User management method and system for online pork trading platform
Through the user management method of the online pork trading platform, the target user matching, sorting and sorting modules are used to solve the problem of low information isolation and matching efficiency in traditional trading platforms, and the accurate matching and efficient distribution of pork trading is achieved, which improves the Transaction efficiency and user satisfaction.
Patent Information
- Application Number
- CN202410181692.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-02-18
- Publication Date
- 2024-12-03
- Estimated Expiration
- 2044-02-18
AI Technical Summary
Due to the huge supply chain of traditional pork trading platforms, it leads to poor information transmission and low transaction efficiency, making it difficult for buyers and sellers to accurately match demand.
Through the user management method of the online pork trading platform, the target user matching module, user sorting module and user sorting module are used to match the target users from the pork industry chain based on product type and transaction type tags, and historical transaction logs are retrieved for serialization and adjustments. , generate a list of recommended target users and product quantity list.
It improves the accuracy and efficiency of transaction matching, optimizes product allocation strategies, and improves user satisfaction and transaction efficiency.
Smart Images

Figure CN118037394B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of user management, and in particular to a user management method and system for an online pork trading platform. Background Art
[0002] The online pork trading platform is used for online pork trading, where buyers and sellers can buy and sell pork products through the online platform. In traditional pork trading, there are some technical problems. On the one hand, pork trading involves a large and complex supply chain. In traditional trading, due to the large supply chain, it is difficult to accurately match buyers and sellers, resulting in poor information transmission and low transaction efficiency; on the other hand, there is an information asymmetry problem between buyers and sellers, making it difficult to accurately obtain the other party's demand and supply situation, resulting in inaccurate transaction matching. Summary of the invention
[0003] This application provides a user management method for an online pork trading platform, aiming to solve the technical problem that traditional pork trading platforms are unable to solve the information isolation of various links in the pork trading industry chain, making it difficult to match trading needs and target users, and unable to achieve accurate user matching, resulting in low trading efficiency.
[0004] The first aspect disclosed in the present application provides a user management method for an online pork trading platform, which is applied to the online pork trading platform, wherein the online pork trading platform includes a client and a server, and the method includes: receiving a pork trading request through a source client, wherein the pork trading request includes a transaction type tag, a product quantity tag and a product type tag; matching a target user set from the pork industry chain based on the product type tag and the transaction type tag through a target user matching module of the server; retrieving a historical transaction log set of the target user set through a user sorting module of the server, and serializing and adjusting the target user set according to the historical transaction log set to generate a target user sequence; sending the product type tag to a target client set of the target user set in parallel to obtain a demand quantity set; allocating the target user sequence according to the product quantity tag and the demand quantity set through a user sorting module of the server to generate a recommended target user list and a recommended product quantity list; and feeding back the recommended target user list and the recommended product quantity list to the source client.
[0005] A second aspect disclosed in the present application provides a user management system for an online pork trading platform, wherein the system is used for the user management method of the online pork trading platform, and is applied to the online pork trading platform. The online pork trading platform includes a client and a server, and the system includes: a pork trading request acquisition unit, wherein the pork trading request acquisition unit is used to receive a pork trading request through a source client, wherein the pork trading request includes a transaction type tag, a product quantity tag, and a product type tag; a target user set matching unit, wherein the target user set matching unit is used to match a target user set from the pork industry chain based on the product type tag and the transaction type tag through a target user matching module of the server; a target user sequence generation unit, wherein the target user sequence generation unit is used to generate a target user sequence through the target user matching module of the server; The user sorting module on the server side retrieves the historical transaction log set of the target user set, performs serialization adjustment on the target user set according to the historical transaction log set, and generates a target user sequence; a demand quantity set acquisition unit, the demand quantity set acquisition unit is used to send the product type tags in parallel to the target client set of the target user set to obtain the demand quantity set; a target user sequence allocation unit, the target user sequence allocation unit is used to allocate the target user sequence according to the product quantity tags and the demand quantity set through the user sorting module on the server side, and generate a recommended target user list and a recommended product quantity list; a recommendation list feedback unit, the recommendation list feedback unit is used to feed back the recommended target user list and the recommended product quantity list to the source client.
[0006] The third aspect disclosed in the present application provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the following steps when executing the computer program: receiving a pork transaction request through a source client, wherein the pork transaction request includes a transaction type tag, a product quantity tag and a product type tag; matching a target user set from the pork industry chain based on the product type tag and the transaction type tag through a target user matching module on the server; retrieving a historical transaction log set of the target user set through a user sorting module on the server, and performing serialization adjustment on the target user set according to the historical transaction log set to generate a target user sequence; sending the product type tag to a target client set of the target user set in parallel to obtain a demand quantity set; allocating the target user sequence according to the product quantity tag and the demand quantity set through a user sorting module on the server to generate a recommended target user list and a recommended product quantity list; and feeding back the recommended target user list and the recommended product quantity list to the source client.
[0007] The fourth aspect disclosed in the present application provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the following steps when executed by a processor: receiving a pork transaction request through a source client, wherein the pork transaction request includes a transaction type tag, a product quantity tag, and a product type tag; matching a target user set from the pork industry chain based on the product type tag and the transaction type tag through a target user matching module on the server; retrieving a historical transaction log set of the target user set through a user sorting module on the server, performing serialization adjustment on the target user set according to the historical transaction log set, and generating a target user sequence; sending the product type tag to a target client set of the target user set in parallel to obtain a demand quantity set; allocating the target user sequence according to the product quantity tag and the demand quantity set through a user sorting module on the server, and generating a recommended target user list and a recommended product quantity list; and feeding back the recommended target user list and the recommended product quantity list to the source client.
