E-commerce content intelligent recommendation method and device based on cross-platform user characteristics

Abstract

The embodiment of the invention provides an e-commerce content intelligent recommendation method and device based on cross-platform user characteristics, equipment and a computer readable storage medium. The method comprises the following steps: acquiring feature information of a current platform target user; matching the feature information with a constructed database to obtain portrait information corresponding to the feature information; the database comprises portrait information of the user acquired based on social media, an e-commerce platform and / or a forum; calculating the similarity between the feature information and the portrait information; on the basis of the similarity, e-commerce content with high integrating degree with the target user is obtained; and pushing the e-commerce content to the target user based on the promotion mode of the current platform. In this way, the user experience is greatly improved while the e-commerce content recommendation accuracy is improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of data processing, and in particular to a method, apparatus, device and computer-readable storage medium for intelligently recommending e-commerce content based on cross-platform user characteristics. Background Art

[0002] With the rapid development of Internet technology, the e-commerce industry has ushered in unprecedented opportunities and challenges. In order to improve user experience and enhance user stickiness, e-commerce platforms need to continuously optimize content recommendation systems. At present, e-commerce content recommendation systems have been widely used in various e-commerce platforms, but how to achieve accurate intelligent recommendations based on user cross-platform characteristics in a complex environment of multiple channels and platforms is still a technical problem in the industry.

[0003] Most existing e-commerce content recommendation systems make recommendations based on user behavior data from a single platform. Although this method can improve the accuracy of recommendations to a certain extent, it ignores the differences in user behavior characteristics between different platforms. In addition, although some systems have begun to try to integrate cross-platform data, due to technical limitations, they cannot achieve true cross-platform user feature analysis and intelligent recommendations.

[0004] In summary, the existing e-commerce content recommendation methods, based on data analysis of a single platform, cannot fully reflect the real needs of users, resulting in recommendation results that may deviate from the actual interests of users; cross-platform data integration is difficult, and existing technologies cannot effectively process multi-source heterogeneous data, which affects the recommendation effect; the mining of user characteristics is not in-depth enough, and it is impossible to fully utilize user cross-platform behavior data for accurate recommendations; existing programmatic advertising will only deliver relevant content that users are interested in based on their historical search records. Summary of the invention

[0005] According to the embodiments of the present application, an intelligent recommendation solution for e-commerce content based on cross-platform user characteristics is provided, which can guide users to pay attention to stores across platforms according to user characteristics, intelligently promote products and activities, etc., thereby enhancing user stickiness and conversion rate, improving the recommendation accuracy of e-commerce content and greatly improving user experience.

[0006] In a first aspect of the present application, a method for intelligently recommending e-commerce content based on cross-platform user characteristics is provided. The method comprises: Obtain characteristic information of the target users of the current platform; Matching the feature information with a constructed database to obtain portrait information corresponding to the feature information; the database includes portrait information of users obtained based on social media, e-commerce platforms and / or forums; Calculating the similarity between the feature information and the portrait information; and obtaining e-commerce content that is highly compatible with the target user based on the similarity; Based on the promotion method of the current platform, the e-commerce content is pushed to the target users.

[0007] In a second aspect of the present application, a device for intelligently recommending e-commerce content based on cross-platform user characteristics is provided. The device comprises: The acquisition module is used to obtain the characteristic information of the target users of the current platform; A matching module, used to match the feature information with a constructed database to obtain portrait information corresponding to the feature information; the database includes user portrait information obtained based on social media, e-commerce platforms and / or forums; A calculation module, used to calculate the similarity between the feature information and the portrait information; based on the similarity, obtain e-commerce content with a high degree of fit with the target user; The push module is used to push the e-commerce content to the target users based on the promotion method of the current platform.

[0008] In a third aspect of the present application, an electronic device is provided, which includes a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the program, the method described above is implemented.

[0009] In a fourth aspect of the present application, a computer-readable storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, the method according to the first aspect of the present application is implemented.

[0010] The embodiment of the present application provides an intelligent e-commerce content recommendation method based on cross-platform user characteristics, which obtains characteristic information of target users of the current platform; matches the characteristic information with a constructed database to obtain portrait information corresponding to the characteristic information; the database includes portrait information of users obtained based on social media, e-commerce platforms and / or forums; calculates the similarity between the characteristic information and the portrait information; based on the similarity, obtains e-commerce content with a high degree of fit with the target user; based on the promotion method of the current platform, pushes the e-commerce content to the target user, thereby greatly improving the user experience.

