Electronic component intelligent dynamic transaction matching method and device based on AI, medium and equipment

Abstract

The invention relates to an AI-based electronic component intelligent dynamic transaction matching method and device, a medium and equipment, and the method comprises the steps: responding to a transaction matching request, and dynamically determining a matching target transaction party from transaction sellers selling electronic components corresponding to the names of the electronic components according to the names of the electronic components; constructing a transaction weighted directed graph by taking a transaction matching intermediate party as an intermediate node, the matching target transaction party as a source point and the transaction matching request as a sink according to the matching request quantity carried in the transaction matching request and the sales quantity of the matching target transaction party; according to the capacity of the edge in each path from each source point to a sink through an intermediate node in the transaction weighted directed graph, determining a plurality of matched paths in a mode of searching the maximum tradeable volume of an augmented path; and determining an intelligent dynamic transaction matching result according to the maximum tradeable volume in the plurality of matching paths, and displaying introduction information of the electronic component in response to a selected browsing operation on the intelligent dynamic transaction matching result.

Description

Technical Field

[0001] The present invention relates to the cross-technical field of e-commerce and artificial intelligence, and in particular to an AI-based intelligent dynamic transaction matching method, device, medium and equipment for electronic components. Background Art

[0002] Traditional B2B platforms rely on manual price inquiries, have low price transparency (for example, the price difference of a certain capacitor model in different channels is as high as 30%), low matching efficiency, and an average transaction requires 5-7 days of manual negotiation. Fluctuations in delivery cycles during special periods result in 60% of orders needing to be re-matched. Summary of the invention

[0003] The purpose of the present invention is to provide an AI-based intelligent dynamic transaction matching method, device, medium and equipment for electronic components to solve the technical problem of low efficiency of electronic component transaction matching in related scenarios.

[0004] The first aspect of the present disclosure provides an AI-based intelligent dynamic transaction matching method for electronic components, the method being applied to a transaction matching intermediary, the method comprising: In response to receiving a transaction matching request, dynamically determining a matching target transaction party for electronic component transaction matching from transaction sellers that sell electronic components corresponding to the electronic component names according to the electronic component names carried in the transaction matching request; According to the matching request amount carried in the transaction matching request and the sales amount of each matching target transaction party, a transaction weighted directed graph is constructed with the transaction matching intermediary as an intermediate node, the matching target transaction party as a source point, and the transaction matching request as a sink point, wherein the capacity of the edge in the transaction weighted directed graph is determined according to the sales amount and the matching request amount; According to the capacity of the edges in each path from each source point in the transaction weighted directed graph through the intermediate node to the sink point, by finding the maximum tradable amount of the augmented path, determining multiple matching paths for the matching target transaction party to trade with the transaction request party through the intermediate node; Based on the maximum tradable quantity in the multiple matching paths, an intelligent dynamic transaction matching result for the transaction matching request is determined, and in response to a selection and browsing operation on the displayed intelligent dynamic transaction matching result, introduction information on electronic components of the matching target transaction party corresponding to the selected intelligent dynamic transaction matching result is displayed.

[0005] In a possible implementation, the transaction weighted directed graph is constructed based on the matching request amount carried in the transaction matching request and the sales amount of each matching target transaction party, with the transaction matching intermediary as the intermediate node, the matching target transaction party as the source point, and the transaction matching request as the sink point, including: Dynamically determine the credibility coefficient of each of the matching target transaction parties according to the historical fulfillment rate of each of the matching target transaction parties for the sales volume; Determine the price-sensitive edge weights from each source point to the intermediate node in the transaction weighted directed graph according to the transaction quotation of the matching target transaction party for the electronic component and the expected price corresponding to the transaction matching request; Determine the delivery-time-sensitive edge weights from each source point to the intermediate node in the transaction weighted directed graph according to the promised delivery cycle of the matching target transaction party for the electronic component, the number of historical overdue days corresponding to the matching target transaction party, and the expected delivery cycle corresponding to the transaction matching request; Determine the capacity of the edge from the source point to the intermediate node corresponding to each matching target transaction party in the transaction weighted directed graph according to the credibility coefficient of each matching target transaction party, the price-sensitive edge weight, the delivery-time-sensitive edge weight, and the product of the smaller value of the sales volume corresponding to each matching target transaction party and the matching request volume; According to the matching request amount carried in the transaction matching request, the capacity of the edge from the sink to the intermediate node in the transaction weighted directed graph is determined, and according to the capacity of the edge from the source point to the intermediate node corresponding to each matching target transaction party in the transaction weighted directed graph and the capacity of the edge from the sink to the intermediate node, the transaction weighted directed graph is constructed.

[0006] In a possible implementation, determining the price-sensitive edge weights from each source point to the intermediate node in the transaction weighted directed graph according to the transaction quotation of the matching target transaction party for the electronic component and the expected price of the transaction matching request includes: Determining a transaction quotation diameter according to a first quotation difference between a highest transaction quotation and a lowest transaction quotation among transaction quotations of the matching target transaction party for the electronic component; Determine an average transaction quotation according to the transaction quotation of each matching target transaction party for the electronic component and the time offset between each transaction quotation and the current time; Determining a transaction quotation offset corresponding to each of the matching target transaction parties according to an absolute value of a second quotation difference between a transaction quotation of each of the matching target transaction parties for the electronic component and the average transaction quotation; The price-sensitive edge weights from each source point to the intermediate node in the transaction weighted directed graph are determined based on the ratio of the transaction quotation offset corresponding to each of the matched target transaction parties to the transaction quotation diameter, and the product of the weight attenuation coefficient corresponding to the preset deviation threshold range in which the ratio is located, wherein each of the preset deviation threshold ranges is provided with a one-to-one corresponding weight attenuation coefficient.

[0007] In a possible implementation, determining the average transaction quotation according to the transaction quotation of each matching target transaction party for the electronic component and the time offset between each transaction quotation and the current time includes: Determine the adaptive volatility according to the preset volatility and the mean and standard deviation of the transaction quotations corresponding to each of the matching target transaction parties within a preset historical time period from the current time; Determine the attenuation weight corresponding to each of the matching target trading parties according to the time offset between the transaction quote corresponding to each of the matching target trading parties and the current time and the adaptive volatility; Determine the attenuated transaction quotation corresponding to each of the matching target transaction parties according to the product of the attenuation weight corresponding to each of the matching target transaction parties and the corresponding transaction quotation of the electronic component; According to the attenuated transaction quotations corresponding to the matched target transaction parties, a sum of attenuated transaction quotations is determined, and according to the attenuation weights corresponding to the matched target transaction parties, an attenuation coefficient is determined by summing up; The average transaction quotation is determined according to the ratio of the sum of the attenuated transaction quotations to the attenuation coefficient.

[0008] In a possible implementation, determining the delivery-sensitive edge weights from each source point to the intermediate node in the transaction weighted directed graph according to the promised delivery cycle of the matching target transaction party for the electronic component, the number of historical overdue days corresponding to the matching target transaction party, and the expected delivery cycle corresponding to the transaction matching request includes: Determine the fulfillment decay rate corresponding to each of the matching target transaction parties according to the number of historical overdue days corresponding to each of the matching target transaction parties; According to the fulfillment decay rate corresponding to each of the matching target transaction parties and the cycle difference between the promised delivery cycle of the electronic components by each of the matching target transaction parties and the expected delivery cycle corresponding to the transaction matching request, the delivery-sensitive edge weights from each source point to the intermediate node in the transaction weighted directed graph are determined.

