CN115329199A

CN115329199A - Product pushing method, device, equipment and storage medium

Info

Publication number: CN115329199A
Application number: CN202211005803.7A
Authority: CN
Inventors: 牛煜超
Original assignee: Ping An Bank Co Ltd
Current assignee: Ping An Bank Co Ltd
Priority date: 2022-08-22
Filing date: 2022-08-22
Publication date: 2022-11-11

Abstract

The embodiment of the invention relates to the field of artificial intelligence, and discloses a product pushing method, a product pushing device, product pushing equipment and a storage medium, wherein the method comprises the steps of acquiring registration information, historical transaction records and product evaluation of a user; analyzing the registration information, the historical transaction records and the product evaluation to obtain the preference degrees of each product and the cover of the product; analyzing the style of the cover of each product preferred by the user according to the preference degree of the cover to obtain the preference of the style of the cover of the user; sorting the products according to the product preference degrees, and selecting a preset number of preferred products; constructing a product cover of a preferred product according to the style preference of the cover; and pushing the preferred products containing the product covers to the user end. According to the embodiment of the invention, the preferred products are pushed according to the preference degrees, so that personalized recommendation is realized; and the product cover is constructed according to the preference condition of the user to the product cover, and the preferred product containing the product cover is pushed to the user, so that the user satisfaction is improved.

Description

Product pushing method, device, equipment and storage medium

Technical Field

The invention relates to the field of artificial intelligence, in particular to a product pushing method, a product pushing device, product pushing equipment and a storage medium.

Background

With the rapid development of computer technology, more and more online popularization modes appear, but business personnel cannot effectively push product data with high matching degree according to limited user information when pushing the product data online.

In a traditional product data pushing mode, product data is generally directly pushed to a user terminal according to existing user information, and personalized pushing of a user is not achieved. Therefore, the products pushed to the user are difficult to arouse the purchasing desire of the user, and the user is also difficult to find out the products in which the user is interested from the pushed mass products. Furthermore, users increasingly demand personalized pushing of products, and the products are demanded in the pushing process to further improve the purchasing interests of the products. Therefore, how to realize personalized pushing of products and further improve the experience effect of users is an urgent problem to be solved.

Disclosure of Invention

In view of the above, to solve the problems in the prior art, the present invention provides a product pushing method, apparatus, device and storage medium applicable to the fields such as financial technology and the like or other fields.

In a first aspect, the present invention provides a product pushing method, including:

acquiring registration information, historical transaction records and product evaluation of a user;

analyzing the registration information, the historical transaction records and the product evaluation to obtain the preference degrees of all products and the preference degree of cover covers of the products;

analyzing the style of each product cover preferred by the user according to the product cover preference degree to obtain the cover style preference of the user;

sorting the products according to the product preference degrees, and selecting a preset number of preferred products;

constructing a product cover of the preferred product according to the cover style preference;

and pushing the preferred products containing the product covers to a user side.

In an optional embodiment, the analyzing the registration information, the historical transaction record, and the product evaluation to obtain each product preference and product cover preference includes:

calculating a first product preference degree and a first product cover preference degree according to the registration information;

calculating the purchase rate of each product according to the historical transaction record, and determining the preference degree of a second product and the preference degree of a cover of the second product according to the purchase rate;

performing emotional tendency analysis on the product evaluation, and determining a third product preference degree and a third product cover preference degree;

determining the product preference of the user for each product according to the first product preference, the second product preference and the third product preference;

determining the product cover preference of the user for each product cover according to the first product cover preference, the second product cover preference and the third product cover preference.

In an alternative embodiment, the analyzing the product rating for emotional tendency to determine a third product preference and a third product cover preference comprises:

classifying the product evaluation to obtain first product evaluation data containing products and second product evaluation data containing product covers;

performing word segmentation processing on the first product evaluation data and the second product evaluation data respectively to obtain a first word to be analyzed and a second word to be analyzed correspondingly;

matching the first words to be analyzed and the second words to be analyzed with the emotional words in a preset word bank respectively, and calculating to obtain corresponding first emotional tendency values and second emotional tendency values;

and determining a third product preference degree according to the first emotional tendency value, and determining a third product cover preference degree according to the second emotional tendency value.

