Intelligent recommendation method and system based on big data

Abstract

The application provides a big data-based intelligent recommendation method and system, and relates to the technical field of big data analysis.The method comprises the following steps: collecting user historical behavior data, performing behavior characteristic analysis, and forming user historical characteristic data; collecting historical product data, performing product characteristic analysis, and forming historical product characteristic data; performing collaborative analysis according to the user historical characteristic data and the historical product characteristic data, and forming user-product collaborative characteristic data; obtaining user current behavior data, combining the user-product collaborative characteristic data to perform preference recommendation analysis, and forming user preference recommendation data.The method can reasonably and accurately perform product recommendation analysis.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of big data analysis, in particular to an intelligent recommendation method and system based on big data. BACKGROUND

[0002] With the development of information technology, e-commerce has gradually become the mainstream of product marketing, and users determine whether the product meets the user's needs by obtaining product information on the e-commerce platform.

[0003] At present, product recommendation methods based on user behavior have gradually appeared, but the accuracy and rationality cannot meet the needs of users.

[0004] Therefore, it is an urgent problem to be solved to design an intelligent recommendation method and system based on big data, which can reasonably and accurately analyze product recommendation. SUMMARY

[0005] The purpose of the present application is to provide an intelligent recommendation method based on big data, which extracts corresponding feature information by obtaining historical behavior data of users and related product data, and performs collaborative analysis to establish the feature relationship between products and user behavior. Thus, on the basis of the collaborative features extracted by big data, the user behavior of the same product is related, the feature data information of the same product mapped by different user behaviors is established, and then in subsequent analysis, the product that the user may be interested in can be determined by the current behavior of the user, and a series of most possible product data is provided, achieving the purpose of accurately pushing products. On the one hand, the correlation analysis is performed by using the product feature information of the user and the related user, the product and the user behavior are deeply bound, and on the basis of big data, the different user behavior features of the same product can be fully obtained, thereby providing data reference for the diversification of product positioning, ensuring that the connection between the product and the user behavior is diversified, realizing more flexible and reasonable mapping of the product and the user behavior, and improving the diversity of product recommendation. On the other hand, the data formed after the feature and collaborative analysis can provide more accurate product recommendation data based on behavior for the user, greatly improving the satisfaction of user demand, and being beneficial to the marketing and promotion of products.

[0006] The application also aims to provide an intelligent recommendation system based on big data, which acquires big data for recommendation analysis through a data acquisition unit, and performs a collaborative analysis on user behavior and product information by using a feature analysis unit and a collaborative analysis unit, extracts collaborative feature data of user behavior and product information, thereby completing the analysis of current user behavior on the recommendation analysis unit, determining the product that the user is currently interested in, and providing accurate and reasonable recommendation information. The different functional units coordinate with each other to form a close recommendation analysis system, which is an important material basis for realizing intelligent recommendation.

[0007] In a first aspect, the application provides an intelligent recommendation method based on big data, which comprises: collecting user historical behavior data, performing behavior feature analysis, and forming user historical feature data; collecting historical product data, performing product feature analysis, and forming historical product feature data; performing collaborative analysis according to the user historical feature data and the historical product feature data, and forming user-product collaborative feature data; acquiring user current behavior data, combining the user-product collaborative feature data to perform preference recommendation analysis, and forming user preference recommendation data.

[0008] In the application, the method extracts corresponding feature information by acquiring the historical behavior data of the user and the related product data, and performs collaborative analysis to establish the feature relationship between the product and the user behavior. Thus, the user behavior correlation of the same product is processed on the basis of the collaborative features extracted by big data, the feature data information of the same product mapped by different user behaviors is established, and then the product that the user may pay attention to can be determined by the current behavior of the user in subsequent analysis, and a series of most possible product data are provided to achieve the purpose of accurate product pushing. On the one hand, the correlation analysis is performed by using the user and the product feature information related to the user, the product is deeply bound with the user behavior, and on the basis of big data, the different user behavior features of the same product can be fully acquired, thereby providing data reference for the diversified positioning of the product, ensuring that the connection of the product to the user behavior is diversified, realizing more flexible and reasonable mapping of the product and the user behavior, and improving the diversity of product recommendation. On the other hand, the data formed after the featureization and collaborative analysis can provide more accurate product recommendation data based on behavior for the user, greatly improving the satisfaction of the user demand, and being beneficial to the marketing and promotion of the product.

[0009] As a possible implementation manner, the collection of user historical behavior data, the behavior feature analysis, and the formation of user historical feature data comprise: extracting the behavior data of different products for different users to form different user product historical behavior data; performing parametrization on the different user product historical behavior data to form a corresponding historical product behavior parameter matrix , wherein, , m represents the number of different products, n represents the number of different behavior parameters, , represents the parameter value of the corresponding numbered n behavior parameter of the corresponding numbered m product of the user; different historical product behavior parameter matrices of different users , the corresponding historical product behavior parameter normalization matrix is formed after normalization processing ; all historical product behavior parameter normalization matrices of different users are collected , user historical feature data is formed.

[0010] In the present application, the products concerned by different users are different, and even in the same period, different users also exist simultaneously concerned with multiple products, and in order to reasonably obtain the recommended content for the user for the product, it is necessary to cluster the data as the data extraction and screening condition of the user and the product, so that the data information obtained can have obvious pertinence to the specific user and the specific product. Of course, most of the data are original record data, which need to be reasonably extracted for feature information to ensure that the data obtained are representative for the specific user and product, and at the same time, the extracted feature information can be reasonably statistically analyzed in subsequent analysis to improve the data processing ability and more accurately reflect the user's attention to the product. It should be noted that the parameterization of the data information of the product corresponding to different users can be extracted from different latitudes, including but not limited to the browsing time of the product corresponding content, the average browsing speed, the browsing click volume of the product, the number of purchases, the number of collections and attentions, the browsing frequency, etc. Of course, it should be noted that in order to ensure that the parameterized data extracted on different products of different users can be compared horizontally, the determined parameters need to be uniform on different users and different products, that is, the parameter types in the established parameter matrix have a one-to-one correspondence between different users and different products. Of course, considering that the extracted parameters do not necessarily have the natural limits of minimum and maximum values, therefore, after obtaining the parameter matrix, it is necessary to reasonably normalize the parameter matrix to facilitate subsequent comparative analysis. The parameter extraction and the establishment of one-to-one correspondence of the parameter matrix can be reasonably extracted and analyzed by means of AI, which can greatly improve the efficiency of data collection and processing.

[0011] As a possible implementation manner, the different historical product behavior parameter matrices of different users are normalized to form corresponding historical product behavior parameter normalization matrices , including: for the same product, according to the historical product behavior parameter matrices of different users, the maximum parameter value of each behavior parameter corresponding to the behavior parameter is determined and the behavior parameter minimum parameter value ; the historical product behavior parameter matrix of different users under the same product Each behavior parameter is normalized to determine the corresponding behavior parameter normalization parameter value , wherein ; the different parameter matrices , the normalization parameter values of different behavior parameters are collected to form a behavior parameter normalization matrix .

