CN116342234B - Method for realizing automatic bidding purchasing aiming at goods - Google Patents
Method for realizing automatic bidding purchasing aiming at goods Download PDFInfo
- Publication number
- CN116342234B CN116342234B CN202310602079.4A CN202310602079A CN116342234B CN 116342234 B CN116342234 B CN 116342234B CN 202310602079 A CN202310602079 A CN 202310602079A CN 116342234 B CN116342234 B CN 116342234B
- Authority
- CN
- China
- Prior art keywords
- bidding
- bid
- time
- data
- party
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000012216 screening Methods 0.000 claims abstract description 7
- 238000012549 training Methods 0.000 claims description 26
- 238000010801 machine learning Methods 0.000 claims description 16
- 238000011156 evaluation Methods 0.000 claims description 15
- 238000013528 artificial neural network Methods 0.000 claims description 12
- 238000005516 engineering process Methods 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 6
- 239000013598 vector Substances 0.000 claims description 6
- 239000002131 composite material Substances 0.000 claims description 5
- 238000003062 neural network model Methods 0.000 claims description 5
- 230000000630 rising effect Effects 0.000 claims description 3
- GOLXNESZZPUPJE-UHFFFAOYSA-N spiromesifen Chemical compound CC1=CC(C)=CC(C)=C1C(C(O1)=O)=C(OC(=O)CC(C)(C)C)C11CCCC1 GOLXNESZZPUPJE-UHFFFAOYSA-N 0.000 claims description 3
- 238000012545 processing Methods 0.000 abstract description 3
- 238000012797 qualification Methods 0.000 description 3
- 238000012550 audit Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012854 evaluation process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/08—Auctions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0206—Price or cost determination based on market factors
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Physics & Mathematics (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Marketing (AREA)
- Economics (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- General Business, Economics & Management (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method for realizing automatic bidding procurement aiming at goods, which relates to the technical field of automatic bidding of goods, and comprises the steps of collecting to-be-bidding notices and to-be-bidding data uploaded by bidding parties, selecting bidding time based on to-be-bidding data and platform bidding data, screening and matching existing suppliers at the bidding time, selecting qualified suppliers, sending to-be-bidding notices to bid account numbers of the qualified suppliers on an electronic bidding platform, collecting bidding information of each bidding notice in real time, obtaining corresponding bidding data based on the bidding information, automatically evaluating bidding data of bidding parties, obtaining bidding scores, sorting bidding parties from large to small, and displaying to bidding parties; the full-flow automatic processing of automatic bidding of goods is realized, the efficiency and the accuracy are improved, and the labor and the time cost are saved.
Description
Technical Field
The invention belongs to the technology of automatic bidding for goods, and particularly relates to a method for realizing automatic bidding and purchasing for goods.
Background
In modern economies, the bidding and purchasing of goods has become a very popular purchasing mode. The buyer issues the purchase demand by bidding bulletin, and the suppliers compete for the purchase contract by bidding. In the conventional goods bidding purchasing process, a signer needs to compile a bidding document, issue bidding notices, accept bids, evaluate the bidding, bid a series of links such as a lot of manpower, material resources and time cost, and the bid evaluation result may be affected by human factors, for example, in the bid evaluation process, the signer often performs subjective evaluation based on the bidding scheme of the bidding party due to excessive bidding parties, and is difficult to perform comprehensive evaluation by combining the basic information of the bidding party and the bidding and bid history of the bidding party, so that the bid evaluation result is subjectively made; therefore, an automatic intelligent evaluation method capable of comprehensively evaluating each bidding party is needed, and bidding parties are ordered based on the evaluation result, so that the bid evaluation personnel can be helped to make better bid evaluation selection, and the bid evaluation efficiency is improved;
therefore, the invention provides a method for realizing automatic bidding purchasing aiming at goods.
Disclosure of Invention
The present invention aims to solve at least one of the technical problems existing in the prior art. Therefore, the invention provides a method for realizing automatic bidding and purchasing aiming at goods, which realizes the full-flow automatic processing of automatic bidding and purchasing aiming at goods, improves the efficiency and accuracy and saves the labor and time cost.
