CN116503001A - Method, device, equipment and medium for generating purchase order - Google Patents
Method, device, equipment and medium for generating purchase order Download PDFInfo
- Publication number
- CN116503001A CN116503001A CN202310331642.9A CN202310331642A CN116503001A CN 116503001 A CN116503001 A CN 116503001A CN 202310331642 A CN202310331642 A CN 202310331642A CN 116503001 A CN116503001 A CN 116503001A
- Authority
- CN
- China
- Prior art keywords
- commodity
- purchase
- score
- scores
- deviation
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 35
- 230000006870 function Effects 0.000 claims description 30
- 238000010606 normalization Methods 0.000 claims description 20
- 238000012549 training Methods 0.000 claims description 12
- 239000004973 liquid crystal related substance Substances 0.000 claims description 6
- 238000003860 storage Methods 0.000 claims description 4
- 238000013528 artificial neural network Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 238000004422 calculation algorithm Methods 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 6
- 239000000463 material Substances 0.000 description 6
- 239000011159 matrix material Substances 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000003153 chemical reaction reagent Substances 0.000 description 1
- 239000003795 chemical substances by application Substances 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 239000002994 raw material Substances 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
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/087—Inventory or stock management, e.g. order filling, procurement or balancing against orders
- G06Q10/0875—Itemisation or classification of parts, supplies or services, e.g. bill of materials
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06315—Needs-based resource requirements planning or analysis
-
- 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
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0605—Supply or demand aggregation
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The embodiment of the specification discloses a method, a device, equipment and a medium for generating a purchase order, which comprise the following steps: acquiring purchase information input by a current user, wherein the scoring purchase information comprises purchase commodity types and purchase quantity; the grading purchasing information is sent to suppliers containing grading purchasing commodity categories to obtain commodity information corresponding to the grading purchasing commodity categories of all the suppliers, wherein the grading commodity information comprises commodity prices and commodity residual quantities; determining the scores corresponding to the commodities of the suppliers according to the commodity prices of the suppliers; and determining the commodity of the winning bid provider according to the scores corresponding to the commodity of each provider, the residual commodity quantity and the score purchasing quantity, and generating a purchasing order according to the commodity of the winning bid provider. According to the embodiment of the specification, under the condition that the number of the quotation commodity list is large, the optimal commodity of the winning bid provider can be automatically selected through the technical characteristics, and a large amount of time of purchasing personnel is saved.
Description
Technical Field
The present disclosure relates to the field of computer technologies, and in particular, to a method, an apparatus, a device, and a medium for generating a purchase order.
Background
The purchase order is a feasible purchase order plan formulated by enterprises according to the material plan and the actual capability of the products and related factors, and is issued to suppliers for execution, so that the enterprises can purchase the commodities required by the enterprises, and qualified raw materials and accessories are conveyed to production departments and demand departments.
The price and the remaining amount of the commodity offered for sale are often different for each supplier. Under the condition that the number of the quotation commodity list is large, the buyer manually selects the optimal winning bid commodity, and the time and the labor are wasted.
Disclosure of Invention
One or more embodiments of the present disclosure provide a method, an apparatus, a device, and a medium for generating a purchase order, which are used to solve the technical problem set forth in the background art.
One or more embodiments of the present disclosure adopt the following technical solutions:
one or more embodiments of the present disclosure provide a method for generating a purchase order, including:
acquiring purchase information input by a current user, wherein the purchase information comprises purchase commodity types and purchase quantity;
sending the purchase information to suppliers containing the purchase commodity categories to obtain commodity information corresponding to the purchase commodity categories of all suppliers, wherein the commodity information comprises commodity prices and commodity residual quantities;
determining price deviation scores and residual quantity deviation scores corresponding to commodity prices and residual quantity of all suppliers respectively through normalization functions;
determining the corresponding scores of the commodities of all suppliers according to the price deviation scores and the residual quantity deviation scores;
and determining the commodity of the winning supplier according to the scores and the residual commodity quantity corresponding to the commodities of the suppliers and the purchasing quantity, and generating a purchasing order according to the commodity of the winning supplier.
Optionally, the determining the commodity of the winning supplier according to the score and the commodity residual quantity corresponding to the commodity of each supplier and the purchase quantity, and generating the purchase order according to the commodity of the winning supplier specifically includes:
determining the commodity of the first supplier with the highest score according to the scores corresponding to the commodities of the suppliers;
if the remaining quantity of the commodities corresponding to the commodities of the first supplier is greater than or equal to the purchase quantity, setting the commodities of the first supplier as the commodities of the first winning bid supplier;
and generating a purchase order according to the commodity of the first winning bid provider and the purchase quantity.
Optionally, if the remaining number of commodities corresponding to the commodities of the first provider is smaller than the purchase number, the method further includes:
determining a difference value of the purchase quantity and the commodity residual quantity corresponding to the commodity of the first provider, and recording the difference value as a difference value purchase quantity;
determining the commodity of a second supplier with a second score according to the corresponding score of the commodity of each supplier;
if the remaining quantity of the commodities corresponding to the commodities of the second provider is greater than or equal to the difference purchase quantity, setting the commodities of the first provider and the commodities of the second provider as commodities of a second winning bid provider;
and generating a purchase order according to the commodity of the second winning bid provider and the purchase quantity.