[0009] In a possible implementation, the determining of multiple matching paths for the matching target transaction party to trade with the transaction request party via the intermediate node by finding the maximum tradable amount of the augmented path according to the capacity of the edges in each path from each source point via the intermediate node to the sink point in the transaction weighted directed graph includes: Constructing a residual network according to each path from each source point in the transaction weighted directed graph through the intermediate node to the sink point; Determining the residual capacity of all edges in the residual network according to a breadth-first search or a depth-first search; According to the capacity of the edges in each path from each source point through the intermediate node to the sink point in the transaction weighted directed graph, by finding the maximum tradable amount of the augmented path, the bottleneck capacity of a single path that meets the matching request quantity supplied by one matching target transaction party alone, or the bottleneck capacity of a combined path that meets the matching request quantity supplied by multiple matching target transaction parties together, is calculated; According to the bottleneck capacity of each of the single paths and / or each of the combined paths, the residual capacity of all edges in the residual network is updated, and a plurality of the single paths and / or the combined paths cannot be obtained in the residual network when performing augmented path finding; According to the multiple single paths and / or the combined paths, multiple matching paths for the matching target transaction party to trade with the transaction request party via the intermediate node are determined.

[0010] In a possible implementation, in response to receiving a transaction matching request, dynamically determining a matching target transaction party for electronic component transaction matching from transaction sellers that sell electronic components corresponding to the electronic component names according to the electronic component names carried in the transaction matching request, includes: In response to receiving the transaction matching request, querying, according to the electronic component name carried in the transaction matching request, a transaction seller of the electronic component corresponding to the electronic component name registered with the transaction matching intermediary; Determine the number of times and frequency of historical browsing of each of the transaction sellers in the transaction matching intermediary; According to the number of times and frequency of historical browsing of each transaction seller at the transaction matching intermediary, a matching target transaction party for electronic component transaction matching is dynamically determined from transaction sellers selling electronic components corresponding to the electronic component names.

[0011] A second aspect of the present disclosure provides an AI-based intelligent dynamic transaction matching device for electronic components, which is applied to a transaction matching intermediary, and the device includes: A first determination module is configured to, in response to receiving a transaction matching request, dynamically determine a matching target transaction party for electronic component transaction matching from transaction sellers that sell electronic components corresponding to the electronic component name according to the electronic component name carried in the transaction matching request; The second determination module is configured to construct a transaction weighted directed graph according to the matching request amount carried in the transaction matching request and the sales amount of each matching target transaction party, with the transaction matching intermediary as the intermediate node, the matching target transaction party as the source point, and the transaction matching request as the sink point, wherein the capacity of the edge in the transaction weighted directed graph is determined according to the sales amount and the matching request amount; A third determination module is configured to determine, according to the capacity of the edges in each path from each source point in the transaction weighted directed graph through the intermediate node to the sink point, a plurality of matching paths for the matching target transaction party to trade with the transaction request party through the intermediate node by finding the maximum tradable amount of the augmented path; The fourth determination module is configured to determine the intelligent dynamic transaction matching result for the transaction matching request based on the maximum tradable quantity in the multiple matching paths, and in response to a selection and browsing operation on the displayed intelligent dynamic transaction matching result, display the introduction information of the electronic components of the matching target transaction party corresponding to the selected intelligent dynamic transaction matching result.

[0012] A third aspect of the present disclosure provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any one of the methods described in the first aspect.

[0013] A fourth aspect of the present disclosure provides an electronic device, including: a memory having a computer program stored thereon; A processor is used to execute the computer program in the memory to implement the steps of any one of the methods in the first aspect.

[0014] The above technical solution can at least have the following beneficial effects: By responding to transaction requests in real time and dynamically screening target sellers, the inefficiency of traditional traversal matching is avoided, and the time complexity of matching is reduced. The transaction problem is converted into a maximum flow problem of a weighted directed graph, and the optimal allocation plan is quickly calculated using the augmenting path algorithm to ensure that the splitting and path planning of complex transaction volumes are completed within milliseconds. By constructing a weighted graph from multiple sources (sellers) to sinks (requesters), large orders can be intelligently split to multiple suppliers to avoid transaction failures caused by insufficient inventory of a single supplier. The capacity of the edge is determined by the real-time sales volume and the request volume to ensure the feasibility of the transaction. The transaction plan is displayed with multiple matching paths, and users can intuitively compare the price, delivery date and other dimensions of different combinations. After selecting the matching result, the detailed information of the supplier is directly displayed to reduce the user jump link and improve the decision-making efficiency. At the same time, the construction and solution of the transaction weighted directed graph can be deployed in a distributed computing framework, supporting real-time computing of millions of nodes, and adapting to the large-scale electronic component trading market. When a path fails due to temporary shortage of suppliers, the augmenting path can be quickly recalculated to ensure the continuity of transaction matching. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The present invention will be further described below in conjunction with the accompanying drawings.

[0016] Figure 1 It is a flow chart of an AI-based intelligent dynamic transaction matching method for electronic components according to an embodiment of the specification.

[0017] Figure 2 It is a block diagram of an AI-based intelligent dynamic transaction matching device for electronic components according to an embodiment of the specification.

[0018] Figure 3 It is a block diagram of a display screen device according to an embodiment of the specification. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0020] like Figure 1 The flowchart of the method for intelligent dynamic transaction matching of electronic components based on AI of the present invention is shown. The method is applied to a transaction matching intermediary, wherein the transaction matching intermediary can provide, for example, a website or an application to a terminal device such as a computer or a mobile phone through a server, and a user can generate a transaction matching request through operations such as search or query on the website or application. The method includes: In step S11, in response to receiving a transaction matching request, dynamically determining a matching target transaction party for electronic component transaction matching from transaction sellers of electronic components corresponding to the electronic component name according to the electronic component name carried in the transaction matching request; Dynamic determination can be based on real-time data (such as inventory, supplier ratings, historical transaction success rates, etc.) and AI models to screen qualified sellers in real time, rather than relying on static rules. Electronic component name matching can be achieved by accurately matching the component name in the request with the components in the seller's database through natural language processing (NLP) or a predefined component classification system.

[0021] In the disclosed embodiment, the electronic component name, matching request quantity, quality requirements and other parameters in the transaction matching request are parsed. Then, the sellers can be dynamically sorted according to the following features through an AI model (such as GBDT or deep learning model): Inventory matching: whether the current inventory meets the demand.

[0022] Transaction evaluation: historical transaction scores (such as on-time delivery rate, quality pass rate).

[0023] Price competitiveness: the ratio of the quotation to the market price.

[0024] Output: A prioritized list of target sellers.

[0025] For example, a transaction matching request is made to purchase 1,000 "resistors X". Supplier A (score 4.9) with an inventory of ≥1,000, supplier B (score 4.8) with an inventory of 800, and supplier C (score 4.7) with an inventory of 500 are screened out. After dynamic sorting, A is given priority. If A is out of stock, B and C are matched in turn.

[0026] In step S12, according to the matching request amount carried in the transaction matching request and the sales amount of each matching target transaction party, a transaction weighted directed graph is constructed with the transaction matching intermediary as an intermediate node, the matching target transaction party as a source point, and the transaction matching request as a sink point, wherein the capacity of the edge in the transaction weighted directed graph is determined according to the sales amount and the matching request amount; In the weighted directed graph, each edge has a direction (such as supplier to intermediary to requester) and a weight (capacity), which indicates the upper limit of transaction flow. The intermediate node is the transaction matching intermediary as the hub node in the graph, connecting all source points (suppliers) and sink points (requesters).

