CN106372961A - Commodity recommendation method and device - Google Patents
Commodity recommendation method and device Download PDFInfo
- Publication number
- CN106372961A CN106372961A CN201610712391.9A CN201610712391A CN106372961A CN 106372961 A CN106372961 A CN 106372961A CN 201610712391 A CN201610712391 A CN 201610712391A CN 106372961 A CN106372961 A CN 106372961A
- Authority
- CN
- China
- Prior art keywords
- category
- commodity
- commodities
- belonging
- determining
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000007477 logistic regression Methods 0.000 claims abstract description 51
- 239000013598 vector Substances 0.000 claims description 41
- 238000012549 training Methods 0.000 claims description 34
- 230000006399 behavior Effects 0.000 claims description 19
- 238000005516 engineering process Methods 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 9
- 239000003086 colorant Substances 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
Landscapes
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to a commodity recommendation method and device, and belongs to the field of the network technology. The method comprises the following steps of on the basis of a plurality of first user amounts, determining a commodity recommendation list, wherein each first user amount is the amount of users who purchase first-category commodities and execute an appointed behavior for each second-category commodity in a plurality of second-category commodities in a preset time period, and the commodity recommendation list comprises N second-category marks; for each second category in N second categories, on the basis of the mark of the second category, determining the marks of the plurality of commodities which belong to the second category; on the basis of target user characteristic information and the commodity characteristic information of the plurality of commodities which belong to the second category, determining a plurality of recommended purchase probabilities through an appointed logistic regression model; and on the basis of the plurality of recommended purchase probabilities, recommending a target commodity in the plurality of commodities which belong to the second category to the target user. Therefore, different commodities are recommended to different users in a targeted way, and commodity recommendation efficiency is improved.
Description
Technical Field
The present disclosure relates to the field of network technologies, and in particular, to a method and an apparatus for recommending a commodity.
Background
With the rapid development of network technology and e-commerce technology, network services are widely used. In the network service, usually, a provider publishes information about a commodity to be sold on a website, and a user can purchase the commodity in the network based on the website and the commodity information. However, at present, different providers can develop network services on the network, that is, different providers can publish different or the same commodity information on different websites, so that massive data appears in the network services, and thus users are prone to getting lost when selecting commodities.
Therefore, in order to solve the above-mentioned problems, that is, in a network service, in order to improve the purchasing efficiency and user experience of a user, a solution is needed to recommend a product that may be interested to the user to be recommended in a targeted manner according to the historical purchasing behavior of the historical user and the characteristic information (e.g., gender, age, income, etc.) of the user to be recommended, for example, different colors are recommended to users of different genders for the same product.
Disclosure of Invention
In order to overcome the problems in the related art, the present disclosure provides a method and an apparatus for recommending a commodity.
In a first aspect, a method for recommending goods is provided, the method comprising:
determining a commodity recommendation list based on the number of a plurality of first users, wherein each first user number is the number of users who purchase commodities of a first category and execute a specified action on the commodities of each second category in the commodities of a plurality of second categories in a preset time period, the commodity recommendation list comprises N second category identifications, and N is greater than or equal to 1 and less than or equal to the number of the second categories;
for each of the N second categories, determining, based on the identity of the second category, identities of a plurality of items belonging to the second category;
determining a plurality of recommended purchase probabilities by specifying a logistic regression model based on the target user feature information and the commodity feature information of the plurality of commodities belonging to the second category, each recommended purchase probability being a probability that the target user purchases each commodity belonging to the second category after each commodity belonging to the second category is recommended to the target user;
recommending a target commodity of the plurality of commodities belonging to the second category to the target user based on the plurality of recommended purchase probabilities.
Optionally, before determining the plurality of recommended purchase probabilities by specifying a logistic regression model based on the feature information of the target user and the feature information of the plurality of commodities belonging to the second category, the method further includes:
for each of the N second categories, obtaining historical user characteristic information of performing the specified behavior on a plurality of commodities belonging to the second category before a current time and commodity characteristic information of the plurality of commodities belonging to the second category;
generating a plurality of training feature vectors according to a specified combination strategy based on historical user feature information for executing the specified behavior on the plurality of commodities belonging to the second category and commodity feature information of the plurality of commodities belonging to the second category;
and training a preset logistic regression model based on the training feature vectors to obtain the specified logistic regression model.
Optionally, the determining a plurality of recommended purchase probabilities by specifying a logistic regression model based on the feature information of the target user and the feature information of the plurality of commodities belonging to the second category includes:
for each commodity in the plurality of commodities belonging to the second category, generating a target feature vector according to a specified combination strategy based on the commodity feature information of the commodity and the target user feature information;
and determining the recommended purchase probability of the commodity through the specified logistic regression model based on the target feature vector.
Optionally, said recommending a target commodity of the plurality of commodities belonging to the second category to the target user based on the plurality of recommended purchase probabilities includes;
determining the commodity with the highest recommended purchase probability in the plurality of commodities belonging to the second category as the target commodity, and recommending the target commodity to the target user; or,
determining the plurality of commodity income numerical values based on the plurality of recommended purchase probabilities and commodity prices of the plurality of commodities belonging to the second category, each commodity income numerical value being used for indicating actual income after each commodity belonging to the second category is recommended to the target user for a preset number of times; and determining the commodity with the largest commodity income value in the plurality of commodities belonging to the second category as the target commodity, and recommending the target commodity to the target user.
Optionally, the determining a recommendation list of goods based on the number of the first users includes:
determining a similarity between the first category and each of the plurality of second categories based on a first number of users;
selecting N second categories with the similarity degree larger than or equal to a preset threshold value with the first category from the plurality of second categories;
and generating the commodity recommendation list based on the identifications of the selected N second categories.
In a second aspect, there is provided an article recommendation device, the device comprising:
the commodity recommendation system comprises a first determining module, a second determining module and a commodity recommendation list, wherein the first determining module is used for determining a commodity recommendation list based on the number of a plurality of first users, each first user number is the number of users who purchase commodities of a first category and execute a specified action on the commodities of each second category in the commodities of a plurality of second categories in a preset time period, the commodity recommendation list comprises N second category identifications, and N is greater than or equal to 1 and smaller than or equal to the number of the second categories;
a second determining module, configured to determine, for each of the N second categories determined by the first determining module, an identification of a plurality of items belonging to the second category based on the identification of the second category;
a third determining module, configured to determine, based on the target user feature information and the commodity feature information of the plurality of commodities belonging to the second category, a plurality of recommended purchase probabilities through specifying a logistic regression model, where each recommended purchase probability is a probability that a target user purchases each commodity belonging to the second category after each commodity belonging to the second category is recommended to the target user;
and the recommending module is used for recommending the target commodity in the plurality of commodities belonging to the second category to the target user based on the plurality of recommended purchase probabilities determined by the third determining module.