[0012] In the present application, the parameter values of the parameters are normalized, the purpose is to ensure that the parameter values of all parameters have a unified numerical measurement basis, so that the comparison of the parameters has the consistency and rationality, ensures the correctness and rationality of the analysis, at the same time, the maximum value and the minimum value are used as the reference benchmark for normalization, which can also eliminate the dimension, and the data consistency between different parameters can also be achieved, which makes the analysis of the correlation more reasonable and effective. The maximum value and the minimum value of each parameter can be obtained by comparing and analyzing the parameter values of the same parameter in the parameter matrix corresponding to different users under the same product.

[0013] As a possible implementation manner, historical product data is collected, product characterization analysis is performed, and historical product feature data is formed, including: according to the historical product data, product historical information of different products is extracted; according to different product historical information, parameterization is performed to form corresponding product information parameter matrix , wherein , i represents the number of different product parameters, represents the parameter value of the product parameter corresponding to the product numbered i of the product numbered m; different product information parameter matrices are normalized to form corresponding product information parameter normalization matrix ; different product information parameter normalization matrices are collected to form historical product feature data.

[0014] In the present application, the extraction of feature data of the product is mainly to obtain the product information that the user is concerned about, including but not limited to product price, product shelf life, product weight, product volume, product arrival date, etc. As long as the information that affects the customer's demand for product use can be extracted as feature information. However, it should be noted that the product yield corresponding to different products should be consistent in the type of parameter, so that different products have a horizontal comparison in subsequent feature analysis, thereby improving the rationality and accuracy of product recommendation content analysis. Of course, after obtaining the feature data, since the parameter values of different product yields do not necessarily have a reasonable range limit, data planning processing is needed to ensure the horizontal comparability of the data. The normalization processing of the product yield is convenient for the user to normalize the behavior data of different products. The normalization processing of the product yield is mainly to determine the level of the product parameter value in all products. This normalized data also provides a reasonable reference for the specific positioning of different products. Similarly, the extraction and establishment of the matching parameter matrix of the product parameter data can be efficiently and accurately analyzed and processed by AI.

[0015] As a possible implementation, the different product information parameter matrices are normalized to form corresponding product information parameter normalized matrices , including: determining the maximum parameter value and the minimum parameter value of the product parameter in the different product information parameter matrices ; normalizing each product parameter in the different product information parameter matrices to determine the corresponding product parameter normalized parameter value , wherein ; and collecting the product parameter normalized parameter values of the different product parameters corresponding to the different product information parameter matrices to form the product information parameter normalized matrix .

[0016] In the present application, the normalization processing of product parameters is to determine the maximum value and the minimum value of the unified parameters in different product parameter matrices, and to obtain the corresponding normalized parameters by taking the maximum value and the minimum value as the limit value of the parameter value. It should be noted here that the normalization matrix established for different products is essentially different in that the parameter values in the matrix are different. For example, different prices of the same product are considered as different products because their corresponding normalized matrix parameter values are different. The same and different division of products based on planning parameters is exactly matched with the same product concerned by different users in essence. After all, the parameter values of the quantities considered by different users are different.

[0017] As a possible implementation, the collaborative analysis according to the user historical feature data and the historical product feature data forms user-product collaborative feature data, including: taking different products in historical product feature data as a benchmark, clustering different historical product behavior parameter normalization matrices corresponding to the same product in user historical feature data , forming a product clustering behavior parameter matrix set corresponding to different products; performing collaborative analysis on the different product clustering behavior parameter matrix set and the corresponding product information parameter normalization matrix , forming product corresponding user-product collaborative information; collecting different user-product collaborative information to form user-product collaborative feature data.

[0018] In the present application, user behavior can only be reasonably data collaborative when it is associated with the behavior object product, so the premise of collaborative analysis is to cluster all behavior data associated with the product. Collaborative analysis mainly analyzes the features of quantified behavior data based on numerical analysis to obtain the relationship between behavior characteristics and products in numerical value. Clustering the parameter data of user behavior and the parameter information of products can be efficiently and accurately processed and analyzed by AI.

[0019] As a possible implementation, the collaborative analysis of the different product clustering behavior parameter matrix set and the corresponding product information parameter normalization matrix forms product corresponding user-product collaborative information, including: comparing the parameter total number in the product information parameter normalization matrix and the historical product behavior parameter normalization matrix , and taking the larger parameter total number as the variable total number of the multi-dimensional coordinate system to be established; performing parameter expansion with unit quantity as parameter value for fixed station of all matrices with smaller parameter total number, so that the parameter total number of all matrices is consistent with the variable total number of the multi-dimensional coordinate system, forming different expanded historical product behavior parameter normalization matrices and expanded product information parameter normalization matrices , u represents the product clustering behavior parameter matrix of different historical product behavior parameter normalized matrix , k represents the different historical product behavior parameter normalized matrix The number of different parameters after dimension expansion, r represents the product information parameter normalized matrix The number of different parameters after dimension expansion, and the maximum number of r is equal to the maximum number of k;The product information parameter normalized matrix after dimension expansion And different historical product behavior parameter normalized matrix after dimension expansion Mapping in the same multidimensional coordinate system, the collaborative envelope range is extracted with the product information parameter normalized matrix after dimension expansion As the center, and the corresponding user-product collaborative information is formed.

[0020] In the present application, for the same product information, the collaborative analysis of all user behavior information after clustering mainly considers two aspects, the first aspect is to perform matrix-based data collaborative analysis on product information and user behavior information, which needs to ensure consistency in matrix dimension. After all, inconsistent matrix parameter quantity requires more complex data processing, and the data processing quantity is very large for big data analysis. Therefore, the same matrix parameter quantity is necessary, which can reduce the difficulty of data processing and improve the efficiency of analysis on the basis of ensuring the rationality and accuracy of analysis. Here, the most parameter number matrix is considered as the reference for the expansion of the matrix with less parameter number. Of course, the matrix with more parameter number can also be reduced in dimension based on the matrix with less parameter number, but dimension reduction will increase the analysis difficulty, so the expansion method is preferred. If the parameter number of the product information parameter matrix is large, the parameter number of the corresponding product behavior parameter matrix needs to be expanded to the same number as the parameter number of the product information parameter matrix. It should be noted that the position of the expanded parameter in the matrix is unchanged. Since all parameters are percentage data, it is reasonable to use the unit value 1 as the supplementary value. Similarly, if the parameter number of the product behavior parameter matrix is large, the parameter number of the corresponding product information parameter matrix needs to be expanded to the same number as the parameter number of the product behavior parameter matrix. The position of the expanded parameter is also filled with the unit value 1. After completing the consistency expansion processing of the matrix dimension, the matrix data can be converted into a coordinate system for collaborative correlation analysis to obtain collaborative feature data.

