A bidding supplier relationship analysis method and device

Abstract

The present invention provides a bidding supplier relationship analysis method and device, which relates to the field of computer application technology. The method includes: obtaining historical bidding data of multiple suppliers; scanning the historical bidding data through an improved Apriori algorithm, recording the number of participating projects of each supplier; collecting suppliers whose number of participating projects is greater than or equal to a support threshold according to the number of participating projects of each supplier, and constructing a first frequent item set; self-connecting the first frequent item set to construct a second frequent item set; connecting the second frequent item set with the first frequent item set to construct a third frequent item set; and performing bidding supplier relationship analysis according to the second frequent item set and the third frequent item set. The present invention can directly compare the connection result with the support threshold, without scanning the entire database and performing support comparison, thereby reducing I / O and CPU overhead.

Description

Technical Field

[0001] The present invention relates to the field of computer application technology, and in particular to a bidding supplier relationship analysis method and device. Background Art

[0002] As market competition intensifies, suppliers' bidding behaviors in commercial procurement and bidding have become more complex, gradually forming a network of competition and cooperation. These networks not only profoundly affect the market competition landscape, but also directly affect the quality of purchasers' decision-making. In recent years, with the rapid development of big data, data mining and machine learning technologies, in-depth analysis of suppliers' bidding behaviors has become possible, and purchasers can more effectively identify suppliers' behavior patterns and assess the risks of bid rigging.

[0003] In the prior art, the Apriori algorithm is usually used to mine frequent itemsets to analyze the frequent combination relationships in supplier bidding behaviors. Through this algorithm, the association relationship between suppliers can be mined from the suppliers' historical bidding data, thereby helping the purchaser to determine whether there is bid-rigging behavior. The Apriori algorithm finds frequent itemsets that meet the minimum support threshold through layer-by-layer connection and pruning operations. These itemsets can be used to identify the cooperation mode between suppliers, so they have been widely used in the field of big data mining.

[0004] However, the traditional Apriori algorithm has some obvious shortcomings when processing large-scale bidding data. First, when generating candidate item sets at each step, too many candidate combinations will be generated, resulting in the pruning process consuming a lot of CPU resources. Second, each time the support of frequent item sets is calculated, the entire database needs to be scanned and the support comparison is performed, which increases the I / O and CPU overhead. Summary of the invention

[0005] In order to solve the technical problem that the traditional bidding supplier relationship analysis method generates too many candidate combinations when generating candidate item sets in each step, resulting in the pruning process consuming a large amount of CPU resources, and each time the support of frequent item sets is calculated, the entire database needs to be scanned and the support comparison is performed, which increases the I / O and CPU overhead, the present invention provides a bidding supplier relationship analysis method and device.

[0006] The technical solution provided by the embodiment of the present invention is as follows:

[0007] First aspect:

[0008] An embodiment of the present invention provides a bidding supplier relationship analysis method, comprising:

[0009] S1: Obtain historical bidding data of multiple suppliers;

[0010] S2: Scan the historical bidding data through the improved Apriori algorithm and record the number of projects participated by each supplier;

[0011] S3: According to the number of projects participated by each supplier, suppliers whose number of projects participated is greater than or equal to the support threshold are collected to construct the first frequent itemset;

[0012] S4: self-connect the first frequent itemsets to construct a second frequent itemset;

[0013] S5: Connect the second frequent itemset with the first frequent itemset to construct a third frequent itemset;

[0014] S6: Repeat step S5 until no new frequent item sets can be created;

[0015] S7: Perform bidding supplier relationship analysis based on the second frequent itemsets and the third frequent itemsets.

[0016] Second aspect:

[0017] An embodiment of the present invention provides a bidding supplier relationship analysis device, comprising:

[0018] The acquisition module is used to obtain historical bidding data of multiple suppliers;

[0019] A recording module, used to scan the historical bidding data and record the number of projects participated by each supplier through an improved Apriori algorithm;

[0020] The first construction module is used to collect suppliers whose number of participating projects is greater than or equal to the support threshold according to the number of participating projects of each supplier, and construct a first frequent itemset;

[0021] A second construction module, configured to self-connect the first frequent itemsets to construct a second frequent itemset;

[0022] A third construction module, configured to connect the second frequent item set with the first frequent item set to construct a third frequent item set;

[0023] The analysis module is used to perform bidding supplier relationship analysis based on the second frequent item set and the third frequent item set.