In an optional implementation manner, each emotion word in the preset word library corresponds to an emotion reference value, and the matching of the first word to be analyzed and the second word to be analyzed with emotion words in the preset word library and the calculation of the first emotion tendency value and the second emotion tendency value that correspond to each other include:

matching the first words to be analyzed and the second words to be analyzed with the emotion words in the preset word bank respectively to obtain target emotion words correspondingly; wherein one product or one product cover corresponds to at least one target emotion word;

and calculating the product of preset weight and the emotion reference value corresponding to the target emotion word, and correspondingly obtaining the first emotion tendency value of each product and the second emotion tendency value of each product cover.

In an alternative embodiment, the determining the preference of each product cover according to the first product cover preference, the second product cover preference and the third product cover preference comprises:

according to a preset weight coefficient, performing weight calculation on the cover preference of the first product, the cover preference of the second product and the cover preference of the third product corresponding to the same product to obtain the cover preference of the product;

and calculating the product cover preference degrees of the products.

In an optional embodiment, the sorting the products according to the product preference degrees and selecting a preset number of preferred products includes:

classifying each product to obtain a plurality of product types;

calculating type preference degrees corresponding to product types according to the product preference degrees of the products;

sorting the product types according to the sequence of the type preference degrees from large to small, and selecting N product types which are sorted in the front, wherein N is a natural number;

and selecting a preset number of preferable products from the N product types.

In an alternative embodiment, the pushing the preferred product containing the product cover to the user side includes:

pushing the preferred products containing the product covers to a user side in a random arrangement order, so that the user side displays the preferred products randomly; or the like, or a combination thereof,

and pushing the preferred products containing the product covers to the user side according to the arrangement sequence of the product preference degrees from large to small, so that the user side preferentially displays the preferred products with the product preference degrees close to the front.

In a second aspect, the present invention provides a product pushing apparatus comprising:

the acquisition module is used for acquiring registration information, historical transaction records and product evaluation of the user;

the first analysis module is used for analyzing the registration information, the historical transaction records and the product evaluation to obtain the preference of each product and the preference of a cover of the product;

the second analysis module is used for analyzing the style of each product cover preferred by the user according to the product cover preference degree to obtain the cover style preference of the user;

the sorting module is used for sorting the products according to the product preference degrees and selecting the preferred products with preset quantity;

the construction module is used for constructing a product cover of the preferred product according to the style preference of the cover;

and the pushing module is used for pushing the preferred products containing the product covers to a user side.

In a third aspect, the present invention provides a computer device comprising a memory storing a computer program and at least one processor configured to execute the computer program to implement the aforementioned product push method.

In a fourth aspect, the present invention provides a computer storage medium storing a computer program, which when executed implements the aforementioned product pushing method.

The embodiment of the invention has the following beneficial effects:

according to the method, the registration information, the historical transaction records and the product evaluation of the user are analyzed to calculate the product preference and the product cover preference of the user to each product, so that the product is pushed according to the preference condition of the user, the personalized recommendation to the user is realized, the products pushed by the user are all products which are interested or preferred by the user, and the product pushing efficiency is improved; and when the product is pushed, the product cover preferred by the user is constructed according to the preference condition of the user to the product cover, so that the preferred product containing the constructed product cover is pushed to the user, the experience effect and the satisfaction degree of the user are improved, and the vitality of the system is further improved.

Drawings

In order to more clearly illustrate the technical solution of the present invention, the drawings required to be used in the embodiments will be briefly described below, and it should be understood that the following drawings only illustrate some embodiments of the present invention, and therefore should not be considered as limiting the scope of the present invention. Like components are numbered similarly in the various figures.

FIG. 1 is a schematic diagram showing a first implementation of a product push method in an embodiment of the present invention;

FIG. 2 is a schematic diagram showing a second embodiment of a product pushing method in the embodiment of the present invention;

FIG. 3 is a schematic diagram showing a third implementation of the product push method in the embodiment of the present invention;

FIG. 4 is a schematic diagram showing a fourth implementation of the product push method in the embodiment of the present invention;

FIG. 5 is a diagram showing a fifth embodiment of the product pushing method in the embodiment of the present invention;

FIG. 6 is a schematic diagram showing a sixth embodiment of the product pushing method in the embodiment of the present invention;

fig. 7 shows a schematic structural diagram of a product pushing device in an embodiment of the present invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments.