[0021] As a possible implementation, the product information parameter normalized matrix after dimension expansion And different historical product behavior parameter normalized matrix after dimension expansion Mapping in the same multidimensional coordinate system, the collaborative envelope range is extracted with the product information parameter normalized matrix after dimension expansion The center-based synergy envelope range extraction forms corresponding user-product synergy information, including: normalizing different extended historical product behavior parameter matrices , determining effective synergy distance and effective synergy angle between the extended product information parameter normalized matrix and the extended product behavior parameter normalized matrix , wherein, , represents the extended historical product behavior parameter normalized matrix numbered u , the extended product behavior parameter normalized parameter value numbered k, represents the extended product information parameter normalized parameter value numbered r and corresponding to the extended product behavior parameter normalized parameter value numbered k, , represents the direction vector from the coordinate point to the coordinate point in the multi-dimensional coordinate system, represents the unit vector composed of each variable value taking 1 in the multi-dimensional coordinate system, represents the angle between two direction vectors and ; according to different effective synergy angles , the effective synergy angle range is determined, and the fitting based on the angle value is carried out according to different effective synergy distances within the effective synergy angle range , forming user-product synergy information , wherein, .

[0022] In the present application, the extraction of the collaborative envelope range features centered on the product information parameter matrix after the extension mainly involves two aspects. One aspect is what kind of characteristic relationship exists between the product information and the user behavior parameter data in the numerical information. The present application can use the coordinate system to spatialize and establish the vector relationship after the data matrix. The vector relationship includes the vector modulus relationship and the vector angle relationship. The vector modulus relationship is decisive, while the vector angle relationship is relative. The relative relationship is absolute by establishing the relationship with the unit vector, which can guarantee the uniformity and the analyzable contrast of the angle relationship. The vector modulus and the angle relationship clearly, accurately and reasonably reflect the characteristic relationship between the behavior information and the product information. The second aspect considers the relationship between the behavior information and the product information marked by the big data. Although the relationship is discrete data, it basically covers the range of the characteristic relationship. Therefore, the present application clearly defines the variation rule of the vector modulus of the behavior information in the range based on the big data by fitting the vector modulus with the angle value change in the range determined by the vector angle, and accurately and reasonably expresses the collaborative characteristic information between the product information and the behavior information.

[0023] As a possible implementation manner, the user current behavior data is acquired, the preference recommendation analysis is performed in combination with the user-product collaborative characteristic data, and the user preference recommendation data is formed. The method comprises the following steps: according to the user current behavior data, the current product behavior information corresponding to different products is extracted respectively, and the parameter normalization and the extension processing are performed, so as to form the product corresponding current product behavior extension normalized matrix; the product information corresponding to the current product behavior extension normalized matrix is acquired, the parameter normalization and the extension processing are performed, so as to form the corresponding current product extension normalized matrix; according to the current product behavior extension normalized matrix and the corresponding current product extension normalized matrix, the current effective collaborative angle and the current effective collaborative distance are determined; and the following manner of preference recommendation analysis is performed according to the user-product collaborative information matched with the current product: the current effective collaborative angle is compared with the corresponding effective collaborative angle range ; if does not belong to , the corresponding product is not recommended; if belongs to , the following steps are performed: according to the user-product collaborative information , the current effective collaborative angle is determined; the corresponding formula effective collaborative distance is determined; if is less than , the corresponding product is not recommended; if is not less than If yes, the corresponding product is recommended.

[0024] In the present application, the main purpose of the preference recommendation analysis of the current behavior of the user by using the collaborative feature data is to determine whether the modulus and angle relationship between the behavior information and the product information belongs to the range of the corresponding collaborative feature clamp. Of course, first, it is determined whether the range belongs to the corresponding clamp range, and when it belongs, it is further determined whether it belongs to the modulus range of the mapping. Only when the modulus and angle conditions are met, it can be determined that the user is interested in the product, and the product can be provided as a recommended product to the user to provide more product-related advertisements and other corresponding content.

[0025] In the second aspect, the present application provides an intelligent recommendation system based on big data, comprising: a data acquisition unit for acquiring user historical behavior data, user historical product data and user current behavior data; a feature analysis unit for performing feature analysis on the user historical behavior data acquired by the data acquisition unit to form user historical feature data, and performing product feature analysis on the user historical product data to form user historical product feature data; a collaborative analysis unit for performing collaborative analysis on the user historical feature data and the user historical product feature data formed by the feature analysis unit to form user-product collaborative feature data; and a recommendation analysis unit for performing preference recommendation analysis on the user current behavior data acquired by the data acquisition unit in combination with the user-product collaborative feature data formed by the collaborative analysis unit to form user preference recommendation data.

[0026] In the present application, the system acquires big data for recommendation analysis by the data acquisition unit, and performs collaborative analysis on the user behavior and product information by using the feature analysis unit and the collaborative analysis unit, extracts the collaborative feature data of the user behavior and the product information, thereby completing the analysis of the current user behavior on the recommendation analysis unit, determining the product currently interested by the user, and providing accurate and reasonable recommendation information. The different functional units are coordinated with each other to form a close recommendation analysis system, which is an important material basis for realizing intelligent recommendation.

[0027] The intelligent recommendation method and system based on big data provided by the present application have the following beneficial effects:

[0028] The method extracts corresponding feature information by obtaining historical behavior data of the user and product data related to the user, and performs collaborative analysis to establish the feature relationship between the product and the user behavior. Thus, on the basis of the collaborative features extracted by the big data, the user behavior of the same product is related, the feature data information of the same product mapped by different user behaviors is established, and then in the subsequent analysis, the product that the user may be interested in can be determined by the current behavior of the user, and a series of most possible product data is provided, so as to achieve the purpose of accurately pushing the product. On the one hand, the correlation analysis is performed by using the user and the product feature information related to the user, the product and the user behavior are deeply bound, and on the basis of the big data, the different user behavior features of the same product can be fully obtained, thereby providing data reference for the diversified positioning of the product, ensuring that the connection of the product to the user behavior is diversified, realizing more flexible and reasonable mapping of the product and the user behavior, and improving the diversity of product recommendation. On the other hand, the data formed after the feature and collaborative analysis can provide more accurate product recommendation data based on the behavior for the user, greatly improving the satisfaction degree of the user demand, and being also beneficial to the marketing and promotion of the product.

[0029] The system obtains the big data for recommendation analysis by the data acquisition unit, and performs collaborative analysis on the user behavior and product information by the feature analysis unit and the collaborative analysis unit, extracts the collaborative feature data of the user behavior and the product information, thereby completing the analysis of the current user behavior on the recommendation analysis unit, determining the product that the user is currently interested in, and providing accurate and reasonable recommendation information. The different functional units are coordinated with each other to form a close recommendation analysis system, which is an important material basis for realizing intelligent recommendation. BRIEF DESCRIPTION OF DRAWINGS

[0030] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments of the present application. It should be understood that the following drawings only show some embodiments of the present application, and therefore should not be regarded as a limitation to the scope. For those skilled in the art, other related drawings can also be obtained without creative labor on the basis of these drawings.

[0031] Fig. 1 The step diagram of the intelligent recommendation method based on big data provided by the embodiments of the present application is provided.

