A transaction management method and system based on multi-transaction object interaction

Abstract

The present invention relates to the field of transaction management technology, and in particular to a transaction management method and system based on the interaction of multiple transaction objects. The present invention analyzes the transaction needs of users through transaction demand data; analyzes the combined transaction matching degree of multiple transaction objects in the user's shopping cart through the characteristic data and function data of multiple transaction objects, obtains multiple transaction object combinations according to the combined transaction matching degree analysis results, and obtains the combined attribute data of the multiple transaction object combinations; analyzes the transaction priority of multiple transaction object combinations in the user's shopping cart according to the transaction demand analysis results of the user and the combined attribute data of the multiple transaction object combinations; and recommends the optimal transaction object combination to the user according to the transaction priority analysis results. The present invention can solve the technical problems of single commodity recommendation, lack of accurate analysis of user needs, lack of basis for combined recommendation, and unclear priority sorting in the prior art, and improve the shopping experience and satisfaction of users.

Description

Technical Field

[0001] The present invention relates to the technical field of transaction management, and in particular to a transaction management method and system based on multi-transaction object interaction. Background Art

[0002] With the rapid development of e-commerce and online trading platforms, users often add multiple transaction objects to the shopping cart during the shopping process, and expect to meet diverse needs in one transaction. Modern consumers not only pay attention to the quality and price of individual products, but also attach great importance to the matching of products and the overall shopping experience. For example, when buying electronic products, users may consider buying mobile phones, protective cases and accessories at the same time, hoping that these products can be compatible with each other and have complementary functions; when buying clothes, they may pay attention to the matching effect of different clothes, hoping that these products can form a unified style.

[0003] However, traditional transaction management methods usually focus on the recommendation of a single product, relying on the sales volume of the product, the user's historical purchase records and simple association rules. Although this recommendation method is effective in some scenarios, it is powerless when dealing with complex interactions between multiple products. Users need to spend a lot of time and energy to manually screen and match products, which increases the complexity of shopping. At the same time, the existing transaction management methods also lack the optimization analysis of multi-product combinations, and cannot consider the compatibility and functional complementarity between products as a whole. For example, when a user buys a set of furniture, he may hope that the furniture is consistent in color, style and size, but the existing technology often cannot provide such a combination recommendation. This leads to users often having difficulty making the best choice when faced with multiple products in the shopping cart, thus failing to fully meet their diverse needs.

[0004] In order to solve these problems, the present application designs a transaction management method and system based on the interaction of multiple transaction objects. Summary of the invention

[0005] In order to overcome the defects and shortcomings of the prior art, the present invention provides a transaction management method and system based on the interaction of multiple transaction objects, which analyzes the transaction priority of multiple transaction object combinations in the user's shopping cart to obtain the optimal transaction object combination. It can effectively solve the technical problems of the prior art such as single product recommendation, lack of accurate analysis of user needs, lack of basis for combination recommendation and unclear priority sorting, and improve the user's shopping experience and satisfaction.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] In a first aspect, an embodiment of the present invention provides a transaction management method based on multi-transaction object interaction, comprising the following steps:

[0008] S1. Obtaining feature data and functional data of multiple transaction objects in the user's shopping cart, and simultaneously obtaining the user's transaction demand data;

[0009] S2. Importing the transaction demand data into the transaction demand analysis model of the transaction object to analyze the transaction demand of the user;

[0010] S3, importing the characteristic data and function data of multiple transaction objects into the transaction object combination transaction matching degree analysis model to analyze the combination transaction matching degree of multiple transaction objects in the user's shopping cart, and obtaining multiple transaction object combinations according to the combination transaction matching degree analysis results, and obtaining the combination attribute data of the multiple transaction object combinations;

[0011] S4. Analyzing the transaction priority of multiple transaction object combinations in the user's shopping cart according to the transaction demand analysis results of the user and the combined attribute data of multiple transaction object combinations;

[0012] S5. Based on the transaction priority analysis results, the optimal transaction object combination is recommended to the user.

[0013] In one implementation of the present invention, step S2 includes the following specific steps:

[0014] S21, extracting the transaction demand data of the user, wherein the transaction demand data includes the evaluation text data of the user on the historical transaction objects and the transaction object type data in the user's shopping cart;

[0015] S22, obtaining the user's evaluation text data on multiple historical transaction objects of the same type as the transaction object in the shopping cart, importing the evaluation text data of the multiple historical transaction objects into the word frequency analysis model, performing noun word frequency analysis on the evaluation text data of the multiple historical transaction objects, summing up the word frequencies of the multiple nouns obtained by the analysis and taking an average value, and obtaining multiple nouns corresponding to word frequencies greater than or equal to the average value as the user's transaction demand for the transaction object in the shopping cart;

[0016] S23. Obtain the user's transaction demand for all transaction objects in the shopping cart, and use the intersection of the user's transaction demand for all transaction objects in the shopping cart as the user's transaction demand.