Optionally, the apparatus further comprises:
an obtaining module, configured to obtain, for each of the N second categories, historical user characteristic information for performing the specified behavior on the plurality of commodities belonging to the second category before a current time and commodity characteristic information of the plurality of commodities belonging to the second category;
a generating module, configured to generate a plurality of training feature vectors according to a specified combination strategy based on historical user feature information for performing the specified behavior on the plurality of commodities belonging to the second category and commodity feature information of the plurality of commodities belonging to the second category;
and the training module is used for training a preset logistic regression model based on the training feature vectors generated by the generation module to obtain the specified logistic regression model.
Optionally, the third determining module includes:
a first generation sub-module, configured to generate, for each of the multiple commodities belonging to the second category, a target feature vector according to a specified combination policy based on the commodity feature information of the commodity and the target user feature information;
and the first determining submodule is used for determining the recommended purchase probability of the commodity through the specified logistic regression model based on the target feature vector.
Optionally, the recommendation module includes:
the first recommending submodule is used for determining the commodity with the highest recommended purchase probability in the commodities belonging to the second category as the target commodity and recommending the target commodity to the target user; or,
a second recommending sub-module, configured to determine the plurality of commodity income numerical values based on the plurality of recommended purchase probabilities and commodity prices of the plurality of commodities belonging to the second category, where each commodity income numerical value is used to indicate an actual income after each commodity belonging to the second category is recommended to the target user for a preset number of times; and determining the commodity with the largest commodity income value in the plurality of commodities belonging to the second category as the target commodity, and recommending the target commodity to the target user.
Optionally, the first determining module includes:
a second determining sub-module, configured to determine, based on a plurality of first user numbers, a similarity between the first category and each of the plurality of second categories;
the selecting submodule is used for selecting N second categories, wherein the similarity between the N second categories and the first category is greater than or equal to a preset threshold value, from the plurality of second categories;
and the second generation submodule is used for generating the commodity recommendation list based on the identifications of the selected N second categories.
In a third aspect, there is provided an article recommendation device, the device comprising:
a processor;
a memory for storing processor-executable instructions;
wherein the processor is configured to:
determining a commodity recommendation list based on the number of a plurality of first users, wherein each first user number is the number of users who purchase commodities of a first category and execute a specified action on the commodities of each second category in the commodities of a plurality of second categories in a preset time period, the commodity recommendation list comprises N second category identifications, and N is greater than or equal to 1 and less than or equal to the number of the second categories;
for each of the N second categories, determining, based on the identity of the second category, identities of a plurality of items belonging to the second category;
determining a plurality of recommended purchase probabilities by specifying a logistic regression model based on the target user feature information and the commodity feature information of the plurality of commodities belonging to the second category, each recommended purchase probability being a probability that the target user purchases each commodity belonging to the second category after each commodity belonging to the second category is recommended to the target user;
recommending a target commodity of the plurality of commodities belonging to the second category to the target user based on the plurality of recommended purchase probabilities.
The technical scheme provided by the embodiment of the disclosure can have the following beneficial effects:
in the embodiment of the present disclosure, based on the number of the plurality of first users, the item recommendation list including the identifiers of the N second categories is determined, that is, the N second categories are predetermined from the plurality of second categories, so that the items to be recommended are further determined based on the N second categories in the following. That is, for each of the N second categories, the identifiers of the plurality of commodities belonging to the second category are determined based on the identifiers of the second category, that is, the second category actually corresponds to the plurality of commodities, and the commodity feature information of the plurality of commodities is usually different, based on the target user feature information and the commodity feature information of the plurality of commodities, a plurality of recommended purchase probabilities can be determined through a specified logistic regression model which has been trained in advance, and since each recommended purchase probability is a probability that a target user purchases each commodity belonging to the second category after recommending the target user each commodity, based on the plurality of recommended purchase probabilities, the target commodity can be selected from the plurality of commodities and recommended to the target user, that is, based on different user feature information, from the plurality of commodities belonging to each second category, different commodities are selected and recommended to different users in a targeted manner, and the commodity recommendation efficiency is improved.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and together with the description, serve to explain the principles of the disclosure.
FIG. 1A is a schematic diagram illustrating one implementation environment in accordance with an illustrative embodiment.
FIG. 1B is a flow chart illustrating a method of merchandise recommendation, according to an example embodiment.
Fig. 2A is a flowchart illustrating a product recommendation method according to another exemplary embodiment.
Fig. 2B is a schematic diagram of a training feature vector according to the embodiment of fig. 2A.
Fig. 2C is a schematic diagram of a target feature vector according to the embodiment of fig. 2A.
FIG. 3A is a block diagram illustrating an article recommendation device according to an exemplary embodiment.
Fig. 3B is a block diagram illustrating an article recommendation device according to another exemplary embodiment.
Fig. 4 is a block diagram illustrating an article recommendation device 400 according to an exemplary embodiment.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.
Before explaining the embodiments of the present disclosure in detail, an application scenario of the embodiments of the present disclosure will be explained.
FIG. 1A is a schematic diagram illustrating one implementation environment in accordance with an illustrative embodiment. The implementation environment mainly includes a user terminal 110 and a server 120, and the user terminal 110 establishes a communication connection with the server 120 through a wired network or a wireless network.
A client or a browser may be operated in the user terminal 110, and web access may be performed through the client or the browser, so as to implement operations such as purchasing or browsing of goods. The user terminal 110 may be a smart phone, a tablet computer, a computer, or other devices, which is not limited in this disclosure.
The server 120 may be one server or a server cluster composed of a plurality of servers, and the server 120 is mainly used for implementing the commodity recommendation method provided by the embodiment of the present disclosure.
Fig. 1B is a flowchart illustrating a product recommendation method according to an exemplary embodiment, where the product recommendation method is used in a server, as shown in fig. 1B, and includes the following steps:
in step 101, a commodity recommendation list is determined based on a plurality of first user numbers, each first user number being a number of users who purchase commodities of a first category and perform a specified action on commodities of each second category in commodities of a plurality of second categories within a preset time period, the commodity recommendation list including identifications of N second categories, where N is greater than or equal to 1 and less than or equal to the number of the second categories.
In step 102, for each of the N second categories, an identification of a plurality of items belonging to the second category is determined based on the identification of the second category.
In step 103, a plurality of recommended purchase probabilities, each of which is a probability that a target user purchases each of the commodities belonging to the second category after recommending the commodity belonging to the second category to the target user, are determined by specifying a logistic regression model based on the target user feature information and the commodity feature information of the commodities belonging to the second category.
In step 104, a target commodity of the plurality of commodities belonging to the second category is recommended to the target user based on the plurality of recommended purchase probabilities.