[0027] In the disclosed embodiment, the capacity of the edge from the source node to the intermediate node in the transaction weighted directed graph can be determined based on the current available inventory (i.e., sales volume) of the supplier and the matching request volume. The capacity of the edge from the intermediate node to the sink in the transaction weighted directed graph is the transaction request volume (if the request volume is split, the capacity of this edge is the total request volume).

[0028] For example, a request is made to purchase 1,000 components, supplier A has 800 in stock, and supplier B has 600 in stock.

[0029] Build a graph: A to the intermediary (capacity 800), B to the intermediary (capacity 600), the intermediary to the requester (capacity 1000). At this time, an algorithm is needed to calculate how to allocate the inventory of A and B to meet the demand of 1000.

[0030] In step S13, according to the capacity of the edges in each path from each source point through the intermediate node to the sink point in the transaction weighted directed graph, multiple matching paths for the matching target transaction party to trade with the transaction request party through the intermediate node are determined by finding the maximum tradable amount of the augmented path; Among them, the augmenting path is the path from the source to the sink in the weighted directed graph, and the remaining capacity (current capacity - allocated amount) of each edge on the path is greater than 0. The maximum tradable volume is the minimum remaining capacity (bottleneck value) of the path in the augmenting path, which determines the maximum transaction volume that can be allocated on the path.

[0031] In the disclosed embodiment, the Edmonds-Karp algorithm (the shortest augmenting path algorithm based on BFS) can be used, and the time complexity is O(E²V). The iterative process can be: Find the augmenting path: find the shortest path from any source point to the sink point through BFS. Calculate the bottleneck value: the minimum value of the remaining capacity in the path. Update the allocation: assign the bottleneck value to the edge on the path to reduce the remaining capacity. Repeat the iteration: until no new augmenting path can be found.

[0032] For example, the initial graph: A to the intermediary (capacity 800), B to the intermediary (capacity 600), the intermediary to the requester (capacity 1000).

[0033] First iteration: Find path A from the middle party to the requester, with a bottleneck value of 800 (the capacity of A). After allocating 800, the remaining capacity of A is 0, and the remaining capacity from the middle party to the requester is 200.

[0034] Second iteration: Find path B to the middle party to the requester, with a bottleneck value of 200 (remaining requests). After allocating 200, B's remaining capacity is 400, and the total allocation of the requester reaches 1000.

[0035] Result: A provides 800 pieces and B provides 200 pieces, completing the match.

[0036] In step S14, based on the maximum tradable quantity in the multiple matching paths, the intelligent dynamic transaction matching result for the transaction matching request is determined, and in response to a selection and browsing operation on the displayed intelligent dynamic transaction matching result, the introduction information of the electronic components of the matching target transaction party corresponding to the selected intelligent dynamic transaction matching result is displayed.

[0037] Among them, the intelligent dynamic transaction matching result is the output multi-path allocation plan (such as supplier combination and allocation amount). The selected browsing operation is the user's interactive behavior on the matching result (such as clicking to view details).

[0038] In the disclosed embodiment, the multi-path allocation scheme is converted into structured data (such as JSON), including supplier ID, allocation amount, price, etc.

[0039] Front-end display: Matching result list: Display multiple feasible solutions by priority (such as "Solution 1: A+B, total cost X; Solution 2: B only, total cost Y"). After the user clicks on the solution, the detailed introduction of the supplier (such as quality inspection report, logistics information) is obtained through API call.

[0040] The above technical solution avoids the inefficiency of traditional traversal matching by responding to transaction requests in real time and dynamically screening target sellers, thus reducing the time complexity of matching. The transaction problem is converted into a maximum flow problem of a weighted directed graph, and the optimal allocation scheme is quickly calculated using the augmenting path algorithm to ensure that the splitting and path planning of complex transaction volumes are completed within milliseconds. By constructing a weighted graph from multiple sources (sellers) to sinks (requesters), large orders can be intelligently split to multiple suppliers to avoid transaction failures caused by insufficient inventory of a single supplier. The capacity of the edge is determined by the real-time sales volume and the request volume to ensure the feasibility of the transaction. The transaction plan is displayed with multiple matching paths, and users can intuitively compare the price, delivery date and other dimensions of different combinations. After selecting the matching result, the detailed information of the supplier is directly displayed to reduce the user jump link and improve the decision-making efficiency. At the same time, the construction and solution of the weighted directed graph of the transaction can be deployed in a distributed computing framework, supporting real-time computing of millions of nodes, and adapting to the large-scale electronic component trading market. When a path fails due to temporary shortage of suppliers, the augmenting path can be quickly recalculated to ensure the continuity of transaction matching.

[0041] In a possible implementation, in step S12, according to the matching request amount carried in the transaction matching request and the sales amount of each matching target transaction party, a transaction weighted directed graph is constructed with the transaction matching intermediary as an intermediate node, the matching target transaction party as a source point, and the transaction matching request as a sink point, including: In step S121, the credibility coefficient of each matching target transaction party is dynamically determined according to the historical fulfillment rate of each matching target transaction party for the sales volume; The historical fulfillment rate is the proportion of transactions completed by suppliers in the past (on-time delivery and qualified quality). The fulfillment rate can be mapped to a coefficient in the [0,1] interval to adjust the priority of suppliers in transaction matching.

[0042] In the disclosed embodiment, the supplier's fulfillment records of the past N transactions (such as the most recent 100 orders) are obtained in real time to calculate the historical fulfillment rate. The fulfillment rate is converted into a credibility coefficient through a nonlinear function (such as Sigmoid) to amplify the advantage of a high fulfillment rate. For example, the credibility coefficient = 1 / (1+e −k⋅(履约率−θ) ).

[0043] In step S122, according to the transaction quotation of the matching target transaction party for the electronic component and the expected price corresponding to the transaction matching request, the price-sensitive edge weights from each source point to the intermediate node in the transaction weighted directed graph are determined; The price-sensitive edge weight is used to reflect the degree of deviation between the supplier's quotation and the requester's expected price. For example, the difference between the transaction quotation of the matching target transaction party for the electronic component and the expected price corresponding to the transaction matching request can be divided by the expected price and then multiplied by the price sensitivity coefficient to obtain the price parameter, and then the natural exponential function is determined according to the price parameter to obtain the price-sensitive edge weight.

[0044] In step S123, according to the promised delivery period of the matching target transaction party for the electronic component, the number of historical overdue days corresponding to the matching target transaction party, and the expected delivery period corresponding to the transaction matching request, the delivery-sensitive edge weights from each source point to the intermediate node in the transaction weighted directed graph are determined; Among them, the delivery-sensitive edge weight is used to comprehensively consider the matching degree between the supplier's promised delivery cycle, the number of historical overdue days, and the requester's expected cycle. For example, the delivery-sensitive edge weight can be determined according to the following formula: Delivery time deviation ΔT i Calculation: ΔT = promised delivery cycle t i −Expected period T; Delivery risk A i =β×T i +γ×historical overdue days, where β is the delivery date deviation coefficient and γ is the historical overdue penalty coefficient.