[0011] It should be understood that the contents described in the Summary of the Invention are not intended to limit the key or important features of the embodiments of the present application, nor are they intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The above and other features, advantages and aspects of the embodiments of the present application will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein: Figure 1 It is a flowchart of an e-commerce content intelligent recommendation method based on cross-platform user characteristics according to an embodiment of the present application; Figure 2 is a block diagram of an e-commerce content intelligent recommendation device based on cross-platform user characteristics according to an embodiment of the present application; Figure 3 It is a schematic diagram of the structure of a terminal device or a server suitable for implementing the embodiments of the present application. DETAILED DESCRIPTION

[0013] In order to make the purpose, technical solution and advantages of the embodiments of the present disclosure clearer, the technical solution in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0014] In addition, the term "and / or" in this article is only a description of the association relationship between the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0015] Figure 1 A flow chart of a method for intelligently recommending e-commerce content based on cross-platform user characteristics according to an embodiment of the present disclosure is shown. The method may include: S110, obtaining characteristic information of the target user of the current platform.

[0016] In some embodiments, characteristic information of the currently logged-in target user may be obtained by wired or wireless means; the characteristic information includes easily accessible public information such as the user's nickname, gender, province and / or age.

[0017] S120, matching the feature information with a constructed database to obtain portrait information corresponding to the feature information.

[0018] In some embodiments, in order to obtain more accurate push results, the feature information obtained through step S110 may be cleaned to remove duplicate, erroneous or invalid information, thereby providing a basis for subsequent analysis.

[0019] In some embodiments, the database can be constructed in the following manner: through big data analysis, web crawling, etc., various platforms, that is, user information of different source platforms, such as social media, e-commerce platforms and / or forums, etc., the obtained user information is removed from duplicate, erroneous or invalid information (cleaning), and the data from different platforms are integrated into a unified database.

[0020] In some embodiments, in order to reduce the amount of calculation, based on actual user habits (it has been found through research that based on consumer behavior habits, the nicknames used by users on different application platforms are mostly similar), the user nickname in the acquired feature information can be matched with the constructed database to obtain portrait information corresponding to the feature information, that is, portrait information that is highly similar to the user nickname.

[0021] Specifically, the similarity between the user nickname in the feature information and the portrait data stored in the database can be calculated in the following manner: Similarity=∑ c ∈Σmin(| A ∣ f ( c ),∣ B ∣ f ( c )); Among them, ∑ is the set of all possible characters; fA(c) and fB(c) are the frequencies of occurrence of character c in nicknames A and B respectively.

[0022] S130, calculating the similarity between the feature information and the portrait information; and obtaining e-commerce content that is highly compatible with the target user based on the similarity.

[0023] In some embodiments, portrait information that is highly similar (highly similar) to the characteristic information of the target user is calculated in step S120. Further, the similarity of the age, province and / or gender of the characteristic information and the portrait information that is highly similar to the characteristic information nickname is calculated respectively, and the calculated similarities of age, province and / or gender are weighted summed to obtain the similarity of the characteristic information and the portrait information.

[0024] Specifically, the age similarity (sim_age(A_1, A_2)) can be calculated as follows: K(x,x′)=exp(-2σ2∥xx′∥2); Where x and x′ are two points in d-dimensional space; ∥xx′∥ is the Euclidean distance between x and x′; σ is the width parameter, which determines the smoothness (“width”) of the function. Smaller σ values ​​make the function sharper, while larger σ values ​​make the function smoother.

[0025] Furthermore, to calculate the similarity between two objects (such as user A and user B) in terms of age features, we can regard x and x′ as the age values ​​of the two objects (i.e., scalars rather than vectors), and simplify the Gaussian kernel function to: sim_age(A1,A2)=exp(-2σ2(A1-A2)2), where A1 and A2 are the ages of the two objects, and σ is a parameter that controls the degree of influence of age differences on similarity. For example, the form of the Gaussian kernel function may be exp(-(A_1 - A_2)^2 / (2 * sigma^2)), where sigma is a hyperparameter that controls the degree of influence of age differences on similarity. Furthermore, in view of the poor interpretability of the Gaussian function, this paper uses an interpretable kernel function combination for optimization. Combining the Gaussian kernel with the linear kernel can retain the interpretability of the linear model to a certain extent. The linear kernel expression is: K(x,x′)=x·x′+c; Among them, x and x′ are two input vectors; c is an optional constant.

