perform boundary checking on the second data set to obtain a set of information to be evaluated.

[0014] The step of performing bid evaluation on the bid evaluation information set to obtain optimal bidding solution information includes:

[0015] S31, screening the set of information to be evaluated to obtain a first bidding scheme indicator set;

[0016] S32, performing an indicator ranking and evaluation process on the first bidding scheme indicator set to obtain an indicator matching evaluation value for each bidding scheme information;

[0017] S33, performing an indicator performance evaluation process on the first bidding scheme indicator set to obtain an indicator performance evaluation value for each bidding scheme information;

[0018] S34, performing fusion evaluation processing on the indicator performance evaluation values and indicator matching evaluation values of all bidding scheme information to obtain the optimal bidding scheme information.

[0019] The filtering process of the set of information to be evaluated to obtain a first set of bidding scheme indicators includes:

[0020] S311, performing indicator compliance judgment on each bidding scheme information in the bidding scheme indicator set in the bid evaluation information set to obtain a corresponding first judgment result;

[0021] S312: Delete the bidding scheme information for which the first judgment result is negative from the bidding scheme indicator set of the information set to be evaluated, and obtain a first bidding scheme indicator set.

[0022] The step of performing indicator ranking and evaluation processing on the first bidding scheme indicator set to obtain an indicator matching evaluation value for each bidding scheme information includes:

[0023] S321, performing index ranking calculation on the bidding requirement information set in the to-be-evaluated information set to obtain an index ranking vector;

[0024] S322 , performing a matching calculation on the indicator ranking vector and the indicator importance ranking vector of the bidding scheme information of the first bidding scheme indicator set to obtain an indicator matching evaluation value of the bidding scheme information.

[0025] The step of performing index ranking calculation on the bidding requirement information set in the bid evaluation information set to obtain an index ranking vector includes:

[0026] S3211, normalizing all priority values in the bidding requirement information set in the bid evaluation information set to obtain a normalized priority value;

[0027] S3212, quantifying and assigning values to all indicator type values in the bidding requirement information set in the bid evaluation information set to obtain corresponding task coefficients;

[0028] S3213, performing importance calculation on each demand indicator in the bidding demand information set in the bid evaluation information set to obtain a corresponding importance value;

[0029] S3214 , based on the importance values of all demand indicators, perform descending processing on the serial numbers of all demand indicators in the bidding demand information set to obtain an indicator ranking vector.

[0030] The expression for the matching calculation is:

[0031]

[0032] Among them, ma is the indicator matching evaluation value of a bidding scheme information, conv represents the convolution operation, β i and α iRepresent the indicator ranking vector and the i-th element of the indicator importance ranking vector of the bidding scheme information of the first bidding scheme indicator set respectively, α and β represent the indicator importance ranking vector and the indicator ranking vector respectively, and M is an element of the indicator ranking vector.

[0033] In a second aspect of an embodiment of the present invention, an intelligent bid evaluation device based on big data analysis is disclosed, the device comprising:

[0034] a memory storing executable program code;

[0035] a processor coupled to the memory;

[0036] The processor calls the executable program code stored in the memory to execute the intelligent bid evaluation method based on big data analysis.

[0037] In a third aspect of an embodiment of the present invention, a computer-storable medium is disclosed, wherein the computer-storable medium stores computer instructions. When the computer instructions are called by a computer, they are used to execute the intelligent bid evaluation method based on big data analysis.

[0038] In a fourth aspect of an embodiment of the present invention, an information data processing terminal is disclosed, which is used to implement the intelligent bid evaluation method based on big data analysis.

[0039] The beneficial effects of the present invention are:

[0040] This invention systematically preprocesses the bidding requirements information set and the bidding proposal indicator set, including steps such as data cleaning, category identification, and boundary checking. This removes impurities from the data, accurately identifies data categories, and ensures that the data meets established boundary requirements. On this basis, all subsequent bid evaluation steps are based on strict calculation and evaluation rules, avoiding the subjective arbitrariness that can easily arise in manual bid evaluation. This makes the entire bid evaluation process and final results more objective and fair, ensuring the fairness of bidding activities.