The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present invention, as presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present invention without making any creative effort, shall fall within the protection scope of the present invention.

Hereinafter, the terms "including", "having", and their derivatives, which may be used in various embodiments of the present invention, are intended to indicate only specific features, numerals, steps, operations, elements, components, or combinations of the foregoing, and should not be construed as first excluding the presence of or adding to one or more other features, numerals, steps, operations, elements, components, or combinations of the foregoing.

Furthermore, the terms "first," "second," "third," and the like are used solely to distinguish one from another and are not to be construed as indicating or implying relative importance.

Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which various embodiments of the present invention belong. The terms (such as terms defined in a commonly used dictionary) will be construed to have the same meaning as the contextual meaning in the related art and will not be construed to have an idealized or overly formal meaning unless expressly so defined in various embodiments of the present invention.

Example 1

In an actual scene, each merchant can promote each product to the user in an online promotion mode. For example, in the process of bank transaction, each bank pushes a plurality of products including financial products, activity commodities and the like to users through websites or application software on lines, but in the existing mode of user mining or product data pushing, products meeting the requirements of users or being interested by the users cannot be pushed individually to the users, so that the product pushing efficiency is low; in the product pushing process, the cover of the product is too single, so that the user is easy to lack interest and the purchasing desire is difficult to generate. Therefore, the embodiment provides a product pushing method, which is used for realizing personalized pushing of a product and a product cover thereof, and improving the experience effect of a user and the product pushing efficiency.

Referring to fig. 1, the product pushing method will be described in detail.

And S10, acquiring registration information, historical transaction records and product evaluation of the user.

The server acquires registration information of the user in the account registration process, and historical transaction records and product evaluation of the user in the account use process.

Exemplarily, when a user logs in a website or application software of a bank for the first time, the user needs to register, and in the user registration process, a plurality of options of products (or product types) and/or product covers (or product cover styles) are preset by the system for the user to select, and the user can select or input interested products and/or product covers (or product types and/or product cover styles) by himself according to needs; of course, the user may directly skip the operation and directly register. Thus, the user's registration information includes personal account information and data such as the product or product cover selected or entered by the user. When a user logs in a website or application software of a bank and purchases or evaluates a corresponding product or a product cover through an account of the user, the back end can automatically record the purchase record and the evaluation record of the user and specific purchase condition and evaluation content of the user.

And S20, analyzing the registration information, the historical transaction records and the product evaluation to obtain the preference degrees of all products and the preference degree of the cover of the product.

And respectively carrying out natural language processing on the registration information, the historical transaction records and the product evaluation, thereby extracting the language descriptions of the products and the product covers involved in the registration information, the historical transaction records and the product evaluation, and analyzing the language descriptions to calculate the preference of the user to each product and the preference of the product covers.

As a possible implementation manner, referring to fig. 2, the step S20 may specifically include the following steps:

s21, calculating the first product preference degree and the first product cover preference degree according to the registration information.

According to the products and/or product covers (or product types and/or product cover styles) selected from the registration information of the user or input by the user, calculating the first product preference and the first product cover preference of the user on each product. Further, a preset higher preference degree is set for the interested products and product covers selected by the user, in addition, the preference degree can be set to be zero or a preset lower preference degree is set for other products and product covers not selected by the user, and the preset preference degree can be set according to the actual situation, which is not limited herein.

And S22, calculating the purchase rate of each product according to the historical transaction records, and determining the preference degree of the second product and the preference degree of the cover of the second product according to the purchase rate.

The method comprises the steps of extracting the purchase condition of a user on each product from the historical transaction record of the user, calculating the number of each product purchased by the user, calculating the purchase rate of each product, and determining the product preference degree of the user on each product and the product cover preference degree of a product cover corresponding to the product according to the purchase rate.

Further, the product types corresponding to the purchased products can be counted according to the historical transaction records, the purchase rate of the product types corresponding to the products is calculated, and the product types interested by the user are determined according to the purchase rate of the product types.

And S23, performing emotional tendency analysis on the product evaluation, and determining the preference degree of the third product and the preference degree of the cover of the third product.