[0017] In one implementation of the present invention, step S3 includes the following specific steps:

[0018] S31, extracting feature data and function data of multiple transaction objects in the user's shopping cart, wherein the feature data includes a transaction object image of the transaction object; and the function data includes a function list of the transaction object extracted from a preset transaction object database;

[0019] S32. Perform image feature extraction on the transaction object image to obtain an image feature vector of the transaction object; perform function feature extraction on the function list of the transaction object to obtain a function feature vector of the transaction object; perform splicing processing on the image feature vector and the function feature vector to obtain a multidimensional feature vector of the transaction object, wherein the number of dimensions of the multidimensional feature vector of the transaction object is the sum of the number of dimensions of the image feature vector and the number of dimensions of the function feature vector.

[0020] In one implementation of the present invention, step S3 further includes the following specific steps:

[0021] S33, obtaining a multidimensional feature vector of all transaction objects in the user's shopping cart;

[0022] S34. According to step S33, a calculation formula for the characteristic difference value within the transaction object combination is constructed:

[0023] ;

[0024] Among them, wcv represents the characteristic difference value within the transaction object combination, represents the jth eigenvalue in the multidimensional feature vector of the ith transaction object in the qth transaction object combination, represents the average value of the jth eigenvalue in the multidimensional feature vector of all transaction objects in the qth transaction object combination, Q represents the number of transaction object combinations, m represents the total number of transaction objects in the qth transaction object combination, n represents the number of eigenvalues ​​in the multidimensional feature vector of the ith transaction object in the qth transaction object combination; j is any item from 1 to n, i is any item from 1 to m, and q is any item from 1 to Q;

[0025] S35. According to step S33, a calculation formula for the characteristic difference value between transaction object combinations is constructed:

[0026] ;

[0027] Where bcv represents the characteristic difference value between transaction object combinations, Represents the average value of the jth eigenvalue in the multidimensional feature vector of all transaction objects in all transaction object combinations;

[0028] S36. Constructing the objective function ; Where a and b represent the weight coefficient of the characteristic difference within the transaction object combination and the weight coefficient of the characteristic difference between the transaction object combinations respectively;

[0029] S37, extracting multiple groups of transaction object combination sequences generated by multiple random combinations of all transaction objects in the user's shopping cart, wherein the transaction object combination sequence includes multiple transaction object combinations generated by each random combination, substituting the multidimensional feature vectors of all transaction objects corresponding to each group of transaction object combination sequence into the formula of steps S34-S36, and obtaining the transaction object combination sequence corresponding to the maximum value of the objective function J as the combination transaction matching degree analysis result;

[0030] S38. Acquire multiple transaction object combinations in the combined transaction matching degree analysis result, and acquire combined attribute data of each transaction object combination, wherein the combined attribute data includes historical transaction evaluation text data, favorable comment rate and price of all transaction objects in the transaction object combination.

[0031] In one implementation of the present invention, step S4 includes the following specific steps:

[0032] S41, extracting the combined attribute data of the user's transaction demand and multiple transaction object combinations; importing the historical transaction evaluation text data of each transaction object in each transaction object combination into the word frequency analysis model to perform noun word frequency analysis on the historical transaction evaluation of each transaction object, summing up the word frequencies of multiple nouns obtained by the analysis and taking the average value, obtaining multiple nouns corresponding to the word frequencies greater than or equal to the average value as the demand characteristics of the corresponding transaction objects; obtaining the demand characteristics of all transaction objects in each transaction object combination, and eliminating the repeated demand characteristics in the demand characteristics of all transaction objects in each transaction object combination, and using the demand characteristics of all transaction objects in each transaction object combination after elimination as the demand characteristics of each transaction object combination;

[0033] S42, substituting the transaction demand of the user, the demand characteristics of multiple transaction object combinations and the combination attribute data into the transaction priority index calculation formula to calculate the transaction priority index of each transaction object combination; the transaction priority index calculation formula is:

[0034] ;

[0035] Among them, JYq represents the transaction priority index of the qth transaction object combination, represents the mean of the favorable reviews of all transaction objects in the qth transaction object combination, jx represents the transaction demand of the user, xt represents the demand characteristics of the qth transaction object combination, num() represents the number of elements in the brackets, It means taking the intersection of the user's transaction demand and the demand characteristics of the qth transaction object combination, represents the union of the user's transaction demand and the demand characteristics of the qth transaction object combination, Pq represents the mean of the sum of the prices of all transaction objects in the qth transaction object combination, It represents the mean of the sum of the prices of all transaction objects in all transaction object combinations.

[0036] In one implementation of the present invention, step S5 includes the following specific contents:

[0037] The transaction object combination corresponding to the maximum value of the transaction priority index of all transaction object combinations calculated is obtained and recommended to the user as the optimal transaction object combination.

[0038] In a second aspect, an embodiment of the present invention further provides a transaction management system based on multi-transaction object interaction, comprising:

[0039] The data acquisition module is used to obtain the characteristic data and functional data of multiple transaction objects in the user's shopping cart, and at the same time obtain the user's transaction demand data;

[0040] The transaction demand analysis module is used to import the transaction demand data into the transaction object transaction demand analysis model to analyze the user's transaction demand;

[0041] A combination transaction matching analysis module is used to import the characteristic data and function data of multiple transaction objects into the transaction object combination transaction matching degree analysis model to analyze the combination transaction matching degree of multiple transaction objects in the user's shopping cart, obtain multiple transaction object combinations according to the combination transaction matching degree analysis results, and obtain the combination attribute data of the multiple transaction object combinations;

[0042] A transaction priority analysis module is used to analyze the transaction priority of multiple transaction object combinations in the user's shopping cart based on the user's transaction demand analysis results and the combined attribute data of multiple transaction object combinations;

[0043] The optimal transaction object combination recommendation module is used to recommend the optimal transaction object combination to the user based on the transaction priority analysis results;

[0044] A control module is used to control the operation of the data acquisition module, the transaction demand analysis module, the combination transaction matching analysis module, the transaction priority analysis module and the optimal transaction object combination recommendation module.