[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages:
[0009] Through the target user matching module, the target user set is accurately matched from the pork industry chain based on the product type label and the transaction type label, which improves the accuracy and efficiency of the matching; using the user sorting module, the historical transaction log set is retrieved to serialize and adjust the target user sequence, so that the sorting is more in line with the actual needs, and the accuracy of the recommendation and user satisfaction are improved; through the user sorting module, the target user sequence is intelligently allocated according to the product quantity label and the required quantity set, and the recommended target user list and the recommended product quantity list are generated, which optimizes the product allocation strategy and improves the efficiency and accuracy of the transaction; by feeding back the recommended target user list and the recommended product quantity list to the source client, the user can understand the recommendation more intuitively, which improves the user experience. In general, this method solves the technical problems of matching, sorting and allocation existing in traditional trading platforms, and achieves the technical effect of improving efficiency, accuracy and user satisfaction.
[0010] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS
[0011] Figure 1 A schematic diagram of a user management method for an online pork trading platform provided in an embodiment of the present application;
[0012] Figure 2 A schematic diagram of the user management system structure of an online pork trading platform provided in an embodiment of the present application;
[0013] Figure 3 This is a diagram of the internal structure of a computer device provided in an embodiment of the present application.
[0014] Explanation of the reference numerals: pork transaction request acquisition unit 10, target user set matching unit 20, target user sequence generation unit 30, demand quantity set acquisition unit 40, target user sequence allocation unit 50, recommendation list feedback unit 60. DETAILED DESCRIPTION
[0015] The embodiment of the present application solves the technical problem that traditional pork trading platforms are unable to solve the information isolation of various links in the pork trading industry chain, making it difficult to match trading needs and target users, and unable to achieve accurate matching of users, resulting in low trading efficiency, by providing a user management method for an online pork trading platform.
[0016] After introducing the basic principles of the present application, various non-limiting implementation methods of the present application will be specifically introduced below in conjunction with the accompanying drawings of the specification. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.
[0017] like Figure 1 As shown, the embodiment of the present application provides a user management method for an online pork trading platform, which is applied to the online pork trading platform. The online pork trading platform includes a client and a server. The method includes:
[0018] Receiving a pork transaction request through a source client, wherein the pork transaction request includes a transaction type tag, a product quantity tag, and a product type tag;
[0019] The user management method of the online pork trading platform provided in the embodiment of the present application is applied to the online pork trading platform, and the online pork trading platform includes a client and a server, wherein the client is a terminal device or application used by the user to interact with the online pork trading platform, and can initiate transaction requests and receive recommended products; the server is the central component of the online pork trading platform, which is responsible for processing transaction requests submitted by users, matching target users, generating recommendation information, and finally returning it to the client.
[0020] The source client refers to the client that initiates the pork transaction request. The pork transaction request submitted by the user is received through the source client. The request contains information about the transaction, including a transaction type tag, such as purchase or sales type; a product quantity tag, that is, the quantity of pork products the user wishes to purchase or sell; and a product type tag, which identifies the type or variety of the required pork product.
[0021] By means of the target user matching module of the server, a target user set is matched from the pork industry chain based on the product type tag and the transaction type tag;
[0022] Furthermore, the target user matching module of the server is used to match the target user set from the pork industry chain based on the product type tag and the transaction type tag, including:
[0023] When the transaction type tag is a purchase tag, a sales product category table is obtained according to the pork industry chain;
[0024] When the transaction type tag is a sales tag, a purchase demand category table is obtained according to the pork industry chain;
[0025] The target user set is extracted according to the sales product category table or the purchase demand category table.
[0026] The target user matching module is a component of the server, which is used to match target users. The transaction type tag is obtained from the pork transaction request. The tag is used to identify whether the transaction is a purchase or a sale. If the transaction type is a purchase tag, it means that the user has initiated a purchase request. The structure and information of the pork industry chain are obtained, including the roles and product types of different producers, suppliers, sellers, purchasers, etc. in the pork industry chain. The sales product category table is obtained. The sales product category table includes the types of pork products provided by different suppliers or producers, as well as detailed information such as the specifications, quality, price and inventory status of each product. This ensures that the server can provide product information that matches the user's purchasing needs.
[0027] If the transaction type is a sales tag, it means that the user has initiated a sales request. Based on the information of the pork industry chain, the purchasing demand category table is obtained. The purchasing demand category table includes the types of pork products required by the purchaser, the specifications and quality of each product, as well as the purchase quantity and price requirements, etc. This ensures that the server can provide product information that matches the user's sales needs.
[0028] According to the obtained category table, for the sales product category table, the producers or suppliers that produce or supply pork products that match the sales product category table are screened out. These are potential target users, and a target user set is constructed; for the purchase demand category table, the users whose sales products match the products in the purchase demand category table are screened out. These are also potential target users. The obtained target user set includes users that match the current transaction request, and is used to generate a recommended target user list.
[0029] Retrieving the historical transaction log set of the target user set through the user sorting module of the server, performing serialization adjustment on the target user set according to the historical transaction log set, and generating a target user sequence;
[0030] Furthermore, the historical transaction log set of the target user set is retrieved through the user sorting module of the server, and the target user set is serialized and adjusted according to the historical transaction log set to generate a target user sequence, including:
[0031] Step 1: extracting a first historical transaction log of a first target user of the target user set from the historical transaction log set;
[0032] Step 2: extracting a set of delay period record values according to the first historical transaction log;
[0033] Step 3: performing pooling dimensionality reduction analysis on the delay period record value set to generate a first delay period feature value;
[0034] Repeat steps 1 to 3 to obtain the first delay period characteristic value, the second delay period characteristic value, and the Nth delay period characteristic value, where N is an integer and N≥1;
[0035] The target user set is sorted from small to large according to the first delay period characteristic value, the second delay period characteristic value, and up to the Nth delay period characteristic value to obtain the target user sequence.