To achieve the above object, an embodiment according to a first aspect of the present invention provides a method for implementing automatic bidding purchasing for goods, including the steps of:
step one: collecting the to-be-marked bulletin and platform bidding data uploaded by the bidding party in real time, and obtaining corresponding to-be-marked bidding data based on the to-be-marked bulletin;
step two: selecting a bid amount of time based on the bid amount to be displayed and the platform bid amount; screening and matching the existing suppliers at the bidding showing time, selecting suppliers meeting the requirements, and sending to-be-bidding notices to bidding accounts of the suppliers meeting the requirements on an electronic bidding platform;
step three: collecting bidding information of each bidding announcement in real time, and obtaining corresponding bidding data based on the bidding information;
step four: automatically evaluating bidding data of the bidder to obtain bidding scores, and sorting the bidder from large to small based on the bidding scores;
step five: the ordered bidding party is sent to a bidding party account of an electronic bidding platform of a bidding party, and the bidding party account is displayed to the bidding party;
the to-be-bidding bulletin is a bidding document prefabricated by a bidding party, and the bidding party uploads the bidding bulletin to the electronic bidding platform background through a bidding party account of the electronic bidding platform;
the platform bidding data comprises real-time bidding data and historical bidding data;
the real-time bidding data comprise the current real-time bidding quantity of each type of goods, the current real-time bidding party quantity, the current real-time supplier quantity and the current real-time market price of each type of goods in the electronic bidding platform;
the historical bid bidding data comprise bid amount, bid time, bid price and historical bid data of each bid in the history of each type of goods in an electronic bid platform; the historical bid data includes historical bid training data and historical bid tag data;
for each type of goods, the historical bid training data comprises the unit price of each bidding party in each bidding process, the average bidding price in the bidding process, the comprehensive score of the bidding party, the delivery mode, the delivery location and the duration of delivery time from delivery deadline; the historical bid label data is a label of whether each bidding party is bidding in each bidding process;
the to-be-marked bidding data are to-be-marked cargo types, to-be-marked quantity and to-be-marked period read from to-be-marked bulletins by the electronic bidding platform through an NLP technology;
based on the to-be-presented bid data and the platform bid data, the bid presentation time is selected by the following steps:
drawing a bidding frequency curve, a bidding quantity curve and a bidding price curve of the type of goods to be bidding according to the historical bidding data; the bidding frequency curve is a curve formed by connecting newly-shown bidding times of cargoes of the type to be bidding in each unit time; the bidding quantity curve expresses a curve formed by connecting the number of the newly-shown bidding of the goods type to be bidding within each unit time; the bid-winning price curve is formed by connecting bid-winning prices of goods of the type to be bid-awarded with time;
drawing a real-time spot price curve according to the real-time spot price of the goods of the type to be marked;
taking the bidding frequency curve, the bidding quantity curve and the real-time spot price curve as the input of a multi-feature time series prediction neural network model, taking the real-time spot price curve as the prediction curve of the multi-feature time series prediction neural network output, and training the multi-feature time series prediction neural network for bid price according to the bidding frequency curve, the bidding quantity curve and the real-time spot price curve prediction;
generating future bid price of the goods to be bid by using a multi-feature time sequence prediction neural network in real time, and taking the rising time of the predicted future bid price as bid showing time;
the manner in which the qualified suppliers are selected to participate in bidding is as follows:
screening suppliers with business range including goods of the goods type to be marked from all suppliers, and marking the number of each screened supplier as；
Obtaining basic information of each supplier, including company scale, age, employee number, complaint and dispute record number, and marking the company scale, age, employee number, complaint and dispute record number as respectivelyAnd；
