Purchase plan packaging method, electronic equipment and computer program product

Abstract

The invention provides a purchase plan packaging method, electronic equipment and a computer program product, and is applied to the technical field of data analysis. The method comprises the following steps: determining a plurality of purchase plans needing to be packaged; packaging the plurality of purchase plans based on a target undirected graph to obtain at least one purchase package; wherein the nodes in the target undirected graph represent a purchase plan in the historical packaging process, and the edges in the target undirected graph represent that the nodes at the two ends of the edges are packaged into the same purchase package in the historical packaging process. According to the method, automatic packaging can be realized on the basis of the target undirected graph for the multiple purchase plans needing to be packaged, so that the problems of low manual packaging efficiency and easiness in mistaking are avoided.

Description

Technical Field

[0001] This application relates to the field of data analysis technology, and in particular, to a method for packing procurement plans, an electronic device, and a computer program product. Background Art

[0002] In modern logistics management, the formulation and execution of procurement plans are important links to ensure the smooth operation of the supply chain. Usually, the number of procurement plans is multiple. To improve procurement efficiency and reduce costs, enterprises will pack the procurement plans to form procurement packages, and then implement the procurement plans according to the procurement packages.

[0003] Currently, most enterprises mainly rely on manual operations when packing procurement plans, that is, experienced procurement personnel decide how to combine various procurement plans according to personal experience, and then use the combined procurement plans as procurement packages to achieve the packing of procurement plans.

[0004] However, the manual packing method is limited by the ability of the packer, and there are problems of low packing efficiency and easy errors. Summary of the Invention

[0005] Based on the above technical status quo, this application proposes a method for packing procurement plans, an electronic device, and a computer program product.

[0006] According to the first aspect of the embodiments of the present application, a method for packing procurement plans is provided. The method includes:

[0007] Determine multiple procurement plans to be packed; pack the multiple procurement plans based on a target undirected graph to obtain at least one procurement package; wherein, the nodes in the target undirected graph represent the procurement plans in the historical packing process, and the edges in the target undirected graph represent that the nodes at both ends of the edge are packed into the same procurement package in the historical packing process.

[0008] Optionally, each procurement plan includes one material, and the nodes in the target undirected graph represent the materials of the procurement plans in the historical packing process.

[0009] Optionally, the node is the unique code of the material it represents.

[0010] Optionally, packing the multiple procurement plans based on a target undirected graph to obtain at least one procurement package includes:

[0011] Input the multiple procurement plans into a packing network model to obtain a preliminary packing result output by the packing network model;

[0012] Use the target undirected graph to correct the preliminary packing result to obtain at least one procurement package.

[0013] Optionally, the preliminary packaging result includes multiple intermediate procurement packages, and the target undirected graph is used to correct the preliminary packaging result to obtain at least one procurement package, including:

[0014] For each of the intermediate procurement packages, disassemble the scattered procurement plans therein, determine the second node connected to the first node in the target undirected graph, and pack the scattered procurement plans into the intermediate procurement package to which the first procurement plan belongs;

[0015] Wherein, the scattered procurement plans include: the procurement plans in the intermediate procurement package that are isolated after being connected according to the target undirected graph; the first node is the node representing the scattered procurement plan, and the first procurement plan is the procurement plan represented by the second node.

[0016] Optionally, the packaging network model is trained by the following steps:

[0017] Analyze the packaging habits and bases in the historical packaging data through the frequent item analysis algorithm, and use the historical packaging data with the analyzed packaging habits and bases as the training set;

[0018] Use the training set to train the initial network model to obtain the packaging network model.

[0019] Optionally, based on the target undirected graph, the multiple procurement plans are packaged to obtain at least one procurement package, including:

[0020] Traverse the multiple procurement plans, determine the fourth node connected to the third node in the target undirected graph, and pack the currently traversed procurement plan into the procurement package to which the second procurement plan belongs;

[0021] Wherein, the third node is the node representing the currently traversed procurement plan, and the second procurement plan is the procurement plan represented by the fourth node.

[0022] Optionally, the method further includes:

[0023] Update the target undirected graph with the latest packaging data every first time period, wherein the latest packaging data includes: the historical packaging data of the procurement plans within the second time period before the current moment.

[0024] Optionally, after packaging the multiple procurement plans based on the target undirected graph to obtain at least one procurement package, the method further includes:

[0025] Calculate the total procurement amount of each procurement package;

[0026] In the case where the total procurement amount of the first procurement package is greater than the target amount, add a tender label to the first procurement package;

[0027] When the total purchase amount of the first purchase package is less than or equal to the target amount, an inquiry label is added to the first purchase package;

[0028] The first purchase package is any purchase package among the at least one purchase package.

[0029] Optionally, after packing the multiple purchase plans based on the target undirected graph to obtain at least one purchase package, the method further includes:

[0030] For each purchase package, output the information of the purchase plans in the purchase package according to the target field.

[0031] According to the second aspect of the embodiments of the present application, a method for packing purchase plans is provided, and the method includes:

[0032] Determine multiple purchase plans that need to be packed; determine the purchase types to which the multiple purchase plans belong; when the purchase types of the multiple purchase plans are of the first type, pack the multiple purchase plans based on the target undirected graph to obtain at least one purchase package; wherein, the nodes in the target undirected graph represent the purchase plans in the historical packing process, and the edges in the target undirected graph represent that the nodes at both ends of the edge are packed into the same purchase package in the historical packing process.

[0033] Optionally, after determining the purchase types to which the multiple purchase plans belong, the method further includes:

[0034] When the purchase types of the multiple purchase plans are of the second type, aggregate the multiple purchase plans based on the brand information of the purchase plans to obtain an aggregation result;

[0035] Pack the purchase plans in the aggregation result based on the similarity of the material names in the purchase plans to obtain at least one purchase package.

[0036] Optionally, after determining the purchase types to which the multiple purchase plans belong, the method further includes:

[0037] When the purchase types of the multiple purchase plans are of the third type, pack the multiple purchase plans based on the brand information and the purchaser information in the purchase plans to obtain at least one purchase package.

[0038] According to the third aspect of the embodiments of the present application, a device for packing purchase plans is provided, and the device includes:

[0039] A procurement plan packaging module, configured to determine multiple procurement plans to be packaged; a packaging module, configured to package the multiple procurement plans based on a target undirected graph to obtain at least one procurement package; wherein, the nodes in the target undirected graph represent procurement plans in the historical packaging process, and the edges in the target undirected graph represent that the nodes at both ends of the edge are packaged into the same procurement package in the historical packaging process.

