High-quality supplier screening method, device and equipment and storage medium

By collecting and aggregating data in the bidding system, and using association rule analysis and multi-dimensional scoring, the problems of insufficient data utilization and lack of consideration for the relationship between bidding suppliers in existing technologies are solved, thus achieving efficient and low-cost screening of high-quality suppliers.

CN118967285APending Publication Date: 2024-11-15CHINA MOBILE (SUZHOU) SOFTWARE TECH CO LTD +1
View PDF 0 Cites 4 Cited by

Patent Information

Application Number
CN202411015301.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-26
Publication Date
2024-11-15

AI Technical Summary

Technical Problem

Existing technologies fail to fully utilize the relationship information between bidding suppliers in the bidding unit's system, and the use of neural network models requires large-scale web crawling data, resulting in high costs and failure to fully utilize the supplier's existing data information.

Method used

By collecting bidding information, winning bid information, and negative behavior identification information from the bidding system, aggregating and statistically processing them, potential abnormal suppliers and successful bidders are screened out. The association rule analysis method is used to discover suppliers with high correlation, and scores are given based on multi-dimensional indicators to obtain high-quality suppliers.

Benefits of technology

It improves the efficiency and reliability of screening high-quality suppliers, reduces the size and cost of algorithm models, makes full use of existing data and information, and provides multi-dimensional screening references.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118967285A_ABST
    Figure CN118967285A_ABST
Patent Text Reader

Abstract

The invention provides a high-quality supplier screening method and device, equipment and a storage medium. The method comprises the following steps: acquiring bidding information, bid winning information and negative behavior identification information of bidding suppliers from a bidding system; performing aggregation and statistical processing on the bidding information, the bidding-winning information and the negative behavior identification information of the bidding suppliers, screening potential abnormal suppliers, high-bidding-winning suppliers and high-bidding-winning and low-bidding-winning suppliers from the bidding suppliers, and taking the high-bidding-winning suppliers and the high-bidding-winning and low-bidding-winning suppliers as candidate high-quality suppliers; carrying out association relationship mining on the potential abnormal suppliers and the high bid winning suppliers to obtain suppliers with high association degree, and judging the suppliers with high association degree as suspected abnormal suppliers; and scoring the candidate high-quality suppliers based on the preset indexes of the multiple dimensions and the condition that the suppliers are judged to be suspected abnormal suppliers, and obtaining scores of the candidate high-quality suppliers in each dimension, so that purchasers can determine the high-quality suppliers according to the scores.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the field of data mining technology, and in particular to a method, device, equipment and storage medium for screening high-quality suppliers. Background Art

[0002] Suppliers play a very important role in the procurement process of an enterprise, and high-quality suppliers are crucial to the development of an enterprise. If the quality of the supplier is unstable or the service does not meet the needs of the enterprise, it will lead to an increase in procurement costs, so it is necessary to screen high-quality suppliers. In the related technology, suppliers are divided into first suppliers and second suppliers according to the length of registration, and the attributes and behavior data of the first supplier and the second supplier are collected respectively; the XGBoost model is used to transform the behavior data of the first supplier to obtain an n-dimensional number vector, and the n-dimensional number vector is uniquely encoded and concatenated with the original feature and input into the logistic regression model for prediction; the behavior data of the second supplier is converted into evidence weights, and the IV value is calculated for feature dimension screening, and a semi-supervised learning algorithm is used for prediction; the n suppliers with the highest prediction probability are selected according to the proportion of high-quality suppliers in the first supplier and the second supplier, so as to improve the prediction accuracy.

[0003] However, the related technology does not take into account the relationship information between the bidding suppliers in the bidding unit system, the use of neural network models requires large-scale crawler data, the cost of building a related model system is high, and the existing data information of the supplier is not fully utilized. Summary of the invention

[0004] The first aspect of the present disclosure provides a method for screening high-quality suppliers, which includes: collecting bidding information, winning bid information and negative behavior identification information of bidding suppliers from a bidding system; aggregating and statistically processing the bidding information, winning bid information and negative behavior identification information of bidding suppliers, screening out potential abnormal suppliers, high-bid suppliers and high-bid and low-winning bid suppliers from the bidding suppliers, and selecting the high-bid suppliers and high-bid and low-winning bid suppliers as candidate high-quality suppliers; mining the association relationship between potential abnormal suppliers and high-bid suppliers to obtain suppliers with high association, and determining the suppliers with high association as suspected abnormal suppliers; scoring the candidate high-quality suppliers based on preset indicators of multiple dimensions and the situation in which the supplier is determined to be a suspected abnormal supplier, and obtaining the scores of the candidate high-quality suppliers in each dimension, so that the purchaser can determine the high-quality suppliers according to the scores.

[0005] In some embodiments of the present disclosure, collecting bidding information, winning bid information and negative behavior identification information of bidding suppliers from a bidding system includes: obtaining a project information table, a supplier response table, a supplier winning bid table and a supplier identification table from the bidding system; obtaining non-failed and completed valid project information from the project information table, associating the valid project information with the supplier response table to obtain bidding supplier information associated with the valid project; obtaining bidding information of bidding suppliers by counting bidding supplier information and valid project information; associating valid project information and bidding supplier information with the supplier winning bid table to obtain the winning bid information of each bidding supplier; associating valid project information and bidding supplier information with the supplier identification table to obtain behavior identification information of each bidding supplier.

[0006] In some embodiments of the present disclosure, the bidding information, winning bid information, and negative behavior identification information of the bidding suppliers are aggregated and statistically processed to screen out potential abnormal suppliers, high-bid suppliers, and high-bid and low-bid suppliers from the bidding suppliers, including: the bidding information, winning bid information, and negative behavior identification information of the bidding suppliers are aggregated to obtain the number of bids, the number of winning bids, and the number of times negative behaviors are identified of the bidding suppliers; the ratio of the number of winning bids of the bidding suppliers to the number of bids is determined as the bidding rate of the bidding suppliers, and the ratio of the number of times negative behaviors of the bidding suppliers are identified to the number of bids is determined as the bidding rate of the bidding suppliers. The abnormal rate of suppliers; based on the preset high bid number threshold and the number of bids of the bidding suppliers, screen out high bid suppliers from the bidding suppliers; based on the preset low winning bid number threshold, high winning bid number threshold and the number of bids of the bidding suppliers, screen out low winning bid suppliers and high winning bid suppliers from the bidding suppliers, and associate high bid suppliers with low winning bid suppliers to obtain high bid and low winning bid suppliers; based on the comparison result of the preset potential abnormal rate threshold and the abnormal rate of the bidding suppliers, screen out high abnormal bid suppliers from the bidding suppliers, and take high bid suppliers, low winning bid suppliers and high abnormal bid suppliers as potential abnormal suppliers.