[0032] Fig. 2 The structure schematic diagram of the intelligent recommendation system based on big data provided by the embodiments of the present application is provided. DETAILED DESCRIPTION

[0033] The technical solutions in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application.

[0034] With the development of information technology, e-commerce gradually becomes the mainstream of product marketing, and users determine whether the product meets the needs of the user by obtaining product information on the e-commerce platform.

[0035] At present, product recommendation methods based on user behavior are gradually emerging, but the accuracy and rationality cannot meet the needs of users.

[0036] Reference Figs. 1-2 The embodiment of the application provides an intelligent recommendation method based on big data, which extracts corresponding feature information by obtaining historical behavior data of users and related product data, and performs collaborative analysis to establish the feature relationship between products and user behavior. Thus, on the basis of the collaborative features extracted by big data, the user behavior related to the same product is processed, the feature data information of the same product mapped by different user behaviors is established, and then in subsequent analysis, the product that the user may be interested in can be determined by the current behavior of the user, and a series of most possible product data is provided, so as to achieve the purpose of accurately pushing products. On the one hand, the correlation analysis is performed by using the product feature information related to the user and the user, the product and the user behavior are deeply bound, and on the basis of big data, the different user behavior features of the same product can be fully obtained, thereby providing data reference for diversified positioning of the product, ensuring that the connection of the product to the user behavior is diversified, realizing more flexible and reasonable mapping of the product and the user behavior, and improving the diversity of product recommendation. On the other hand, the data formed after the featureization and collaborative analysis can provide more accurate product recommendation data based on behavior for the user, greatly improve the satisfaction degree of the user demand, and also be beneficial to the marketing and promotion of the product.

[0037] The intelligent recommendation method based on big data specifically includes the following steps:

[0038] S1: collecting user historical behavior data, performing behavior feature analysis, and forming user historical feature data.

[0039] Collecting user historical behavior data, performing behavior feature analysis, and forming user historical feature data include: extracting behavior data for different products for different users to form different user product historical behavior data; and parameterizing different user product historical behavior data to form corresponding historical product behavior parameter matrix , wherein m represents the number of different products, n represents the number of different behavior parameters, represents the parameter value of the behavior parameter corresponding to the number n of the user under the product corresponding to the number m; and different historical product behavior parameter matrices of different users Normalization processing is performed to form a corresponding historical product behavior parameter normalized matrix ; all historical product behavior parameter normalized matrices of different users are collected to form user historical feature data.

[0040] The products of interest of different users are different, and even in the same period, different users have simultaneous interest in multiple products. In order to reasonably obtain recommended content for users for products, both users and products need to be used as data extraction and screening conditions for data clustering. Only in this way can the data information obtained have obvious pertinence to specific users and specific products. Of course, most of the data are original record data, and reasonable feature information extraction is needed to ensure that the data obtained are representative of specific users and products, and the extracted feature information can be reasonably statistically analyzed in subsequent analysis to improve the data processing capability and more accurately reflect the user's interest in the product. It should be noted that the parameterization of data information corresponding to different products of different users can be extracted from different latitudes, including but not limited to the browsing time of the content corresponding to the product, the average browsing speed, the browsing click volume of the product, the number of purchases, the number of collections and attentions, the browsing frequency, etc. Of course, it should be noted that in order to ensure that the parameterized data extracted on different products of different users can be compared horizontally, the determined parameters need to be unified on different users and different products, that is, the parameter types in the established parameter matrix have a one-to-one correspondence between different users and different products. Of course, considering that the extracted parameters do not necessarily have the natural limits of minimum and maximum values, after obtaining the parameter matrix, reasonable normalization processing of the parameter matrix is needed to facilitate subsequent comparative analysis. The parameter extraction and the establishment of a one-to-one corresponding parameter matrix can be reasonably extracted and analyzed by means of AI, which can greatly improve the efficiency of data collection and processing.

[0041] Different historical product behavior parameter matrices of different users Normalization processing is performed to form a corresponding historical product behavior parameter normalized matrix , including: for the same product, according to the historical product behavior parameter matrix of different users , determining the behavior parameter maximum parameter value and the behavior parameter minimum parameter value of each behavior parameter; for each behavior parameter in the historical product behavior parameter matrix of different users under the same product , normalization processing is performed to determine the corresponding behavior parameter normalized parameter value , wherein ; different parameter matrices The normalized parameter values of different behavior parameters corresponding to the set form a behavior parameter normalized matrix .

[0042] The parameter values of the parameters are normalized, which aims to ensure that the parameter values of all parameters have a unified numerical measurement basis, so that the comparison of the parameters has comparability and rationality, ensuring the correctness and rationality of the analysis, and taking the maximum value and the minimum value as the reference benchmark for normalization, which can also eliminate the dimension, achieve data consistency between different parameters, and make the analysis of the correlation more reasonable and effective. The maximum value and the minimum value of each parameter can be obtained by comparing and analyzing the parameter values of the same parameter in the parameter matrix corresponding to different users of the same product.

[0043] S2: Collect historical product data and perform product characteristic analysis to form historical product characteristic data.

[0044] Collecting historical product data and performing product characteristic analysis to form historical product characteristic data includes: extracting product historical information of different products according to historical product data; parameterizing according to different product historical information to form corresponding product information parameter matrix , wherein i represents the number of different product parameters, represents the parameter value of the product parameter numbered i corresponding to the product numbered m; different product information parameter matrices are normalized to form corresponding product information parameter normalized matrices ; different product information parameter normalized matrices are collected to form historical product characteristic data.

[0045] Extracting product feature data primarily involves acquiring product information that users care about, including but not limited to product price, shelf life, weight, volume, and delivery date. Any information that influences customer needs regarding product usage can be extracted as feature information. However, it's important to note that the product output for different products should be consistent in terms of parameter type. This ensures horizontal comparability across products in subsequent feature analysis, improving the rationality and accuracy of product recommendation content analysis. After acquiring feature data, since the parameter values ​​for different product outputs may not have reasonable ranges, data planning and processing are necessary to ensure horizontal comparability. Normalization of product output should facilitate the normalization of user behavior data for different products. Normalization primarily determines the product's parameter value's position within all products. This normalized data provides a reasonable reference for the specific positioning of different products. Similarly, the extraction of product parameter data and the establishment of matching parameter matrices can be achieved efficiently and accurately through AI analysis.

[0046] For different product information parameter matrices Normalization is performed to form the corresponding product information parameter normalization matrix. This includes: determining the information parameter matrix for different products based on different product parameters. Maximum parameter value of product parameters and minimum parameter value of product parameters For different product information parameter matrices Each product parameter in the data is normalized to determine the corresponding normalized parameter value. ,in, For different product information parameter matrices The product information parameter normalization matrix is ​​formed by collecting the normalized parameter values ​​of different product parameters. .

