A multi-party data real-time interaction and collaboration method and system of a digitalized procurement platform

Abstract

The application discloses a kind of multi-party data real-time interaction and collaborative method and system of digitalization procurement platform, it is related to data processing and interaction technical field, including: in combination with blockchain technology and big data technology, establish the digitalization procurement platform for multi-party data interaction;Based on message queue technology, data real-time interaction channel is built in digitalization procurement platform, at the same time, the data interaction process is automatically controlled using smart contract technology;In the process of data interaction, machine learning algorithm is introduced for data analysis and prediction, and intelligent selection scheme is provided.The application solves the problems of data interaction delay, poor collaboration, low transparency and insufficient security in the existing procurement mode, realizes the real-time interaction and collaboration of multi-party data in the procurement process, and improves the procurement efficiency, transparency and security.

Description

Technical Field

[0001] This invention relates to the field of data processing and interaction technology, and more specifically to a method and system for real-time multi-party data interaction and collaboration in a digital procurement platform. Background Technology

[0002] In the long-term operation of the traditional procurement model, a series of drawbacks have gradually become apparent, significantly hindering the efficient, fair, and secure advancement of procurement activities. The procurement process involves multiple roles, including the purchaser, suppliers, agents, and evaluation experts; however, the information transmission channels between these parties are complex and lack efficient integration, resulting in extremely poor communication. After submitting a procurement request, the purchaser often struggles to quickly and accurately convey it to suitable suppliers. Furthermore, supplier feedback, in its transmission back to the purchaser, is frequently delayed or inaccurate due to cumbersome intermediary steps, leading to a significant increase in unnecessary waiting time and extremely low efficiency in the procurement process.

[0003] In the traditional model, data interaction mainly relies on manual operations, such as sending emails and copying and transferring files. This method is not only time-consuming and labor-intensive, but also prone to errors. As the amount of data increases, the delay in data interaction becomes more and more serious, making it impossible for various stages of the procurement project to be closely connected, and further exacerbating the complexity of the procurement process.

[0004] Furthermore, the systems and tools used by different participants vary significantly. The purchaser may use a custom-designed internal procurement management system, while suppliers employ different types of sales management software based on their own business characteristics. Agencies and evaluation experts also have their own independent work platforms. The lack of unified data interfaces and interaction standards between these systems makes data integration and sharing extremely difficult. This difficulty in data flow and integration makes it hard for all parties to grasp the overall picture of the procurement project, significantly reducing the transparency of the procurement process.

[0005] During the evaluation process, bidding experts need to comprehensively understand a supplier's past performance, product quality, credit status, and other information to make an objective and fair assessment. However, in practice, experts have limited and cumbersome access to this information, often requiring them to search through multiple channels, which consumes a significant amount of time and energy. Moreover, due to the untimely and incomplete acquisition of information, experts struggle to quickly form a comprehensive judgment on suppliers, which greatly affects the accuracy and fairness of the evaluation results and fails to guarantee that the procurement project can select the best supplier.

[0006] Therefore, how to provide a method and system for real-time multi-party data interaction and collaboration in a digital procurement platform, break down information barriers between parties, achieve real-time data interaction and efficient collaboration, improve procurement efficiency, enhance transparency, ensure data security, and thus comprehensively improve the overall effectiveness of procurement activities is a problem that urgently needs to be solved by those skilled in the art. Summary of the Invention

[0007] In view of this, the present invention provides a method and system for real-time multi-party data interaction and collaboration in a digital procurement platform, which solves the problems of data interaction delay, poor collaboration, low transparency and insufficient security in the existing procurement model, realizes real-time multi-party data interaction and collaboration in the procurement process, and improves procurement efficiency, transparency and security.

[0008] To achieve the above objectives, the present invention adopts the following technical solution: a method for real-time multi-party data interaction and collaboration in a digital procurement platform, comprising:

[0009] By combining blockchain and big data technologies, a digital and intelligent procurement platform will be established for multi-party data interaction.