[0007] In some embodiments of the present disclosure, association relationships between potential abnormal suppliers and high-best bid suppliers are mined to obtain suppliers with high association, and suppliers with high association are determined as suspected abnormal suppliers, including: calculating the support of each supplier among the potential abnormal suppliers and the high-best bid suppliers respectively, and taking the set of suppliers with support higher than a preset minimum support threshold as a frequent item set; extracting association rules from the frequent item sets to obtain association rules and calculating the confidence of the association rules, taking the association rules with confidence higher than the preset confidence threshold as strong rules, and taking suppliers associated with the strong rules as suspected abnormal suppliers.

[0008] In some embodiments of the present disclosure, based on preset indicators of multiple dimensions and situations where suppliers are judged as suspected abnormal suppliers, candidate high-quality suppliers are scored to obtain scores of the candidate high-quality suppliers in each dimension, so that the purchaser can determine the high-quality suppliers based on the scores, including: based on situations where suppliers are judged as suspected abnormal suppliers, using the achievement-driven high-reliability ADHR evaluation system to score the candidate high-quality suppliers to obtain corresponding scores; based on at least one of the contract performance, bid evaluation process scores, breach of trust behavior, and collusion risk, using the ADHR evaluation system to score the candidate high-quality suppliers to obtain corresponding scores.

[0009] In some embodiments of the present disclosure, the method further includes: calculating the total score of the candidate high-quality suppliers according to the scores of the candidate high-quality suppliers in each dimension; and sorting the candidate high-quality suppliers based on the total score or the score of any dimension.

[0010] The second aspect of the embodiment of the present disclosure proposes a high-quality supplier screening device, which includes: a collection module, which is used to collect the bidding information, winning bid information and negative behavior identification information of the bidding suppliers from the bidding system; an aggregation module, which is used to aggregate and statistically process the bidding information, winning bid information and negative behavior identification information of the bidding suppliers, and screen out potential abnormal suppliers, high-bid suppliers and high-bid and low-winning bid suppliers from the bidding suppliers, and use the high-bid suppliers and high-bid and low-winning bid suppliers as candidate high-quality suppliers; an association module, which is used to mine the association relationship between the potential abnormal suppliers and the high-bid suppliers to obtain suppliers with high correlation, and judge the suppliers with high correlation as suspected abnormal suppliers; a scoring module, which is used to score the candidate high-quality suppliers based on preset indicators of multiple dimensions and the situations in which they are judged as suspected abnormal suppliers, and obtain the scores of the candidate high-quality suppliers in each dimension, so that the purchaser can determine the high-quality suppliers according to the scores.

[0011] The third aspect embodiment of the present disclosure proposes a communication device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method described in the first aspect embodiment of the present disclosure.

[0012] The fourth aspect embodiment of the present disclosure proposes a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable a computer to execute the method described in the first aspect embodiment of the present disclosure.

[0013] The fifth aspect embodiment of the present disclosure provides a computer program product, including a computer program, which implements the method described in the first aspect embodiment of the present disclosure when executed by a processor.

[0014] In summary, the method for screening high-quality suppliers proposed in the present disclosure includes collecting bidding information, winning bid information and negative behavior identification information of bidding suppliers from the bidding system; aggregating and statistically processing the bidding information, winning bid information and negative behavior identification information of bidding suppliers, screening out potential abnormal suppliers, high-bid suppliers and high-bid and low-winning bid suppliers from the bidding suppliers, and taking the high-bid suppliers and high-bid and low-winning bid suppliers as candidate high-quality suppliers; mining the association relationship between potential abnormal suppliers and high-bid suppliers to obtain suppliers with high correlation, and determining the suppliers with high correlation as suspected abnormal suppliers; scoring the candidate high-quality suppliers based on preset indicators of multiple dimensions and the situation in which the supplier is determined to be a suspected abnormal supplier, and obtaining the scores of the candidate high-quality suppliers in each dimension, so that the purchaser can determine the high-quality suppliers according to the scores. This solution introduces association rule analysis to mine association rules between suppliers, fully considering the association relationship between bidding suppliers in the bidding unit system; it mainly uses the existing data of the bidding unit to screen high-quality suppliers. Compared with large-scale neural network models, the algorithm model of this solution is smaller in scale, fully utilizes the existing data information of the supplier and has low cost; it conducts multi-dimensional scoring of the candidate set of high-quality suppliers for reference by procurement personnel to obtain high-quality suppliers, which improves the screening efficiency and has high reliability.

[0015] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings herein are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the description are used to explain the principles of the present disclosure, and do not constitute improper limitations on the present disclosure.

[0017] Figure 1 A flowchart of a method for selecting high-quality suppliers provided in an embodiment of the present disclosure;

[0018] Figure 2 A flowchart of a method for selecting high-quality suppliers provided in an embodiment of the present disclosure;

[0019] Figure 3 A flowchart of a method for selecting high-quality suppliers provided in an embodiment of the present disclosure;

[0020] Figure 4 An example diagram of a process for collecting bidding information of bidding suppliers provided in an embodiment of the present disclosure;

[0021] Figure 5 An example diagram of a process for classifying bidding suppliers provided in an embodiment of the present disclosure;

[0022] Figure 6 An example diagram of a process for obtaining a suspected abnormal supplier provided by an embodiment of the present disclosure;

[0023] Figure 7 A schematic diagram of the structure of a high-quality supplier screening device provided in an embodiment of the present disclosure;

[0024] Figure 8 A schematic diagram of the hardware structure of a communication device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0025] Embodiments of the present disclosure are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present disclosure, and should not be construed as limiting the present disclosure.

