Commercial data mining method and device, electronic equipment and product

Abstract

The invention discloses a business data mining method and device, electronic equipment and a product, and the method comprises the steps: carrying out the mining processing of user preference features based on the attributes of a commodity, and obtaining the preference commodity features of a user; then, based on the preference commodity features, first user data mining processing is carried out, and first commercial mining data of the user is obtained; then, performing second user data mining processing in combination with the personal information and historical behavior data of the user to obtain second commercial mining data of the user; then, on the basis of the data, the optimal commercial mining data of the user can be obtained; and finally, on the basis, the personalized recommendation service of the user can be completed. Therefore, when data mining is carried out, feedback data does not need to be displayed depending on user scores and the like, so that compared with a traditional technology, the effectiveness of data mining can be greatly improved, and effective personalized recommendation of commodities can be realized.

Description

Technical Field

[0001] The present invention belongs to the technical field of data mining, and in particular relates to a commercial data mining method, device, electronic equipment and product. Background Art

[0002] With the continuous development of the Internet, online sales have become one of the main sales methods for many companies. When users browse Web sites online, product recommendations have become a major promotion method for companies. Among them, the most widely used personalized recommendation algorithms are: content-based personalized recommendation, collaborative filtering personalized recommendation, and Web log-based personalized recommendation. The above recommendation methods can provide customers with personalized recommendation services, which can not only improve the company's sales performance, but also greatly improve the user experience.

[0003] At present, the recommendation method based on collaborative filtering (CF) is one of the most widely used recommendation methods. It mainly uses display feedback such as rating data to mine user business data to obtain user preferences, interests, purchasing tendencies, etc.; so far, many researchers have conducted in-depth research on collaborative filtering recommendation methods based on user data mining from various aspects, and have also achieved some remarkable results; however, the traditional user data mining method based on collaborative filtering has the following shortcomings: it is necessary to rely on display feedback data such as user ratings to mine user data, but this display feedback data is often unclear. Therefore, in the absence of display feedback data, user data cannot be effectively mined, and thus effective recommendations cannot be made; therefore, based on the aforementioned shortcomings, how to provide a data mining method that does not rely on display feedback data and can achieve effective mining of user business data has become a problem that needs to be solved urgently. Summary of the invention

[0004] The purpose of the present invention is to provide a commercial data mining method, device, electronic device and product to solve the problem in the prior art that when display feedback data is missing, user data cannot be effectively mined and effective recommendations cannot be made.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions:

[0006] In a first aspect, a commercial data mining method is provided, comprising:

[0007] Obtain the target user’s personal information and historical behavior data on the e-commerce platform;

[0008] Based on the historical behavior data, determining the purchase commodity data of the target user;

[0009] According to the purchase commodity data of the target user, a preference feature mining process is performed on the target user, so as to obtain the preferred commodity features of the target user after the preference feature mining process;

[0010] Using the preferred commodity characteristics of the target user, first user data mining processing is performed on the target user to obtain first commercial mining data of the target user, wherein the first commercial mining data includes a plurality of first similar users having similar preferred commodity characteristics as the target user and first user data corresponding to each first similar user;

[0011] Based on the historical behavior data and the personal information, performing second user data mining processing on the target user to obtain second business mining data of the target user, wherein the second business mining data includes a number of second similar users having similar personal information and behavior data to the target user and second user data corresponding to each second similar user;

[0012] The optimal business mining data of the target user is generated based on the first business mining data and the second business mining data, so as to make personalized commodity recommendations for the target user by using the optimal business mining data.

[0013] Based on the above disclosed content, the present invention first obtains the personal information of the target user and its historical behavior data on the e-commerce platform; then, based on the historical behavior data, the target user's purchase product data is determined, and based on this, the user preference feature mining process is performed to obtain the target user's preferred product characteristics; then, based on the preferred product characteristics, the first data mining process of the target user is performed to obtain the first business mining data containing the first similar user with similar preferred product characteristics as the target user and the corresponding user data; then, the historical behavior data and personal information are used to perform the second data mining process to obtain the second business mining data containing the second similar user with similar personal information and behavior data as the target user and the corresponding user data; finally, based on the aforementioned first and second business mining data, the optimal business mining data of the target user can be obtained; in this way, the optimal business mining data can be used to complete the personalized product recommendation for the target user.

[0014] Through the above design, when the present invention conducts user data mining, it conducts mining processing of user preference characteristics based on the attributes of the goods themselves, so as to obtain the user's preferred product characteristics; then, based on the preferred product characteristics, it conducts first user data mining processing to obtain first commercial mining data related to the user's preference characteristics; then, it combines the user's own personal information and historical behavior data to conduct second user data mining processing to obtain second commercial mining data related to the user's personal information and historical behavior; then, based on the aforementioned first commercial mining data and second commercial mining data, the user's optimal commercial mining data can be obtained; finally, the user's personalized recommendation service can be completed based on the optimal commercial mining data; in this way, the present invention can complete the effective mining of user data based on the goods purchased by the user, personal information and historical behavior, without relying on display feedback data such as user ratings. Therefore, compared with traditional technologies, the effectiveness of data mining can be greatly improved, thereby achieving effective personalized recommendation of goods, and thus, it is very suitable for large-scale application and promotion.

[0015] In a possible design, based on the purchase commodity data of the target user, a preference feature mining process is performed on the target user, so as to obtain the preferred commodity features of the target user after the preference feature mining process, including:

[0016] Based on the purchase commodity data of the target user, generating a commodity attribute set corresponding to the purchase commodity data;

[0017] For the i-th commodity attribute in the commodity attribute set, the total number of commodities in the purchased commodity data containing the i-th commodity attribute is counted as the attribute influence value corresponding to the i-th commodity attribute;

[0018] According to the attribute influence value corresponding to the i-th commodity attribute and in accordance with the following formula (1), the importance of the i-th commodity attribute to the target user is calculated;

[0019]

[0020] In the above formula (1), P i represents the importance of the i-th product attribute to the target user, Y i represents the attribute impact value of the i-th commodity attribute, Y m represents the attribute influence value of the mth commodity attribute, and n represents the total number of commodity attributes in the commodity attribute set;

[0021] i is incremented by 1, and the number of commodities in the purchased commodity data that contain the i-th commodity attribute is recounted until i is equal to n, and the importance of each commodity attribute to the target user is obtained, wherein the initial value of i is 1;

[0022] According to the importance of each commodity attribute to the target user, several commodity attributes are selected from the commodity attribute set to serve as the preferred commodity features of the target user.

[0023] In a possible design, the number of the target user's preferred product features is multiple, wherein the target user's preferred product features are used to perform first user data mining processing on the target user to obtain the target user's first commercial mining data, including:

[0024] Filtering a number of initial similar users corresponding to the target user from a user database of the e-commerce platform;

[0025] Determining, based on the plurality of initial similar users, a feature weight of each of the preferred product features of the target user;

[0026] Calculate a first similarity between the target user and each user in the user database by using a plurality of preferred product features of the target user and a feature weight of each preferred product feature;

[0027] According to the first similarity between the target user and each user, determining a plurality of first similar users corresponding to the target user from the user database;

[0028] The first user data of each first similar user is obtained, and each first similar user and the first user data of each first similar user are used to form the first business mining data.