In the embodiment of the present disclosure, based on the number of the plurality of first users, the item recommendation list including the identifiers of the N second categories is determined, that is, the N second categories are predetermined from the plurality of second categories, so that the items to be recommended are further determined based on the N second categories in the following. That is, for each of the N second categories, the identifiers of the plurality of commodities belonging to the second category are determined based on the identifiers of the second category, that is, the second category actually corresponds to the plurality of commodities, and the commodity feature information of the plurality of commodities is usually different, based on the target user feature information and the commodity feature information of the plurality of commodities, a plurality of recommended purchase probabilities can be determined through a specified logistic regression model which has been trained in advance, and since each recommended purchase probability is a probability that a target user purchases each commodity belonging to the second category after recommending the target user each commodity, based on the plurality of recommended purchase probabilities, the target commodity can be selected from the plurality of commodities and recommended to the target user, that is, based on different user feature information, from the plurality of commodities belonging to each second category, different commodities are selected and recommended to different users in a targeted manner, and the commodity recommendation efficiency is improved.
Optionally, before determining the plurality of recommended purchase probabilities by specifying a logistic regression model based on the feature information of the target user and the feature information of the plurality of commodities belonging to the second category, the method further includes:
for each of the N second categories, obtaining historical user characteristic information of a plurality of commodities belonging to the second category purchased before the current time and commodity characteristic information of the commodities belonging to the second category;
generating a plurality of training feature vectors according to a specified combination strategy based on historical user feature information of a plurality of commodities which are purchased and belong to the second category and commodity feature information of the commodities which belong to the second category;
and training a preset logistic regression model based on the training feature vectors to obtain the specified logistic regression model.
Optionally, determining a plurality of recommended purchase probabilities by specifying a logistic regression model based on the feature information of the target user and the feature information of the plurality of commodities belonging to the second category, including:
for each commodity in the plurality of commodities belonging to the second category, generating a target feature vector according to a specified combination strategy based on the commodity feature information of the commodity and the target user feature information;
and determining the recommended purchase probability of the commodity through the specified logistic regression model based on the target feature vector.
Optionally, recommending a target commodity of the plurality of commodities belonging to the second category to the target user based on the plurality of recommended purchase probabilities, including;
determining the commodity with the highest recommended purchase probability in the plurality of commodities belonging to the second category as the target commodity, and recommending the target commodity to the target user; or,
determining a plurality of commodity income numerical values based on the plurality of recommended purchase probabilities and commodity prices of a plurality of commodities belonging to the second category, wherein each commodity income numerical value is used for indicating actual income of each commodity belonging to the second category after being recommended to the target user for a preset number of times; and determining the commodity with the largest commodity income value in the plurality of commodities belonging to the second category as the target commodity, and recommending the target commodity to the target user.
Optionally, determining a recommendation list of goods based on the number of the first users comprises:
determining a similarity between the first category and each of the plurality of second categories based on a number of first users;
selecting N second categories with the similarity greater than or equal to a preset threshold value with the first category from the plurality of second categories;
and generating the commodity recommendation list based on the identifications of the selected N second categories.
All the above optional technical solutions can be combined arbitrarily to form optional embodiments of the present disclosure, and the embodiments of the present disclosure are not described in detail again.
Fig. 2A is a flowchart illustrating an article recommendation method according to another exemplary embodiment, as shown in fig. 2A, the article recommendation method being used in a server, the article recommendation method including the steps of:
in step 201, a product recommendation list is determined based on a plurality of first user numbers.
The number of the first users is the number of users who purchase the commodities of the first category and perform the specified action on the commodities of the second categories in the plurality of commodities of the second categories within the preset time period.
The preset time period may be set by a user according to actual needs in a self-defined manner, or may be set by a server in a default manner, which is not limited in the embodiment of the present disclosure.
The specific behavior can also be customized by the user according to actual needs, for example, the specific behavior can be a purchasing behavior or a browsing behavior.
Here, the first category of products is only one category of products, and actually, the products are not classified in detail, and for example, the first category of products may be a mobile phone, but information such as a color and a price of the mobile phone is not particularly indicated, that is, the first category of products is only a mobile phone, and what color and price are not mentioned. The second category of merchandise is similar to the first category of merchandise in meaning and will not be described herein.
The commodity recommendation list includes identifiers of N second categories, where N is greater than or equal to 1 and less than or equal to the number of the second categories. Wherein the identifier of the second category is used to uniquely identify a second category, for example, the identifier of the second category may be product _ id. That is, in this step, N items of the second category are determined based only on the number of the first users, for example, the N items of the second category include the mobile phone case, the mobile phone power supply, and the headset.
It should be noted that, the determining the recommended commodity list based on the number of the plurality of first users may be implemented by using a collaborative filtering method, and the implementation process may include: determining the similarity between the first category and each of the plurality of second categories based on the number of the first users, selecting N second categories from the plurality of second categories, wherein the similarity between the N second categories and the first category is greater than or equal to a preset threshold, and generating the commodity recommendation list based on the identifications of the N selected second categories.
The preset threshold may be set by a user according to actual needs in a self-defined manner, or may be set by the server in a default manner, which is not limited in the embodiment of the present disclosure.
The above specific implementation process for determining the similarity between the first category and each of the plurality of second categories based on the number of the first users may include: for each of the plurality of second categories, the server determines a similarity between the second category and the first category based on the plurality of first numbers of users by the following formula (1):
wherein J represents the similarity between the second class and the first class, uijRepresents the number of the first users, the uiRepresenting the number of users who purchased the first category of goods, ujRepresenting the number of users who purchased the second category of merchandise.
It should be noted that, the implementation method for determining the similarity between the first category and each of the plurality of second categories based on the number of the first users is only an example, and in another embodiment, the similarity may also be determined in other ways, which is not limited in the embodiment of the present disclosure.
In this embodiment of the disclosure, the greater the similarity between the second category and the first category is, it is indicated that after the commodity of the first category is purchased, the more the first users performing the specified action on the second category are, that is, the more the first users interested in the second category are, therefore, the server selects N second categories having a similarity greater than or equal to a preset threshold value with respect to the first category from the plurality of second categories, and generates the commodity recommendation list based on the identifiers of the N second categories.
In a possible implementation manner, after the server selects the N second categories, the identifiers of the N second categories may be sorted according to a descending order of similarity, so as to obtain the commodity recommendation list.
In step 202, for each of the N second categories, an identification of a plurality of items belonging to the second category is determined based on the identification of the second category.
That is, each second category includes a plurality of items, for example, if the item of the second category is a mobile phone shell, since the mobile phone shell includes a plurality of colors, for each color of mobile phone shell, an identification of an item is corresponding, and the identification of the item may be denoted as a goods _ id, that is, the product _ id corresponds to a plurality of goods _ ids.
The second category identifiers are stored in the server in correspondence with identifiers of a plurality of commodities belonging to the second category, and the server obtains identifiers of a plurality of commodities corresponding to each second category identifier.
In step 203, a plurality of recommended purchase probabilities are determined by specifying a logistic regression model based on the target user feature information and the commodity feature information of the plurality of commodities belonging to the second category.
And recommending the commodities belonging to the second category to a target user according to the recommended purchase probabilities, wherein the recommended purchase probabilities are probabilities that the target user purchases the commodities belonging to the second category after recommending the commodities belonging to the second category to the target user.