[0036] The historical transaction log set includes the user's past transaction records, which record detailed transaction information such as transaction time, product type, etc. The target user set is a potential user set extracted based on the sales product category table or the purchase demand category table. The first target user is randomly determined from this set, and the log related to the user is extracted from the historical transaction log set as the first historical transaction log.
[0037] According to the transaction type label, determine whether it is a purchase or sales transaction. If it is a purchase label, it means that the first target user is an upstream seller. At this time, the first target user’s delivery delay time is counted, that is, the time difference between order confirmation and actual delivery. If it is a sales label, it means that the first target user is a downstream buyer, and the first target user’s payment delay time needs to be counted, that is, the time difference between order confirmation and actual payment. According to the first target user’s delivery or payment delay time, a delay period record value set is obtained, which contains the first target user’s delay period information.
[0038] Pooling dimensionality reduction analysis is a method for reducing data dimensions by performing statistics on the values in a data set. Specifically, for every two values in the delay deadline record value set, the distance between them is calculated to form a distance set, and the outlier coefficient is evaluated based on the distance set. According to the outlier coefficient threshold, the delay deadline record values with outlier coefficient evaluation values greater than or equal to the threshold are deleted from the set. According to the delay deadline distance threshold, the processed delay deadline record value set is clustered to form a multi-cluster delay deadline record value concentration value. The cluster with the largest number of record values is selected from the clustering results, and the mean of the delay deadline record values in the cluster is calculated to obtain the first delay deadline characteristic value, which represents the overall trend of the delay deadline in the cluster.
[0039] For each target user in the target user set, repeat the process from step 1 to step 3 until the delay period characteristic values of the first to Nth target users are obtained, where N is an integer, N ≥ 1, and each target user corresponds to a delay period characteristic value. The value of N is determined in the subsequent steps of generating a recommended target user list and a recommended product quantity list.
[0040] The delay period characteristic values of the first to Nth target users are sorted in ascending order, and the target user set is sorted according to the sorted delay period characteristic values to obtain a target user sequence. After sorting, users with smaller delay periods will be at the front of the sequence, and users with larger delay periods will be at the back of the sequence, which makes users with less delay have higher priority.
[0041] Furthermore, performing pooling dimensionality reduction analysis on the delay deadline record value set to generate a first delay deadline feature value includes:
[0042] Performing pairwise distance enumeration calculation on the delay deadline record value set to obtain a delay deadline record value distance set;
[0043] Traversing the delay deadline record value set, performing outlier coefficient evaluation based on the delay deadline record value distance set, and generating an outlier coefficient evaluation value set;
[0044] According to the outlier coefficient evaluation value set, the delay deadline record values whose outlier coefficient evaluation values are greater than or equal to the outlier coefficient threshold are deleted from the delay deadline record value set to obtain a delay deadline record value concentration value;
[0045] Clustering the concentrated values of the delay deadline record values according to the delay deadline distance threshold to obtain multiple clusters of concentrated values of the delay deadline record values;
[0046] The mean value of the largest cluster of concentrated values of the multiple clusters of delay deadline record values is calculated to obtain the first delay deadline characteristic value.
[0047] For every two values in the delay deadline record value set, the distance between them is calculated. The distance calculation can directly calculate the absolute value of the difference between the two values. All the distances calculated pairwise are combined into a delay deadline record value distance set, which contains the relative distances between the delay deadline record values.
[0048] For each value in the delay deadline record value set, according to the delay deadline record value distance set, calculate the characteristic neighborhood distance set from near to far that meets the neighborhood quantity threshold, calculate the sum mean of the characteristic neighborhood distance set, and obtain the local outlier parameter of the current delay deadline record value. This parameter reflects the relative position of the current value in the neighborhood. For all values in the delay deadline record value set, calculate the mean of the local outlier parameter. For the current delay deadline record value, calculate the ratio of its local outlier parameter to the mean, and obtain the outlier coefficient evaluation value. This value represents the degree of outlier of the current value. Perform the above steps for each value in the delay deadline record value set to generate a complete outlier coefficient evaluation value set.
[0049] Configure the outlier coefficient threshold to determine which delay deadline record values are considered outliers. The threshold is set according to the actual situation and specific needs. A larger threshold will more strictly define outliers, while a smaller threshold may tolerate more variations. Traverse the outlier coefficient evaluation value set, and delete the delay deadline record values corresponding to the values greater than or equal to the outlier coefficient threshold from the original delay deadline record value set, that is, filter out the records considered to be outliers, and the remaining delay deadline record values are considered to be relatively normal values. After screening, the concentrated value of the delay deadline record value is obtained.
[0050] Configure the delay deadline distance threshold, which is used to define the similarity between samples in the cluster. The threshold is set according to the actual situation and specific needs. Use clustering algorithms, such as K-means clustering and hierarchical clustering, to divide the delay deadline record value concentration into multiple clusters according to the delay deadline distance threshold. The goal of clustering is to assign similar record values to the same cluster, and the record values within the cluster are as similar as possible. For each formed cluster, calculate its central value, such as the average value, as the center point of the cluster. These center points are the concentrated values of the delay deadline record values of multiple clusters.
[0051] In the concentrated values of multiple clusters of delay deadline record values, the number of record values is counted, and the cluster with the most record values, that is, the largest cluster, is identified. For all the record values in the largest cluster, their mean is calculated, and the value obtained is the first delay deadline characteristic value, which reflects the overall trend of the delay deadline record values in the largest cluster.
