Supply demand intelligent matching and information issuing method

Abstract

The invention discloses a supply demand intelligent matching and information issuing method, and particularly relates to the technical field of information. The core structure of the method comprises the following steps: receiving information from a plurality of suppliers and demanders through an electronic interface; performing data cleaning, format standardization and classification arrangement on the information to generate a structured data set; inputting the data set into an intelligent matching process, comprehensively calculating a matching degree based on attribute similarity, time correlation and geographical proximity factors through a multi-dimensional matching algorithm, and generating a matching score by adopting a weighted scoring model; screening candidate matching results according to the matching scores and a preset threshold value; and the result is actively pushed to the user through an information issuing channel. According to the method, efficient and accurate matching of supply and demand is realized, the timeliness of a matching result is kept through a dynamic adjustment mechanism, the matching quality is continuously optimized by means of semantic analysis and a feedback mechanism, meanwhile, the data security is ensured through hierarchical privacy protection, and the accuracy, adaptability and practicability of a matching system are improved.

Description

Technical Field

[0001] This invention relates to the field of information technology, and more specifically, to a method for intelligent matching of supply and demand and information dissemination. Background Technology

[0002] In recent years, with the rapid development of e-commerce and the digital economy, research and application in this field have become increasingly widespread both domestically and internationally. From early simple systems based on keyword matching to today's intelligent platforms combining big data analytics and artificial intelligence, this field has evolved from single-function systems to comprehensive services, and from static matching to dynamic optimization. Current trends indicate that supply and demand matching systems are developing towards greater intelligence, personalization, and real-time capabilities, with increasing research focusing on how to improve matching efficiency through algorithm optimization and data mining. Simultaneously, the widespread adoption of IoT and 5G technologies has enhanced real-time data acquisition and processing capabilities, providing a technological foundation for more accurate supply and demand matching.

[0003] Existing supply and demand matching technologies have several significant shortcomings. First, most systems employ single-dimensional matching algorithms, relying primarily on keyword or category matching, lacking comprehensive consideration of multiple dimensions such as time and geographical location, leading to discrepancies between matching results and actual demand. Second, existing technologies have weak control over data quality, lacking effective data verification mechanisms, allowing errors or false information to affect matching accuracy. Third, traditional systems mostly employ static matching models, unable to adjust matching strategies in real time according to changes in supply and demand, reducing the system's adaptability and timeliness. Furthermore, information dissemination methods are relatively limited, lacking personalized push mechanisms, making it difficult to meet the specific needs of different users. In terms of data processing, existing technologies often neglect the depth of semantic understanding, having limited capabilities in processing unstructured information. Simultaneously, most systems lack effective feedback optimization mechanisms, failing to continuously improve matching quality through user feedback. Privacy protection measures are also inadequate, posing a risk of data leakage. Finally, existing technologies often face efficiency bottlenecks when processing large-scale supply and demand data, struggling to achieve rapid response while maintaining matching quality.

[0004] Therefore, this paper proposes an intelligent supply and demand matching and information dissemination method to address the above-mentioned problems. The aim is to solve the following technical issues: improve the accuracy and comprehensiveness of supply and demand matching, improve data quality control, enhance the system's real-time response capability, optimize the targeting of information dissemination, strengthen user privacy protection, improve the efficiency of large-scale data processing, and achieve continuous optimization of the matching process. Summary of the Invention