obtaining the product and service quality of each provider; the product and the service quality comprise the historical bid amount and the historical bid amount on the electronic bidding platform, and the historical bid amount are respectively marked as and />；
Acquiring price fluctuation information of bid-winning in the history of each provider; the price fluctuation information is the average value of the absolute value of the difference between the bid price and the final bid price, and the average value is marked as；
Obtaining a reputation level of each provider; the reputation level is the number of the finally completed purchases after the merchant history is marked as；
Calculating a composite score for an ith vendorThe method comprises the steps of carrying out a first treatment on the surface of the Wherein, comprehensive score->The calculation formula of (2) is as follows:
； wherein ,/> and />Respectively preset proportional coefficients;
if at firstComprehensive score of home provider->If the score is larger than or equal to the score threshold value according to the preset, marking the score as a supplier meeting the requirements; if%>Of home suppliersComprehensive score->If the score is smaller than the preset score threshold, marking the score as an unsatisfactory supplier;
the bidding information is a bidding document sent to a bidding account number of a bidding party on an electronic bidding platform after each provider meeting the requirements receives a bid-to-be-bidding notice;
based on the bidding information, the corresponding bidding data is obtained by the following steps:
the electronic bidding platform reads the price of goods, delivery mode, delivery place and delivery time from the bidding document by NLP technology;
the bidding data of the bidder is automatically evaluated, and the bidding scores are obtained by the following modes:
the method comprises the steps that historical bid training data of each bidding party in each historical bidding process are used as input of a machine learning model, the machine learning model takes predicted bid winning probability of the bidding party as output, labels of historical bid label data corresponding to the bidding party are used as prediction targets, and the sum of prediction accuracy of all the historical bid training data is minimized to be used as a training target; the calculation formula of the prediction accuracy is as follows:, wherein />jk is>In the secondary bidding process, the machine learning model predicts the bidding probability of the kth bidding party; />Is->In the secondary bidding process, the->Marking historical bid label data of a home bidding party; training the machine learning model until the sum of prediction accuracy reaches convergence, and stopping training; wherein (1)> and />The number of the bidding process and the number of the bidding party are respectively;
combining bidding data of each bidding party, average value of unit price of goods in all bidding data received by bidding account numbers and comprehensive scores of the bidding parties to obtain evaluation vectors, and inputting the evaluation vectors into a machine learning model to obtain probability of bidding in each bidding party; the probability is the bid score.
Compared with the prior art, the invention has the beneficial effects that:
according to the invention, through collecting advertisement to be bid and platform bid-bidding data in advance, based on a cargo price curve, the moment of lower cargo price is automatically selected as bid-bidding showing time, then, based on qualification, historical bid-bidding conditions and the like of each supplier in an electronic bid-bidding platform, automatic qualification audit is carried out on each supplier, and for suppliers passing the qualification audit and sending bidding schemes to bidding parties, based on price, floating condition of price and average price and shipping schemes in the bidding schemes provided by the suppliers, the probability of bid-bidding in the bidding schemes is automatically and intelligently estimated by using a machine learning model, and automatic sequencing display is carried out on the order of the probability of bidding schemes from large to small; therefore, the full-flow automatic processing of automatic bidding of goods is realized, the efficiency and the accuracy are improved, and the labor and time cost are saved.
Drawings
Fig. 1 is a flowchart of a method for implementing automatic bidding and purchasing for goods in embodiment 1 of the present invention.