[0047] The normalization processing of product parameters is to determine the maximum value and the minimum value of the unified parameters in different product parameter matrices, and to obtain the corresponding normalized parameters by taking the maximum value and the minimum value as the limit value of the parameter value. It should be noted here that the normalization matrix established for different products is essentially distinguished by the different parameter values in the matrix, such as different prices of the same product, which is also considered as different products because their corresponding normalized matrix parameter values are different. The same and different division of products based on planning parameters is exactly matched with the same product concerned by different users in essence, because the parameter values of the quantities considered by different users are different.

[0048] S3: Collaborative analysis according to user historical feature data and historical product feature data to form user-product collaborative feature data.

[0049] Collaborative analysis according to user historical feature data and historical product feature data to form user-product collaborative feature data, including: taking different products in historical product feature data as a reference, clustering the same product corresponding different historical product behavior parameter normalization matrix in user historical feature data , forming a product clustering behavior parameter matrix set corresponding to different products; collaborative analysis of different product clustering behavior parameter matrix set with corresponding product information parameter normalization matrix to form product corresponding user-product collaborative information; collection of different user-product collaborative information to form user-product collaborative feature data.

[0050] User behavior can only be reasonably data collaborative when it is associated with the behavior object product, so the premise of collaborative analysis is to cluster all behavior data associated with the product. Collaborative analysis mainly analyzes the features of quantitative behavior data based on numerical analysis to obtain the relationship between behavior characteristics and product in numerical value. Clustering the parameter data of user behavior with the parameter information of the product can be efficiently and accurately processed and analyzed by AI.

[0051] Collaborative analysis of different product clustering behavior parameter matrix set with corresponding product information parameter normalization matrix to form product corresponding user-product collaborative information, including: comparing the total number of parameters in product information parameter normalization matrix and historical product behavior parameter normalization matrix , and taking the larger total number of parameters as the total number of variables of the multi-dimensional coordinate system to be established; all matrices with smaller total number of parameters are expanded in fixed position with unit quantity as parameter value, so that the total number of parameters of all matrices is consistent with the total number of variables of the multi-dimensional coordinate system, forming different expanded historical product behavior parameter normalization matrix and the product information parameter matrix after dimension expansion , u represents the product cluster behavior parameter matrix, and different historical product behavior parameter matrices are normalized , k represents different historical product behavior parameter matrices the number of different parameters after dimension expansion, and r represents the product information parameter matrix the number of different parameters after dimension expansion, and the maximum number of r is equal to the maximum number of k; the product information parameter matrix after dimension expansion and different historical product behavior parameter matrices after dimension expansion are mapped in the same multi-dimensional coordinate system, and the product information parameter matrix after dimension expansion is taken as the center to extract the collaborative envelope range, forming the corresponding user-product collaborative information.

[0052] For the same product information, after clustering all user behavior information, the collaborative analysis mainly considers two aspects: first, the product information and user behavior information are analyzed collaboratively based on matrix data, which requires consistency in matrix dimensions. After all, inconsistent matrix parameters require more complex data processing, and the amount of data processing is very large for big data analysis. Therefore, the same matrix parameter quantity is necessary to reduce the difficulty of data processing and improve the efficiency of analysis on the basis of ensuring the rationality and accuracy of the analysis. Here, the matrix with the most parameters is taken as the reference to expand the matrix with fewer parameters. Of course, the matrix with fewer parameters can also be taken as the reference to reduce the dimension of the matrix with more parameters, but reducing the dimension will increase the analysis difficulty, so the expansion method is preferred. If the number of product information parameter matrix parameters is large, the number of corresponding product behavior parameter matrix parameters needs to be expanded to the same number as the product information parameter matrix. It should be noted that the expanded parameters need to remain in the same position in the matrix. Since all parameters are percentage data, it is reasonable to use a unit value of 1 as a supplementary value. Similarly, if the number of product behavior parameter matrix parameters is large, the number of corresponding product information parameter matrix parameters needs to be expanded to the same number as the product behavior parameter matrix. The position of the expanded parameter is also filled with a unit value of 1. After completing the consistency expansion of the matrix dimensions, the matrix data can be converted to a coordinate system for collaborative correlation analysis to obtain collaborative feature data.

[0053] the product information parameter matrix after dimension expansion and different historical product behavior parameter matrices after dimension expansion are mapped in the same multi-dimensional coordinate system, and the product information parameter matrix after dimension expansion The center of the synergy envelope range extraction, the corresponding user-product synergy information is formed, including: the different expansion of the historical product behavior parameter matrix , determine the effective synergy distance and effective synergy angle between the expansion of the product information parameter matrix , , The expansion of the historical product behavior parameter matrix numbered u The expansion of the product behavior parameter matrix numbered k The expansion of the product information parameter matrix numbered r corresponding to the expansion of the product behavior parameter matrix numbered k The direction vector from the coordinate point to the coordinate point in the multi-dimensional coordinate system, The unit vector composed of each variable value taking 1 in the multi-dimensional coordinate system, The angle between two direction vectors and ; according to the different effective synergy angle , the effective synergy angle range is determined, and the fitting based on the angle value is carried out according to the different effective synergy distance in the effective synergy angle range , and the user-product synergy information is formed, wherein .

[0054] The center of the synergy envelope range extraction, the corresponding user-product synergy information is formed, including: the different expansion of the historical product behavior parameter matrix , determine the effective synergy distance and effective synergy angle between the expansion of the product information parameter matrix , , The expansion of the historical product behavior parameter matrix numbered u The expansion of the product behavior parameter matrix numbered k The expansion of the product information parameter matrix numbered r corresponding to the expansion of the product behavior parameter matrix numbered k The direction vector from the coordinate point to the coordinate point in the multi-dimensional coordinate system, The unit vector composed of each variable value taking 1 in the multi-dimensional coordinate system, The angle between two direction vectors and ; according to the different effective synergy angle , the effective synergy angle range is determined, and the fitting based on the angle value is carried out according to the different effective synergy distance in the effective synergy angle range , and the user-product synergy information is formed, wherein .

[0054] The center of the synergy envelope range extraction, the corresponding user-product synergy information is formed, including: the different expansion of the historical product behavior parameter matrix , determine the effective synergy distance and effective synergy angle between the expansion of the product information parameter matrix , , The expansion of the historical product behavior parameter matrix numbered u The expansion of the product behavior parameter matrix numbered k The expansion of the product information parameter matrix numbered r corresponding to the expansion of the product behavior parameter matrix numbered k The direction vector from the coordinate point to the coordinate point in the multi-dimensional coordinate system, The unit vector composed of each variable value taking 1 in the multi-dimensional coordinate system, The angle between two direction vectors and ; according to the different effective synergy angle , the effective synergy angle range is determined, and the fitting based on the angle value is carried out according to the different effective synergy distance in the effective synergy angle range , and the user-product synergy information is formed, wherein .