[0026] First, the technical problems to be solved by the technical solution of the present disclosure and related technologies are described in detail.

[0027] Suppliers play a very important role in the procurement process of an enterprise, and high-quality suppliers are crucial to the development of an enterprise. In the past, the core of an enterprise's operation was products and markets, but now, supply chain management with suppliers as the core has become a new trend in the development of enterprises. If the quality of the supplier is unstable or the service does not meet the needs of the enterprise, it will lead to an increase in procurement costs. Therefore, when selecting suppliers, enterprises need to comprehensively consider the qualifications of suppliers. In addition to conventional product quality and price, the image and reputation of suppliers are also receiving more and more attention. If the selected supplier has a good reputation and corporate image, it can also improve the quality image of the enterprise and increase the market influence of the enterprise while controlling procurement costs.

[0028] A method for predicting high-quality suppliers is proposed in the related art, including the following steps: dividing suppliers into the first supplier and the second supplier according to the length of registration, and collecting the attributes and behavior data of the first supplier and the second supplier respectively; using the XGBoost model to transform the behavior data of the first supplier to obtain an n-dimensional number vector, performing unique hot encoding on the n-dimensional number vector and concatenating it with the original feature, and then inputting it into the logistic regression model for prediction; performing evidence weight conversion on the behavior data of the second supplier, and calculating the IV value for feature dimension screening, and using the semi-supervised learning algorithm for prediction; selecting the n suppliers with the highest prediction probability according to the proportion of high-quality suppliers in the first and second suppliers, so as to improve the prediction accuracy. A method for screening suppliers of e-commerce platforms is disclosed in the related art, which collects the sales volume and financial status information of suppliers on various network platforms through big data technology, builds a supplier information database, and establishes a comprehensive supplier comprehensive ability evaluation system based on the supplier information database, evaluation model and algorithm. The evaluation system covers the entire process of access inspection stage, bad management stage, after-sales management stage, line stop stage and service attitude, and sets different weight calculation and scoring mechanisms based on different evaluation items, which can improve the accuracy of supplier evaluation and quickly screen out high-quality suppliers and their high-quality products. Related technologies also disclose a supplier evaluation method based on a data warehouse as follows: Reputation evaluation: The quantity and quality of the products are tested according to the supplier's invoice, and the test results are recorded. The supplier's reputation is then evaluated based on the gap between the test results and the invoice information; Punctuality evaluation: The supplier's delivery time is set, and the supplier is notified in advance to ship the goods according to the delivery time. After the goods arrive, the supplier's arrival time is recorded, and then the deviation value between the delivery time and the arrival time and the stability value of the arrival time are counted, and the supplier's punctuality is evaluated based on the deviation value and the stability value.

[0029] The relevant technology has the following shortcomings: it does not take into account the relationship information between the bidding suppliers in the bidding unit system; the use of neural network models requires large-scale crawler data, the cost of building a related model system is high, and the existing data information of the supplier is not fully utilized.

[0030] In order to solve the above problems, the present invention proposes a new high-quality supplier screening method, device, equipment and medium, which uses the existing bidding data of the tendering unit and the supplier reputation information disclosed on the Internet to conduct supplier qualification risk assessment. First, collect historical project information, supplier bidding and winning information from the tendering system of the tendering unit, and obtain a set of high-quality supplier candidates (including high-bid and low-winning suppliers, high- and medium-winning suppliers) and a set of potential abnormal suppliers through summary statistics; then use the association rule analysis algorithm to mine the association relationship between potential abnormal suppliers and high- and medium-winning suppliers to obtain a set of suspected abnormal suppliers; finally, the high-quality supplier candidate set is scored in multiple dimensions, including abnormal situations, contract performance, dishonest behavior, bid evaluation process scores, and bid-rigging risks, so as to obtain high-quality suppliers for reference in subsequent links.

[0031] The present disclosure is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0032] Figure 1 A flowchart of a method for selecting high-quality suppliers provided in an embodiment of the present disclosure.

[0033] like Figure 1 As shown, the method for selecting high-quality suppliers provided by the embodiment of the present disclosure includes the following steps 101-104:

[0034] Step 101, collecting bidding information, winning bid information and negative behavior identification information of bidding suppliers from the bidding system.

[0035] In some embodiments of the present disclosure, Figure 2 As shown, from the project information table, supplier response table, supplier winning bid table and supplier identification table in the bidding system owned by the bidding unit, the bidding information, winning bid information and negative behavior identification information of the bidding suppliers are collected and put into the collection result table.

[0036] In some embodiments of the present disclosure, the bidding information includes relevant information about the bidding project and the bidding suppliers involved, the winning bid information includes relevant information about whether the bidding supplier has won the bidding project, and the negative behavior identification information includes relevant information about whether the bidding supplier has been confirmed as an abnormal supplier by experts during the review process.

[0037] Step 102, aggregate and statistically process the bidding information, winning bid information, and negative behavior identification information of the bidding suppliers, screen out potential abnormal suppliers, high-bid suppliers, and high-bid but low-winning bid suppliers from the bidding suppliers, and select the high-bid suppliers and high-bid but low-winning bid suppliers as candidate high-quality suppliers.

[0038] In some embodiments of the present disclosure, the collection result data obtained through the above step 101 is aggregated and analyzed, and indicator statistics are performed based on the aggregated data. The indicators include the total number of bids, the winning rate, the abnormality rate, etc. of the bidding suppliers, among which the winning rate is the ratio of the total number of winning bids to the total number of bids, and the abnormality rate is the ratio of the number of identified negative behaviors to the total number of bids.

[0039] In some embodiments of the present disclosure, high-bidding suppliers are screened out according to the total number of bids of the bidding suppliers, high- and low-winning suppliers are screened out according to the winning rate of the bidding suppliers, highly abnormal suppliers are screened out according to the abnormal rate of the bidding suppliers, and high-bidding suppliers are associated with low-winning suppliers to screen out high-bidding and low-winning suppliers.