[0045] The delivery risk A is transformed into i Convert to weights in the [0,1] interval: Delivery-sensitive edge weight: , where n is the number of matching target transaction parties.

[0046] In step S124, the capacity of the edge from the source point to the intermediate node corresponding to each matching target transaction party in the transaction weighted directed graph is determined according to the credibility coefficient of each matching target transaction party, the price-sensitive edge weight, the delivery-time-sensitive edge weight, and the product of the smaller value of the sales volume corresponding to each matching target transaction party and the matching request volume; Among them, the edge capacity (Edge Capacity) is in a weighted directed graph, which represents the maximum tradable quantity from the source point (supplier) to the intermediate node (transaction matching intermediary), which requires comprehensive consideration of factors such as reliability, price, and delivery time.

[0047] In the disclosed embodiment, the capacity of an edge = credibility coefficient × price-sensitive edge weight × delivery-sensitive edge weight × min (sold volume, matching request volume).

[0048] In step S125, the capacity of the edge from the sink to the intermediate node in the transaction weighted directed graph is determined according to the matching request quantity carried in the transaction matching request, and the transaction weighted directed graph is constructed according to the capacity of the edge from the source point to the intermediate node corresponding to each matching target transaction party in the transaction weighted directed graph and the capacity of the edge from the sink to the intermediate node.

[0049] In the disclosed embodiment, the sink is used to represent the transaction matching requester and needs to receive traffic from the intermediate node (matching intermediate party). The transaction matching problem can be transformed into a network flow problem, and the optimal matching can be achieved through the capacity constraint of the edge.

[0050] In the disclosed embodiment, the capacity of the sink edge is determined as follows: the edge capacity from the sink to the intermediate node is equal to the matching request amount. Graph structure construction: From the source to the intermediate node: the capacity of each edge is the value calculated in step S124. From the intermediate node to the sink: the edge capacity is the matching request amount. The maximum feasible flow from all source points to the sink is found through the maximum flow algorithm (such as Ford-Fulkerson), that is, the matching solution.

[0051] The above technical solution converts the supplier's historical performance, price competitiveness, and delivery reliability into calculable weights. The credibility coefficient and weight jointly determine the matching order of suppliers to avoid giving priority to "low-price but high-risk" suppliers. When constructing a weighted directed graph, cost, delivery, and reliability are comprehensively considered rather than a single indicator. Reliability, price, delivery, and supply / demand are then converted into edge capacity to avoid single indicator decisions. The capacity of the edge changes with the real-time status of the supplier (such as inventory, quotation), and supports dynamic adjustment. The global optimal matching solution is found through the maximum flow algorithm, rather than the local optimal solution. Suppliers with high price / delivery risks have lower edge capacity, reducing the probability of being selected.

[0052] In a possible implementation, in step S122, determining the price-sensitive edge weights from each source point to the intermediate node in the transaction weighted directed graph according to the transaction quotation of the matching target transaction party for the electronic component and the expected price of the transaction matching request includes: In step S1221, a transaction quotation diameter is determined according to a first quotation difference between a highest transaction quotation and a lowest transaction quotation in transaction quotations of the matching target transaction party for the electronic component; Among them, the transaction quotation diameter (Price Diameter) is the difference between the maximum and minimum quotations of all target transaction sellers, reflecting the degree of dispersion of the quotations and measuring the fluctuation range of the quotations.

[0053] In step S1222, an average transaction quotation is determined according to the transaction quotation of each matching target transaction party for the electronic component and the time offset between each transaction quotation and the current time; Among them, the time offset is the time difference between the current time and the quotation time (such as hours / days), which is used to measure the timeliness of the quotation. The average transaction quotation is weighted according to the time offset, and the newer the quotation, the higher the weight.

[0054]

[0055] Among them, V is the average transaction price calculated this time, v i is the transaction quotation of the i-th matching target trading party, △t i is the time offset of the i-th matching target trading party. is the attenuation coefficient, which is used to control the speed of the influence of time weight and reduce the weight of outdated quotes.

[0056] In step S1223, the transaction quotation offset corresponding to each of the matching target transaction parties is determined according to the absolute value of the second quotation difference between the transaction quotation of each of the matching target transaction parties for the electronic component and the average transaction quotation; Among them, the price offset is the absolute difference between a single quote and the average transaction quote, reflecting the degree of outlier of the quote.

[0057] In step S1224, the price-sensitive edge weights from each source point to the intermediate node in the transaction weighted directed graph are determined based on the ratio of the transaction quotation offset corresponding to each of the matched target transaction parties to the transaction quotation diameter, and the product of the weight attenuation coefficient corresponding to the preset deviation threshold range in which the ratio is located, wherein each of the preset deviation threshold ranges is set with a one-to-one corresponding weight attenuation coefficient.

[0058] The deviation threshold range is a preset offset ratio interval (such as 0-0.3, 0.3-0.6, 0.6-1.0), corresponding to different weight decay coefficients. The weight decay coefficient is used to reduce the edge weight coefficient according to the degree of deviation.

[0059] In the disclosed embodiment, the relative deviation of the quotation is quantified by the ratio, and the deviation is converted into the edge weight using the threshold range and the attenuation coefficient. The larger the ratio, the farther the quotation deviates from the average, but the attenuation coefficient may reduce its impact and prevent extreme values ​​from excessively affecting the weight. Specific quotation data can be set, the diameter, offset, and ratio can be calculated, and then the attenuation coefficient can be determined according to the preset threshold range, and finally the price-sensitive edge weight can be obtained.

[0060] By presetting multiple deviation threshold ranges, the continuous deviation ratio is divided into discrete risk levels, which facilitates differentiated treatment of quotations with different deviation degrees. According to the risk level interval of the quotation deviation ratio, the corresponding attenuation coefficient is selected and multiplied by the deviation ratio to obtain the final edge weight. The greater the deviation (the higher the risk), the greater the edge weight, but the attenuation coefficient will limit its growth to avoid excessive influence of extreme quotations on matching results.

[0061] The above technical solution combines time decay and offset to avoid a single quote or outdated data dominating the weight. The supplier with a greater deviation from the average quote has a higher edge weight. The decay coefficient is used to limit the impact of extreme quotes to prevent the weight from being too large or too small. Parameters such as quote diameter and offset are clarified to facilitate debugging and strategy adjustment.

[0062] In a possible implementation, in step S1222, determining an average transaction quotation according to the transaction quotation of each matching target transaction party for the electronic component and the time offset between each transaction quotation and the current time includes: In step S12221, an adaptive volatility is determined according to a preset volatility and the mean and standard deviation of the transaction quotations corresponding to each of the matching target transaction parties within a preset historical time period from the current time; Among them, Volatility: an indicator to measure the volatility of quotes, usually expressed as standard deviation. Adaptive Volatility: a volatility parameter that is dynamically adjusted based on the mean, standard deviation and preset volatility of historical quotes.

[0063] In the disclosed embodiment, the volatility of historical quotations and preset parameters are combined to enable volatility to adapt to market changes in different time periods. The mean (μ) and standard deviation (σ) of historical quotations are calculated. If the current quotation volatility (σ) exceeds the preset volatility threshold, the adaptive volatility is equal to σ; otherwise, it is equal to the preset value.

[0064] In step S12222, the attenuation weight corresponding to each of the matching target transaction parties is determined according to the time offset between the transaction quotation corresponding to each of the matching target transaction parties and the current time and the adaptive volatility; Among them, Time Offset: the time difference between the current time and the quote time (such as hours / days). Decay Weight: a weight based on the time offset and adaptive volatility, used to reduce the impact of outdated quotes.