[0024] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0025] In the present invention, an improved Apriori algorithm is used to scan historical bidding data, record the number of projects participated by each supplier, collect suppliers whose number of projects participated is greater than or equal to a support threshold according to the number of projects participated by each supplier, construct a first frequent item set, self-connect the first frequent item set, construct a second frequent item set, connect the second frequent item set with the first frequent item set, construct a third frequent item set, directly use the generated frequent item sets for connection, avoid generating too many candidate combinations, do not need an additional pruning process, thereby reducing the CPU resources consumed by the pruning process, directly compare the connection result with the support threshold, do not need to scan the entire database and perform support comparison, and reduce I / O and CPU overhead. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0027] Figure 1 A schematic diagram of a process for analyzing the relationship between bidding suppliers provided by an embodiment of the present invention;

[0028] Figure 2 A schematic diagram of the structure of a bidding supplier relationship analysis device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0029] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0030] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "example" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "example" is intended to present the concept in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or it can be either of the two.

[0031] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0032] Reference Manual Attached Figure 1 , showing a flow chart of a bidding supplier relationship analysis method provided by an embodiment of the present invention.

[0033] The embodiment of the present invention provides a bidding supplier relationship analysis method, which can be implemented by a bidding supplier relationship analysis device, and the bidding supplier relationship analysis device can be a terminal or a server. The processing flow of the bidding supplier relationship analysis method may include the following steps:

[0034] S1: Obtain historical bidding data of multiple suppliers.

[0035] S2: Scan historical bidding data through the improved Apriori algorithm and record the number of projects participated by each supplier.

[0036] It should be noted that the improved Apriori algorithm is mainly optimized in the following aspects: in each round of calculation, instead of traversing the entire historical bidding data set like the traditional Apriori algorithm, each round of frequent itemsets is directly associated with the first frequent itemset (L1) for calculation, and support analysis is directly performed when connecting, which reduces unnecessary pruning process and data scanning, thereby significantly reducing the computational complexity and resource consumption, and improving the execution efficiency of the algorithm.

[0037] It should be noted that participation in a project is equivalent to support.

[0038] Among them, the Apriori algorithm is a classic data mining algorithm for mining frequent item sets and association rules. Its core working principle is based on the "prior property", that is, if an item set is frequent, then all its subsets must also be frequent. The algorithm first finds frequent 1-item sets from the database, then gradually generates higher-dimensional candidate item sets through self-connection, and removes item sets that are unlikely to be frequent through pruning. In each round of calculation, the database is scanned to count the support, and the item sets with support greater than or equal to the minimum threshold are retained until no new frequent item sets can be generated.

[0039] In the present invention, the improved Apriori algorithm avoids repeated scanning of the entire data set, but directly associates and calculates the frequent itemsets generated in each round with the first frequent itemset (L1), thereby reducing unnecessary data access and calculation times. This greatly reduces the time complexity of the algorithm, and is particularly suitable for processing massive bidding data. The improved Apriori algorithm directly performs support analysis when associating, and the pruning process is built into the calculation, and no additional steps are required to generate and prune candidate itemsets. This not only simplifies the algorithm process, but also improves operating efficiency.

[0040] S3: According to the number of projects participated by each supplier, suppliers whose number of projects participated is greater than or equal to the support threshold are collected to construct the first frequent itemset.

[0041] Specifically, according to the number of projects participated by each supplier, suppliers that meet the condition (the number of projects participated by the supplier is greater than or equal to the support threshold) are screened out. Only suppliers that meet this condition will be collected and constitute the first frequent item set L1.

[0042] In the present invention, suppliers are screened by the support threshold, and only qualified suppliers are retained, and those suppliers who do not frequently participate in bidding are eliminated, thereby significantly reducing the amount of data to be processed in subsequent calculations. By screening out suppliers who frequently participate in bidding (i.e. suppliers whose support is greater than or equal to the threshold), constructing L1 can quickly lock in potential high-frequency supplier combinations. This process lays the foundation for the connection and frequent item set generation in the subsequent steps, avoiding re-traversal and screening of low-frequency data in subsequent calculations.

[0043] S4: Self-connect the first frequent itemset to construct the second frequent itemset.