[0040] According to a fourth aspect of the embodiments of the present application, there is provided a procurement plan packaging device, the device includes:

[0041] A procurement plan determination module, configured to determine multiple procurement plans to be packaged; a type determination module, configured to determine the procurement types to which the multiple procurement plans belong; a packaging module, configured to, when the procurement types of the multiple procurement plans are of a first type, package the multiple procurement plans based on a target undirected graph to obtain at least one procurement package; wherein, the nodes in the target undirected graph represent procurement plans in the historical packaging process, and the edges in the target undirected graph represent that the nodes at both ends of the edge are packaged into the same procurement package in the historical packaging process.

[0042] According to a fifth aspect of the embodiments of the present application, there is provided an electronic device, including a memory and a processor; the memory is connected to the processor and is configured to store a program; the processor is configured to implement the procurement plan packaging method as described in the first aspect or the second aspect by running the program in the memory.

[0043] According to a sixth aspect of the embodiments of the present application, there is provided a storage medium, on which a computer program is stored, and when the computer program is run by a processor, the procurement plan packaging method as described in the first aspect or the second aspect is implemented.

[0044] According to a seventh aspect of the embodiments of the present application, there is provided a computer program product, including: a computer program, and when the computer program is executed by a processor, the procurement plan packaging method as described in the first aspect or the second aspect is implemented.

[0045] In the embodiments of the present application, for multiple procurement plans to be packaged, automatic packaging can be realized based on a target undirected graph, thereby avoiding the problems of low efficiency and easy errors in manual packaging; at the same time, the target undirected graph is generated according to the data in the historical packaging process, and its edges can represent the historical packaging situation, so the method of obtaining procurement packages using the target undirected graph can greatly ensure the reliability of the packaging result. Description of the Drawings

[0046] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only the embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on the provided drawings.

[0047] Figure 1 One of the schematic flowcharts of a method for packing a procurement plan provided by an embodiment of the present application;

[0048] Figure 2 Schematic diagram of the target undirected graph provided by an embodiment of the present application;

[0049] Figure 3 Schematic diagram of the BERT network architecture;

[0050] Figure 4 Another schematic flowchart of a method for packing a procurement plan provided by an embodiment of the present application;

[0051] Figure 5 Another schematic flowchart of a method for packing a procurement plan provided by an embodiment of the present application;

[0052] Figure 6 One of the schematic structural diagrams of a device for packing a procurement plan provided by an embodiment of the present application;

[0053] Figure 7 Another schematic structural diagram of a device for packing a procurement plan provided by an embodiment of the present application;

[0054] Figure 8 Schematic structural diagram of an electronic device provided by an embodiment of the present application. Detailed implementation manners

[0055] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0056] Overview

[0057] As described in the background art, the packaging of procurement plans is a crucial task for a company's procurement, which directly affects the efficiency and effectiveness of subsequent procurement processes. Traditional procurement plan packaging methods mostly rely on manual operations. Currently, although there are already some automated procurement plan packaging methods, they can only handle single procurement plans. For complex and non-single procurement plans, accurate packaging results that comply with business rules are often not achievable.

[0058] In view of the above technical status quo, an embodiment of the present application proposes a method for packaging procurement plans. For multiple procurement plans that need to be packaged, automatic packaging can be achieved based on a target undirected graph, thereby avoiding the problems of low efficiency and error-proneness in manual packaging; at the same time, the target undirected graph is generated based on data in the historical packaging process, and its edges can represent the historical packaging situation. Therefore, the method of obtaining procurement packages using the target undirected graph can greatly ensure the reliability of the packaging results.

[0059] Exemplary Method

[0060] In an exemplary embodiment, a method for packaging procurement plans is provided. This method for packaging procurement plans can be applied to any electronic device. For example, the electronic device can include a computer, a server, a smart phone, etc. As Figure 1 shown, this method for packaging procurement plans can include:

[0061] S101: Determine multiple procurement plans that need to be packaged.

[0062] In this step, the multiple procurement plans that need to be packaged can be procurement plans specified by the user. Among them, any method can be used for the user to specify procurement plans. In some embodiments, the user can use the input or import method to transmit the information of multiple procurement plans to the electronic device, and these procurement plans transmitted to the electronic device are the multiple procurement plans that need to be packaged. In some embodiments, the user can also perform operations on the electronic device to directly download multiple procurement plans from the cloud, and these downloaded procurement plans are the multiple procurement plans that need to be packaged. Of course, a procurement plan library can also be established locally on the electronic device to store a large number of procurement plans. The user can freely select multiple procurement plans that need to be packaged through operations on the electronic device.

[0063] Regarding the specific content of the procurement plan, it usually includes information such as the purchaser, the supplier, and the procurement object. The present application does not make any limitations. In some embodiments, the procurement plan includes multiple pieces of information such as purchaser information, material information, procurement method, evaluation method, public or invitation, whether it is a priority, the name of the supplier, the attributes of the supplier, the classification to which the supplier belongs, the service fee ratio, and the procurement amount.

[0064] S102: Package multiple procurement plans based on the target undirected graph to obtain at least one procurement package;

[0065] In this step, the procurement package is the packaging result of the procurement plan. In some embodiments, the number of procurement packages is not fixed and is determined by the specific packaging situation. For example, if the number of procurement plans is 5, and during the packaging process, it is determined that three of the procurement plans can be packaged into one procurement package, and the remaining two procurement plans cannot be packaged with other procurement plans, then the remaining two procurement plans can be used as two separate procurement packages, and the number of procurement packages in the final packaging result is three. If it is determined during the packaging process that the five procurement plans can be packaged into one procurement package, the number of procurement packages in the final packaging result is one. If each procurement plan cannot be packaged with other procurement plans during the packaging process, the number of procurement packages in the final packaging result is five.

[0066] The target undirected graph is an undirected graph generated based on historical packaging data. Among them, an undirected graph is a basic type in graph theory, which has edges but no direction, and will not be elaborated here. In this embodiment, the packaging strategy or packaging habit in the historical packaging process is recorded or counted through the undirected graph, and then multiple procurement plans are packaged according to this packaging strategy or packaging habit. Among them, the nodes in the target undirected graph represent the procurement plans in the historical packaging process, and the edges in the target undirected graph represent that the nodes at both ends of the edge in the historical packaging process are packaged into the same procurement package. In some embodiments, when generating the target undirected graph based on historical packaging data, the procurement plans are used as nodes, and the basis for establishing edges is that the procurement plans are packaged together to generate the target undirected graph. Among them, the historical packaging data can be the packaging data within any period of time before the current moment. For example, it can be the packaging data of the past three years, but it is not limited to this. The target undirected graph can be, for example, as Figure 2 shown. The black origin is used as node 201, representing the procurement plan. The edges connect different nodes 201 together, and all the edges 202 connected together represent that the procurement plans have been packaged into one procurement package. Among them, Figure 2 only some of the nodes 201 and edges 202 are marked for illustration.