[0041] During the bid evaluation process, the present invention first screens bid proposals for compliance, eliminating those that fail to meet basic requirements. Subsequently, the bidding requirements information set is ranked by indicators, and then a matching calculation is performed with the indicator importance ranking vector of the bid proposal information to obtain an indicator matching evaluation value for each bid proposal. This series of operations accurately measures the degree of fit between the bid proposal and the tenderer's requirements, ensuring that the optimal bid proposal selected can best meet the tenderer's expectations across all key indicators, thereby improving the matching degree between project implementation and expectations.

[0042] This invention not only considers indicator matching but also further performs an indicator performance evaluation on the bidding proposal information. This comprehensively considers the performance of the bidding proposal in actual implementation from multiple dimensions, and integrates the indicator performance evaluation value and the indicator matching evaluation value into an evaluation process. This comprehensive evaluation method can comprehensively and comprehensively analyze the advantages and disadvantages of the bidding proposal, avoiding the situation where only a single factor is focused on while ignoring other important aspects. It helps to screen out bidding proposals that truly perform well in all aspects and have good feasibility and expected benefits. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 4 is an implementation flow chart of the method of the present invention. DETAILED DESCRIPTION

[0044] In order to better understand the content of the present invention, an embodiment is given here.

[0045] Figure 1 4 is an implementation flow chart of the method of the present invention.

[0046] In a first aspect, an embodiment of the present invention discloses an intelligent bid evaluation method based on big data analysis, comprising:

[0047] S1, obtaining a set of bidding requirement information and a set of bidding scheme indicators; the set of bidding requirement information includes a priority value, indicator type value, indicator requirement value, standard value, and lower limit value of each requirement indicator; the set of bidding scheme indicators includes bidding scheme information; the bidding scheme information includes a capability value and an indicator importance ranking vector for each technical indicator; the elements of the indicator importance ranking vector are serial numbers of the technical indicators;

[0048] The indicator importance ranking vector is obtained by arranging the serial numbers of all technical indicators in descending order according to the preset estimated importance value of each technical indicator. The indicator importance ranking vector is the serial number of the technical indicator with the largest estimated importance value.

[0049] S2, pre-processing the bidding requirement information set and the bidding scheme indicator set to obtain a bid evaluation information set;

[0050] S3, performing bid evaluation on the set of information to be evaluated to obtain the optimal bidding solution information.

[0051] By accurately selecting the optimal bidding proposal, the present invention enables the tendering party's resources to be reasonably allocated to the bidder that is most capable and best meets the needs, avoiding the waste of resources on inappropriate project undertaking entities. At the same time, it also allows bidders that truly have advantages and strengths to have more opportunities to obtain projects, thereby promoting the optimal allocation of resources within the entire industry and promoting the healthy and efficient development of the industry.

[0052] The pre-processing of the bidding requirement information set and the bidding scheme indicator set to obtain the information set to be evaluated includes:

[0053] S21, performing data cleaning processing on the bidding requirement information set and the bidding scheme indicator set to obtain a first data set;

[0054] S22, performing category discrimination processing on the first data set to obtain a second data set;

[0055] S23, performing boundary check processing on the second data set to obtain a set of information to be evaluated;

[0056] The step of performing bid evaluation on the bid evaluation information set to obtain optimal bidding solution information includes:

[0057] S31, screening the set of information to be evaluated to obtain a first bidding scheme indicator set;

[0058] S32, performing an indicator ranking and evaluation process on the first bidding scheme indicator set to obtain an indicator matching evaluation value for each bidding scheme information;

[0059] S33, performing an indicator performance evaluation process on the first bidding scheme indicator set to obtain an indicator performance evaluation value for each bidding scheme information;

[0060] S34, performing fusion evaluation processing on the indicator performance evaluation values and indicator matching evaluation values of all bidding scheme information to obtain the optimal bidding scheme information.

[0061] The filtering process of the set of information to be evaluated to obtain a first set of bidding scheme indicators includes:

[0062] Performing an indicator compliance judgment on each bidding scheme information in the bidding scheme indicator set in the bid evaluation information set to obtain a corresponding first judgment result;

[0063] The bidding scheme information for which the first judgment result is negative is deleted from the bidding scheme indicator set of the information set to be evaluated to obtain a first bidding scheme indicator set.