[0026] The province similarity (sim_province(P_1, P_2)) can be calculated as follows: Considering the geographic, cultural and / or economic similarities between provinces usually involves multiple dimensions, and each dimension of similarity requires a different measurement method: Comprehensive similarity (A, B) = ∑i = 1nwi · Distinction i (A, B); Where n is the total number of similarity dimensions considered; Wi is the weight of the i-th similarity dimension, satisfying ∑i=1nwi=1 (the sum of the weights is 1 to ensure that the comprehensive similarity is a normalized value); Similarity i(A, B) is the similarity between A and B in the i-th dimension calculated according to a certain measurement method. This value is usually between 0 (completely different) and 1 (completely the same), and may also vary according to the specific application scenario.

[0027] Gender similarity (sim_gender(S_1, S_2)) can be calculated as follows: Usually, gender similarity is calculated based on whether they are the same, that is, if S_1 and S_2 are the same, 1 is returned; otherwise, 0 is returned. In actual scenarios, gender differences have little impact on similarity, and other values ​​(such as 0.5) can be considered to represent the similarity of different genders.

[0028] Furthermore, the following weighted summation method can be used to calculate the overall similarity: Similarity=w1×sim_age(A1,A2)+w2×sim_nickname(N1,N2)+w3sim_personalized_signature(PS1,PS2)+w4×sim_trends(T1,T2)+w5sim_province(P1,P2)+w6·sim_gender(S1,S2); Among them, sim_age(A1,A2) is the similarity between ages; Sim_nickname(N1,N2) is the similarity of nicknames; Sim_personalized_signature(PS1,PS2) similarity of personalized signatures; Sim_trends(T1,T2) is the similarity of dynamic information; sim_province(P1,P2) is the similarity between provinces; sim_gender(S1,S2) is the similarity between genders; wn is the weight, which is used to determine the importance of each feature in the overall similarity calculation. It can be set according to the actual application scenario. For example, if the nickname is very important, w_2 can be set to a larger value.

[0029] Furthermore, the calculation method of the similarity between the personal signature and the dynamic information can refer to the calculation method of the nickname similarity, which will not be repeated here.

[0030] Furthermore, according to the above algorithm, under the hard condition of nickname similarity threshold of 1.0, other user information under the custom weight matching algorithm, through data comparison and analysis, when the comprehensive threshold is >0.846, it is a highly accurate match for cross-platform users, and accurate intelligent push is carried out based on these users, thereby effectively reaching potential users. Retrieve user portraits that meet the above similarity conditions, perform data analysis on the user portraits, and obtain the e-commerce data content to be recommended, such as the store information, consumption information and / or other e-commerce content information.

[0031] S140: Push the e-commerce content to the target user based on the promotion method of the current platform.

[0032] In some embodiments, based on the promotion methods of the current platform, such as social media advertising, in-site message push, email marketing, etc., the e-commerce data content to be recommended obtained according to the matching in step S130 is pushed to the target users, guiding the users to pay attention to the store, intelligently promote products and activities, and realize precise marketing and efficient conversion.

[0033] According to the embodiments of the present disclosure, the following technical effects are achieved: Based on the matching of user nicknames, combined with the user's public and legal multi-dimensional information, it realizes the identification and positioning of users across platforms and intelligently generates cross-platform promotion strategies; through the customized weighted similarity matching algorithm, it can more accurately match target users based on multi-dimensional information, greatly improving the user experience while improving the accuracy of pushed content. It solves the problems in the existing technology, such as inaccurate advertising and difficulty in effectively reaching potential users; poor user experience, frequent advertising pushes easily cause user disgust; lack of in-depth analysis of user cross-platform behavior characteristics, and limited promotion effect.

[0034] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present application.

[0035] The above is an introduction to the method embodiment. The following is a further explanation of the scheme described in this application through an apparatus embodiment.

[0036] Figure 2 FIG. 1 shows a block diagram of an e-commerce content intelligent recommendation device based on cross-platform user characteristics according to an embodiment of the present application, such as Figure 2 Shown include: The acquisition module 210 is used to acquire characteristic information of the target user of the current platform; A matching module 220 is used to match the feature information with a constructed database to obtain portrait information corresponding to the feature information; the database includes user portrait information obtained based on social media, e-commerce platforms and / or forums; A calculation module 230 is used to calculate the similarity between the feature information and the portrait information; based on the similarity, obtain e-commerce content that is highly compatible with the target user; The push module 240 is used to push the e-commerce content to the target user based on the promotion method of the current platform.