Detailed Description
The technical solutions of the present invention will be clearly and completely described in connection with the embodiments, and it is obvious that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1
As shown in fig. 1, a method for realizing automatic bidding purchasing for goods comprises the following steps:
step one: collecting the to-be-marked bulletin and platform bidding data uploaded by the bidding party in real time, and obtaining corresponding to-be-marked bidding data based on the to-be-marked bulletin;
step two: selecting a bid amount of time based on the bid amount to be displayed and the platform bid amount; screening and matching the existing suppliers at the bidding showing time, selecting suppliers meeting the requirements, and sending to-be-bidding notices to bidding accounts of the suppliers meeting the requirements on an electronic bidding platform;
step three: collecting bidding information of each bidding announcement in real time, and obtaining corresponding bidding data based on the bidding information;
step four: automatically evaluating bidding data of the bidder to obtain bidding scores, and sorting the bidder from large to small based on the bidding scores;
step five: the ordered bidding party is sent to a bidding party account of an electronic bidding platform of a bidding party, and the bidding party account is displayed to the bidding party;
the to-be-bidding bulletin is a bidding document prefabricated by a bidding party, and the bidding party uploads the bidding bulletin to the electronic bidding platform background through a bidding party account of the electronic bidding platform;
the platform bidding data comprises real-time bidding data and historical bidding data;
the real-time bidding data comprise the current real-time bidding quantity of each type of goods, the current real-time bidding party quantity, the current real-time supplier quantity and the current real-time market price of each type of goods in the electronic bidding platform; it should be noted that, for each type of goods, the number of real-time bidding parties is the number of bidding notices of the type of goods that have been released, the number of real-time bidding is obtained according to the bidding notices, the number of suppliers is obtained according to the operation range provided when the suppliers register the account number of the electronic bidding platform, and the real-time market price is obtained by connecting the real-time spot price of the type of goods with the internet;
the historical bid bidding data comprise bid amount, bid time, bid price and historical bid data of each bid in the history of each type of goods in an electronic bid platform; the historical bid data includes historical bid training data and historical bid tag data;
for each type of goods, the historical bid training data comprises the unit price of each bidding party in each bidding process, the average bidding price in the bidding process, the comprehensive score of the bidding party, the delivery mode, the delivery location and the duration of delivery time from delivery deadline; the historical bid label data is a label of whether each bidding party is bidding in each bidding process; preferably, if the bidding party is bidding, the label of the historical bidding label data corresponding to the bidding party is marked as 1, and if the bidding party is not bidding, the label of the historical bidding label data corresponding to the bidding party is marked as 0;
the to-be-marked bidding data are to-be-marked cargo types, to-be-marked quantity and to-be-marked period read from to-be-marked bulletins by the electronic bidding platform through an NLP technology;
it should be noted that, NLP is a widely applied technology, reading text content and analyzing key information therein is a conventional application, and is not a main solution of the present invention, so the present invention will not be repeated here;
based on the to-be-presented bid data and the platform bid data, the bid presentation time is selected by the following steps:
drawing a bidding frequency curve, a bidding quantity curve and a bidding price curve of the type of goods to be bidding according to the historical bidding data; the bidding frequency curve is a curve formed by connecting newly-shown bidding times of cargoes of the type to be bidding in each unit time; the bidding quantity curve expresses a curve formed by connecting the number of the newly-shown bidding of the goods type to be bidding within each unit time; the bid-winning price curve is formed by connecting bid-winning prices of goods of the type to be bid-awarded with time;
drawing a real-time spot price curve according to the real-time spot price of the goods of the type to be marked;
taking the bidding frequency curve, the bidding quantity curve and the real-time spot price curve as the input of a multi-feature time series prediction neural network model, taking the real-time spot price curve as the prediction curve of the multi-feature time series prediction neural network output, and training the multi-feature time series prediction neural network for bid price according to the bidding frequency curve, the bidding quantity curve and the real-time spot price curve prediction; the multi-feature time series prediction neural network may be an LSTM neural network model;