[0029] In a possible design, determining the feature weight of each of the preferred product features of the target user according to the plurality of initial similar users includes:

[0030] Determine any product from the historical purchase products corresponding to each initial similar user as a test product;

[0031] Performing multiple initialization processing on the feature weights of each preferred product feature, so that after each initialization processing, an initial weight vector is formed using the initialized feature weights of each preferred product feature;

[0032] Using the initial weight vector obtained in each initialization process, multiple individual particles are generated, wherein each individual particle corresponds to an initial position vector and an initial velocity vector, and the initial position vector of any individual particle corresponds to an initial weight vector;

[0033] Initialize the number of iterations t to 1, and obtain the position vector and velocity vector of each particle individual at the t-th iteration, wherein when t is 1, the position vector and velocity vector of any particle individual at the t-th iteration are the initial position vector and initial velocity vector of any particle individual;

[0034] According to a number of initial similar users and the position vectors of each particle individual at the t-th iteration, the fitness of each particle individual at the t-th iteration is calculated, wherein the fitness of any particle individual at the t-th iteration is used to characterize the error of the target user's purchase probability of the test product calculated using the position vector of any particle individual at the t-th iteration;

[0035] Based on the fitness of each particle individual at the tth iteration, the global optimal position and the individual optimal position of each particle individual are updated, wherein the global optimal position is the position vector corresponding to the particle individual with the smallest fitness during the 1st to tth iterations;

[0036] Determine whether an iteration stop condition is met, wherein the iteration stop condition is that the fitness of the particle individual corresponding to the updated global optimal position is less than the fitness threshold, or t reaches the maximum number of iterations;

[0037] If not, then use the updated global optimal position and the updated individual optimal position of each individual particle to update the velocity vector of each individual particle at the tth iteration to obtain the updated velocity vector corresponding to each individual particle, and use the updated velocity vector corresponding to each individual particle to update the position vector of each individual particle to obtain the updated position vector corresponding to each individual particle;

[0038] Add 1 to t, replace the position vector and velocity vector of each particle individual at the tth iteration with the corresponding updated position vector and updated velocity vector, and recalculate the fitness of each particle individual at the tth iteration based on several initial similar users and the position vector of each particle individual at the tth iteration until the iteration stop condition is met, so as to determine the feature weights of each preferred product feature according to the global optimal position that meets the iteration stop condition.

[0039] In a possible design, the fitness of each individual particle at the tth iteration is calculated based on a number of initial similar users and the position vector of each individual particle at the tth iteration, including:

[0040] For any individual particle, according to the position vector of the individual particle at the t-th iteration, determine the weight vector of the individual particle at the t-th iteration;

[0041] According to the preferred product features of the target user and the weight vector of any particle individual at the tth iteration, the real similarity between the target user and each initial similar user is calculated according to the following formula (2);

[0042]

[0043] In the above formula (2), S(K,a) represents the true similarity between the target user K and the ath initial similar user among several initial similar users. is the feature weight of the jth preferred product feature in the weight vector of any particle individual at the tth iteration, represents the importance of the jth preferred product feature to the target user, represents the importance of the jth preferred product feature to the ath initial similar user, R represents the total number of preferred product features, where a=1,2,...,A, and A represents the total number of initial similar users;

[0044] Based on the real similarity between the target user and each initial similar user, and according to the following formula (3), the probability of the target user purchasing the test product is calculated when the weight vector corresponding to any particle individual is used as the feature weight of the preferred product feature;

[0045]

[0046] In the above formula (3), G represents the purchase probability of the target user for the test product, and U(a) represents whether the a-th initial similar user has purchased the test product. If the a-th initial similar user has purchased the test product, U(a) is 1, otherwise, U(a) is -1.

[0047] According to the purchase probability of the target user for the test product, and in accordance with the following formula (4), the fitness of any particle individual at the tth iteration is calculated;

[0048] D t =|GU(K)| (4)

[0049] In the above formula (4), D t represents the fitness of any particle individual at the tth iteration, and U(K) represents whether the target user has purchased the test product. If the target user has purchased the test product, U(K) is 1, otherwise, U(K) is -1.

[0050] In a possible design, based on the historical behavior data and the personal information, a second user data mining process is performed on the target user to obtain the second commercial mining data of the target user, including:

[0051] Obtain personal information and historical behavior data of each user in the user database of the e-commerce platform;

[0052] Calculate the similarity between the personal information of the target user and the personal information of each user in the user database according to the personal information of the target user and the personal information of each user;

[0053] Based on the historical behavior data of the target user and the historical behavior data of each user, calculating the behavior similarity between the target user and each user in the user database;

[0054] Calculate the second similarity between the target user and each user in the user database based on the similarity of personal information and behavior between the target user and each user in the user database;

[0055] Determining a plurality of second similar users corresponding to the target user from the user database according to the second similarity between the target user and each user;

[0056] The second user data of each second similar user is obtained, and the second business mining data is formed by using each second similar user and the second user data of each second similar user.

[0057] In a possible design, based on the historical behavior data of the target user and the historical behavior data of each user, the behavior similarity between the target user and each user in the user database is calculated, including:

[0058] Determining a behavior category set of the target user based on the historical behavior data of the target user;

[0059] For any user in the user database, counting the number of behaviors of each type of behaviors in the behavior category set generated by the any user on the e-commerce platform;

[0060] Based on the number of behaviors of each type of behavior in the behavior type set generated by any user on the e-commerce platform, and according to the following formula (5), the behavior similarity between the target user and any user is calculated;

[0061]

[0062] In the above formula (5), Q(K,b) represents the behavior similarity between the target user and any of the users. Indicates the number of x-type behaviors generated by the target user on the e-commerce platform, represents the number of x-th type behaviors generated by any user on the e-commerce platform, and X represents the total number of behavior categories in the behavior category set.

[0063] In a second aspect, a commercial data mining device is provided, comprising:

[0064] An acquisition unit, used to acquire the target user's personal information and the target user's historical behavior data on the e-commerce platform;

[0065] The acquisition unit is further used to determine the purchase commodity data of the target user based on the historical behavior data;

[0066] A commodity feature mining unit, configured to perform a preference feature mining process on the target user according to the commodity purchase data of the target user, so as to obtain the preferred commodity features of the target user after the preference feature mining process;

[0067] A commercial data mining unit, configured to perform first user data mining processing on the target user by using the preferred commodity characteristics of the target user to obtain first commercial mining data of the target user, wherein the first commercial mining data includes a plurality of first similar users having similar preferred commodity characteristics as the target user and first user data corresponding to each of the first similar users;

[0068] A business data mining unit, configured to perform a second user data mining process on the target user based on the historical behavior data and the personal information to obtain second business mining data of the target user, wherein the second business mining data includes a plurality of second similar users having similar personal information and behavior data to the target user and second user data corresponding to each second similar user;

[0069] The business data mining unit is further used to generate optimal business mining data for the target user based on the first business mining data and the second business mining data, so as to use the optimal business mining data to make personalized product recommendations for the target user.

[0070] In the third aspect, another commercial data mining device is provided. Taking the device as an electronic device as an example, the device includes a memory, a processor and a transceiver which are communicatively connected in sequence, wherein the memory is used to store computer programs, the transceiver is used to send and receive messages, and the processor is used to read the computer program to execute the commercial data mining method as described in the first aspect or any possible design of the first aspect.