[0040] In some embodiments of the present disclosure, high-bidding suppliers, low-winning suppliers, and highly abnormal suppliers are defined as potential abnormal suppliers.

[0041] In some embodiments of the present disclosure, suppliers with high bids and low winning bids and suppliers with high winning bids are taken as a set of high-quality supplier candidates, and only these two types of suppliers are subsequently scored to further obtain a set of high-quality suppliers.

[0042] Step 103, mining the association relationship between potential abnormal suppliers and high-winning suppliers to obtain suppliers with high association, and determining suppliers with high association as suspected abnormal suppliers.

[0043] In some embodiments of the present disclosure, an association rule analysis method Apriori algorithm is used to mine the association relationship between potential abnormal suppliers and high-winning suppliers.

[0044] In some embodiments of the present disclosure, the Apriori algorithm is a classic association rule mining algorithm, which is mainly used to discover frequent associations between items in a data set. The basic idea of ​​the algorithm is based on the a priori properties of frequent item sets (Apriori principle), that is, if an item set is frequent, then all its subsets must also be frequent.

[0045] In some embodiments of the present disclosure, the process of the Apriori algorithm is as follows: first, a set of all possible single items is generated as a candidate item set, including potential abnormal suppliers, high-bid suppliers, and abnormal suppliers that appear as a combination of potential abnormal suppliers and high-bid suppliers; the support of each candidate item set is calculated, a support threshold is set to filter out frequent item sets, and a candidate item set for the next iteration is generated based on the frequent item sets. The above steps are repeated, and the size of the item set is increased each time until no more frequent item sets can be generated. Based on the frequent item sets, association rules are generated, and the confidence of the rules is calculated.

[0046] Step 104, based on the preset indicators of multiple dimensions and the situation where the supplier is determined to be a suspected abnormal supplier, the candidate high-quality suppliers are scored to obtain the scores of the candidate high-quality suppliers in each dimension, so that the purchaser can determine the high-quality suppliers based on the scores.

[0047] In some embodiments of the present disclosure, the multiple dimensions include abnormal situations, contract performance, breach of trust, bid evaluation process scores, risk of bid rigging and collusion, etc., among which the abnormal situation refers to the situation where the supplier is judged to be a suspected abnormal supplier.

[0048] In some embodiments of the present disclosure, based on abnormal situations, contract performance, breach of trust, bid evaluation process scores, and bid rigging risk indicators, the supplier's abnormality (Abnormal), delivery capability (Delivery), historical score (History), and reputation (Reputation) are scored through the ADHR evaluation system.

[0049] In summary, the embodiment provided by the present invention introduces the association rule analysis method to mine the association rules between suppliers, and fully considers the association relationship between the bidding suppliers in the bidding unit system; it mainly uses the existing data of the bidding unit to screen high-quality suppliers. Compared with the large-scale neural network model, the algorithm model of this solution is smaller in scale, fully utilizes the existing data information of the supplier and has low cost; multi-dimensional scoring is performed on the candidate set of high-quality suppliers for reference by procurement personnel to obtain high-quality suppliers, which improves the screening efficiency and has high reliability.

[0050] based on Figure 1 The embodiment shown, such as Figure 3 As shown, Figure 3 A flowchart of another method for screening high-quality suppliers provided in an embodiment of the present disclosure.

[0051] The method for selecting high-quality suppliers provided in the embodiment of the present disclosure includes the following steps:

[0052] Step 201, collecting bidding information, winning bid information and negative behavior identification information of bidding suppliers from the bidding system.

[0053] In some embodiments of the present disclosure, collecting bidding information, winning bid information and negative behavior identification information of bidding suppliers from a bidding system includes: obtaining a project information table, a supplier response table, a supplier winning bid table and a supplier identification table from the bidding system; obtaining non-failed and completed valid project information from the project information table, associating the valid project information with the supplier response table to obtain bidding supplier information associated with the valid project; obtaining bidding information of bidding suppliers by counting bidding supplier information and valid project information; associating valid project information and bidding supplier information with the supplier winning bid table to obtain the winning bid information of each bidding supplier; associating valid project information and bidding supplier information with the supplier identification table to obtain behavior identification information of each bidding supplier.

[0054] In some embodiments of the present disclosure, Figure 4 As shown, the project information table, supplier response table, supplier winning table, and supplier certification table are obtained from the bidding system. First, the non-failed and completed valid project information is obtained from the project information table, and then the supplier response table is associated with the project ID and other information to obtain the name of the supplier participating in the bidding for each project, the supplier ID and other information, and then the supplier winning table is associated with the project ID and supplier ID information to obtain the winning situation of each supplier.

[0055] In some embodiments of the present disclosure, the supplier identification table stores the negative behaviors of suppliers participating in the bidding in each bidding project. If there is any supplier involved in bid rigging and collusion and identified by the evaluation experts, it will be recorded in this table. The table is associated with the project ID, supplier ID and other information obtained above to obtain suppliers with negative behavior records.

[0056] In some embodiments of the present disclosure, the collected information specifically includes the name of the bidding project, the category of the bidding product, the subcategory of the bidding product, the name of the bidding supplier, whether the bid is successful, and whether it is identified as abnormal, as shown in Table 1:

[0057] Table 1 Collection result table field description example table

[0058]

[0059] In some embodiments of the present disclosure, the data in the collection result table is converted into a format. For example, the value range of the is_zb field is {yes, no}. In order to facilitate subsequent statistics, the result is converted into a numeric type, where 1 represents "yes" and 0 represents "no". The is_yc field value is mapped to 1 if there is a negative behavior and to 0 if there is no negative behavior. A column "number of bids" is added and assigned a value of 1. After the above collection and data processing, the data format obtained is shown in Table 2:

[0060] Table 2 Collection results example table

[0061]

[0062] Step 202, aggregate and statistically process the bidding information, winning bid information, and negative behavior identification information of the bidding suppliers, screen out potential abnormal suppliers, high-bid suppliers, and high-bid but low-winning bid suppliers from the bidding suppliers, and select the high-bid suppliers and high-bid but low-winning bid suppliers as candidate high-quality suppliers.