[0045] In a third aspect, an embodiment of the present invention provides an electronic device, comprising: a processor and a memory, wherein the memory stores a computer program that can be called by the processor, and the processor executes a transaction management method based on the interaction of multiple transaction objects by calling the computer program stored in the memory.

[0046] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium storing instructions, which, when executed on a computer, enables the computer to execute a transaction management method based on interaction between multiple transaction objects.

[0047] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0048] The present invention analyzes the transaction needs of users through transaction demand data; analyzes the combined transaction matching degree of multiple transaction objects in the user's shopping cart through the characteristic data and function data of multiple transaction objects, obtains multiple transaction object combinations according to the combined transaction matching degree analysis results, and obtains the combined attribute data of the multiple transaction object combinations; analyzes the transaction priority of multiple transaction object combinations in the user's shopping cart according to the transaction demand analysis results of the user and the combined attribute data of the multiple transaction object combinations; and recommends the optimal transaction object combination to the user according to the transaction priority analysis results. It can solve the technical problems of single commodity recommendation, lack of accurate analysis of user needs, lack of basis for combined recommendation, and unclear priority sorting in the prior art, and improve the shopping experience and satisfaction of users. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings:

[0050] Figure 1 It is a schematic diagram of the overall process of a transaction management method based on multi-transaction object interaction of the present invention;

[0051] Figure 2 A flowchart of a word frequency analysis model in a transaction management method based on multi-transaction object interaction of the present invention;

[0052] Figure 3 A schematic diagram of the structure of a transaction management system based on multi-transaction object interaction of the present invention;

[0053] Figure 4 The present invention is a flowchart of the reverse clustering method in a transaction management method based on the interaction of multiple transaction objects. DETAILED DESCRIPTION

[0054] The technical solution of the present invention is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical solution of the present invention, rather than limitations on the technical solution of the present invention. The embodiments of the present invention and the technical features in the embodiments may be combined with each other unless there is a conflict.

[0055] Example 1

[0056] like Figure 1 As shown, this embodiment provides a transaction management method based on multi-transaction object interaction, which specifically includes the following steps:

[0057] S1. Obtaining feature data and functional data of multiple transaction objects in the user's shopping cart, and simultaneously obtaining the user's transaction demand data;

[0058] S2. Importing the transaction demand data into the transaction demand analysis model of the transaction object to analyze the transaction demand of the user;

[0059] S3, importing the characteristic data and function data of multiple transaction objects into the transaction object combination transaction matching degree analysis model to analyze the combination transaction matching degree of multiple transaction objects in the user's shopping cart, and obtaining multiple transaction object combinations according to the combination transaction matching degree analysis results, and obtaining the combination attribute data of the multiple transaction object combinations;

[0060] S4. Analyzing the transaction priority of multiple transaction object combinations in the user's shopping cart according to the transaction demand analysis results of the user and the combined attribute data of multiple transaction object combinations;

[0061] S5. Based on the transaction priority analysis results, the optimal transaction object combination is recommended to the user.

[0062] In this embodiment, step S2 includes the following specific steps:

[0063] S21, extracting the transaction demand data of the user, wherein the transaction demand data includes the evaluation text data of the user on the historical transaction objects and the transaction object type data in the user's shopping cart;

[0064] S22, obtaining the user's evaluation text data of multiple historical transaction objects of the same type as a transaction object in the shopping cart, and importing the evaluation text data of the multiple historical transaction objects into the system in this embodiment. Figure 2 In a word frequency analysis model shown, a noun word frequency analysis is performed on the evaluation text data of multiple historical transaction objects, the word frequencies of the multiple nouns obtained by the analysis are summed and averaged, and multiple nouns corresponding to the word frequencies greater than or equal to the average are obtained as the user's transaction demand for a transaction object in the shopping cart;

[0065] S23. Obtain the user's transaction demand for all transaction objects in the shopping cart, and use the intersection of the user's transaction demand for all transaction objects in the shopping cart as the user's transaction demand.

[0066] In this embodiment, we analyze the user's transaction needs by importing the user's transaction demand data into the transaction demand analysis model. This step can provide a clear goal and direction for the subsequent transaction object combination recommendation. By analyzing the user's transaction needs and analyzing the user's historical evaluation data, we can accurately understand the user's focus when the current transaction is the same type of transaction object as the historical transaction. These preferences will directly affect the subsequent transaction object combination matching and priority sorting. At the same time, the transaction demand analysis results provide a basis for personalized recommendations. Only by fully understanding the user's needs can we ensure that the recommended transaction object combination truly meets the user's expectations, thereby improving the user's satisfaction with the recommendation results. Moreover, through the transaction demand analysis in this embodiment, the transaction objects that obviously do not meet the user's needs can be filtered out, narrowing the candidate range and reducing the complexity of subsequent analysis and calculation.