[0052] Furthermore, traversing the delay deadline record value set, performing outlier coefficient evaluation based on the delay deadline record value distance set, and generating an outlier coefficient evaluation value set includes:
[0053] Configure the neighborhood number threshold;
[0054] Extracting a first delay deadline record value from the delay deadline record value set, and configuring a characteristic neighborhood distance set satisfying the neighborhood quantity threshold from near to far for the first delay deadline record value based on the delay deadline record value distance set;
[0055] Calculate the mean of the sum of the characteristic neighborhood distance set and set it as the local outlier parameter of the first delay deadline record value;
[0056] Traversing the set of delay period record values, and calculating the mean of local outlier parameters;
[0057] The ratio of the local outlier parameter of the first delay deadline record value to the mean of the local outlier parameter is calculated, set as the outlier coefficient evaluation value of the first delay deadline record value, and added to the outlier coefficient evaluation value set.
[0058] According to the actual situation and specific needs, a threshold for judging the number of neighbors is set, and this threshold is used to define a characteristic neighborhood distance set. The first delay deadline record value is randomly selected from the delay deadline record value set as the initial reference point. For the selected first delay deadline record value, its distance from all other delay deadline record values is calculated. From the calculated delay deadline record value distances, those record values whose distances are within the neighborhood number threshold range are selected to form a characteristic neighborhood distance set. The record values in the characteristic neighborhood distance set are sorted from near to far according to the distance, so that the record values with closer distances are arranged in front.
[0059] For all record values in the characteristic neighborhood distance set, calculate the sum of their distances from the first delay deadline record value, divide the calculated sum by the number of record values in the characteristic neighborhood distance set, and obtain the mean of the sum. A larger mean sum indicates that the record value is relatively far away in its neighborhood and has a certain degree of outlier. The calculated mean sum is set as the local outlier parameter of the first delay deadline record value, and the local outlier parameter reflects the degree of outlier of the first delay deadline record value relative to its neighborhood.
[0060] For each record value in the delay deadline record value set, perform the aforementioned neighborhood distance set extraction and value mean calculation, statistically analyze the sum mean of all record values, and calculate their mean as the overall mean of the local outlier parameter. This overall mean represents an overall measure of the local outlier nature of the entire data set, and it is the average level of outlier degree of all record values in their neighborhood.
[0061] The local outlier parameter of the first delay deadline record value is divided by the local outlier parameter mean to obtain a ratio, and the calculated ratio is set as the outlier coefficient evaluation value of the first delay deadline record value. The outlier coefficient evaluation value is used to measure the degree of outlier of the first delay deadline record value relative to the overall data set. A larger outlier coefficient indicates that the record value is relatively far away in its neighborhood and has a certain degree of outlier. The calculated outlier coefficient evaluation value is added to the constructed outlier coefficient evaluation value set.
[0062] Sending the product type tags in parallel to the target client set of the target user set to obtain a required quantity set;
[0063] The product type tags are sent in parallel to the target client set of the target user set, that is, to all target clients in parallel. After receiving the product type tags, the target clients perform analysis and processing according to the tags, including first determining whether the corresponding product type of pork can be sold or purchased, then checking the inventory or production capacity according to the product type, and finally calculating the demand quantity for the product type to obtain the demand quantity set, which includes the demand quantity of each user in the target user set for a specific product type.
[0064] By means of the user sorting module of the server, the target user sequence is allocated according to the product quantity tags and the required quantity set, and a recommended target user list and a recommended product quantity list are generated;
[0065] Furthermore, the target user sequence is allocated according to the product quantity label and the required quantity set by the user sorting module of the server, and a recommended target user list and a recommended product quantity list are generated, including:
[0066] According to the target user sequence and the demand quantity set, obtaining a first target user demand quantity, a second target user demand quantity, and finally an Nth target user demand quantity, wherein N is an integer, and N≥1;
[0067] According to the product quantity label, the first target user demand quantity, the second target user demand quantity, and finally the Nth target user demand quantity are allocated in sequence to obtain the recommended target user list and the recommended product quantity list.
[0068] Set a counter with an initial value of 1, and set a target user demand quantity set to store the target user demand quantity. Traverse the target user sequence, starting from the first target user in the target user sequence, obtain the current target user's demand quantity from the demand quantity set as the first target user's demand quantity, add it to the target user demand quantity set, and determine whether the sum of the current target user demand quantity set meets the value of the product quantity label. If so, output the first target user demand quantity, and N=1; if not, add one to the counter, and continue to traverse the next target user until the sum of the target user demand quantity set meets the value of the product quantity label, and N takes the value of the counter.
[0069] According to the first target user demand quantity, the second target user demand quantity, and the Nth target user demand quantity, the first target user, the second target user, and the Nth target user are obtained to generate a recommended target user list; according to the product quantity label, the product quantity is allocated to the first target user, the second target user, and the Nth target user. For example, the demand quantities of the first N-1 target users are respectively used as the recommended product quantities of the first N-1 target users, and they are sorted. Finally, the Nth target user only obtains the remaining quantity after the product quantity label allocation is completed, as the Nth recommended product quantity, and a recommended product quantity list is generated.
