Supplier intelligent recommendation method and device, electronic equipment and storage medium

Abstract

This application provides a supplier intelligent recommendation method, apparatus, electronic device, and storage medium, relating to the field of information processing technology. The method includes: responding to a user-triggered target instruction, acquiring the user's target query information, wherein the target instruction is triggered after the user inputs the target query information; determining a set of supplier feature profiles matching the target query information from a feature profile group, wherein the feature profile group includes multiple supplier feature profiles, each supplier's feature profile being generated based on the corresponding supplier's multi-dimensional data; scoring and ranking each supplier in the set of supplier feature profiles to obtain a ranking result, and displaying the ranking result to the user. Implementing the technical solution provided in this application improves the efficiency and accuracy of supplier selection.

Description

Technical Field

[0001] This application relates to the field of information processing technology, specifically to a supplier intelligent recommendation method, apparatus, electronic device, and storage medium. Background Technology

[0002] With the rapid development of the new energy industry and the continuous expansion of supermarket scale, supplier management has become a key link in improving supermarket operational efficiency. Supplier management not only involves the overall optimization of the supply chain, but also directly affects the service quality and profit level of supermarkets. Therefore, how to efficiently and accurately select suppliers has become an urgent problem for supermarkets. However, existing supplier recommendation methods face many challenges, especially in the environment of integrated new energy supermarkets. Traditional supplier recommendation methods have obvious shortcomings, such as information asymmetry: traditional supplier recommendation methods rely on manual operation and paper document management, and information updates are not timely. This information asymmetry seriously affects the accuracy and timeliness of supplier selection; slow response speed: when faced with sudden changes in market demand or procurement orders, traditional recommendation methods are often slow to respond and cannot quickly match suitable suppliers; in addition, traditional recommendation methods are difficult to comprehensively assess the capabilities and reputation of suppliers, resulting in inaccurate recommendation results that cannot effectively meet the needs of supermarkets for efficient and accurate supplier selection. It is evident that related technologies for supermarket supplier recommendation lack intelligent management tools. These problems are particularly prominent in the new energy industry because the characteristics of new energy products and market demands change rapidly, and traditional recommendation methods cannot adapt to the needs of efficient management in this dynamic environment. Summary of the Invention

[0003] To address the aforementioned technical problems, this application provides a supplier intelligent recommendation method, apparatus, electronic device, and storage medium.

[0004] Firstly, this application provides a supplier intelligent recommendation method applied to a commercial supermarket platform, comprising: responding to a user-triggered target instruction, obtaining the user's target query information, wherein the target instruction is triggered by the user after inputting the target query information; determining a set of supplier feature profiles matching the target query information from a feature profile group, wherein the feature profile group includes feature profiles of multiple suppliers, and each supplier's feature profile is generated based on the corresponding supplier's multi-dimensional data; scoring and ranking each supplier in the set of supplier feature profiles to obtain a ranking result, and displaying the ranking result to the user.

[0005] By adopting the above technical solution, the intelligent supplier recommendation method can respond to the target command triggered by the user, obtain the user's target query information, and determine a set of supplier feature profiles that match the target query information from the feature profile group. The feature profiles are generated based on multi-dimensional data of suppliers. Each supplier in the set of suppliers is scored and ranked, and the ranking results are displayed to the user. This realizes intelligent screening and recommendation of suppliers, improves the accuracy and response speed of supplier management, solves the problem of information asymmetry in traditional recommendation methods, and can quickly respond to changes in market demand, improving the efficiency and accuracy of supplier selection for supermarkets.

[0006] Supplier profiles can be derived through integrated analysis of various data sources, including basic supplier information, sales data, contract terms, and logistics performance. For example, a solar photovoltaic panel manufacturer registered and selling its products in a new energy commercial supermarket can have its profile analyzed based on its sales data, customer reviews, and logistics services. This analysis can reveal characteristics such as stable product quality, timely delivery, and excellent after-sales service. The multi-dimensional data for suppliers can include, but is not limited to: basic information such as company name, address, contact information, business license, and certifications; sales data such as sales revenue, sales volume, sales growth rate, and customer feedback; contract terms such as payment terms, delivery deadlines, quality assurance, and liability for breach of contract; logistics data such as delivery speed, logistics costs, delivery range, and customer satisfaction; financial data such as financial health and credit rating; and market performance such as market share, brand awareness, and media coverage.

[0007] Optionally, the suppliers in a set of suppliers are scored and ranked according to their feature profiles to obtain a ranking result. This includes: the set of suppliers includes N suppliers. For the feature profile of the i-th supplier, the following operations are performed to obtain the i-th score value: a set of feature data corresponding to the i-th supplier is determined, where the i-th supplier is any supplier in the set of suppliers, where N is a positive integer greater than or equal to 1, and i is a positive integer greater than or equal to 1 and less than or equal to N; the i-th score value is calculated based on the set of feature data according to a set of preset feature weight coefficients, where the number of weight coefficients in the set of preset feature weight coefficients is equal to the number of feature dimensions in the set of feature data; the N score values ​​are sorted in descending order to obtain a ranking result, where the N score values ​​include the i-th score value.

