Intelligent bid evaluation system and method for bidding and tendering

Abstract

The invention relates to the technical field of bidding and tendering, and particularly discloses an intelligent bid evaluation system and method for bidding and tendering, and the system comprises a data processing module which is used for obtaining to-be-evaluated data, and determining the field type of the to-be-evaluated data according to the keyword of the to-be-evaluated data; the model establishing module is used for determining a bid evaluation standard of the to-be-evaluated data according to the field type to which the to-be-evaluated data belongs; the identity confirmation module is used for acquiring identity information of bid evaluation personnel and setting bid evaluation weights of the bid evaluation personnel according to the identity information of the bid evaluation personnel; and the bid evaluation supervision module is used for acquiring the bid evaluation score of the bid evaluation personnel on the to-be-evaluated data, determining the bid evaluation deviation level of the bid evaluation personnel according to the bid evaluation weight and the bid evaluation score, and supervising the bid evaluation result according to the bid evaluation deviation level of the bid evaluation personnel. According to the method, a rich and accurate scoring standard is provided for the to-be-bid-invitation data, and meanwhile, the bid evaluation efficiency and fairness of bidding and tendering can be effectively improved by calculating the deviation level of the bid evaluation result.

Description

Technical Field

[0001] The present application relates to the technical field of bidding and tendering, and more specifically, to an intelligent bid evaluation system and method for bidding and tendering. Background Art

[0002] Electronic bidding is a bidding activity completed in the form of data telegrams. In layman's terms, it means partially or completely abandoning paper documents and completing bidding activities with the help of computers and the Internet. The electronic bidding system provides technologies such as electronic bid documents, digital certificate encryption and decryption, and computer-assisted bid opening / evaluation. It fully realizes the electronicization and computer-assisted bid evaluation of qualification bids, technical bids, and commercial bids, supports electronic sign-in, bid failure processing, and bid winning lock, supports electronic bid evaluation reports and bidding digital files, greatly improving the efficiency of bidding and saving bidding costs.

[0003] At present, there are many intelligent bid evaluation technologies that have been implemented in the domestic electronic bidding industry, such as anonymous bidding evaluation system, intelligent assisted bid evaluation, electronic bidding system, etc. However, the existing intelligent bid evaluation technology cannot realize the full process supervision of the entire bidding process, the evaluation workload is large and the efficiency is low, the evaluation results lack objectivity and fairness, and the data accuracy cannot be effectively guaranteed. Comprehensive intelligent bid evaluation technology is a major barrier to my country's electronic bidding industry, and it has increased a lot of manpower and costs for bidding companies. Summary of the invention

[0004] The present invention provides an intelligent bid evaluation system and method for bidding, which is used to solve the problem that the bid evaluation technology in the prior art lacks objectivity and fairness and the accuracy of data cannot be effectively guaranteed, including:

[0005] A data processing module is used to obtain the bid evaluation data and determine the field type of the bid evaluation data according to the keywords of the bid evaluation data;

[0006] A model building module is used to determine the evaluation criteria of the data to be evaluated according to the field type to which the data to be evaluated belongs;

[0007] The identity confirmation module is used to obtain the identity information of the bid evaluators and set the bid evaluation weights of the bid evaluators according to their identity information;

[0008] The bid evaluation supervision module is used to obtain the bid evaluation scores of the bid evaluators on the bid evaluation data, determine the bid evaluation deviation level of the bid evaluators according to the bid evaluation weights and the bid evaluation scores, and supervise the bid evaluation results according to the bid evaluation deviation level of the bid evaluators.

[0009] Furthermore, the data processing module is used for:

[0010] Obtain the bid evaluation data, perform word segmentation on the bid evaluation data, and extract keywords from the bid evaluation data;

[0011] The keywords of the bid evaluation data are vectorized, and the vectorized keywords are clustered based on the k-means clustering algorithm to obtain the central keywords;

[0012] A domain knowledge base is established, the cosine similarity between the central keyword and the keyword in the domain knowledge base is calculated, the keywords in the domain knowledge base whose cosine similarity with the central keyword is greater than a first preset threshold are screened out, and the domain type corresponding to the keyword in the domain knowledge base whose cosine similarity with the central keyword is greater than the first preset threshold is determined as the domain type to which the data to be evaluated belongs.