[0070] Furthermore, the target user sequence is allocated according to the product quantity label and the required quantity set by the user sorting module of the server, and a recommended target user list and a recommended product quantity list are generated, including:
[0071] According to the target user sequence, obtaining a first target user delay period characteristic value, a second target user delay period characteristic value, and finally an Nth target user delay period characteristic value, wherein N is an integer, and N≥1;
[0072] According to the target user sequence, obtaining the first target user delivery distance, the second target user delivery distance, and so on until the Nth target user delivery distance;
[0073] The interactive client configures a first weight for the delivery distance and a second weight for the delay period characteristic value, wherein the sum of the first weight and the second weight is equal to 1;
[0074] Construct a ranking and reconstruction scoring function:
[0075]
[0076] Among them, Q i Represents the reconstructed rating value of the i-th target user, d iCharacterizes the delivery distance of the i-th target user, Characterizes the minimum value of n delivery distances, Characterizes the maximum value of n delivery distances, t i Characterizes the delay period characteristic value of the i-th target user, Characterize the minimum value of n delay period characteristic values, Characterize the maximum value of n delay period characteristic values;
[0077] According to the ranking reconstruction scoring function, the target user sequence is evaluated to obtain a target user ranking reconstruction scoring set;
[0078] According to the target user sorting and reconstruction score set, the target user sequence is sorted and reconstructed from small to large to obtain a target user reconstructed sequence;
[0079] The target user reconstruction sequence is allocated through the user sorting module of the server according to the product quantity tags and the required quantity set, and the recommended target user list and the recommended product quantity list are generated.
[0080] For the target user sequence, each target user is traversed one by one. For each target user, the aforementioned method for obtaining the delay period characteristic value is used to obtain the first, second, and finally Nth target user delay period characteristic values in turn. For the sake of brevity in the specification, the calculation steps are not repeated here.
[0081] For the target user sequence, each target user is traversed one by one. For each target user, its historical transaction log set is retrieved, and information related to the delivery distance is extracted from the historical transaction log, including the delivery address, delivery location, etc. The obtained delivery distance information is organized into a sequence, including the delivery distance of the first target user, the delivery distance of the second target user, and so on, until the delivery distance of the Nth target user.
[0082] Through the client interaction with the user, the user can specify the weights of the delivery distance and delay period feature values. According to the user's preference, the first weight, that is, the weight of the delivery distance, and the second weight, that is, the weight of the delay period feature value, are set. The weights are normalized. For example, if the user sets the first weight to 0.7, the second weight is set to 0.3 to ensure that the sum of the weights is equal to 1.
[0083] The above-mentioned sorting and reconstruction scoring function is used to evaluate the target user sequence. The function takes into account the user's personalized weight configuration and integrates the delivery distance and delay period characteristic values to provide users with recommendation results that are more in line with their preferences. Among them, the user with a lower reconstruction score is of higher quality because his or her delay period characteristic value is smaller and the delivery distance is smaller.
[0084] The target user sequence is traversed by using the ranking reconstruction scoring function, and the reconstruction score value of each target user is calculated and integrated into a target user ranking reconstruction score set.
[0085] The target user sequence is reordered from small to large according to the score values in the target user ranking reconstruction score set. The obtained sorted sequence is the target user reconstruction sequence. Sorting from small to large makes the users with smaller delivery distances and smaller delay period characteristic values appear at the front, that is, the users have higher priority. In this way, a recommended target user sequence that better meets the user's expectations can be provided based on the user's personalized needs and historical transaction records.
[0086] Obtain product quantity labels and required quantity sets, traverse the target user reconstruction sequence, and assign appropriate product quantities to each target user. The allocation method is the same as the previous steps, and for the sake of brevity, it will not be repeated here. Based on the allocation results, generate a recommended target user list and a recommended product quantity list, which contains the number of pork products assigned to each target user. In this way, it is possible to provide users with pork product recommendations that meet their expectations based on user needs and system resources, which helps to improve user satisfaction and the system's recommendation accuracy.
[0087] The recommended target user list and the recommended product quantity list are fed back to the source client.
[0088] The generated recommended target user list and recommended product quantity list are fed back to the source client, so that the users of the source client can easily view and confirm the recommended transaction information. After receiving the information, the source client can conduct user confirmation to complete the entire pork transaction process, thereby achieving the effectiveness and accuracy of the entire transaction process and improving user satisfaction with the transaction.
[0089] In summary, the user management method of the online pork trading platform provided in the embodiment of the present application has the following technical effects:
[0090] 1. Through the target user matching module, based on product type tags and transaction type tags, the target user set is accurately matched from the pork industry chain, improving the accuracy and efficiency of matching;
[0091] 2. Using the user sorting module, the historical transaction log set is retrieved to make serial adjustments to the target user sequence, so that the sorting is more in line with actual needs, improving the accuracy of recommendations and user satisfaction;
[0092] 3. Through the user sorting module, the target user sequence is intelligently allocated according to the product quantity label and the required quantity set, and a recommended target user list and a recommended product quantity list are generated, which optimizes the product allocation strategy and improves the efficiency and accuracy of transactions;
[0093] 4. By feeding back the recommended target user list and the recommended product quantity list to the source client, users can understand the recommendation situation more intuitively, thereby improving the user experience.
[0094] Overall, this method solves the technical problems of matching, sorting and allocation existing in traditional trading platforms, and achieves the technical effect of improving efficiency, accuracy and user satisfaction.