Optionally, the commodity information further includes a commodity period and a supplier order performance rate;
the determining, by using a normalization function, a price deviation score and a remaining quantity deviation score corresponding to a commodity price and a remaining quantity of each provider, and determining a score corresponding to a commodity of each provider according to the price deviation score and the remaining quantity deviation score, specifically includes:
determining price deviation scores, residual quantity deviation scores, goods period deviation scores and order performance rate deviation scores corresponding to the goods period and the order performance rate of the suppliers respectively through normalization functions;
and determining the corresponding scores of the commodities of all suppliers according to the price deviation score, the residual quantity deviation score, the period deviation score and the order performance rate deviation score.
Optionally, the determining the score corresponding to the commodity of each supplier according to the price deviation score, the remaining quantity deviation score, the period deviation score and the order performance rate deviation score specifically includes:
determining the weight proportion among commodity price, commodity residual quantity, commodity period and order performance rate of each supplier respectively;
and determining scores corresponding to commodities of all suppliers according to the weight proportion, the price deviation score, the residual quantity deviation score, the period deviation score and the order performance rate deviation score.
Optionally, the determining the score corresponding to the commodity of each supplier according to the weight proportion, the price deviation score, the remaining quantity deviation score, the period deviation score and the order performance rate deviation score includes:
determining a score corresponding to the commodity of each supplier according to a preset formula w= Σpi Qi; wherein W is a score corresponding to a commodity, pi is a weight value of price, residual quantity, period and order performance rate, and Qi is the price deviation score, residual quantity deviation score, period deviation score and order performance rate deviation score.
Optionally, the method is applied to an intelligent price comparison model, and before the current purchase information input by the user is obtained, the method further includes:
inputting purchase information and commodity information in a training set into an intelligent price comparison model to be trained, calculating the scores of all suppliers through the intelligent price comparison model to be trained, and outputting the winning commodity with the highest score;
inputting preselected commodities in the training set into the intelligent price comparison model to set the highest score of the winning commodity as the score of the preselected commodity;
invoking a weight value try function, and adjusting the weight proportion among the commodity price, the commodity residual quantity, the commodity period and the order performance rate of the supplier in the commodity information so that the score of the preselected commodity is the score of the winning bid commodity;
and calling a weight value changing function, and replacing the weight proportion in the intelligent price comparison model by the adjusted weight proportion to generate the intelligent price comparison model meeting the requirements.
An apparatus for generating a purchase order according to one or more embodiments of the present disclosure includes:
the purchasing information acquisition unit acquires purchasing information input by a current user, wherein the purchasing information comprises purchasing commodity types and purchasing quantity;
the commodity information acquisition unit is used for transmitting the purchase information to suppliers containing the purchase commodity categories so as to acquire commodity information corresponding to the purchase commodity categories of all the suppliers, wherein the commodity information comprises commodity prices and commodity residual quantity;
a deviation score determining unit for determining price deviation scores and residual quantity deviation scores corresponding to commodity prices and residual quantity of the suppliers respectively through normalization functions;
a scoring unit for determining scores corresponding to the commodities of the suppliers according to the price deviation scores and the residual quantity deviation scores;
and the purchase order generation unit is used for determining the commodity of the winning bid provider according to the scores and the commodity residual quantity corresponding to the commodities of the suppliers and the purchase quantity, and generating a purchase order according to the commodity of the winning bid provider.
One or more embodiments of the present specification provide a purchase order generating apparatus, including:
at least one processor; the method comprises the steps of,
a memory communicatively coupled to the at least one processor; wherein, the liquid crystal display device comprises a liquid crystal display device,
the memory stores instructions executable by the at least one processor to enable the at least one processor to:
acquiring purchase information input by a current user, wherein the purchase information comprises purchase commodity types and purchase quantity;
sending the purchase information to suppliers containing the purchase commodity categories to obtain commodity information corresponding to the purchase commodity categories of all suppliers, wherein the commodity information comprises commodity prices and commodity residual quantities;
determining price deviation scores and residual quantity deviation scores corresponding to commodity prices and residual quantity of all suppliers respectively through normalization functions;
determining the corresponding scores of the commodities of all suppliers according to the price deviation scores and the residual quantity deviation scores;
and determining the commodity of the winning supplier according to the scores and the residual commodity quantity corresponding to the commodities of the suppliers and the purchasing quantity, and generating a purchasing order according to the commodity of the winning supplier.
One or more embodiments of the present specification provide a non-volatile computer storage medium storing computer-executable instructions configured to:
acquiring purchase information input by a current user, wherein the purchase information comprises purchase commodity types and purchase quantity;
sending the purchase information to suppliers containing the purchase commodity categories to obtain commodity information corresponding to the purchase commodity categories of all suppliers, wherein the commodity information comprises commodity prices and commodity residual quantities;
determining price deviation scores and residual quantity deviation scores corresponding to commodity prices and residual quantity of all suppliers respectively through normalization functions;
determining the corresponding scores of the commodities of all suppliers according to the price deviation scores and the residual quantity deviation scores;
and determining the commodity of the winning supplier according to the scores and the residual commodity quantity corresponding to the commodities of the suppliers and the purchasing quantity, and generating a purchasing order according to the commodity of the winning supplier.