[0013] Furthermore, the extracting of keywords of the bid evaluation data includes:

[0014] Obtain the word segmentation of the bid evaluation data after word segmentation processing, establish a bid evaluation keyword knowledge base, and determine the keywords of the bid evaluation data segmentation according to the bid evaluation keyword knowledge base;

[0015] The frequencies of occurrence of the keywords of the data to be evaluated are counted, the frequencies of occurrence of the keywords of the data to be evaluated are sorted, and the keywords of the data to be evaluated with preset positions are determined as the keywords of the data to be evaluated according to the sorting results.

[0016] Furthermore, clustering the vectorized keywords based on the k-means clustering algorithm includes:

[0017] A keyword data set is established based on the keyword vector after vectorization, and k initial clustering centers of the keyword data set are randomly selected;

[0018] Calculate the Euclidean distance between the keyword vector in the keyword data set and the initial cluster center, and divide the keyword vector into corresponding partitions according to the Euclidean distance between the keyword vector in the keyword data set and the initial cluster center;

[0019] Calculate the average value of the keyword vectors in each partition, and recalculate the cluster center based on the average value of the keyword vectors in each partition;

[0020] Repeat the above steps until the cluster center no longer changes or the number of iterations reaches the maximum number of iterations, and obtain k final cluster centers.

[0021] Furthermore, the model building module is used to:

[0022] Obtain historical bid evaluation standard data and corresponding field types, pre-process the historical bid evaluation standard data and corresponding field types, and obtain a bid evaluation data set;

[0023] A bid evaluation standard model is established based on the bid evaluation data set, and the field type of the current bid evaluation data is input into the bid evaluation standard model to obtain the corresponding bid evaluation standard.

[0024] Furthermore, establishing a bid evaluation standard model based on the bid evaluation data set includes:

[0025] Conduct exploratory data analysis on the bid evaluation data set to obtain the bid evaluation data set after data analysis;

[0026] Perform feature extraction based on the bid evaluation data set after data analysis to obtain quantitative features of the bid evaluation criteria;

[0027] A bid evaluation standard model is constructed according to the quantitative characteristics of the bid evaluation standard, and the bid evaluation standard model is trained to obtain a trained bid evaluation standard model.

[0028] Furthermore, the identity confirmation module is used to:

[0029] Obtain the identity information of the bid evaluators, and set the corresponding roles of the bid evaluators according to their identity information;

[0030] Determine the initial weight according to the corresponding role of the bid evaluator, obtain the historical bid evaluation data of the bid evaluator, and calculate the bid evaluation data curve of the bid evaluator based on the historical bid evaluation data of the bid evaluator;

[0031] Obtaining a preset standard curve for bid evaluation data, and calculating the standard deviation between the bid evaluation data curve of the bid evaluators and the preset standard curve for bid evaluation data;

[0032] The weight calculation formula is set according to the standard deviation between the bid evaluation data curve of the bid evaluation personnel and the preset bid evaluation data standard curve, and the bid evaluation weight of the bid evaluation personnel is determined according to the weight calculation formula. The weight calculation formula is specifically as follows:

[0033]

[0034] Among them, W is the evaluation weight of the evaluator, W r is the initial weight, S is the standard deviation between the bid evaluation data curve of the bid evaluator and the preset bid evaluation data standard curve, and T is the preset range coefficient.

[0035] Furthermore, the bid evaluation and supervision module is used to:

[0036] Obtain the bid evaluation scores of the bid evaluation personnel for the bid evaluation data, calculate the difference between the bid evaluation scores of the bid evaluation personnel for the bid evaluation data and the preset bid evaluation qualified value, and obtain the bid evaluation deviation of the bid evaluation personnel;

[0037] The bid evaluation deviation of the bid evaluation personnel is normalized to obtain the normalized bid evaluation deviation;

[0038] The normalized bid evaluation deviation is weightedly summed according to the weights of all bid evaluation personnel to obtain the deviation calculation result, and the bid evaluation deviation level of the bid evaluation personnel is determined based on the deviation calculation result.