[0071] In a fourth aspect, a storage medium is provided, on which instructions are stored. When the instructions are executed on a computer, the commercial data mining method as described in the first aspect or any possible design of the first aspect is executed.

[0072] In a fifth aspect, a computer program product comprising instructions is provided, which, when executed on a computer, causes the computer to execute the commercial data mining method as described in the first aspect or any possible design of the first aspect.

[0073] Beneficial effects:

[0074] (1) When performing user data mining, the present invention conducts mining processing of user preference characteristics based on the attributes of the product itself, thereby obtaining the user's preferred product characteristics; then, based on the preferred product characteristics, a first user data mining process is performed to obtain first commercial mining data related to the user's preference characteristics; then, in combination with the user's own personal information and historical behavior data, a second user data mining process is performed to obtain second commercial mining data related to the user's personal information and historical behavior; then, based on the aforementioned first commercial mining data and second commercial mining data, the user's optimal commercial mining data can be obtained; finally, the user's personalized recommendation service can be completed based on the optimal commercial mining data; in this way, the present invention can complete the effective mining of user data based on the user's purchased products, personal information and historical behavior, without relying on display feedback data such as user ratings. Therefore, compared with traditional technologies, the effectiveness of data mining can be greatly improved, thereby enabling effective personalized recommendation of products, and thus, it is very suitable for large-scale application and promotion. BRIEF DESCRIPTION OF THE DRAWINGS

[0075] Figure 1 A schematic diagram of the steps of the commercial data mining method provided by an embodiment of the present invention;

[0076] Figure 2 A schematic diagram of the structure of a commercial data mining device provided by an embodiment of the present invention;

[0077] Figure 3 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0078] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the present invention will be briefly introduced below in combination with the drawings and the description of the embodiments or the prior art. Obviously, the following description of the structure of the drawings is only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. It should be noted that the description of these embodiments is used to help understand the present invention, but does not constitute a limitation of the present invention.

[0079] It should be understood that although the terms first, second, etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are only used to distinguish one unit from another unit. For example, a first unit can be referred to as a second unit, and similarly, a second unit can be referred to as a first unit without departing from the scope of the exemplary embodiments of the present invention.

[0080] It should be understood that the term "and / or" that may appear in this article is merely a description of the association relationship between associated objects, indicating that three relationships may exist. For example, A and / or B can represent three situations: A exists alone, B exists alone, and A and B exist at the same time. The term " / and" that may appear in this article describes another type of association object relationship, indicating that two relationships may exist. For example, A / and B can represent two situations: A exists alone, and A and B exist alone. In addition, the character " / " that may appear in this article generally indicates that the previous and next associated objects are in an "or" relationship.

[0081] Example:

[0082] See also Figure 1 As shown, the commercial data mining method provided in this embodiment mines user data based on the attributes of the product itself (such as color, brand, price, type and other attributes), user personal information (such as age, education, gender and other information) and user historical behavior data (such as collection, purchase, browsing and other behaviors), so as to obtain user data with similar preferences, similar personal information and behaviors; then, personalized recommendation services for users can be provided based on this; thus, compared with traditional technologies, when performing data mining, this method does not need to rely on display feedback data such as user ratings, so it can solve the problem of missing display feedback data, thereby greatly improving the effectiveness of data mining, and thus achieving a more effective personalized recommendation effect for products, thus, it is very suitable for large-scale application and promotion; among them, for example, this method can be but not limited to running on the data mining end side, optionally, the data mining end can be but not limited to a personal computer (PC), a tablet computer or a smart phone, it can be understood that the aforementioned execution subject does not constitute a limitation on the embodiments of the present application, and accordingly, the operation steps of this method can be but not limited to the following steps S1 to S6.

[0083] S1. Obtain the target user's personal information and the target user's historical behavior data on the e-commerce platform; in this embodiment, the personal information may include but is not limited to basic information such as the target user's age, gender, and education level, and the historical behavior data refers to various behaviors of the target user on the electronic commodity platform, such as browsing behavior, commodity collection behavior, purchase behavior, adding to shopping cart behavior, etc.; wherein the aforementioned data can be obtained from the operation log of the e-commerce platform, and the historical data of one month can be obtained to obtain the aforementioned historical behavior data.

[0084] After obtaining the target user's personal information and historical behavior data, user data mining can be performed based on this. Among them, this embodiment performs data mining processing from two aspects. On the one hand, based on the attributes of the product itself, the user's preferred product features are mined, and data mining is performed based on this. On the other hand, data mining is performed based on historical behavior data and personal information. Finally, the mining data of the above two aspects are combined to generate the optimal commercial mining data of the target user. Optionally, the mining process of user preferred product features can be but is not limited to the following steps S2 and S3.

[0085] S2. Based on the historical behavior data, the purchase product data of the target user is determined; in the present embodiment, it has been explained above that the historical behavior data contains the purchase behavior, therefore, the purchase behavior data can be screened out from the historical behavior data, and then the purchase product data of the target user can be obtained based on the purchase behavior data; then, the user preference features can be mined based on the purchase product data, and the process can be but is not limited to as shown in the following step S3.

[0086] S3. Based on the purchase data of the target user, the target user's preference feature mining is performed to obtain the target user's preferred product features after the preference feature mining. In the specific implementation, the following steps S31 to S35 may be used, for example but not limited to, to mine the user's preferred product features.

[0087] S31. Based on the purchase commodity data of the target user, generate a commodity attribute set corresponding to the purchase commodity data; in this embodiment, each commodity has corresponding attributes, such as type, brand, price, color, etc. Therefore, this embodiment counts all attributes of the commodities purchased by the target user to obtain the commodity attribute set.

[0088] After obtaining the set of product attributes, the influence value of each product attribute can be determined based on it, so as to subsequently calculate the importance of each product attribute to the target user based on the influence value of the product attribute; wherein, the process of determining the influence value of the product attribute can be but is not limited to as shown in the following step S32.

[0089] S32. For the ith commodity attribute in the commodity attribute set, the total number of commodities containing the ith commodity attribute in the purchased commodity data is counted as the attribute influence value corresponding to the ith commodity attribute; in the present embodiment, if the ith commodity attribute is red in color, then the total number of red commodities in all commodities purchased by the commodity is counted; similarly, if the ith commodity attribute is green in color, then the total number of green commodities in all commodities purchased by the commodity is counted, and so on; for another example, if the ith commodity attribute is commodity type, which includes mobile phones, computers, etc., then the total number of mobile phones and computers in all commodities purchased by the commodity is counted; of course, the process of determining the attribute influence values ​​of the remaining commodities is the same as the above example and will not be repeated here.

[0090] After obtaining the attribute influence value corresponding to the i-th product attribute, the importance of the i-th product attribute to the target user can be calculated based on it. The calculation process can be but is not limited to the following step S33.

[0091] S33. Based on the attribute influence value corresponding to the i-th commodity attribute and according to the following formula (1), calculate the importance of the i-th commodity attribute to the target user.

[0092]

[0093] In the above formula (1), P i represents the importance of the i-th product attribute to the target user, Y i represents the attribute impact value of the i-th commodity attribute, Y m represents the attribute influence value of the mth commodity attribute, and n represents the total number of commodity attributes in the commodity attribute set.