[0064] The indicator compliance judgment is to judge whether the capability value of each technical indicator in the bidding scheme information is all greater than the lower limit value of the corresponding demand indicator. If all are satisfied, the first judgment result is confirmed to be yes; if not all are satisfied, the first judgment result is confirmed to be no;

[0065] The non-fulfillment means that there is a capability value of a technical indicator that is not greater than the lower limit value of the corresponding demand indicator.

[0066] The step of performing indicator ranking and evaluation processing on the first bidding scheme indicator set to obtain an indicator matching evaluation value for each bidding scheme information includes:

[0067] S321, performing index ranking calculation on the bidding requirement information set in the to-be-evaluated information set to obtain an index ranking vector;

[0068] S322 , performing a matching calculation on the indicator ranking vector and the indicator importance ranking vector of the bidding scheme information of the first bidding scheme indicator set to obtain an indicator matching evaluation value of the bidding scheme information.

[0069] The bidding requirement information set and the bidding scheme indicator set can be obtained by performing text recognition on the bidding technical requirement document and the bidding scheme document respectively.

[0070] The step of performing index ranking calculation on the bidding requirement information set in the bid evaluation information set to obtain an index ranking vector includes:

[0071] S3211, normalizing all priority values in the bidding requirement information set in the bid evaluation information set to obtain a normalized priority value;

[0072] S3212, quantifying and assigning values to all indicator type values in the bidding requirement information set in the bid evaluation information set to obtain corresponding task coefficients;

[0073] S3213, performing importance calculation on each demand indicator in the bidding demand information set in the bid evaluation information set to obtain a corresponding importance value;

[0074] S3214 , based on the importance values of all demand indicators, perform descending processing on the serial numbers of all demand indicators in the bidding demand information set to obtain an indicator ranking vector.

[0075] The expression for the matching calculation is:

[0076]

[0077] Among them, ma is the indicator matching evaluation value of a bidding scheme information, conv represents the convolution operation, β i and α i Represent the indicator ranking vector and the i-th element of the indicator importance ranking vector of the bidding scheme information of the first bidding scheme indicator set respectively, α and β represent the indicator importance ranking vector and the indicator ranking vector respectively, and M is an element of the indicator ranking vector.

[0078] The expression for the matching calculation compares the corresponding elements of the indicator ranking vector with the bid proposal's indicator importance ranking vector, highlighting the degree of difference between the two using an exponential function. When the ratio of the corresponding elements of the two vectors deviates significantly from 1, the value of the exponential function increases significantly, emphasizing the importance of this difference in the evaluation. This enables the evaluation to keenly capture the match between the bid proposal's indicator importance ranking and the bidding requirements, avoiding potential risks caused by ranking differences.

[0079] The introduction of convolution further considers the overall similarity and correlation between two vectors. It not only focuses on the differences in individual elements, but also assesses the degree of match between the two vectors from a structural perspective. This approach can more comprehensively reflect the consistency between the bid proposal and the bidding requirements in terms of the importance ranking of indicators, avoiding the limitations of simple element-based comparisons and improving the accuracy and reliability of the assessment.

[0080] The indicator matching evaluation value ma, ultimately obtained through the summation operation, provides a quantitative measure of the degree of match between the bid proposal and the tender requirements. This value can be easily used to compare different bid proposals, making the bid evaluation process more objective and fair, and helping to quickly select the bid proposal that best matches the tender requirements based on the indicator importance ranking.

[0081] The first element of the indicator ranking vector is the serial number of the demand indicator with the largest importance value; the last element of the indicator ranking vector is the serial number of the demand indicator with the smallest importance value.

[0082] The demand indicators and technical indicators with the same serial numbers are the same.