[0039] Furthermore, the step of determining the bid evaluation deviation level of the bid evaluation personnel according to the deviation calculation result includes:

[0040] Calculate the difference between the deviation calculation result and the preset deviation tolerance value, and determine whether the difference between the deviation calculation result and the preset deviation tolerance value is greater than a second preset threshold;

[0041] If the difference between the deviation calculation result and the preset deviation tolerance value is greater than the second preset threshold, the first level is set as the bid evaluation deviation level of the bid evaluation personnel;

[0042] If the difference between the calculated deviation result and the preset deviation tolerance value is less than or equal to the second preset threshold, then determining whether the difference between the calculated deviation result and the preset deviation tolerance value is greater than a third preset threshold;

[0043] If the difference between the deviation calculation result and the preset deviation tolerance value is greater than the third preset threshold, the second level is set as the bid evaluation deviation level of the bid evaluation personnel;

[0044] If the difference between the deviation calculation result and the preset deviation tolerance value is less than or equal to the third preset threshold value, the third level is set as the evaluation deviation level of the evaluator.

[0045] In order to achieve the above object, the present invention also provides an intelligent bid evaluation method for bidding, comprising:

[0046] Obtain the data to be evaluated, and determine the field type to which the data to be evaluated belongs based on the keywords of the data to be evaluated;

[0047] Determine the bid evaluation criteria for the bid evaluation data according to the field to which the bid evaluation data belongs;

[0048] Obtain the identity information of the bid evaluators, and set the bid evaluation weights of the bid evaluators according to their identity information;

[0049] Obtain the evaluation scores of the bid evaluators on the bid evaluation data, determine the evaluation deviation level of the bid evaluators according to the evaluation weights and the evaluation scores, and supervise the evaluation results according to the evaluation deviation level of the bid evaluators.

[0050] The beneficial effects of the present invention are:

[0051] By applying the above technical scheme, the present invention analyzes the type of field to which the bid evaluation data belongs, sets different bid evaluation criteria based on different types of bid evaluation data, can be quickly adjusted according to the needs of different industries and projects, adapts to various bid evaluation scenarios, ensures the standardization and consistency of bid evaluation work, and at the same time, by calculating the bid evaluation deviation level of the evaluators, can enhance the trust of all parties in the bid evaluation results, improve the overall reputation of the bidding industry, and ensure the bid evaluation efficiency and fairness of the bidding. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0053] Figure 1 The overall structure diagram of an intelligent bidding evaluation system for bidding proposed in an embodiment of the present invention is shown;

[0054] Figure 2 A schematic diagram of a process flow of an intelligent bid evaluation method for bidding proposed in an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0055] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0056] The present application embodiment provides an intelligent bidding evaluation system for bidding, such as Figure 1 As shown, including:

[0057] The data processing module is used to obtain the data to be evaluated and determine the type of field to which the data to be evaluated belongs based on the keywords of the data to be evaluated; the model building module is used to determine the evaluation criteria for the data to be evaluated based on the type of field to which the data to be evaluated belongs; the identity confirmation module is used to obtain the identity information of the evaluators and set the evaluation weights of the evaluators based on their identity information; the evaluation supervision module is used to obtain the evaluation scores of the evaluators for the data to be evaluated, determine the evaluation deviation levels of the evaluators based on the evaluation weights and scores, and supervise the evaluation results based on the evaluation deviation levels of the evaluators.

[0058] In this embodiment, by establishing an intelligent bid evaluation system, the bid evaluation criteria for the bid evaluation data can be automatically generated. The evaluators evaluate and score according to the automatically generated bid evaluation criteria. The evaluation results are supervised by counting the evaluation scores of the evaluators, which can effectively ensure the bid evaluation efficiency and fairness of the bidding.

[0059] In some embodiments of the present application, the data processing module is used to: obtain the data to be evaluated, perform word segmentation on the data to be evaluated, and extract keywords of the data to be evaluated; perform vectorization processing on the keywords of the data to be evaluated, and cluster the vectorized keywords based on the k-means clustering algorithm to obtain central keywords; establish a domain knowledge base, calculate the cosine similarity between the central keyword and the keywords in the domain knowledge base, screen out the keywords in the domain knowledge base whose cosine similarity with the central keyword is greater than a first preset threshold, and determine the domain type corresponding to the keywords in the domain knowledge base whose cosine similarity with the central keyword is greater than the first preset threshold as the domain type to which the data to be evaluated belongs.