[0010] Based on message queue technology, a real-time data interaction channel is built in the digital procurement platform. At the same time, smart contract technology is used to automate the data interaction process.

[0011] During the data interaction process, machine learning algorithms are introduced to perform data analysis and prediction, providing intelligent selection options.

[0012] Preferably, the digital procurement platform includes a front-end interaction layer, a middle business logic layer, and a back-end data storage layer;

[0013] The front-end interaction layer provides personalized operation interfaces for purchasers, suppliers, agencies, and bid evaluation experts.

[0014] The intermediate business logic layer is used for data verification, process control, and access control.

[0015] The backend data storage layer uses a distributed database for centralized data storage and management.

[0016] Preferably, the digital procurement platform performs real-time data preprocessing during the data access process and converts data of various formats into a standard format through data standardization.

[0017] Preferably, based on message queue technology, a real-time data interaction channel is established in the intelligent procurement platform, including:

[0018] When a user updates data, the updated data is encapsulated into a message and sent to the message queue. The message queue pushes the message to the relevant parties quickly and accurately according to the first-in-first-out principle.

[0019] Utilizing smart contract technology to automate data interaction processes, including:

[0020] Once a purchaser publishes a procurement project, the smart contract automatically filters potential suppliers according to preset rules and sends them procurement invitations.

[0021] Preferably, a digital and intelligent procurement platform is established by combining blockchain and big data technologies for multi-party data interaction, including:

[0022] Build a private blockchain network and connect it to the public blockchain network, Boom Blockchain Network;

[0023] Define enterprise database data specifications based on the data content of the enterprise database;

[0024] Analyze the requirements of the business system and build blockchain nodes accordingly;

[0025] Write the relevant smart contracts and deploy them to the blockchain network;

[0026] Build a blockchain data center to encrypt and record data in a chain;

[0027] A digital procurement platform for multi-party data interaction is established based on a blockchain data center.

[0028] Preferably, machine learning algorithms are introduced for data analysis and prediction to provide intelligent selection solutions, including:

[0029] Extract historical procurement data from the backend data storage layer;

[0030] Identify influencing factors and predictive factors, and establish a predictive model based on machine learning algorithms;

[0031] The parameters of the prediction model were optimized using an improved quantum gray wolf algorithm to obtain the optimal parameters.

[0032] The optimal parameter combination obtained from the improved quantum gray wolf algorithm is applied to machine learning algorithms;

[0033] The optimized forecasting model is used to analyze and predict procurement data;

[0034] The analysis and forecast results are integrated into the front-end interaction layer of the intelligent procurement platform to provide decision-making solutions for all users.

[0035] Preferably, the improved quantum gray wolf algorithm is used to optimize the prediction model parameters to obtain the optimal parameters, including:

[0036] (1) Initialize the algorithm parameters and population location, where the population size is N and the maximum number of iterations is N. maxgen The number of qubits is M, the number of decision variables is P, and the range of decision variables is [V]. min V max The maximum number of times the global optimum has not been updated is N. maxup ;

[0037] (2) Let the number of iterations N gen =0, the global optimal number of times N has not been updated up =0, and encode the probability amplitude of each individual in the population using qubits, with all probability amplitudes (α) being 0. ij ,β ij The initial values ​​are all The initial population position Q is formed, where (α) ij ,β ij ) represents the probability amplitude of the j-th qubit of the i-th individual;

[0038] (3) Encode all individuals in Q using binary and convert the binary representation to decimal to determine the population X = [X1, X2, ..., X...]. i , ..., X N Then, the fitness value of each individual in the population is calculated, where the binary encoding method is shown in the following formula:

[0039]

[0040] Among them, b ij It is a binary code, and r is a random variable, r∈(0,1);

[0041] (4) Sort the individuals by fitness value from smallest to largest, and select and save the three individuals with the lowest fitness: X α X β X δ The corresponding fitness values ​​are f α f β f δ , where X α The gray wolf that is globally optimal has the smallest fitness value;

[0042] (5) Introduce a preference ratio weighting strategy, according to X α X β X δ Update all individual gray wolves in the population;

[0043] (6) Determine the global optimal number of times N has not been updated. up Is it greater than N? maxupIf yes, perform a quantum catastrophe operation and then proceed to step (2); otherwise, skip the quantum catastrophe operation and proceed to the next step.