The method comprises the steps of obtaining at least one sentence containing a product or a product cover from product evaluation, carrying out semantic analysis on the sentences, carrying out sentiment tendency analysis on the product or the product cover related to the sentence according to the semantics of the sentence, and determining the product preference and the product cover preference of a user on each product according to the product evaluation. The emotional tendency includes a positive tendency, a negative tendency and a neutral tendency.

According to the method and the device, the emotional tendency analysis is carried out on the product evaluation, the preference condition of the user to each product or product cover can be accurately judged, the accuracy of calculating the preference degree of the product or product cover is improved, the preference condition of the user to each product or product cover is further improved, and the reliability and the accuracy of carrying out personalized recommendation on the user are achieved.

As a possible implementation manner, referring to fig. 3, the step S23 may specifically include the following steps:

s231, classifying the product evaluation to obtain first product evaluation data containing the product and second product evaluation data containing the product cover.

And performing natural language processing on the product evaluation, extracting a statement containing a keyword as a certain product to serve as the product evaluation corresponding to the product, and extracting a statement containing the keyword as a cover of the certain product to serve as the cover evaluation corresponding to the cover of the product. It can be understood that, in all product evaluations of the user, evaluation sentences corresponding to each product or each product cover may be extracted, that is, the product evaluations are classified according to keywords including the product or the product cover, so as to obtain first product evaluation data including the product and second product evaluation data including the product cover.

S232, performing word segmentation processing on the first product evaluation data and the second product evaluation data respectively to obtain a first word to be analyzed and a second word to be analyzed correspondingly.

And performing word segmentation processing on the first product evaluation data and the second product evaluation data respectively, namely performing word segmentation processing on a first product evaluation sentence containing a product and a second product evaluation sentence containing a product cover respectively to correspondingly obtain a first word to be analyzed and a second word to be analyzed. The word segmentation processing process can be implemented by using a preset word segmentation tool or a word segmentation algorithm with a word segmentation function, and the specific word segmentation tool or the word segmentation algorithm is not limited herein.

And S233, matching the first to-be-analyzed word and the second to-be-analyzed word with the emotional words in the preset word bank respectively, and calculating to obtain a corresponding first emotional tendency value and a corresponding second emotional tendency value.

And respectively matching the first words to be analyzed and the second words to be analyzed with the emotional words in the preset word bank so as to calculate the first emotional tendency value of the user to each product and the second emotional tendency value of the user to the cover of each product.

Specifically, the emotional tendency value can be determined according to the number of matched emotional words in the first word to be analyzed and the second word to be analyzed. For example, if the number of words in the first words to be analyzed that match the emotional words with positive tendencies is greater than the number of words that match the emotional words with negative tendencies, and the number of words that match the emotional words with positive tendencies is significantly higher than the negative tendencies, it indicates that the emotional tendency corresponding to the first words to be analyzed is a positive tendency. Therefore, the mapping relation between the number of words matched with the emotional words and the emotional tendency value can be set, so that the corresponding emotional tendency value can be determined. The setting of the mapping relationship may be set according to actual conditions, and is not limited herein.

As a possible implementation manner, referring to fig. 4, when each emotion word in the preset word library corresponds to an emotion reference value, step S233 specifically includes the following steps:

s2331, respectively matching the first words to be analyzed and the second words to be analyzed with emotion words in a preset word bank, and correspondingly obtaining target emotion words; wherein, a product or a product cover corresponds to at least one target emotional word.

And respectively matching the first to-be-analyzed word and the second to-be-analyzed word with the emotional words representing the positive tendency, the negative tendency and the neutral tendency in a preset word bank to correspondingly obtain a target emotional word, wherein one product or one product cover corresponds to at least one target emotional word.

S2332, calculating the product of the preset weight and the emotion reference value corresponding to the target emotion word, and correspondingly obtaining the first emotion tendency value of each product and the second emotion tendency value of each product cover.

Setting different emotion reference values for different emotion words according to the relevance of the emotion words and products or product covers provided by a bank, for example, setting the emotion reference value of the emotion words with positive tendency as a positive number, wherein the stronger the positive emotion is, the higher the emotion reference value is; setting the negative emotion reference value of negative emotion words as a negative number, wherein the stronger the negative emotion is, the lower the emotion reference value is; and setting the emotion reference value of the neutral tendency emotion words to be zero. It can be understood that the assignment of the specific emotion reference value can be set according to the actual situation, and is not limited herein.