[0067] In this embodiment, step S3 includes the following specific steps:

[0068] S31, extracting feature data and function data of multiple transaction objects in the user's shopping cart, wherein the feature data includes a transaction object image of the transaction object; and the function data includes a function list of the transaction object extracted from a preset transaction object database;

[0069] S32. Perform image feature extraction on the transaction object image to obtain an image feature vector of the transaction object; perform function feature extraction on the function list of the transaction object to obtain a function feature vector of the transaction object; perform splicing processing on the image feature vector and the function feature vector to obtain a multidimensional feature vector of the transaction object, wherein the number of dimensions of the multidimensional feature vector of the transaction object is the sum of the number of dimensions of the image feature vector and the number of dimensions of the function feature vector.

[0070] It should be noted that in this embodiment, when extracting functional features from the function list of the transaction object, it is necessary to encode the category data in the function list. The function list usually contains numerical data and category data. When extracting functional features for these two types of data, we use different encoding methods: First, the numerical data in the function list does not require special encoding processing, and its original value can be used directly. For the category data in the function list, it needs to be converted into a numerical form, because most machine learning models cannot directly process string categories. Therefore, we use two common encoding methods: The first encoding method is one-hot encoding: for each category variable, create a sparse vector in which only one value is 1 and the other values ​​are 0. This method is suitable for category data in the function list that does not have an order relationship. For example: there is a category feature color in the function list, which may take values ​​of red, blue, and green. One-hot encoding will convert it into: red→[1,0,0], blue→[0,1,0], green→[0,0,1]; another encoding method is label encoding: convert the category variables in the function list into integer labels. This method is suitable for category data with a natural order. For example, there is a category feature size in the function list, which may take values ​​of small, medium, and large. Label encoding will convert it into: small → 0, medium → 1, large → 2; the data in the function list is uniformly encoded and converted into a numerical form, and then a transaction object function feature vector that can be spliced ​​with the transaction object image feature vector is generated; image feature extraction of the transaction object image can be performed through the texture feature, color feature or shape feature of the transaction object in the image, which belongs to the existing technology and will not be repeated here.

[0071] In this embodiment, step S3 also includes the following specific steps:

[0072] S33, obtaining a multidimensional feature vector of all transaction objects in the user's shopping cart;

[0073] S34. According to step S33, a calculation formula for the characteristic difference value within the transaction object combination is constructed:

[0074] ;

[0075] Among them, wcv represents the characteristic difference value within the transaction object combination, represents the jth eigenvalue in the multidimensional feature vector of the ith transaction object in the qth transaction object combination, represents the average value of the jth eigenvalue in the multidimensional feature vector of all transaction objects in the qth transaction object combination, Q represents the number of transaction object combinations, m represents the total number of transaction objects in the qth transaction object combination, n represents the number of eigenvalues ​​in the multidimensional feature vector of the ith transaction object in the qth transaction object combination; j is any item from 1 to n, i is any item from 1 to m, and q is any item from 1 to Q;

[0076] S35. According to step S33, a calculation formula for the characteristic difference value between transaction object combinations is constructed:

[0077] ;

[0078] Where bcv represents the characteristic difference value between transaction object combinations, Represents the average value of the jth eigenvalue in the multidimensional feature vector of all transaction objects in all transaction object combinations;

[0079] S36. Constructing the objective function ; Where a and b represent the weight coefficient of the characteristic difference within the transaction object combination and the weight coefficient of the characteristic difference between the transaction object combinations respectively;

[0080] S37, extracting multiple groups of transaction object combination sequences generated by multiple random combinations of all transaction objects in the user's shopping cart, wherein the transaction object combination sequence includes multiple transaction object combinations generated by each random combination, substituting the multidimensional feature vectors of all transaction objects corresponding to each group of transaction object combination sequence into the formula of steps S34-S36, and obtaining the transaction object combination sequence corresponding to the maximum value of the objective function J as the combination transaction matching degree analysis result;

[0081] It should be noted that the method for obtaining the weight coefficient of the characteristic difference within the transaction object combination and the weight coefficient of the characteristic difference between the transaction object combinations is as follows: obtaining the multidimensional characteristic vectors of all transaction objects in 5000 groups of user shopping carts, importing them into the objective function J to calculate multiple values ​​of 5000 groups of objective function J, and obtaining the combined transaction matching degree judgment results of all transaction objects in 5000 groups of user shopping carts; importing the multiple values ​​of 5000 groups of objective function J and the combined transaction matching degree judgment results into the fitting software, and outputting the values ​​of the characteristic difference weight coefficient within the transaction object combination and the characteristic difference weight coefficient between the transaction object combinations that meet the highest combined transaction matching degree judgment accuracy;

[0082] S38. Acquire multiple transaction object combinations in the combined transaction matching degree analysis result, and acquire combined attribute data of each transaction object combination, wherein the combined attribute data includes historical transaction evaluation text data, favorable comment rate and price of all transaction objects in the transaction object combination.