[0063] In some embodiments of the present disclosure, the collected bidding supplier data is statistically analyzed, mainly based on the supplier's bidding information, winning bid information, and negative behavior identification information, to obtain a set of potentially abnormal suppliers and a set of high-quality supplier candidates, where the high-quality supplier candidates include: high-winning suppliers and high-bid and low-winning bid suppliers, so as to be used in the subsequent scoring process.

[0064] In some embodiments of the present disclosure, the acquired collection result data is aggregated and analyzed, such as Figure 5 As shown in Table 3, taking product category and supplier name as dimensions, the indicators of "whether to win the bid", "whether abnormal", and "number of bids" are aggregated, and the resulting data is shown in Table 3:

[0065] Table 3 Example of indicator aggregation results

[0066]

[0067] In some embodiments of the present disclosure, the index statistics are performed based on the aggregated data, including the bid winning rate and the abnormality rate, wherein the bid winning rate refers to the ratio of the total number of bids won by the supplier in the product category to the total number of bids, and the abnormality rate refers to the ratio of the number of times the supplier is identified as having negative behavior in the product category to the total number of bids. The specific calculation formula is as follows:

[0068]

[0069]

[0070] Among them, represents the winning rate, represents the total number of winning bids, represents the total number of abnormalities, and represents the total number of bids. Based on the above formula, we can calculate the "winning rate" and "abnormality rate" of each supplier in each product dimension.

[0071] In some embodiments of the present disclosure, the bidding number index is sorted in descending order to set a high bidding threshold, and the bidding suppliers whose bidding number is higher than the threshold are high bidding suppliers, and the bidding suppliers whose bidding number is not higher than the threshold are ordinary bidding suppliers; the abnormality rate is calculated based on the bidding number and the abnormality number, and the abnormality rate is sorted in descending order to set a high abnormality threshold, and the bidding suppliers whose abnormality rate is higher than the threshold are high abnormality suppliers, and the bidding suppliers whose abnormality rate is not higher than the threshold are ordinary bidding suppliers; the winning rate is calculated based on the bidding number and the winning bid number, and the winning rate is sorted in descending order to set a high winning bid threshold and a low winning bid threshold, and the bidding suppliers whose winning bid rate is higher than the high winning bid threshold are high winning bid suppliers, and the bidding suppliers whose winning bid rate is lower than the low winning bid threshold are low winning bid suppliers, and the bidding suppliers whose winning bid rate is neither higher than the high winning bid threshold nor lower than the low winning bid threshold are ordinary bidding suppliers.

[0072] For example, the bid number index is sorted in descending order. It is assumed that 20 is set as the threshold for screening suppliers with high bid rates. If the total number of bids of a supplier is higher than 20, it is identified as a high bid supplier, and if it is lower than 20, it is identified as an ordinary bid supplier. The abnormality rate index is sorted in descending order. It is assumed that 60% is set as the threshold for high abnormality rate. If the abnormality rate of negative behavior of a supplier is higher than 60%, it is identified as a high abnormal supplier, otherwise it is an ordinary bid supplier. The winning bid rate index is sorted in descending order. It is assumed that 70% is set as the threshold for suppliers with high winning bid rates and 20% is set as the threshold for suppliers with low winning bid rates. If the winning bid rate of a supplier is higher than 70%, it is identified as a high winning bid supplier, and if it is lower than 20%, it is identified as a low winning bid supplier. Suppliers between 20% and 70% are ordinary bid suppliers.

[0073] In some embodiments of the present disclosure, based on the three risk indicators of "high bidding supplier", "high abnormal supplier" and "low bidding supplier", such suppliers may be abnormal, and therefore such suppliers are defined as potentially abnormal suppliers.

[0074] In some embodiments of the present disclosure, suppliers with "high bids" and "low winning bids" and "high winning bids" are taken as a set of high-quality supplier candidates, and only these two types of suppliers are subsequently scored to further obtain a set of high-quality suppliers.

[0075] Step 203, respectively calculate the support of each supplier among the potential abnormal suppliers and the high-winning suppliers, and take the set of suppliers whose support is higher than the preset minimum support threshold as a frequent itemset.

[0076] In some embodiments of the present disclosure, the potential abnormal suppliers and the high-quality bidding suppliers are analyzed for correlation to obtain the bidding suppliers with high correlation between the two types of suppliers. Such suppliers are determined to be suspected abnormal suppliers. This module uses the Apriori algorithm, a commonly used association rule analysis method in data mining. The specific process is as follows: Figure 6 shown.

[0077] In some embodiments of the present disclosure, the bidding supplier data is aggregated based on the product category dimension to obtain a supplier set, including potential abnormal suppliers and high-winning suppliers. The two types of data are used as input data for the association rule algorithm. The support of each supplier and the support of the combined suppliers are calculated based on the data set. The data is traversed in turn to calculate all item sets and the corresponding support values. A minimum support threshold is set to eliminate data below the threshold, and the data set above the threshold is used as a frequent item set to facilitate subsequent association rule mining.

[0078] In some embodiments of the present disclosure, the calculation formula for each supplier's support is as follows:

[0079]

[0080] Among them, S A represents the support of supplier A, N A represents the total number of times supplier A appears in the input data, N A Indicates the total number of input data.

[0081] Step 204, extract association rules from frequent item sets to obtain association rules and calculate the confidence of the association rules, take the association rules with confidence higher than a preset confidence threshold as strong rules, and take the suppliers associated with the strong rules as suspected abnormal suppliers.

[0082] In some embodiments of the present disclosure, association rules are extracted from the acquired frequent item set data. First, association rules are obtained based on the frequent item sets, and then confidence calculation is performed. By calculating the confidence value, the frequency of supplier B in the item set appearing in the transaction containing supplier A can be determined, and the minimum confidence threshold C is set. th , will be lower than the minimum confidence threshold C th Association rules with a confidence level higher than the confidence threshold are called weak rules, and those with a confidence level higher than the confidence threshold are called strong rules. The specific calculation formula is as follows:

[0083]

[0084] Among them, C A=>B represents the confidence of association rule A→B, N AB N represents the total number of times supplier A and supplier B appear together. AIndicates the total number of times supplier A appears.