[0044] Determine if the number of iterations has reached N. maxgen If yes, terminate the operation and output the result; otherwise, return to step (4).

[0045] Preferably, a multi-party real-time data interaction and collaboration system for a digital procurement platform includes:

[0046] The platform establishment module is used to combine blockchain technology and big data technology to establish a digital and intelligent procurement platform for multi-party data interaction;

[0047] The real-time interaction module is used to build a real-time data interaction channel in the digital procurement platform based on message queue technology, and at the same time, it uses smart contract technology to automate the data interaction process.

[0048] The analysis and prediction module is used to introduce machine learning algorithms to perform data analysis and prediction during the data interaction process, and to provide intelligent selection solutions.

[0049] As can be seen from the above technical solutions, compared with the prior art, the present invention discloses a method and system for real-time interaction and collaboration of multi-party data in a digital procurement platform. The present invention has the following beneficial effects: (1) Improve data security and credibility: Through the distributed ledger and encrypted storage of blockchain technology, the data is guaranteed to be decentralized, tamper-proof and traceable, and the trust of all participants in the data is enhanced.

[0050] (2) Message queue technology enables asynchronous data transmission, and smart contracts automatically control the data interaction process, reducing data congestion and human intervention, and improving interaction efficiency.

[0051] (3) Machine learning algorithms combined with improved quantum gray wolf algorithms can perform in-depth analysis and accurate prediction of procurement data, providing intelligent decision-making solutions for all users, which helps to reduce procurement costs and ensure supply chain stability.

[0052] (4) The layered architecture design makes the functions of the digital procurement platform clear, the front-end interaction layer facilitates user operation, the middle business logic layer ensures data security and business process standardization, and the back-end data storage layer ensures reliable data storage and efficient retrieval. Attached Figure Description

[0053] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0054] Figure 1 This invention provides a schematic diagram of a method for real-time multi-party data interaction and collaboration in a digital procurement platform.

[0055] Figure 2 This invention provides a schematic diagram of a multi-party real-time data interaction and collaboration system structure for an intelligent procurement platform. Detailed Implementation

[0056] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0057] This invention discloses a method for real-time multi-party data interaction and collaboration in a digital procurement platform, such as... Figure 1 As shown, it includes:

[0058] By combining blockchain and big data technologies, a digital procurement platform will be established for multi-party data interaction. Utilizing the distributed ledger characteristics of blockchain, the decentralized and immutable nature of data storage will be ensured, guaranteeing the security and trustworthiness of data from all participants. Through big data technology, hundreds of millions of procurement-related data points will be collected, organized, and stored, covering supplier information, product price fluctuations, market supply and demand trends, etc., constructing a comprehensive procurement data resource pool to facilitate subsequent data interaction and analysis.

[0059] Based on message queue technology, a real-time data interaction channel is established in the intelligent procurement platform. Simultaneously, smart contract technology is used to automate the data interaction process. Message queues can orderly arrange data requests and responses of different formats and sources, enabling asynchronous data transmission, greatly improving data interaction efficiency and avoiding delays caused by data congestion. Smart contracts pre-define data interaction rules in code, such as data transmission time nodes, data format requirements, and authorized access mechanisms. Once the contract conditions are triggered, the corresponding data interaction operations will be executed automatically without manual intervention, effectively reducing human error and communication costs.