The target user characteristic information may be filled by the target user when registering an account, and then sent to the server through the user terminal, and stored in the database by the server.
Each commodity feature information is used for describing features of each commodity, and each commodity feature information may include a commodity color, a commodity price, a commodity size, a commodity specification, and the like, and referring to fig. 2B, each commodity feature information may further include a material, a style, and the like, which is not limited in this embodiment of the disclosure.
The implementation process of determining the recommended purchase probabilities by specifying a logistic regression model based on the target user feature information and the commodity feature information of the plurality of commodities belonging to the second category includes: and for each commodity in the plurality of commodities belonging to the second category, generating a target feature vector according to a specified combination strategy based on the commodity feature information of the commodity and the target user feature information, and determining the recommended purchase probability of the commodity through the specified logistic regression model based on the target feature vector.
The implementation process of generating the target feature vector according to the specified combination policy based on the commodity feature information of the commodity and the target user feature information may include: referring to fig. 2C, in a possible implementation manner, according to actual needs, the color of the product in the product feature information and the gender in the target user feature information may be feature-combined, and the price of the product in the product feature information and the income in the target user feature information may be feature-combined to obtain the target feature vector.
Through the combination mode, commodities with colors and prices which may be interested in can be recommended for the target user according to the gender and income of the target user. The recommendation process comprises the following steps: based on the target feature vector, through the specified logistic regression model, the probability that the target user may purchase each commodity after each commodity with different color, different price and other features is recommended to the target user can be determined.
It should be noted that, the above feature combination of the color of the product in the product feature information and the gender in the feature information of the target user, and the feature combination of the price of the product in the product feature information and the income in the feature information of the target user are only examples, in another embodiment, the specified combination policy may further include other combination manners, and the embodiment of the present disclosure does not limit this.
In addition, it should be noted that, the specific implementation process for determining the recommended purchase probability of the commodity through the specified logistic regression model based on the target feature vector may be referred to in the related art, and this is not described in detail in this embodiment of the disclosure.
Further, before determining the plurality of recommended purchase probabilities, determining the designated logistic regression model is further required, wherein determining the implementation process of the designated logistic regression module comprises:
for each of the N second categories, obtaining historical user feature information for performing a specified behavior on a plurality of commodities belonging to the second category before the current time and commodity feature information of the plurality of commodities belonging to the second category, generating a plurality of training feature vectors according to a specified combination strategy based on the historical user feature information for performing the specified behavior on the plurality of commodities belonging to the second category and the commodity feature information of the plurality of commodities belonging to the second category, and training a preset logistic regression model based on the plurality of training feature vectors to obtain the specified logistic regression model.
The specified combination policy may be set in the server in advance.
That is, for each of the N second categories, since some historical users purchased a plurality of commodities belonging to the second category or some historical users viewed only a plurality of commodities belonging to the second category before the current time, the server may generate the training feature vector based on all of the historical user feature information for performing the specified behavior on each commodity belonging to the second category and the commodity feature information of each commodity.
In the process of generating the training feature vector, the historical user feature information and the commodity feature information may also be feature-combined according to an appointed combination strategy according to an actual requirement, for example, refer to fig. 2B, where fig. 2B shows a training feature vector, that is, gender in the historical user feature information and color in the commodity feature information may be feature-combined, and income in the historical user feature information and price may be feature-combined, and through the combination method, through an appointed logistic regression model after training, color preferences of users with different genders for commodities belonging to the second category and price preferences of users with different incomes for commodities belonging to the second category may be determined.
In the generated training feature vector, it is necessary to mark the designated behavior of the historical user in order to determine how many historical users purchased the product, for example, in fig. 2B, when a historical user purchased the product, the server marks "Yes" in the purchase field corresponding to the position of the purchase field, and when the historical user browses the product but did not purchase the product, the server marks "NO" in the purchase field corresponding to the position of the purchase field.
It should be noted that, in the process of generating the training feature vector, besides the historical user feature information and the commodity feature information, context feature information and other feature information may also be involved, which is not limited by the embodiment of the present disclosure.
Based on the training feature vectors, the implementation process of training the preset logistic regression model may include processes of training feature vector transformation, logistic regression, model generation and the like, and in addition, after the specified logistic regression model is obtained through training, operations such as evaluation and storage and the like may also be performed on the specified logistic regression model, which is not described in detail in the embodiments of the present disclosure.
In step 204, a target commodity in the plurality of commodities belonging to the second category is recommended to the target user based on the plurality of recommended purchase probabilities.
In an actual implementation, for a product provider, different recommendation purposes may be desired to be achieved in a product recommendation process, for example, in one possible implementation, a purpose of performing product recommendation is to increase a sales volume of a product, and in another possible implementation, a purpose of performing product recommendation is to increase a total sales volume, so that, according to a purpose of product recommendation, recommending a target product of the plurality of products belonging to the second category to the target user based on the plurality of recommended purchase probabilities may include any one of the following implementations:
the first mode is as follows: and determining the commodity with the highest recommended purchase probability in the plurality of commodities belonging to the second category as the target commodity, and recommending the target commodity to the target user.
That is, in this implementation, since the greater the recommended purchase probability, the greater the possibility that the target user will purchase after recommending the product corresponding to the recommended purchase probability to the target user is described, it is understood that, in order to increase the sales volume of the product, the product having the highest recommended purchase probability among the plurality of products belonging to the second category may be recommended to the target user for each of the plurality of second categories, and thus, the sales volume of the product may be increased.
The second mode is as follows: determining the plurality of commodity income numerical values based on the plurality of recommended purchase probabilities and commodity prices of the plurality of commodities belonging to the second category, wherein each commodity income numerical value is used for indicating actual income of each commodity belonging to the second category after the commodity is recommended to the target user for a preset number of times, determining the commodity with the largest commodity income numerical value in the plurality of commodities belonging to the second category as the target commodity, and recommending the target commodity to the target user.
The preset times may be set by a user according to actual needs in a user-defined manner, or may be set by the server in a default manner, which is not limited in the embodiment of the present disclosure.
Unlike the first implementation, in this implementation, the main purpose is to increase the total sales amount, that is, in the first implementation described above, although the item with the largest value of the commodity income among the plurality of items belonging to the second category is determined as the target item, since the price of the determined target item may be low, the total sales amount may not be the largest after the determined target item is recommended to the target user.
To this end, in this implementation, the server determines the income values of the plurality of commodities based on the recommended purchase probabilities and commodity prices of the commodities belonging to the second category, and the specific implementation process includes: and the server multiplies the recommended purchase probabilities by the prices of the commodities, and then multiplies the products obtained by the multiplication by the preset times to obtain commodity income numerical values of the commodities belonging to the second category.
For example, in the above implementation, if the product price of a certain product belonging to the second category is P, the preset number of times is 1000 times, and the recommended purchase probability of the product is B, the product income value of the product is R ═ B × P × 1000, where "×" represents multiplication, and thus the product income value of the product is obtained.