[0060] In this embodiment, the jieba word segmentation tool is used to perform word segmentation on the bid evaluation data and stop words are filtered out, the keywords after word segmentation are vectorized to obtain keyword vectors, and the keyword vectors are clustered to obtain the central keyword of each cluster partition. The field type to which the bid evaluation data belongs is obtained by calculating the cosine similarity between the central keyword and the keywords in the field knowledge base.

[0061] In some embodiments of the present application, the extracting of keywords of the data to be evaluated includes: obtaining the segmentation of the data to be evaluated after segmentation processing, establishing a bid evaluation keyword knowledge base, and determining the keywords of the segmentation of the data to be evaluated based on the bid evaluation keyword knowledge base; counting the frequency of occurrence of the keywords of the segmentation of the data to be evaluated in the data to be evaluated, sorting the frequency of occurrence of the keywords of the segmentation of the data to be evaluated in the data to be evaluated, and determining the keywords of the segmentation of the data to be evaluated with a preset position as the keywords of the data to be evaluated according to the sorting result.

[0062] In this embodiment, the frequencies of occurrence of the keywords of the data to be evaluated are counted in the data to be evaluated, and the top 10 keywords of the data to be evaluated are extracted from high to low according to the ranking results of the frequencies, so as to obtain the keywords of the data to be evaluated.

[0063] In some embodiments of the present application, the k-means clustering algorithm is used to cluster the vectorized keywords, including: establishing a keyword data set based on the vectorized keyword vectors, and randomly selecting k initial clustering centers of the keyword data set; calculating the Euclidean distance from the keyword vector in the keyword data set to the initial clustering center, and dividing the keyword vector into corresponding partitions according to the Euclidean distance from the keyword vector in the keyword data set to the initial clustering center; calculating the average value of the keyword vector in each partition, and recalculating the clustering center according to the average value of the keyword vector in each partition; and repeatedly iterating the above steps until the clustering center no longer changes or the number of iterations reaches the maximum number of iterations, and obtaining k final clustering centers.

[0064] In this embodiment, the k value is set to 10, and the vectorized keywords are clustered based on the k-means clustering algorithm to obtain 10 cluster partitions and the corresponding final cluster centers, and the keyword closest to the final cluster center is set as the central keyword of the cluster partition.

[0065] In some embodiments of the present application, the model building module is used to: obtain historical bid evaluation standard data and the corresponding field types, pre-process the historical bid evaluation standard data and the corresponding field types to obtain a bid evaluation data set; establish a bid evaluation standard model based on the bid evaluation data set, input the field type of the current data to be evaluated into the bid evaluation standard model, and obtain the corresponding bid evaluation standard.

[0066] In this embodiment, data cleaning is performed on historical bid evaluation standard data and the corresponding field types to which they belong, to obtain a high-quality bid evaluation data set, and a bid evaluation standard model is established based on the bid evaluation data set, thereby obtaining the bid evaluation standards corresponding to the field type to which the current data to be evaluated belongs.

[0067] In some embodiments of the present application, establishing a bid evaluation criteria model based on a bid evaluation data set includes: performing exploratory data analysis on the bid evaluation data set to obtain the bid evaluation data set after data analysis; performing feature extraction on the bid evaluation data set after data analysis to obtain quantitative features of the bid evaluation criteria; constructing a bid evaluation criteria model based on the quantitative features of the bid evaluation criteria, and training the bid evaluation criteria model to obtain a trained bid evaluation criteria model.

[0068] In this embodiment, a bid evaluation criteria model is established based on a deep learning neural network model, and the bid evaluation criteria model is trained through the quantitative characteristics of the bid evaluation criteria of the bid evaluation data set to obtain a trained bid evaluation criteria model, and the bid evaluation criteria corresponding to the field type to which the current data to be evaluated belongs are determined through the trained bid evaluation criteria model.