[0067] In the embodiments of the present application, for multiple procurement plans that need to be packaged, automatic packaging can be realized based on the target undirected graph, thereby avoiding the problems of low efficiency and easy errors in manual packaging; at the same time, the target undirected graph is generated according to the data in the historical packaging process, and its edges can represent the historical packaging situation. Therefore, the method of obtaining procurement packages using the target undirected graph can greatly ensure the reliability of the packaging result.

[0068] In some embodiments of the present application, each procurement plan includes one material, and the nodes in the target undirected graph represent the materials of the procurement plans in the historical packaging process.

[0069] It should be noted that the procurement objects in the procurement plan are usually referred to as materials. In the case where a procurement plan contains multiple materials, the suppliers, business requirements, etc. of each material may be different. This makes the packaging process of such a procurement plan very complex and cumbersome, and prone to errors. For this reason, this embodiment can only package the procurement plan containing one material. In some embodiments, in the case where the procurement plan contains n materials, the procurement plan can be disassembled to obtain n procurement plans, and each procurement plan contains one material. Wherein, n is an integer greater than 1.

[0070] It can be understood that when packaging the procurement plan, the key factors to be considered usually include the materials in the procurement plan. And each procurement plan contains one material. Therefore, in the target undirected graph, materials can be used as representatives of the procurement plan, and whether the materials are packaged together is equivalent to whether the procurement plans are packaged together. In this way, when using the target undirected graph to package multiple procurement plans, the materials in multiple procurement plans can be packaged according to the use of the target undirected graph.

[0071] In the embodiments of the present application, in the target undirected graph, materials can be used as representatives of the procurement plan, and whether the materials are packaged together is equivalent to whether the procurement plans are packaged together. Thus, when packaging the procurement plan, the materials in the procurement plan can be packaged, simplifying the packaging process of the procurement plan and facilitating packaging.

[0072] In some embodiments of the present application, the nodes in the target undirected graph are the unique codes of the materials they represent.

[0073] It should be noted that the names of materials may be different at different suppliers. To facilitate the unification of the same materials, in this embodiment, the unique code of the material is used as the node. Wherein, the unique code of the material is a code for distinguishing different materials, the same materials have the same code, and correspondingly, different materials have different codes. Regarding the specific form of the code, it is not limited here. For example, the code can be a code composed of at least one of numbers, letters, and special symbols.

[0074] In the embodiments of the present application, using the unique code of the material as the node of the target undirected graph can unify the procurement plans with the same materials and simplify the target undirected graph.

[0075] In some embodiments of the present application, based on the target undirected graph, multiple procurement plans are packaged to obtain at least one procurement package, including:

[0076] Input multiple procurement plans into the packaging network model to obtain the preliminary packaging result output by the packaging network model;

[0077] Correct the preliminary packaging result using the target undirected graph to obtain at least one procurement package.

[0078] It should be noted that the packaging network model can be a network model pre-trained with historical packaging data, which learns the packaging habits, packaging basis, etc. of the procurement plan through training. Furthermore, this packaging network model can package multiple input procurement plans, and its packaging result is used as the preliminary packaging result for subsequent steps. Among them, the preliminary packaging result includes multiple intermediate procurement packages, and each intermediate procurement package includes at least one procurement plan.

[0079] In this embodiment, limited by the complexity of the packaging process and the limitations of the training data, the preliminary packaging result output by this packaging network model is usually worse than the packaging result directly output by the target undirected graph. For this reason, the target undirected graph can be used to correct the preliminary packaging result, which can not only improve the packaging effect but also reduce the processing time of packaging using the target undirected graph. In some embodiments, the target undirected graph can be used to perform unpacking and recombination operations on the intermediate procurement packages in the preliminary packaging result, so that the procurement packages obtained after unpacking and recombination are more reasonable. For example, the preliminary packaging result includes multiple intermediate procurement packages. Correcting the preliminary packaging result using the target undirected graph to obtain at least one procurement package includes: for each intermediate procurement package, removing the scattered procurement plans therein, determining the second node connected to the first node in the target undirected graph, and packing the scattered procurement plans into the intermediate procurement package to which the first procurement plan belongs; wherein, the scattered procurement plans include: the procurement plans that are isolated after the procurement plans in the intermediate procurement package are connected according to the target undirected graph; the first node is the node representing the scattered procurement plan, and the first procurement plan is the procurement plan represented by the second node.

[0080] In the embodiments of the present application, correcting the preliminary packaging result using the target undirected graph can not only improve the packaging effect but also reduce the processing time of packaging using the target undirected graph.

[0081] In some embodiments of the present application, the packaging network model is trained using the following steps:

[0082] Analyze the packaging habits and packaging basis in the historical packaging data through the frequent item analysis algorithm, and use the historical packaging data with the analyzed packaging habits and packaging basis as the training set;

[0083] Use the training set to train the initial network model to obtain the packaging network model.

[0084] It should be noted that the frequent item analysis algorithm includes, but is not limited to, the Apriori algorithm. It can be understood that the content considered during the packaging process is usually complex and diverse, and some content that needs to be considered is not fixed, and some are accidental. For example, accidental events that occur during the packaging process. Therefore, not every packaging or every procurement package conforms to fixed packaging habits and bases. If all historical packaging data is used as the training set, these accidental packaging data may cause interference and affect the final effect of the model. Therefore, the historical packaging data can be screened, and only the data that can analyze the packaging habits and bases is selected as the training set.

[0085] Regarding the model training process, it will not be elaborated here. It should be noted that this initial network model can be, for example, Figure 3 the model of the BERT (Bidirectional Encoder Representations from Transformers) network architecture shown. The BERT network architecture can include: an input layer 301, an encoding layer 302, and an output layer 303, which will not be elaborated here. In some embodiments, when training using the BERT network model, the BERT network model and the BERT tokenizer can be imported into the preset Transformers library first. Since the input historical packaging data for learning is Chinese text, the Bert-Base-Chinese pre-trained language model can be used, and the BertTokenizer classifier is based on characters, and it is also based on Chinese characters in the Chinese Bert vocabulary.

[0086] In the embodiments of the present application, the data in the historical packaging data that may interfere with model training can be filtered out, and the remaining historical packaging data is selected for model training, so as to improve the performance of the model.

[0087] In some embodiments of the present application, based on the target undirected graph, multiple procurement plans are packaged to obtain at least one procurement package, including:

[0088] Traverse multiple procurement plans, determine the fourth node connected to the third node in the target undirected graph, and package the currently traversed procurement plan into the procurement package to which the second procurement plan belongs;

[0089] Wherein, the third node is the node representing the currently traversed procurement plan, and the second procurement plan is the procurement plan represented by the fourth node.