And calculating the product of the preset weight and the corresponding emotion reference value of the corresponding target emotion word for one product or one product cover to obtain an emotion tendency sub-value. Specifically, the same or different weights are set for the positive tendency, the negative tendency and the neutral tendency respectively, and the emotional tendency sub-value of the product or the product cover is calculated according to the emotional reference value and the corresponding weight of each emotional word corresponding to the product or the product cover. In the same way, the emotional tendency value corresponding to each product or each product cover can be obtained. The specific value setting of the preset weight is not limited herein, and can be set correspondingly according to actual requirements.

And S234, determining the preference degree of a third product according to the first emotional tendency value, and determining the preference degree of a cover of the third product according to the second emotional tendency value.

And determining the preference degree of the user for the product or the product cover according to the emotional tendency value corresponding to each product or each product cover. For example, when the emotional tendency value of the product or the product cover is positive, it indicates that the user is positively inclined to the product or the product cover, and the greater the numerical value of the emotional tendency value, the higher the preference. Furthermore, the mapping relation between the value of the emotional tendency value and the preference degree can be preset, so that the preference degree of the user for each product or product cover can be determined according to the mapping relation. The specific mapping relationship between the value of the emotional tendency value and the preference degree can be set correspondingly according to actual requirements, and is not limited herein.

And S24, determining the product preference of the user to each product according to the first product preference, the second product preference and the third product preference.

And comprehensively calculating the preference degrees of the first product, the second product and the third product corresponding to the same product to obtain the preference degree of the user to the product, and calculating the product preference degrees of the user to all the products in the same way.

And S25, determining the product cover preference of the user to each product cover according to the first product cover preference, the second product cover preference and the third product cover preference.

The first product cover preference degree, the second product cover preference degree and the third product cover preference degree corresponding to the same product cover are comprehensively calculated, the product cover preference degree corresponding to the product cover by the user is obtained, and in the same way, the product cover preference degree of the user to all the product covers can be calculated.

As a possible implementation manner, referring to fig. 5, the step S25 may specifically include the following steps:

and S251, performing weight calculation on the cover preference of the first product, the cover preference of the second product and the cover preference of the third product corresponding to the same product according to a preset weight coefficient to obtain the cover preference of the product.

And calculating the weight of the first product cover preference degree, the second product cover preference degree and the third product cover preference degree corresponding to the same product according to a preset weight coefficient so as to obtain the product cover preference degree corresponding to the product. The registration information of the user, the historical transaction record and the weight value corresponding to the product evaluation can be preset, so that the weight value of the product cover preference of the user, the historical transaction record and the product evaluation can be calculated, and the product cover preference corresponding to the product can be obtained. The preset weight coefficient or the weight value can be set according to actual conditions, and is not limited herein.

And S252, calculating the product cover preference of each product.

After the product cover preference degrees of the same product are obtained, the product cover preference degrees of all the products can be calculated, namely the product cover preference degrees of all the products are calculated.

And S30, analyzing the style of the cover of each product preferred by the user according to the preference degree of the cover of the product to obtain the preference of the style of the cover of the user.

Analyzing the style of each product cover preferred by a user according to the product cover preference of each product; that is, the user's preference for the type of each product cover is analyzed.

Furthermore, the product covers are classified according to the corresponding styles, the product covers belonging to the same style characteristic can be classified according to the style characteristics corresponding to the product covers during classification, the product covers belonging to the same style characteristic belong to the same style type, and then the preference degree of the style type is calculated according to the preference degree of the product covers in the same style type. Specifically, one style type corresponds to at least one style characteristic, and product covers containing the corresponding style characteristic are classified into one style type, and one style type comprises at least one product cover. And performing addition operation or preset coefficient calculation on the preference degrees of the covers of all products contained in one style type to obtain the style preference of the covers of the users.

S40, sorting the products according to the product preference degrees, and selecting a preset number of preferred products.

And sequencing the products according to the corresponding product preference degrees, so as to select the optimal products with preset quantity. The preferable products are products with higher product preference degrees, and the preset number of the preferable products can be set according to actual conditions, and is not limited herein.