[0069] In some embodiments of the present application, the identity confirmation module is used to: obtain the identity information of the bid evaluator, set the role corresponding to the bid evaluator according to the identity information of the bid evaluator; determine the initial weight according to the role corresponding to the bid evaluator, obtain the historical bid evaluation data of the bid evaluator, and calculate the bid evaluation data curve of the bid evaluator based on the historical bid evaluation data of the bid evaluator; obtain the preset bid evaluation data standard curve, and calculate the standard deviation of the bid evaluation data curve of the bid evaluator and the preset bid evaluation data standard curve; set the weight calculation formula according to the standard deviation of the bid evaluation data curve of the bid evaluator and the preset bid evaluation data standard curve, and determine the bid evaluation weight of the bid evaluator according to the weight calculation formula, and the weight calculation formula is specifically as follows:

[0070]

[0071] Among them, W is the evaluation weight of the evaluator, W r is the initial weight, S is the standard deviation between the evaluation data curve of the evaluator and the preset evaluation data standard curve, and T is the preset range coefficient.

[0072] In this embodiment, the role corresponding to the identity information of the evaluator is determined through the role mapping table of the evaluators and the initial weight corresponding to the role is obtained. The evaluation data curve of the evaluators reflects the distribution of the historical evaluation scores of the evaluators. The evaluation weight of the evaluators is obtained by calculating the standard deviation of the evaluation data curve of the evaluators and the corresponding data of the preset evaluation data standard curve.

[0073] In some embodiments of the present application, the bid evaluation supervision module is used to: obtain the bid evaluation scores of the bid evaluators for the bid evaluation data, calculate the difference between the bid evaluation scores of the bid evaluators for the bid evaluation data and the preset bid evaluation qualified value, and obtain the bid evaluation deviation of the bid evaluators; normalize the bid evaluation deviation of the bid evaluators to obtain the normalized bid evaluation deviation; multiply the normalized bid evaluation deviation by the bid evaluation weight of the bid evaluators to obtain the deviation calculation result, and determine the bid evaluation deviation level of the bid evaluators according to the deviation calculation result.

[0074] In some embodiments of the present application, determining the bid evaluation deviation level of the bid evaluator based on the deviation calculation result includes: calculating the difference between the deviation calculation result and the preset deviation tolerance value, and judging whether the difference between the deviation calculation result and the preset deviation tolerance value is greater than a second preset threshold value; if the difference between the deviation calculation result and the preset deviation tolerance value is greater than the second preset threshold value, setting the first level as the bid evaluation deviation level of the bid evaluator; if the difference between the deviation calculation result and the preset deviation tolerance value is less than or equal to the second preset threshold value, judging whether the difference between the deviation calculation result and the preset deviation tolerance value is greater than a third preset threshold value; if the difference between the deviation calculation result and the preset deviation tolerance value is greater than the third preset threshold value, setting the second level as the bid evaluation deviation level of the bid evaluator; if the difference between the deviation calculation result and the preset deviation tolerance value is less than or equal to the third preset threshold value, setting the third level as the bid evaluation deviation level of the bid evaluator.

[0075] In this embodiment, the deviation calculation result is obtained by multiplying the normalized evaluation deviation by the evaluation weight of the bid evaluator. The corresponding bid evaluation deviation level is determined by the difference between the deviation calculation result and the preset deviation tolerance value. The larger the difference between the deviation calculation result and the preset deviation tolerance value, the higher the corresponding bid evaluation deviation level. When the bid evaluation deviation level of the bid evaluator is the first level, the abnormal bid evaluation score of the bid evaluator is uploaded to the supervisor, who cancels the bid evaluation qualification of the bid evaluator to achieve supervision of the bid evaluation results.

[0076] Based on the same technical concept, see Figure 2 As shown, the present invention also provides an intelligent bid evaluation method for bidding, comprising:

[0077] S101, obtaining data to be evaluated, and determining the field type to which the data to be evaluated belongs according to keywords of the data to be evaluated;

[0078] S102, determining the bid evaluation criteria of the bid evaluation data according to the field type to which the bid evaluation data belongs;

[0079] S103, obtaining the identity information of the bid evaluators, and setting the bid evaluation weights of the bid evaluators according to the identity information of the bid evaluators;

[0080] S104, obtaining the bid evaluation scores of the bid evaluation personnel for the bid evaluation data, determining the bid evaluation deviation level of the bid evaluation personnel according to the bid evaluation weight and the bid evaluation score, and supervising the bid evaluation results according to the bid evaluation deviation level of the bid evaluation personnel.

[0081] In order to further explain the technical idea of ​​the present invention, the technical solution of the present invention is now described in combination with specific application scenarios.