[0094] It can be seen from the above formula (1) that the importance of the i-th product attribute to the target user is actually the ratio of a certain attribute in the products purchased by the customer to the total attributes of all purchased products; therefore, the larger the ratio, the more important the attribute is to the customer, and the more the customer values ​​the attribute.

[0095] Thus, after calculating the importance of the i-th product attribute to the target user through the aforementioned formula (1), the importance of the remaining product attributes to the target user can be calculated in the same manner, wherein the cyclic calculation process can be but is not limited to the following step S34.

[0096] S34. Increment i by 1, and re-count the number of commodities in the purchased commodity data that contain the i-th commodity attribute, until i equals n, to obtain the importance of each commodity attribute to the target user, where the initial value of i is 1.

[0097] After calculating the importance of each product attribute in the product attribute set to the target user based on the aforementioned steps S31 to S34, the target user's preferred product features can be determined based on the importance; wherein the process of determining the preferred product features can be but is not limited to as shown in the following step S35.

[0098] S35. According to the importance of each product attribute to the target user, select several product attributes from the product attribute set to serve as the target user's preferred product features. In this embodiment, the product attributes may be sorted in descending order of importance, and then the first H attributes are taken as the target user's preferred product features. In this way, the number of the target user's preferred product features is multiple. In addition, the value of H may be set specifically according to actual use and is not specifically limited here.

[0099] In this way, through the aforementioned steps S31 to S35, the user's preferred product characteristics can be mined based on the attributes of the product itself; then, based on this, the first user data mining of the target user can be carried out; wherein, the first user data mining process can be but is not limited to as shown in the following step S4.

[0100] S4. Perform first user data mining on the target user using the target user's preferred product characteristics to obtain the target user's first commercial mining data, wherein the first commercial mining data includes a number of first similar users who have similar preferred product characteristics as the target user and the first user data corresponding to each first similar user; in specific applications, the following steps S41 to S45 may be used, for example but not limited to, to complete the target user's first user data mining.

[0101] S41. Filter out several initial similar users corresponding to the target user from the user database of the e-commerce platform; in this embodiment, a traditional similar user recommendation method (such as collaborative filtering, association rules, etc.) can be used to obtain similar users of the target user, and thus serve as initial similar users; of course, the aforementioned traditional similar user recommendation is a commonly used technology for content recommendation, and its principle will not be repeated here.

[0102] After determining several initial similar users corresponding to the target user, the feature weight of each preferred product feature can be calculated based on this, so that the similarity between users can be calculated based on this later, thereby completing the mining process of the first user data; wherein, the process of determining the feature weight of each preferred product feature can be but is not limited to as shown in the following step S42.

[0103] S42. Determine the feature weight of each of the target user's preferred product features based on the several initial similar users; in this embodiment, a genetic algorithm is used to optimize the weight of each preferred product feature, wherein the optimization process may be but is not limited to steps S42a to S42i as shown below.

[0104] S42a. Determine any product from the historical purchase products corresponding to each initial similar user to serve as a test product. In this embodiment, the test product is selected to calculate the probability of the target user purchasing the test product under different feature weights, thereby using the error between the purchase probability and whether the target user actually purchases the product as a fitness function for optimization, wherein the specific calculation process of the fitness function is described below.

[0105] After the test product is determined, the feature weights may be initialized to form a number of particle individuals using the initialized feature weights; wherein the initialization process may be, but is not limited to, as shown in the following step S42b.

[0106] S42b. Perform multiple initialization processing on the feature weights of each preferred product feature, so that after each initialization processing, an initial weight vector is formed using the initialized feature weights of each preferred product feature; in this embodiment, it is equivalent to one initialization processing to generate an initial weight vector, and the initial weight vector includes the feature weights of each preferred product feature at the time of this initialization; in this way, after multiple initialization processing, multiple initial weight vectors can be obtained; then, based on this, particle individuals can be generated, and the process can be but not limited to as shown in the following step S42c.

[0107] S42c. Generate multiple individual particles using the initial weight vector obtained from each initialization process, wherein each individual particle corresponds to an initial position vector and an initial velocity vector, and the initial position vector of any individual particle corresponds to an initial weight vector; in this embodiment, the number of individual particles is equal to the number of initial weight vectors, and the initial position vector of the individual particle is essentially the initial weight vector; in this way, during the optimization process, the position of the individual particle is continuously updated, which is essentially to update the initial weight vector corresponding to the individual particle; based on this, when the iteration stop condition is met, the optimal weight vector can be obtained, and each weight in the optimal weight vector is the feature weight of each preferred product feature.

[0108] Optionally, the optimization process of the weight vector may be but is not limited to the following steps S42d to S42i.

[0109] S42d. Initialize the number of iterations t to 1, and obtain the position vector and velocity vector of each individual particle at the t-th iteration, wherein, when t is 1, the position vector and velocity vector of any individual particle at the t-th iteration are the initial position vector and initial velocity vector of any individual particle; in this embodiment, after obtaining the position vector of each individual particle at the t-th iteration, the fitness of each individual particle can be calculated based on this, so that the global optimal position and the individual optimal position can be updated based on the fitness later; wherein, the fitness calculation process can be but is not limited to as shown in the following step S42e.

[0110] S42e. Calculate the fitness of each individual particle at the t iteration based on a number of initial similar users and the position vector of each individual particle at the t iteration, wherein the fitness of any individual particle at the t iteration is used to characterize the error of the target user's purchase probability of the test product calculated using the position vector of any individual particle at the t iteration; in specific implementation, any individual particle is taken as an example to explain in detail; optionally, the fitness calculation process can be but is not limited to the following steps S42e1 to S42e4.

[0111] S42e1. For any individual particle, determine the weight vector of any individual particle at the tth iteration based on the position vector of any individual particle at the tth iteration; in the present embodiment, it has been explained above that the initial position vector of each individual particle corresponds to an initial weight vector, therefore, the position vector at the tth iteration is also the weight vector at the tth iteration, based on this, the position vector of any individual particle at the tth iteration is its corresponding weight vector, and each element inside it is the feature weight of each preferred product feature at the tth iteration.

[0112] In this way, after obtaining the weight vector of any of the aforementioned individual particles at the tth iteration, the similarity calculation can be performed so that the probability of the target user purchasing the test product under the weight vector can be calculated based on the real similarity between the target user and each initial similar user; wherein, the calculation process of the real similarity can be but is not limited to as shown in the following step S42e2.

[0113] S42e2. Based on the preferred product features of the target user and the weight vector of any particle individual at the tth iteration, and according to the following formula (2), calculate the true similarity between the target user and each initial similar user.

[0114]

[0115] In the above formula (2), S(K,a) represents the true similarity between the target user K and the ath initial similar user among several initial similar users. is the feature weight of the jth preferred product feature in the weight vector of any particle individual at the tth iteration, represents the importance of the jth preferred product feature to the target user, represents the importance of the j-th preferred product feature to the a-th initial similar user, R represents the total number of preferred product features, where a=1, 2, ..., A, and A represents the total number of initial similar users; in this embodiment, the calculation method of the importance of the ith preferred product feature to the a-th initial similar user can be referred to the aforementioned step S33, and its principle will not be repeated here.

[0116] In this way, after calculating the real similarity between the target user and each initial similar user based on the aforementioned formula (2), the probability of the target user purchasing the test product when the feature weight of the preferred product feature is taken as the corresponding weight vector of any particle individual can be calculated according to each real similarity; wherein, the calculation process of the purchase probability is shown in the following step S42e3.