If the value of the commodity income is larger, the actual income obtained after the commodity is recommended to the target user is larger, that is, the obtained total sales amount is larger, therefore, for each second category in the second categories, the server determines the commodity with the largest commodity income value in the commodities belonging to the second category as the target commodity, so that the recommended commodity is a commodity which is interested by the target user, and meanwhile, the total sales amount is also improved, that is, the maximum total sales amount is ensured.
In one possible implementation, the commodity revenue values of the respective target commodities belonging to the respective second categories recommended for the target users may be in the form of a list, for example, as shown in table 1 below.
TABLE 1
| User_id | Value of commodity income |
| User_1 | goods_i:Ri,goods_g:Rg,... |
| ... | ... |
Wherein, User _1 represents the target User, and the goods _ i: Ri represents the target product goods _ i belonging to the second category i, and similarly, the goods _ g: Rg represents the target product goods _ g belonging to the second category g, and the product income value is Rg.
The method and the device for recommending the commodities to the target user in different modes can achieve different effects and increase commodity recommending modes.
In the embodiment of the present disclosure, based on the number of the plurality of first users, the item recommendation list including the identifiers of the N second categories is determined, that is, the N second categories are predetermined from the plurality of second categories, so that the items to be recommended are further determined based on the N second categories in the following. That is, for each of the N second categories, the identifiers of the plurality of commodities belonging to the second category are determined based on the identifiers of the second category, that is, the second category actually corresponds to the plurality of commodities, and the commodity feature information of the plurality of commodities is usually different, based on the target user feature information and the commodity feature information of the plurality of commodities, a plurality of recommended purchase probabilities can be determined through a specified logistic regression model which has been trained in advance, and since each recommended purchase probability is a probability that a target user purchases each commodity belonging to the second category after recommending the target user each commodity, based on the plurality of recommended purchase probabilities, the target commodity can be selected from the plurality of commodities and recommended to the target user, that is, based on different user feature information, from the plurality of commodities belonging to each second category, different commodities are selected and recommended to different users in a targeted manner, and the commodity recommendation efficiency is improved.
FIG. 3A is a block diagram illustrating an article recommendation device according to an exemplary embodiment. Referring to fig. 3A, the apparatus includes a first determination module 310, a second determination module 320, a third determination module 330, and a recommendation module 340.
A first determining module 310, configured to determine a commodity recommendation list based on a plurality of first user numbers, where each first user number is a number of users who purchase a first category of commodities and perform a specified action on each second category of commodities in a plurality of second categories of commodities within a preset time period, and the commodity recommendation list includes identifiers of N second categories, where N is greater than or equal to 1 and less than or equal to the number of the plurality of second categories;
a second determining module 320, configured to determine, for each of the N second categories determined by the first determining module, an identification of a plurality of items belonging to the second category based on the identification of the second category;
a third determining module 330, configured to determine, based on the target user feature information and the commodity feature information of the multiple commodities belonging to the second category, multiple recommended purchase probabilities through specifying a logistic regression model, where each recommended purchase probability is a probability that a target user purchases each commodity belonging to the second category after recommending each commodity belonging to the second category to the target user;
a recommending module 340, configured to recommend a target product of the plurality of products belonging to the second category to the target user based on the plurality of recommended purchase probabilities determined by the third determining module.
Optionally, referring to fig. 3B, the apparatus further includes:
an obtaining module 350, configured to obtain, for each of the N second categories, historical user characteristic information of performing the specified behavior on the multiple commodities belonging to the second category before the current time and commodity characteristic information of the multiple commodities belonging to the second category;
a generating module 360, configured to generate a plurality of training feature vectors according to a specified combination strategy based on historical user feature information for performing the specified behavior on the plurality of commodities belonging to the second category and commodity feature information of the plurality of commodities belonging to the second category;
the training module 370 is configured to train a preset logistic regression model based on the training feature vectors generated by the generating module to obtain the specified logistic regression model.
Optionally, the third determining module 330 includes:
the first generation submodule is used for generating a target feature vector according to a specified combination strategy on the basis of the commodity feature information of the commodity and the target user feature information for each commodity in the plurality of commodities belonging to the second category;
and the first determining submodule is used for determining the recommended purchase probability of the commodity through the specified logistic regression model based on the target feature vector.
Optionally, the recommending module 340 includes:
the first recommending submodule is used for determining the commodity with the highest recommended purchase probability in the commodities belonging to the second category as the target commodity and recommending the target commodity to the target user; or,
a second recommending sub-module, configured to determine, based on the plurality of recommended purchase probabilities and commodity prices of a plurality of commodities belonging to the second category, a plurality of commodity income values, each commodity income value being used to indicate an actual income after recommending, to the target user, each commodity belonging to the second category for a preset number of times; and determining the commodity with the largest commodity income value in the plurality of commodities belonging to the second category as the target commodity, and recommending the target commodity to the target user.
Optionally, the first determining module 310 includes:
a second determining sub-module, configured to determine a similarity between the first category and each of the plurality of second categories based on a plurality of first user numbers;
the selecting submodule is used for selecting N second categories, wherein the similarity between the N second categories and the first category is greater than or equal to a preset threshold value, from the plurality of second categories;
and the second generation submodule is used for generating the commodity recommendation list based on the identifications of the selected N second categories.
In the embodiment of the present disclosure, based on the number of the plurality of first users, the item recommendation list including the identifiers of the N second categories is determined, that is, the N second categories are predetermined from the plurality of second categories, so that the items to be recommended are further determined based on the N second categories in the following. That is, for each of the N second categories, the identifiers of the plurality of commodities belonging to the second category are determined based on the identifiers of the second category, that is, the second category actually corresponds to the plurality of commodities, and the commodity feature information of the plurality of commodities is usually different, based on the target user feature information and the commodity feature information of the plurality of commodities, a plurality of recommended purchase probabilities can be determined through a specified logistic regression model which has been trained in advance, and since each recommended purchase probability is a probability that a target user purchases each commodity belonging to the second category after recommending the target user each commodity, based on the plurality of recommended purchase probabilities, the target commodity can be selected from the plurality of commodities and recommended to the target user, that is, based on different user feature information, from the plurality of commodities belonging to each second category, different commodities are selected and recommended to different users in a targeted manner, and the commodity recommendation efficiency is improved.
With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.
Fig. 4 is a block diagram illustrating an article recommendation device 400 according to an exemplary embodiment. For example, the apparatus 400 may be provided as a server. Referring to fig. 4, apparatus 400 includes a processing component 422, which further includes one or more processors, and memory resources, represented by memory 432, for storing instructions, such as applications, that are executable by processing component 422. The application programs stored in memory 432 may include one or more modules that each correspond to a set of instructions. Further, the processing component 422 is configured to execute instructions to perform the method for recommending merchandise according to the embodiment of fig. 1B or fig. 2.