generating future bid price of the goods to be bid by using a multi-feature time sequence prediction neural network in real time, and taking the rising time of the predicted future bid price as bid showing time;
it should be noted that, as the prior art in the field, the multi-feature time series prediction neural network is essentially a tool, and given a specific input and output task, a specific training process and parameter settings depend on a specific engineering implementation situation;
the manner in which the qualified suppliers are selected to participate in bidding is as follows:
screening suppliers with goods of the type of goods to be marked in business ranges from all suppliers, and marking the number of each screened supplier as i;
obtaining basic information of each supplier, including company scale, age, employee number, complaint and dispute record number, and marking the company scale, age, employee number, complaint and dispute record number as respectivelyAnd；
obtaining the product and service quality of each provider; the product and the service quality comprise the historical bid amount and the historical bid amount on the electronic bidding platform, and the historical bid amount are respectively marked as and />；
Acquiring price fluctuation information of bid-winning in the history of each provider; the price fluctuation information is the average value of the absolute value of the difference between the bid price and the final bid price, and the average value is marked as；
Obtaining a reputation level of each provider; the reputation level is the number of the finally completed purchases after the merchant history is marked as；
Calculating a composite score for an ith vendorThe method comprises the steps of carrying out a first treatment on the surface of the Wherein, comprehensive score->The calculation formula of (2) is as follows:； wherein ,/> and />Respectively preset proportional coefficients; it will be appreciated that the larger the company size, age, number of employees, the higher the reliability of the company, the comprehensive score +.>The higher; historical bid rate->The higher the reliability of the company, the higher the composite score +.>The higher; the smaller the price fluctuation information is, the higher the reliability of the company is, the comprehensive score +.>The higher; the higher the number of final purchases completed, the higher the reliability of the company, the composite score +.>The higher;
if the comprehensive score of the ith providerIf the score is larger than or equal to the score threshold preset according to practical experience, marking the score as a provider meeting the requirements; if%>Comprehensive score of home provider->If the score is smaller than the score threshold preset according to practical experience, marking the score as an unsatisfactory supplier; it should be noted that the scoring threshold is set by the electronic bidding platform according to the specific scoring distribution condition of each provider;
the bidding information is a bidding document sent to a bidding account number of a bidding party on an electronic bidding platform after each provider meeting the requirements receives a bid-to-be-bidding notice;
based on the bidding information, the corresponding bidding data is obtained by the following steps:
the electronic bidding platform reads the price of goods, delivery mode, delivery place and delivery time from the bidding document by NLP technology;
the bidding data of the bidder is automatically evaluated, and the bidding scores are obtained by the following modes:
the method comprises the steps that historical bid training data of each bidding party in each historical bidding process are used as input of a machine learning model, the machine learning model takes predicted bid winning probability of the bidding party as output, labels of historical bid label data corresponding to the bidding party are used as prediction targets, and the sum of prediction accuracy of all the historical bid training data is minimized to be used as a training target; the calculation formula of the prediction accuracy is as follows:, wherein />jk is>In the secondary bidding process, the machine learning model predicts the bidding probability of the kth bidding party; />Is->In the secondary bidding process, the->Marking historical bid label data of a home bidding party; training the machine learning model until the sum of prediction accuracy reaches convergence, and stopping training; wherein (1)> and />The number of the bidding process and the number of the bidding party are respectively; it should be noted that, the convergence criterion is set according to specific model training conditions by those skilled in the art;
combining bidding data of each bidding party, average value of unit price of goods in all bidding data received by bidding account numbers and comprehensive scores of the bidding parties to obtain evaluation vectors, and inputting the evaluation vectors into a machine learning model to obtain probability of bidding in each bidding party; the probability is the bid score.
The above embodiments are only for illustrating the technical method of the present invention and not for limiting the same, and it should be understood by those skilled in the art that the technical method of the present invention may be modified or substituted without departing from the spirit and scope of the technical method of the present invention.