[0090] It should be noted that the target undirected graph will not be elaborated here. When directly packing the procurement plans using the target undirected graph, usually each procurement plan corresponds to a node in the target undirected graph. According to the connection relationships between the corresponding nodes in the target undirected graph, the procurement plans are packed or combined. Among them, for the connected nodes, the corresponding procurement plans will be packed together, and for the unconnected nodes, the corresponding procurement plans cannot be packed together. In some embodiments, when using the unique code of the material as the node of the target undirected graph, the unique codes of the materials in multiple procurement plans to be packed can be determined first, and then the materials / unique codes / procurement plans are traversed. For each traversed material / unique code / procurement plan, determine the nodes connected to the corresponding node in the target undirected graph, and pack the procurement plans corresponding to these nodes in the multiple procurement plans to be packed together with the traversed procurement plan.

[0091] In the embodiments of the present application, directly packing the procurement plans using the target undirected graph is simpler than the method of first packing using a network model and then correcting using the target undirected graph.

[0092] To avoid the situation where the packing effect deteriorates after the packing habits and packing strategies change over time, in some embodiments of the present application, the method further includes:

[0093] Updating the target undirected graph with the latest packing data every first time period, where the latest packing data includes: the historical packing data of the procurement plans within the second time period before the current moment.

[0094] It should be noted that over time, the packing habits and packing strategies of the procurement plans may change. Therefore, it is necessary to update the target undirected graph in a timely manner using the latest packing data. Among them, the first time period can be a fixed time period, for example, it can be 24 hours, but it is not limited thereto. The second time period can be a relatively long time period, for example, it can be 1 year, but it is not limited thereto. In some embodiments, the target undirected graph can also be updated when the data used by the target undirected graph is updated.

[0095] In some embodiments, the historical packing data is recorded in the historical packing table, the procurement plan table, and the supplier table. These three tables can be updated regularly, and the target undirected graph is regenerated after the update.

[0096] In the embodiments of the present application, after the packing habits and packing strategies change over time, the target undirected graph can be updated in a timely manner, thereby avoiding the situation where the packing effect deteriorates due to this.

[0097] To facilitate the subsequent processing of the procurement packages, in some embodiments of the present application, after packing multiple procurement plans based on the target undirected graph to obtain at least one procurement package, the method further includes:

[0098] Calculate the total procurement amount of each procurement package;

[0099] When the total procurement amount of the first procurement package is greater than the target amount, add a tender label to the first procurement package; when the total procurement amount of the first procurement package is less than or equal to the target amount, add an inquiry label to the first procurement package; the first procurement package is any procurement package among at least one procurement package.

[0100] It should be noted that each procurement plan contains the information of the procurement amount, and the total procurement amount of the procurement package is the sum of the procurement amounts in all procurement plans in the procurement package. It can be understood that the processing methods of procurement plans usually include inquiry, tender, etc., and for procurement plans with a large amount, the tender method is generally used for processing. Therefore, for the convenience of subsequent processing of procurement packages, corresponding labels can be added after generating the procurement packages to prompt the subsequent business processing methods. Among them, the target amount can be a relatively large amount set in advance. For example, the target amount can be 2 million, but it is not limited to this.

[0101] In the embodiments of the present application, by adding tender labels and inquiry labels, the subsequent processing of procurement packages can be facilitated.

[0102] To facilitate business personnel's mastery of procurement plan information, in some embodiments of the present application, after packing multiple procurement plans based on the target undirected graph to obtain at least one procurement package, the method further includes: for each procurement package, output the information of the procurement plans in the procurement package according to the target fields.

[0103] It should be noted that in the subsequent processing process of the procurement package, it is usually necessary to understand the key information of the procurement plans therein. To facilitate business personnel to quickly understand this information, after obtaining the procurement package, these key information can be directly output for it. Among them, the target fields are the fields of key information, and the key information includes but is not limited to: procurement method, evaluation method, public or invitation method, whether it is priority, name of the supplier, attributes of the supplier, classification to which the supplier belongs, service fee ratio, etc. In some embodiments, in the process of outputting this key information, data regularization can be performed on this key information to ensure the consistency and accuracy of all information.

[0104] In some embodiments, when implementing packing through the packing network model and the target undirected graph, the ability of the packing network model to output procurement plan information can be trained during the training of the packing network model.

[0105] In the embodiments of the present application, by outputting the information of the procurement plans in the procurement package, business personnel can quickly understand the situation of the procurement package.

[0106] Such as Figure 4As shown in the figure, an embodiment of the present application also provides a method for packing procurement plans, and the method includes:

[0107] S401: Determine multiple procurement plans to be packed.

[0108] S402: Determine the procurement types to which the multiple procurement plans belong.

[0109] S403: When the procurement types of the multiple procurement plans are of the first type, pack the multiple procurement plans based on the target undirected graph to obtain at least one procurement package;

[0110] Wherein, the nodes in the target undirected graph represent procurement plans in the historical packing process, and the edges in the target undirected graph indicate that the nodes at both ends of the edge are packed into the same procurement package in the historical packing process.

[0111] It should be noted that for the process of packing the multiple procurement plans based on the target undirected graph in S401 and S403 to obtain at least one procurement package, refer to Figure 1 the relevant descriptions of S101 and S102 shown in the figure, which will not be elaborated here. The procurement type is the type divided for the procurement plan. The basis for dividing the procurement type is not limited here. The first type can be any procurement type.

[0112] In the embodiment of the present application, for multiple procurement plans to be packed, automatic packing can be realized based on the target undirected graph, thereby avoiding the problems of low efficiency and error-proneness in manual packing; at the same time, the target undirected graph is generated according to the data in the historical packing process, and its edges can represent the historical packing situation. Therefore, the method of obtaining procurement packages using the target undirected graph can ensure the reliability of the packing result to a large extent.

[0113] To expand the packing scope of the procurement plan, in some embodiments of the present application, after determining the procurement types to which the multiple procurement plans belong, the method further includes:

[0114] When the procurement types of the multiple procurement plans are of the second type, aggregate the multiple procurement plans based on the brand information of the procurement plans to obtain an aggregation result;

[0115] Pack the procurement plans in the aggregation result based on the similarity of the material names in the procurement plans to obtain at least one procurement package.

[0116] It should be noted that for some procurement plans, they have strong rules or rigid requirements, and these rigid requirements will have the highest priority and will be packed according to them first. For example, some purchasers have special requirements and need to implement the procurement plan according to their special requirements. Then, for such procurement plans, the procurement plans are aggregated according to the purchaser information (such as unit name, brand information) to obtain an aggregation result, and then they are packed according to the material classification, and the same and similar materials are packed into one procurement package. Among them, the cosine similarity of the material names can be used as the similarity of the materials.