The apparatus 400 may also include a power component 426 configured to perform power management of the apparatus 400, a wired or wireless network interface 450 configured to connect the apparatus 400 to a network, and an input output (I/O) interface 458. The apparatus 400 may operate based on an operating system, such as Windows Server, stored in the memory 432TM，Mac OS XTM，UnixTM,LinuxTM，FreeBSDTMOr the like.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
Claims (11)
1. A method for recommending an article, the method comprising:
determining a commodity recommendation list based on the number of a plurality of first users, wherein each first user number is the number of users who purchase commodities of a first category and execute a specified action on the commodities of each second category in the commodities of a plurality of second categories in a preset time period, the commodity recommendation list comprises N second category identifications, and N is greater than or equal to 1 and less than or equal to the number of the second categories;
for each of the N second categories, determining, based on the identity of the second category, identities of a plurality of items belonging to the second category;
determining a plurality of recommended purchase probabilities by specifying a logistic regression model based on the target user feature information and the commodity feature information of the plurality of commodities belonging to the second category, each recommended purchase probability being a probability that the target user purchases each commodity belonging to the second category after each commodity belonging to the second category is recommended to the target user;
recommending a target commodity of the plurality of commodities belonging to the second category to the target user based on the plurality of recommended purchase probabilities.
2. The method of claim 1, wherein before determining the plurality of recommended purchase probabilities by specifying a logistic regression model based on the characteristic information of the target user and the characteristic information of the plurality of commodities belonging to the second category, further comprising:
for each of the N second categories, obtaining historical user characteristic information of performing the specified behavior on a plurality of commodities belonging to the second category before a current time and commodity characteristic information of the plurality of commodities belonging to the second category;
generating a plurality of training feature vectors according to a specified combination strategy based on historical user feature information for executing the specified behavior on the plurality of commodities belonging to the second category and commodity feature information of the plurality of commodities belonging to the second category;
and training a preset logistic regression model based on the training feature vectors to obtain the specified logistic regression model.
3. The method of claim 1 or 2, wherein the determining a plurality of recommended purchase probabilities by specifying a logistic regression model based on the characteristic information of the target user and the characteristic information of the plurality of commodities belonging to the second category comprises:
for each commodity in the plurality of commodities belonging to the second category, generating a target feature vector according to a specified combination strategy based on the commodity feature information of the commodity and the target user feature information;
and determining the recommended purchase probability of the commodity through the specified logistic regression model based on the target feature vector.
4. The method of claim 1, wherein said recommending a target item of the plurality of items belonging to the second category to the target user based on the plurality of recommended purchase probabilities comprises;
determining the commodity with the highest recommended purchase probability in the plurality of commodities belonging to the second category as the target commodity, and recommending the target commodity to the target user; or,
determining the plurality of commodity income numerical values based on the plurality of recommended purchase probabilities and commodity prices of the plurality of commodities belonging to the second category, each commodity income numerical value being used for indicating actual income after each commodity belonging to the second category is recommended to the target user for a preset number of times; and determining the commodity with the largest commodity income value in the plurality of commodities belonging to the second category as the target commodity, and recommending the target commodity to the target user.
5. The method of claim 1, wherein determining a recommendation list for the item based on the first plurality of user quantities comprises:
determining a similarity between the first category and each of the plurality of second categories based on a first number of users;
selecting N second categories with the similarity degree larger than or equal to a preset threshold value with the first category from the plurality of second categories;
and generating the commodity recommendation list based on the identifications of the selected N second categories.
6. An article recommendation device, the device comprising:
the commodity recommendation system comprises a first determining module, a second determining module and a commodity recommendation list, wherein the first determining module is used for determining a commodity recommendation list based on the number of a plurality of first users, each first user number is the number of users who purchase commodities of a first category and execute a specified action on the commodities of each second category in the commodities of a plurality of second categories in a preset time period, the commodity recommendation list comprises N second category identifications, and N is greater than or equal to 1 and smaller than or equal to the number of the second categories;
a second determining module, configured to determine, for each of the N second categories determined by the first determining module, an identification of a plurality of items belonging to the second category based on the identification of the second category;
a third determining module, configured to determine, based on the target user feature information and the commodity feature information of the plurality of commodities belonging to the second category, a plurality of recommended purchase probabilities through specifying a logistic regression model, where each recommended purchase probability is a probability that a target user purchases each commodity belonging to the second category after each commodity belonging to the second category is recommended to the target user;
and the recommending module is used for recommending the target commodity in the plurality of commodities belonging to the second category to the target user based on the plurality of recommended purchase probabilities determined by the third determining module.
7. The apparatus of claim 6, wherein the apparatus further comprises:
an obtaining module, configured to obtain, for each of the N second categories, historical user characteristic information for performing the specified behavior on the plurality of commodities belonging to the second category before a current time and commodity characteristic information of the plurality of commodities belonging to the second category;
a generating module, configured to generate a plurality of training feature vectors according to a specified combination strategy based on historical user feature information for performing the specified behavior on the plurality of commodities belonging to the second category and commodity feature information of the plurality of commodities belonging to the second category;
and the training module is used for training a preset logistic regression model based on the training feature vectors generated by the generation module to obtain the specified logistic regression model.
8. The apparatus of claim 6 or 7, wherein the third determining module comprises:
a first generation sub-module, configured to generate, for each of the multiple commodities belonging to the second category, a target feature vector according to a specified combination policy based on the commodity feature information of the commodity and the target user feature information;
and the first determining submodule is used for determining the recommended purchase probability of the commodity through the specified logistic regression model based on the target feature vector.
9. The apparatus of claim 6, wherein the recommendation module comprises:
the first recommending submodule is used for determining the commodity with the highest recommended purchase probability in the commodities belonging to the second category as the target commodity and recommending the target commodity to the target user; or,
a second recommending sub-module, configured to determine the plurality of commodity income numerical values based on the plurality of recommended purchase probabilities and commodity prices of the plurality of commodities belonging to the second category, where each commodity income numerical value is used to indicate an actual income after each commodity belonging to the second category is recommended to the target user for a preset number of times; and determining the commodity with the largest commodity income value in the plurality of commodities belonging to the second category as the target commodity, and recommending the target commodity to the target user.
10. The apparatus of claim 6, wherein the first determining module comprises:
a second determining sub-module, configured to determine, based on a plurality of first user numbers, a similarity between the first category and each of the plurality of second categories;
the selecting submodule is used for selecting N second categories, wherein the similarity between the N second categories and the first category is greater than or equal to a preset threshold value, from the plurality of second categories;
and the second generation submodule is used for generating the commodity recommendation list based on the identifications of the selected N second categories.