The above-mentioned at least one technical scheme that this description embodiment adopted can reach following beneficial effect:
according to the embodiment of the specification, commodity information corresponding to the purchased commodity category of each supplier is screened out through the purchased commodity category in the purchase information, then the grade corresponding to the commodity of each supplier is determined according to the commodity price of each supplier, the commodity of the winning supplier is determined according to the grade corresponding to the commodity of each supplier, the residual quantity of the commodity and the purchased quantity in the purchase information, and finally the purchase order is determined. Through the technical characteristics, under the condition that the number of the quotation commodity list is large, the optimal commodity of the winning bid provider can be automatically selected, and a great amount of time of purchasing personnel is saved.
Drawings
In order to more clearly illustrate the embodiments of the present description or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described below, it being obvious that the drawings in the following description are only some of the embodiments described in the present description, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
In the drawings:
FIG. 1 is a flow diagram of a method for generating a purchase order according to one or more embodiments of the present disclosure;
FIG. 2 is a flow diagram of a method for generating a purchase order through an intelligent price comparison model provided in one or more embodiments of the present disclosure;
FIG. 3 is a schematic diagram illustrating a device for generating a purchase order according to one or more embodiments of the present disclosure;
FIG. 4 is a schematic diagram of a device for generating a purchase order according to one or more embodiments of the present disclosure.
Detailed Description
The embodiment of the specification provides a method, a device, equipment and a medium for generating a purchase order.
In a material purchase management system commonly used in the current enterprises, the price query function has the following defects:
the price, the supply quantity, the freight rate and the freight period of the commodity quoted by each supplier are often different, and the order performance rate and the after-sales service score of each supplier are also different. Under the condition that the number of the quotation commodity list is large, the buyer manually selects the optimal winning bid commodity, and the time and the labor are wasted.
In addition, when the supply quantity of the optimal bid price commodity does not meet the purchasing demand quantity, the purchasing demand quantity is manually calculated by the purchasing staff, and the supplementary bid price commodity is selected again from the suboptimal bid price commodity to ensure that the purchasing quantity meets the demand. This also brings about considerable effort.
The terms of the embodiments of the present specification are explained as follows:
the material purchase management system comprises: the digital solution of enterprise productive and non-productive material purchasing is provided for enterprises.
The suppliers: merchants providing commodity quotation and commodity selling services for the material purchase management system.
Inquiring price comparing purchase: and generating a purchase order by inviting a plurality of suppliers to offer the purchase demand and preferentially selecting commodities.
The experimenter: and a role of material query price comparison purchasing requirement is put forward.
Purchasing agent: after each provider inquires price comparison demand commodity quotation, the role of the bid-winning commodity is preferentially selected.
In order to make the technical solutions in the present specification better understood by those skilled in the art, the technical solutions in the embodiments of the present specification will be clearly and completely described below with reference to the drawings in the embodiments of the present specification, and it is obvious that the described embodiments are only some embodiments of the present specification, not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, shall fall within the scope of the present disclosure.
FIG. 1 is a flow diagram of a method of generating a purchase order that may be performed by a purchase order generating system, provided in one or more embodiments of the present description. Some input parameters or intermediate results in the flow allow for manual intervention adjustments to help improve accuracy.
The method flow steps of the embodiment of the present specification are as follows:
s102, acquiring purchase information input by a current user, wherein the purchase information comprises purchase commodity types and purchase quantity.
In the embodiment of the present specification, the purchase information is the item information required to be purchased by the user, and the purchase information may include, in addition to the category of the purchased goods and the purchase quantity, estimated total price, demand urgency, and the like.
S104, sending the purchase information to suppliers containing the purchase commodity categories to acquire commodity information corresponding to the purchase commodity categories of all suppliers, wherein the commodity information comprises commodity prices and commodity residual quantities.
In this embodiment of the present disclosure, the commodity information may include, in addition to the commodity price and the remaining commodity amount given by each provider, related information of each provider, for example, a commodity period, a provider order performance rate, and a preferential activity of each provider.
And S106, determining price deviation scores and residual quantity deviation scores of commodity prices and commodity residual quantities of the suppliers respectively through normalization functions.
In the embodiment of the present specification, when the price deviation score and the remaining quantity deviation score corresponding to the commodity price and the commodity remaining quantity of each of the suppliers are respectively determined by the normalization function, the price deviation score may be represented by Q (price deviation score) =1 to J (price per commodity)/K (arithmetic average of price per commodity of all quotations); and determining the scores corresponding to the commodities of the suppliers according to the price deviation scores and the residual quantity deviation scores, and adding the price deviation scores and the residual quantity deviation scores to obtain the scores corresponding to the commodities of the suppliers.
And S108, determining the scores corresponding to the commodities of the suppliers according to the price deviation scores and the residual quantity deviation scores.
Further, in the embodiment of the present disclosure, other factors may be considered when determining the score corresponding to the commodity of each provider, so that the score corresponding to the commodity of each provider better meets the user requirement. To this end, the merchandise information may also include a period of the merchandise, an after-market service score, and a supplier order performance rate, by which the score corresponding to each supplier's merchandise is determined.
Specifically, in the embodiment of the present disclosure, when determining the scores corresponding to the commodities of each provider according to the commodity prices of each provider, the commodity prices, the commodity residual amounts, the commodity periods, the after-sales service scores and the price deviation scores, the residual amount deviation scores, the commodity period deviation scores, the after-sales service scores and the order performance rate deviation scores of each provider may be determined by a normalization function; and determining the scores corresponding to the commodities of the suppliers according to the price deviation score, the residual quantity deviation score, the goods period deviation score, the after-sales service score and the order performance rate deviation score, and adding the price deviation score, the residual quantity deviation score, the goods period deviation score, the after-sales service score and the order performance rate deviation score to obtain the scores corresponding to the commodities of the suppliers.