[0082] By applying the above technical scheme, the present invention includes a data processing module for obtaining data to be evaluated, and determining the type of field to which the data to be evaluated belongs according to the keywords of the data to be evaluated; a model building module for determining the bid evaluation criteria of the data to be evaluated according to the type of field to which the data to be evaluated belongs; an identity confirmation module for obtaining the identity information of the bid evaluators, and setting the bid evaluation weights of the bid evaluators according to the identity information of the bid evaluators; a bid evaluation supervision module for obtaining the bid evaluation scores of the bid evaluation personnel on the data to be evaluated, determining the bid evaluation deviation level of the bid evaluation personnel according to the bid evaluation weights and the bid evaluation scores, and supervising the bid evaluation results according to the bid evaluation deviation levels of the bid evaluation personnel. The present invention provides rich and accurate scoring criteria for the data to be tendered, and at the same time, by calculating the deviation level of the bid evaluation results, it can effectively improve the bid evaluation efficiency and fairness of bidding.

[0083] Through the description of the above implementation methods, those skilled in the art can clearly understand that the present invention can be implemented by hardware, or by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present invention can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each implementation scenario of the present invention.

[0084] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application 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 cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. An intelligent bidding evaluation system for bidding, characterized in that: include: A data processing module is used to obtain the bid evaluation data and determine the field type of the bid evaluation data according to the keywords of the bid evaluation data; A model building module is used to determine the evaluation criteria of the data to be evaluated according to the field type to which the data to be evaluated belongs; The identity confirmation module is used to obtain the identity information of the bid evaluators and set the bid evaluation weights of the bid evaluators according to their identity information; The bid evaluation supervision module is used to obtain the bid evaluation scores of the bid evaluators on the bid evaluation data, determine the bid evaluation deviation level of the bid evaluators according to the bid evaluation weights and the bid evaluation scores, and supervise the bid evaluation results according to the bid evaluation deviation level of the bid evaluators.

2. The intelligent bidding evaluation system for bidding as claimed in claim 1, characterized in that: The data processing module is used for: Obtain the bid evaluation data, perform word segmentation on the bid evaluation data, and extract keywords from the bid evaluation data; The keywords of the bid evaluation data are vectorized, and the vectorized keywords are clustered based on the k-means clustering algorithm to obtain the central keywords; A domain knowledge base is established, the cosine similarity between the central keyword and the keyword in the domain knowledge base is calculated, the keywords in the domain knowledge base whose cosine similarity with the central keyword is greater than a first preset threshold are screened out, and the domain type corresponding to the keyword in the domain knowledge base whose cosine similarity with the central keyword is greater than the first preset threshold is determined as the domain type to which the data to be evaluated belongs.

3. The intelligent bidding evaluation system for bidding as claimed in claim 2, characterized in that: The keywords for extracting the bid evaluation data include: Obtain the word segmentation of the bid evaluation data after word segmentation processing, establish a bid evaluation keyword knowledge base, and determine the keywords of the bid evaluation data segmentation according to the bid evaluation keyword knowledge base; The frequencies of occurrence of the keywords of the data to be evaluated are counted, the frequencies of occurrence of the keywords of the data to be evaluated are sorted, and the keywords of the data to be evaluated with preset positions are determined as the keywords of the data to be evaluated according to the sorting results.

4. The intelligent bidding evaluation system for bidding as claimed in claim 3, characterized in that: The step of clustering the vectorized keywords based on the k-means clustering algorithm includes: A keyword data set is established based on the keyword vector after vectorization, and k initial clustering centers of the keyword data set are randomly selected; Calculate the Euclidean distance between the keyword vector in the keyword data set and the initial cluster center, and divide the keyword vector into corresponding partitions according to the Euclidean distance between the keyword vector in the keyword data set and the initial cluster center; Calculate the average value of the keyword vectors in each partition, and recalculate the cluster center based on the average value of the keyword vectors in each partition; Repeat the above steps until the cluster center no longer changes or the number of iterations reaches the maximum number of iterations, and obtain k final cluster centers.

5. The intelligent bidding evaluation system for bidding as claimed in claim 1, characterized in that: The model building module is used to: Obtain historical bid evaluation standard data and corresponding field types, pre-process the historical bid evaluation standard data and corresponding field types, and obtain a bid evaluation data set; A bid evaluation standard model is established based on the bid evaluation data set, and the field type of the current bid evaluation data is input into the bid evaluation standard model to obtain the corresponding bid evaluation standard.