11. An article recommendation device, the device comprising:
a processor;
a memory for storing processor-executable instructions;
wherein the processor is configured to:
determining a commodity recommendation list based on the number of a plurality of first users, wherein each first user number is the number of users who purchase commodities of a first category and execute a specified action on the commodities of each second category in the commodities of a plurality of second categories in a preset time period, the commodity recommendation list comprises N second category identifications, and N is greater than or equal to 1 and less than or equal to the number of the second categories;
for each of the N second categories, determining, based on the identity of the second category, identities of a plurality of items belonging to the second category;
determining a plurality of recommended purchase probabilities by specifying a logistic regression model based on the target user feature information and the commodity feature information of the plurality of commodities belonging to the second category, each recommended purchase probability being a probability that the target user purchases each commodity belonging to the second category after each commodity belonging to the second category is recommended to the target user;
recommending a target commodity of the plurality of commodities belonging to the second category to the target user based on the plurality of recommended purchase probabilities.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610712391.9A CN106372961A (en) | 2016-08-23 | 2016-08-23 | Commodity recommendation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610712391.9A CN106372961A (en) | 2016-08-23 | 2016-08-23 | Commodity recommendation method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106372961A true CN106372961A (en) | 2017-02-01 |
Family
ID=57878937
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610712391.9A Pending CN106372961A (en) | 2016-08-23 | 2016-08-23 | Commodity recommendation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106372961A (en) |
Cited By (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107341272A (en) * | 2017-08-25 | 2017-11-10 | 北京奇艺世纪科技有限公司 | A kind of method for pushing, device and electronic equipment |
| CN108053305A (en) * | 2018-02-12 | 2018-05-18 | 北京小度信息科技有限公司 | The data processing method and device promoted applied to trade company |
| CN108090807A (en) * | 2017-12-13 | 2018-05-29 | 北京小度信息科技有限公司 | Information recommendation method and device |
| CN108154420A (en) * | 2017-12-26 | 2018-06-12 | 泰康保险集团股份有限公司 | Products Show method and device, storage medium, electronic equipment |
| CN108198051A (en) * | 2018-03-01 | 2018-06-22 | 口碑(上海)信息技术有限公司 | Across the Method of Commodity Recommendation and device of merchandise classification |
| CN108304115A (en) * | 2018-02-12 | 2018-07-20 | 广东欧珀移动通信有限公司 | Terminal entry selection method, device and storage medium and terminal |
| CN108628863A (en) * | 2017-03-15 | 2018-10-09 | 百度在线网络技术（北京）有限公司 | Information acquisition method and device |
| CN108932530A (en) * | 2018-06-29 | 2018-12-04 | 新华三大数据技术有限公司 | The construction method and device of label system |
| CN108959340A (en) * | 2018-03-30 | 2018-12-07 | 深圳春沐源控股有限公司 | Page display method and page display system |
| CN109242649A (en) * | 2018-10-31 | 2019-01-18 | 广州品唯软件有限公司 | A kind of Method of Commodity Recommendation and relevant apparatus |
| CN109635153A (en) * | 2018-11-22 | 2019-04-16 | 腾讯音乐娱乐科技（深圳）有限公司 | Migration path generation method, device and storage medium |
| CN110069540A (en) * | 2017-09-08 | 2019-07-30 | 北京京东尚科信息技术有限公司 | Information output method and device |
| CN110111186A (en) * | 2019-05-10 | 2019-08-09 | 拉扎斯网络科技（上海）有限公司 | Information processing method, information processing device, electronic equipment and computer readable storage medium |
| CN110134469A (en) * | 2018-02-09 | 2019-08-16 | 优视科技有限公司 | Switching method, device and the computer equipment of holiday theme |
| CN110519318A (en) * | 2018-05-22 | 2019-11-29 | 北京京东尚科信息技术有限公司 | Information-pushing method and device |
| CN110838043A (en) * | 2019-11-05 | 2020-02-25 | 智者四海（北京）技术有限公司 | Commodity recommendation method and device |
| CN111009299A (en) * | 2019-12-17 | 2020-04-14 | 武汉海云健康科技股份有限公司 | Similar medicine recommendation method and system, server and medium |
| CN111199459A (en) * | 2019-12-30 | 2020-05-26 | 深圳市盟天科技有限公司 | Commodity recommendation method and device, electronic equipment and storage medium |
| CN111695922A (en) * | 2019-03-15 | 2020-09-22 | 北京沃东天骏信息技术有限公司 | Potential user determination method and device, storage medium and electronic equipment |
| CN111861623A (en) * | 2019-12-30 | 2020-10-30 | 北京骑胜科技有限公司 | Information recommendation method, device and equipment |
| US10922737B2 (en) | 2017-12-22 | 2021-02-16 | Industrial Technology Research Institute | Interactive product recommendation method and non-transitory computer-readable medium |
| CN113379516A (en) * | 2021-08-12 | 2021-09-10 | 永正信息技术(南京)有限公司 | Recommended product determination method and device |
| CN113610608A (en) * | 2021-08-19 | 2021-11-05 | 创优数字科技(广东)有限公司 | User preference recommendation method and device, electronic equipment and storage medium |
| CN115471302A (en) * | 2022-11-14 | 2022-12-13 | 山东智豆数字科技有限公司 | Electronic marketing data processing method based on big data analysis |
| CN113486948B (en) * | 2021-07-01 | 2024-09-06 | 有米科技股份有限公司 | Clothing commodity gender classification method and device based on text data |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8452797B1 (en) * | 2011-03-09 | 2013-05-28 | Amazon Technologies, Inc. | Personalized recommendations based on item usage |
| CN103345695A (en) * | 2013-06-25 | 2013-10-09 | 百度在线网络技术（北京）有限公司 | Commodity recommendation method and device |
| CN103577473A (en) * | 2012-08-03 | 2014-02-12 | 纽海信息技术（上海）有限公司 | Classification and disambiguation method, classification and disambiguation device and system thereof |
| CN103679494A (en) * | 2012-09-17 | 2014-03-26 | 阿里巴巴集团控股有限公司 | Commodity information recommendation method and device |
| CN105469263A (en) * | 2014-09-24 | 2016-04-06 | 阿里巴巴集团控股有限公司 | Commodity recommendation method and device |
| CN105809479A (en) * | 2016-03-07 | 2016-07-27 | 海信集团有限公司 | Item recommending method and device |
-
2016
- 2016-08-23 CN CN201610712391.9A patent/CN106372961A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8452797B1 (en) * | 2011-03-09 | 2013-05-28 | Amazon Technologies, Inc. | Personalized recommendations based on item usage |
| CN103577473A (en) * | 2012-08-03 | 2014-02-12 | 纽海信息技术（上海）有限公司 | Classification and disambiguation method, classification and disambiguation device and system thereof |
| CN103679494A (en) * | 2012-09-17 | 2014-03-26 | 阿里巴巴集团控股有限公司 | Commodity information recommendation method and device |