[0085] It should be noted that through information mining of association rule algorithms, the hidden associations between bidding suppliers can be obtained, and suppliers with strong rule associations can be regarded as suspected abnormal suppliers to facilitate the use of subsequent scoring mechanisms.

[0086] Step 205, based on the preset indicators of multiple dimensions and the situation where the supplier is determined to be a suspected abnormal supplier, the candidate high-quality suppliers are scored to obtain the scores of the candidate high-quality suppliers in each dimension, so that the purchaser can determine the high-quality suppliers based on the scores.

[0087] In some embodiments of the present disclosure, a set of high-quality supplier candidates is scored in multiple dimensions, including suspected abnormal situations, contract performance, dishonest behavior, and risk of bid rigging and collusion. Among them, contract performance and risk of bid rigging and collusion can be directly obtained from the enterprise bidding system, dishonest behavior can be obtained from channels such as Credit China and China Enforcement Information Disclosure Network, and suspected abnormal situations are obtained by analyzing and mining association rules between potential abnormal suppliers and high-best bidders, specifically through the above-mentioned steps 203 and 204.

[0088] In some embodiments of the present disclosure, the suspected abnormal situation includes whether the supplier is a suspected abnormal supplier, the contract performance includes early delivery, on-time delivery, delayed delivery, midway withdrawal, etc., the bid evaluation process score includes the score of the evaluation experts in the historical bidding process, the dishonest behavior includes whether there is a dishonest negative behavior, and the risk of bid rigging includes whether there is a risk of bid rigging. The specific scoring dimensions are shown in Table 4 below:

[0089] Table 4 Specific scoring dimensions

[0090]

[0091] In some embodiments of the present disclosure, the ADHR evaluation system is used to calculate the scores of the four dimensional attributes of the supplier, namely, abnormality, delivery capability, history score, and reputation. The calculation formula is as follows:

[0092] S=W A S A +W D S D +W h S h +W R S R

[0093] Among them, W iIt represents the weight value of each dimension, which can be set manually according to the actual data situation, or calculated through models such as entropy weight method. S is the total score, S i Indicates the score of each dimension, where S A is the score of the abnormality dimension, S D is the score of the delivery capability dimension, S H is the score of the historical score dimension, S R1 is the score of dishonest behavior in the credibility dimension, S r2 is the score of the risk of bid rigging in the credibility dimension, S R is the total score of the credibility dimension. For details, please refer to the following calculation:

[0094] S A = 6, by default, it is not in the suspected abnormal supplier. When it is in the abnormal supplier set, S A =-6

[0095] S D = C number of early deliveries × 4 + C number of on-time deliveries × 2 + C number of delayed deliveries × (-4) + C number of midway withdrawals × (-5)

[0096]

[0097] S R1 =C 存在失信行为次数 ×(-3), when C=0, S R1 =3

[0098] S R2 =C 存在围串标风险次数 ×(-5), when C=0, S R2 =5

[0099] S R =S R1 +S R2

[0100] In some embodiments of the present disclosure, the method also includes: sorting the suppliers in descending order according to the total score or the score of any dimension, where the higher the ranking, the better the supplier, and displaying the detailed scores of multiple dimensions together with the total score for reference by purchasing personnel.

[0101] In summary, the solution provided by the present disclosure has the following improvements and beneficial effects:

[0102] 1. By introducing the association rule algorithm, the association rules between suppliers are mined, and the association relationship between bidding suppliers in the bidding unit system is fully considered.

[0103] 2. Use the existing data of the bidding unit to screen high-quality suppliers. Compared with large-scale neural network models, the algorithm model of this solution is smaller in scale and more efficient.

[0104] 3. Based on the ADHR evaluation system, multi-dimensional scoring and qualification evaluation are performed on the candidate set of high-quality suppliers to obtain high-quality suppliers for reference in subsequent links.

[0105] The disclosed embodiment also provides a high-quality supplier screening device, such as Figure 7 shown. Figure 7 This is a schematic diagram of the structure of a high-quality supplier screening device provided in an embodiment of the present disclosure. The high-quality supplier screening device 300 includes:

[0106] The collection module 310 is used to collect the bidding information, winning bid information and negative behavior identification information of the bidding suppliers from the bidding system; the aggregation module 320 is used to aggregate and statistically process the bidding information, winning bid information and negative behavior identification information of the bidding suppliers, screen out potential abnormal suppliers, high-bid suppliers and high-bid and low-winning bid suppliers from the bidding suppliers, and use the high-bid suppliers and high-bid and low-winning bid suppliers as candidate high-quality suppliers; the association module 330 is used to mine the association relationship between the potential abnormal suppliers and the high-bid suppliers to obtain suppliers with high correlation, and judge the suppliers with high correlation as suspected abnormal suppliers; the scoring module 340 is used to score the candidate high-quality suppliers based on preset indicators of multiple dimensions and the situations in which they are judged as suspected abnormal suppliers, and obtain the scores of the candidate high-quality suppliers in each dimension, so that the purchaser can determine the high-quality suppliers according to the scores.

[0107] In some embodiments of the present disclosure, the acquisition module 310 is specifically used to: obtain a project information table, a supplier response table, a supplier winning bid table, and a supplier certification table from the bidding system; obtain non-failed and completed valid project information from the project information table, and associate the valid project information with the supplier response table to obtain the bidding supplier information associated with the valid project; obtain the bidding information of the bidding suppliers by counting the bidding supplier information and the valid project information; associate the valid project information and the bidding supplier information with the supplier winning bid table to obtain the winning bid information of each bidding supplier; associate the valid project information and the bidding supplier information with the supplier certification table to obtain the behavior certification information of each bidding supplier.