[0054] The center of the synergy envelope range extraction, the corresponding user-product synergy information is formed, including: the different expansion of the historical product behavior parameter matrix , determine the effective synergy distance and effective synergy angle between the expansion of the product information parameter matrix , , The expansion of the historical product behavior parameter matrix numbered u The expansion of the product behavior parameter matrix numbered k The expansion of the product information parameter matrix numbered r corresponding to the expansion of the product behavior parameter matrix numbered k The direction vector from the coordinate point to the coordinate point in the multi-dimensional coordinate system, The unit vector composed of each variable value taking 1 in the multi-dimensional coordinate system, The angle between two direction vectors and ; according to the different effective synergy angle , the effective synergy angle range is determined, and the fitting based on the angle value is carried out according to the different effective synergy distance in the effective synergy angle range , and the user-product synergy information is formed, wherein .

[0054] The center of the synergy envelope range extraction, the corresponding user-product synergy information is formed, including: the different expansion of the historical product behavior parameter matrix , determine the effective synergy distance and effective synergy angle between the expansion of the product information parameter matrix , , The expansion of the historical product behavior parameter matrix numbered u The expansion of the product behavior parameter matrix numbered k The expansion of the product information parameter matrix numbered r corresponding to the expansion of the product behavior parameter matrix numbered k The direction vector from the coordinate point to the coordinate point in the multi-dimensional coordinate system, The unit vector composed of each variable value taking 1 in the multi-dimensional coordinate system, The angle between two direction vectors and ; according to the different effective synergy angle , the effective synergy angle range is determined, and the fitting based on the angle value is carried out according to the different effective synergy distance in the effective synergy angle range , and the user-product synergy information is formed, wherein .

[0054] The center of the synergy envelope range extraction, the corresponding user-product synergy information is formed, including: the different expansion of the historical product behavior parameter matrix , determine the effective synergy distance and effective synergy angle between the expansion of the product information parameter matrix , , The expansion of the historical product behavior parameter matrix numbered u The expansion of the product behavior parameter matrix numbered k The expansion of the product information parameter matrix numbered r corresponding to the expansion of the product behavior parameter matrix numbered k The direction vector from the coordinate point to the coordinate point in the multi-dimensional coordinate system, The unit vector composed of each variable value taking 1 in the multi-dimensional coordinate system, The angle between two direction vectors and ; according to the different effective synergy angle , the effective synergy angle range is determined, and the fitting based on the angle value is carried out according to the different effective synergy distance in the effective synergy angle range , and the user-product synergy information is formed, wherein .

[0054] The center of the synergy envelope range extraction, the corresponding user-product synergy information is formed, including: the different expansion of the historical product behavior parameter matrix , determine the effective synergy distance and effective synergy angle between the expansion of the product information parameter matrix , , The expansion of the historical product behavior parameter matrix numbered u The expansion of the product behavior parameter matrix numbered k <000025

[0055] S4: Obtain the user's current behavior data, combine the user-product collaborative feature data to conduct preference recommendation analysis, and form user preference recommendation data.

[0056] Obtaining the user's current behavior data, combining the user-product collaborative feature data to conduct preference recommendation analysis, and forming user preference recommendation data, comprising: according to the user's current behavior data, extracting the current product behavior information corresponding to different products respectively, and conducting parameter normalization and dimension expansion processing to form the current product behavior expansion normalized matrix corresponding to the product; obtaining the product information corresponding to the current product behavior expansion normalized matrix, and conducting parameter normalization and dimension expansion processing to form the corresponding current product expansion normalized matrix; according to the current product behavior expansion normalized matrix and the corresponding current product expansion normalized matrix, determining the current effective collaborative angle and the current effective collaborative distance , and according to the user-product collaborative information matched with the current product , the following way of preference recommendation analysis is conducted: comparing the current effective collaborative angle with the corresponding effective collaborative angle range , if does not belong to , the corresponding product is not recommended; if belongs to , then: according to the user-product collaborative information , the current effective collaborative angle corresponding formula effective collaborative distance is determined, if is less than , the corresponding product is not recommended, if is not less than , the corresponding product is recommended.

[0057] The main purpose of using collaborative feature data to conduct preference recommendation analysis on the user's current behavior is to determine whether the modulus and angle relationship between the behavior information and the product information in the numerical vectorization belongs to the range of the corresponding collaborative feature clamp. Of course, first of all, it is judged whether the range belongs to the corresponding clamping range, and then it is confirmed whether it belongs to the modulus range of the mapping. Only when the modulus and angle conditions are met at the same time can it be determined that the user is interested in the product, and the product can be provided as a recommended product to the user to provide more product-related advertisements and other corresponding content.

[0058] The application further provides an intelligent recommendation system based on big data, which comprises: a data acquisition unit configured to acquire user historical behavior data, user historical product data and user current behavior data; a feature analysis unit configured to perform feature analysis on the user historical behavior data acquired by the data acquisition unit to form user historical feature data, and perform product feature analysis on the user historical product data to form user historical product feature data; a collaborative analysis unit configured to perform collaborative analysis on the user historical feature data and the user historical product feature data formed by the feature analysis unit to form user-product collaborative feature data; and a recommendation analysis unit configured to perform preference recommendation analysis on the user current behavior data acquired by the data acquisition unit in combination with the user-product collaborative feature data formed by the collaborative analysis unit to form user preference recommendation data.

[0059] The system acquires big data for recommendation analysis by the data acquisition unit, and performs collaborative analysis on user behavior and product information by the feature analysis unit and the collaborative analysis unit, extracts collaborative feature data of user behavior and product information, thereby completing analysis on current user behavior on the recommendation analysis unit, determining products currently interested by the user, and providing accurate and reasonable recommendation information. The different functional units are coordinated with each other to form a close recommendation analysis system, which is an important material basis for realizing intelligent recommendation.

[0060] In summary, the intelligent recommendation method and system based on big data provided by the embodiments of the application have the following advantages:

[0061] The method extracts corresponding feature information from the historical behavior data of the user and the related product data, performs collaborative analysis to establish the feature relationship between the product and the user behavior, and then performs user behavior correlation processing on the same product based on the collaborative features extracted from the big data, thereby establishing feature data information of the same product mapped by different user behaviors, and determining the product that may be interested by the user according to the current behavior of the user in subsequent analysis, and then providing a series of most possible product data, so as to achieve the purpose of accurately pushing the product. On the one hand, the feature information of the user and the related product is used for correlation analysis, the product is deeply bound with the user behavior, and on the basis of big data, different user behavior features of the same product can be fully acquired, thereby providing data reference for diversified positioning of the product, ensuring that the product is associated with various user behaviors, realizing more flexible and reasonable mapping of the product and the user behavior, and improving the diversity of product recommendation. On the other hand, the data formed after the feature analysis and the collaborative analysis can provide more accurate product recommendation data based on the behavior for the user, greatly improve the satisfaction degree of the user demand, and also be beneficial to marketing and promotion of the product.