| CN103345695A (en) * | 2013-06-25 | 2013-10-09 | 百度在线网络技术（北京）有限公司 | Commodity recommendation method and device |
| CN105469263A (en) * | 2014-09-24 | 2016-04-06 | 阿里巴巴集团控股有限公司 | Commodity recommendation method and device |
| CN105809479A (en) * | 2016-03-07 | 2016-07-27 | 海信集团有限公司 | Item recommending method and device |
Cited By (31)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108628863A (en) * | 2017-03-15 | 2018-10-09 | 百度在线网络技术（北京）有限公司 | Information acquisition method and device |
| CN107341272A (en) * | 2017-08-25 | 2017-11-10 | 北京奇艺世纪科技有限公司 | A kind of method for pushing, device and electronic equipment |
| CN110069540A (en) * | 2017-09-08 | 2019-07-30 | 北京京东尚科信息技术有限公司 | Information output method and device |
| CN108090807A (en) * | 2017-12-13 | 2018-05-29 | 北京小度信息科技有限公司 | Information recommendation method and device |
| US10922737B2 (en) | 2017-12-22 | 2021-02-16 | Industrial Technology Research Institute | Interactive product recommendation method and non-transitory computer-readable medium |
| CN108154420A (en) * | 2017-12-26 | 2018-06-12 | 泰康保险集团股份有限公司 | Products Show method and device, storage medium, electronic equipment |
| CN110134469A (en) * | 2018-02-09 | 2019-08-16 | 优视科技有限公司 | Switching method, device and the computer equipment of holiday theme |
| CN108304115A (en) * | 2018-02-12 | 2018-07-20 | 广东欧珀移动通信有限公司 | Terminal entry selection method, device and storage medium and terminal |
| CN108053305B (en) * | 2018-02-12 | 2021-07-30 | 北京星选科技有限公司 | Data processing method and device applied to merchant promotion |
| CN108304115B (en) * | 2018-02-12 | 2020-12-04 | Oppo广东移动通信有限公司 | Terminal item selection method and device, storage medium and terminal |
| CN108053305A (en) * | 2018-02-12 | 2018-05-18 | 北京小度信息科技有限公司 | The data processing method and device promoted applied to trade company |
| CN108198051A (en) * | 2018-03-01 | 2018-06-22 | 口碑(上海)信息技术有限公司 | Across the Method of Commodity Recommendation and device of merchandise classification |
| CN108959340A (en) * | 2018-03-30 | 2018-12-07 | 深圳春沐源控股有限公司 | Page display method and page display system |
| CN110519318A (en) * | 2018-05-22 | 2019-11-29 | 北京京东尚科信息技术有限公司 | Information-pushing method and device |
| CN110519318B (en) * | 2018-05-22 | 2023-08-04 | 北京京东尚科信息技术有限公司 | Information pushing method and device |
| CN108932530A (en) * | 2018-06-29 | 2018-12-04 | 新华三大数据技术有限公司 | The construction method and device of label system |
| CN109242649A (en) * | 2018-10-31 | 2019-01-18 | 广州品唯软件有限公司 | A kind of Method of Commodity Recommendation and relevant apparatus |
| CN109635153B (en) * | 2018-11-22 | 2023-01-13 | 腾讯音乐娱乐科技（深圳）有限公司 | Migration path generation method, device and storage medium |
| CN109635153A (en) * | 2018-11-22 | 2019-04-16 | 腾讯音乐娱乐科技（深圳）有限公司 | Migration path generation method, device and storage medium |
| CN111695922A (en) * | 2019-03-15 | 2020-09-22 | 北京沃东天骏信息技术有限公司 | Potential user determination method and device, storage medium and electronic equipment |
| CN110111186A (en) * | 2019-05-10 | 2019-08-09 | 拉扎斯网络科技（上海）有限公司 | Information processing method, information processing device, electronic equipment and computer readable storage medium |
| CN110838043A (en) * | 2019-11-05 | 2020-02-25 | 智者四海（北京）技术有限公司 | Commodity recommendation method and device |
| CN111009299A (en) * | 2019-12-17 | 2020-04-14 | 武汉海云健康科技股份有限公司 | Similar medicine recommendation method and system, server and medium |
| CN111199459A (en) * | 2019-12-30 | 2020-05-26 | 深圳市盟天科技有限公司 | Commodity recommendation method and device, electronic equipment and storage medium |
| CN111861623A (en) * | 2019-12-30 | 2020-10-30 | 北京骑胜科技有限公司 | Information recommendation method, device and equipment |
| CN111199459B (en) * | 2019-12-30 | 2024-02-09 | 深圳市盟天科技有限公司 | Commodity recommendation method, commodity recommendation device, electronic equipment and storage medium |
| CN111861623B (en) * | 2019-12-30 | 2024-07-12 | 北京骑胜科技有限公司 | Information recommendation method, device and equipment |
| CN113486948B (en) * | 2021-07-01 | 2024-09-06 | 有米科技股份有限公司 | Clothing commodity gender classification method and device based on text data |
| CN113379516A (en) * | 2021-08-12 | 2021-09-10 | 永正信息技术(南京)有限公司 | Recommended product determination method and device |
| CN113610608A (en) * | 2021-08-19 | 2021-11-05 | 创优数字科技(广东)有限公司 | User preference recommendation method and device, electronic equipment and storage medium |
| CN115471302A (en) * | 2022-11-14 | 2022-12-13 | 山东智豆数字科技有限公司 | Electronic marketing data processing method based on big data analysis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106372961A (en) | Commodity recommendation method and device | |
| CN109784973B (en) | Advertisement putting method and device based on big data analysis and electronic equipment | |
| US20170061500A1 (en) | Systems and methods for data service platform | |
| US20150379609A1 (en) | Generating recommendations for unfamiliar users by utilizing social side information | |
| US8725559B1 (en) | Attribute based advertisement categorization | |
| CN108665329A (en) | A kind of Method of Commodity Recommendation based on user browsing behavior | |
| CN112132660B (en) | Commodity recommendation method, system, equipment and storage medium | |
| CN111008335B (en) | Information processing method, device, equipment and storage medium | |
| CN104765758A (en) | Systems and Methods for Search Results Targeting | |
| CN113379449B (en) | Multimedia resource recall method and device, electronic equipment and storage medium | |
| CN109978580A (en) | Object recommendation method, apparatus and computer readable storage medium | |
| CN112015986B (en) | Data pushing method, device, electronic equipment and computer readable storage medium | |
| Joghee | RETRACTED ARTICLE: Internet of Things-assisted E-marketing and distribution framework | |
| CN111787042B (en) | Method and device for pushing information | |
| CN112749323B (en) | Method and device for constructing user portrait | |
| US20140372197A1 (en) | Systems, apparatuses and methods for providing a price point to a consumer for products in an electronic shopping cart of the consumer | |
| CN114245165A (en) | Live broadcast recommendation method and device, electronic equipment and storage medium | |
| CN116664222A (en) | Data processing method and device | |
| CN112308648A (en) | Information processing method and device | |
| CN116308663A (en) | Recommendation method, terminal and storage medium | |
| CN110766478A (en) | Method and device for improving user connectivity | |
| US9779443B1 (en) | Event-based personalized merchandising schemes and applications in messaging | |
| CN115169583A (en) | Training method and device of user behavior prediction system | |
| CN111784091B (en) | Method and device for processing information | |
| CN114912015A (en) | Object recommendation method, model training method, device, equipment and medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170201 |