[0083] The normalization process includes: for the priority A of the i-th demand indicator i , and its normalized priority value is recorded as Among them, A max and A min Respectively represent the upper and lower limits of the priority value range;

[0084] The quantitative assignment of the indicator type value is to assign a corresponding quantitative value to each indicator type value according to a preset indicator type assignment set; the indicator type assignment set includes the quantitative value of each indicator type value;

[0085] The expression for calculating the importance is:

[0086]

[0087] Among them, κ iis the importance value of the i-th demand indicator, ω1, ω2 and ω3 are the preset first weight coefficient, second weight coefficient and third weight coefficient respectively, a i is the normalized priority value of the i-th demand indicator, γ i is the quantized value of the i-th indicator type value, ψ0 i and ψl i are the standard value and lower limit value of the i-th indicator type value respectively.

[0088] The bidding requirement information set includes the priority value, indicator type value, indicator requirement value, standard value and lower limit value of each requirement indicator; the bidding scheme indicator set includes bidding scheme information; the bidding scheme information includes the capability value of each technical indicator and the indicator importance ranking vector; the elements of the indicator importance ranking vector are the serial numbers of the technical indicators;

[0089] The step of performing an indicator performance evaluation process on the first bidding scheme indicator set to obtain an indicator performance evaluation value for each bidding scheme information includes:

[0090] Constructing a technical indicator vector based on the capability values of all technical indicators of each bidding scheme information in the first bidding scheme indicator set;

[0091] Constructing a demand vector using the indicator demand values of all demand indicators in the bidding demand information set;

[0092] Using the standard values of all demand indicators in the bidding demand information set, a standard vector is constructed;

[0093] Calculate the absolute value of the difference between the standard vector and the technical indicator vector to obtain the first difference vector cy1;

[0094] Perform a first difference calculation on the demand vector and the technical indicator vector to obtain a second difference vector cy2;

[0095] performing statistical processing on the first difference vector to obtain a mean, variance, and median value of the first difference vector;

[0096] performing statistical processing on the second difference vector to obtain a median value and a mode value of the second difference vector;

[0097] Performing technical feature extraction processing on the first difference vector and the second difference vector to obtain a technical feature value set; the technical feature value set includes first to sixth technical feature values;

[0098] The expression for the technical feature extraction process is:

[0099] tz1 i=VMD(cy1 i 2 cy2 i 3 ),

[0100] tz2 i =SVMD(cy1 i 2 cy2 i 3 ),

[0101] tz3 i =VMD(cy1 i 3 cy2 i 4 ),

[0102] tz4 i =SVMD(cy1 i 3 cy2 i 4 ),

[0103] tz5 i =VMD(cy1 i 4 cy2 i 3 ),

[0104] tz6 i =SVMD(cy1 i 4 cy2 i 3 ),

[0105] Among them, VMD and SVMD represent variational mode decomposition and successive variational mode decomposition, respectively, tz1 i to tz6 i are the i-th elements of the first to sixth technical characteristic values, cy1 i and cy2 i are the i-th element of the first difference vector and the second difference vector respectively;

[0106] Performing evaluation vector calculation on the technical feature value set to obtain an evaluation vector;

[0107] The technical feature extraction process, which processes the first and second difference vectors through variational mode decomposition (VMD) and successive variational mode decomposition (SVMD), can deeply explore the difference characteristics between technical indicators and bidding requirements. VMD and SVMD are advanced signal processing techniques that can decompose complex difference signals into components of different modes, each representing a specific frequency characteristic or pattern. By analyzing these components, richer and more representative technical feature values can be extracted, thereby providing a more comprehensive understanding of the bidding proposal's performance in terms of technical indicators.

[0108] In the expression used for technical feature extraction, six distinct technical feature values were obtained by performing VMD and SVMD on the difference vectors of different power combinations. This multi-dimensional feature extraction method can reflect the discrepancies between technical indicators and bidding requirements from different perspectives, including the magnitude, trend, and frequency distribution of the discrepancies. By comprehensively considering these multi-dimensional feature values, the technical performance of bid proposals can be more accurately assessed, avoiding the one-sidedness of relying solely on a single feature, and improving the accuracy and reliability of bid evaluation results.