[0044] In the present invention, in the process of mining frequent itemsets, it is ensured that the elements (i.e., suppliers) in each itemset are high frequency, which means that they are more highly correlated. By self-connecting the first frequent itemset to generate the second frequent itemset, not only valuable supplier combinations are retained, but also subsequent association rule analysis is ensured to be more accurate.

[0045] In a possible implementation, S4 specifically includes sub-steps S401 to S403:

[0046] S401: Connect each supplier in the first frequent item set in pairs to obtain multiple first supplier combinations.

[0047] S402: Obtain the number of projects jointly participated by the suppliers in the first supplier combination through intersection operation.

[0048] S403: According to the number of suppliers in the first supplier combination and the number of projects jointly participated by each supplier, first supplier combinations that meet the first preset condition are collected to construct a second frequent itemset.

[0049] The first preset condition is specifically:

[0050] The number of suppliers in the first supplier combination is equal to the first preset number of suppliers, and the number of common participating projects between the suppliers in the first supplier combination is greater than or equal to the support threshold.

[0051] Specifically, each supplier in the first frequent item set is connected in pairs to obtain multiple first supplier combinations. The number of projects jointly participated by each supplier in the first supplier combination is obtained through intersection operation. According to the number of suppliers in the first supplier combination and the number of projects jointly participated by each supplier, the first supplier combinations that meet the conditions (1. The number of suppliers in the first supplier combination is equal to the first preset number of suppliers. 2. The number of projects jointly participated by each supplier in the first supplier combination is greater than or equal to the support threshold) are screened out. Only the first supplier combinations that meet both conditions will be collected and constitute the first frequent item set L2.

[0052] In the present invention, by connecting the suppliers in the first frequent item set in pairs, it is possible to effectively discover combinations of multiple suppliers participating in the project, thereby mining higher-dimensional supplier cooperation relationships. In this way, cooperation or collusion between suppliers can be identified, which is not limited to the behavior of a single supplier, but also extends to the cooperation of two or more suppliers. The number of projects jointly participated by the supplier combination is calculated through the intersection operation, and the frequency of each supplier combination can be quickly determined. In this way, only the intersection between suppliers needs to be calculated instead of rescanning the entire data set, which significantly reduces the computational complexity. Based on the support threshold, those supplier combinations whose number of jointly participated projects is greater than or equal to the threshold are screened out to ensure that the retained combinations have a high degree of correlation in the project. This process effectively excludes those combinations that do not frequently or occasionally participate in bidding, ensuring the concentration and effectiveness of the analysis.

[0053] S5: Connect the second frequent itemset with the first frequent itemset to construct a third frequent itemset.

[0054] In the present invention, since the first frequent itemset (L1) and the second frequent itemset (L2) have been screened, the subsequent connection step only involves the elements of these frequent itemsets, avoiding redundant calculations for a large number of low-frequency or irrelevant suppliers. This enables the algorithm to effectively save computing resources and reduce the load on memory and CPU when processing large-scale data. By connecting the second frequent itemset with the first frequent itemset, the support of the supplier combination (i.e., the number of jointly participating projects) can be calculated more accurately. This accurate calculation of support can help further filter out the third frequent itemset (L3) that meets the minimum support threshold, avoiding the generation of low-frequency, unimportant supplier combinations.

[0055] In a possible implementation, S5 specifically includes sub-steps S501 to S503:

[0056] S501: Connect each supplier combination in the second frequent itemset with each supplier in the frequent itemset to obtain a plurality of second supplier combinations.

[0057] S502: Obtain the number of projects jointly participated by the suppliers in the second supplier combination through intersection operation.

[0058] S503: According to the number of suppliers in the second supplier combination and the number of projects jointly participated by each supplier, second supplier combinations that meet the second preset condition are collected to construct a third frequent itemset.

[0059] The second preset condition is specifically:

[0060] The number of suppliers in the second supplier combination is equal to the second preset number of suppliers, and the number of common participating projects between the suppliers in the second supplier combination is greater than or equal to the support threshold.