[0095] Based on the same inventive concept as the user management method of the online pork trading platform in the aforementioned embodiment, Figure 2 As shown, the present application provides a user management system for an online pork trading platform, which is applied to the online pork trading platform. The online pork trading platform includes a client and a server. The system includes:
[0096] A pork transaction request acquisition unit 10, the pork transaction request acquisition unit 10 is used to receive a pork transaction request through a source client, wherein the pork transaction request includes a transaction type tag, a product quantity tag and a product type tag;
[0097] A target user set matching unit 20, the target user set matching unit 20 is used to match a target user set from the pork industry chain based on the product type tag and the transaction type tag through the target user matching module of the server;
[0098] A target user sequence generating unit 30, the target user sequence generating unit 30 is used to retrieve the historical transaction log set of the target user set through the user sorting module of the server, perform serialization adjustment on the target user set according to the historical transaction log set, and generate a target user sequence;
[0099] A demand quantity set acquisition unit 40, wherein the demand quantity set acquisition unit 40 is used to send the product type tags to the target client set of the target user set in parallel to obtain a demand quantity set;
[0100] A target user sequence allocation unit 50, the target user sequence allocation unit 50 is used to allocate the target user sequence according to the product quantity label and the required quantity set through the user sorting module of the server, and generate a recommended target user list and a recommended product quantity list;
[0101] The recommendation list feedback unit 60 is used to feed back the recommendation target user list and the recommended product quantity list to the source client.
[0102] Furthermore, the system further includes a target user set acquisition module to perform the following operation steps:
[0103] When the transaction type tag is a purchase tag, a sales product category table is obtained according to the pork industry chain;
[0104] When the transaction type tag is a sales tag, a purchase demand category table is obtained according to the pork industry chain;
[0105] The target user set is extracted according to the sales product category table or the purchase demand category table.
[0106] Furthermore, the system further includes a target user sequence acquisition module to perform the following operation steps:
[0107] Step 1: extracting a first historical transaction log of a first target user of the target user set from the historical transaction log set;
[0108] Step 2: extracting a set of delay period record values according to the first historical transaction log;
[0109] Step 3: performing pooling dimensionality reduction analysis on the delay period record value set to generate a first delay period feature value;
[0110] Repeat steps 1 to 3 to obtain the first delay period characteristic value, the second delay period characteristic value, and the Nth delay period characteristic value, where N is an integer and N≥1;
[0111] The target user set is sorted from small to large according to the first delay period characteristic value, the second delay period characteristic value, and up to the Nth delay period characteristic value to obtain the target user sequence.
[0112] Furthermore, the system further includes a delay period characteristic value acquisition module to perform the following operation steps:
[0113] Performing pairwise distance enumeration calculation on the delay deadline record value set to obtain a delay deadline record value distance set;
[0114] Traversing the delay deadline record value set, performing outlier coefficient evaluation based on the delay deadline record value distance set, and generating an outlier coefficient evaluation value set;
[0115] According to the outlier coefficient evaluation value set, the delay deadline record values whose outlier coefficient evaluation values are greater than or equal to the outlier coefficient threshold are deleted from the delay deadline record value set to obtain a delay deadline record value concentration value;
[0116] Clustering the concentrated values of the delay deadline record values according to the delay deadline distance threshold to obtain multiple clusters of concentrated values of the delay deadline record values;
[0117] The mean value of the largest cluster of concentrated values of the multiple clusters of delay deadline record values is calculated to obtain the first delay deadline characteristic value.
[0118] Furthermore, the system further includes an evaluation value set acquisition module to perform the following operation steps:
[0119] Configure the neighborhood number threshold;
[0120] Extracting a first delay deadline record value from the delay deadline record value set, and configuring a characteristic neighborhood distance set satisfying the neighborhood quantity threshold from near to far for the first delay deadline record value based on the delay deadline record value distance set;
[0121] Calculate the mean of the sum of the characteristic neighborhood distance set and set it as the local outlier parameter of the first delay deadline record value;
[0122] Traversing the set of delay period record values, and calculating the mean of local outlier parameters;
[0123] The ratio of the local outlier parameter of the first delay deadline record value to the mean of the local outlier parameter is calculated, set as the outlier coefficient evaluation value of the first delay deadline record value, and added to the outlier coefficient evaluation value set.
[0124] Furthermore, the system further includes a recommendation list acquisition module to perform the following operation steps:
[0125] According to the target user sequence and the demand quantity set, obtaining a first target user demand quantity, a second target user demand quantity, and finally an Nth target user demand quantity, wherein N is an integer, and N≥1;
[0126] According to the product quantity label, the first target user demand quantity, the second target user demand quantity, and finally the Nth target user demand quantity are allocated in sequence to obtain the recommended target user list and the recommended product quantity list.
[0127] Furthermore, the system further includes a recommendation list generation module to perform the following operation steps:
[0128] According to the target user sequence, obtaining a first target user delay period characteristic value, a second target user delay period characteristic value, and finally an Nth target user delay period characteristic value, wherein N is an integer, and N≥1;
[0129] According to the target user sequence, obtaining the first target user delivery distance, the second target user delivery distance, and so on until the Nth target user delivery distance;
[0130] The interactive client configures a first weight for the delivery distance and a second weight for the delay period characteristic value, wherein the sum of the first weight and the second weight is equal to 1;
[0131] Construct a ranking and reconstruction scoring function:
[0132]
[0133] Among them, Q i Represents the reconstructed rating value of the i-th target user, d i Characterizes the delivery distance of the i-th target user, Characterizes the minimum value of n delivery distances, Characterizes the maximum value of n delivery distances, t i Characterizes the delay period characteristic value of the i-th target user, Characterize the minimum value of n delay period characteristic values, Characterize the maximum value of n delay period characteristic values;
[0134] According to the ranking reconstruction scoring function, the target user sequence is evaluated to obtain a target user ranking reconstruction scoring set;
[0135] According to the target user sorting and reconstruction score set, the target user sequence is sorted and reconstructed from small to large to obtain a target user reconstructed sequence;
[0136] The target user reconstruction sequence is allocated through the user sorting module of the server according to the product quantity tags and the required quantity set, and the recommended target user list and the recommended product quantity list are generated.