[0117] S42e3. Based on the real similarity between the target user and each initial similar user, and in accordance with the following formula (3), the probability of the target user purchasing the test product is calculated when the weight vector corresponding to any particle individual is used as the feature weight of the preferred product feature.

[0118]

[0119] In the above formula (3), G represents the purchase probability of the target user for the test product, and U(a) represents whether the a-th initial similar user has purchased the test product. If the a-th initial similar user has purchased the test product, U(a) is 1, otherwise, U(a) is -1.

[0120] Therefore, based on the aforementioned formula (3), the purchase probability of the target user for the test product can be calculated when the weight vector of any particle individual at the tth iteration is the feature weight of the preferred product feature; then, the fitness of any particle individual at the tth time can be calculated based on the purchase probability; wherein, in this embodiment, the error between the predicted purchase probability and the actual purchase result of the target user of the test product is used as the fitness function; optionally, the calculation process can be but is not limited to the following step S42e4.

[0121] S42e4. Based on the purchase probability of the target user for the test product and according to the following formula (4), calculate the fitness of any particle individual at the tth iteration.

[0122] D t =|GU(K)| (4)

[0123] In the above formula (4), D t represents the fitness of any particle individual at the tth iteration, and U(K) represents whether the target user has purchased the test product. If the target user has purchased the test product, U(K) is 1, otherwise, U(K) is -1.

[0124] It can be seen from the above formula (4) that G represents the purchase probability of the test product when the target user takes the weight vector of any particle individual at the tth iteration as the feature weight of the preferred product feature, and U(K) represents the representation value of the target user's actual purchase result of the test product; therefore, the smaller the absolute value of the error between the two, the higher the accuracy of the feature weight. Based on this, the purpose of optimization is to find the position vector whose fitness is less than the fitness threshold (i.e., the error threshold), so as to obtain the optimal feature weight.

[0125] Therefore, through the aforementioned steps S42e1 to S42e4, the fitness of each individual particle at the tth iteration can be calculated, and then the global optimal position and the individual optimal position can be updated according to each fitness, and the process can be but not limited to as shown in the following step S42f.

[0126] S42f. Based on the fitness of each particle individual at the t-th iteration, update the global optimal position and the individual optimal position of each particle individual, wherein the global optimal position is the position vector corresponding to the particle individual with the smallest fitness during the 1st to t-th iterations; in this embodiment, if the minimum fitness at the t-th iteration is less than the fitness of the particle individual corresponding to the global optimal position at the t-1th iteration, then the position vector of the particle individual corresponding to the minimum fitness at the t-th iteration is used as the global optimal position, otherwise, no update is performed; similarly, the individual optimal position of the particle individual is performed on a particle individual basis, that is, the individual optimal position of each particle individual is the position vector corresponding to the minimum fitness during the 1st to t-th iterations; of course, the same is true for the global optimal position, which will not be repeated.

[0127] After completing the update of the global optimal position and the individual optimal position of each particle, it can be determined whether the iteration can be stopped; wherein the determination process can be but is not limited to as shown in the following step S42g.

[0128] S42g. Determine whether the iteration stop condition is met, wherein the iteration stop condition is that the fitness of the individual particle corresponding to the updated global optimal position is less than the fitness threshold, or t reaches the maximum number of iterations; in this embodiment, if the iteration stop condition is met, then each element in the weight vector corresponding to the global optimal position at this time is used as the optimal feature weight of each preferred product feature, that is, based on the global optimal position when the iteration stop condition is met, the feature weight of each preferred product feature is determined; otherwise, it is necessary to continue the iteration, that is, to update the position and speed of each individual particle, wherein the position and speed update process can be but is not limited to as shown in the following step S42h.

[0129] S42h. If not, then use the updated global optimal position and the updated individual optimal position of each individual particle to update the velocity vector of each individual particle at the tth iteration, and obtain the updated velocity vector corresponding to each individual particle, and use the updated velocity vector corresponding to each individual particle to update the position vector of each individual particle, and obtain the updated position vector corresponding to each individual particle; in specific applications, the position update formula and velocity update formula of the traditional PSO (particle swarm) algorithm are used in this embodiment to update the position vector and velocity vector of each particle; of course, the position update and velocity update formulas of the aforementioned PSO algorithm are commonly used formulas for optimization algorithms, and their principles are not repeated here.

[0130] After completing the update of the position and velocity of each individual particle, the updated position and velocity can be used as the initial position and velocity for the next iteration; in this way, the aforementioned process is continuously repeated until the iteration conditions are met, and the feature weights of each preferred product feature can be obtained; wherein, the cyclic optimization process can be but is not limited to as shown in the following step S42i.

[0131] S42i. Add 1 to t, replace the position vector and velocity vector of each individual particle at the tth iteration with the corresponding updated position vector and updated velocity vector, and recalculate the fitness of each individual particle at the tth iteration based on a number of initial similar users and the position vector of each individual particle at the tth iteration until the iteration stop condition is met, so as to determine the feature weight of each preferred product feature according to the global optimal position that meets the iteration stop condition; in this embodiment, the global optimal position equivalent to the global optimal position when the iteration stop condition is met is used as the optimal weight vector, and based on the optimal weight vector, the feature weight of each preferred product feature can be obtained.

[0132] In this way, based on the aforementioned steps S42a to S42i, the feature weights of each preferred product feature can be optimally obtained; then, based on the feature weights of each preferred product feature, the user similarity can be recalculated to obtain multiple first similar users who are similar to the target user's preferred product features; wherein, the user similarity calculation process can be but is not limited to as shown in the following step S43.

[0133] S43. Utilize the multiple preferred product features of the target user and the feature weights of each preferred product feature to calculate the first similarity between the target user and each user in the user database. In this embodiment, the aforementioned formula (2) can be used to calculate the first similarity between the target user and each user in the user database, and the calculation principle thereof will not be repeated. Thus, after obtaining the first similarity between the target user and each user, the first similar user can be determined based on this. The process of determining the first similar user can be, but is not limited to, as shown in the following step S44.

[0134] S44. According to the first similarity between the target user and each user, several first similar users corresponding to the target user are determined from the user database; in this embodiment, each user is sorted in descending order according to the first similarity, and then the top 5 or 10 users are taken as the first similar users; then, the user data of the first similar users (i.e., their historical purchase data) can be obtained to form the first commercial mining data; wherein, the generation process of the first commercial mining data can be but is not limited to as shown in the following step S45.

[0135] S45. Obtain the first user data of each first similar user, and use each first similar user and the first user data of each first similar user to form the first business mining data.

[0136] Thus, through the aforementioned steps S41 to S45, the first data mining process based on the characteristics of the user's preferred products can be completed; then, the second data mining process can be performed based on the historical behavior data and personal information, and the process can be but is not limited to as shown in the following step S5.

[0137] S5. Based on the historical behavior data and the personal information, the target user is subjected to second user data mining processing to obtain second commercial mining data of the target user, wherein the second commercial mining data includes a number of second similar users having similar personal information and behavior data to the target user and second user data corresponding to each second similar user; in specific implementation, the second commercial mining data may be generated by, for example but not limited to, the following steps S51 to S56.