As a possible implementation manner, referring to fig. 6, step S40 further includes the following steps:

and S41, classifying the products to obtain a plurality of product types.

And classifying the products to obtain a plurality of product types, wherein one product type corresponds to at least one product. Further, the classification process may classify products that contain one or more of the same product characteristics into a product type based on at least one product characteristic (or product characteristic) contained in each product. That is, one product type corresponds to at least one product characteristic, and products including the corresponding product characteristic are classified as one product type. Wherein one product type may include at least one product.

And S42, calculating type preference degrees corresponding to the product types according to the product preference degrees of the products.

And calculating the type preference degree corresponding to each product type according to the product preference degree and the product type corresponding to each product. Specifically, the preference degrees of the products included in one product type are subjected to addition operation or predetermined coefficient calculation to obtain the type preference degrees of the product types.

S43, sorting the product types according to the sequence of the preference degrees of the types from large to small, and selecting N product types which are sorted in the front, wherein N is a natural number.

And selecting the product type with higher type preference from the multiple product types so as to conveniently select multiple products from the selected product types as preferred products. Specifically, the product types are sorted according to the order of the preference degrees of the types from large to small, and then N product types which are sorted in the front are selected, wherein N is a natural number.

And S44, selecting a preset number of preferable products from the N product types.

And selecting a preset number of preferable products from the N product types, wherein the preset number can be set according to actual conditions and is not limited herein.

For example, X products are respectively selected from N product types, that is, X products are selected as preferred products for each of the N product types, that is, (N × X) preferred products are selected, and X is a natural number; or, a certain number of products are randomly selected from each of the N product types as preferred products, and the number of the selected preferred products in each product type is not necessarily equal.

And S50, constructing a product cover of the preferred product according to the style preference of the cover.

And constructing a product cover of the preferred product according to the style preference of the cover corresponding to different users. In the process, the cover style with the highest cover style preference is selected as the design style of the product cover, and then the product cover of the preferred product is automatically generated according to the preferred product and the cover style by adopting the intelligent picture generator.

Illustratively, the intelligent picture generator may be a Dall-E (image generation system) that can create extremely realistic and clear images from a simple description, and master various artistic styles including illustrations and landscapes. It can also generate words to make signs on buildings and respectively make sketches and full-color images of the same scene. Further, deep learning can be performed on the Dall-E, so that a qualified product cover picture can be generated.

S60, pushing the preferred products containing the product covers to a user side.

The preferred product containing the product cover is pushed to the user side, i.e. the preferred product and its product cover are pushed to the user.

In one embodiment, when the product is pushed to the user, the preferred product containing the product cover can be pushed to the user terminal in a random arrangement order, so that the user terminal can randomly display the preferred product. That is, when the user receives the preferred product, the display effect is consistent, the display sequence is random display, the condition that a certain product is recommended in a key point does not exist, and the user can randomly select the product which is interested in to know or purchase.

In one embodiment, when pushing the product to the user, the preferred products including the product covers are pushed to the user side according to the order of the product preferences from large to small, so that the user side preferentially displays the preferred products with the product preferences being front. In this pushing manner, the user side may set different or the same display effects for the received preferred products, but the display order thereof will be displayed according to the respective corresponding preference degrees of each preferred product. For example, the preferred products are M in total, the M preferred products are sorted according to the preference degrees corresponding to the products from large to small, and N preferred products in the top of the sorting are selected for preferential display, wherein N and M are positive integers, and N is smaller than M. Furthermore, the preferential display mode can be that the selected N preferential products are preferentially displayed on a product display interface, then other preferential products are displayed in a paging mode, and finally other products are displayed, namely, a user can firstly view the selected N preferential products on a product display page, then click the next page or draw down the page or turn the page to view other preferential products, and finally view other products on the next page.

In the embodiment, the preference degree of the user for the product and the product cover is calculated by analyzing the registration information, the historical transaction record and the product evaluation of the user, the product cover of the style of the user preference cover is constructed according to the preference degree, and the preferred product containing the constructed product cover is pushed. According to the embodiment, the personalized recommendation to the user is realized, the products pushed by the user are all products which are interesting or preferred by the user, and the product pushing efficiency is improved; and when the product is pushed, the product cover preferred by the user is constructed according to the preference condition of the user to the product cover, so that the preferred product containing the constructed product cover is pushed to the user, the experience effect and the satisfaction degree of the user are improved, and the vitality of the system is further improved.