[0137] Through the above-mentioned detailed description of the user management method of the online pork trading platform in this specification, those skilled in the art can clearly understand the user management system of the online pork trading platform in this embodiment. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the description of the method part.
[0138] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as shown in FIG. Figure 3As shown. The computer device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store news data and data such as time decay factors. The network interface of the computer device is used to communicate with an external terminal through a network connection. The computer program is executed by the processor to implement a user management method for an online pork trading platform.
[0139] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.
[0140] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the following steps when executing the computer program: receiving a pork transaction request through a source client, wherein the pork transaction request includes a transaction type tag, a product quantity tag, and a product type tag; matching a target user set from the pork industry chain based on the product type tag and the transaction type tag through a target user matching module on the server; retrieving a historical transaction log set of the target user set through a user sorting module on the server, and performing serialization adjustment on the target user set according to the historical transaction log set to generate a target user sequence; sending the product type tag to a target client set of the target user set in parallel to obtain a demand quantity set; allocating the target user sequence according to the product quantity tag and the demand quantity set through a user sorting module on the server to generate a recommended target user list and a recommended product quantity list; and feeding back the recommended target user list and the recommended product quantity list to the source client.
[0141] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented: a pork transaction request is received through a source client, wherein the pork transaction request includes a transaction type tag, a product quantity tag, and a product type tag; a target user set is matched from the pork industry chain based on the product type tag and the transaction type tag through a target user matching module of the server; a historical transaction log set of the target user set is retrieved through a user sorting module of the server, and the target user set is serialized and adjusted according to the historical transaction log set to generate a target user sequence; the product type tag is sent in parallel to a target client set of the target user set to obtain a demand quantity set; the target user sequence is allocated through a user sorting module of the server according to the product quantity tag and the demand quantity set to generate a recommended target user list and a recommended product quantity list; and the recommended target user list and the recommended product quantity list are fed back to the source client.
[0142] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0143] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.
Claims
1. A user management method for an online pork trading platform, characterized in that: Applied to an online pork trading platform, the online pork trading platform includes a client and a server, and the method includes: Receiving a pork transaction request through a source client, wherein the pork transaction request includes a transaction type tag, a product quantity tag, and a product type tag; By means of the target user matching module of the server, a target user set is matched from the pork industry chain based on the product type tag and the transaction type tag; Retrieving the historical transaction log set of the target user set through the user sorting module of the server, performing serialization adjustment on the target user set according to the historical transaction log set, and generating a target user sequence; Sending the product type tags in parallel to the target client set of the target user set to obtain a required quantity set; By means of the user sorting module of the server, the target user sequence is allocated according to the product quantity tags and the required quantity set, and a recommended target user list and a recommended product quantity list are generated; Feedback the recommended target user list and the recommended product quantity list to the source client; The process of retrieving the historical transaction log set of the target user set through the user sorting module of the server, performing serialization adjustment on the target user set according to the historical transaction log set, and generating a target user sequence includes: Step 1: extracting a first historical transaction log of a first target user of the target user set from the historical transaction log set; Step 2: extracting a set of delay period record values according to the first historical transaction log, wherein the set of delay period record values is obtained by counting the delay period for the first target user to deliver goods or pay money, and the set includes the delay period information of the first target user; Step 3: performing pooling dimensionality reduction analysis on the delay period record value set to generate a first delay period feature value; Repeat steps 1 to 3 to obtain the first delay period characteristic value, the second delay period characteristic value, and the Nth delay period characteristic value, where N is an integer and N≥1; According to the first delay period characteristic value, the second delay period characteristic value, and the Nth delay period characteristic value, the target user set is sorted from small to large to obtain the target user sequence; The user sorting module of the server allocates the target user sequence according to the product quantity label and the required quantity set to generate a recommended target user list and a recommended product quantity list, including: According to the target user sequence, obtaining a first target user delay period characteristic value, a second target user delay period characteristic value, and finally an Nth target user delay period characteristic value, wherein N is an integer, and N≥1; According to the target user sequence, obtaining the first target user delivery distance, the second target user delivery distance, and finally the Nth target user delivery distance; The interactive client configures a first weight for the delivery distance and a second weight for the delay period characteristic value, wherein the sum of the first weight and the second weight is equal to 1; Construct a ranking and reconstruction scoring function: ; in, Represents the reconstructed rating value of the i-th target user, Characterizes the delivery distance of the i-th target user, Characterizes the minimum value of n delivery distances, Characterizes the maximum value of n delivery distances, Characterizes the delay period characteristic value of the i-th target user, Characterize the minimum value of n delay period characteristic values, Characterize the maximum value of n delay period eigenvalues, , are the first weight and the second weight respectively, and ; According to the ranking reconstruction scoring function, the target user sequence is evaluated to obtain a target user ranking reconstruction scoring set; According to the target user sorting and reconstruction score set, the target user sequence is sorted and reconstructed from small to large to obtain a target user reconstructed sequence; The target user reconstruction sequence is allocated through the user sorting module of the server according to the product quantity tags and the required quantity set, and the recommended target user list and the recommended product quantity list are generated.
2. The method according to claim 1, characterized in that By means of the target user matching module of the server, based on the product type tag and the transaction type tag, a target user set is matched from the pork industry chain, including: When the transaction type tag is a purchase tag, a sales product category table is obtained according to the pork industry chain; When the transaction type tag is a sales tag, a purchase demand category table is obtained according to the pork industry chain; The target user set is extracted according to the sales product category table or the purchase demand category table.