[0083] In this embodiment, we import the characteristic data and functional data of multiple transaction objects into the transaction object combination transaction matching degree analysis model, and combine the following Figure 4 The reverse clustering method shown analyzes the degree of matching of the combination of multiple transaction objects in the user's shopping cart. Through the reverse clustering method, we can calculate that the transaction objects in the same combination can cover the needs that can be met by most of the transaction objects in the user's shopping cart in terms of features and functions, while different combinations are similar to each other in features and functions. This combination can better meet the various needs of users and spread risks. It can obtain an optimization result in which the transaction objects in the same combination meet the diverse needs of users, and the different combinations are similar to each other in features and functions. This method ensures that the recommended transaction object combination not only has a high degree of consistency and demand coverage internally, but also maintains a certain degree of similarity overall, thereby improving the effectiveness of the recommendation results and user satisfaction.

[0084] In this embodiment, step S4 includes the following specific steps:

[0085] S41, extracting the combined attribute data of the user's transaction needs and multiple transaction object combinations; importing the historical transaction evaluation text data of each transaction object in each transaction object combination into the data in this embodiment as shown in FIG. Figure 2 In a word frequency analysis model shown, a noun word frequency analysis is performed on the historical transaction evaluation of each transaction object, the word frequencies of multiple nouns obtained by the analysis are summed and averaged, and multiple nouns corresponding to word frequencies greater than or equal to the average are obtained as demand features of the corresponding transaction objects; the demand features of all transaction objects in each transaction object combination are obtained, and repeated demand features in the demand features of all transaction objects in each transaction object combination are eliminated, and the demand features of all transaction objects in each transaction object combination after elimination are used as the demand features of each transaction object combination;

[0086] S42, substituting the transaction demand of the user, the demand characteristics of multiple transaction object combinations and the combination attribute data into the transaction priority index calculation formula to calculate the transaction priority index of each transaction object combination; the transaction priority index calculation formula is:

[0087] ;

[0088] Among them, JYq represents the transaction priority index of the qth transaction object combination, represents the mean of the favorable reviews of all transaction objects in the qth transaction object combination, jx represents the transaction demand of the user, xt represents the demand characteristics of the qth transaction object combination, num() represents the number of elements in the brackets, It means taking the intersection of the user's transaction demand and the demand characteristics of the qth transaction object combination, represents the union of the user's transaction demand and the demand characteristics of the qth transaction object combination, Pq represents the mean of the sum of the prices of all transaction objects in the qth transaction object combination, It represents the mean of the sum of the prices of all transaction objects in all transaction object combinations.

[0089] In this embodiment, step S5 includes the following specific contents:

[0090] The transaction object combination corresponding to the maximum value of the transaction priority index of all transaction object combinations calculated is obtained and recommended to the user as the optimal transaction object combination.

[0091] Example 2

[0092] like Figure 3 As shown, this embodiment provides a transaction management system based on multi-transaction object interaction, including:

[0093] The data acquisition module is used to obtain the characteristic data and functional data of multiple transaction objects in the user's shopping cart, and at the same time obtain the user's transaction demand data;

[0094] The transaction demand analysis module is used to import the transaction demand data into the transaction object transaction demand analysis model to analyze the user's transaction demand;

[0095] A combination transaction matching analysis module is used to import the characteristic data and function data of multiple transaction objects into the transaction object combination transaction matching degree analysis model to analyze the combination transaction matching degree of multiple transaction objects in the user's shopping cart, obtain multiple transaction object combinations according to the combination transaction matching degree analysis results, and obtain the combination attribute data of the multiple transaction object combinations;

[0096] A transaction priority analysis module is used to analyze the transaction priority of multiple transaction object combinations in the user's shopping cart based on the user's transaction demand analysis results and the combined attribute data of multiple transaction object combinations;

[0097] The optimal transaction object combination recommendation module is used to recommend the optimal transaction object combination to the user based on the transaction priority analysis results;

[0098] The control module is used to control the operation of the data acquisition module, the transaction demand analysis module, the combination transaction matching analysis module, the transaction priority analysis module and the optimal transaction object combination recommendation module.

[0099] In this embodiment, the transaction demand analysis module is used to import the transaction demand data into the transaction object transaction demand analysis model to analyze the transaction demand of the user; analyzing the transaction demand of the user includes the following specific steps:

[0100] Extracting the user's transaction demand data, wherein the transaction demand data includes the user's evaluation text data on historical transaction objects and the transaction object type data in the user's shopping cart;

[0101] Obtaining user evaluation text data on multiple historical transaction objects of the same type as a transaction object in the shopping cart, importing the evaluation text data on the multiple historical transaction objects into a word frequency analysis model, performing noun word frequency analysis on the evaluation text data on the multiple historical transaction objects, summing up the word frequencies of the multiple nouns obtained by the analysis and taking an average value, and obtaining multiple nouns corresponding to word frequencies greater than or equal to the average value as the user's transaction demand for a transaction object in the shopping cart;

[0102] The user's transaction demands for all transaction objects in the shopping cart are obtained, and the intersection of the user's transaction demands for all transaction objects in the shopping cart is used as the user's transaction demand.