Example 2

Referring to fig. 7, an embodiment of the present invention provides a product pushing apparatus, including:

an obtaining module 71, configured to obtain registration information, a historical transaction record, and product evaluation of a user;

a first analysis module 72, configured to analyze the registration information, the historical transaction records, and the product evaluations to obtain product preferences and product cover preferences;

the second analysis module 73 is configured to analyze styles of product covers preferred by the user according to the product cover preference degrees to obtain cover style preferences of the user;

the sorting module 74 is used for sorting the products according to the product preference degrees and selecting a preset number of preferred products;

a construction module 75 for constructing a product cover of the preferred product according to the cover style preference;

a pushing module 76 for pushing the preferred product containing the product cover to the user end.

The above-described product pushing apparatus corresponds to the product pushing method of embodiment 1, and any options in embodiment 1 are also applicable to this embodiment, and are not described in detail here.

The embodiment of the present invention further provides a computer device, which includes a memory and at least one processor, where the memory stores a computer program, and the processor is configured to execute the computer program to implement the product pushing method of the foregoing embodiment.

The memory may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created from use of the computer device (such as preferred products, product preferences, etc.), and the like. Further, the memory may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device.

The embodiment of the present invention further provides a computer-readable storage medium, where a machine executable instruction is stored in the computer-readable storage medium, and when the machine executable instruction is called and executed by a processor, the computer executable instruction causes the processor to execute the steps of the product pushing method of the foregoing embodiment.

In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other manners. The apparatus embodiments described above are merely illustrative and, for example, the flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems that perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

In addition, each functional module or unit in each embodiment of the present invention may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention or a part of the technical solution that contributes to the prior art in essence can be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a smart phone, a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.

The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention.

Claims

1. A product push method, comprising:

and pushing the preferred products containing the product covers to a user end.

2. The product pushing method according to claim 1, wherein the analyzing the registration information, the historical transaction record and the product evaluation to obtain each product preference and product cover preference comprises:

3. The product pushing method of claim 2, wherein the performing an emotional tendency analysis on the product rating to determine a third product preference and a third product cover preference comprises:

4. The product pushing method according to claim 3, wherein each emotion word in the preset word bank corresponds to an emotion reference value, and the matching and calculating the first to-be-analyzed word and the second to-be-analyzed word with emotion words in the preset word bank to obtain a corresponding first emotion tendency value and a corresponding second emotion tendency value respectively comprises:

5. The product pushing method of claim 2, wherein determining the preference of each product cover based on the first product cover preference, the second product cover preference, and the third product cover preference comprises:

according to a preset weight coefficient, carrying out weight calculation on the first product cover preference degree, the second product cover preference degree and the third product cover preference degree corresponding to the same product to obtain the product cover preference degree of the product;

and calculating the product cover preference degrees of the products.

6. The product pushing method according to claim 1, wherein the sorting the products according to the product preference degrees and selecting a preset number of preferred products comprises:

classifying each product to obtain a plurality of product types;

calculating type preference degrees corresponding to various product types according to the product preference degrees of the various products;

and selecting a preset number of preferable products from the N product types.

7. The method for pushing a product according to claim 1, wherein the pushing a preferred product containing the product cover to a user side comprises:

pushing the preferred products containing the product covers to a user side in a random arrangement order, so that the user side displays the preferred products randomly; or the like, or, alternatively,

8. A product pusher device, comprising:

the acquisition module is used for acquiring registration information, historical transaction records and product evaluation of a user;

the sorting module is used for sorting the products according to the product preference degrees and selecting a preset number of preferred products;

the construction module is used for constructing a product cover of the preferred product according to the cover style preference;

9. A computer device, characterized in that the computer device comprises a memory and at least one processor, the memory storing a computer program for executing the computer program to implement the product push method of any of claims 1-7.

10. A computer storage medium, characterized in that it stores a computer program that, when executed, implements the product push method according to any one of claims 1-7.