[0117] In the embodiments of the present application, the packing scope of the procurement plan can be expanded, and the procurement plan with rigid requirements is packed.

[0118] To expand the packing scope of the procurement plan, in some embodiments of the present application, after determining the procurement types to which multiple procurement plans belong, the method further includes:

[0119] When the procurement types of multiple procurement plans are of the third type, the multiple procurement plans are packed based on the brand information and purchaser information in the procurement plan to obtain at least one procurement package.

[0120] It should be noted that for some procurement plans, they have special requirements for suppliers. For example, for some materials involving patented products, the suppliers should be the patent owners. Since the materials can only be collected from specific suppliers, these procurement plans can be regarded as single-source procurement plans. For such procurement plans, the multiple procurement plans are packed based on the brand information and purchaser information.

[0121] In the embodiments of the present application, the packing scope of the procurement plan can be expanded, and the procurement plan with a single source is packed.

[0122] In some embodiments, when determining the procurement types to which the multiple procurement plans belong, the pre-set single-source table can be used first to determine which procurement plans are single-source procurement plans, and then they are determined as the above-mentioned third-type procurement plans. Then, the procurement plans with rigid requirements are screened out by using the pre-set rigid requirement rules, and then they are determined as the above-mentioned second-type procurement plans. Finally, the remaining procurement plans are determined as the above-mentioned first-type procurement plans. The different types of procurement plans are packed according to the corresponding processing methods respectively. For example, Figure 5 as shown.

[0123] S501: Obtain M procurement plans, where M is an integer greater than 1. These M procurement plans can be regarded as all the procurement plans that need to be packed.

[0124] S502: Differentiate the procurement methods for each procurement plan based on business rules. Here, the procurement methods are the same as the procurement types in the above embodiments and will not be elaborated here. Among them, for all procurement plans of the first type, perform packaging according to S503 - S504. For all procurement plans of the second type, perform packaging according to S505. For all procurement plans of the third type, perform packaging according to S506 - S507.

[0125] S503: Perform preliminary packaging based on the BERT model to generate a preliminary packaging result. This process is the same as the process of performing packaging through the packaging network model in the above embodiments and will not be elaborated here.

[0126] S504: Correct the preliminary packaging result based on the target undirected graph to obtain at least one procurement package.

[0127] S505: Package all procurement plans of the second type based on the brand and the procurement unit to obtain at least one procurement package.

[0128] S506: Aggregate all procurement plans of the third type based on the brand to obtain an aggregation result.

[0129] S507: Package the procurement plans in the aggregation result based on the material similarity, and package the same materials or materials with relatively high similarity into one procurement package.

[0130] S508: For each procurement package, determine whether its total procurement amount is greater than the target amount. If so, add a bidding label to the procurement package; if not, add an inquiry label to the procurement package.

[0131] S509: Package attribute detection and writing. Use the BERT model to output the key information of the procurement plans in the procurement package, and then write this key information as the package attribute into the procurement package.

[0132] S510: Data regularization to obtain N procurement packages. Regularize the relevant information of the procurement packages to ensure the consistency and accuracy of all information. The regularized procurement package information includes not only the basic information of the procurement package but also the detailed procurement execution strategy, thus providing a comprehensive and efficient procurement plan.

[0133] In this embodiment, through this intelligent and automated packaging method, the procurement efficiency can be greatly improved, and human errors in the packaging process can be reduced. Moreover, it can also enhance the transparency and fairness of the procurement process, and at the same time better meet different procurement needs and optimize procurement costs.

[0134] In some embodiments of the present application, each procurement plan contains one material, and the nodes in the target undirected graph represent the materials of the procurement plans in the historical packaging process.

[0135] In some embodiments of the present application, the node is the unique code of the material it represents.

[0136] In some embodiments of the present application, multiple procurement plans are packaged based on the target undirected graph to obtain at least one procurement package, including:

[0137] Input the multiple procurement plans into the packaging network model to obtain a preliminary packaging result output by the packaging network model; use the target undirected graph to correct the preliminary packaging result to obtain at least one procurement package.

[0138] In some embodiments of the present application, the preliminary packaging result includes multiple intermediate procurement packages. Using the target undirected graph to correct the preliminary packaging result to obtain at least one procurement package, including:

[0139] For each intermediate procurement package, remove the scattered procurement plans therein, determine the second node connected to the first node in the target undirected graph, and package the scattered procurement plans into the intermediate procurement package to which the first procurement plan belongs; wherein, the scattered procurement plans include: the procurement plans that are isolated after the procurement plans in the intermediate procurement package are connected according to the target undirected graph; the first node is the node representing the scattered procurement plan, and the first procurement plan is the procurement plan represented by the second node.

[0140] In some embodiments of the present application, the packaging network model is trained by the following steps:

[0141] Analyze the packaging habits and bases in the historical packaging data through the frequent item analysis algorithm, and use the historical packaging data with the analyzed packaging habits and bases as the training set; use the training set to train the initial network model to obtain the packaging network model.

[0142] In some embodiments of the present application, multiple procurement plans are packaged based on the target undirected graph to obtain at least one procurement package, including:

[0143] Traverse the multiple procurement plans, determine the fourth node connected to the third node in the target undirected graph, and package the currently traversed procurement plan into the procurement package to which the second procurement plan belongs; wherein, the third node is the node representing the currently traversed procurement plan, and the second procurement plan is the procurement plan represented by the fourth node.

[0144] In some embodiments of the present application, the method further includes:

[0145] Update the target undirected graph with the latest packaging data every first time period, where the latest packaging data includes: the historical packaging data of the procurement plans within the second time period before the current moment.

[0146] In some embodiments of the present application, after packing multiple procurement plans based on a target undirected graph to obtain at least one procurement package, the method further includes:

[0147] Calculate the total procurement amount of each procurement package;

[0148] In the case where the total procurement amount of the first procurement package is greater than the target amount, add a tender label to the first procurement package; in the case where the total procurement amount of the first procurement package is less than or equal to the target amount, add an inquiry label to the first procurement package; the first procurement package is any procurement package among the at least one procurement package.

[0149] In some embodiments of the present application, after packing multiple procurement plans based on a target undirected graph to obtain at least one procurement package, the method further includes:

[0150] For each procurement package, output the information of the procurement plans in the procurement package according to the target fields.

[0151] It should be noted that the relevant descriptions of each embodiment can refer to the above similar embodiments, and will not be repeated here.