Claims (1)
1. A method for implementing automatic bidding and purchasing for goods, comprising the following steps:
step one: collecting the to-be-marked bulletin and platform bidding data uploaded by the bidding party in real time, and obtaining corresponding to-be-marked bidding data based on the to-be-marked bulletin;
the to-be-bidding bulletin is a bidding document prefabricated by a bidding party, and the bidding party uploads the bidding bulletin to a background of an electronic bidding platform through a bidding party account of the electronic bidding platform, wherein the platform bidding data comprises real-time bidding data and historical bidding data;
the real-time bidding data comprise the current real-time bidding quantity of each type of goods, the current real-time bidding party quantity, the current real-time supplier quantity and the current real-time market price of each type of goods in the electronic bidding platform;
the historical bid bidding data comprise bid amount, bid time, bid price and historical bid data of each bid in the history of each type of goods in an electronic bid platform; the historical bid data includes historical bid training data and historical bid tag data;
for each type of goods, the historical bid training data comprises the unit price of each bidding party in each bidding process, the average bidding price in the bidding process, the comprehensive score of the bidding party, the delivery mode, the delivery location and the duration of delivery time from delivery deadline; the historical bid label data is a label of whether each bidding party is bidding in each bidding process;
step two: selecting a bid amount of time based on the bid amount to be displayed and the platform bid amount; screening and matching the existing suppliers at the bidding showing time, selecting suppliers meeting the requirements, and sending bid waiting notices to the bidding account numbers of the suppliers meeting the requirements on the electronic bidding platform;
the to-be-marked bidding data are to-be-marked cargo types, to-be-marked quantity and to-be-marked period read from to-be-marked bulletins by the electronic bidding platform through an NLP technology;
step three: collecting bidding information of each bidding announcement in real time, and obtaining corresponding bidding data based on the bidding information;
step four: automatically evaluating bidding data of the bidder to obtain bidding scores, and sorting the bidder from large to small based on the bidding scores;
step five: the ordered bidding party is sent to a bidding party account of an electronic bidding platform of a bidding party, and the bidding party account is displayed to the bidding party;
based on the to-be-presented bid data and the platform bid data, the bid presentation time is selected by the following steps:
drawing a bidding frequency curve, a bidding quantity curve and a bidding price curve of the type of goods to be bidding according to the historical bidding data; the bidding frequency curve is a curve formed by connecting newly-shown bidding times of cargoes of the type to be bidding in each unit time; the bidding quantity curve expresses a curve formed by connecting the number of the newly-shown bidding goods of the goods type to be bidding in each unit time; the bid-winning price curve is a curve formed by connecting bid-winning prices of goods of the type to be bid-awarded with time each time;
drawing a real-time spot price curve according to the real-time spot price of the goods of the type to be marked;
taking the bidding frequency curve, the bidding quantity curve and the real-time spot price curve as inputs of a multi-feature time series prediction neural network model, taking the real-time spot price curve as a prediction curve of multi-feature time series prediction neural network output, and training a multi-feature time series prediction neural network for bid price according to the bidding frequency curve, the bidding quantity curve and the real-time spot price curve prediction, wherein the multi-feature time series prediction neural network is an LSTM neural network model;
generating future bid price of the goods to be bid by using a multi-feature time sequence prediction neural network in real time, and taking the rising time of the predicted future bid price as bid showing time;
the manner in which the qualified suppliers are selected to participate in bidding is as follows:
screening suppliers with business range including goods of the goods type to be marked from all suppliers, and marking the number of each screened supplier as；
Obtaining basic information of each supplier, including company scale, age, employee number, complaint and dispute record number, and marking the company scale, age, employee number, complaint and dispute record number as respectively and />；