[0008] By employing the above technical solution, automatic supplier scoring and ranking can be achieved. Specifically, by extracting feature data from a set of suppliers and calculating a score for each supplier using preset feature weight coefficients, a multi-dimensional comprehensive evaluation of suppliers is realized. Finally, the scores of each supplier are sorted in descending order to generate a ranking result. This technical solution helps improve the accuracy and response speed of supplier recommendations, while comprehensively evaluating the capabilities and reputation of suppliers, achieving more efficient supplier screening. The weight coefficients can be adjusted and optimized according to actual conditions, making this recommendation method more flexible to adapt to different market demands and user preferences.

[0009] Optionally, a set of preset feature weight coefficients is obtained through one of the following methods: a set of preset feature weight coefficients is obtained by learning from historical procurement data using a machine learning model; a set of preset feature weight coefficients is predetermined; or a set of preset feature weight coefficients is set by the user, wherein the target query information includes a set of preset feature weight coefficients.

[0010] By adopting the above technical solutions, suppliers can be scored and ranked based on a set of preset feature weight coefficients obtained through different methods, thereby improving the accuracy and flexibility of the scoring and ranking. Specifically, feature weight coefficients obtained by using machine learning models to learn from historical procurement data can automatically optimize weight allocation, making the scoring more in line with actual needs; pre-determined feature weight coefficients ensure a certain degree of stability and consistency; user-defined feature weight coefficients further enhance the level of personalized service, making the scoring and ranking closer to the user's specific needs. By providing multiple methods for obtaining weight coefficients, it is possible to more flexibly adapt to different market demands and user preferences, avoiding the problem of unreasonable weight coefficient settings; using machine learning models to learn weight coefficients from historical data can achieve intelligent and automated weight coefficient settings, reducing the influence of manual intervention and subjective judgment.

[0011] Optionally, the i-th score value is calculated based on a set of feature data according to a set of preset feature weight coefficients, including: obtaining a user profile, wherein the user profile is generated based on the user's historical purchase data; determining a set of preset feature weight coefficients based on the user profile; and performing a weighted summation of each feature data in the set of feature data according to the set of preset feature weight coefficients to obtain the i-th score value.

[0012] By employing the aforementioned technical solution, user profiles are created through analysis of users' historical purchasing behavior, allowing the system to understand the user's preferences and concerns. Based on these user profiles, corresponding feature weight coefficients are determined to ensure the scoring mechanism more closely aligns with actual needs. These personalized weight coefficients are then used to comprehensively consider relevant supplier feature data, resulting in scoring results that better meet user expectations, thus improving the accuracy and personalization of the recommendation process. By determining a set of preset feature weight coefficients based on user profiles, the recommendation results better match user preferences and needs, thereby enhancing the personalization of the recommendations.

[0013] Optionally, a set of supplier feature profiles matching the target query information can be determined from the feature profile group, including: extracting target keywords from the target query information, wherein the target keywords include the purchased goods, expected price and expected delivery time; and determining a set of supplier feature profiles matching the target keywords from the feature profile group, wherein the multi-dimensional data includes at least the product name, product price and average delivery time.

[0014] By adopting the above technical solution, target keywords are extracted from the target procurement information, including the purchased goods, expected price and expected delivery time. A set of supplier feature profiles matching these target keywords are determined from the feature profile group. The multi-dimensional data includes at least the product name, product price and average delivery time, thereby achieving more accurate supplier matching and improving the accuracy and timeliness of the recommendation results.

[0015] Optionally, the feature profile of the target supplier in the feature profile group is generated in the following way, where the target supplier is any one of multiple suppliers: obtaining an initial dataset, which includes the target supplier's basic data, sales data, contract terms data, and logistics data; cleaning and organizing the data in the initial dataset to remove redundant and erroneous data to obtain the target dataset; extracting features from the target dataset to obtain feature combinations; and constructing the feature profile of the target supplier based on the feature combinations.

[0016] By adopting the above technical solutions, it is possible to ensure that the supplier's profile accurately reflects their strength and credibility, thereby improving the accuracy of recommendation results. Specifically, by collecting and cleaning the supplier's basic data, sales data, contract terms data, and logistics data, and removing redundant and erroneous information, a more reliable data foundation is obtained. Furthermore, feature extraction is used to form feature combinations, and based on these, a supplier profile is constructed, enabling an objective and quantitative evaluation of the supplier's capabilities and performance, thus supporting a more accurate and efficient supplier recommendation process.

[0017] Optionally, the above method further includes: in response to a user-triggered purchase order, generating a target purchase order based on query information and target supplier information, wherein the target supplier information is the information of the supplier selected by the user based on the sorting results, a group of suppliers includes the target supplier, and the purchase order is triggered by the user after selecting the target supplier; and recommending the target purchase order to the target supplier.

[0018] By adopting the above technical solutions, rapid response to user-triggered procurement orders can be achieved. Based on user query information and target supplier information selected according to ranking results, target purchase orders are automatically generated and recommended to target suppliers. This enables intelligent supplier recommendation and automated procurement process management within the commercial supermarket platform, significantly improving the procurement efficiency and accuracy of the platform in the new energy environment and meeting the needs of efficient management under dynamic market changes. Through automated and intelligent procurement processes, manual operations and time costs for users are reduced, thereby improving procurement efficiency.