[0060] During data interaction, machine learning algorithms are introduced for data analysis and prediction, providing intelligent selection solutions. These algorithms are used to deeply mine historical procurement data, analyzing procurement behavior patterns, supplier performance, cost variation patterns, and other information. By analyzing this data, a comprehensive understanding of the procurement operation can be achieved, providing accurate data support for subsequent decision-making.

[0061] By predicting market price trends in advance through forecasting models, we can help buyers seize the best purchasing opportunities and reduce procurement costs. By analyzing suppliers' historical delivery data, we can predict suppliers' future delivery capabilities and risks, enabling buyers to develop contingency plans in advance, such as finding alternative suppliers or adjusting procurement plans, to ensure the smooth progress of procurement operations.

[0062] Specifically, the digital procurement platform includes a front-end interaction layer, a middle business logic layer, and a back-end data storage layer;

[0063] The front-end interaction layer provides personalized operation interfaces for purchasers, suppliers, agencies, and evaluation experts; it supports access from multiple terminal devices, ensuring that users can conveniently input data, query, and obtain feedback; purchasers can publish detailed procurement project requirements on the interface, including the specifications, quantity, quality requirements, and delivery time of the procured items; suppliers can upload tender documents, covering product introductions, quotations, after-sales service commitments, and other information; agencies can conduct project management and coordination; and evaluation experts can enter review opinions and scores.

[0064] The intermediate business logic layer is used for data validation, process control, and access management. It validates the format, logic, and compliance of user-input data to ensure accuracy and integrity. It controls the process according to a pre-defined procurement workflow, guiding all parties to complete each step. Different operational permissions are precisely assigned based on user roles and responsibilities to ensure data security. Specifically, purchasers can create, modify, and publish procurement projects; suppliers can only view and operate projects related to their own bids; and evaluation experts can only review designated projects.

[0065] The backend data storage layer employs a distributed database for centralized data storage and management. Leveraging the high availability, fault tolerance, and scalability of the distributed database, data security and reliability are ensured, supporting rapid data retrieval and updates. Combined with blockchain technology, critical data is encrypted and stored in a chain, ensuring data immutability and traceability. Important data such as procurement contracts, transaction records, and review results are securely stored on the blockchain.

[0066] Specifically, during the data access process, the digital procurement platform performs real-time data preprocessing, uses data denoising algorithms to remove duplicate, erroneous, or incomplete data, and converts data of various formats into a standard format that the platform can recognize and process through data standardization.

[0067] Specifically, based on message queue technology, a real-time data interaction channel is built in the intelligent procurement platform, including:

[0068] When a user updates data, the updated data is encapsulated into a message and sent to the message queue. The message queue then pushes the message to the relevant parties quickly and accurately according to the first-in, first-out principle.

[0069] Specifically, when suppliers submit their bids and evaluation experts enter their review comments, the operational data is immediately encapsulated into messages and sent to a message queue. The message queue, following a first-in, first-out (FIFO) principle, quickly and accurately pushes messages to the purchaser, agency, and other relevant parties, enabling real-time data interaction.

[0070] Utilizing smart contract technology to automate data interaction processes, including:

[0071] Once a purchaser publishes a procurement project, the smart contract automatically filters potential suppliers according to preset rules and sends them procurement invitations. This automates and intelligently processes data interaction, significantly improving efficiency.

[0072] The preset rules include supplier qualification levels, credit scores, business scope, past performance, and other conditions. The smart contract filters out qualified suppliers from the database and automatically sends them invitations containing detailed information about the procurement project. In other stages of the procurement process, such as receiving bid documents and publicizing review results, the smart contract can also automatically execute corresponding operations according to the preset rules, realizing the automation and intelligence of data interaction and improving interaction efficiency.

[0073] Specifically, by combining blockchain and big data technologies, a digital and intelligent procurement platform will be established for multi-party data interaction, including:

[0074] Build a private blockchain network and connect it to the public blockchain network, BUMMING; by leveraging the extensive connectivity of the public blockchain and the security of the private blockchain, a reliable network foundation is provided for data interaction.