[0005] In order to overcome the above-mentioned defects of the prior art, embodiments of the present invention provide a supply and demand intelligent matching and information dissemination method to solve the problems mentioned in the background art.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a method for intelligent matching of supply and demand and information dissemination, comprising the following steps: S1. Receive supply information submitted by multiple suppliers and demand information submitted by multiple demanders through an electronic interface, wherein the supply information contains attribute descriptions of the supplied goods or services and the demand information contains attribute descriptions of the demanded goods or services. S2. Process the received supply and demand information, including data cleaning, format standardization, and classification, to generate structured supply and demand datasets. S3. Input the structured supply and demand datasets into the intelligent matching process. This process calculates the matching degree between the supply and demand data by executing a multi-dimensional matching algorithm. The matching degree is comprehensively evaluated based on attribute similarity, time relevance and geographical proximity factors, and a weighted scoring model is used to generate a matching score. S4. Based on the matching score and the preset matching threshold, select supply and demand pairs with matching scores higher than the threshold from the supply dataset and the demand dataset as candidate matching results. S5. Proactively push candidate matching results to the corresponding suppliers and demanders through information dissemination channels.

[0007] Preferably, the multi-dimensional matching algorithm includes a machine learning-based method that uses historical supply and demand data to train a predictive model to identify potential correlation patterns between supply and demand, and applies the model in real time during the matching process to calculate a matching score. The machine learning model may be one or more combinations of collaborative filtering, decision trees, or neural networks, and the training data is updated regularly to reflect the latest trends.

[0008] Preferably, the method also includes a verification step for supply and demand information. This step assesses the reliability of the information by cross-validating the completeness and consistency of the information submitted by the user, and triggers a resubmission or exclusion mechanism when the information does not meet the verification conditions. The verification conditions include the completeness of required fields, logical rationality, and consistency checks with data from other sources.

[0009] Preferably, the intelligent matching process is dynamically adjustable, capable of updating the matching calculation in real time based on newly input supply or demand information, automatically re-evaluating the matching score when information changes, and promptly notifying relevant users of the updated matching results through information dissemination channels to ensure the timeliness and adaptability of the matching.

[0010] Preferably, it also includes an integrated user feedback mechanism that allows suppliers and demanders to provide evaluations or corrections to the matching results and stores the feedback data for subsequent analysis. The feedback data includes matching satisfaction, error reports, or suggestions for adjustment. This data is incorporated into the parameter optimization process of the intelligent matching process to dynamically adjust the weights or rules of the matching algorithm.

[0011] Preferably, the information dissemination channel supports multimodal output, including mobile device push notifications, email reminders, SMS services, and in-web page messages. Users can customize the receiving method and frequency according to their personal preferences, and the published content can be presented differently according to user roles or permissions to enhance the flexibility and targeting of information access.

[0012] Preferably, when processing supply and demand information, privacy protection measures are implemented, including anonymizing or encrypting personal information and sensitive data, using de-identified data only to the extent necessary for matching calculations, and limiting the disclosure of details during information release to comply with data protection regulations and user privacy requirements.

[0013] Preferably, the method also includes post-processing optimization of the matching results, which involves applying conflict resolution rules to handle competition or overlap between multiple suppliers or demanders and allocating matching resources according to priority. The conflict resolution rules are determined based on one or more of the following: first-come, first-served, user level, or custom preferences.

[0014] Preferably, the data processing step further includes semantic analysis of supply and demand information to extract key features and eliminate ambiguity. The semantic analysis uses natural language processing technology to parse text descriptions and convert unstructured information into a structured format to facilitate subsequent matching calculations and classification management.

[0015] Preferably, the intelligent matching process includes a multi-stage screening mechanism. First, coarse screening quickly eliminates obviously irrelevant supply and demand. Then, fine screening applies a detailed matching algorithm to calculate the matching score. Coarse screening is based on key attribute matching, while fine screening combines multiple dimensions for comprehensive evaluation to improve matching efficiency and accuracy.

[0016] The technical effects and advantages of this invention are as follows: Compared to existing technologies, this invention constructs a multi-dimensional matching algorithm that incorporates factors such as attribute similarity, temporal relevance, and geographical proximity into a unified calculation framework, employing a weighted scoring model to comprehensively evaluate the degree of matching between supply and demand. This method quantifies features of different dimensions into calculable indicators by defining a matching score calculation formula, and dynamically optimizes weight coefficients based on historical data. This approach more comprehensively reflects the complex characteristics of supply and demand relationships, avoiding the limitations of single-dimensional matching. The result is improved accuracy and practicality of matching results, enabling suppliers and demanders to find potential partners who meet multiple requirements more quickly. The advantage of this method lies in reducing the bias of subjective judgment through quantitative multi-factor comprehensive analysis, while maintaining the transparency and interpretability of the calculation process.