Further, in the embodiment of the present disclosure, when determining the scores corresponding to the commodities of each provider, the weight ratio between the commodity price, the commodity remaining quantity, the commodity period and the order performance rate of the provider in the commodity information may also be determined, so that the scores corresponding to the commodities of each provider are more accurate.
Specifically, when determining the scores corresponding to the commodities of each supplier according to the price deviation score, the remaining quantity deviation score, the goods period deviation score and the order performance rate deviation score, the commodity price, the remaining quantity of the commodity, the weight ratio between the goods period and the order performance rate of the supplier can be respectively determined, the weight ratio can be set according to actual conditions, and the adjustment can be performed in the application process; determining the scores corresponding to the commodities of each supplier according to the weight proportion, the price deviation score, the residual quantity deviation score, the period deviation score and the order performance rate deviation score, wherein the calculation formula can be as follows: w (score) =Σpi×qi, pi may be a weight value of a price, a remaining quantity, a period of the goods, and an order performance rate, qi may be the price deviation score, the remaining quantity deviation score, the period of the goods deviation score, and the order performance rate deviation score.
S110, determining the commodity of the winning supplier according to the scores and the commodity residual quantity corresponding to the commodities of the suppliers and the purchasing quantity, and generating a purchasing order according to the commodity of the winning supplier.
In the embodiment of the present disclosure, the commodity of the first provider with the highest score may be determined according to the score corresponding to the commodity of each provider; judging whether the residual quantity of the commodities corresponding to the commodities of the first supplier is larger than or equal to the purchase quantity in the purchase information, and if the residual quantity of the commodities corresponding to the commodities of the first supplier is larger than or equal to the purchase quantity, setting the commodities of the first supplier as the commodities of the first winning bid supplier; and finally, generating a purchase order according to the commodity of the first winning bid provider and the purchase quantity.
Further, the remaining number of commodities corresponding to the commodity of the first supplier with the highest score may be lower than the purchase number, and the embodiment of the present specification may generate the purchase order by way of spelling.
Specifically, if the remaining quantity of the commodity corresponding to the commodity of the first provider is smaller than the purchase quantity, a difference between the purchase quantity and the remaining quantity of the commodity corresponding to the commodity of the first provider may be determined and recorded as a difference purchase quantity; determining the commodity of a second supplier with a second score according to the scores corresponding to the commodity of each supplier; if the remaining quantity of the commodities corresponding to the commodities of the second provider is greater than or equal to the difference purchase quantity, setting the commodities of the first provider and the commodities of the second provider as commodities of a second winning bid provider; and finally, generating a purchase order according to the commodities of the second winning-bid provider and the purchase quantity, namely, carrying out the pooling purchase of the commodities of the first provider and the commodities of the second provider, and generating the purchase order according to the residual quantity of the commodities corresponding to the commodities of the first provider and the differential purchase quantity corresponding to the commodities of the second provider, wherein the purchase quantity of the commodities of the class A in the purchase order is 1000, the commodities of the class A of the first provider remain 800, the commodities of the class A of the second provider remain 500, and when the purchase order is generated, the commodities of the class A of the first provider purchase 800, and the commodities of the class A of the second provider purchase 200.
It should be noted that, the above technical features of the embodiments of the present disclosure may be applied to an intelligent price comparison model, and before acquiring purchase information input by a current user, purchase information and commodity information in a training set may be input to the intelligent price comparison model to be trained, and the score of each supplier is calculated by the intelligent price comparison model to be trained, and the winning commodity with the highest score is output; inputting the preselected commodities in the training set into the intelligent price comparison model to set the highest score of the winning commodity as the score of the preselected commodity; then, a weight value try function is called, and the weight proportion among the commodity price, the commodity residual quantity, the commodity period and the order performance rate of the supplier is adjusted in the commodity information, so that the score of the preselected commodity is the score of the winning bid commodity; and calling a weight value changing function, and replacing the weight proportion in the intelligent price comparison model by the adjusted weight proportion to generate the intelligent price comparison model meeting the requirements.
It should be noted that, the intelligent price comparison model in the embodiment of the present disclosure may be trained by a plurality of data in a training set, and the finally trained intelligent price comparison model meets a preset requirement. The process determines the goods of the winning bid provider through the intelligent price comparison model meeting the requirements, and generates a purchase order according to the goods of the winning bid provider.
It should be noted that, the embodiment of the specification can apply the neural network intelligent algorithm with self-learning to build the intelligent price comparison model, realize the automatic price comparison flow and solve the problem of large manual price comparison workload. FIG. 2 is a schematic flow chart of a method for generating a purchase order by an intelligent price comparison model according to an embodiment of the present disclosure, and the following is a flow chart of an embodiment of the present disclosure:
before the intelligent price comparing module is formally started, the neural network training is carried out by using the real historical price comparing data to form basic parameter configuration.
After the experimenter submits the query price purchasing requirement (purchasing information), the system automatically sends the query price purchasing requirement to suppliers which can respond to the query price of the categories through an automatic distribution module according to the categories of the required commodities.