[0152] Exemplary Apparatus

[0153] Correspondingly, the embodiments of the present application further provide a packing device for procurement plans. Refer to Figure 6 As shown, the device includes:

[0154] A plan determination module 601, configured to determine multiple procurement plans that need to be packed;

[0155] A packing module 602, configured to pack multiple procurement plans based on a target undirected graph to obtain at least one procurement package; wherein, the nodes in the target undirected graph represent the procurement plans in the historical packing process, and the edges in the target undirected graph represent that the nodes at both ends of the edge are packed into the same procurement package in the historical packing process.

[0156] In some embodiments, each procurement plan includes one material, and the nodes in the target undirected graph represent the materials of the procurement plans in the historical packing process.

[0157] In some embodiments, the node is the unique code of the material it represents.

[0158] In some embodiments, the packing module 602 includes:

[0159] A first packing unit, configured to input multiple procurement plans into a packing network model to obtain a preliminary packing result output by the packing network model;

[0160] A second packing unit, configured to correct the preliminary packing result by using the target undirected graph to obtain at least one procurement package.

[0161] In some embodiments, the preliminary packaging result includes a plurality of intermediate procurement packages. The second packaging unit is specifically configured to, for each intermediate procurement package, remove the scattered procurement plans therein, determine the second nodes connected to the first node in the target undirected graph, and package the scattered procurement plans into the intermediate procurement package to which the first procurement plan belongs. The scattered procurement plans include: the procurement plans that are isolated after the procurement plans in the intermediate procurement package are connected according to the target undirected graph. The first node is the node representing the scattered procurement plan, and the first procurement plan is the procurement plan represented by the second node.

[0162] In some embodiments, the packaging network model is trained by the following steps:

[0163] Analyze the packaging habits and bases in the historical packaging data through the frequent item analysis algorithm, and use the historical packaging data with the analyzed packaging habits and bases as the training set. Use the training set to train the initial network model to obtain the packaging network model.

[0164] In some embodiments, the packaging module 602 is specifically configured to traverse a plurality of procurement plans, determine the fourth nodes connected to the third node in the target undirected graph, and package the currently traversed procurement plan into the procurement package to which the second procurement plan belongs. The third node is the node representing the currently traversed procurement plan, and the second procurement plan is the procurement plan represented by the fourth node.

[0165] In some embodiments, the device further includes:

[0166] An update module, configured to update the target undirected graph with the latest packaging data every first time period, where the latest packaging data includes: the historical packaging data of the procurement plans within the second time period before the current moment.

[0167] In some embodiments, the device further includes: a label module, specifically configured to:

[0168] Calculate the total procurement amount of each procurement package; add a tender label to the first procurement package when the total procurement amount of the first procurement package is greater than the target amount; add an inquiry label to the first procurement package when the total procurement amount of the first procurement package is less than or equal to the target amount. The first procurement package is any procurement package among at least one procurement package.

[0169] In some embodiments, the device further includes: an information output module, configured to output the information of the procurement plans in the procurement package according to the target fields for each procurement package.

[0170] It should be noted that the packaging device for the procurement plan provided in this embodiment belongs to the same inventive concept as the procurement plan packaging method provided in the above embodiments of the present application. It can execute the procurement plan packaging method provided in any of the above embodiments of the present application and has the corresponding functional modules and beneficial effects of the execution method. For the technical details not described in detail in this embodiment, reference can be made to the specific processing content of the procurement plan packaging method provided in the above embodiments of the present application, which will not be elaborated here.

[0171] Correspondingly, an embodiment of the present application also provides a packaging device for a procurement plan. As shown in Figure 7 the figure, the device includes:

[0172] A plan determination module 701, configured to determine a plurality of procurement plans that need to be packaged;

[0173] A type determination module 702, configured to determine the procurement types to which the plurality of procurement plans belong;

[0174] A first packaging module 703, configured to package the plurality of procurement plans based on a target undirected graph to obtain at least one procurement package when the procurement types of the plurality of procurement plans are of the first type; wherein, the nodes in the target undirected graph represent the procurement plans in the historical packaging process, and the edges in the target undirected graph indicate that the nodes at both ends of the edge are packaged into the same procurement package in the historical packaging process.

[0175] In some embodiments, the device further includes:

[0176] A second packaging module, configured to aggregate the plurality of procurement plans based on the brand information of the procurement plans to obtain an aggregation result when the procurement types of the plurality of procurement plans are of the second type; and package the procurement plans in the aggregation result based on the similarity of the material names in the procurement plans to obtain at least one procurement package.

[0177] In some embodiments, the device further includes:

[0178] A third packaging module, configured to package the plurality of procurement plans based on the brand information and the purchaser information in the procurement plans to obtain at least one procurement package when the procurement types of the plurality of procurement plans are of the third type.

[0179] In some embodiments, each procurement plan includes one material, and the nodes in the target undirected graph represent the materials of the procurement plans in the historical packaging process.

[0180] In some embodiments, the node is the unique code of the material it represents.

[0181] In some embodiments, the first packaging module 703 includes:

[0182] The first packaging unit is used to input multiple procurement plans into a packaging network model to obtain a preliminary packaging result output by the packaging network model;

[0183] The second packaging unit is used to correct the preliminary packaging result by using a target undirected graph to obtain at least one procurement package.

[0184] In some embodiments, the preliminary packaging result includes multiple intermediate procurement packages. The second packaging unit is specifically configured to, for each intermediate procurement package, remove the scattered procurement plans therein, determine the second node connected to the first node in the target undirected graph, and pack the scattered procurement plans into the intermediate procurement package to which the first procurement plan belongs; wherein, the scattered procurement plans include: the procurement plans that are isolated after the procurement plans in the intermediate procurement package are connected according to the target undirected graph; the first node is a node representing the scattered procurement plan, and the first procurement plan is the procurement plan represented by the second node.

[0185] In some embodiments, the packaging network model is trained by the following steps:

[0186] Analyze the packaging habits and bases in the historical packaging data through the frequent item analysis algorithm, and use the historical packaging data with the analyzed packaging habits and bases as the training set; use the training set to train the initial network model to obtain the packaging network model.

[0187] In some embodiments, the first packaging module 703 is specifically configured to traverse multiple procurement plans, determine the fourth node connected to the third node in the target undirected graph, and pack the currently traversed procurement plan into the procurement package to which the second procurement plan belongs; wherein, the third node is a node representing the currently traversed procurement plan, and the second procurement plan is the procurement plan represented by the fourth node.

[0188] In some embodiments, the device further includes:

[0189] An update module is used to update the target undirected graph with the latest packaging data every first time period, where the latest packaging data includes: the historical packaging data of the procurement plans within the second time period before the current moment.

[0190] In some embodiments, the device further includes: a labeling module, specifically configured to:

[0191] Calculate the total procurement amount of each procurement package; add a tender label to the first procurement package if the total procurement amount of the first procurement package is greater than the target amount; add an inquiry label to the first procurement package if the total procurement amount of the first procurement package is less than or equal to the target amount; the first procurement package is any procurement package among at least one procurement package.