[0061] Specifically, each supplier combination in the second frequent item set is connected with each supplier in the frequent item set to obtain multiple second supplier combinations. The number of projects jointly participated by each supplier in the second supplier combination is obtained through intersection operation. According to the number of suppliers in the second supplier combination and the number of projects jointly participated by each supplier, the first supplier combination that meets the conditions (1. The number of suppliers in the second supplier combination is equal to the second preset number of suppliers. 2. The number of projects jointly participated by each supplier in the second supplier combination is greater than or equal to the support threshold) is screened out. Only the first supplier combinations that meet both conditions will be collected and constitute the third frequent item set L3.

[0062] In the present invention, by gradually expanding frequent item sets, the algorithm does not need to build a high-dimensional supplier combination from scratch, but connects based on the existing frequent item sets (L1, L2) to generate L3. This progressive method reduces the repeated scanning and pruning steps in the overall calculation process and avoids repeated processing of the full amount of data. The second preset condition is used for screening to ensure that the supplier combination generated in each round has a certain frequency and commercial significance, so that irrelevant data and low-frequency supplier combinations can be effectively filtered out. This screening mechanism reduces the processing of useless data and improves the overall efficiency of data processing. Constructing the third frequent item set (L3) is the basis for further generating higher-dimensional frequent item sets. Through this process, the algorithm gradually generates a high-dimensional item set containing multiple suppliers, and can continue to expand to the fourth and fifth frequent item sets according to actual needs. This extended analysis method provides support for subsequent more complex supplier behavior and partnership analysis.

[0063] S6: Repeat step S5 until no new frequent item sets can be created.

[0064] It should be noted that starting from step S5, that is, in the process of generating the third frequent item set and subsequent higher-dimensional frequent item sets, the newly created frequent item set L k Connect with the first frequent item set L1. In this way, frequent item sets of higher dimensions are constructed layer by layer. Each time a connection is made, the number of common projects of each supplier combination is calculated by intersection operation. In the connected supplier combination, the supplier combination that meets the conditions (1. The number of suppliers in the supplier combination is equal to the preset number of suppliers. 2. The number of common projects between suppliers is greater than or equal to the support threshold) is screened out. Only supplier combinations that meet both conditions will be collected and form a new frequent item set L k , each time a round of L is completed k After connecting with L1, if no new frequent item set L can be generated k+1 , that is, all combinations that meet the conditions have been calculated and there are no more new combinations that meet the conditions, the algorithm ends, and the frequent item set L is finally output k , which can be used for subsequent bidding supplier relationship analysis. This frequent item set contains all eligible supplier combinations and can provide the purchaser with the basis for possible cooperation or bid-rigging behaviors among suppliers. Where k=2,3,…,N, N represents the dimension of the maximum frequent item set.

[0065] In the present invention, by gradually connecting the newly created frequent item sets L k Compared with the first frequent item set L1, a higher-dimensional frequent item set can be effectively discovered and constructed, thereby accurately calculating the number of common projects between suppliers. This method ensures that the combinations generated in each round meet the preset conditions, improves the efficiency of the algorithm, and reduces redundant calculations. In addition, by limiting the collection of only combinations that meet the conditions, it can effectively filter out low-frequency and irrelevant supplier combinations, providing a more reliable basis for subsequent bidding supplier relationship analysis.

[0066] S7: Based on the second frequent item set and the third frequent item set, perform bidding supplier relationship analysis.

[0067] It should be noted that those skilled in the art can set the support threshold, the first preset number of suppliers, and the second preset number of suppliers according to actual needs, and the present invention is not limited thereto.

[0068] In the present invention, the bidding supplier relationship analysis is performed based on the second frequent item set and the third frequent item set, which can deeply explore the cooperative relationship between suppliers and potential bid-rigging behaviors. This analysis can help the purchaser identify high-frequency cooperative supplier combinations, thereby optimizing procurement decisions and risk management. In addition, the technicians are allowed to adjust the support threshold and the preset number of suppliers according to actual needs, so that the algorithm has flexibility, can adapt to different scenarios and data characteristics, and improve the accuracy and practicality of the analysis results.

[0069] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0070] In the present invention, an improved Apriori algorithm is used to scan historical bidding data, record the number of projects participated by each supplier, collect suppliers whose number of projects participated is greater than or equal to a support threshold according to the number of projects participated by each supplier, construct a first frequent item set, self-connect the first frequent item set, construct a second frequent item set, connect the second frequent item set with the first frequent item set, construct a third frequent item set, directly use the generated frequent item sets for connection, avoid generating too many candidate combinations, do not need an additional pruning process, thereby reducing the CPU resources consumed by the pruning process, directly compare the connection result with the support threshold, do not need to scan the entire database and perform support comparison, and reduce I / O and CPU overhead.