3. The method according to claim 1, characterized in that Performing pooling dimensionality reduction analysis on the delay deadline record value set to generate a first delay deadline feature value, including: Performing pairwise distance enumeration calculation on the delay deadline record value set to obtain a delay deadline record value distance set; Traversing the delay deadline record value set, performing outlier coefficient evaluation based on the delay deadline record value distance set, and generating an outlier coefficient evaluation value set; According to the outlier coefficient evaluation value set, the delay deadline record values whose outlier coefficient evaluation values are greater than or equal to the outlier coefficient threshold are deleted from the delay deadline record value set to obtain a delay deadline record value concentration value; Clustering the concentrated values of the delay deadline record values according to the delay deadline distance threshold to obtain a plurality of clusters of concentrated values of the delay deadline record values; The mean value of the largest cluster of concentrated values of the multiple clusters of delay deadline record values is calculated to obtain the first delay deadline characteristic value.
4. The method according to claim 3, characterized in that Traversing the delay deadline record value set, performing outlier coefficient evaluation based on the delay deadline record value distance set, and generating an outlier coefficient evaluation value set, including: Configure the neighborhood number threshold; Extracting a first delay deadline record value from the delay deadline record value set, and configuring a characteristic neighborhood distance set satisfying the neighborhood quantity threshold from near to far for the first delay deadline record value based on the delay deadline record value distance set; Calculate the mean of the sum of the characteristic neighborhood distance set and set it as the local outlier parameter of the first delay deadline record value; Traversing the set of delay period record values, and calculating the mean of local outlier parameters; The ratio of the local outlier parameter of the first delay deadline record value to the mean of the local outlier parameter is calculated, set as the outlier coefficient evaluation value of the first delay deadline record value, and added to the outlier coefficient evaluation value set.
5. The method according to claim 1, characterized in that The user sorting module of the server allocates the target user sequence according to the product quantity label and the required quantity set, and generates a recommended target user list and a recommended product quantity list, including: According to the target user sequence and the demand quantity set, obtaining a first target user demand quantity, a second target user demand quantity, and finally an Nth target user demand quantity, wherein N is an integer, and N≥1; According to the product quantity label, the first target user demand quantity, the second target user demand quantity, and finally the Nth target user demand quantity are allocated in sequence to obtain the recommended target user list and the recommended product quantity list.
6. The user management system of the online pork trading platform is characterized by: Applied to an online pork trading platform, the online pork trading platform includes a client and a server, and is used to implement the user management method of the online pork trading platform according to any one of claims 1 to 5, the system includes: A pork transaction request acquisition unit, the pork transaction request acquisition unit is used to receive a pork transaction request through a source client, wherein the pork transaction request includes a transaction type tag, a product quantity tag and a product type tag; A target user set matching unit, the target user set matching unit is used to match a target user set from the pork industry chain based on the product type tag and the transaction type tag through the target user matching module of the server; A target user sequence generating unit, the target user sequence generating unit is used to retrieve the historical transaction log set of the target user set through the user sorting module of the server, perform serialization adjustment on the target user set according to the historical transaction log set, and generate a target user sequence; A demand quantity set acquisition unit, the demand quantity set acquisition unit is used to send the product type tags to the target client set of the target user set in parallel to obtain a demand quantity set; A target user sequence allocation unit, the target user sequence allocation unit is used to allocate the target user sequence according to the product quantity label and the required quantity set through the user sorting module of the server, and generate a recommended target user list and a recommended product quantity list; A recommendation list feedback unit, the recommendation list feedback unit is used to feed back the recommendation target user list and the recommended product quantity list to the source client; The target user sequence generation unit further comprises the following steps: Step 1: extracting a first historical transaction log of a first target user of the target user set from the historical transaction log set; Step 2: extracting a set of delay period record values according to the first historical transaction log, wherein the set of delay period record values is obtained by counting the delay period for the first target user to deliver goods or pay money, and the set includes the delay period information of the first target user; Step 3: performing pooling dimensionality reduction analysis on the delay period record value set to generate a first delay period feature value; Repeat steps 1 to 3 to obtain the first delay period characteristic value, the second delay period characteristic value, and the Nth delay period characteristic value, where N is an integer and N≥1; According to the first delay period characteristic value, the second delay period characteristic value, and the Nth delay period characteristic value, the target user set is sorted from small to large to obtain the target user sequence; The target user sequence allocation unit further comprises the following operation steps: According to the target user sequence, obtaining a first target user delay period characteristic value, a second target user delay period characteristic value, and finally an Nth target user delay period characteristic value, wherein N is an integer, and N≥1; According to the target user sequence, obtaining the first target user delivery distance, the second target user delivery distance, and finally the Nth target user delivery distance; The interactive client configures a first weight for the delivery distance and a second weight for the delay period characteristic value, wherein the sum of the first weight and the second weight is equal to 1; Construct a ranking and reconstruction scoring function: ; in, Represents the reconstructed rating value of the i-th target user, Characterizes the delivery distance of the i-th target user, Characterizes the minimum value of n delivery distances, Characterizes the maximum value of n delivery distances, Characterizes the delay period characteristic value of the i-th target user, Characterize the minimum value of n delay period characteristic values, Characterize the maximum value of n delay period eigenvalues, , are the first weight and the second weight respectively, and ; According to the ranking reconstruction scoring function, the target user sequence is evaluated to obtain a target user ranking reconstruction scoring set; According to the target user sorting and reconstruction score set, the target user sequence is sorted and reconstructed from small to large to obtain a target user reconstructed sequence; The target user reconstruction sequence is allocated through the user sorting module of the server according to the product quantity tags and the required quantity set, and the recommended target user list and the recommended product quantity list are generated.
7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the user management method for an online pork trading platform according to any one of claims 1 to 5 are implemented.
8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the user management method for an online pork trading platform according to any one of claims 1 to 5 are implemented.