[0062] In the embodiments of the present application, the indication can include direct indication and indirect indication, and can also include explicit indication and implicit indication. The information indicated by certain information is referred to as to-be-indicated information. In the implementation process, there are many ways to indicate the to-be-indicated information, for example, but not limited to, the to-be-indicated information can be directly indicated, such as the to-be-indicated information itself or an index of the to-be-indicated information. The to-be-indicated information can also be indirectly indicated by indicating other information, where the other information and the to-be-indicated information have an association relationship. The to-be-indicated information can also be indicated only by a part of the to-be-indicated information, and the other part of the to-be-indicated information is known or agreed in advance. For example, the indication of a specific information can also be achieved by means of the arrangement order of various information agreed in advance (for example, specified by a protocol), thereby reducing the indication overhead to a certain extent. Meanwhile, a common part of various information can be identified and uniformly indicated, so as to reduce the indication overhead caused by separately indicating the same information.

[0063] In addition, the specific indication manner can also be various existing indication manners, for example, but not limited to, the above indication manners and various combinations thereof. The specific details of various indication manners can refer to the prior art, and will not be described herein. As known from the above, for example, when multiple information of the same type needs to be indicated, the indication manners of different information can be different. In the implementation process, the required indication manner can be selected according to the specific needs, and the selected indication manner is not limited in the embodiments of the present application. In this way, the indication manner involved in the embodiments of the present application should be understood as covering various methods that can enable the to-be-indicated party to know the to-be-indicated information.

[0064] It should be understood that the to-be-indicated information can be sent as a whole, or can be divided into multiple sub-information and sent separately, and the sending period and / or sending occasion of the sub-information can be the same or different. The specific sending method is not limited in the embodiments of the present application. The sending period and / or sending occasion of the sub-information can be pre-defined, for example, pre-defined according to a protocol, or configured by the sending end device by sending configuration information to the receiving end device.

[0065] The "pre-definition" or "pre-configuration" can be implemented by pre-saving corresponding codes, tables or other methods that can be used to indicate related information in the device, and the specific implementation manner is not limited in the embodiments of the present application. The "saving" can mean saving in one or more memories. The one or more memories can be separately set, or integrated in the encoder or decoder, processor, or communication device. The one or more memories can be partially separately set and partially integrated in the decoder, processor, or communication device. The type of the memory can be any form of storage medium, and the present application is not limited thereto.

[0066] The "protocol" referred to in the embodiments of the present application can refer to a protocol family in the communication field, a standard protocol similar to the protocol family frame structure, or a related protocol applied to a future communication system, and the embodiments of the present application do not make specific limitations thereon.

[0067] In the embodiments of the present application, "when", "in the case of", "if", and the like all refer to the device making corresponding processing under certain objective conditions, and are not limited to time, and do not require the device to have a judgment action when implemented, nor does it mean that there are other limitations.

[0068] In the description of the embodiments of the present application, unless otherwise specified, " / " represents that the objects before and after the " / " are in an "or" relationship, for example, A / B can represent A or B; "and / or" in the embodiments of the present application is only a description of the association relationship of the associated objects, and represents that there can be three relationships, for example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone, where A and B can be singular or plural. In addition, in the description of the embodiments of the present application, unless otherwise specified, "multiple" refers to two or more than two. "At least one of the following" or the like refers to any combination of these items, including any combination of single item or multiple items. For example, at least one of a, b, or c can represent: a, b, c, a-b, a-c, b-c, or a-b-c, where a, b, and c can be single or multiple. In addition, in order to clearly describe the technical solutions of the embodiments of the present application, in the embodiments of the present application, "first", "second", and the like are used to distinguish the same items or similar items with basically the same function and role. Those skilled in the art can understand that "first", "second", and the like do not limit the quantity and execution order, and "first", "second", and the like do not necessarily mean different. At the same time, in the embodiments of the present application, "exemplary" or "for example" is used to represent as an example, illustration, or description. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as more preferred or more advantageous than other embodiments or design schemes. Rather, "exemplary" or "for example" is used to present the relevant concept in a specific manner, and is convenient for understanding.

[0069] It should be appreciated that a processor in the embodiments of the present application can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can be any conventional processor.

[0070] It should also be understood that the memory in the embodiments of the present application can be a volatile memory or a nonvolatile memory, or can include both volatile and nonvolatile memory. The nonvolatile memory can be a read-only memory (ROM), programmable ROM (PROM), erasable PROM (EPROM), electrically EPROM (EEPROM) or flash memory. The volatile memory can be a random access memory (RAM) used as an external cache. By way of example, and not limitation, many forms of random access memory (RAM) can be used, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchlink DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0071] The above-described embodiments can be implemented in whole or in part by software, hardware (such as a circuit), firmware, or any combination thereof. When implemented in software, the above-described embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are wholly or partially generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center through a wired (such as infrared, wireless, microwave, etc.) manner. The computer-readable storage medium can be any available medium accessible by a computer or a data storage device such as a server, data center, etc. containing one or more available medium collections. The available medium can be a magnetic medium (such as a floppy disk, a hard disk, a magnetic tape), an optical medium (such as a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state disk.

[0072] It should be understood that the term "and / or" herein merely describes an association relationship of associated objects, which means that there can be three relationships, for example, A and / or B can represent three cases of A alone, A and B together, and B alone, where A and B can be singular or plural. In addition, the character " / " herein generally represents an "or" relationship between the front and rear associated objects, but can also represent an "and / or" relationship, which can be understood in the context before and after.

[0073] In this application, "at least one" means one or more, and "multiple" means two or more. "At least one of the following" or similar expressions means any combination of these items, including any combination of single or multiple items. For example, at least one of a, b, or c can mean a, b, c, a-b, a-c, b-c, or a-b-c, where a, b, and c can be single or multiple.

[0074] It should be understood that in various embodiments of the present application, the size of the sequence number of the above-described processes does not mean the order of execution, and the execution order of the processes should be determined by their functions and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0075] Those skilled in the art can clearly understand that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0076] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working processes of the above-described system, device and unit can refer to the corresponding processes in the foregoing method embodiments, which will not be repeated here.

[0077] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other ways. For example, the above-described device embodiments are only schematic, for example, the division of the units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interface, device or unit, and can be electrical, mechanical or other forms.

[0078] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on a plurality of network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0079] In addition, each functional unit in each embodiment of the present application can be integrated into a processing unit, or each unit can exist physically independently, or two or more units can be integrated into one unit.