[0138] S51. Obtain personal information and historical behavior data of each user in the user database of the e-commerce platform; in this embodiment, the process of obtaining the personal information and historical behavior data of each user in the user database is the same as that of the aforementioned target user, and will not be repeated here.

[0139] After obtaining the personal information and historical behavior data of each user in the user database, a second data mining process can be performed from two aspects: personal information and behavior data; wherein, the data mining process based on personal information can be but is not limited to as shown in the following step S52.

[0140] S52. Based on the personal information of the target user and the personal information of each user, calculate the similarity between the personal information of the target user and each user in the user database; in this embodiment, for the target user and any user, if the two have the same personal attributes (such as male gender, and undergraduate education or above), then the similarity of the personal attribute is 1, otherwise it is 0; at the same time, for numerical personal attributes such as age, they are divided according to a certain range and compared in the same way. If the two belong to the same age range, then the similarity of the personal attribute of age is 1; in this way, by obtaining the weights of different personal attributes in the personal information, and then multiplying the weight of each personal attribute by the similarity of the personal attribute, and taking the sum, the similarity of the personal information between the target user and any user can be obtained; based on this, in the same way as above, the similarity of the personal information between the target user and each user can be obtained.

[0141] After completing the similarity calculation based on personal information, the behavior similarity calculation may be performed based on the historical behavior data, and the calculation process may be, but is not limited to, as shown in the following step S53.

[0142] S53. Based on the historical behavior data of the target user and the historical behavior data of each user, calculate the behavior similarity between the target user and each user in the user database; in the specific implementation, take any user as an example to explain in detail, the calculation process of the behavior similarity between the target user and the target user can be but is not limited to the following steps S53a~S53c.

[0143] S53a. Based on the historical behavior data of the target user, determine the behavior type set of the target user; in the present embodiment, an example is used to illustrate this step. Assuming that the historical behavior data of the target user includes browsing behavior, purchasing behavior, collecting behavior, and adding to shopping cart behavior, then the behavior type set includes browsing behavior, purchasing behavior, collecting behavior, and adding to shopping cart behavior; in this way, the behavior similarity can be calculated based on the behavior type set, and the process can be but is not limited to as shown in S53b to S53c below.

[0144] S53b. For any user in the user database, the number of each type of behavior in the behavior type set generated by any user on the e-commerce platform is counted; in this embodiment, based on the above example, the number of browsing behaviors, the number of collection behaviors, the number of adding to shopping cart behaviors, and the number of purchase behaviors performed by any user on the e-commerce platform in the same time period (such as within a historical month) are counted; in this way, after the statistics are completed, the behavioral similarity between the target user and any user can be calculated based on the number of each type of behavior counted, and the calculation process is shown in the following step S53c.

[0145] S53c. Based on the number of behaviors of each type in the behavior category set generated by any user on the e-commerce platform, and according to the following formula (5), calculate the behavioral similarity between the target user and any user.

[0146]

[0147] In the above formula (5), Q(K,b) represents the behavior similarity between the target user and any of the users. Indicates the number of x-type behaviors generated by the target user on the e-commerce platform, represents the number of x-th type behaviors generated by any user on the e-commerce platform, and X represents the total number of behavior categories in the behavior category set.

[0148] In this way, through the aforementioned steps S53a to S53c, the behavioral similarity between the target user and any of the aforementioned users can be calculated, and then, in the same manner as described above, the behavioral similarity between the target user and each of the remaining users can be calculated; then, the second similarity between the target user and each user in the user database can be obtained in combination with the personal information similarity; wherein, the calculation process of the second similarity can be but is not limited to as shown in the following step S54.

[0149] S54. Based on the similarity of personal information and behavior between the target user and each user in the user database, calculate the second similarity between the target user and each user in the user database; in this embodiment, any user is taken as an example for explanation, wherein, for example, the sum of the total number of each type of behavior in the historical behavior data set of the target user can be calculated to obtain the first behavior number, and the sum of the total number of each type of behavior in the historical behavior data set of any user can be calculated to obtain the second behavior number; then, the first behavior number and the second behavior number are summed and the average is taken, so as to calculate the behavior control factor based on the average; finally, according to the behavior control factor, the second similarity between the target user and any user is calculated based on the similarity of personal information and behavior between the target user and any user.

[0150] Optionally, the second similarity between the target user and any user may be calculated by, for example but not limited to, using the following formula (6).

[0151]

[0152] In the above formula (6), Q′(K, b) represents the second similarity between the target user and the any user, s′(K, b) represents the similarity of personal information between the target user and the any user, represents the behavior control factor, and ζ represents the aforementioned mean.

[0153] Thus, after calculating the second similarity between the target user and each user through the aforementioned formula (6), a number of second similar users corresponding to the target user can be determined based on the second similarity. The determination process can be but is not limited to the following step S55.

[0154] S55. According to the second similarity between the target user and each user, several second similar users corresponding to the target user are determined from the user database; in this embodiment, each user is also arranged in descending order according to the second similarity, and then the top 5 or 10 users are selected as the second similar users; then, the user data of the second similar users can be obtained to form the second business mining data, and the process can be but is not limited to as shown in the following step S56.

[0155] S56. Acquire the second user data of each second similar user, and use each second similar user and the second user data of each second similar user to form the second commercial mining data.

[0156] In this way, through the aforementioned steps S51 to S56, the second user data mining process based on personal information and historical behavior data can be completed, and then, the aforementioned first business mining data can be combined to generate the optimal business mining data for the target user. The process can be but is not limited to as shown in the following step S6.

[0157] S6. Generate the optimal business mining data of the target user based on the first business mining data and the second business mining data, so as to use the optimal business mining data to make personalized product recommendations for the target user; in this embodiment, the optimal business mining data can be obtained by taking the union of the first business mining data and the second business mining data; among them, if there are multiple first similar users and second similar users that are the same user, then one is taken, and the similarity between the similar user and the target user in the optimal business mining data is the average of the corresponding first similarity and the second similarity; in this way, after obtaining the optimal business mining data, personalized product recommendations for the target user can be made based on it.

[0158] In this embodiment, one of the recommended methods is disclosed below, and the process is as follows:

[0159] Step 1: According to the product category currently browsed by the target user and the product features preferred by the user, select the products to be recommended from the products of the same category as the product category on the e-commerce platform; in this embodiment, the products that are of the same category as the products browsed by the user and whose product attributes meet the product features preferred by the user are selected as the products to be recommended.

[0160] Step 2: Calculate the recommendation score of each product to be recommended based on the optimal business mining data; in this embodiment, the recommendation score of each product to be recommended can be calculated by, but not limited to, the following formula (7).

[0161]

[0162] In the above formula (7), T(K,δ) represents the recommendation score of the δth recommended product to the target user. represents the similarity (the first similarity, the second similarity or the average of the two) between the rth similar user (the first similar user or the second similar user) in the optimal business mining data and the target user, pc(r,j) represents whether the rth similar user has purchased the δth recommended product, where if so, pc(r,j) takes the value of 1, otherwise, it takes the value of 0, and δ = 1, 2, ..., μ, where μ represents the total number of recommended products.

[0163] Thus, through the aforementioned formula (7), the recommendation score of each recommended product to the target user can be calculated, and then, personalized product recommendations can be made based on the aforementioned recommendation score, and the process is shown in the third step below.