[0071] Reference Manual Attached Figure 2 , showing a structural schematic diagram of a bidding supplier relationship analysis device provided by the present invention.

[0072] The present invention also provides a bidding supplier relationship analysis device 20, comprising:

[0073] The acquisition module 201 is used to acquire historical bidding data of multiple suppliers.

[0074] The recording module 202 is used to scan the historical bidding data and record the number of projects participated by each supplier through the improved Apriori algorithm.

[0075] The first construction module 203 is used to collect suppliers whose number of participating projects is greater than or equal to the support threshold according to the number of participating projects of each supplier, and construct a first frequent itemset.

[0076] The second construction module 204 is used to self-connect the first frequent itemsets to construct second frequent itemsets.

[0077] The third construction module 205 is used to connect the second frequent itemset with the first frequent itemset to construct a third frequent itemset.

[0078] The analysis module 206 is used to perform bidding supplier relationship analysis based on the second frequent itemset and the third frequent itemset.

[0079] Furthermore, the second building module 204 is specifically used for:

[0080] The suppliers in the first frequent item set are connected in pairs to obtain multiple first supplier combinations.

[0081] The number of common projects among the suppliers in the first supplier combination is obtained through the intersection operation.

[0082] According to the number of suppliers in the first supplier combination and the number of projects jointly participated by the suppliers, first supplier combinations that meet the first preset condition are collected to construct a second frequent item set.

[0083] Furthermore, the first preset condition is specifically:

[0084] The number of suppliers in the first supplier combination is equal to the first preset number of suppliers, and the number of common participating projects between the suppliers in the first supplier combination is greater than or equal to the support threshold.

[0085] Furthermore, the third building block 205 is specifically used for:

[0086] Each supplier combination in the second frequent item set is connected with each supplier in the frequent item set to obtain multiple second supplier combinations.

[0087] The number of common projects among the suppliers in the second supplier combination is obtained through the intersection operation.

[0088] According to the number of suppliers in the second supplier combination and the number of projects jointly participated by each supplier, the second supplier combinations that meet the second preset condition are collected to construct a third frequent item set.

[0089] Furthermore, the second preset condition is specifically:

[0090] The number of suppliers in the second supplier combination is equal to the second preset number of suppliers, and the number of common participating projects between the suppliers in the second supplier combination is greater than or equal to the support threshold.

[0091] It should be noted that the bidding supplier relationship analysis device 20 can implement the above-mentioned bidding supplier relationship analysis method and can achieve the same or similar technical effects. To avoid repetition, the present invention will not go into details.

[0092] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0093] In the present invention, an improved Apriori algorithm is used to scan historical bidding data, record the number of projects participated by each supplier, collect suppliers whose number of projects participated is greater than or equal to a support threshold according to the number of projects participated by each supplier, construct a first frequent item set, self-connect the first frequent item set, construct a second frequent item set, connect the second frequent item set with the first frequent item set, construct a third frequent item set, directly use the generated frequent item sets for connection, avoid generating too many candidate combinations, do not need an additional pruning process, thereby reducing the CPU resources consumed by the pruning process, directly compare the connection result with the support threshold, do not need to scan the entire database and perform support comparison, and reduce I / O and CPU overhead.

[0094] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art 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.

[0095] There are a few points to note:

[0096] (1) The drawings of the embodiments of the present invention only involve structures related to the embodiments of the present invention. Other structures may refer to conventional designs.

[0097] (2) For the sake of clarity, in the drawings used to describe the embodiments of the present invention, the thickness of layers or regions is exaggerated or reduced, that is, these drawings are not drawn according to the actual scale. It is understood that when an element such as a layer, film, region or substrate is referred to as being "on" or "under" another element, the element may be "directly" "on" or "under" the other element or there may be intermediate elements.

[0098] (3) In the absence of conflict, the embodiments of the present invention and the features therein may be combined with each other to obtain new embodiments.