6. The intelligent bidding evaluation system for bidding as claimed in claim 5, characterized in that: The step of establishing a bid evaluation standard model based on the bid evaluation data set includes: Conduct exploratory data analysis on the bid evaluation data set to obtain the bid evaluation data set after data analysis; Perform feature extraction based on the bid evaluation data set after data analysis to obtain quantitative features of the bid evaluation criteria; A bid evaluation standard model is constructed according to the quantitative characteristics of the bid evaluation standard, and the bid evaluation standard model is trained to obtain a trained bid evaluation standard model.

7. The intelligent bidding evaluation system for bidding as claimed in claim 1, characterized in that: The identity confirmation module is used for: Obtain the identity information of the bid evaluators, and set the corresponding roles of the bid evaluators according to their identity information; Determine the initial weight according to the corresponding role of the bid evaluator, obtain the historical bid evaluation data of the bid evaluator, and calculate the bid evaluation data curve of the bid evaluator based on the historical bid evaluation data of the bid evaluator; Obtaining a preset standard curve for bid evaluation data, and calculating the standard deviation between the bid evaluation data curve of the bid evaluators and the preset standard curve for bid evaluation data; The weight calculation formula is set according to the standard deviation between the bid evaluation data curve of the bid evaluation personnel and the preset bid evaluation data standard curve, and the bid evaluation weight of the bid evaluation personnel is determined according to the weight calculation formula. The weight calculation formula is specifically as follows: Among them, W is the evaluation weight of the evaluator, W r is the initial weight, S is the standard deviation between the evaluation data curve of the evaluator and the preset evaluation data standard curve, and T is the preset range coefficient.

8. The intelligent bidding evaluation system for bidding as claimed in claim 7, characterized in that: The bid evaluation supervision module is used to: Obtain the bid evaluation scores of the bid evaluation personnel for the bid evaluation data, calculate the difference between the bid evaluation scores of the bid evaluation personnel for the bid evaluation data and the preset bid evaluation qualified value, and obtain the bid evaluation deviation of the bid evaluation personnel; The bid evaluation deviation of the bid evaluation personnel is normalized to obtain the normalized bid evaluation deviation; The normalized bid evaluation deviation is multiplied by the bid evaluation weight of the bid evaluator to obtain the deviation calculation result, and the bid evaluation deviation level of the bid evaluator is determined based on the deviation calculation result.

9. The intelligent bidding evaluation system for bidding as claimed in claim 8, characterized in that: Determining the bid evaluation deviation level of the bid evaluation personnel according to the deviation calculation result includes: Calculate the difference between the deviation calculation result and the preset deviation tolerance value, and determine whether the difference between the deviation calculation result and the preset deviation tolerance value is greater than a second preset threshold; If the difference between the deviation calculation result and the preset deviation tolerance value is greater than the second preset threshold, the first level is set as the bid evaluation deviation level of the bid evaluation personnel; If the difference between the calculated deviation result and the preset deviation tolerance value is less than or equal to the second preset threshold, then determining whether the difference between the calculated deviation result and the preset deviation tolerance value is greater than a third preset threshold; If the difference between the deviation calculation result and the preset deviation tolerance value is greater than the third preset threshold, the second level is set as the bid evaluation deviation level of the bid evaluation personnel; If the difference between the deviation calculation result and the preset deviation tolerance value is less than or equal to the third preset threshold value, the third level is set as the evaluation deviation level of the evaluator.

10. An intelligent bid evaluation method for bidding, characterized in that: include: Obtain the data to be evaluated, and determine the field type to which the data to be evaluated belongs based on the keywords of the data to be evaluated; Determine the bid evaluation criteria for the bid evaluation data according to the field to which the bid evaluation data belongs; Obtain the identity information of the bid evaluators, and set the bid evaluation weights of the bid evaluators according to their identity information; Obtain the evaluation scores of the bid evaluators on the bid evaluation data, determine the evaluation deviation level of the bid evaluators according to the evaluation weights and the evaluation scores, and supervise the evaluation results according to the evaluation deviation level of the bid evaluators.

Images