[0065] In the disclosed embodiment, attenuation weight = e -自适应波动率×时间偏移量 , the larger the time offset (the older the quotes), or the higher the adaptive volatility (the more volatile the market), the smaller the decay weight.

[0066] In step S12223, the attenuated transaction quotation corresponding to each of the matching target transaction parties is determined according to the product of the attenuation weight corresponding to each of the matching target transaction parties and the corresponding transaction quotation of the electronic component; The decayed transaction quote is the product of the original quote and the decay weight, reflecting the current reference value of the quote. The decay weight of the outdated quote is lower, and its decayed transaction quote is also lower, reducing its impact on the average.

[0067] In step S12224, the sum of the attenuated transaction quotations corresponding to the matched target transaction parties is determined by summing up, and the attenuation coefficient is determined by summing up the attenuation weights corresponding to the matched target transaction parties; The sum of decay transaction quotes is the accumulation of all decay transaction quotes, which is used for subsequent weighted averaging. The sum of decay coefficients is the accumulation of all decay weights to ensure weight normalization.

[0068] In step S12225, the average transaction quotation is determined according to the ratio of the sum of the attenuated transaction quotations to the attenuation coefficient.

[0069] The average transaction quote is the average of quotes that takes time decay and volatility into account.

[0070] In the disclosed embodiment, an average quotation closer to the current market level is obtained by calculating the ratio of the sum of attenuated transaction quotations to the sum of attenuation coefficients.

[0071] The above technical solution automatically calibrates volatility based on historical data to adapt to different market environments. It reduces the weight of outdated quotes to prevent historical data from interfering with current decisions. It also considers quote volatility and time factors to make the average quote more reasonable. By attenuating weights and adaptive volatility, it clarifies the time value of quotes and the impact of market fluctuations.

[0072] In a possible implementation, in step S123, determining the delivery-sensitive edge weights from each source point to the intermediate node in the transaction weighted directed graph according to the promised delivery cycle of the matching target transaction party for the electronic component, the number of historical overdue days corresponding to the matching target transaction party, and the expected delivery cycle corresponding to the transaction matching request includes: In step S1231, the fulfillment decay rate corresponding to each of the matching target transaction parties is determined according to the number of historical overdue days corresponding to each of the matching target transaction parties; The historical overdue days is the total number of days that the supplier's actual delivery cycle exceeds the promised cycle in past transactions. The fulfillment decay rate is an indicator used to measure the supplier's fulfillment ability. The more overdue days, the higher the decay rate (indicating lower reliability).

[0073] In the disclosed embodiment, the total number of days overdue of suppliers in the evaluation period (such as the past 12 months) is counted, and the number of days overdue is divided by the total number of days in the evaluation period to obtain the fulfillment decay rate.

[0074] In step S1232, the delivery-sensitive edge weights from each source point to the intermediate node in the transaction weighted directed graph are determined based on the fulfillment decay rate corresponding to each of the matching target transaction parties and the cycle difference between the promised delivery cycle of each of the matching target transaction parties for the electronic components and the expected delivery cycle corresponding to the transaction matching request.

[0075] Among them, Committed Lead Time is the number of days the supplier promises to deliver. Desired Lead Time is the number of days the requester expects to deliver. Cycle Difference is the difference between the committed lead time and the desired lead time (which may be a negative value).

[0076] In the disclosed embodiment, the cycle difference is calculated: if the committed cycle is greater than the expected cycle, the difference is positive; otherwise, it is negative. Combined with the fulfillment decay rate, the difference is converted into an edge weight.

[0077] The weight of the delivery-sensitive edge = |cycle difference| × (1-fulfillment decay rate), where the absolute value is used to ensure that the positive or negative difference does not affect the weight, and only the deviation is considered. 1-fulfillment decay rate is used to reduce the impact of the decay rate (the higher the decay rate, the smaller the weight increase).

[0078] The above technical solution uses the historical overdue days to convert the reliability of suppliers into a decay rate to avoid subjective judgment. Through the product of the cycle difference and the decay rate, both delivery deviation and performance risk are punished. The performance decay rate makes the delivery deviation of unreliable suppliers more severely punished. The edge weight directly reflects the superposition effect of delivery deviation and performance risk, which is convenient for subsequent matching algorithm optimization.

[0079] In a possible implementation, in step S13, the method of determining multiple matching paths for the matching target transaction party to trade with the transaction request party via the intermediate node by finding the maximum tradable amount of the augmented path according to the capacity of the edges in each path from each source point in the transaction weighted directed graph via the intermediate node to the sink point includes: In step S131, a residual network is constructed according to each path from each source point in the transaction weighted directed graph through the intermediate node to the sink point; Among them, the residual network is an auxiliary network built based on the original weighted directed graph, which is used to calculate the maximum flow. The augmented path is a feasible path from the source to the sink in the residual network, and its edge capacity is not fully utilized.

[0080] In the disclosed embodiment, a reverse edge is added to each edge in the original graph, and the initial capacity is 0. The residual capacity is defined as the remaining capacity of the forward edge (initial capacity minus the allocated flow) or the reflowable capacity of the reverse edge (allocated flow). The residual network is used to dynamically track the available capacity of the edge.

[0081] In step S132, the residual capacity of all edges in the residual network is determined according to a breadth-first search or a depth-first search; Among them, breadth-first search (BFS) can traverse the nodes of the graph layer by layer to find the shortest path. Depth-first search (DFS) can traverse deeply along a single path and backtrack to find other paths. Residual Capacity is the remaining available capacity of the edge under the current allocation.

[0082] In the disclosed embodiment, BFS or DFS is used to traverse the residual network and calculate the residual capacity of each edge. Forward edge residual capacity = initial capacity - allocated flow; reverse edge residual capacity = allocated flow. If the residual capacity > 0, the edge can participate in the augmenting path.

[0083] In step S133, according to the capacity of the edges in each path from each source point through the intermediate node to the sink point in the transaction weighted directed graph, by finding the maximum tradable amount of the augmented path, the bottleneck capacity of a single path that the matching target transaction party supplies alone to meet the matching request amount, or the bottleneck capacity of a combined path that multiple matching target transaction parties jointly supply to meet the matching request amount is calculated; The bottleneck capacity is the edge with the smallest capacity in the augmented path, which determines the maximum tradable volume of the path. A single path is a complete transaction path involving only one supplier. A combined path is a collection of parallel or serial paths in which multiple suppliers collaborate to supply.

[0084] In the disclosed embodiment, for each augmented path, all its edges are traversed to find the minimum residual capacity as the bottleneck capacity. The bottleneck capacity of a single path directly limits the transaction volume of the path. The bottleneck capacity of a combined path needs to comprehensively consider the capacity limitations of each sub-path (e.g., the minimum value is taken for a parallel path, and the sum of the minimum values ​​of each segment is taken for a serial path).

[0085] In step S134, the residual capacity of all edges in the residual network is updated according to the bottleneck capacity of each of the single paths and / or each of the combined paths, and a plurality of the single paths and / or the combined paths cannot be obtained in the residual network when performing augmented path finding; Among them, the residual capacity update is to adjust the residual network according to the flow distribution of the augmented path. The Max-Flow Min-Cut Theorem is that the maximum flow of the network is equal to the capacity of the minimum cut.

[0086] In the disclosed embodiment, for each augmented path, the flow is allocated according to the bottleneck capacity. The residual network is updated: the residual capacity of the forward edge -= the bottleneck capacity. The residual capacity of the reverse edge += the bottleneck capacity. The augmented path is repeatedly searched until there is no feasible path in the residual network (i.e., the maximum flow is achieved).

[0087] In step S135, multiple matching paths for the matching target transaction party to trade with the transaction request party via the intermediate node are determined based on the multiple single paths and / or the combined paths.

[0088] In the disclosed embodiment, all augmented paths and their allocated traffic are collected. A matching path list is generated based on the provider combination and traffic allocation of the path. It is ensured that the total allocated traffic is equal to the transaction request volume and that the traffic of each path does not exceed its bottleneck capacity.

[0089] Through the above steps, the transaction matching problem is transformed into a network maximum flow problem to ensure global optimization. The available capacity is updated in real time through the residual network, supporting multi-round path optimization and realizing dynamic capacity allocation. It allows flexible matching of a single supplier or a combination of suppliers to improve transaction robustness. Combining BFS / DFS and bottleneck capacity calculation, it is guaranteed to find a feasible solution in polynomial time.

[0090] In a possible implementation, in step S11, in response to receiving the transaction matching request, dynamically determining a matching target transaction party for electronic component transaction matching from transaction sellers that sell electronic components corresponding to the electronic component names according to the electronic component names carried in the transaction matching request, including: In step S111, in response to receiving the transaction matching request, querying the transaction seller of the electronic component corresponding to the electronic component name registered in the transaction matching intermediary according to the electronic component name carried in the transaction matching request; In the disclosed embodiment, a database may be maintained to record all electronic components registered for sale and their corresponding seller information. When a transaction matching request is received, the system queries the database to obtain a list of all sellers selling the component according to the electronic component name in the request. The query result may include metadata such as the seller's name, historical transaction records, inventory information, etc.

[0091] In step S112, the number of times and frequency of historical browsing of each of the transaction sellers on the transaction matching intermediary is determined; Among them, the Historical View Count is the total number of times the electronic components on the platform are viewed by potential buyers. The View Frequency is the statistical value of the number of views within a preset time period (such as the average daily views).

[0092] In the disclosed embodiment, the browsing log of each electronic component of the seller is recorded, including the timestamp and the information of the viewer. The number of views is calculated by counting the total number of browsing records of the component in the log. The browsing frequency is obtained by dividing the number of views within a time window (such as the last 30 days) by the length of the time window. The frequency calculation needs to take into account time decay (such as a higher weight for recent views).

[0093] In step S113, according to the historical browsing times and browsing frequencies of each transaction seller in the transaction matching intermediary, a matching target transaction party for electronic component transaction matching is dynamically determined from the transaction sellers selling the electronic components corresponding to the electronic component names.

[0094] In the disclosed embodiment, the number of views and frequency are combined to construct a "attention" index (such as a weighted sum or product) of the seller. The attention index reflects the market attractiveness and potential transaction willingness of the seller. The sellers are sorted according to the attention, and the sellers with the highest ranking are selected as matching targets. A threshold mechanism (such as only selecting sellers with a frequency higher than a certain value) or hierarchical screening (such as filtering by component type or region) can be introduced.

[0095] Through the above steps, the browsing behavior data is used to quantify the seller's attractiveness, avoiding subjective judgment. The browsing index is updated in real time to reflect changes in market popularity and improve dynamic adaptability. The matching range is narrowed to sellers with high attention, reducing the calculation amount of subsequent matching algorithms and improving matching efficiency.

[0096] The disclosed embodiment also provides an AI-based electronic component intelligent dynamic transaction matching device, which is applied to the transaction matching middleman, see Figure 2 As shown, the device comprises: The first determination module 210 is configured to, in response to receiving a transaction matching request, dynamically determine a matching target transaction party for electronic component transaction matching from transaction sellers that sell electronic components corresponding to the electronic component name according to the electronic component name carried in the transaction matching request; The second determination module 220 is configured to construct a transaction weighted directed graph according to the matching request amount carried in the transaction matching request and the sales amount of each matching target transaction party, with the transaction matching intermediary as the intermediate node, the matching target transaction party as the source point, and the transaction matching request as the sink point, wherein the capacity of the edge in the transaction weighted directed graph is determined according to the sales amount and the matching request amount; The third determination module 230 is configured to determine multiple matching paths for the matching target transaction party to trade with the transaction request party via the intermediate node by finding the maximum tradable amount of the augmented path according to the capacity of the edges in each path from each source point in the transaction weighted directed graph via the intermediate node to the sink point; The fourth determination module 240 is configured to determine the intelligent dynamic transaction matching result for the transaction matching request based on the maximum tradable quantity in the multiple matching paths, and in response to a selection and browsing operation on the displayed intelligent dynamic transaction matching result, display the introduction information of the electronic components of the matching target transaction party corresponding to the selected intelligent dynamic transaction matching result.

[0097] In a possible implementation, the second determining module 220 is configured to: Dynamically determine the credibility coefficient of each of the matching target transaction parties according to the historical fulfillment rate of each of the matching target transaction parties for the sales volume; Determine the price-sensitive edge weights from each source point to the intermediate node in the transaction weighted directed graph according to the transaction quotation of the matching target transaction party for the electronic component and the expected price corresponding to the transaction matching request; Determine the delivery-time-sensitive edge weights from each source point to the intermediate node in the transaction weighted directed graph according to the promised delivery cycle of the matching target transaction party for the electronic component, the number of historical overdue days corresponding to the matching target transaction party, and the expected delivery cycle corresponding to the transaction matching request; Determine the capacity of the edge from the source point to the intermediate node corresponding to each matching target transaction party in the transaction weighted directed graph according to the credibility coefficient of each matching target transaction party, the price-sensitive edge weight, the delivery-time-sensitive edge weight, and the product of the smaller value of the sales volume corresponding to each matching target transaction party and the matching request volume; According to the matching request amount carried in the transaction matching request, the capacity of the edge from the sink to the intermediate node in the transaction weighted directed graph is determined, and according to the capacity of the edge from the source point to the intermediate node corresponding to each matching target transaction party in the transaction weighted directed graph and the capacity of the edge from the sink to the intermediate node, the transaction weighted directed graph is constructed.

[0098] In a possible implementation, the second determining module 220 is configured to: Determining a transaction quotation diameter according to a first quotation difference between a highest transaction quotation and a lowest transaction quotation among transaction quotations of the matching target transaction party for the electronic component; Determine an average transaction quotation according to the transaction quotation of each matching target transaction party for the electronic component and the time offset between each transaction quotation and the current time; Determining a transaction quotation offset corresponding to each of the matching target transaction parties according to an absolute value of a second quotation difference between a transaction quotation of each of the matching target transaction parties for the electronic component and the average transaction quotation; The price-sensitive edge weights from each source point to the intermediate node in the transaction weighted directed graph are determined based on the ratio of the transaction quotation offset corresponding to each of the matched target transaction parties to the transaction quotation diameter, and the product of the weight attenuation coefficient corresponding to the preset deviation threshold range in which the ratio is located, wherein each of the preset deviation threshold ranges is provided with a one-to-one corresponding weight attenuation coefficient.