[0080] If the functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application or the parts of the technical solutions that essentially contribute to the prior art or the parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0081] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A big data-based intelligent recommendation method, characterized in that, include: Collect users' historical behavior data, perform behavioral feature analysis, and form users' historical feature data; Collect historical product data, conduct product feature analysis, and form historical product feature data; Based on the user's historical feature data and the historical product feature data, a collaborative analysis is performed to form user-product collaborative feature data; Acquire current user behavior data and combine it with the user-product collaborative feature data to perform preference recommendation analysis, thereby forming user preference recommendation data; The process of collecting historical user behavior data, performing behavioral feature analysis, and forming historical user feature data includes: For different users, behavioral data for different products is extracted to form different user product historical behavior data; The historical behavior data of different users are parametrically quantified to form a corresponding historical product behavior parameter matrix. ,in, , m represents the product number, and n represents the parameter number of different behaviors. This represents the parameter value of the action parameter with ID n under the product with ID m for the user. Different historical product behavior parameter matrices for different users Normalization is performed to form a corresponding historical product behavior parameter normalization matrix. ; A normalized matrix of all historical product behavior parameters for different users This forms the user's historical feature data; The process of collecting historical product data, performing product feature analysis, and forming historical product feature data includes: Based on the historical product data, extract the product history information for different products; Based on the different historical information of the products, parameters are quantified to form a corresponding product information parameter matrix. ,in, , where i represents the number of different product parameters. This represents the parameter value of the product parameter corresponding to product number i, which is product number m. Based on different products in the historical product feature data, cluster the normalization matrix of different historical product behavior parameters corresponding to the same product in the user's historical feature data. This forms a set of product clustering behavior parameter matrices corresponding to different products; For different sets of product clustering behavior parameter matrices, perform corresponding product information parameter normalization matrix operations. Collaborative analysis is used to generate user-product collaborative information corresponding to the product; By aggregating the different user-product collaboration information, the user-product collaboration feature data is formed. The product information parameter normalization matrix is ​​then applied to different sets of product clustering behavior parameter matrices. The collaborative analysis generates user-product collaborative information corresponding to the product, including: Compare the product information parameter normalization matrix and the historical product behavior parameter normalization matrix The total number of parameters in the system is used, and the larger total number of parameters is taken as the total number of variables in the multidimensional coordinate system to be established. For all matrices with a small total number of parameters, parameter expansion is performed using unit values ​​at fixed positions to ensure that the total number of parameters in all matrices matches the total number of variables in the multidimensional coordinate system, thus forming different expanded historical product behavior parameter normalization matrices. And the normalized matrix of product information parameters after dimensional expansion u represents the normalization matrix of different historical product behavior parameters in the product clustering behavior parameter matrix set. k represents the normalization matrix of the behavior parameters of different historical products. The numbering of different parameters after dimension expansion, where r represents the normalization matrix of the product information parameters. The numbering of different parameters after dimension expansion, and the maximum number of numbers for r is equal to the maximum number of numbers for k; The normalization matrix of the expanded product information parameters And the normalized matrix of historical product behavior parameters after dimensional expansion as described above. Mapped within the same multidimensional coordinate system, the product information parameter normalization matrix after dimensional expansion is used. The collaborative envelope range centered on the user is extracted to form corresponding user-product collaborative information.

2. The intelligent recommendation method based on big data according to claim 1, characterized in that, The parameter matrix for different historical product behaviors of different users Normalization is performed to form a corresponding historical product behavior parameter normalization matrix. ,include: For the same product, based on the historical product behavior parameter matrix of different users Determine the maximum parameter value of each behavior parameter. and minimum parameter value of behavior parameters ; The historical product behavior parameter matrix for different users under the same product Each behavior parameter is normalized to determine the corresponding behavior parameter normalization parameter value. ,in, ; For different parameter matrices The normalized parameter values ​​of the corresponding different behavioral parameters are used to form the behavioral parameter normalization matrix. ; The set of different product information parameter normalization matrices This forms the historical product feature data.

3. The intelligent recommendation method based on big data according to claim 1, characterized in that, The parameter matrix of different product information Normalization is performed to form the corresponding product information parameter normalization matrix. ,include: For different product parameters, determine the product information parameter matrix for different product parameters. Maximum parameter value of product parameters and minimum parameter value of product parameters ; For different product information parameter matrices Each product parameter in the data is normalized to determine the corresponding normalized parameter value. ,in, ; For different product information parameter matrices The product information parameter normalization matrix is ​​formed by collecting the normalized parameter values ​​of the corresponding different product parameters. .

4. The intelligent recommendation method based on big data according to claim 1, characterized in that, The normalization matrix of the expanded product information parameters is then used. And the normalized matrix of historical product behavior parameters after dimensional expansion as described above. Mapped within the same multidimensional coordinate system, the product information parameter normalization matrix after dimensional expansion is used. The collaborative envelope range centered on the user is extracted to form corresponding user-product collaborative information, including: Normalization matrix of historical product behavior parameters after dimensional expansion for different dimensions The normalized matrix of product information parameters after the dimension expansion is determined. Effective collaborative distance between and effective collaboration perspective ,in, , The expanded-dimensional historical product behavior parameter normalization matrix, numbered u, represents the matrix. The normalized parameter value of the expanded product behavior parameter with dimension number k in the middle. This represents the normalized parameter value of the expanded product information parameter corresponding to the normalized parameter value of the expanded product behavior parameter with the number r and the number k. This indicates that in a multidimensional coordinate system, coordinates are represented by points. To coordinate point directional vector, This represents the unit vector synthesized by each variable taking the value 1 in a multidimensional coordinate system. Represents two direction vectors and The included angle; According to different effective synergy perspectives Determine the effective range of collaborative angles And within the effective cooperative angle range The effective coordination distance varies depending on the specific circumstances. The user-product collaborative information is generated by fitting angle values. ,in, .

5. The intelligent recommendation method based on big data according to claim 4, characterized in that, The process of acquiring current user behavior data and combining it with user-product collaborative feature data to perform preference recommendation analysis to form user preference recommendation data includes: Based on the user's current behavior data, extract the current product behavior information for different products, and perform parameter normalization and dimension expansion processing to form a dimension-expanded normalized matrix of the current product behavior for each product. Obtain the product information corresponding to the current product behavior dimension-expanded normalization matrix, and perform parameter normalization and dimension expansion processing to form the corresponding current product dimension-expanded normalization matrix; Based on the current product behavior dimension-expanded normalized matrix and the corresponding current product dimension-expanded normalized matrix, the current effective collaboration angle is determined. and current effective collaborative distance And based on the user-product collaboration information matched with the current product. The following preference recommendation analysis methods were performed: Comparison of the current effective collaborative perspectives and the corresponding effective range of collaborative angles ,like Not belonging to If not, then no product will be recommended or labeled accordingly; like belong ,but: Based on the user-product collaboration information Determine the current effective collaborative angle The corresponding formula is the effective collaborative distance. ,like Less than If so, no product will be recommended or labeled accordingly. Not less than Then, the corresponding products will be recommended and calibrated.

6. A big data-based intelligent recommendation system, employing the big data-based intelligent recommendation method according to any one of claims 1-5, characterized in that, include: The data acquisition unit is used to collect user historical behavior data, user historical product data, and user current behavior data. The feature analysis unit is used to perform feature analysis on the user historical behavior data collected by the data acquisition unit to form user historical feature data, and to perform product feature analysis on the user historical product data to form user historical product feature data. The collaborative analysis unit is used to perform collaborative analysis based on the user historical feature data and user historical product feature data formed by the feature analysis unit to form user-product collaborative feature data. The recommendation analysis unit is used to perform preference recommendation analysis based on the user's current behavior data collected by the data collection unit and the user-product collaborative feature data formed by the collaborative analysis unit, thereby forming user preference recommendation data.

Images