Obtaining the product and service quality of each provider; the product and the service quality comprise the historical bid amount and the historical bid amount on the electronic bidding platform, and the historical bid amount are respectively marked as and />；
Acquiring price fluctuation information of bid-winning in the history of each provider; the price fluctuation information is the average value of the absolute value of the difference between the bid price and the final bid price, and the average value is calculatedMean value is marked as；
Obtaining a reputation level of each provider; the reputation level is the number of the finally completed purchases after the merchant history is marked as；
Calculating a composite score for an ith vendorThe method comprises the steps of carrying out a first treatment on the surface of the Wherein, comprehensive score->The calculation formula of (2) is as follows:
；
wherein , and />Respectively preset proportional coefficients;
if at firstComprehensive score of home provider->If the score is larger than or equal to the preset score threshold, marking the provider as a qualified provider; if%>Comprehensive score of home provider->If the score is smaller than the preset score threshold, marking the score as an unsatisfactory supplier;
the bidding information is a bidding document sent to a bidding account number of a bidding party on an electronic bidding platform after each provider meeting the requirements receives a bid-to-be-bidding notice;
based on the bidding information, the corresponding bidding data is obtained by the following steps:
the electronic bidding platform reads the price of goods, delivery mode, delivery place and delivery time from the bidding document by NLP technology;
the bidding data of the bidder is automatically evaluated, and the bidding scores are obtained by the following modes:
the method comprises the steps that historical bid training data of each bidding party in each historical bidding process are used as input of a machine learning model, the machine learning model takes predicted bid winning probability of the bidding party as output, labels of historical bid label data corresponding to the bidding party are used as prediction targets, and the sum of prediction accuracy of all the historical bid training data is minimized to be used as a training target; the calculation formula of the prediction accuracy is as follows:, wherein />jk is>In the secondary bidding process, the machine learning model pair +.>The bid winning probability of the home bidding party prediction; />Is->In the secondary bidding process, the->Marking historical bid label data of a home bidding party; training the machine learning model until the sum of prediction accuracy reaches convergence, and stopping training; wherein (1)> and />The number of the bidding process and the number of the bidding party are respectively;
combining bidding data of each bidding party, average value of unit price of goods in all bidding data received by bidding account numbers and comprehensive scores of the bidding parties to obtain evaluation vectors, and inputting the evaluation vectors into a machine learning model to obtain probability of bidding in each bidding party; the probability is the bid score.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310602079.4A CN116342234B (en) | 2023-05-26 | 2023-05-26 | Method for realizing automatic bidding purchasing aiming at goods |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310602079.4A CN116342234B (en) | 2023-05-26 | 2023-05-26 | Method for realizing automatic bidding purchasing aiming at goods |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116342234A CN116342234A (en) | 2023-06-27 |
| CN116342234B true CN116342234B (en) | 2023-08-29 |
Family
ID=86884364
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310602079.4A Active CN116342234B (en) | 2023-05-26 | 2023-05-26 | Method for realizing automatic bidding purchasing aiming at goods |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116342234B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002074111A (en) * | 2000-08-28 | 2002-03-15 | Etsuro Doi | Method and device for selling and buying merchandise at time series price |
| CN106504015A (en) * | 2016-10-17 | 2017-03-15 | 鞍钢集团矿业有限公司 | A kind of field supplier of enterprise of combination BP neural network recommends method |
| CN110458672A (en) * | 2018-05-08 | 2019-11-15 | 南京福佑在线电子商务有限公司 | Logistics bid platform and implementation method |
| CN110766278A (en) * | 2019-09-20 | 2020-02-07 | 国家电网有限公司 | Automatic bidding method and device and terminal equipment |
| CN111882391A (en) * | 2020-07-25 | 2020-11-03 | 广州城市职业学院 | BIM intelligent system of auxiliary bid procurement system |
| CN112396211A (en) * | 2019-08-19 | 2021-02-23 | 中移(苏州)软件技术有限公司 | Data prediction method, device, equipment and computer storage medium |
| CN113986869A (en) * | 2021-09-09 | 2022-01-28 | 昆明行列科技有限公司 | Construction engineering material price information data calculation method based on machine learning time sequence prediction algorithm |