[0099] In a possible implementation, the second determining module 220 is configured to: Determine the adaptive volatility according to the preset volatility and the mean and standard deviation of the transaction quotations corresponding to each of the matching target transaction parties within a preset historical time period from the current time; Determine the attenuation weight corresponding to each of the matching target trading parties according to the time offset between the transaction quote corresponding to each of the matching target trading parties and the current time and the adaptive volatility; Determine the attenuated transaction quotation corresponding to each of the matching target transaction parties according to the product of the attenuation weight corresponding to each of the matching target transaction parties and the corresponding transaction quotation of the electronic component; According to the attenuated transaction quotations corresponding to the matched target transaction parties, a sum of attenuated transaction quotations is determined, and according to the attenuation weights corresponding to the matched target transaction parties, an attenuation coefficient is determined by summing up; The average transaction quotation is determined according to the ratio of the sum of the attenuated transaction quotations to the attenuation coefficient.

[0100] In a possible implementation, the second determining module 220 is configured to: Determine the fulfillment decay rate corresponding to each of the matching target transaction parties according to the number of historical overdue days corresponding to each of the matching target transaction parties; According to the fulfillment decay rate corresponding to each of the matching target transaction parties and the cycle difference between the promised delivery cycle of the electronic components by each of the matching target transaction parties and the expected delivery cycle corresponding to the transaction matching request, the delivery-sensitive edge weights from each source point to the intermediate node in the transaction weighted directed graph are determined.

[0101] In a possible implementation, the third determining module 230 is configured to: Constructing a residual network according to each path from each source point in the transaction weighted directed graph through the intermediate node to the sink point; Determining the residual capacity of all edges in the residual network according to a breadth-first search or a depth-first search; According to the capacity of the edges in each path from each source point through the intermediate node to the sink point in the transaction weighted directed graph, by finding the maximum tradable amount of the augmented path, the bottleneck capacity of a single path that meets the matching request quantity supplied by a matching target transaction party alone, or the bottleneck capacity of a combined path that meets the matching request quantity supplied by multiple matching target transaction parties together, is calculated; According to the bottleneck capacity of each of the single paths and / or each of the combined paths, the residual capacity of all edges in the residual network is updated, and a plurality of the single paths and / or the combined paths cannot be obtained in the residual network when performing augmented path finding; According to the multiple single paths and / or the combined paths, multiple matching paths for the matching target transaction party to trade with the transaction request party via the intermediate node are determined.

[0102] In a possible implementation, the first determining module 210 is configured to: In response to receiving the transaction matching request, querying, according to the electronic component name carried in the transaction matching request, a transaction seller of the electronic component corresponding to the electronic component name registered with the transaction matching intermediary; Determine the number of times and frequency of historical browsing of each of the transaction sellers in the transaction matching intermediary; According to the number of times and frequency of historical browsing of each transaction seller at the transaction matching intermediary, a matching target transaction party for electronic component transaction matching is dynamically determined from transaction sellers selling electronic components corresponding to the electronic component names.

[0103] The present disclosure also provides an electronic device, including: processor; a memory for storing processor-executable instructions; The processor is configured to execute the executable instructions stored in the memory to implement the method described in any one of the aforementioned embodiments.

[0104] The embodiments of the present disclosure further provide a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the method described in any one of the aforementioned embodiments are implemented.

[0105] Figure 3 The AI-based electronic component intelligent dynamic transaction matching device 100 shown can be configured as a server, which displays a user interface in the form of a terminal website, and then receives a transaction matching request or introduction information on the user interface. The device 100 includes: a processor 1001 and a memory 1003. Among them, the processor 1001 and the memory 1003 are connected, such as through a bus 1002. Optionally, the AI-based electronic component intelligent dynamic transaction matching device 100 may also include a communication component 1004, which can be used for data interaction between the device 100 and other devices, such as data sending and / or data receiving. It should be noted that the communication component 1004 is not limited to one in actual scheduling, and the structure of the AI-based electronic component intelligent dynamic transaction matching device 100 does not constitute a limitation on the embodiments of the present application.

[0106] Processor 1001 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. Processor 1001 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0107] The bus 1002 may include a path to transmit information between the above components. The bus 1002 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 1002 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0108] The memory 1003 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), magnetic disk storage medium, other magnetic storage devices, or any other medium that can be used to carry or store program code and can be read by a computer, without limitation herein.

[0109] The memory 1003 is used to store program codes for executing the embodiments of the present disclosure, and the execution is controlled by the processor 1001. The processor 1001 is used to execute the program codes stored in the memory 1003 to implement the steps shown in the embodiment of the aforementioned AI-based electronic component intelligent dynamic transaction matching method.

[0110] The embodiments of the present disclosure also provide a computer-readable storage medium having program code stored thereon. When the program code is executed by a processor, the steps and corresponding contents of the aforementioned AI-based electronic component intelligent dynamic transaction matching method embodiment can be implemented.

[0111] The preferred embodiments of the present disclosure are described in detail above in conjunction with the accompanying drawings; however, the present disclosure is not limited to the specific details in the above embodiments; within the technical concept of the present disclosure, various changes, modifications, substitutions and variations may be made to these embodiments, and these changes, modifications, substitutions and variations all fall within the protection scope of the present disclosure.

[0112] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any appropriate manner without contradiction, and they should also be regarded as the contents disclosed in this disclosure. In order to avoid unnecessary repetition, this disclosure will not further describe various possible combinations. The technical scope of this application is not limited to the contents in the specification, and its technical scope must be determined according to the scope of the claims.

Claims

1. An AI-based intelligent dynamic transaction matching method for electronic components, characterized in that: The method is applied to a transaction matching intermediary, and the method comprises: In response to receiving a transaction matching request, dynamically determining a matching target transaction party for electronic component transaction matching from transaction sellers that sell electronic components corresponding to the electronic component names according to the electronic component names carried in the transaction matching request; According to the matching request amount carried in the transaction matching request and the sales amount of each matching target transaction party, a transaction weighted directed graph is constructed with the transaction matching intermediary as an intermediate node, the matching target transaction party as a source point, and the transaction matching request as a sink point, wherein the capacity of the edge in the transaction weighted directed graph is determined according to the sales amount and the matching request amount; According to the capacity of the edges in each path from each source point in the transaction weighted directed graph through the intermediate node to the sink point, by finding the maximum tradable amount of the augmented path, determining multiple matching paths for the matching target transaction party to trade with the transaction request party through the intermediate node; Based on the maximum tradable quantity in the multiple matching paths, an intelligent dynamic transaction matching result for the transaction matching request is determined, and in response to a selection and browsing operation on the displayed intelligent dynamic transaction matching result, introduction information on electronic components of the matching target transaction party corresponding to the selected intelligent dynamic transaction matching result is displayed.

2. The method according to claim 1, characterized in that The step of constructing a transaction weighted directed graph based on the matching request amount carried in the transaction matching request and the sales amount of each matching target transaction party, with the transaction matching intermediary as the intermediate node, the matching target transaction party as the source point, and the transaction matching request as the sink point, includes: Dynamically determine the credibility coefficient of each of the matching target transaction parties according to the historical fulfillment rate of each of the matching target transaction parties for the sales volume; Determine the price-sensitive edge weights from each source point to the intermediate node in the transaction weighted directed graph according to the transaction quotation of the matching target transaction party for the electronic component and the expected price corresponding to the transaction matching request; Determine the delivery-time-sensitive edge weights from each source point to the intermediate node in the transaction weighted directed graph according to the promised delivery cycle of the matching target transaction party for the electronic component, the number of historical overdue days corresponding to the matching target transaction party, and the expected delivery cycle corresponding to the transaction matching request; Determine the capacity of the edge from the source point to the intermediate node corresponding to each matching target transaction party in the transaction weighted directed graph according to the credibility coefficient of each matching target transaction party, the price-sensitive edge weight, the delivery-time-sensitive edge weight, and the product of the smaller value of the sales volume corresponding to each matching target transaction party and the matching request volume; According to the matching request amount carried in the transaction matching request, the capacity of the edge from the sink to the intermediate node in the transaction weighted directed graph is determined, and according to the capacity of the edge from the source point to the intermediate node corresponding to each matching target transaction party in the transaction weighted directed graph and the capacity of the edge from the sink to the intermediate node, the transaction weighted directed graph is constructed.

3. The method according to claim 2, characterized in that The step of determining the price-sensitive edge weights from each source point to the intermediate node in the transaction weighted directed graph according to the transaction quotation of the matching target transaction party for the electronic component and the expected price of the transaction matching request includes: Determining a transaction quotation diameter according to a first quotation difference between a highest transaction quotation and a lowest transaction quotation among transaction quotations of the matching target transaction party for the electronic component; Determine an average transaction quotation according to the transaction quotation of each matching target transaction party for the electronic component and the time offset between each transaction quotation and the current time; Determining a transaction quotation offset corresponding to each of the matching target transaction parties according to an absolute value of a second quotation difference between a transaction quotation of each of the matching target transaction parties for the electronic component and the average transaction quotation; The price-sensitive edge weights from each source point to the intermediate node in the transaction weighted directed graph are determined based on the ratio of the transaction quotation offset corresponding to each of the matched target transaction parties to the transaction quotation diameter, and the product of the weight attenuation coefficient corresponding to the preset deviation threshold range in which the ratio is located, wherein each of the preset deviation threshold ranges is provided with a one-to-one corresponding weight attenuation coefficient.

4. The method according to claim 3, characterized in that The determining an average transaction quotation according to the transaction quotation of each matching target transaction party for the electronic component and the time offset between each transaction quotation and the current time includes: Determine the adaptive volatility according to the preset volatility and the mean and standard deviation of the transaction quotations corresponding to each of the matching target transaction parties within a preset historical time period from the current time; Determine the attenuation weight corresponding to each of the matching target trading parties according to the time offset between the transaction quote corresponding to each of the matching target trading parties and the current time and the adaptive volatility; Determine the attenuated transaction quotation corresponding to each of the matching target transaction parties according to the product of the attenuation weight corresponding to each of the matching target transaction parties and the corresponding transaction quotation of the electronic component; According to the attenuated transaction quotations corresponding to the matched target transaction parties, a sum of attenuated transaction quotations is determined, and according to the attenuation weights corresponding to the matched target transaction parties, an attenuation coefficient is determined by summing up; The average transaction quotation is determined according to the ratio of the sum of the attenuated transaction quotations to the attenuation coefficient.

5. The method according to claim 2, characterized in that: The step of determining the delivery-time-sensitive edge weights from each source point to the intermediate node in the transaction weighted directed graph according to the promised delivery cycle of the matching target transaction party for the electronic component, the number of historical overdue days corresponding to the matching target transaction party, and the expected delivery cycle corresponding to the transaction matching request includes: Determine the fulfillment decay rate corresponding to each of the matching target transaction parties according to the number of historical overdue days corresponding to each of the matching target transaction parties; According to the fulfillment decay rate corresponding to each of the matching target transaction parties and the cycle difference between the promised delivery cycle of the electronic components by each of the matching target transaction parties and the expected delivery cycle corresponding to the transaction matching request, the delivery-sensitive edge weights from each source point to the intermediate node in the transaction weighted directed graph are determined.

6. The method according to claim 1, characterized in that The determining of multiple matching paths for the matching target transaction party to trade with the transaction request party via the intermediate node by finding the maximum tradable amount of the augmented path according to the capacity of the edges in each path from each source point via the intermediate node to the sink point in the transaction weighted directed graph includes: Constructing a residual network according to each path from each source point in the transaction weighted directed graph through the intermediate node to the sink point; Determining the residual capacity of all edges in the residual network according to a breadth-first search or a depth-first search; According to the capacity of the edges in each path from each source point through the intermediate node to the sink point in the transaction weighted directed graph, by finding the maximum tradable amount of the augmented path, the bottleneck capacity of a single path that meets the matching request quantity supplied by a matching target transaction party alone, or the bottleneck capacity of a combined path that meets the matching request quantity supplied by multiple matching target transaction parties together, is calculated; According to the bottleneck capacity of each of the single paths and / or each of the combined paths, the residual capacity of all edges in the residual network is updated, and a plurality of the single paths and / or the combined paths cannot be obtained in the residual network when performing augmented path finding; According to the multiple single paths and / or the combined paths, multiple matching paths for the matching target transaction party to trade with the transaction request party via the intermediate node are determined.

7. The method according to any one of claims 1 to 6, characterized in that In response to receiving the transaction matching request, dynamically determining a matching target transaction party for electronic component transaction matching from transaction sellers that sell electronic components corresponding to the electronic component names according to the electronic component names carried in the transaction matching request, including: In response to receiving the transaction matching request, querying, according to the electronic component name carried in the transaction matching request, a transaction seller of the electronic component corresponding to the electronic component name registered with the transaction matching intermediary; Determine the number of times and frequency of historical browsing of each of the transaction sellers in the transaction matching intermediary; According to the number of times and frequency of historical browsing of each transaction seller at the transaction matching intermediary, a matching target transaction party for electronic component transaction matching is dynamically determined from transaction sellers selling electronic components corresponding to the electronic component names.

8. An AI-based intelligent dynamic transaction matching device for electronic components, characterized in that: Applied to a transaction matching intermediary, the device comprises: A first determination module is configured to, in response to receiving a transaction matching request, dynamically determine a matching target transaction party for electronic component transaction matching from transaction sellers that sell electronic components corresponding to the electronic component name according to the electronic component name carried in the transaction matching request; The second determination module is configured to construct a transaction weighted directed graph according to the matching request amount carried in the transaction matching request and the sales amount of each matching target transaction party, with the transaction matching intermediary as the intermediate node, the matching target transaction party as the source point, and the transaction matching request as the sink point, wherein the capacity of the edge in the transaction weighted directed graph is determined according to the sales amount and the matching request amount; A third determination module is configured to determine, according to the capacity of the edges in each path from each source point in the transaction weighted directed graph through the intermediate node to the sink point, a plurality of matching paths for the matching target transaction party to trade with the transaction request party through the intermediate node by finding the maximum tradable amount of the augmented path; The fourth determination module is configured to determine the intelligent dynamic transaction matching result for the transaction matching request based on the maximum tradable quantity in the multiple matching paths, and in response to a selection and browsing operation on the displayed intelligent dynamic transaction matching result, display the introduction information of the electronic components of the matching target transaction party corresponding to the selected intelligent dynamic transaction matching result.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method described in any one of claims 1 to 7 are implemented.

10. An electronic device, characterized in that: include: a memory having a computer program stored thereon; A processor, configured to execute the computer program in the memory to implement the steps of the method according to any one of claims 1 to 7.

Images