[0037] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the described module can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0038] Figure 3 A schematic diagram of the structure of a terminal device or a server suitable for implementing an embodiment of the present application is shown.

[0039] like Figure 3 As shown, the terminal device or server includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 302 or the program loaded from the storage part 308 to the random access memory (RAM) 303. In RAM303, various programs and data required for the operation of the terminal device or server are also stored. CPU 301, ROM 302 and RAM303 are connected to each other through a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0040] The following components are connected to the I / O interface 305: an input section 306 including a keyboard, a mouse, etc.; an output section 307 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 308 including a hard disk, etc.; and a communication section 309 including a network interface card such as a LAN card, a modem, etc. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the I / O interface 305 as needed. A removable medium 311, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 310 as needed, so that a computer program read therefrom is installed into the storage section 308 as needed.

[0041] In particular, according to an embodiment of the present application, the above method flow steps can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a machine-readable medium, and the computer program includes a program code for executing the method shown in the flow chart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 309, and / or installed from the removable medium 311. When the computer program is executed by the central processing unit (CPU) 301, the above-mentioned functions defined in the system of the present application are executed.

[0042] It should be noted that the computer-readable medium shown in the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0043] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of the code, and the aforementioned module, program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0044] The units or modules involved in the embodiments described in the present application may be implemented by software or hardware. The units or modules described may also be arranged in a processor. The names of these units or modules do not, in some cases, constitute limitations on the units or modules themselves.

[0045] As another aspect, the present application further provides a computer-readable storage medium, which may be included in the electronic device described in the above embodiment; or may exist independently without being assembled into the electronic device. The above computer-readable storage medium stores one or more programs, and when the above programs are used by one or more processors to execute the method described in the present application.

[0046] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of application involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the aforementioned application concept. For example, the above features are replaced with (but not limited to) technical features with similar functions applied in the present application.

Claims

1. An e-commerce content intelligent recommendation method based on cross-platform user characteristics, characterized in that: include: Obtain characteristic information of the target users of the current platform; Matching the feature information with a constructed database to obtain portrait information corresponding to the feature information; the database includes portrait information of users obtained based on social media, e-commerce platforms and / or forums; Calculating the similarity between the feature information and the portrait information; and obtaining e-commerce content that is highly compatible with the target user based on the similarity; Based on the promotion method of the current platform, the e-commerce content is pushed to the target users.

2. The method according to claim 1, characterized in that The portrait information includes nickname, gender, province and / or age information.

3. The method according to claim 2, characterized in that The step of matching the feature information with the constructed database to obtain the portrait information corresponding to the feature information includes: Matching is performed based on the user nickname in the feature information and the constructed database to obtain portrait data with a high similarity to the user nickname.

4. The method according to claim 3, characterized in that Also includes: The similarity between the user nickname in the feature information and the portrait data stored in the database is calculated in the following manner: Similarity=∑ c ∈Σmin(∣ A ∣ f ( c ),∣ B ∣ f ( c )); Among them, ∑ is the set of all possible characters; fA(c) and fB(c) are the frequencies of occurrence of character c in nicknames A and B respectively.

5. The method according to claim 4, characterized in that The calculating the similarity between the feature information and the portrait information comprises: Calculating the similarity of age, province and / or gender of the feature information and the portrait information respectively; The calculated similarities of age, province and / or gender are weightedly summed to obtain the similarity between the feature information and the portrait information.

6. The method according to claim 5, characterized in that Also includes: The age similarity between the feature information and the portrait information can be calculated as follows: K(x,x′)=exp(-2σ2∥xx′∥2); Where x and x′ are two points in d-dimensional space; ∥xx′∥ is the Euclidean distance between x and x′; σ is the width parameter.

7. The method according to claim 1, characterized in that Also includes: The characteristic information is removed and / or error processed.

8. An e-commerce content intelligent recommendation device based on cross-platform user characteristics, characterized in that: include: The acquisition module is used to obtain the characteristic information of the target users of the current platform; A matching module, used to match the feature information with a constructed database to obtain portrait information corresponding to the feature information; the database includes user portrait information obtained based on social media, e-commerce platforms and / or forums; A calculation module, used to calculate the similarity between the feature information and the portrait information; based on the similarity, obtain e-commerce content with a high degree of fit with the target user; The push module is used to push the e-commerce content to the target users based on the promotion method of the current platform.

9. An electronic device comprising a memory and a processor, wherein a computer program is stored in the memory, wherein: When the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images