[0019] In a second aspect of this application, a supplier intelligent recommendation device is also provided, located in a commercial supermarket platform, comprising: an acquisition module, configured to acquire the user's target query information in response to a target instruction triggered by the user, wherein the target instruction is triggered by the user after inputting the target query information; a determination module, configured to determine a set of supplier feature profiles matching the target query information from a feature profile group, wherein the feature profile group includes multiple supplier feature profiles, each supplier feature profile being generated based on the corresponding supplier's multi-dimensional data; and a processing module, configured to score and rank each supplier in the set of supplier feature profiles according to the set of supplier feature profiles, obtain a ranking result, and display the ranking result to the user.

[0020] In a third aspect of this application, an electronic device is also provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor executes the program to implement the method steps of any of the above claims.

[0021] In a fourth aspect of this application, a computer-readable storage medium is also provided, which stores instructions that, when executed, perform the method steps of any of the above claims.

[0022] In summary, one or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages: 1. It enables intelligent screening and recommendation of suppliers, improving the accuracy and response speed of supplier management, and enhancing the efficiency and precision of supplier selection for supermarkets; 2. By using machine learning models to learn weight coefficients from historical data, intelligent and automated weight coefficient setting can be achieved, reducing the impact of human intervention and subjective judgment. 3. By determining a set of preset feature weight coefficients based on user profiles, the recommendation results are made more in line with user preferences and needs, thereby improving the personalization of the recommendations; 4. It can realize intelligent supplier recommendation and automated procurement process management in the commercial supermarket platform, thereby significantly improving the procurement efficiency of the commercial supermarket platform in the new energy environment and meeting the needs of efficient management under dynamic market changes. Attached Figure Description

[0023] Figure 1 This is a flowchart of a supplier intelligent recommendation method provided in an embodiment of this application; Figure 2 This is a structural block diagram of a supplier intelligent recommendation device provided in an embodiment of this application; Figure 3 This is a schematic diagram of the structure of an electronic device disclosed in an embodiment of this application.

[0024] Explanation of reference numerals in the attached figures: 300 - Electronic device; 301 - Processor; 302 - Communication bus; 303 - User interface; 304 - Network interface; 305 - Memory. Detailed Implementation

[0025] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments.

[0026] In the description of the embodiments of this application, the words "for example" or "for instance" are used to indicate examples, illustrations, or explanations. Any embodiment or design that is described as "for example" or "for instance" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design options. Rather, the use of the words "for example" or "for instance" is intended to present the relevant concepts in a specific manner.

[0027] In the description of the embodiments of this application, the term "multiple" means two or more. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. The terms "comprising," "including," "having," and variations thereof all mean "including but not limited to," unless otherwise specifically emphasized.

[0028] This application provides a supplier intelligent recommendation method, applied to a commercial supermarket platform, with reference to... Figure 1 , Figure 1 This is a flowchart of a supplier intelligent recommendation method provided in an embodiment of this application, including the following steps: Step S101: In response to the target instruction triggered by the user, obtain the user's target query information, wherein the target instruction is triggered by the user after entering the target query information; Step S102: Determine a set of supplier feature profiles that match the target query information from the feature profile group. The feature profile group includes feature profiles of multiple suppliers, and each supplier's feature profile is generated based on the multi-dimensional data of the corresponding supplier. Step S103: Based on the feature profiles of a group of suppliers, score and rank each supplier in the group to obtain the ranking results, and display the ranking results to the user.

[0029] In the above embodiments, the intelligent supplier recommendation method can respond to user-triggered target commands, obtain the user's target query information, and determine a set of supplier feature profiles matching the target query information from a feature profile group. These feature profiles are generated based on multi-dimensional supplier data. Each supplier in the group is scored and ranked, and the ranking results are displayed to the user. This achieves intelligent supplier screening and recommendation, improving the accuracy and response speed of supplier management, solving the information asymmetry problem in traditional recommendation methods, and enabling rapid response to changes in market demand, thus improving the efficiency and accuracy of supplier selection for supermarkets. By collecting and organizing multi-dimensional supplier data and generating feature profiles, a more comprehensive and accurate understanding of supplier situations can be achieved, reducing information asymmetry and enabling supermarkets to obtain the latest supplier information. This intelligent recommendation method can quickly respond to user query requests and recommend suitable suppliers based on real-time data, improving response speed. By constructing supplier feature profiles using multi-dimensional data, the capabilities and reputation of suppliers can be more comprehensively evaluated, resulting in more accurate recommendation results. Because the recommendation results are more accurate, the probability of users finding suitable suppliers increases, thereby improving user satisfaction. The aforementioned supermarket platform possesses the capability to collect and organize multi-dimensional supplier data, and can transform this data into feature profiles using algorithms or models. Ranking can be based on multi-dimensional data within these feature profiles (such as supplier historical performance, reputation, and price competitiveness). Displaying the ranking results to users is also a fundamental function of the recommendation system. Intelligent recommendation systems can automate most recommendation tasks, reducing manual operations and paper document management, and improving supermarket operational efficiency. Intelligent recommendation methods can update data and information in real time, quickly adapting to changes in market demand, and providing supermarkets with more flexible and efficient supplier selection solutions.

[0030] Supplier profiles can be derived through integrated analysis of various data sources, including basic supplier information, sales data, contract terms, and logistics performance. For example, a solar photovoltaic panel manufacturer registered and selling its products in a new energy commercial supermarket can have its profile analyzed based on its sales data, customer reviews, and logistics services. This analysis could reveal characteristics such as stable product quality, timely delivery, and excellent after-sales service. The multi-dimensional data for suppliers may include, but is not limited to: basic information such as company name, address, contact information, business license, and certifications; sales data such as sales revenue, sales volume, sales growth rate, and customer feedback; contract terms such as payment terms, delivery deadlines, quality assurance, and liability for breach of contract; logistics data such as delivery speed, logistics costs, delivery range, and customer satisfaction; financial data such as financial health and credit rating; and market performance such as market share, brand awareness, and media coverage. In practice, supplier profiles are updated in real-time or periodically.

[0031] In an optional embodiment, the suppliers in a set of suppliers are scored and ranked according to the feature profiles of a set of suppliers to obtain a ranking result. The process includes: the set of suppliers includes N suppliers. For the feature profile of the i-th supplier, the following operations are performed to obtain the i-th score value: a set of feature data corresponding to the i-th supplier is determined, where the i-th supplier is any supplier in the set of suppliers, where N is a positive integer greater than or equal to 1, and i is a positive integer greater than or equal to 1 and less than or equal to N; the i-th score value is calculated according to a set of feature data based on a set of preset feature weight coefficients, where the number of weight coefficients in the set of preset feature weight coefficients is equal to the number of feature dimensions in the set of feature data; and the N score values ​​are sorted in descending order to obtain a ranking result, where the N score values ​​include the i-th score value.

[0032] In the above embodiments, automatic scoring and ranking of suppliers can be achieved. Specifically, by extracting feature data from a set of suppliers and calculating a score for each supplier using preset feature weight coefficients, a multi-dimensional comprehensive evaluation of suppliers is achieved. Finally, the scores of each supplier are sorted in descending order to generate a ranking result. This embodiment helps improve the accuracy and response speed of supplier recommendations, while comprehensively evaluating the capabilities and reputation of suppliers, achieving more efficient supplier screening. The weight coefficients can be adjusted and optimized according to actual conditions, making the recommendation method more flexible to adapt to different market demands and user preferences. By introducing weight coefficients, the importance of different feature dimensions in supplier evaluation can be more accurately reflected, thereby improving the accuracy of scoring; by sorting according to the score values ​​from largest to smallest, a priority-arranged supplier list can be obtained, improving the accuracy of recommendations and user satisfaction, and better meeting the actual needs of users. For each supplier, a set of feature data corresponding to that supplier is determined. This data may include, but is not limited to, the supplier's delivery time, quality control, price, service level, etc.; a weight coefficient is assigned to each feature data, and these weight coefficients are preset according to the importance of the feature to the overall performance of the supplier. The number of weighting coefficients is equal to the dimensionality of the feature data; by setting specific feature weighting coefficients, the evaluation of suppliers is more standardized, avoiding bias caused by inconsistent evaluation standards; all suppliers are scored according to the same feature dimensions and weights, ensuring the fairness of the evaluation process. Related supplier selection methods may rely on human experience or simple scoring systems, which are not only inefficient but also potentially subjective. This method improves the efficiency and objectivity of supplier selection through an automated scoring system. Automated scoring and ranking significantly reduce the time required for manual supplier screening; it provides a data-driven supplier selection method to help supermarkets make more scientific procurement decisions; the weighting coefficients can be adjusted according to market changes and supplier performance, enabling the scoring system to adapt to the ever-changing business environment.

[0033] The aforementioned set of feature data can be data from some dimensions of the multi-dimensional data of various suppliers. Feature weight coefficients are used to evaluate the importance of different features of suppliers. These weights can be set according to the specific needs of the buyer, or they can be set by an intelligent recommendation system (or device). If the buyer attaches great importance to delivery time, the feature weight of "expected delivery time" will be higher. Suppose the buyer is very concerned about product quality and after-sales service, then the weights of "product quality" and "after-sales service" will be higher than "price". These feature weights can be determined by the buyer according to their own needs, or they can be automatically learned and adjusted by algorithms. For example, based on historical procurement data, the system can automatically identify which features are more important to the final procurement decision and adjust the weights accordingly. For example: Suppose there are three feature dimensions: product quality (weight 30%), price (weight 20%), and delivery time (weight 50%). Supplier A: Product quality score 90, price score 80, delivery time 95; Supplier B: Product quality score 85, price score 85, delivery time 90. Supplier A's score is: 90×0.3+80×0.2+95×0.5=27+16+47.5=90.5; Supplier B's score is: 85×0.3+85×0.2+90×0.5=25.5+17+45=87.5. Therefore, according to this scoring system, Supplier A has a higher score, and the system will prioritize recommending Supplier A to the buyer.

[0034] In an optional embodiment, a set of preset feature weight coefficients is obtained in one of the following ways: a set of preset feature weight coefficients is obtained by learning from historical procurement data using a machine learning model; a set of preset feature weight coefficients is predetermined; or a set of preset feature weight coefficients is set by the user, wherein the target query information includes a set of preset feature weight coefficients.

[0035] In the above embodiments, suppliers can be scored and ranked based on a set of preset feature weight coefficients obtained through different methods, thereby improving the accuracy and flexibility of the scoring and ranking. Specifically, feature weight coefficients obtained by learning from historical procurement data using a machine learning model can automatically optimize weight allocation, making the scoring more in line with actual needs; pre-determined feature weight coefficients ensure a certain degree of stability and consistency; user-defined feature weight coefficients further enhance the level of personalized service, making the scoring and ranking closer to the user's specific needs. By providing multiple ways to obtain weight coefficients, it is possible to more flexibly adapt to different market demands and user preferences, avoiding the problem of unreasonable weight coefficient settings; using machine learning models to learn weight coefficients from historical data can achieve intelligent and automated weight coefficient settings, reducing the impact of manual intervention and subjective judgment. As an optional implementation method, using machine learning models can extract useful information and patterns from a large amount of historical data to guide future decisions. By learning from historical procurement data, the model can identify which feature dimensions are more important for supplier evaluation, thereby generating reasonable weight coefficients. Obtaining weight coefficients through multiple methods can more accurately reflect the importance of different feature dimensions in supplier evaluation, improving the accuracy of scoring and the precision of recommendation results. By learning from historical procurement data through machine learning models, the weight coefficients can be dynamically adjusted to better reflect actual market conditions, thereby improving the relevance and accuracy of recommendations. Pre-determined feature weight coefficients or user-defined weights allow for flexible adjustment based on specific circumstances, meeting the needs of different scenarios. User participation in setting the weight coefficients ensures that system recommendations better align with actual user needs, enhancing user experience satisfaction.

[0036] Supervised learning methods in machine learning can be used to automatically learn and adjust feature weights. For example, historical procurement data can be collected, including buyer satisfaction ratings for suppliers and data on relevant feature dimensions; this data can be divided into training and test sets; a linear regression model can be trained using the training set data to find the optimal feature weights; the accuracy of the model can be verified on the test set, and the model can be adjusted until satisfactory performance is achieved; the trained model can be applied to predict future procurement decisions to obtain new supplier ratings.

[0037] In an optional embodiment, the process of calculating the i-th score value based on a set of feature data according to a set of preset feature weight coefficients includes: obtaining a user profile, wherein the user profile is generated based on the user's historical purchase data; determining a set of preset feature weight coefficients based on the user profile; and performing a weighted summation of each feature data in the set of feature data according to the set of preset feature weight coefficients to obtain the i-th score value.

[0038] In the above embodiments, user profiles are formed by analyzing users' historical purchasing behavior, allowing the system to understand the user's preferences and concerns. Based on these user profiles, corresponding feature weight coefficients are determined to ensure the scoring mechanism is closer to actual needs. These personalized weight coefficients are used to comprehensively consider the relevant feature data of suppliers, resulting in scoring results that better meet user expectations, thus improving the accuracy and personalization of the recommendation process. By determining a set of preset feature weight coefficients based on user profiles, the recommendation results better match user preferences and needs, thereby improving the personalization of the recommendations. Personalized recommendations can significantly improve user satisfaction because the recommendation results are more aligned with the user's actual needs. Generating user profiles using users' historical purchasing data allows for better data value mining, ensuring that each purchasing record has a positive impact on future recommendations. The introduction of user profiles makes intelligent recommendation systems (or devices) more intelligent, enabling them to provide differentiated services based on the characteristics of different users. User profiles are generated based on users' historical purchasing data and reflect their purchasing habits, preferences, and needs. User profiles contain multi-dimensional information related to the user, which can be used to guide the setting of weight coefficients. For example, if users' historical purchasing data indicates that they value price more, then the weighting coefficient for the price feature should be set higher.

[0039] Buyer profiles are built based on buyer behavior data, preferences, and historical records, enabling more precise matching of buyer needs. By analyzing these profiles, the system can recommend the most suitable suppliers for each buyer. For example, if a buyer has a history of frequently purchasing high-quality new energy products and is willing to pay higher prices, the system can prioritize suppliers offering high-quality products with strong brand reputations. Similarly, if a buyer profile indicates a high sensitivity to delivery time, the system will prioritize suppliers with fast delivery and good logistics services. When a buyer issues a purchase order, the system can filter for the most suitable suppliers based on information in the buyer profile (such as expected price range and desired delivery time). This improves the efficiency of the procurement process and reduces unnecessary communication costs. By continuously updating and maintaining buyer profiles, the system can continuously optimize supply chain management. Over time, the system can more accurately predict changes in buyer behavior and demand, allowing for proactive adjustments to supply chain strategies and ensuring timely responses from the supply side to changes in the purchasing side.

[0040] In an optional embodiment, determining a set of supplier feature profiles that match the target query information from the feature profile group includes: extracting target keywords from the target query information, wherein the target keywords include the purchased goods, expected price, and expected delivery time; determining a set of supplier feature profiles that match the target keywords from the feature profile group, wherein the multi-dimensional data includes at least the product name, product price, and average delivery time.

[0041] In the above embodiments, target keywords, including the purchased goods, expected price, and expected delivery time, are extracted from the target procurement information. A set of supplier feature profiles matching these target keywords is then determined from a feature profile group. The multi-dimensional data includes at least the product name, product price, and average delivery time, thereby achieving more accurate supplier matching and improving the accuracy and timeliness of the recommendation results. By extracting specific keywords from the procurement information, such as product name, expected price, and delivery time, suppliers meeting procurement needs can be found more precisely. By extracting target keywords and accurately matching them with supplier feature profiles, it can be ensured that the selected suppliers meet the user's procurement needs, improving the accuracy of the matching. Target query information typically includes key information such as the products the user wishes to purchase, the expected price range, and the expected delivery time. Extracting this information as target keywords helps in subsequent matching with supplier feature profiles. The feature profile group contains multi-dimensional data from multiple suppliers, such as product name, product price, and average delivery time. By matching this data with the extracted target keywords, supplier feature profiles that meet the user's needs can be selected. With a large number of suppliers, traditional screening methods may require a lot of time and effort. This embodiment improves screening efficiency and reduces manual intervention through an automated matching process.

[0042] In an optional embodiment, the feature profile of the target supplier in the feature profile group is generated in the following way, wherein the target supplier is any one of multiple suppliers: obtaining an initial dataset, wherein the initial dataset includes the target supplier's basic data, sales data, contract terms data, and logistics data; cleaning and organizing the data in the initial dataset to remove redundant and erroneous data to obtain the target dataset; extracting features from the target dataset to obtain feature combinations; and constructing the feature profile of the target supplier based on the feature combinations.

[0043] In the above embodiments, it is possible to ensure that the supplier's profile accurately reflects its strength and credibility, thereby improving the accuracy of the recommendation results. Specifically, by collecting and cleaning the supplier's basic data, sales data, contract terms data, and logistics data, and removing redundant and erroneous information, a more reliable data foundation is obtained. Furthermore, feature extraction is used to form feature combinations, and based on these, a supplier profile is constructed, enabling an objective and quantitative evaluation of the supplier's capabilities and performance, thus supporting a more accurate and efficient supplier recommendation process. Through data cleaning, processing, and feature extraction, accurate and comprehensive profiles can be generated, providing strong support for subsequent supplier evaluation and selection. Accurate profiles can help purchasers better understand the supplier's situation, thereby optimizing supplier management strategies and improving the stability and efficiency of the supply chain. The initial dataset contains basic data, sales data, contract terms data, and logistics data of the target supplier. This data forms the basis for building a feature profile. In practical applications, the initial dataset often contains redundant and erroneous data. If this data is not cleaned and organized, it will affect the accuracy of subsequent feature extraction and feature profile construction. It is necessary to clean and organize the data to obtain the target dataset. By extracting useful feature information from the target dataset, feature combinations can be formed, which provide the basis for subsequent feature profile construction. The extracted feature information is then integrated to form a complete feature profile.

[0044] In an optional embodiment, the method further includes: generating a target purchase order based on query information and target supplier information in response to a purchase instruction triggered by a user, wherein the target supplier information is information of suppliers selected by the user based on a ranking result, a group of suppliers includes the target supplier, and the purchase instruction is triggered by the user after selecting the target supplier; and recommending the target purchase order to the target supplier.

[0045] In the above embodiments, rapid response to user-triggered procurement instructions is achieved. Target purchase orders are automatically generated based on user query information and target supplier information selected according to ranking results, and recommended to target suppliers. This enables intelligent supplier recommendation and automated procurement process management within the commercial supermarket platform, significantly improving the procurement efficiency and accuracy of the platform in the new energy environment and meeting the needs of efficient management under dynamic market changes. The automated and intelligent procurement process reduces manual operations and time costs for users, improving procurement efficiency. Purchase orders generated based on query information and target supplier information ensure the accuracy and consistency of order information, avoiding procurement problems caused by inconsistencies. Directly recommending purchase orders to target suppliers shortens supplier response time, improving the smoothness of the procurement process and user satisfaction. Traditional procurement processes may require users to manually fill out purchase orders and engage in multiple communications and confirmations with suppliers. This technical solution simplifies the procurement process and improves procurement efficiency through automation and intelligence. Traditional procurement methods may require users to actively send order information to suppliers, which may take time to process and respond. This technical solution shortens supplier response time and improves the smoothness of the procurement process by directly recommending purchase orders to target suppliers. By reducing the need for manual input, automated order generation can decrease the likelihood of errors.

[0046] It should be noted that the embodiments described above are only some embodiments of this application, and not all embodiments. The present application will be described in detail below with reference to specific embodiments.

[0047] This application provides a supplier intelligent recommendation method for commercial supermarkets, which can be applied to the intelligent and efficient management of various new energy product suppliers in integrated new energy commercial supermarkets.

[0048] (1) When a supplier registers in the New Energy Commercial Supermarket, obtain the supplier's basic information (name, address, qualifications, etc.); and when the supplier sells in the New Energy Commercial Supermarket, be able to collect the supplier's sales data; among which, the sales data includes the name of the goods sold, sales volume, etc.; and obtain the supplier's sales contract template in the New Energy Commercial Supermarket, parse the sales contract template, and obtain the supplier's sales terms data; and collect the logistics data of each order of the supplier (average delivery time, logistics service provider, logistics satisfaction, etc.). (2) For each supplier, a characteristic profile of the supplier is generated by combining the above-mentioned supplier basic information, sales data, sales terms data and logistics data and other multi-dimensional data. (3) For the feature profiles of each supplier, the supplier multi-dimensional data can be updated regularly to update the feature profiles of the suppliers in sync and improve the accuracy of the feature profiles of the suppliers. (4) Respond to the procurement instructions triggered by the purchaser in the new energy commercial supermarket and obtain procurement demand information; wherein, the procurement demand information includes information such as the procurement goods, procurement quantity, expected price, and expected delivery time; (5) Determine the supplier characteristic dimensions that match the procurement demand information, and determine the characteristic weight of each characteristic (based on the buyer profile or based on the parsing of the procurement instructions). (6) Based on the characteristic dimensions and characteristic weights of each supplier determined in step (5), each supplier is screened and a score is calculated. Each supplier is then recommended to the purchaser based on the supplier score.

[0049] Optionally, based on the feature profiles of each supplier, an overall distribution map of all suppliers registered in the new energy commercial supermarket can be generated. A visual map structure such as a tree diagram or grid diagram between suppliers can be established in the form of multi-level feature dimensions. Furthermore, the overall distribution map of all suppliers can be used by the new energy commercial supermarket to determine the supplier introduction strategy from the platform side.

[0050] Specifically, this includes: 1) Data preparation. This involves collecting and organizing supplier characteristic data. This data should include, but is not limited to: sales revenue, customer satisfaction, on-time delivery rate, quality rating, price competitiveness, financial stability, market share, and contract performance. 2) Data preprocessing. This includes data cleaning (removing missing values ​​and outliers), feature scaling (standardizing or normalizing numerical features to avoid the impact of different units of measurement), and feature encoding (one-hot encoding if categorical features exist, such as market share). 3) Feature selection. Selecting the features most relevant to supplier performance. Feature selection methods (such as Recursive Feature Emission (RFE) and LASSO regression) can be used to determine which features are most important. 4) Feature combination. Combining the selected features into a comprehensive feature profile. For example, suppliers can be categorized into different types, such as "high-quality suppliers," "general suppliers," and "suppliers to be observed." 5) Visualization map construction. Using visualization tools (such as D3.js, NetworkX, and Tableau) to construct a visual map of the supplier. The specific steps are as follows: First, determine the hierarchical structure: divide the system into levels based on the importance of the features. For example, the first level could be "Sales Revenue" and "Customer Satisfaction," the second level "On-Time Delivery Rate" and "Quality Rating," and the third level "Price Competitiveness" and "Financial Stability." Second, construct a tree diagram / grid diagram: build a tree diagram or grid diagram based on the hierarchical structure. Each node represents a supplier or a class of suppliers, and the connections between nodes represent the relationships between features. Third, visualize the data: use tools to generate a visual graph that intuitively shows the relationships between suppliers and the distribution of their features.

[0051] A visual graph provides an intuitive view of the relationships and characteristic distribution among suppliers, facilitating a quick understanding of the overall supplier group's situation. This graph helps managers quickly identify high-quality suppliers and potential problem suppliers, enabling more targeted decision-making. As the data is updated, the graph can be dynamically adjusted to reflect the latest supplier status.

[0052] This application also provides a supplier intelligent recommendation device, located in a commercial supermarket platform, such as... Figure 2 As shown, Figure 2 This is a structural block diagram of a supplier intelligent recommendation device provided in an embodiment of this application. The device includes: The acquisition module 201 is used to acquire the user's target query information in response to the target command triggered by the user, wherein the target command is triggered by the user after inputting the target query information; The determination module 202 is used to determine a set of supplier feature profiles that match the target query information from the feature profile group. The feature profile group includes feature profiles of multiple suppliers, and each supplier's feature profile is generated based on the corresponding supplier's multi-dimensional data. The processing module 203 is used to score and rank each supplier in a set of suppliers based on the feature profiles of a set of suppliers, obtain the ranking results, and display the ranking results to the user.

[0053] Other device embodiments correspond to the aforementioned method embodiments, and other technical features are described in the previous embodiments, and will not be repeated here.

[0054] This application also provides a computer-readable storage medium storing instructions that, when executed, perform the steps of any of the methods described above.

[0055] In one exemplary embodiment, the aforementioned computer-readable storage medium may include, but is not limited to, various media capable of storing computer programs, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard disk, magnetic disk, or optical disk.

[0056] This application also discloses an electronic device. For example... Figure 3 As shown, Figure 3 This is a schematic diagram of the structure of an electronic device disclosed in an embodiment of this application. The electronic device 300 may include: at least one processor 301, at least one network interface 304, a user interface 303, a memory 305, and at least one communication bus 302.

[0057] The communication bus 302 is used to enable communication between these components.

[0058] The user interface 303 may include a display screen and a camera. Optionally, the user interface 303 may also include a standard wired interface and a wireless interface.

[0059] The network interface 304 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface).

[0060] The processor 301 may include one or more processing cores. The processor 301 connects to various parts of the electronic device (such as a server) using various interfaces and lines, and performs various server functions and processes data by running or executing instructions, programs, code sets, or instruction sets stored in memory 305, and by calling data stored in memory 305. Optionally, the processor 301 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The processor 301 may integrate one or a combination of several of the following: Central Processing Unit (CPU), Graphics Processing Unit (GPU), and modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the content required for display; and the modem handles wireless communication. It is understood that the modem may also not be integrated into the processor 301 and may be implemented as a separate chip.

[0061] The memory 305 may include random access memory (RAM) or read-only memory. Optionally, the memory 305 may include a non-transitory computer-readable storage medium. The memory 305 may be used to store instructions, programs, code, code sets, or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-described method embodiments, etc.; the data storage area may store data involved in the above-described method embodiments, etc. Optionally, the memory 305 may also be at least one storage device located remotely from the aforementioned processor 301. (Refer to...) Figure 3 The memory 305, which serves as a computer storage medium, may include an operating system, a network communication module, a user interface module, and an application program for a supplier intelligent recommendation method.

[0062] exist Figure 3In the illustrated electronic device 300, the user interface 303 is primarily used to provide an input interface for the user and acquire user input data. The processor 301 can be used to call an application program storing a supplier intelligent recommendation method in the memory 305. When executed by one or more processors 301, the electronic device 300 performs one or more of the methods described in the above embodiments. It should be noted that, for the foregoing method embodiments, for the sake of simplicity, they are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, because according to this application, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0063] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0064] In the various embodiments provided in this application, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some service interface; the indirect coupling or communication connection between apparatuses or units may be electrical or other forms.

[0065] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0066] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0067] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as USB flash drives, portable hard drives, magnetic disks, or optical disks.

[0068] The foregoing description is merely an exemplary embodiment of this disclosure and should not be construed as limiting the scope of this disclosure. Any equivalent changes and modifications made in accordance with the teachings of this disclosure shall still fall within the scope of this disclosure. Other embodiments of this disclosure will be readily apparent to those skilled in the art upon consideration of the specification and practical application.

[0069] This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art that are not described in this disclosure.

Claims

1. A supplier intelligent recommendation method, applied to a commercial supermarket platform, characterized in that, include: In response to a user-triggered target instruction, the user's target query information is obtained, wherein the target instruction is triggered by the user after inputting the target query information; A set of supplier feature profiles matching the target query information is determined from the feature profile group, wherein the feature profile group includes feature profiles of multiple suppliers, and each supplier feature profile is generated based on the multi-dimensional data of the corresponding supplier. The suppliers in the group are scored and ranked according to their feature profiles, and the ranking results are then displayed to the user.

2. The method according to claim 1, characterized in that, Based on the characteristic profiles of the aforementioned group of suppliers, each supplier in the group is scored and ranked to obtain the ranking results, including: The set of suppliers includes N suppliers. For the feature profile of the i-th supplier, the following operations are performed to obtain the i-th score: A set of feature data corresponding to the i-th supplier is determined, wherein the i-th supplier is any one of the suppliers in the set, and N is a positive integer greater than or equal to 1, and i is a positive integer greater than or equal to 1 and less than or equal to N; The i-th score value is calculated based on the set of feature data according to a set of preset feature weight coefficients, wherein the number of weight coefficients in the set of preset feature weight coefficients is equal to the number of feature dimensions in the set of feature data. The N rating values ​​are sorted in descending order to obtain the sorting result, wherein the N rating values ​​include the i-th rating value.

3. The method according to claim 2, characterized in that, The set of preset feature weight coefficients is obtained through one of the following methods: The set of preset feature weight coefficients is obtained by learning from historical procurement data using a machine learning model; The set of preset feature weight coefficients is predetermined; The set of preset feature weight coefficients is set by the user, and the target query information includes the set of preset feature weight coefficients.

4. The method according to claim 2, characterized in that, The i-th score value is calculated based on the set of feature data according to a set of preset feature weight coefficients, including: Obtain the user profile of the user, wherein the user profile is generated based on the user's historical purchasing data; Based on the user profile, the set of preset feature weight coefficients are determined; The i-th score value is obtained by weighting and summing each feature data of the set of feature data according to the set of preset feature weight coefficients.

5. The method according to claim 1, characterized in that, From the feature profile group, a set of supplier feature profiles matching the target query information is determined, including: Extract target keywords from the target query information, wherein the target keywords include the goods to be purchased, the expected price, and the expected delivery time; The feature profiles of the group of suppliers that match the target keywords are determined from the feature profile group, wherein the multi-dimensional data includes at least the product name, product price and average delivery time.

6. The method according to claim 1, characterized in that, The feature profiles of the target suppliers in the feature profile group are generated in the following way, wherein the target supplier is any one of the plurality of suppliers: Obtain an initial dataset, wherein the initial dataset includes the target supplier's basic data, sales data, contract terms data, and logistics data; The data in the initial dataset is cleaned and organized to remove redundant and erroneous data, resulting in the target dataset; Feature extraction is performed on the target dataset to obtain feature combinations; The feature profile of the target supplier is constructed based on the combination of the features.

7. The method according to claim 1, characterized in that, The method further includes: In response to a purchase order triggered by the user, a target purchase order is generated based on the query information and the target supplier information, wherein the target supplier information is the information of the supplier selected by the user based on the sorting result, the group of suppliers includes the target supplier, and the purchase order is triggered by the user after selecting the target supplier; The target purchase order is recommended to the target supplier.

8. A supplier intelligent recommendation device, located in a commercial supermarket platform, characterized in that, include: The acquisition module is used to acquire the user's target query information in response to a target instruction triggered by the user, wherein the target instruction is triggered by the user after inputting the target query information; The determination module is used to determine a set of supplier feature profiles that match the target query information from the feature profile group, wherein the feature profile group includes feature profiles of multiple suppliers, and each supplier feature profile is generated based on the multi-dimensional data of the corresponding supplier. The processing module is used to score and rank each supplier in the group of suppliers according to the feature profiles of the group of suppliers, obtain the ranking result, and display the ranking result to the user.

9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the program, it implements the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores instructions that, when executed, perform the method as described in any one of claims 1 to 7.

Images