[0103] In this embodiment, the combined transaction matching analysis module is used to import the feature data and function data of multiple transaction objects into the transaction object combined transaction matching degree analysis model to analyze the combined transaction matching degree of multiple transaction objects in the user's shopping cart, obtain multiple transaction object combinations according to the combined transaction matching degree analysis result, and obtain the combined attribute data of the multiple transaction object combinations; analyzing the combined transaction matching degree of multiple transaction objects in the user's shopping cart includes the following specific steps:

[0104] Extracting feature data and function data of multiple transaction objects in a user's shopping cart, wherein the feature data includes a transaction object image of the transaction object; the function data includes a function list of the transaction object extracted from a preset transaction object database;

[0105] Perform image feature extraction on the transaction object image to obtain the image feature vector of the transaction object; perform function feature extraction on the function list of the transaction object to obtain the function feature vector of the transaction object; perform splicing processing on the image feature vector and the function feature vector to obtain the multidimensional feature vector of the transaction object, wherein the number of dimensions of the multidimensional feature vector of the transaction object is the sum of the number of dimensions of the image feature vector and the number of dimensions of the function feature vector.

[0106] In this embodiment, analyzing the combined transaction matching degree of multiple transaction objects in the user's shopping cart also includes the following specific steps:

[0107] Obtain the multidimensional feature vectors of all transaction objects in the user's shopping cart;

[0108] Construct the calculation formula of the characteristic difference value within the transaction object combination:

[0109] ;

[0110] Among them, wcv represents the characteristic difference value within the transaction object combination, represents the jth eigenvalue in the multidimensional feature vector of the ith transaction object in the qth transaction object combination, represents the average value of the jth eigenvalue in the multidimensional feature vector of all transaction objects in the qth transaction object combination, Q represents the number of transaction object combinations, m represents the total number of transaction objects in the qth transaction object combination, n represents the number of eigenvalues ​​in the multidimensional feature vector of the ith transaction object in the qth transaction object combination; j is any item from 1 to n, i is any item from 1 to m, and q is any item from 1 to Q;

[0111] Construct the calculation formula of the characteristic difference value between transaction object combinations:

[0112] ;

[0113] Where bcv represents the characteristic difference value between transaction object combinations, Represents the average value of the jth eigenvalue in the multidimensional feature vector of all transaction objects in all transaction object combinations;

[0114] Constructing the objective function ; Where a and b represent the weight coefficient of the characteristic difference within the transaction object combination and the weight coefficient of the characteristic difference between the transaction object combinations respectively;

[0115] Extract multiple sets of transaction object combination sequences generated by multiple random combinations of all transaction objects in the user's shopping cart, where the transaction object combination sequence includes multiple transaction object combinations generated by each random combination, and substitute the multidimensional feature vectors of all transaction objects corresponding to each set of transaction object combination sequence into the calculation formula of the feature difference value within the transaction object combination, the calculation formula of the feature difference value between the transaction object combinations and the objective function , obtaining the transaction object combination sequence corresponding to the maximum value of the objective function J as the combination transaction matching degree analysis result;

[0116] It should be noted that the method for obtaining the weight coefficient of the characteristic difference within the transaction object combination and the weight coefficient of the characteristic difference between the transaction object combinations is as follows: obtaining the multidimensional characteristic vectors of all transaction objects in 5000 groups of user shopping carts, importing them into the objective function J to calculate multiple values ​​of 5000 groups of objective function J, and obtaining the combined transaction matching degree judgment results of all transaction objects in 5000 groups of user shopping carts; importing the multiple values ​​of 5000 groups of objective function J and the combined transaction matching degree judgment results into the fitting software, and outputting the values ​​of the characteristic difference weight coefficient within the transaction object combination and the characteristic difference weight coefficient between the transaction object combinations that meet the highest combined transaction matching degree judgment accuracy;

[0117] Acquire multiple transaction object combinations in the combined transaction matching degree analysis result, and acquire combined attribute data of each transaction object combination, wherein the combined attribute data includes historical transaction evaluation text data, favorable comment rate and price of all transaction objects in the transaction object combination.

[0118] In this embodiment, the transaction priority analysis module is used to analyze the transaction priority of multiple transaction object combinations in the user's shopping cart according to the transaction demand analysis results of the user and the combined attribute data of the multiple transaction object combinations;

[0119] In this embodiment, analyzing the transaction priority of multiple transaction object combinations in the user's shopping cart includes the following specific steps:

[0120] Extract the transaction needs of the user and the combined attribute data of multiple transaction object combinations; import the historical transaction evaluation text data of each transaction object in each transaction object combination into the word frequency analysis model to perform noun word frequency analysis on the historical transaction evaluation of each transaction object, sum up the word frequencies of multiple nouns obtained by the analysis and take the average value, and obtain multiple nouns corresponding to the word frequencies greater than or equal to the average value as the demand characteristics of the corresponding transaction objects; obtain the demand characteristics of all transaction objects in each transaction object combination, and eliminate the repeated demand characteristics in the demand characteristics of all transaction objects in each transaction object combination, and use the demand characteristics of all transaction objects in each transaction object combination after elimination as the demand characteristics of each transaction object combination;

[0121] Substitute the user's transaction demand, the demand characteristics of multiple transaction object combinations and the combination attribute data into the transaction priority index calculation formula to calculate the transaction priority index of each transaction object combination; the transaction priority index calculation formula is:

[0122] ;

[0123] Among them, JYq represents the transaction priority index of the qth transaction object combination, represents the mean of the favorable reviews of all transaction objects in the qth transaction object combination, jx represents the transaction demand of the user, xt represents the demand characteristics of the qth transaction object combination, num() represents the number of elements in the brackets, It means taking the intersection of the user's transaction demand and the demand characteristics of the qth transaction object combination, represents the union of the user's transaction demand and the demand characteristics of the qth transaction object combination, Pq represents the mean of the sum of the prices of all transaction objects in the qth transaction object combination, It represents the mean of the sum of the prices of all transaction objects in all transaction object combinations.