[0164] Step 3: Sort the recommended products in descending order according to the recommendation scores to obtain a sorting sequence, and use the first 5 or 10 recommended products in the sorting sequence as recommended products for the target users.

[0165] Based on the above steps, personalized product recommendations for target users can be completed.

[0166] Thus, through the commercial data mining method described in detail in the aforementioned steps S1 to S6, the present invention mines the user data based on the attributes of the product itself, the user's personal information and the user's historical behavior data, thereby obtaining the user data with similar preferences, similar personal information and behaviors; then, personalized recommendation services for the user can be performed based on this; thus, compared with traditional technologies, the present invention does not need to rely on display feedback data such as user ratings when performing data mining, and therefore can solve the problem of missing display feedback data, thereby greatly improving the effectiveness of data mining, and thus achieving a more effective personalized product recommendation effect, which is very suitable for large-scale application and promotion.

[0167] like Figure 2 As shown, the second aspect of this embodiment provides a hardware device for implementing the commercial data mining method described in the first aspect of the embodiment, including:

[0168] The acquisition unit is used to acquire the target user's personal information and the target user's historical behavior data on the e-commerce platform.

[0169] The acquisition unit is further used to determine the purchase commodity data of the target user based on the historical behavior data.

[0170] The commodity feature mining unit is used to perform a preference feature mining process on the target user according to the commodity purchase data of the target user, so as to obtain the preferred commodity features of the target user after the preference feature mining process.

[0171] The commercial data mining unit is used to utilize the preferred product characteristics of the target user to perform first user data mining processing on the target user to obtain the first commercial mining data of the target user, wherein the first commercial mining data includes a number of first similar users who have similar preferred product characteristics as the target user and the first user data corresponding to each first similar user.

[0172] A business data mining unit is used to perform second user data mining processing on the target user based on the historical behavior data and the personal information to obtain second business mining data of the target user, wherein the second business mining data includes a number of second similar users who have similar personal information and behavior data to the target user and second user data corresponding to each second similar user.

[0173] The business data mining unit is further used to generate optimal business mining data for the target user based on the first business mining data and the second business mining data, so as to use the optimal business mining data to make personalized product recommendations for the target user.

[0174] The working process, working details and technical effects of the device provided in this embodiment can be found in the first aspect of the embodiment and will not be described in detail here.

[0175] like Figure 3 As shown, the third aspect of this embodiment provides another commercial data mining device, taking the device as an electronic device as an example, comprising: a memory, a processor and a transceiver that are communicatively connected in sequence, wherein the memory is used to store computer programs, the transceiver is used to send and receive messages, and the processor is used to read the computer program to execute the commercial data mining method as described in the first aspect of the embodiment.

[0176] For example, the memory may include, but is not limited to, random access memory (RAM), read-only memory (ROM), flash memory, first-in-first-out memory (FIFO) and / or first-in-last-out memory (FILO), etc. Specifically, the processor may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor may be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). At the same time, the processor may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in the standby state.

[0177] In some embodiments, the processor may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the display screen. For example, the processor may not be limited to a microprocessor of the STM32F105 series, a reduced instruction set computer (RISC) microprocessor, an X86 or other architecture processor, or a processor with an integrated embedded neural network processor (NPU); the transceiver may be, but is not limited to, a wireless fidelity (WIFI) wireless transceiver, a Bluetooth wireless transceiver, a general packet radio service technology (Genera l Packet Rad ioService, GPRS) wireless transceiver, a ZigBee protocol (a low-power LAN protocol based on the IEEE 802.15.4 standard, ZigBee) wireless transceiver, a 3G transceiver, a 4G transceiver and / or a 5G transceiver, etc. In addition, the device may also include, but is not limited to, a power module, a display screen and other necessary components.

[0178] The working process, working details and technical effects of the electronic device provided in this embodiment can be found in the first aspect of the embodiment and will not be described in detail here.

[0179] The fourth aspect of this embodiment provides a storage medium storing instructions including the commercial data mining method described in the first aspect of the embodiment, that is, the storage medium stores instructions, and when the instructions are run on a computer, the commercial data mining method described in the first aspect of the embodiment is executed.

[0180] The storage medium refers to a carrier for storing data, which may include but is not limited to a floppy disk, a CD, a hard disk, a flash memory, a USB flash drive and / or a memory stick, etc. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.

[0181] The working process, working details and technical effects of the storage medium provided in this embodiment can be found in the first aspect of the embodiment and will not be described in detail here.

[0182] The fifth aspect of this embodiment provides a computer program product comprising instructions, which, when executed on a computer, causes the computer to execute the commercial data mining method as described in the first aspect of the embodiment, wherein the computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device.

[0183] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A commercial data mining method, characterized in that: include: Obtain the target user’s personal information and historical behavior data on the e-commerce platform; Based on the historical behavior data, determining the purchase commodity data of the target user; According to the purchase commodity data of the target user, a preference feature mining process is performed on the target user, so as to obtain the preferred commodity features of the target user after the preference feature mining process; Using the preferred commodity characteristics of the target user, first user data mining processing is performed on the target user to obtain first commercial mining data of the target user, wherein the first commercial mining data includes a plurality of first similar users having similar preferred commodity characteristics as the target user and first user data corresponding to each first similar user; Based on the historical behavior data and the personal information, performing second user data mining processing on the target user to obtain second business mining data of the target user, wherein the second business mining data includes a number of second similar users having similar personal information and behavior data to the target user and second user data corresponding to each second similar user; The optimal business mining data of the target user is generated based on the first business mining data and the second business mining data, so as to make personalized commodity recommendations for the target user by using the optimal business mining data.

2. The method according to claim 1, characterized in that According to the purchase commodity data of the target user, a preference feature mining process is performed on the target user to obtain the preferred commodity features of the target user after the preference feature mining process, including: Based on the purchase commodity data of the target user, generating a commodity attribute set corresponding to the purchase commodity data; For the i-th commodity attribute in the commodity attribute set, the total number of commodities in the purchased commodity data containing the i-th commodity attribute is counted as the attribute influence value corresponding to the i-th commodity attribute; According to the attribute influence value corresponding to the i-th commodity attribute and in accordance with the following formula (1), the importance of the i-th commodity attribute to the target user is calculated; In the above formula (1), P i represents the importance of the i-th product attribute to the target user, Y i represents the attribute impact value of the i-th commodity attribute, Y m represents the attribute influence value of the mth commodity attribute, and n represents the total number of commodity attributes in the commodity attribute set; i is incremented by 1, and the number of commodities in the purchased commodity data that contain the i-th commodity attribute is recounted until i is equal to n, and the importance of each commodity attribute to the target user is obtained, wherein the initial value of i is 1; According to the importance of each commodity attribute to the target user, several commodity attributes are selected from the commodity attribute set to serve as the preferred commodity features of the target user.

3. The method according to claim 1, characterized in that The number of the target user's preferred product features is multiple, wherein the target user's preferred product features are used to perform first user data mining processing on the target user to obtain first commercial mining data of the target user, including: Filtering a number of initial similar users corresponding to the target user from a user database of the e-commerce platform; Determining, based on the plurality of initial similar users, a feature weight of each of the preferred product features of the target user; Calculate a first similarity between the target user and each user in the user database by using a plurality of preferred product features of the target user and a feature weight of each preferred product feature; According to the first similarity between the target user and each user, determining a plurality of first similar users corresponding to the target user from the user database; The first user data of each first similar user is obtained, and the first business mining data is formed by using each first similar user and the first user data of each first similar user.