[0099] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. The protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A bidding supplier relationship analysis method, characterized in that: include: S1: Obtain historical bidding data of multiple suppliers; S2: Scan the historical bidding data through the improved Apriori algorithm and record the number of projects participated by each supplier; S3: According to the number of projects participated by each supplier, suppliers whose number of projects participated is greater than or equal to the support threshold are collected to construct the first frequent itemset; S4: self-connect the first frequent itemsets to construct a second frequent itemset; S5: Connect the second frequent itemset with the first frequent itemset to construct a third frequent itemset; S6: Repeat step S5 until no new frequent item sets can be created; S7: performing bidding supplier relationship analysis according to the second frequent item set and the third frequent item set; Wherein, the S5 specifically includes: S501: Connect each supplier combination in the second frequent item set with each supplier in the frequent item set to obtain multiple second supplier combinations; S502: Obtaining the number of projects jointly participated by each supplier in the second supplier combination through an intersection operation; S503: According to the number of suppliers in the second supplier combination and the number of projects jointly participated by each supplier, second supplier combinations that meet the second preset condition are collected to construct the third frequent itemset.

2. The bidding supplier relationship analysis method according to claim 1 is characterized in that: The S4 specifically includes: S401: Connecting suppliers in the first frequent item set in pairs to obtain multiple first supplier combinations; S402: Obtaining the number of projects jointly participated by each supplier in the first supplier combination through intersection operation; S403: According to the number of suppliers in the first supplier combination and the number of projects jointly participated by each supplier, first supplier combinations that meet the first preset condition are collected to construct the second frequent itemsets.

3. The bidding supplier relationship analysis method according to claim 2 is characterized in that: The first preset condition is specifically: The number of suppliers in the first supplier combination is equal to the first preset number of suppliers, and the number of common participating projects between the suppliers in the first supplier combination is greater than or equal to the support threshold.

4. The bidding supplier relationship analysis method according to claim 1 is characterized in that: The second preset condition is specifically: The number of suppliers in the second supplier combination is equal to the second preset number of suppliers, and the number of common participating projects between the suppliers in the second supplier combination is greater than or equal to the support threshold.

5. A bidding supplier relationship analysis device, characterized in that: The bidding supplier relationship analysis device is used to implement the bidding supplier relationship analysis method according to any one of claims 1 to 4, wherein the device specifically comprises: The acquisition module is used to obtain historical bidding data of multiple suppliers; A recording module, used to scan the historical bidding data and record the number of projects participated by each supplier through an improved Apriori algorithm; The first construction module is used to collect suppliers whose number of participating projects is greater than or equal to the support threshold according to the number of participating projects of each supplier, and construct a first frequent itemset; A second construction module, configured to self-connect the first frequent itemsets to construct a second frequent itemset; A third construction module, configured to connect the second frequent item set with the first frequent item set to construct a third frequent item set; an analysis module, configured to perform bidding supplier relationship analysis based on the second frequent itemset and the third frequent itemset; Wherein, the third building block is specifically used for: Connecting each supplier combination in the second frequent item set with each supplier in the frequent item set to obtain multiple second supplier combinations; Obtaining the number of common projects between the suppliers in the second supplier combination through an intersection operation; According to the number of suppliers in the second supplier combination and the number of projects jointly participated by each supplier, second supplier combinations that meet the second preset condition are collected to construct the third frequent item set.

6. The bidding supplier relationship analysis device according to claim 5, characterized in that: The second building block is specifically used for: Connecting each supplier in the first frequent item set in pairs to obtain multiple first supplier combinations; Obtaining the number of projects jointly participated by each supplier in the first supplier combination through an intersection operation; According to the number of suppliers in the first supplier combination and the number of projects jointly participated by each supplier, first supplier combinations that meet the first preset condition are collected to construct the second frequent item sets.

7. The bidding supplier relationship analysis device according to claim 6, characterized in that: The first preset condition is specifically: The number of suppliers in the first supplier combination is equal to the first preset number of suppliers, and the number of common participating projects between the suppliers in the first supplier combination is greater than or equal to the support threshold.

8. The bidding supplier relationship analysis device according to claim 5, characterized in that: The second preset condition is specifically: The number of suppliers in the second supplier combination is equal to the second preset number of suppliers, and the number of common participating projects between the suppliers in the second supplier combination is greater than or equal to the support threshold.

Images