When the price inquiry list opening time is reached, the system automatically calls an intelligent price comparison module, and inputs the price quotation price, the supply quantity, the freight rate, the freight period and the like of the commodity to be marked of the required commodity class business to the intelligent price comparison module, and the data such as the order performance, the demand quantity, the estimated total price, the demand urgency degree and the like of the provider, the offer rate, the historical order quantity, the historical order total amount, the after-sale service score and the like.
After the intelligent price comparing module acquires the input data, the scores of the quotation commodities are automatically calculated, and the commodities are reordered from high to low according to the scores.
The intelligent price comparing module reorders the commodities according to the scores, marks the commodity with the highest score as a winning bid commodity A1, automatically judges whether the supply quantity N1 of the winning bid commodity A1 is smaller than the required quantity N, if N1 is smaller than N, records the winning bid commodity A1 and the corresponding quantity N1 into a to-be-output list, marks the commodity with the highest score as a winning bid commodity A2, resets N to N-N1, and continuously and automatically judges whether the supply quantity N2 of the winning bid commodity A2 is smaller than the new required quantity N. And analogically, until the number of suppliers of a certain winning bid commodity Ak is greater than or equal to the latest required number, recording the winning bid commodity Ak and the corresponding number (latest) N into a to-be-output list. And outputting a total list to be output, and exiting the intelligent price comparing module.
The output total list contains all the winning commodities and the corresponding pre-purchase quantity, and the winning commodities and the corresponding pre-purchase quantity are automatically submitted to a buyer for final confirmation.
The buyer can directly generate a purchase order by one key of the bid-winning commodity list, or replace some bid-winning commodity with other commodity in the quotation list.
If the buyer replaces the commodity, the system automatically inputs the commodity before replacement and the commodity after replacement into the self-learning module, retrains the neural network algorithm, and updates the latest trained parameter configuration to the intelligent price comparing module.
It should be noted that, the intelligent price comparing module and the self-learning model in the embodiment of the present disclosure are described in detail:
the intelligent price comparing module can be carried into a scoring calculation algorithm according to the input demand commodity data, quotation commodity data and quotation provider data to obtain the score of each quotation commodity, and reorders the quotation commodities according to the score from high to low, wherein the recommendation degree of the intelligent price comparing module to the commodity, namely the winning priority is marked by the score.
It should be noted that the principle of the scoring algorithm in the embodiment of the present disclosure is as follows:
according to the required commodity classification and the range of the estimated total price, a corresponding weight value group in a neural network weight value matrix is called, and each weight value of the weight value group is initialized to a scoring calculation formula; for example, the required commodity is classified as reagent consumable, the estimated total price is 10000 yuan, the called weight value group is Pn [ ], pn [ ] is a one-dimensional array, and the elements in the weight value group are weight values of all parameters;
invoking parameter values corresponding to each weight value of the quotation commodity, inputting a normalization function of each parameter, calculating deviation scores (positive values represent added scores and negative values represent subtracted scores) of each parameter, and taking the obtained deviation scores into a scoring calculation formula; for example, the normalized function of the price of the offered commodity is: q (unit price deviation score) =1-J (unit price of the commodity price per commodity)/K (arithmetic average of unit price of all commodity price per commodity;
and (3) calling a scoring calculation formula to calculate the final score of each quotation commodity, wherein the calculation formula is as follows: w (score) =Σpi×qi, pi representing the weight value of a certain parameter, qi representing the deviation score of a certain parameter (each deviation score corresponds to a set of scoring criteria, such as quote price, shelf life, supply quantity, supplier order performance rate, etc., the score of the deviation score is calculated by a normalization function).
The self-learning model can train the neural network according to the input historical price-inquiring data, continuously optimize the weight value configuration of each weight value matrix in the neural network, and change the calculation result of the scores of all quotation commodities through the continuous adjustment of configuration parameters, so that the recommended bid-winning commodities given by the intelligent price-comparing module are more and more close to manual selection.
It should be noted that, the algorithm principle of the self-learning model in the embodiment of the present disclosure is as follows:
initializing an initial value of a neural network weight value matrix to be an empirical value between 0 and 1, inputting required commodity information, quotation commodity information and supplier information into an intelligent price comparing module, calculating a score by the intelligent price comparing module, and outputting recommended bid-winning commodities (the bid-winning commodities at the moment are likely not manually selected bid-winning commodities);
inputting a manually selected winning bid commodity (winning bid commodity after manual replacement) into a self-learning model (in a self-learning model training stage), wherein the model sets the highest score in the commodity of the previous bid price as a target score of the commodity;
invoking a weight value try function, calculating how the weight value is adjusted so that the score calculated by the manually selected winning bid commodity reaches a target score, and the variance of the variation of the whole set of weight values is minimum;
invoking a weight value changing function, and reassigning the set of weight values by using the calculated new weight value set;
the self-learning model automatically records the price-polling data to a historical price-polling record database, and calls the historical price-polling record database and the intelligent price-polling module before, and re-verifies and deep learns the historical data after the weight value is adjusted.
Further, the implementation procedure of the embodiment of the present specification is as follows:
1. and collecting enterprise historical price-inquiring record data, sorting the record data into a template format which can be identified by a self-learning model, importing a template containing the historical data into the self-learning model, training a neural network model of the intelligent price-comparing module by using the historical data, and automatically adjusting configuration parameters in the model to a reference initial value.