[0192] In some embodiments, the apparatus further includes an information output module configured to output information of the procurement plan in the procurement package according to the target fields for each procurement package.

[0193] The procurement plan packaging apparatus provided in this embodiment belongs to the same inventive concept as the procurement plan packaging method provided in the foregoing embodiments of the present application. It can execute the procurement plan packaging method provided in any of the foregoing embodiments of the present application and has the corresponding functional modules and beneficial effects of the executed method. For technical details not described in detail in this embodiment, reference may be made to the specific processing content of the procurement plan packaging method provided in the foregoing embodiments of the present application, which will not be elaborated herein.

[0194] It should be understood that the modules in the above apparatus can be implemented in the form of a processor invoking software. For example, the apparatus includes a processor connected to a memory. Instructions are stored in the memory, and the processor invokes the instructions stored in the memory to implement any of the above methods or the functions of each unit of the apparatus. The processor can be a general-purpose processor, such as a CPU or a microprocessor, etc., and the memory can be a memory inside or outside the apparatus. Alternatively, the units in the apparatus can be implemented in the form of a hardware circuit. By designing the hardware circuit, the functions of some or all of the units can be implemented. The hardware circuit can be understood as one or more processors. For example, in one implementation, the hardware circuit is an ASIC, and the functions of some or all of the above units are implemented by designing the logical relationship of the components in the circuit. Another example is that in another implementation, the hardware circuit can be implemented by a PLD. Taking an FPGA as an example, it can include a large number of logic gate circuits, and the connection relationship between the logic gate circuits is configured through a configuration file to implement the functions of some or all of the above units. All units of the above apparatus can be all implemented in the form of a processor invoking software, or all implemented in the form of a hardware circuit, or some implemented in the form of a processor invoking software and the remaining part implemented in the form of a hardware circuit.

[0195] In the embodiments of the present application, a processor is a circuit with signal processing capabilities. In one implementation, the processor can be a circuit with instruction reading and running capabilities, such as a CPU, a microprocessor, a GPU, or a DSP, etc. In another implementation, the processor can implement certain functions through the logical relationship of a hardware circuit, and the logical relationship of the hardware circuit is fixed or can be reconfigured. For example, the processor is a hardware circuit implemented by an ASIC or a PLD, such as an FPGA. In a reconfigurable hardware circuit, the process of the processor loading a configuration document to implement the configuration of the hardware circuit can be understood as the process of the processor loading instructions to implement the functions of some or all of the above units. In addition, it can also be a hardware circuit designed for artificial intelligence, which can be understood as a type of ASIC, such as an NPU, a TPU, a DPU, etc.

[0196] It can be seen that each unit in the above device can be one or more processors (or processing circuits) configured to implement the above method. For example: CPU, GPU, NPU, TPU, DPU, microprocessor, DSP, ASIC, FPGA, or a combination of at least two of these processor forms.

[0197] In addition, each unit in the above device can be integrated in whole or in part, or can be independently implemented. In one implementation, these units are integrated together and implemented in the form of an SOC. The SOC can include at least one processor for implementing any of the above methods or implementing the functions of each unit of the device. The types of the at least one processor can be different. For example, it includes a CPU and an FPGA, a CPU and an artificial intelligence processor, a CPU and a GPU, etc.

[0198] Exemplary Electronic Device

[0199] An embodiment of the present application provides an electronic device. Refer to Figure 8 As shown, the device includes:

[0200] A memory 800 and a processor 810;

[0201] Wherein, the memory 800 is connected to the processor 810 and is used for storing programs;

[0202] The processor 810 is used for implementing the packing method of the procurement plan disclosed in any of the above embodiments by running the program stored in the memory 800.

[0203] Specifically, the above electronic device may further include: a bus, a communication interface 820, an input device 830, and an output device 840.

[0204] The processor 810, the memory 800, the communication interface 820, the input device 830, and the output device 840 are interconnected through the bus. Among them:

[0205] The bus may include a path for transmitting information between various components of the computer system.

[0206] The processor 810 can be a general-purpose processor, such as a general-purpose central processing unit (CPU), a microprocessor, etc., or an application-specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of the program of the present invention solution. It can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0207] The processor 810 may include a main processor, and may also include a baseband chip, a modem, etc.

[0208] The memory 800 stores a program for implementing the technical solution of the present invention, and may also store an operating system and other critical services. Specifically, the program may include program code, and the program code includes computer operation instructions. More specifically, the memory 800 may include a read-only memory (ROM), other types of static storage devices that can store static information and instructions, a random access memory (RAM), other types of dynamic storage devices that can store information and instructions, a disk memory, a flash memory, etc.

[0209] The input device 830 may include a device for receiving data and information input by a user, such as a keyboard, a mouse, a camera, a scanner, a light pen, a voice input device, a touch screen, a pedometer, or a gravity sensor, etc.

[0210] The output device 840 may include a device for allowing information to be output to a user, such as a display screen, a printer, a speaker, etc.

[0211] The communication interface 820 may include a device of any transceiver type for communicating with other devices or communication networks, such as an Ethernet, a radio access network (RAN), a wireless local area network (WLAN), etc.

[0212] The processor 810 executes the program stored in the memory 800 and calls other devices, and can be used to implement each step of any one of the procurement plan packaging methods provided in the above embodiments of the present application.

[0213] An embodiment of the present application also proposes a chip, which includes a processor and a data interface. The processor reads and runs a program stored on a memory through the data interface to execute the procurement plan packaging method introduced in any of the above embodiments. The specific processing process and its beneficial effects can be referred to the embodiment introduction of the procurement plan packaging method above.

[0214] Exemplary Computer Program Product and Storage Medium

[0215] In addition to the above methods and devices, an embodiment of the present application may also be a computer program product, which includes computer program instructions. When the computer program instructions are run by a processor, the processor is caused to execute the steps in the procurement plan packaging method according to various embodiments of the present application described in any of the above embodiments of this specification.

[0216] The computer program product can be written in any combination of one or more programming languages for programming code to perform the operations of the embodiments of the present application. The programming languages include object-oriented programming languages such as Java, C++, etc., and also include conventional procedural programming languages such as the "C" language or similar programming languages. The programming code can be executed entirely on the user's computing device, partially on the user's device, executed as an independent software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0217] In addition, an embodiment of the present application can also be a storage medium on which a computer program is stored, and the computer program is executed by a processor to perform the steps in the packaging method of the procurement plan according to various embodiments of the present application described in any of the above embodiments of this specification.

[0218] For the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to the present application.