[0124] In this embodiment, the optimal transaction object combination recommendation module is used to recommend the optimal transaction object combination to the user according to the transaction priority analysis result; specifically, it includes the following contents:

[0125] The transaction object combination corresponding to the maximum value of the transaction priority index of all transaction object combinations calculated is obtained and recommended to the user as the optimal transaction object combination.

[0126] The above-mentioned parameters and steps for each unit module to implement corresponding functions in a transaction management system based on interaction of multiple transaction objects of the present invention can refer to the parameters and steps in the embodiment of a transaction management method based on interaction of multiple transaction objects above, and will not be repeated here.

[0127] Example 3

[0128] An electronic device according to an embodiment of the present invention comprises: a processor and a memory, wherein the memory stores a computer program that can be called by the processor, and the processor executes a transaction management method based on the interaction of multiple transaction objects by calling the computer program stored in the memory. It should be noted that: all computer programs of the transaction management method based on the interaction of multiple transaction objects are implemented in C language, wherein the data acquisition module, the transaction demand analysis module, the combination transaction matching analysis module, the transaction priority analysis module, the optimal transaction object combination recommendation module and the control module are all controlled by a remote server.

[0129] Example 4

[0130] This embodiment provides a computer-readable storage medium having a rewritable computer program stored thereon;

[0131] When the computer program runs on a computer device, the computer device executes the above-mentioned transaction management method based on interaction of multiple transaction objects.

[0132] Each embodiment of the present invention is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the IoT device and medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0133] The system and medium provided in the embodiments of the present invention correspond one-to-one to the method, and therefore, the system and medium also have similar beneficial technical effects to the corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the system and medium will not be repeated here.

[0134] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0135] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0136] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0137] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0138] Memory may include non-permanent storage in a computer-readable medium, in the form of random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0139] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0140] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0141] The above are only embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent substitution, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of the claims of the present invention.

Claims

1. A transaction management method based on multi-transaction object interaction, characterized in that: The steps include: S1. Obtain feature data and function data of multiple transaction objects in the user's shopping cart, and simultaneously obtain the user's transaction demand data; S2. Importing the transaction demand data into the transaction demand analysis model of the transaction object to analyze the transaction demand of the user; S3, importing the characteristic data and function data of multiple transaction objects into the transaction object combination transaction matching degree analysis model to analyze the combination transaction matching degree of multiple transaction objects in the user's shopping cart, and obtaining multiple transaction object combinations according to the combination transaction matching degree analysis results, and obtaining the combination attribute data of the multiple transaction object combinations; S4. Analyzing the transaction priority of multiple transaction object combinations in the user's shopping cart according to the transaction demand analysis results of the user and the combined attribute data of multiple transaction object combinations; S5. Recommend the best transaction object combination to the user based on the transaction priority analysis results; The step S3 comprises the following specific steps: S31, extracting feature data and function data of multiple transaction objects in the user's shopping cart, wherein the feature data includes a transaction object image of the transaction object; and the function data includes a function list of the transaction object extracted from a preset transaction object database; S32, extracting image features from the transaction object image to obtain an image feature vector of the transaction object; extracting function features from the function list of the transaction object to obtain a function feature vector of the transaction object; concatenating the image feature vector and the function feature vector to obtain a multidimensional feature vector of the transaction object, wherein the number of dimensions of the multidimensional feature vector of the transaction object is the sum of the number of dimensions of the image feature vector and the number of dimensions of the function feature vector; The step S3 also includes the following specific steps: S33, obtaining a multidimensional feature vector of all transaction objects in the user's shopping cart; S34. According to step S33, a calculation formula for the characteristic difference value within the transaction object combination is constructed: ； Among them, wcv represents the characteristic difference value within the transaction object combination, represents the jth eigenvalue in the multidimensional feature vector of the ith transaction object in the qth transaction object combination, represents the average value of the jth eigenvalue in the multidimensional feature vector of all transaction objects in the qth transaction object combination, Q represents the number of transaction object combinations, m represents the total number of transaction objects in the qth transaction object combination, n represents the number of eigenvalues ​​in the multidimensional feature vector of the ith transaction object in the qth transaction object combination; j is any item from 1 to n, i is any item from 1 to m, and q is any item from 1 to Q; S35. According to step S33, a calculation formula for the characteristic difference value between transaction object combinations is constructed: ； Where bcv represents the characteristic difference value between transaction object combinations, Represents the average value of the jth eigenvalue in the multidimensional feature vector of all transaction objects in all transaction object combinations; S36. Constructing the objective function ; Where a and b represent the weight coefficient of the characteristic difference within the transaction object combination and the weight coefficient of the characteristic difference between the transaction object combinations respectively; S37, extracting multiple groups of transaction object combination sequences generated by multiple random combinations of all transaction objects in the user's shopping cart, wherein the transaction object combination sequence includes multiple transaction object combinations generated by each random combination, substituting the multidimensional feature vectors of all transaction objects corresponding to each group of transaction object combination sequence into the formula of steps S34-S36, and obtaining the transaction object combination sequence corresponding to the maximum value of the objective function J as the combination transaction matching degree analysis result; S38, obtaining multiple transaction object combinations in the combined transaction matching degree analysis result, and obtaining combined attribute data of each transaction object combination, wherein the combined attribute data includes historical transaction evaluation text data, favorable comment rate and price of all transaction objects in the transaction object combination; The step S4 comprises the following specific steps: S41, extracting the combined attribute data of the user's transaction demand and multiple transaction object combinations; importing the historical transaction evaluation text data of each transaction object in each transaction object combination into the word frequency analysis model to perform noun word frequency analysis on the historical transaction evaluation of each transaction object, summing up the word frequencies of multiple nouns obtained by the analysis and taking the average value, obtaining multiple nouns corresponding to the word frequencies greater than or equal to the average value as the demand characteristics of the corresponding transaction objects; obtaining the demand characteristics of all transaction objects in each transaction object combination, and eliminating the repeated demand characteristics in the demand characteristics of all transaction objects in each transaction object combination, and using the demand characteristics of all transaction objects in each transaction object combination after elimination as the demand characteristics of each transaction object combination; S42. Substitute the transaction demand of the user, the demand characteristics of multiple transaction object combinations, and the combination attribute data into the transaction priority index calculation formula to calculate the transaction priority index of each transaction object combination; the transaction priority index calculation formula is: ； Among them, JYq represents the transaction priority index of the qth transaction object combination, represents the mean of the favorable reviews of all transaction objects in the qth transaction object combination, jx represents the transaction demand of the user, xt represents the demand characteristics of the qth transaction object combination, num() represents the number of elements in the brackets, It represents the intersection of the user's transaction demand and the demand characteristics of the qth transaction object combination. represents the union of the user's transaction demand and the demand characteristics of the qth transaction object combination, Pq represents the mean of the sum of the prices of all transaction objects in the qth transaction object combination, It represents the mean of the sum of the prices of all transaction objects in all transaction object combinations.