4. The method according to claim 3, characterized in that: Determining the feature weight of each of the preferred product features of the target user according to the plurality of initial similar users includes: Determine any product from the historical purchase products corresponding to each initial similar user as a test product; Performing multiple initialization processing on the feature weights of each preferred product feature, so that after each initialization processing, an initial weight vector is formed using the initialized feature weights of each preferred product feature; Using the initial weight vector obtained in each initialization process, multiple individual particles are generated, wherein each individual particle corresponds to an initial position vector and an initial velocity vector, and the initial position vector of any individual particle corresponds to an initial weight vector; Initialize the number of iterations t to 1, and obtain the position vector and velocity vector of each particle individual at the t-th iteration, wherein when t is 1, the position vector and velocity vector of any particle individual at the t-th iteration are the initial position vector and initial velocity vector of any particle individual; According to a number of initial similar users and the position vectors of each particle individual at the t-th iteration, the fitness of each particle individual at the t-th iteration is calculated, wherein the fitness of any particle individual at the t-th iteration is used to characterize the error of the target user's purchase probability of the test product calculated using the position vector of any particle individual at the t-th iteration; Based on the fitness of each particle individual at the tth iteration, the global optimal position and the individual optimal position of each particle individual are updated, wherein the global optimal position is the position vector corresponding to the particle individual with the smallest fitness during the 1st to tth iterations; Determine whether an iteration stop condition is met, wherein the iteration stop condition is that the fitness of the individual particle corresponding to the updated global optimal position is less than the fitness threshold, or t reaches the maximum number of iterations; If not, then use the updated global optimal position and the updated individual optimal position of each individual particle to update the velocity vector of each individual particle at the tth iteration to obtain the updated velocity vector corresponding to each individual particle, and use the updated velocity vector corresponding to each individual particle to update the position vector of each individual particle to obtain the updated position vector corresponding to each individual particle; Add 1 to t, replace the position vector and velocity vector of each particle individual at the tth iteration with the corresponding updated position vector and updated velocity vector, and recalculate the fitness of each particle individual at the tth iteration based on several initial similar users and the position vector of each particle individual at the tth iteration until the iteration stop condition is met, so as to determine the feature weights of each preferred product feature according to the global optimal position that meets the iteration stop condition.

5. The method according to claim 4, characterized in that According to several initial similar users and the position vectors of each particle individual at the tth iteration, the fitness of each particle individual at the tth iteration is calculated, including: For any individual particle, according to the position vector of the individual particle at the t-th iteration, determine the weight vector of the individual particle at the t-th iteration; According to the preferred product features of the target user and the weight vector of any particle individual at the tth iteration, the real similarity between the target user and each initial similar user is calculated according to the following formula (2); In the above formula (2), S(K,a) represents the true similarity between the target user K and the ath initial similar user among several initial similar users. is the feature weight of the jth preferred product feature in the weight vector of any particle individual at the tth iteration, represents the importance of the jth preferred product feature to the target user, represents the importance of the jth preferred product feature to the ath initial similar user, R represents the total number of preferred product features, where a=1,2,...,A, and A represents the total number of initial similar users; Based on the real similarity between the target user and each initial similar user, and according to the following formula (3), the probability of the target user purchasing the test product is calculated when the weight vector corresponding to any particle individual is used as the feature weight of the preferred product feature; In the above formula (3), G represents the purchase probability of the target user for the test product, and U(a) represents whether the a-th initial similar user has purchased the test product. If the a-th initial similar user has purchased the test product, U(a) is 1, otherwise, U(a) is -1. According to the purchase probability of the target user for the test product, and in accordance with the following formula (4), the fitness of any particle individual at the tth iteration is calculated; D t =|G-U(K)| (4) In the above formula (4), D t represents the fitness of any particle individual at the tth iteration, and U(K) represents whether the target user has purchased the test product. If the target user has purchased the test product, U(K) is 1, otherwise, U(K) is -1.

6. The method according to claim 1, characterized in that Based on the historical behavior data and the personal information, a second user data mining process is performed on the target user to obtain second commercial mining data of the target user, including: Obtain personal information and historical behavior data of each user in the user database of the e-commerce platform; Calculate the similarity between the personal information of the target user and the personal information of each user in the user database according to the personal information of the target user and the personal information of each user; Based on the historical behavior data of the target user and the historical behavior data of each user, calculating the behavior similarity between the target user and each user in the user database; Calculate the second similarity between the target user and each user in the user database based on the similarity of personal information and behavior between the target user and each user in the user database; Determining a plurality of second similar users corresponding to the target user from the user database according to the second similarity between the target user and each user; The second user data of each second similar user is obtained, and the second business mining data is formed by using each second similar user and the second user data of each second similar user.

7. The method according to claim 6, characterized in that Based on the historical behavior data of the target user and the historical behavior data of each user, the behavior similarity between the target user and each user in the user database is calculated, including: Determining a behavior category set of the target user based on the historical behavior data of the target user; For any user in the user database, counting the number of behaviors of each type of behaviors in the behavior category set generated by the any user on the e-commerce platform; Based on the number of behaviors of each type of behavior in the behavior type set generated by any user on the e-commerce platform, and according to the following formula (5), the behavior similarity between the target user and any user is calculated; In the above formula (5), Q(K,b) represents the behavior similarity between the target user and any of the users. Indicates the number of x-type behaviors generated by the target user on the e-commerce platform, represents the number of x-th type behaviors generated by any user on the e-commerce platform, and X represents the total number of behavior categories in the behavior category set.

8. A commercial data mining device, characterized in that: include: An acquisition unit, used to acquire the target user's personal information and the target user's historical behavior data on the e-commerce platform; The acquisition unit is further used to determine the purchase commodity data of the target user based on the historical behavior data; A commodity feature mining unit, configured to perform a preference feature mining process on the target user according to the commodity purchase data of the target user, so as to obtain the preferred commodity features of the target user after the preference feature mining process; A commercial data mining unit, configured to perform first user data mining processing on the target user by using the preferred commodity characteristics of the target user to obtain first commercial mining data of the target user, wherein the first commercial mining data includes a plurality of first similar users having similar preferred commodity characteristics as the target user and first user data corresponding to each of the first similar users; A business data mining unit, configured to perform a second user data mining process on the target user based on the historical behavior data and the personal information to obtain second business mining data of the target user, wherein the second business mining data includes a plurality of second similar users having similar personal information and behavior data to the target user and second user data corresponding to each second similar user; The business data mining unit is further used to generate optimal business mining data for the target user based on the first business mining data and the second business mining data, so as to use the optimal business mining data to make personalized product recommendations for the target user.

9. An electronic device, characterized in that: include: A memory, a processor and a transceiver which are sequentially communicatively connected, wherein the memory is used to store a computer program, the transceiver is used to send and receive messages, and the processor is used to read the computer program to execute the commercial data mining method as described in any one of claims 1 to 7.

10. A computer program product comprising instructions, characterized in that When the instructions are executed on a computer, the computer is caused to execute the commercial data mining method according to any one of claims 1 to 7.

Images