2. And formally starting the intelligent price comparing module, and automatically guiding the winning-winning goods before and after manual replacement into the self-learning model in cooperation with the self-learning model to perform fine adjustment of the configuration parameters of the neural network model.
3. When the accuracy of the price comparison result output by the intelligent price comparison module meets the threshold value of the enterprise requirement, the step of manual intervention can be closed, and a purchase order is directly generated by the result output by the intelligent price comparison module.
It should be noted that, in the embodiment of the specification, before the intelligent price comparing module is formally started, the real historical price comparing data is imported into the self-learning model to perform training of the neural network, so that basic configuration coefficients are primarily formed, after the formal starting, the accuracy of the recommended bid-winning commodity provided by the intelligent price comparing module is very high (commodity replacement is not needed, a purchase order can be directly generated), and after the manual auxiliary processing of several months after the online operation and the continuous training of the self-learning model are performed, the goal of automatically generating the purchase order without manual intervention and automatic price comparing can be realized.
It should be noted that, in the intelligent price comparing module in the embodiment of the present disclosure, the model parameters involved in calculating the score include the type of the required commodity, the required quantity, the estimated total price, the required urgency, etc., and the price, the supplied quantity, the freight rate, the freight period, etc. of the commodity should be marked by the supplier, and the data such as the order performance rate, the historical order quantity, the historical order total quantity, the after-sales service score, etc. of the supplier, so that the purchase order can be more accurate, and the result of manual selection is more satisfied. In addition, in the intelligent price comparing module of the embodiment of the specification, an algorithm for winning a splice is provided, when the optimal commodity supply quantity cannot meet the demand quantity, suboptimal commodities can be sequentially inquired backwards according to a grading sequence until the demand quantity is met, all winning commodities and pre-purchase quantity are output, and therefore ordering schemes in purchase orders can be more reasonable.
Fig. 3 is a schematic structural diagram of a purchase order generating apparatus provided in one or more embodiments of the present disclosure, where the apparatus includes: a purchase information acquiring unit 302, a commodity information acquiring unit 304, a deviation score determining unit 306, a scoring unit 308, and a purchase order generating unit 310.
A purchase information acquiring unit 302, configured to acquire purchase information input by a current user, where the purchase information includes a purchase commodity category and a purchase quantity;
a commodity information obtaining unit 304, configured to send the purchase information to suppliers including the purchased commodity category, so as to obtain commodity information corresponding to the purchased commodity category of each supplier, where the commodity information includes a commodity price and a commodity remaining quantity;
a deviation score determining unit 306, configured to determine price deviation scores and remaining quantity deviation scores corresponding to the commodity prices and the remaining quantity of the commodity of the suppliers through normalization functions, respectively;
a scoring unit 308 for determining a score corresponding to the commodity of each supplier according to the price deviation score and the remaining quantity deviation score;
the purchase order generating unit 310 determines the goods of the winning supplier according to the scores and the remaining quantity of the goods corresponding to the goods of the suppliers and the purchase quantity, and generates a purchase order according to the goods of the winning supplier.
FIG. 4 is a schematic diagram of a device for generating a purchase order according to one or more embodiments of the present disclosure, including:
at least one processor; the method comprises the steps of,
a memory communicatively coupled to the at least one processor; wherein, the liquid crystal display device comprises a liquid crystal display device,
the memory stores instructions executable by the at least one processor to enable the at least one processor to:
acquiring purchase information input by a current user, wherein the purchase information comprises purchase commodity types and purchase quantity;
sending the purchase information to suppliers containing the purchase commodity categories to obtain commodity information corresponding to the purchase commodity categories of all suppliers, wherein the commodity information comprises commodity prices and commodity residual quantities;
determining price deviation scores and residual quantity deviation scores corresponding to commodity prices and residual quantity of all suppliers respectively through normalization functions;
determining the corresponding scores of the commodities of all suppliers according to the price deviation scores and the residual quantity deviation scores;
and determining the commodity of the winning supplier according to the scores and the residual commodity quantity corresponding to the commodities of the suppliers and the purchasing quantity, and generating a purchasing order according to the commodity of the winning supplier.
One or more embodiments of the present specification provide a non-volatile computer storage medium storing computer-executable instructions configured to:
acquiring purchase information input by a current user, wherein the purchase information comprises purchase commodity types and purchase quantity;
sending the purchase information to suppliers containing the purchase commodity categories to obtain commodity information corresponding to the purchase commodity categories of all suppliers, wherein the commodity information comprises commodity prices and commodity residual quantities;
determining price deviation scores and residual quantity deviation scores corresponding to commodity prices and residual quantity of all suppliers respectively through normalization functions;
determining the corresponding scores of the commodities of all suppliers according to the price deviation scores and the residual quantity deviation scores;
and determining the commodity of the winning supplier according to the scores and the residual commodity quantity corresponding to the commodities of the suppliers and the purchasing quantity, and generating a purchasing order according to the commodity of the winning supplier.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for apparatus, devices, non-volatile computer storage medium embodiments, the description is relatively simple, as it is substantially similar to method embodiments, with reference to the section of the method embodiments being relevant.
The foregoing describes specific embodiments of the present disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
The foregoing is merely one or more embodiments of the present description and is not intended to limit the present description. Various modifications and alterations to one or more embodiments of this description will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, or the like, which is within the spirit and principles of one or more embodiments of the present description, is intended to be included within the scope of the claims of the present description.