2. A transaction management method based on multi-transaction object interaction according to claim 1, characterized in that: The step S2 comprises the following specific steps: S21, extracting the transaction demand data of the user, wherein the transaction demand data includes the evaluation text data of the user on the historical transaction objects and the transaction object type data in the user's shopping cart; S22, obtaining the user's evaluation text data on multiple historical transaction objects of the same type as the transaction object in the shopping cart, importing the evaluation text data of the multiple historical transaction objects into the word frequency analysis model, performing noun word frequency analysis on the evaluation text data of the multiple historical transaction objects, summing up the word frequencies of the multiple nouns obtained by the analysis and taking an average value, and obtaining multiple nouns corresponding to word frequencies greater than or equal to the average value as the user's transaction demand for the transaction object in the shopping cart; S23. Obtain the user's transaction demand for all transaction objects in the shopping cart, and use the intersection of the user's transaction demand for all transaction objects in the shopping cart as the user's transaction demand.

3. A transaction management method based on multi-transaction object interaction according to claim 1, characterized in that: The step S5 includes the following specific contents: The transaction object combination corresponding to the maximum value of the transaction priority index of all transaction object combinations calculated is obtained and recommended to the user as the optimal transaction object combination.

4. A transaction management system based on the interaction of multiple transaction objects, which is implemented based on a transaction management method based on the interaction of multiple transaction objects according to any one of claims 1 to 3, characterized in that: The system comprises: The data acquisition module is used to obtain the characteristic data and functional data of multiple transaction objects in the user's shopping cart, and at the same time obtain the user's transaction demand data; The transaction demand analysis module is used to import the transaction demand data into the transaction object transaction demand analysis model to analyze the user's transaction demand; A combination transaction matching analysis module is used to import the characteristic data and function data of multiple transaction objects into the transaction object combination transaction matching degree analysis model to analyze the combination transaction matching degree of multiple transaction objects in the user's shopping cart, obtain multiple transaction object combinations according to the combination transaction matching degree analysis results, and obtain the combination attribute data of the multiple transaction object combinations; A transaction priority analysis module is used to analyze the transaction priority of multiple transaction object combinations in the user's shopping cart based on the user's transaction demand analysis results and the combined attribute data of multiple transaction object combinations; The optimal transaction object combination recommendation module is used to recommend the optimal transaction object combination to the user based on the transaction priority analysis results; A control module is used to control the operation of the data acquisition module, the transaction demand analysis module, the combination transaction matching analysis module, the transaction priority analysis module and the optimal transaction object combination recommendation module.

5. An electronic device comprising: A processor and a memory, wherein the memory stores a computer program that can be called by the processor; characterized in that the processor executes a transaction management method based on multi-transaction object interaction as described in any one of claims 1 to 3 by calling the computer program stored in the memory.

6. A computer-readable storage medium, characterized in that: Instructions are stored, and when the instructions are executed on a computer, the computer is caused to execute a transaction management method based on interaction of multiple transaction objects as described in any one of claims 1 to 3.

Images