[0219] It should be noted that the various embodiments in this specification are described in a progressive manner. Each embodiment focuses on the differences from other embodiments. The same or similar parts among the various embodiments can be referred to each other. For the device embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0220] The steps in the methods of the various embodiments of the present application can be adjusted, combined, and deleted according to actual needs. The technical features recorded in the various embodiments can be replaced or combined.

[0221] The modules and sub-modules in the devices and terminals in the various embodiments of the present application can be combined, divided, and deleted according to actual needs.

[0222] In several embodiments provided by the present application, it should be understood that the disclosed terminals, devices, and methods can be implemented in other ways. For example, the terminal embodiments described above are merely illustrative. For example, the division of modules or sub-modules is only a logical function division. In actual implementation, there may be other division methods. For example, multiple sub-modules or modules can be combined or integrated into another module, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling, direct coupling, or communication connection between each other can be through some interfaces. The indirect coupling or communication connection of devices or modules can be in the form of electricity, machinery, or other forms.

[0223] The modules or sub-modules described as separate components may or may not be physically separated. The components as modules or sub-modules may or may not be physical modules or sub-modules, that is, they can be located in one place, or can be distributed to multiple network modules or sub-modules. Some or all of the modules or sub-modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0224] In addition, in each embodiment of the present application, each functional module or sub-module can be integrated in a processing module, or each module or sub-module can exist physically alone, or two or more modules or sub-modules can be integrated in one module. The above-mentioned integrated modules or sub-modules can be implemented in the form of hardware, or can be implemented in the form of software functional modules or sub-modules.

[0225] Those skilled in the art can further realize that the units and algorithm steps of each example described in combination with the embodiments disclosed in this article can be implemented by electronic hardware, computer software, or a combination of the two. To clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described according to functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0226] The steps of the methods or algorithms described in combination with the embodiments disclosed in this article can be directly implemented by hardware, software units executed by a processor, or a combination of the two. The software units can be placed in a random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium well-known in the technical field.

[0227] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0228] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for packing a procurement plan, characterized in that, The packing method of the procurement plan includes: Determine multiple procurement plans to be packed; Pack the multiple procurement plans based on a target undirected graph to obtain at least one procurement package; Wherein, the nodes in the target undirected graph represent procurement plans in the historical packing process, and the edges in the target undirected graph represent that the nodes at both ends of the edge are packed into the same procurement package in the historical packing process.

2. The method according to claim 1, characterized in that Each of the procurement plans contains one material, and the nodes in the target undirected graph represent the materials of the procurement plans in the historical packing process.

3. The method according to claim 2, wherein The node is the unique code of the material it represents.

4. The method according to claim 1 or 2 or 3, characterized in that Packing the multiple procurement plans based on the target undirected graph to obtain at least one procurement package includes: Input the multiple procurement plans into a packing network model to obtain a preliminary packing result output by the packing network model; Use the target undirected graph to correct the preliminary packing result to obtain at least one procurement package.

5. The method according to claim 4, wherein The preliminary packing result includes multiple intermediate procurement packages. Using the target undirected graph to correct the preliminary packing result to obtain at least one procurement package includes: For each of the intermediate procurement packages, remove the scattered procurement plans therein, determine the second node connected to the first node in the target undirected graph, and pack the scattered procurement plans into the intermediate procurement package to which the first procurement plan belongs; Wherein, the scattered procurement plans include: the procurement plans that are isolated after the procurement plans in the intermediate procurement package are connected according to the target undirected graph; the first node is the node representing the scattered procurement plan, and the first procurement plan is the procurement plan represented by the second node.

6. The method according to claim 4, characterized in that The packing network model is trained by the following steps: Analyze the packing habits and packing bases in the historical packing data through a frequent item analysis algorithm, and use the historical packing data with the analyzed packing habits and packing bases as the training set; Use the training set to train an initial network model to obtain a packing network model.

7. The method according to claim 1 or 2 or 3, characterized in that Packing the multiple procurement plans based on the target undirected graph to obtain at least one procurement package includes: Traverse the multiple procurement plans, determine the fourth node connected to the third node in the target undirected graph, and pack the currently traversed procurement plan into the procurement package to which the second procurement plan belongs; Wherein, the third node is the node representing the currently traversed procurement plan, and the second procurement plan is the procurement plan represented by the fourth node.

8. The method according to claim 1 or 2 or 3, characterized in that, The method further includes: Update the target undirected graph with the latest packing data every first time period, wherein the latest packing data includes: the historical packing data of the procurement plans within the second time period before the current moment.

9. The method according to claim 1 or 2 or 3, characterized in that, After packing the multiple procurement plans based on the target undirected graph to obtain at least one procurement package, the method further includes: Calculate the total procurement amount of each procurement package; In the case where the total procurement amount of the first procurement package is greater than the target amount, add a bidding label to the first procurement package; In the case where the total procurement amount of the first procurement package is less than or equal to the target amount, add an inquiry label to the first procurement package; The first procurement package is any procurement package among the at least one procurement package.

10. The method according to claim 1 or 2 or 3, characterized in that, After packing the multiple procurement plans based on the target undirected graph to obtain at least one procurement package, the method further includes: For each of the procurement packages, output the information of the procurement plans in the procurement package according to the target field.

11. A method for packing a procurement plan, characterized in that, The method for packing the procurement plans includes: Determine multiple procurement plans that need to be packed; Determine the procurement types to which the multiple procurement plans belong; When the procurement types of the multiple procurement plans are of the first type, pack the multiple procurement plans based on the target undirected graph to obtain at least one procurement package; Wherein, the nodes in the target undirected graph represent procurement plans in the historical packing process, and the edges in the target undirected graph represent that the nodes at both ends of the edge are packed into the same procurement package in the historical packing process.

12. The method according to claim 11, wherein After determining the procurement types to which the multiple procurement plans belong, the method further includes: When the procurement types of the multiple procurement plans are of the second type, aggregate the multiple procurement plans based on the brand information of the procurement plans to obtain an aggregation result; Pack the procurement plans in the aggregation result based on the similarity of the material names in the procurement plans to obtain at least one procurement package.

13. The method according to claim 11, wherein After determining the procurement types to which the multiple procurement plans belong, the method further includes: When the procurement types of the multiple procurement plans are of the third type, pack the multiple procurement plans based on the brand information and the purchaser information in the procurement plans to obtain at least one procurement package.

14. An electronic device, characterized in that, Including a memory and a processor; The memory is connected to the processor and is used to store programs; The processor is used to implement the method for packing the procurement plans as described in any one of claims 1 to 13 by running the programs in the memory.

15. A computer program product, characterized in that, Including: A computer program, which implements the method for packing the procurement plans as described in any one of claims 1 to 13 when executed by a processor.

Images