Claims (10)
1. A method of generating a purchase order, the method comprising:
acquiring purchase information input by a current user, wherein the purchase information comprises purchase commodity types and purchase quantity;
sending the purchase information to suppliers containing the purchase commodity categories to obtain commodity information corresponding to the purchase commodity categories of all suppliers, wherein the commodity information comprises commodity prices and commodity residual quantities;
determining price deviation scores and residual quantity deviation scores corresponding to commodity prices and residual quantity of all suppliers respectively through normalization functions;
determining the corresponding scores of the commodities of all suppliers according to the price deviation scores and the residual quantity deviation scores;
and determining the commodity of the winning supplier according to the scores and the residual commodity quantity corresponding to the commodities of the suppliers and the purchasing quantity, and generating a purchasing order according to the commodity of the winning supplier.
2. The method according to claim 1, wherein the determining the goods of the winning supplier according to the scores and the remaining quantities of the goods and the purchase quantities, and generating the purchase order according to the goods of the winning supplier, specifically comprises:
determining the commodity of the first supplier with the highest score according to the scores corresponding to the commodities of the suppliers;
if the remaining quantity of the commodities corresponding to the commodities of the first supplier is greater than or equal to the purchase quantity, setting the commodities of the first supplier as the commodities of the first winning bid supplier;
and generating a purchase order according to the commodity of the first winning bid provider and the purchase quantity.
3. The method of claim 2, wherein if the remaining quantity of the first provider's corresponding merchandise is less than the purchase quantity, the method further comprises:
determining a difference value of the purchase quantity and the commodity residual quantity corresponding to the commodity of the first provider, and recording the difference value as a difference value purchase quantity;
determining the commodity of a second supplier with a second score according to the corresponding score of the commodity of each supplier;
if the remaining quantity of the commodities corresponding to the commodities of the second provider is greater than or equal to the difference purchase quantity, setting the commodities of the first provider and the commodities of the second provider as commodities of a second winning bid provider;
and generating a purchase order according to the commodity of the second winning bid provider and the purchase quantity.
4. The method of claim 1, wherein the commodity information further comprises a date and a supplier order performance rate;
the determining, by using a normalization function, a price deviation score and a remaining quantity deviation score corresponding to a commodity price and a remaining quantity of each provider, and determining a score corresponding to a commodity of each provider according to the price deviation score and the remaining quantity deviation score, specifically includes:
determining price deviation scores, residual quantity deviation scores, goods period deviation scores and order performance rate deviation scores corresponding to the goods period and the order performance rate of the suppliers respectively through normalization functions;
and determining the corresponding scores of the commodities of all suppliers according to the price deviation score, the residual quantity deviation score, the period deviation score and the order performance rate deviation score.
5. The method of claim 4, wherein determining the score corresponding to the commodity of each supplier according to the price deviation score, the remaining quantity deviation score, the period deviation score, and the order performance rate deviation score comprises:
determining the weight proportion among commodity price, commodity residual quantity, commodity period and order performance rate of each supplier respectively;
and determining scores corresponding to commodities of all suppliers according to the weight proportion, the price deviation score, the residual quantity deviation score, the period deviation score and the order performance rate deviation score.
6. The method of claim 5, wherein the determining the score for each supplier's commodity correspondence based on the weight ratio, the price bias score, the remaining quantity bias score, the period bias score, and the order performance rate bias score comprises:
determining a score corresponding to the commodity of each supplier according to a preset formula w= Σpi Qi; wherein W is a score corresponding to a commodity, pi is a weight value of price, residual quantity, period and order performance rate, and Qi is the price deviation score, residual quantity deviation score, period deviation score and order performance rate deviation score.
7. The method of claim 1, wherein the method is applied to an intelligent price ratio model, and wherein prior to the obtaining of the purchase information entered by the current user, the method further comprises:
inputting purchase information and commodity information in a training set into an intelligent price comparison model to be trained, calculating the scores of all suppliers through the intelligent price comparison model to be trained, and outputting the winning commodity with the highest score;
inputting preselected commodities in the training set into the intelligent price comparison model to set the highest score of the winning commodity as the score of the preselected commodity;
invoking a weight value try function, and adjusting the weight proportion among the commodity price, the commodity residual quantity, the commodity period and the order performance rate of the supplier in the commodity information so that the score of the preselected commodity is the score of the winning bid commodity;
and calling a weight value changing function, and replacing the weight proportion in the intelligent price comparison model by the adjusted weight proportion to generate the intelligent price comparison model meeting the requirements.
8. A purchase order generating apparatus, the apparatus comprising:
the purchasing information acquisition unit acquires purchasing information input by a current user, wherein the purchasing information comprises purchasing commodity types and purchasing quantity;
the commodity information acquisition unit is used for transmitting the purchase information to suppliers containing the purchase commodity categories so as to acquire commodity information corresponding to the purchase commodity categories of all the suppliers, wherein the commodity information comprises commodity prices and commodity residual quantity;
a deviation score determining unit for determining price deviation scores and residual quantity deviation scores corresponding to commodity prices and residual quantity of the suppliers respectively through normalization functions;
a scoring unit for determining scores corresponding to the commodities of the suppliers according to the price deviation scores and the residual quantity deviation scores;
and the purchase order generation unit is used for determining the commodity of the winning bid provider according to the scores and the commodity residual quantity corresponding to the commodities of the suppliers and the purchase quantity, and generating a purchase order according to the commodity of the winning bid provider.