[0109] The expression for calculating the evaluation vector is:

[0110]

[0111] Among them, jlb i represents the i-th element of the evaluation vector, v1 to v3 represent the mean, variance, and median values of the first difference vector, respectively, and v4 to v5 represent the median and mode values of the second difference vector, respectively;

[0112] The evaluation vectors are jointly quantified and calculated to obtain an indicator performance evaluation value of the bidding scheme information.

[0113] The expression of the joint quantization calculation is:

[0114]

[0115] Among them, zbp is the performance evaluation value of a bidding scheme information, zjl k is the kth element of the intermediate evaluation vector, jlb i is the i-th element of the evaluation vector, and N is the length of the intermediate evaluation vector.

[0116] The expression of the first difference calculation process is:

[0117]

[0118] Among them, xq i and zb iThe i-th element of the demand vector and the technical indicator vector, cy2 i is the i-th element of the second difference vector.

[0119] The absolute value calculation process of the difference is to subtract the elements of corresponding serial numbers in the two vectors and calculate the absolute value to obtain the corresponding elements in the first difference vector.

[0120] The category discrimination process is to discriminate the attributes of each data in the data set, to determine whether the attributes are consistent with the preset attributes, and to delete the inconsistent data from the data set.

[0121] The data cleaning process includes filling missing values, smoothing noise data, and smoothing or deleting outliers. Smoothing noise data involves first identifying noise data and then smoothing it based on the preceding and following data. Noise data is defined as values that are less than the sensor's sensitivity or greater than the sensor's upper limit. Kalman filtering can be used to identify outliers. The value to fill missing values can be determined by averaging the measured values within a certain sampling interval before and after the missing value.

[0122] The performing boundary check processing on the second data set to obtain the information set to be evaluated includes:

[0123] For each type of data attribute of the second data set, using data collection information of the data as a known independent variable and data values of the data as a known dependent variable, constructing a curve to be approximated using the known independent variables and the known dependent variables;

[0124] Performing curve fitting on the curve to be approximated using a function approximation method to obtain an optimal consistent approximation polynomial for the class data attribute;

[0125] Using the optimal consistent approximation polynomial, calculating and processing the known independent variables to obtain approximate dependent variables;

[0126] Determine whether the absolute value of the difference between the approximate dependent variable and the corresponding known dependent variable is greater than a set first regression discrimination threshold; if it is greater than the first regression discrimination threshold, delete the data from the second data set; if it is less than or equal to the first regression discrimination threshold, do not process the data;

[0127] Performing fusion processing on all data of the second data set after boundary checking to obtain a set of information to be evaluated;

[0128] The curve fitting for the curve to be approximated by using a function approximation method may be performed using an optimal consistent linear approximation method.

[0129] The data collection information is collection time information.

[0130] In a second aspect of an embodiment of the present invention, an intelligent bid evaluation device based on big data analysis is disclosed, the device comprising:

[0131] a memory storing executable program code;

[0132] a processor coupled to the memory;

[0133] The processor calls the executable program code stored in the memory to execute the intelligent bid evaluation method based on big data analysis.

[0134] In a third aspect of an embodiment of the present invention, a computer-storable medium is disclosed, wherein the computer-storable medium stores computer instructions. When the computer instructions are called by a computer, they are used to execute the intelligent bid evaluation method based on big data analysis.

[0135] In a fourth aspect of an embodiment of the present invention, an information data processing terminal is disclosed, which is used to implement the intelligent bid evaluation method based on big data analysis.

[0136] The foregoing is merely an embodiment of the present invention and is not intended to limit the present invention. It will be apparent to those skilled in the art that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention are intended to be included within the scope of the claims of the present invention.

Claims

1. An intelligent bid evaluation method based on big data analysis, characterized in that: include: S1, obtaining a set of bidding requirement information and a set of bidding scheme indicators; the set of bidding requirement information includes a priority value, indicator type value, indicator requirement value, standard value, and lower limit value of each requirement indicator; the set of bidding scheme indicators includes bidding scheme information; the bidding scheme information includes an indicator importance ranking vector and a capability value of each technical indicator; The elements of the indicator importance ranking vector are the serial numbers of the technical indicators; S2, pre-processing the bidding requirement information set and the bidding scheme indicator set to obtain a bid evaluation information set; S3, performing bid evaluation on the set of information to be evaluated to obtain the optimal bidding solution information.