[0108] In some embodiments of the present disclosure, the aggregation module 320 is specifically used to: aggregate the bidding information, winning bid information and negative behavior identification information of the bidding suppliers to obtain the number of bids, the number of winning bids and the number of identified negative behaviors of the bidding suppliers; determine the ratio of the number of winning bids of the bidding supplier to the number of bids as the bidding rate of the bidding supplier, and determine the ratio of the number of identified negative behaviors of the bidding supplier to the number of bids as the abnormal rate of the bidding supplier; based on a preset high bid number threshold and the number of bids of the bidding suppliers, screen out high-bidding suppliers from the bidding suppliers; based on a preset low winning bid number threshold, a high winning bid number threshold and the number of bids of the bidding suppliers, screen out low-winning bid suppliers and high-winning bid suppliers from the bidding suppliers, and associate high-bidding suppliers with low-winning bid suppliers to obtain high-bidding and low-winning bid suppliers; based on the comparison result of the preset potential abnormal rate threshold and the abnormal rate of the bidding supplier, screen out high-abnormal bidding suppliers from the bidding suppliers, and use high-bidding suppliers, low-winning bid suppliers and high-abnormal bidding suppliers as potential abnormal suppliers.

[0109] In some embodiments of the present disclosure, the association module 330 is specifically used to: respectively calculate the support of each supplier among the potential abnormal suppliers and the high-winning suppliers, and take the set of suppliers whose support is higher than a preset minimum support threshold as a frequent item set; extract association rules from the frequent item sets to obtain association rules and calculate the confidence of the association rules, take the association rules whose confidence is higher than the preset confidence threshold as strong rules, and take the suppliers associated with the strong rules as suspected abnormal suppliers.

[0110] In some embodiments of the present disclosure, the scoring module 340 is specifically used for: based on the situation where a supplier is determined to be a suspected abnormal supplier, using the achievement-driven high-reliability ADHR evaluation system to score the candidate high-quality suppliers to obtain corresponding scores; based on at least one of the contract performance, the bid evaluation process score, the breach of trust behavior, and the risk of collusion in bidding, using the ADHR evaluation system to score the candidate high-quality suppliers to obtain corresponding scores.

[0111] In some embodiments of the present disclosure, the scoring module 340 is also used to: calculate the total score of the candidate high-quality suppliers according to the scores of the candidate high-quality suppliers in each dimension; and sort the candidate high-quality suppliers based on the total score or the score of any dimension.

[0112] In summary, the high-quality supplier screening device provided by the present invention mines the association rules between suppliers by introducing the association rule analysis method, and fully considers the association relationship between the bidding suppliers in the bidding unit system; it mainly uses the existing data of the bidding unit to screen high-quality suppliers. Compared with the large-scale neural network model, the algorithm model of this scheme is smaller in scale, fully utilizes the existing data information of the supplier and has low cost; multi-dimensional scoring is performed on the candidate set of high-quality suppliers for reference by procurement personnel to obtain high-quality suppliers, which improves the screening efficiency and has high reliability.

[0113] The high-quality supplier screening device provided in the above embodiment and the high-quality supplier screening method embodiment provided in the embodiment of the present disclosure belong to the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0114] Figure 8 A schematic diagram of the hardware structure of the communication device provided in the embodiment of the present disclosure is shown in FIG. Figure 8 As shown, the communication device 400 includes at least one processor 402; and a memory 401 communicatively connected to the at least one processor 402; wherein the memory 401 stores instructions that can be executed by the at least one processor 402, and the instructions are executed by the at least one processor 402 to implement the steps of the high-quality supplier screening method of the embodiment of the present disclosure; or, the instructions are executed by the at least one processor 402 to implement the steps of the high-quality supplier screening method of the embodiment of the present disclosure.

[0115] Optionally, the communication device may specifically be a control device of an embodiment of the present application, and the communication device may implement corresponding processes implemented by the control device in each method of the embodiment of the present application, which will not be described in detail here for the sake of brevity.

[0116] It is understood that the communication device also includes a communication interface 403. The various components in the communication device are coupled together through a bus system 404. It is understood that the bus system 404 is used to realize the connection and communication between these components. In addition to the data bus, the bus system 404 also includes a power bus, a control bus, and a status signal bus. However, for the sake of clarity, Figure 8 Various buses are labeled as bus system 404 .

[0117] It can be understood that the memory 401 can be a volatile memory or a non-volatile memory, and can also include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a magnetic random access memory (FRAM), a flash memory, a magnetic surface memory, an optical disc, or a compact disc read-only memory (CD-ROM); the magnetic surface memory can be a disk memory or a tape memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), synchronous static random access memory (SSRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct memory bus random access memory (DRRAM).The memory 401 described in the embodiment of the present invention is intended to include but is not limited to these and any other suitable types of memories.

[0118] The method disclosed in the above embodiment of the present disclosure can be applied to the processor 402, or implemented by the processor 402. The processor 402 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit in the processor 402 or the instruction in the form of software. The above processor 402 may be a general-purpose processor, a DSP, or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The processor 402 can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiments of the present invention. The general-purpose processor may be a microprocessor or any conventional processor, etc. In combination with the steps of the method disclosed in the embodiment of the present invention, it can be directly embodied as a hardware decoding processor to execute, or it can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium, which is located in the memory 401, and the processor 402 reads the information in the memory 401 and completes the steps of the above method in combination with its hardware.

[0119] In an exemplary embodiment, the communication device can be implemented by one or more application specific integrated circuits (ASIC), DSP, programmable logic device (PLD), complex programmable logic device (CPLD), FPGA, general processor, controller, MCU, microprocessor, or other electronic components to execute the aforementioned method.

[0120] The present public security embodiment also provides a non-transitory computer-readable storage medium storing computer instructions, and the computer instructions are used to implement the steps of the high-quality supplier screening method of the embodiment of the present invention when the computer is executed; or, the computer instructions are used to implement the steps of the high-quality supplier screening method of the embodiment of the present invention when the computer is executed.

[0121] Optionally, the computer-readable storage medium can be applied to the control device in the embodiments of the present application, and the computer instructions enable the computer to execute the corresponding processes implemented by the control device in the various methods of the embodiments of the present application. For the sake of brevity, they are not repeated here.

[0122] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0123] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0124] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0125] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above-mentioned method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium, which, when executed, executes the steps of the above-mentioned method embodiment; and the aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, disks or optical disks.