[0075] Define enterprise database data specifications based on the data in the enterprise database; ensure consistency of data in terms of format and content to facilitate subsequent data processing and analysis.

[0076] Analyze the requirements of the business system and build blockchain nodes accordingly; these nodes are used for data interaction and storage.

[0077] Write relevant smart contracts and deploy them to the blockchain network; the smart contracts will play a role in the automated control of subsequent data interaction processes, such as screening potential suppliers according to preset rules and automatically processing the receipt of tender documents.

[0078] Build a blockchain data center to encrypt and store data and record it on a chain; ensure the security, immutability and traceability of the data.

[0079] A digital procurement platform based on a blockchain data center has been established for multi-party data interaction. This platform integrates a front-end interaction layer, a middleware business logic layer, and a back-end data storage layer, enabling real-time interaction and collaboration of data from multiple parties.

[0080] The digital procurement platform established through the above steps provides a comprehensive and efficient solution for multi-party data interaction and collaboration.

[0081] Specifically, machine learning algorithms are introduced for data analysis and prediction to provide intelligent selection solutions, including:

[0082] Historical procurement data is extracted from the backend data storage layer, such as supplier price fluctuations, which reflect dynamic changes in market prices and supplier pricing strategies; on-time delivery rate, which reflects the supplier's fulfillment capabilities and supply chain stability; product quality rating, which is directly related to whether the procured products can meet business needs; and dynamic changes in market supply and demand, etc. This data can help grasp the overall market trend; this data serves as the basis for subsequent algorithm processing and provides multi-dimensional information for model training.

[0083] Identify influencing and predictive factors, and establish a predictive model based on machine learning algorithms; conduct in-depth analysis of extracted historical procurement data, and combine the actual needs and objectives of procurement operations to identify key factors influencing procurement decisions as influencing factors.

[0084] Specifically, for procurement costs, supplier price fluctuations and market supply and demand are likely to be important influencing factors; for supplier selection, on-time delivery rate and product quality rating are key factors. At the same time, it is important to identify the indicators that need to be predicted as forecasting factors, such as future procurement prices and supplier delivery capabilities.

[0085] Specifically, the machine learning algorithms include neural network models, support vector machine models, long short-term memory network models, etc.

[0086] The parameters of the prediction model were optimized using an improved quantum gray wolf algorithm to obtain the optimal parameters.

[0087] The optimal parameter combination obtained from the improved quantum gray wolf algorithm is applied to machine learning algorithms;

[0088] The optimized forecasting model is used to analyze and predict procurement data;

[0089] The analysis and forecast results are integrated into the front-end interaction layer of the intelligent procurement platform to provide decision-making solutions for all users.

[0090] Specifically, the improved quantum gray wolf algorithm is a highly efficient optimization algorithm that combines the characteristics of quantum computing with the search capabilities of the gray wolf algorithm, enabling it to quickly find optimal solutions in complex parameter spaces. In this step, the parameters of the prediction model are used as variables to be optimized, and the improved quantum gray wolf algorithm is used to optimize them. The improved quantum gray wolf algorithm is used to optimize the parameters of the prediction model to obtain the optimal parameters, including:

[0091] (1) Initialize the algorithm parameters and population location, where the population size is N and the maximum number of iterations is N. maxgen The number of qubits is M, the number of decision variables is P, and the range of decision variables is [V]. min V max The maximum number of times the global optimum has not been updated is N. maxup ;

[0092] (2) Let the number of iterations N gen =0, the global optimal number of times N has not been updated up =0, and encode the probability amplitude of each individual in the population using qubits, with all probability amplitudes (α) being 0. ij ,β ij The initial values ​​are all The initial population position Q is formed, where (α) ij ,β ij ) represents the probability amplitude of the j-th qubit of the i-th individual;