2. The intelligent bid evaluation method based on big data analysis according to claim 1, characterized in that: The pre-processing of the bidding requirement information set and the bidding scheme indicator set to obtain the information set to be evaluated includes: S21, performing data cleaning processing on the bidding requirement information set and the bidding scheme indicator set to obtain a first data set; S22, performing category discrimination processing on the first data set to obtain a second data set; S23: Perform boundary checking on the second data set to obtain a set of information to be evaluated.

3. The intelligent bid evaluation method based on big data analysis according to claim 1, characterized in that: The step of performing bid evaluation on the bid evaluation information set to obtain optimal bidding solution information includes: S31, screening the set of information to be evaluated to obtain a first bidding scheme indicator set; S32, performing an indicator ranking and evaluation process on the first bidding scheme indicator set to obtain an indicator matching evaluation value for each bidding scheme information; S33, performing an indicator performance evaluation process on the first bidding scheme indicator set to obtain an indicator performance evaluation value for each bidding scheme information; S34, performing fusion evaluation processing on the indicator performance evaluation values and indicator matching evaluation values of all bidding scheme information to obtain the optimal bidding scheme information.

4. The intelligent bid evaluation method based on big data analysis according to claim 3 is characterized in that: The filtering process of the set of information to be evaluated to obtain a first set of bidding scheme indicators includes: S311, performing indicator compliance judgment on each bidding scheme information in the bidding scheme indicator set in the bid evaluation information set to obtain a corresponding first judgment result; S312: Delete the bidding scheme information for which the first judgment result is negative from the bidding scheme indicator set of the information set to be evaluated, and obtain a first bidding scheme indicator set.

5. The intelligent bid evaluation method based on big data analysis according to claim 3 is characterized in that: The step of performing indicator ranking and evaluation processing on the first bidding scheme indicator set to obtain an indicator matching evaluation value for each bidding scheme information includes: S321, performing index ranking calculation on the bidding requirement information set in the to-be-evaluated information set to obtain an index ranking vector; S322 , performing a matching calculation on the indicator ranking vector and the indicator importance ranking vector of the bidding scheme information of the first bidding scheme indicator set to obtain an indicator matching evaluation value of the bidding scheme information.

6. The intelligent bid evaluation method based on big data analysis according to claim 5 is characterized in that: The step of performing index ranking calculation on the bidding requirement information set in the bid evaluation information set to obtain an index ranking vector includes: S3211, normalizing all priority values in the bidding requirement information set in the bid evaluation information set to obtain a normalized priority value; S3212, quantifying and assigning values to all indicator type values in the bidding requirement information set in the bid evaluation information set to obtain corresponding task coefficients; S3213, performing importance calculation on each demand indicator in the bidding demand information set in the bid evaluation information set to obtain a corresponding importance value; S3214 , based on the importance values of all demand indicators, perform descending processing on the serial numbers of all demand indicators in the bidding demand information set to obtain an indicator ranking vector.

7. The intelligent bid evaluation method based on big data analysis according to claim 6, characterized in that: The expression for the matching calculation is: Among them, ma is the indicator matching evaluation value of a bidding scheme information, conv represents the convolution operation, β i and α i Represent the indicator ranking vector and the i-th element of the indicator importance ranking vector of the bidding scheme information of the first bidding scheme indicator set respectively, α and β represent the indicator importance ranking vector and the indicator ranking vector respectively, and M is an element of the indicator ranking vector.

8. An intelligent bidding evaluation device based on big data analysis, characterized in that: The device comprises: a memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the intelligent bid evaluation method based on big data analysis as described in any one of claims 1 to 7.

9. A computer storable medium, characterized in that The computer storable medium stores computer instructions, which, when called by a computer, are used to execute the intelligent bid evaluation method based on big data analysis as described in any one of claims 1 to 7.

10. An information data processing terminal, characterized in that: The information data processing terminal is used to implement the intelligent bid evaluation method based on big data analysis as described in any one of claims 1 to 7.

Images