[0017] Compared to existing technologies, this invention introduces a dynamically adjustable matching mechanism, establishing a matching score recalculation process based on real-time data updates. This method employs an update formula including a decay factor, enabling the system to automatically adjust existing matching results based on newly input supply or demand information. When market conditions or user demands change, the system maintains the timeliness of matching results by re-evaluating the matching scores. This implementation ensures the matching system's adaptability to dynamic environments, avoiding the problem of traditional static matching methods becoming outdated. The result is that matching results can reflect market changes promptly, improving the system's responsiveness and usability. By establishing a continuously optimizing feedback loop, the stability of matching quality is maintained over a longer period.

[0018] Compared to existing technologies, this invention integrates a user feedback mechanism to construct a parameter optimization process based on evaluation data. This method collects user satisfaction ratings and correction suggestions for matching results, and quantifies user feedback into actionable optimization parameters by defining a formula for calculating feedback influence factors. These parameters are systematically incorporated into the weight adjustment and rule optimization processes of the matching algorithm, forming a closed-loop improvement mechanism. This allows the system to continuously learn from practical experience and gradually improve its matching strategy. The result is that the system possesses self-improvement capabilities, continuously enhancing matching accuracy with increased usage time. By transforming user experience into system intelligence, a gradual improvement in algorithm performance is achieved.

[0019] Compared to existing technologies, this invention performs deep semantic analysis on supply and demand information and employs natural language processing techniques to parse key features in text descriptions. This method transforms unstructured information into structured feature vectors by calculating semantic similarity, effectively eliminating ambiguity in textual expressions. This approach enhances the ability to parse complex descriptions, enabling the system to more accurately understand the user's true intent, improving its adaptability to diverse expression methods, and reducing matching omissions caused by differences in expression. By deepening the semantic understanding layer, it improves the system's ability to process complex information, laying a better foundation for accurate matching.

[0020] Compared to existing technologies, this invention establishes a protection level calculation model based on data sensitivity and anonymization by implementing tiered privacy protection measures. This method employs differentiated processing strategies for personal information and sensitive data, limiting data exposure through anonymization and encryption while ensuring the effectiveness of matching calculations. This approach achieves a balance between functionality and privacy protection, satisfying the data requirements of matching calculations while safeguarding user information security, constructing a trustworthy data processing environment, and enhancing user confidence in the system. The advantage of this method lies in ensuring the compliance and security of the data processing process through a systematic privacy protection framework. Attached Figure Description

[0021] Figure 1 This is a system framework diagram of the present invention.

[0022] Figure 2 This is a flowchart of the process of the present invention.

[0023] Figure 3 This is a flowchart of the core intelligent matching process of the present invention. Detailed Implementation

[0024] 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.

[0025] Example 1: As attached Figure 1 Figure 3 The method for intelligent matching of supply and demand and information dissemination shown has a core architecture that includes an information receiving and processing module, an intelligent matching calculation module, and a result dissemination and feedback module.

[0026] The information receiving and processing module receives information from multiple suppliers and demanders via electronic interfaces, and performs data cleaning, format standardization, and classification to generate structured supply and demand datasets. The intelligent matching calculation module inputs the structured datasets into a multi-dimensional matching algorithm, calculates the matching degree based on attribute similarity, temporal relevance, and geographical proximity, generates a matching score, and then filters candidate matching results according to preset thresholds. The result publishing and feedback module proactively pushes candidate matching results to users through information publishing channels and supports user interaction and feedback collection. Through the collaboration of these modules, efficient, accurate, and dynamic matching of supply and demand is achieved, effectively solving the problems of single matching dimensions, weak data quality control, poor system real-time performance, and lack of personalized publishing methods in existing technologies.

[0027] Furthermore, the multi-dimensional matching algorithm includes machine learning-based methods. In its implementation, the system employs an updatable predictive model trained on historical supply and demand data, capable of identifying potential patterns of correlation between supply and demand. The machine learning model can utilize a combination of collaborative filtering, decision trees, and neural networks, deployed on a distributed computing framework. Training data is periodically updated to reflect the latest market trends. During the matching process, real-time data flows through the model for inference, outputting a matching score. The matching score calculation integrates three dimensions: attribute similarity, temporal matching degree, and geographical matching degree, and is consolidated through a weighted scoring model. The weighted scoring model ensures a reasonable balance among the various dimensions, and its mathematical expression is: in, , and These represent attribute similarity score, time matching score, and geographical matching score, respectively. , and Let be the weight coefficient, and satisfy... The weighting coefficients are determined through optimization using historical data to ensure the model's adaptability in different scenarios. Through this design, the system can more comprehensively assess supply and demand relationships, improving the accuracy and practicality of the matching results.

[0028] Furthermore, the system performs verification steps on supply and demand information. This step is implemented through a three-layer verification architecture: the first layer checks the completeness of required fields; the second layer verifies the logical rationality of numerical parameters through a rule engine; and the third layer cross-references the data with external trusted data sources via an API interface. The verification results are quantified into a verification score, which triggers automated processing. The verification score is calculated using a weighted model. in, , and These represent the completeness score, logical rationality score, and consistency score, respectively. , and Let be the coefficient, and satisfy . Information with a verification score below a preset threshold will be isolated and a resubmission mechanism will be triggered. Through this design, the system improves data quality from the source and reduces the interference of erroneous information on the matching process.

[0029] Furthermore, the intelligent matching process is dynamically adjustable. In its implementation, the system employs an event-driven real-time computing engine. When new supply or demand information is detected, the matching score recalculation process is automatically triggered. The matching score update uses a gradual adjustment strategy: in, This is the attenuation factor, with a value ranging from 0 to 1; The change in matching score is calculated based on new information. The decay factor is dynamically adjusted according to the magnitude of data change. Updated matching results are promptly communicated to relevant users through information dissemination channels. Through this design, the system maintains the timeliness and adaptability of matching results.

[0030] Furthermore, the system integrates a user feedback mechanism. This mechanism is implemented through a structured feedback collection platform, allowing both suppliers and demanders to provide evaluations or suggestions for improvement regarding the matching results. Feedback data is persistently stored and used for parameter optimization. Feedback impact factors are calculated using a quantitative model. in, It is a numerical rating provided by the user. The system is based on user reputation. Feedback factors are incorporated into the weight adjustment process of the matching algorithm, forming a closed-loop optimization mechanism. Through this design, the system can continuously learn from practical experience and dynamically optimize its matching strategy.

[0031] Furthermore, the information dissemination channels support multimodal output. In practice, the system maintains user preference configuration files, recording each user's settings for push methods and receiving frequency. Published content is presented differently based on user roles or permissions. Publishing priority is calculated using a quantitative model. in, and Let be the weight coefficient, and satisfy... The urgency level of a user is determined based on both the time sensitivity of their demand and the availability of the supply. Through this design, the system enhances the flexibility and relevance of information access.

[0032] Furthermore, the system implements privacy protection measures when processing supply and demand information. Specifically, a tiered data anonymization and encryption framework is used to anonymize or encrypt personal and sensitive data. The privacy protection level is evaluated using a computational model. in, Indicates the level of data sensitivity. Indicates the degree of anonymization. and The weights are determined by the data type. Anonymized data is used only within the scope necessary for matching calculations. Through this design, the system ensures the compliance and security of the data processing procedure.

[0033] Furthermore, the system performs post-processing optimization on the matching results. This optimization addresses competition or overlap between multiple suppliers or demanders through conflict resolution rules. Resource allocation scores are calculated using a quantification model. in, and This represents the resource weighting coefficient. User priority is calculated based on a comprehensive analysis of historical user behavior data. Through this design, the system optimizes overall matching efficiency and ensures fairness in resource allocation.

[0034] Furthermore, the data processing steps include semantic analysis of supply and demand information. Specifically, the system uses natural language processing techniques to parse text descriptions and convert unstructured information into a structured format. Semantic similarity is calculated using a vector space model. The feature vectors are generated based on a word embedding model. Through this design, the system effectively eliminates ambiguity in textual expressions and improves the ability to understand complex descriptions.

[0035] Furthermore, the intelligent matching process includes a multi-stage screening mechanism. Specifically, the system first uses a coarse screening process to quickly eliminate obviously irrelevant supply and demand. The coarse screening threshold is calculated using an adaptive mechanism. in, The baseline threshold is used, while the AdjustmentFactor dynamically changes based on the amount of data. The fine-tuning phase then incorporates a comprehensive evaluation across multiple dimensions. Through this design, the system significantly improves processing efficiency while ensuring matching accuracy.

[0036] To more clearly illustrate the technical solution, a specific application scenario will be used as an example below. Referring to the attached diagram, this scenario uses the matching of commodity supply and demand as an example to demonstrate the end-to-end workflow of the system.

[0037] In this scenario, the information receiving and processing module is specifically manifested as a set of API services deployed in the cloud; the intelligent matching calculation module is deployed on a high-performance computing cluster; and the result publishing and feedback module pushes information through multiple communication channels.

[0038] Its detailed working process is as follows: 1. Information Collection and Verification: Suppliers submit supply information via the client, including product type, quantity, supply time window, and service scope. Demanders submit corresponding demand information. The system performs three layers of verification on the data; data with a verification score higher than the threshold proceeds to the next stage of the process.

[0039] 2. Data Processing and Semantic Analysis: Validated data is cleaned and standardized. The semantic analysis engine parses the text descriptions and generates feature vectors.

[0040] 3. Intelligent Matching Calculation: The system initiates a multi-stage screening process. The initial screening quickly eliminates irrelevant entries based on key attributes. The final screening stage applies a multi-dimensional matching algorithm to calculate a weighted matching score.

[0041] 4. Conflict resolution and resource allocation: When multiple parties compete, the system applies conflict resolution rules and determines the final matching pair based on resource allocation scores.

[0042] 5. Personalized Information Delivery: The system proactively pushes matching results based on user preferences. Delivery priority is calculated based on matching score and user urgency.

[0043] 6. Feedback Collection and System Optimization: Users evaluate the matching results, and the feedback data is collected and used to optimize the matching algorithm.

[0044] This scenario clearly demonstrates the organic integration of various technical elements, achieving full automation and intelligence from data collection to matching and publishing.

[0045] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention.

[0046] Finally, the following points should be noted: First, in the description of this application, it should be noted that, unless otherwise specified and limited, the terms "installation", "connection", and "linkage" should be interpreted broadly, and can be mechanical or electrical connections, or internal connections between two components, or direct connections. "Up", "down", "left", "right", etc. are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may change. Secondly: The accompanying drawings of the embodiments disclosed in this invention only involve the structures involved in the embodiments disclosed in this invention. Other structures can refer to the general design. In the absence of conflict, the same embodiment and different embodiments of this invention can be combined with each other. In conclusion, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for intelligent matching of supply and demand and information publishing, characterized in that, The method comprises the following steps: S1, receiving supply information submitted by multiple suppliers and demand information submitted by multiple demanders through an electronic interface, wherein the supply information contains attribute descriptions of supply goods or services, and the demand information contains attribute descriptions of demand goods or services; S2, performing data processing on the received supply information and demand information, including data cleaning, format standardization and classification arrangement, to generate structured supply data sets and demand data sets; S3, inputting the structured supply data sets and demand data sets into an intelligent matching process, which calculates the matching degree between the supply data and the demand data by executing a multi-dimensional matching algorithm, the matching degree is evaluated based on attribute similarity, time correlation and geographical proximity factors, and a matching score is generated using a weighted scoring model; S4, according to the matching score and a preset matching threshold, filtering out the supply-demand pairs with a matching score higher than the threshold from the supply data sets and demand data sets as candidate matching results; S5, actively pushing the candidate matching results to the corresponding suppliers and demanders through an information publishing channel.

2. The method of claim 1, wherein the method further comprises: The multi-dimensional matching algorithm includes a machine learning-based method that uses historical supply and demand data to train a prediction model to identify potential association patterns between supply and demand, and applies the model to calculate the matching score in real time during the matching process. The machine learning model can use one or more combinations of collaborative filtering, decision trees or neural networks, and the training data is updated regularly to reflect the latest trends.

3. The method of claim 1, wherein the method further comprises: It also includes a verification step for supply information and demand information, which evaluates the reliability of the information by cross-verifying the completeness and consistency of the user-submitted information, and triggers a re-submission or exclusion mechanism when the information does not meet the verification conditions, which include mandatory field completeness, logical reasonableness and consistency check with other source data. ​ 4. The method of claim 1, wherein the method further comprises: The intelligent matching process is dynamically adjustable, capable of updating the matching calculation in real time according to new input supply information or demand information, and automatically re-evaluating the matching score when the information changes. At the same time, the updated matching results are promptly notified to the relevant users through the information publishing channel, ensuring the timeliness and adaptability of the matching. ​ 5. The method of claim 1, wherein the method further comprises: It also includes an integrated user feedback mechanism that allows suppliers and demanders to provide evaluations or corrections on the matching results, and stores the feedback data for subsequent analysis, including matching satisfaction, error reports or suggestions for adjustment. These data are incorporated into the parameter optimization process of the intelligent matching process to dynamically adjust the weights or rules of the matching algorithm. ​ 6. The method of claim 1, wherein the method further comprises: The information publishing channel supports multi-modal output, including mobile device push notifications, email reminders, SMS services and in-page messages. Users can customize the receiving method and frequency according to their personal preferences, and the published content can be presented differently according to user roles or permissions to enhance the flexibility and relevance of information access.

7. The intelligent supply and demand matching and information dissemination method as described in claim 1, characterized in that, In processing supply information and demand information, privacy protection measures are implemented, including anonymization or encryption of personal information and sensitive data, use of desensitized data only within the necessary range of matching calculation, and limitation of public details in information release process, to comply with data protection regulations and user privacy requirements.

8. The intelligent supply and demand matching and information dissemination method as described in claim 1, characterized in that, It also includes post-processing optimization of matching results, which handles competition or overlap between multiple suppliers or demanders by applying conflict resolution rules based on one or more of first-come-first-served, user level or custom preferences, and assigns matching resources according to priority.

9. The intelligent supply and demand matching and information dissemination method as described in claim 1, characterized in that, The data processing steps also include semantic analysis of supply information and demand information to extract key features and eliminate ambiguity, where semantic analysis uses natural language processing techniques to parse textual descriptions and convert unstructured information into structured formats for subsequent matching calculations and classification management.

10. The method of claim 1, wherein the method further comprises: The intelligent matching process includes a multi-stage screening mechanism, first quickly excluding obviously irrelevant supplies and demands through coarse screening, and then applying detailed matching algorithms to calculate matching scores through fine screening, coarse screening based on key attribute matching, and fine screening combining multi-dimensional factors for comprehensive evaluation to improve matching efficiency and accuracy. ​

Images