[0093] (3) Encode all individuals in Q using binary and convert the binary representation to decimal to determine the population X = [X1, X2, ..., X...]. i , ..., X N Then, the fitness value of each individual in the population is calculated, where the binary encoding method is shown in the following formula:

[0094]

[0095] Among them, b ij It is a binary code, and r is a random variable, r∈(0,1);

[0096] (4) Sort the individuals by fitness value from smallest to largest, and select and save the three individuals with the lowest fitness: X α X β X δThe corresponding fitness values ​​are f α f β f δ , where X α The gray wolf that is globally optimal has the smallest fitness value;

[0097] (5) Introduce a preference ratio weighting strategy, according to X α X β X δ Update all individual gray wolves in the population;

[0098] (6) Determine the global optimal number of times N has not been updated. up Is it greater than N? maxup If yes, perform a quantum catastrophe operation and then proceed to step (2); otherwise, skip the quantum catastrophe operation and proceed to the next step.

[0099] Determine if the number of iterations has reached N. maxgen If yes, terminate the operation and output the result; otherwise, return to step (4).

[0100] Specifically, the update equation for individual gray wolves based on the preference ratio weighting strategy is as follows:

[0101] D α =|C·X α (k)-X i (k)|;

[0102] D β =|C·X β (k)-X i (k)|;

[0103] D δ =|C·X δ (k)-X i (k)|;

[0104] X1 = X α (k)-A·D α ;

[0105] X2 = X β (k)-A·D β ;

[0106] X3 = X δ (k)-A·D δ ;

[0107] ω1=1-f α / (f α +f β +f δ );

[0108] ω2=1-fβ / (f α +f β +f δ );

[0109] ω3=1-f δ / (f α +f β +f δ );

[0110]

[0111] Where k is the iteration number, A = 2a × r1 - a, C = 2 × r2, a = 2 - 2k / N maxgen Parameters A, C, and a are convergence factors; r1 and r2 are random variables, r1 and r2 ∈ (0, 1), D α D β D δ They represent individual X respectively α X β X δ With individual X i The distance between them.

[0112] Specifically, the quantum catastrophe operation involves preserving the global optimal solution and re-encoding the probability amplitudes of the remaining individuals' qubits. The update equations for all probability amplitudes (α, β) are as follows:

[0113] Update to α:

[0114] Update to β:

[0115] Where poi, r3, and r4 are random variables, where poi ∈ (-1, 1) and r3 and r4 ∈ (0, 1).

[0116] In one specific embodiment of the present invention, a multi-party real-time data interaction and collaboration system for an intelligent procurement platform, such as... Figure 2 As shown, it includes:

[0117] The platform establishment module is used to combine blockchain technology and big data technology to establish a digital and intelligent procurement platform for multi-party data interaction;

[0118] The real-time interaction module is used to build a real-time data interaction channel in the digital procurement platform based on message queue technology, and at the same time, it uses smart contract technology to automate the data interaction process.

[0119] The analysis and prediction module is used to introduce machine learning algorithms to perform data analysis and prediction during the data interaction process, and to provide intelligent selection solutions.

[0120] In one specific embodiment of the present invention, a method for real-time multi-party data interaction and collaboration in a digital procurement platform includes:

[0121] Building a digital procurement platform

[0122] Build a private blockchain network and connect it to the public blockchain network, BUMM, leveraging the extensive connectivity of the public blockchain and the security of the private blockchain to provide a reliable network foundation for data interaction;

[0123] Based on the data in the enterprise database, define the enterprise database data specifications to ensure consistency in data format, content, etc., which will facilitate subsequent data processing and analysis.

[0124] Analyze the requirements of the business system and build blockchain nodes based on those requirements for data interaction and storage;

[0125] By writing relevant smart contracts and deploying them on the blockchain network, the smart contracts will play a role in the automated control of subsequent data interaction processes, such as screening potential suppliers according to preset rules and automatically processing the receipt of tender documents.

[0126] Build a blockchain data center to encrypt and store data and record it on a chain, ensuring data security, immutability and traceability;

[0127] A digital procurement platform is established based on a blockchain data center, integrating a front-end interaction layer, a middle business logic layer, and a back-end data storage layer.

[0128] Real-time data interaction and collaboration

[0129] When a user performs a data update operation, such as a supplier submitting a tender document or an evaluation expert entering review comments, the updated data is packaged into a message and sent to the message queue. The message queue pushes the message quickly and accurately to the purchaser, agency and other relevant parties according to the first-in-first-out principle, so as to realize real-time data interaction.

[0130] After the procuring entity publishes a procurement project, the smart contract automatically filters potential suppliers based on preset rules (such as supplier qualification level, credit score, business scope, past performance, etc.) and sends procurement invitations to them. In other stages of the procurement process, such as receiving tender documents and publicizing review results, the smart contract also automatically executes corresponding operations according to preset rules, realizing the automation and intelligence of data interaction and improving interaction efficiency.

[0131] Data analysis and forecasting and decision support

[0132] Historical procurement data is extracted from the backend data storage layer and preprocessed, including noise reduction and standardization.

[0133] Identify influencing and predictive factors. For example, for procurement costs, supplier price fluctuations and market supply and demand are influencing factors, while future procurement prices are predictive factors. For supplier selection, on-time delivery rate and product quality rating are influencing factors, while supplier delivery capability is a predictive factor.

[0134] Choose appropriate machine learning algorithms (such as neural network models, support vector machine models, long short-term memory network models, etc.) to build a predictive model;

[0135] The improved quantum gray wolf algorithm is used to optimize the prediction model parameters. Algorithm parameters are set, such as population size N=50 and maximum number of iterations N. maxgen =200, number of qubits M=30, number of decision variables P determined according to model parameters, range of decision variables [V] min V max [Set according to actual conditions, the maximum number of times the global optimal update has not been performed N] maxup =20. Perform iterative optimization to obtain the optimal parameters and apply them to the machine learning algorithm;

[0136] The optimized prediction model is used to analyze and predict procurement data. The analysis and prediction results are integrated into the front-end interactive layer of the digital procurement platform to provide decision-making solutions to all users in the form of charts, reports and other forms. For example, it can recommend the best procurement time and suppliers to the purchaser, and provide market demand forecasts and competitive analysis to the suppliers.

[0137] The embodiments of the present invention can effectively realize real-time interaction and collaboration of multi-party data in a digital procurement platform, thereby improving the overall efficiency and effectiveness of procurement operations.

[0138] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to the method section.

[0139] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily 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 invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for real-time multi-party data interaction and collaboration in a digital procurement platform, characterized in that, include: By combining blockchain and big data technologies, a digital and intelligent procurement platform will be established for multi-party data interaction. Based on message queue technology, a real-time data interaction channel is built in the digital procurement platform. At the same time, smart contract technology is used to automate the data interaction process. During the data interaction process, machine learning algorithms are introduced for data analysis and prediction, providing intelligent selection options; Based on message queue technology, a real-time data interaction channel is built in the intelligent procurement platform, including: When a user updates data, the updated data is encapsulated into a message and sent to the message queue. The message queue pushes the message to the relevant parties quickly and accurately according to the first-in-first-out principle. Utilizing smart contract technology to automate data interaction processes, including: Once the purchaser publishes a procurement project, the smart contract automatically filters potential suppliers according to preset rules and sends procurement invitations to them. By combining blockchain and big data technologies, a digital and intelligent procurement platform will be established for multi-party data interaction, including: Build a private blockchain network and connect it to the public blockchain network, Boom Blockchain Network; Define enterprise database data specifications based on the data content of the enterprise database; Analyze the requirements of the business system and build blockchain nodes accordingly; Write the relevant smart contracts and deploy them to the blockchain network; Build a blockchain data center to encrypt and record data in a chain; A digital procurement platform for multi-party data interaction is established based on a blockchain data center.

2. The method for real-time multi-party data interaction and collaboration in a digital procurement platform according to claim 1, characterized in that, The digital procurement platform includes a front-end interaction layer, a middle business logic layer, and a back-end data storage layer. The front-end interaction layer provides personalized operation interfaces for purchasers, suppliers, agencies, and bid evaluation experts. The intermediate business logic layer is used for data verification, process control, and access control. The backend data storage layer uses a distributed database for centralized data storage and management.

3. The method for real-time multi-party data interaction and collaboration in a digital procurement platform according to claim 1, characterized in that, During the data access process, the digital procurement platform performs real-time data preprocessing and converts data of various formats into a standard format through data standardization.

4. The method for real-time multi-party data interaction and collaboration in a digital procurement platform according to claim 2, characterized in that, Introducing machine learning algorithms for data analysis and prediction provides intelligent selection options, including: Extract historical procurement data from the backend data storage layer; determine influencing factors and predictive factors, and establish a predictive model based on machine learning algorithms; The parameters of the prediction model were optimized using an improved quantum gray wolf algorithm to obtain the optimal parameters. The optimal parameter combination obtained from the improved quantum gray wolf algorithm is applied to machine learning algorithms; The optimized forecasting model is used to analyze and predict procurement data; The analysis and forecast results are integrated into the front-end interaction layer of the intelligent procurement platform to provide decision-making solutions for all users.

5. The method for real-time multi-party data interaction and collaboration in a digital procurement platform according to claim 4, characterized in that, The improved quantum gray wolf algorithm was used to optimize the parameters of the prediction model to obtain the optimal parameters, including: (1) Initialize the algorithm parameters and population position, where the population size is N and the maximum number of iterations is N. maxgen The number of qubits is M, the number of decision variables is P, and the range of decision variables is [V]. min V max The maximum number of times the global optimum has not been updated is N. maxup ; (2) Let the number of iterations N gen =0, the global optimal number of times N has not been updated up =0, and encode the probability amplitude of each individual in the population using qubits, with all probability amplitudes (α) being 0. ij ,β ij The initial values ​​are all , forming the initial population position Q, where, (α ij ,β ij ) represents the probability amplitude of the j-th qubit of the i-th individual; (3) Encode all individuals in Q in binary form and convert the binary representation to decimal to determine the population X = [X1, X2, ..., X]. i , ..., X N Then, the fitness value of each individual in the population is calculated, where the binary encoding method is shown in the following formula: ； Among them, b ij It is a binary code, and r is a random variable, r∈(0,1); (4) Sort the individuals according to their fitness values ​​from smallest to largest, and select and save the three individuals with the lowest fitness values: X α X β X δ The corresponding fitness values ​​are f α f β f δ , where X α The gray wolf that is globally optimal has the smallest fitness value; (5) Introduce a preference ratio weighting strategy, according to X α X β X δ Update all individual gray wolves in the population; (6) Determine the global optimal number of times N has not been updated. up Is it greater than N? maxup If yes, perform a quantum catastrophe operation and then proceed to step (2); otherwise, skip the quantum catastrophe operation and proceed to the next step. Determine if the number of iterations has reached N. maxgen If yes, terminate the operation and output the result; otherwise, return to step (4).

6. A multi-party real-time data interaction and collaboration system for a digital procurement platform, employing the multi-party real-time data interaction and collaboration method for a digital procurement platform as described in any one of claims 1-5, characterized in that, include: The platform establishment module is used to combine blockchain technology and big data technology to establish a digital and intelligent procurement platform for multi-party data interaction; The real-time interaction module is used to build a real-time data interaction channel in the digital procurement platform based on message queue technology, and at the same time, it uses smart contract technology to automate the data interaction process. The analysis and prediction module is used to introduce machine learning algorithms to perform data analysis and prediction during the data interaction process, and to provide intelligent selection solutions.

Images