9. A purchase order generating apparatus, comprising:
at least one processor; the method comprises the steps of,
a memory communicatively coupled to the at least one processor; wherein, the liquid crystal display device comprises a liquid crystal display device,
the memory stores instructions executable by the at least one processor to enable the at least one processor to:
acquiring purchase information input by a current user, wherein the purchase information comprises purchase commodity types and purchase quantity;
sending the purchase information to suppliers containing the purchase commodity categories to obtain commodity information corresponding to the purchase commodity categories of all suppliers, wherein the commodity information comprises commodity prices and commodity residual quantities;
determining price deviation scores and residual quantity deviation scores corresponding to commodity prices and residual quantity of all suppliers respectively through normalization functions;
determining the corresponding scores of the commodities of all suppliers according to the price deviation scores and the residual quantity deviation scores;
and determining the commodity of the winning supplier according to the scores and the residual commodity quantity corresponding to the commodities of the suppliers and the purchasing quantity, and generating a purchasing order according to the commodity of the winning supplier.
10. A non-transitory computer storage medium storing computer-executable instructions configured to:
acquiring purchase information input by a current user, wherein the purchase information comprises purchase commodity types and purchase quantity;
sending the purchase information to suppliers containing the purchase commodity categories to obtain commodity information corresponding to the purchase commodity categories of all suppliers, wherein the commodity information comprises commodity prices and commodity residual quantities;
determining price deviation scores and residual quantity deviation scores corresponding to commodity prices and residual quantity of all suppliers respectively through normalization functions;
determining the corresponding scores of the commodities of all suppliers according to the price deviation scores and the residual quantity deviation scores;
and determining the commodity of the winning supplier according to the scores and the residual commodity quantity corresponding to the commodities of the suppliers and the purchasing quantity, and generating a purchasing order according to the commodity of the winning supplier.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310331642.9A CN116503001A (en) | 2023-03-30 | 2023-03-30 | Method, device, equipment and medium for generating purchase order |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310331642.9A CN116503001A (en) | 2023-03-30 | 2023-03-30 | Method, device, equipment and medium for generating purchase order |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116503001A true CN116503001A (en) | 2023-07-28 |
Family
ID=87323858
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310331642.9A Pending CN116503001A (en) | 2023-03-30 | 2023-03-30 | Method, device, equipment and medium for generating purchase order |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116503001A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117495508A (en) * | 2023-11-23 | 2024-02-02 | 网麒科技(北京)有限责任公司 | Multi-data collaborative purchase screening method, device, equipment and storage medium |
| CN117495508B (en) * | 2023-11-23 | 2024-04-30 | 网麒科技(北京)有限责任公司 | Multi-data collaborative purchase screening method, device, equipment and storage medium |
-
2023
- 2023-03-30 CN CN202310331642.9A patent/CN116503001A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117495508A (en) * | 2023-11-23 | 2024-02-02 | 网麒科技(北京)有限责任公司 | Multi-data collaborative purchase screening method, device, equipment and storage medium |
| CN117495508B (en) * | 2023-11-23 | 2024-04-30 | 网麒科技(北京)有限责任公司 | Multi-data collaborative purchase screening method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109034979B (en) | Quotation system and quotation method | |
| Cheung et al. | A multi-perspective knowledge-based system for customer service management | |
| CN110348963B (en) | Method and system for realizing intelligent transaction recommendation of multiple commodities for transaction platform | |
| WO2004102323A2 (en) | System or method for analyzing information organized in a configurable manner | |
| CN108846689B (en) | Food price supervision method, equipment and system | |
| US20070250401A1 (en) | Searching method and apparatus | |
| US20120232952A1 (en) | Inventory price optimization | |
| CN110659937A (en) | Gradient-lifting-tree-based improved supplier quantitative scoring prediction algorithm | |
| Huang | Information architecture for effective Workload Control: an insight from a successful implementation | |
| CN110796416A (en) | Industrial networking based order processing method and computer storage medium | |
| US20120271741A1 (en) | Inventory price optimization with key price list | |
| CN116503001A (en) | Method, device, equipment and medium for generating purchase order | |
| CN113516492A (en) | Data processing method and device | |
| CN113469598A (en) | Intelligent supply chain system and server platform | |
| CN113515790B (en) | Fishing gear interactive customization method and system | |
| Mehrmanesh et al. | Modelling the customer relationship management in a multi-layer supply chain considering product life cycle | |
| JP7392725B2 (en) | Negotiation systems, negotiation methods and negotiation programs | |
| CN112926997A (en) | Customer relationship management system and method | |
| CN115587689B (en) | Data management system and method based on big data technology | |
| JP4617926B2 (en) | Sales production integrated plan data processing device, sales production integrated plan data processing method, and sales production integrated plan data processing program | |
| WO2001002927A2 (en) | Integrated business-to-business web commerce and business automation system | |
| JPH09179916A (en) | Component inventory schedule planning support system | |
| CN116434928B (en) | Medical SPD supply chain intelligent management method and device and computer equipment | |
| Yarova et al. | MARKETPLACES AS A KEY DRIVER OF GLOBAL E-COMMERCE | |
| CN117522267A (en) | Order decision method and system for information update in uncertain supply scene |
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 |