[0126] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods of each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

[0127] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art who is familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for screening high-quality suppliers, characterized in that: Methods include: Collect bidding information, winning bid information and negative behavior identification information of bidding suppliers from the bidding system; Aggregate and statistically process the bidding information, winning bid information, and negative behavior identification information of bidding suppliers, screen out potential abnormal suppliers, high-bid suppliers, and high-bid but low-winning bid suppliers from the bidding suppliers, and select high-bid suppliers and high-bid but low-winning bid suppliers as candidate high-quality suppliers; Adopt association rule analysis method to mine the association relationship between potential abnormal suppliers and high-quality bid suppliers to obtain suppliers with high association, and identify suppliers with high association as suspected abnormal suppliers; Based on the preset indicators of multiple dimensions and the situations in which suppliers are judged as suspected abnormal suppliers, the candidate high-quality suppliers are scored, and the scores of the candidate high-quality suppliers in each dimension are obtained, so that the purchaser can determine the high-quality suppliers based on the scores.

2. The method according to claim 1, characterized in that The bidding information, winning bid information and negative behavior identification information collected from the bidding system include: Obtain project information form, supplier response form, supplier winning bid form and supplier certification form from the bidding system; Obtaining non-failed and completed valid project information from the project information table, and associating the valid project information with the supplier response table to obtain the bidding supplier information associated with the valid project; Obtain bidding information of bidding suppliers by counting bidding supplier information and valid project information; Associate the valid project information and bidding supplier information with the supplier winning bid table to obtain the winning bid information of each bidding supplier; Associate the valid project information and bidding supplier information with the supplier identification table to obtain the behavior identification information of each bidding supplier.

3. The method according to claim 1, characterized in that The bidding information, winning bid information and negative behavior identification information of the bidding suppliers are aggregated and statistically processed to screen out potential abnormal suppliers, high-winning suppliers and high-bidding and low-winning suppliers from the bidding suppliers, including: Aggregate the bidding information, winning bid information, and negative behavior identification information of the bidding supplier to obtain the number of bids, winning bids, and negative behavior identifications of the bidding supplier; The ratio of the number of successful bids of a bidding supplier to the number of bids submitted is determined as the successful bid rate of the bidding supplier, and the ratio of the number of negative behaviors identified by the bidding supplier to the number of bids submitted is determined as the abnormal rate of the bidding supplier; Based on a preset high bid number threshold and the number of bids of the bidding suppliers, the high bid supplier is screened out from the bidding suppliers; Based on the preset low winning bid number threshold, high winning bid number threshold and the number of bids of the bidding suppliers, the low winning bid suppliers and the high winning bid suppliers are screened out from the bidding suppliers, and the high bidding suppliers are associated with the low winning bid suppliers to obtain the high bidding low winning bid suppliers; Based on the comparison result between the preset potential abnormal rate threshold and the abnormal rate of the bidding suppliers, the highly abnormal bidding suppliers are screened out from the bidding suppliers, and the high bidding suppliers, the low winning bid suppliers and the highly abnormal bidding suppliers are taken as the potential abnormal suppliers.

4. The method according to claim 1, characterized in that The association rule analysis method is used to mine the association relationship between potential abnormal suppliers and high-bid suppliers to obtain suppliers with high association, and the suppliers with high association are judged as suspected abnormal suppliers, including: The support of each supplier among the potential abnormal suppliers and the high-winning suppliers is calculated respectively, and the set of suppliers whose support is higher than a preset minimum support threshold is taken as a frequent item set; Association rules are extracted from the frequent item sets to obtain association rules and the confidence of the association rules is calculated, the association rules with confidence higher than a preset confidence threshold are taken as strong rules, and the suppliers associated with the strong rules are taken as suspected abnormal suppliers.

5. The method according to claim 4, characterized in that The preset indicators based on multiple dimensions and the situation where the supplier is determined to be a suspected abnormal supplier are used to score the candidate high-quality suppliers, and the scores of the candidate high-quality suppliers in each dimension are obtained, so that the purchaser can determine the high-quality suppliers according to the scores, including: Based on the situation where a supplier is judged as a suspected abnormal supplier, the achievement-driven high reliability ADHR evaluation system is used to score the candidate high-quality suppliers to obtain the corresponding score; Based on at least one of the contract performance, bid evaluation process score, breach of trust behavior, and bid rigging risk, the ADHR evaluation system is used to score the candidate high-quality suppliers and obtain corresponding scores.

6. The method according to claim 5, characterized in that The method also includes: Calculate the total score of the candidate high-quality suppliers based on their scores in each dimension; Rank the candidate high-quality suppliers based on the total score or the score of any dimension.

7. A high-quality supplier screening device, characterized in that: The device includes: The collection module is used to collect the bidding information, winning bid information and negative behavior identification information of the bidding suppliers from the bidding system; Aggregation module, used to aggregate and statistically process the bidding information, winning bid information and negative behavior identification information of bidding suppliers, screen out potential abnormal suppliers, high-bid suppliers and high-bid but low-winning bid suppliers from the bidding suppliers, and select high-bid suppliers and high-bid but low-winning bid suppliers as candidate high-quality suppliers; The association module is used to mine the association relationship between potential abnormal suppliers and high-quality bidders to obtain suppliers with high association, and to identify suppliers with high association as suspected abnormal suppliers; The scoring module is used to score candidate high-quality suppliers based on preset indicators in multiple dimensions and situations where they are judged to be suspected abnormal suppliers, and obtain the scores of the candidate high-quality suppliers in each dimension so that the purchaser can determine the high-quality suppliers based on the scores.

8. A communication device, characterized in that: include: at least one processor; as well as a memory communicatively connected to at least one processor; wherein, The memory stores instructions that can be executed by at least one processor, and the instructions are executed by at least one processor to enable the at least one processor to perform the method of any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are for causing a computer to execute a method according to any one of claims 1 to 6.

10. A computer program product, characterized in that It comprises a computer program which, when executed by a processor, implements the method according to any one of claims 1 to 6.

Citation Information

Cited By

  • Bidding supplier relation analysis method and device

    CN119204200A

  • A bidding supplier relationship analysis method and device

    CN119204200B

  • Cross-border e-commerce supply chain financial risk monitoring system based on big data acquisition

    CN119991299A

  • Information processing method and device, electronic equipment and computer readable storage medium

    CN121387876A