| CN114943279A (en) * | 2022-04-28 | 2022-08-26 | 阿里巴巴（中国）有限公司 | Method, device and system for predicting bidding cooperative relationship |
| CN115619450A (en) * | 2022-11-09 | 2023-01-17 | 哈尔滨工业大学（深圳） | Virtual power plant real-time electricity price prediction system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120030137A1 (en) * | 2010-07-30 | 2012-02-02 | Technische Universitat Berlin | Method and device for valuation of a traded commodity |
-
2023
- 2023-05-26 CN CN202310602079.4A patent/CN116342234B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002074111A (en) * | 2000-08-28 | 2002-03-15 | Etsuro Doi | Method and device for selling and buying merchandise at time series price |
| CN106504015A (en) * | 2016-10-17 | 2017-03-15 | 鞍钢集团矿业有限公司 | A kind of field supplier of enterprise of combination BP neural network recommends method |
| CN110458672A (en) * | 2018-05-08 | 2019-11-15 | 南京福佑在线电子商务有限公司 | Logistics bid platform and implementation method |
| CN112396211A (en) * | 2019-08-19 | 2021-02-23 | 中移(苏州)软件技术有限公司 | Data prediction method, device, equipment and computer storage medium |
| CN110766278A (en) * | 2019-09-20 | 2020-02-07 | 国家电网有限公司 | Automatic bidding method and device and terminal equipment |
| CN111882391A (en) * | 2020-07-25 | 2020-11-03 | 广州城市职业学院 | BIM intelligent system of auxiliary bid procurement system |
| CN113986869A (en) * | 2021-09-09 | 2022-01-28 | 昆明行列科技有限公司 | Construction engineering material price information data calculation method based on machine learning time sequence prediction algorithm |
| CN114943279A (en) * | 2022-04-28 | 2022-08-26 | 阿里巴巴（中国）有限公司 | Method, device and system for predicting bidding cooperative relationship |
| CN115619450A (en) * | 2022-11-09 | 2023-01-17 | 哈尔滨工业大学（深圳） | Virtual power plant real-time electricity price prediction system |
Non-Patent Citations (1)
| Title |
|---|
| 引入合理低价中标价预测值的工程量清单招投标模型分析;钟胜;赵磊;宋吉荣;;四川建筑科学研究;39(05);第353-356页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116342234A (en) | 2023-06-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Duffy et al. | Measuring distributive and procedural justice: An exploratory investigation of the fairness of retailer‐supplier relationships in the UK food industry | |
| Al-Zaqeba et al. | The effect of management accounting and blockchain technology characteristics on supply chains efficiency | |
| CN112508436A (en) | Supplier product purchasing method and device and storage medium | |
| CN111915399A (en) | Price inquiring purchasing system | |
| CN111292149A (en) | Method and device for generating return processing information | |
| CN114708072A (en) | Electronic bidding management system based on big data | |
| CN112948667A (en) | Supplier recommendation system and method based on bidding | |
| Samudro et al. | Perceived quality and relationship quality as antecedents and predictors of loyalty in the chemical industry: A literature review | |
| CN1564176A (en) | Electronic biding method and system for subsidiary agricultural products | |
| CN116342234B (en) | Method for realizing automatic bidding purchasing aiming at goods | |
| CN101599139A (en) | Logistic service electronic trading system | |
| Bhattacharya et al. | A Delphi study of RFID applicable business processes and value chain activities in retail | |
| CN112288305A (en) | Bid evaluation data analysis system and bid evaluation data analysis method thereof | |
| Puma-Flores et al. | Promoting sustainable agri-food systems through sustainability and responsible marketing: The case of peruvian companies at international trade shows | |
| CN116433179A (en) | Database-based public bidding information standardization method | |
| Oteki et al. | Influence of electronic order processing on supply chain performance of sugar processing firms in Kenya | |
| Aswar | Determination Cost of Sales and Utilization of Internet Media for SMEs Marketing in Kelanggaran Unyur | |
| CN113947442A (en) | Novel large-scale accurate marketing advertisement system based on big data internet technology | |
| Mangmang | Development and Implementation of Point of Sale System (POS): Profitability Measurement for Retail Business | |
| Ahmad et al. | Knowledge management, technology, strategy, and environment in halal food industry green supply chain and logistics management performance | |
| Riswandi et al. | Reducing the Delayed Lead Time of Purchase Requisition to Purchase Orders for Standard Part Commodity in the Procurement Department of the Avionics Sector | |
| Choirunnisa et al. | The Effect of Business Environment on The Performance of SMIs in The Food and Beverage Sector through Marketplace Adoption as A Mediating Variable | |
| KHONG | ECONOMIC APPROACHES FOR E-COMMERCE DEVELOPMENT FOR AGRICULTURAL SECTOR IN DEVELOPING COUNTRIES | |
| Russell | The ASQ supply chain management primer | |
| CN115796973A (en) | Purchasing method based on intelligent bidding building material purchasing platform |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |