CN108388630A

CN108388630A - A kind of shopping information method for pushing, device and electronic equipment

Info

Publication number: CN108388630A
Application number: CN201810150212.6A
Authority: CN
Inventors: 彭睿棋
Original assignee: Beijing Qihoo Technology Co Ltd
Current assignee: Beijing Qihoo Technology Co Ltd
Priority date: 2018-02-13
Filing date: 2018-02-13
Publication date: 2018-08-10

Abstract

The present invention discloses a kind of shopping information method for pushing, device and electronic equipment, the search need for class of being done shopping by preposition user when initiating the search of shopping type in user, the search efficiency and user experience of significant increase search engine, personalized search recommendation results are provided, the realization efficiency and user's viscosity of search engine are increased.This method includes：In the search content for detecting target user's search shopping type, the web-based history behavior record of the shopping type of the whole network user is extracted；The web-based history behavior record of shopping type based on the whole network user determines the recommendation information of shopping type corresponding with the target user；The recommendation information of the shopping type is illustrated in result of page searching corresponding with the shopping search content of type.

Description

Shopping information pushing method and device and electronic equipment

Technical Field

The invention relates to the technical field of electronics, in particular to a shopping information pushing method and device and electronic equipment.

Background

With the development of information processing technology, more and more electronic devices appear in the work and life of people, and convenience is brought to the daily life of people. These electronic devices provide convenient services to users via the internet. The amount of information brought by the development of the internet is increasing, so that users increasingly rely on search engines when screening information. The search engine is a system that collects information from the internet by using a specific computer program according to a certain policy, provides a retrieval service for a user after organizing and processing the information, and displays information related to the content searched by the user to the user. Currently, in the process of using a search engine by a user, the traditional search engine only provides official addressing services, such as: the user searches the name of a certain E-commerce website, and the search result determined by the search engine is the website address of the E-commerce website. Therefore, the search engine in the prior art can only meet the query requirement of the user website, the provided search service is single, and the user viscosity is poor.

Disclosure of Invention

In view of the above problems, the present invention is proposed to provide a shopping information pushing method, apparatus and electronic device that overcome the above problems or at least partially solve the above problems.

In a first aspect, the present application provides a shopping information pushing method, including:

under the condition that a target user is detected to search for the search content of the shopping type, extracting historical network behavior records of the shopping type of the whole network user;

determining recommendation information of the shopping type corresponding to the target user based on the historical network behavior record of the shopping type of the whole network user;

and displaying the recommendation information of the shopping type in a search result page corresponding to the search content of the shopping type.

Optionally, the determining recommendation information of the shopping type corresponding to the target user based on the historical network behavior record of the shopping type of the all-network user includes:

determining candidate items based on the historical network behavior record of the shopping type of the whole network user;

determining the scoring of each user in the users of the whole network on the candidate items, and establishing a user scoring matrix;

determining a neighbor user set similar to the target user in the full-network users based on the scoring matrix;

determining recommended items from the candidate items based on the neighbor user set;

and determining that the recommendation information corresponding to the recommended item is the recommendation information of the shopping type corresponding to the target user.

Optionally, the obtaining of the historical network behavior record of the network-wide user includes:

and acquiring any one or more combinations of search records of shopping types, click records of shopping types and browsing records of shopping types of the users in the whole network within a preset time range.

Optionally, the determining a candidate item based on the historical network behavior record of the shopping types of the users over the whole network includes:

determining search contents with the search times larger than a first preset time in the search records of the shopping types of the users in the whole network within the preset time range as candidate items; and/or

Determining click contents with the click times of the point machine being more than a second preset time in the click records of the shopping types of the users in the whole network within the preset time range as candidate items; and/or

And determining browsing contents with browsing times larger than a third preset time in the browsing records of the shopping types of the users in the whole network within the preset time range as candidate items.

Optionally, the determining, based on the scoring matrix, a set of neighbor users similar to the target user in the full-network users includes:

calculating the similarity between the target user and other users in the whole network users based on the scoring matrix;

and determining a neighbor user set similar to the target user based on the similarity between the target user and other users in the full-network users.

Optionally, the determining, based on the similarity between the target user and other users in the full-network users, a neighbor user set similar to the target user includes:

and determining that the neighbor user set similar to the target user comprises users of which the similarity with the target user is greater than a first preset threshold value in the full-network users.

and determining that the neighbor user set similar to the target user comprises a first preset number of users which are arranged from large to small in similarity with the target user in the full-network users.

Optionally, the determining a recommended item from the candidate items based on the neighbor user set includes:

determining an interest degree predicted value of the target user for each item in the candidate items based on the neighbor user set;

determining the items of which the interest degree predicted values are larger than a second preset threshold value in the candidate items as recommended items or determining the items of which the interest degree predicted values are arranged from large to small and the items of which the number is a second preset number in the candidate items as recommended items.

determining a weighted average interest degree of all neighbor users in the neighbor user set for each item in the candidate items;

determining the items with the weighted average interest degree larger than a third preset threshold value in the candidate items as recommended items or determining the items with the weighted average interest degree in the candidate items in a first preset number after the weighted average interest degree is arranged from high to low as recommended items.

Optionally, the displaying the recommendation information of the shopping type in a search result page corresponding to the search content of the shopping type includes:

and displaying the recommendation information of the shopping type under the search result corresponding to the search content of the shopping type, wherein the recommendation information of the shopping type comprises candidate search words and/or webpage links corresponding to the recommended items.

Optionally, the search content of the shopping type includes: any one or more of the shopping website name, the shopping website link and the commodity name.

Optionally, the displaying the recommendation information of the shopping type on the search result page corresponding to the search content of the shopping type includes:

determining recommendation information related to search content of the shopping type searched by the target user from the recommendation information of the shopping type;

and displaying recommendation information related to the search content of the shopping type searched by the target user on a search result page corresponding to the search content of the shopping type.

Optionally, the recommendation information of the shopping type specifically includes a commodity object that a user can directly place an order for purchase, and the method further includes:

and responding to the triggering operation of the user on the commodity object, and loading a purchasing webpage corresponding to the commodity object for the user to purchase the commodity object through the purchasing webpage.

In a second aspect, the present application provides a shopping information pushing method, including:

determining a similar user set similar to the target user based on the historical network behavior record of the shopping type of the whole network user;

determining recommendation information of the shopping type corresponding to the target user based on the information of the shopping type interested by each similar user in the similar user set;

In a second aspect, the present application provides a shopping information pushing device, comprising:

the acquisition unit is used for extracting the historical network behavior record of the shopping type of the whole network user under the condition that the search content of the shopping type searched by the target user is detected;

the determining unit is used for determining recommendation information of the shopping type corresponding to the target user based on the historical network behavior record of the shopping type of the whole network user;

and the display unit is used for displaying the recommendation information of the shopping type in a search result page corresponding to the search content of the shopping type.

Optionally, the determining unit includes:

the first determining module is used for determining candidate items based on historical network behavior records of shopping types of the users in the whole network;

the second determining module is used for determining the scoring of the candidate items by each user in the users of the whole network and establishing a user scoring matrix;

a third determining module, configured to determine, based on the scoring matrix, a neighbor user set that is similar to the target user in the full-network users;

a fourth determining module, configured to determine a recommended item from the candidate items based on the set of neighbor users;

and the fifth determining module is used for determining that the recommendation information corresponding to the recommended item is the recommendation information of the shopping type corresponding to the target user.

Optionally, the obtaining unit is configured to:

Optionally, the first determining module is configured to:

Optionally, the third determining module is configured to:

Optionally, the fourth determining module is configured to:

Optionally, the display unit is configured to:

Optionally, the recommendation information of the shopping type specifically includes a commodity object that a user can directly place an order for purchase, and the apparatus further includes:

and the response unit is used for responding to the triggering operation of the user on the commodity object, loading a purchase webpage corresponding to the commodity object, and allowing the user to purchase the commodity object through the purchase webpage.

In a fourth aspect, the present application provides a shopping information pushing apparatus, comprising:

a first determining unit, configured to determine a similar user set similar to the target user based on a historical network behavior record of the shopping type of the full-network user;

a second determining unit, configured to determine recommendation information of a shopping type corresponding to the target user based on information of a shopping type in which each similar user in the set of similar users is interested;

In a fifth aspect, the present application provides an electronic device comprising a processor and a memory: the memory is used for storing programs for executing the shopping information pushing method of the first and second aspects; the processor is configured to execute programs stored in the memory.

In a sixth aspect, the present application provides a computer storage medium for storing computer software instructions for the shopping information pushing apparatus, which includes a program for executing the above aspect designed for the shopping information pushing apparatus.

One or more technical solutions in the embodiments of the present application have at least one or more of the following technical effects:

in the technical scheme of the embodiment of the invention, under the condition that the search content of the shopping type searched by the target user is detected, the historical network behavior record of the shopping type of the whole network user is extracted; determining recommendation information of the shopping type corresponding to the target user based on the historical network behavior record of the shopping type of the whole network user; and finally, displaying the recommendation information of the shopping type on a search result page corresponding to the search content searched by the target user. Therefore, under the condition that a user initiates shopping type search through a search engine, the potential search requirements of the user for shopping types can be predicted through the historical network behavior records of the shopping types of the users in the whole network, the recommendation information of the shopping types related to the user can be further determined, and the recommendation information of the shopping types related to the user can be displayed together when the search result is displayed. Therefore, by prepositioning the search requirement of the shopping category of the user when the user initiates the shopping type search, the query efficiency and the user experience of the search engine are greatly improved, personalized search recommendation results are provided, and the showing efficiency and the user stickiness of the search engine are increased.

Drawings

Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:

FIG. 1 is a flowchart of a shopping information pushing method according to a first embodiment of the present invention;

FIG. 2 is a flowchart illustrating a shopping information pushing method according to a second embodiment of the present invention;

FIG. 3 is a schematic diagram of a shopping information pushing device according to a third embodiment of the present invention;

FIG. 4 is a schematic view of a shopping information pushing device according to a fourth embodiment of the present invention;

fig. 5 is a schematic diagram of an electronic device in a fifth embodiment of the invention.

Detailed Description

The embodiment discloses a shopping information pushing method, a shopping information pushing device and electronic equipment, which greatly improve the query efficiency and user experience of a search engine, provide personalized search recommendation results and increase the presentation efficiency and user stickiness of the search engine by prepositioning the search requirements of shopping categories of a user when the user initiates a shopping type search. The method comprises the following steps: under the condition that a target user is detected to search for the search content of the shopping type, extracting historical network behavior records of the shopping type of the whole network user; determining recommendation information of the shopping type corresponding to the target user based on the historical network behavior record of the shopping type of the whole network user; and displaying the recommendation information of the shopping type in a search result page corresponding to the search content of the shopping type.

The technical solutions of the present invention are described in detail below with reference to the drawings and specific embodiments, and it should be understood that the specific features in the embodiments and examples of the present invention are described in detail in the technical solutions of the present application, and are not limited to the technical solutions of the present application, and the technical features in the embodiments and examples of the present application may be combined with each other without conflict.

The term "and/or" herein is merely an association describing an associated object, meaning that three relationships may exist, e.g., a and/or B, may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter related objects are in an "or" relationship.

Examples

Referring to fig. 1, a first embodiment of the present invention provides a shopping information pushing method, which includes the following steps:

s101: under the condition that a target user is detected to search for the search content of the shopping type, extracting historical network behavior records of the shopping type of the whole network user;

s102: determining recommendation information of the shopping type corresponding to the target user based on the historical network behavior record of the shopping type of the whole network user;

s103: and displaying the recommendation information of the shopping type in a search result page corresponding to the search content of the shopping type.

Specifically, in this embodiment, the shopping information pushing method is mainly applied to a server side of a search engine, and certainly, may also be applied to a client side. When a user inputs search content of a shopping type through a search engine at a client, the search engine transmits the search content of the shopping type to a server of the search engine, and after the server receives the search content of the shopping type, a corresponding search result is retrieved. On the basis, the server can also obtain historical network behavior records of shopping types of users in the whole network, predict the potential search requirements of the users for shopping types, further determine the recommendation information of the shopping types related to the users, and display the recommendation information of the shopping types related to the users together when the search results are displayed. Therefore, by prepositioning the search requirement of the shopping category of the user when the user initiates the shopping type search, the query efficiency and the user experience of the search engine are greatly improved, personalized search recommendation results are provided, and the showing efficiency and the user stickiness of the search engine are increased.

Further, in this embodiment, in step S101, the search content of the shopping type includes any one or more of a shopping website name, a shopping website link, and a commodity name.

Specifically, in this embodiment, when the target user initiates a search content for searching for a shopping type, the shopping information pushing method in this embodiment is triggered to be executed, for example: when the target user searches for the name of the e-commerce website a, the website of the e-commerce website B or the name of the commodity a in the website search, the shopping information pushing method in the embodiment is triggered to be executed, and personalized shopping type recommendation information is pushed for the user. In a specific implementation process, the search content of the shopping type includes any one or more combinations of a shopping website link and a commodity name of a shopping website name, and of course, other content is also possible, and the present application is not limited herein.

The method in the embodiment is triggered only when the search content of the shopping type is searched, so that the interference to the user caused by the related pushing of the non-shopping type search can be effectively avoided, the data transmission burden of the equipment can be further reduced, and the experience degree of the user is improved.

Further, after the shopping information pushing method in this embodiment is triggered, step S101 may be implemented in a specific implementation process by the following steps:

Specifically, in this embodiment, it is necessary to obtain any one or more combinations of search records of shopping types, click records of shopping types, and browsing records of shopping types of the users all over the network within a preset time range (e.g., 1 hour, 5 hours, 24 hours, etc.). Such as: the shopping-type search record may be a record in which the network-wide user searches for any one or more combinations of a shopping site name, a shopping site link, and a commodity name within a preset time range. Such as: in the case where the user a searches for a website by 20 minutes before the current time to search for the name of the e-commerce website a, it is determined that the record is a search record of a shopping type of the user over the entire network.

For another example: the click record of the shopping type can be a record of any one or more combinations of shopping websites, shopping website links and shopping commodity links clicked by the whole-network users within a preset time range. Such as: in the case where the user B clicks the e-commerce website B30 minutes before the current time, it is determined that the record is a click record of the shopping type of the all-network user.

For another example: the browsing record of the shopping type can be a record of shopping websites and/or shopping commodity links browsed by the full-network user within a preset time range. Such as: when the user C browses the commodity A of the E-commerce website B30 minutes before the current moment, the record is determined to be the browsing record of the shopping type of the whole-network user, and when the browsing record of the shopping type of the whole-network user is recorded, in order to ensure the validity of the record, the browsing duration can be considered, namely the browsing record of the commodity with the browsing duration being greater than the preset duration (such as 1 minute, 5 minutes and the like) is recorded as the browsing record of the shopping type of the whole-network user.

In this way, the historical network behavior record of the shopping type of the user on the whole network can be effectively counted.

Further, after acquiring the historical network behavior record of the shopping types of the users on the whole network, when step S102 in this embodiment is executed, the following steps may be implemented:

Specifically, in this embodiment, the step S102 may employ a collaborative filtering model to filter out the recommendation information of the corresponding shopping type, and of course, other manners may also be adopted to implement the method, and the application is not limited herein. In step S102, first, a candidate item needs to be determined based on the acquired historical network behavior record of the shopping types of the users in the whole network, and when determining the candidate item, the following steps are performed:

Specifically, the historical network behavior records of the network-wide users include search records of shopping types, click records of shopping types, browsing records of shopping types and the like of the network-wide users within a preset time range. Therefore, when determining the candidate item, the search content with the search times larger than the first preset time can be screened from the search records of the shopping types of the users in the whole network within the preset time range to be the candidate item. Such as: the search contents of the shopping types with the searching times of the users in the whole network being more than the first preset times (such as 1000 times, 5000 times and the like) in 24 hours comprise a commodity A, a shopping website B, a commodity B and the like, and the commodity A, the shopping website B and the commodity B can be screened as candidate items.

Similarly, when determining the candidate item, the click content with the click times larger than the second preset times can be screened from the click records of the shopping types of the users in the whole network within the preset time range to serve as the candidate item. Such as: and the click contents of the shopping types with the click times of the users in the whole network being more than a second preset time (such as 1000 times, 5000 times and the like) in 24 hours comprise a commodity C, a shopping website A, a commodity D and the like, and the commodity C, the shopping website A and the commodity D can also be screened as candidate items.

Similarly, when determining the candidate item, the browsing content with the browsing times greater than the third preset time may be screened from the browsing records of the shopping types of the users over the whole network within the preset time range as the candidate item. Such as: and if the browsing content of the shopping types with the browsing times of the users in the whole network being more than the third preset times (such as 1000 times, 5000 times and the like) in 24 hours comprises the commodity E, the shopping website C, the commodity F and the like, the commodity E, the shopping website C and the commodity F can also be screened as candidate items. The candidate items determined in the mode are more in line with the actual shopping intention change trend of the users in the whole network, and the recommendation information of the shopping types determined according to the candidate items is more in line with the user requirements.

In combination with the above three cases, the sum of times of searching, clicking and browsing of a certain content by the whole network user within a preset time range can be comprehensively considered, and the content can also be used as a candidate item when the sum of times is greater than a preset threshold value.

In a specific implementation process, the manner of determining the candidate is not limited to the above manner, and may also be set according to actual needs, for example: and determining the contents with more times of searching, clicking and browsing of the target user as candidate items only by considering the historical network behavior record of the shopping category of the target user, wherein the application is not limited.

Under the condition that the candidate item is determined, a user scoring matrix of the full-network users for the candidate item can be established, and the user scoring matrix can be expressed as follows:

in the above formula, U_iRepresenting users I, I in a network-wide user_jFor candidate item j, Rij is the user i's score for candidate item j. In this embodiment, the scores of the candidate items by the user may be represented by binary 0 and 1, where 0 represents that the candidate item is not interested by the user, and 1 represents that the candidate item is interested by the user. In determining the user's score for a candidate in this manner, a historical network behavior record of the user's shopping category needs to be invoked, such as: and searching the record, and when the number of times that the user searches the candidate item is greater than the preset searching number, determining that the user scores 1 for the candidate item. Otherwise, when the user isAnd the number of times of searching the candidate item is less than or equal to the preset searching number, and the score of the user for the candidate item is determined to be 0.

Or, the number of times that the user searches for all the candidate items may also be obtained, and when the percentage of the number of times that the user searches for the candidate items in the number of times that the user searches for all the candidate items is greater than a preset percentage, the user is determined that the score of the user for the candidate item is 1. Otherwise, when the percentage of the number of times that the user searches the candidate items to the number of times that the user searches all the candidate items is less than or equal to the preset percentage, determining that the user scores 0 for the candidate items.

Of course, the percentage of the number of times that the user searches for a certain candidate item to the number of times that the user searches for all candidate items may also be directly used as the score value of the user for the candidate item. In a specific implementation process, the scoring of the candidate items by the user may also be determined in other manners, and the application is not limited herein.

Further, after the user scoring matrix is established, the method in this embodiment may determine a neighbor user set similar to the target user according to the scoring matrix. When determining the neighbor user set corresponding to the target user, the method can be implemented by the following steps:

calculating the similarity between the target user and other users in the whole network users based on the scoring matrix; and determining a neighbor user set similar to the target user based on the similarity between the target user and other users in the full-network users.

Specifically, in this embodiment, based on the above-mentioned established scoring matrix, a euclidean distance formula may be used to calculate euclidean distances between the target user and other users in the whole network, where the euclidean distances may be used to represent similarities between the target user and other users. The Euclidean distance formula isThe formula surfaces Europe and Europe of user X and user yDistance, Rxj for user x's score for candidate item j and Ryj for user y's score for candidate item j. The larger the Euclidean distance from the target user, the higher the similarity between the user and the target user, and the more similar the interest of shopping between the user and the target user. Of course, in this embodiment, the similarity between the target user and other users in the whole network may also be calculated by using a cosine similarity formula, where the cosine similarity formula isWherein, V_xScore vector for user x for all candidate items, V_yA scoring vector for user y for all candidate items. The greater the cosine similarity to the target user, the more similar the user is to the target user's shopping interests. In a specific implementation process, the method for determining the similarity between the target user and other users may be set according to actual needs, and the present application is not limited herein.

Further, after determining the similarity between the target user and other users in the whole network, the set of neighbor users similar to the target user may be determined in, but not limited to, the following two ways:

the first mode is as follows: and determining that the neighbor user set similar to the target user comprises users of which the similarity with the target user is greater than a first preset threshold value in the full-network users.

Specifically, in this embodiment, a first preset threshold may be preset, and when the similarity between the users in the whole network and the target user is greater than the first preset threshold, the users in the whole network and the target user may be added to a neighbor user set similar to the target user, that is, users with similarity values greater than the first preset threshold are screened from the users in the whole network as a neighbor user set similar to the target user.

The second mode is as follows: and determining that the neighbor user set similar to the target user comprises a first preset number of users which are arranged from large to small in similarity with the target user in the full-network users.

Specifically, in this embodiment, after determining the similarity between the target user and other users in the whole network, the target user and other users in the whole network may be ranked from the largest to the smallest according to the similarity, and then, the first preset number of users ranked in the front may be used as the neighbor user set similar to the target user. Such as: the users in the whole network, which are ranked according to the similarity with the target user from the largest to the smallest, comprise a user 1, a user 3, a user 4, a user 5 and a user 2, and when the first preset number is 2, the neighbor user set which is determined to be similar to the target user comprises the user 1 and the user 3.

In a specific implementation process, the first preset threshold in the first manner and the first preset number in the second manner may be set according to actual needs, and the present application is not limited herein. Of course, other ways may also be used to determine the neighbor user set, and the present application is not limited thereto.

Further, after determining the set of neighbor users, recommended items to the target user may be generated according to the shopping preferences of the neighbors. Specifically, determining recommended items according to the neighbor user set can be implemented in two ways:

the first mode is as follows: determining an interest degree predicted value of the target user for each item in the candidate items based on the neighbor user set; determining the items of which the interest degree predicted values are larger than a second preset threshold value in the candidate items as recommended items or determining the items of which the interest degree predicted values are arranged from large to small and the items of which the number is a second preset number in the candidate items as recommended items.

Specifically, in this embodiment, the predicted value of the interest level of the target user for each item in the candidate items may be determined based on the neighbor user set, and a formula may be used when calculating the predicted value of the interest level of the target user for the candidate itemsWherein,is an objectUser u scores the average of all candidate items, i is the user of the neighbor user set, c_iIs the similarity between the target user u and the neighbor user i, r_ijIs the score of the neighbor user i on the candidate item j,is the average scoring of all candidate items by the neighbor user i.

In this way, the second preset threshold value can be preset, and since the predicted value of the interest degree of the target user for all the candidate items can be determined through the formula, the item with the predicted value of the interest degree of the target user greater than the second preset threshold value is screened from all the candidate items as the recommended item.

Or after the interest degree predicted value of each candidate item by the target user is determined, the candidate items can be ranked from large to small according to the interest degree predicted value, and then the second preset number of the candidate items ranked in the front can be used as recommended items. Such as: the candidate items ranked according to the interestingness predicted value from large to small comprise item 1, item 3, item 4, item 5 and item 2, and when the second preset number is 3, the recommended items are determined to comprise item 1, item 3 and item 4.

The second mode is as follows: determining a weighted average interest degree of all neighbor users in the neighbor user set for each item in the candidate items; determining the items with the weighted average interest degree larger than a third preset threshold value in the candidate items as recommended items or determining the items with the weighted average interest degree in the candidate items in a first preset number after the weighted average interest degree is arranged from high to low as recommended items.

Specifically, in this embodiment, for each candidate item, the weighted average interest level of all neighbor users in the neighbor user set for the candidate item may be determined, and the weighting coefficient may be set according to actual needs, which is not limited in this application. Furthermore, a third preset threshold value may be preset, and since the weighted average interest degree of all the neighboring users for each candidate item may be determined, an item with the weighted average interest degree greater than the third preset threshold value is selected from all the candidate items as a recommended item.

Or after the weighted average interest-degree of each candidate item is determined, the candidate items may be ranked from the largest to the smallest according to the weighted average interest-degree, and then a third preset number of the candidate items ranked in the front may be used as recommended items. Such as: the candidate items ranked according to the weighted average interest degree from high to low comprise an item 1, an item 3, an item 4, an item 5 and an item 2, and when the third preset number is 3, the recommended items are determined to comprise the item 1, the item 3 and the item 4.

After the recommended item is determined, the recommendation information of the shopping type corresponding to the target user is determined based on the recommended item. Specifically, the recommendation information of the shopping type includes candidate search terms and/or web page links corresponding to the recommended items.

Specifically, in this embodiment, the determined recommended item may be some search terms of shopping categories or a shopping website, so that the recommendation information of the shopping category recommended to the target user includes candidate search terms and/or web page links corresponding to the recommended item. Such as: the recommended items comprise the name of the e-commerce website A and the name of the commodity B, the recommended information of the shopping type recommended to the target user is the website of the e-commerce website A and the candidate search word corresponding to the name of the commodity B, or the candidate search word corresponding to the name of the e-commerce website A and the purchase link of the commodity B, and the like, and the target user can directly click the candidate search word to further obtain the search result of the candidate search word. The target user can directly click the recommended webpage link and enter the website corresponding to the webpage link. In a specific implementation process, the recommendation information determined according to the recommendation item may be set according to actual needs, and the present application is not limited herein.

Further, in this embodiment, the recommendation information of the shopping type specifically includes a commodity object that a user can directly place a purchase order, and the method further includes: and responding to the triggering operation of the user on the commodity object, and loading a purchasing webpage corresponding to the commodity object for the user to purchase the commodity object through the purchasing webpage.

Specifically, in this embodiment, the determined recommended items may also be some commodity objects, so that the recommendation information of the shopping type recommended to the target user includes a purchase webpage of the commodity object corresponding to the recommended item. Such as: and a purchase link of the commodity B and the like, and the target user can directly click the recommended commodity object to turn to a purchase webpage link of the target user, so that the target user can quickly purchase the intended commodity.

Further, in step S103, the recommendation information of the shopping type needs to be presented in the search result page corresponding to the search content of the shopping type. When the recommendation information of the shopping category is displayed, the recommendation information of the shopping category can be displayed below the search result corresponding to the search content of the shopping category. Such as: when a target user initiates a search for searching the name of the e-commerce website A, the search result comprises the official website of the e-commerce website A and other related item search results, and the recommendation information of the shopping type determined by the method in the embodiment can be displayed below the official website of the e-commerce website A, so that the user can conveniently check the recommendation information.

Further, in this embodiment, when the recommendation information of the shopping type is displayed on the search result page corresponding to the search content of the shopping type, the following steps may be further implemented:

determining recommendation information related to search content of the shopping type searched by the target user from the recommendation information of the shopping type; and displaying recommendation information related to the search content of the shopping type searched by the target user on a search result page corresponding to the search content of the shopping type.

Specifically, in this embodiment, in order to make the pushed shopping information closer to the purchasing intention of the user and better meet the shopping demand of the user, when the recommendation information of the shopping type is displayed, the recommendation information related to the search content searched by the target user may be determined from the recommendation information determined based on the recommendation item and pushed. Such as: after a target user initiates a search of an e-commerce website A, when the recommendation information of the shopping type determined based on the historical network behavior of the shopping category of the whole-network user comprises an e-commerce website B, a commodity A, a commodity B and a commodity C, if the e-commerce website A is the shopping website for selling books, the e-commerce website B is the shopping website for selling clothes, the commodity A is a commodity of the clothes category, and both the commodity B and the commodity C are the book-type commodities, the recommendation information corresponding to the commodity B and the commodity C can be displayed in a page of a search result, specifically, the recommendation information can be displayed below an official website search result of the e-commerce website A to predict book commodities which the user may be interested in.

For another example: after the target user initiates the search of the commodity D, when the recommendation information of the shopping type determined based on the historical network behavior of the shopping category of the whole-network user comprises an E-commerce website B, a commodity A, a commodity B and a commodity C, if the commodity D is a mother-infant commodity, the E-commerce website B is a shopping website for selling clothes, the commodity A is a clothes commodity, and the commodity B and the commodity C are mother-infant commodities, the recommendation information corresponding to the commodity B and the commodity C can be displayed in a page of a search result, specifically below an official website search result of the E-commerce website A, and the commodity which is possibly interested by the user can be predicted. Therefore, recommendation information related to the search content of the target user can be pushed to the target user, so that the target user can quickly locate interested commodities through the recommendation information, and user experience is improved.

Further, in the method in this embodiment, recommendation information with a higher degree of correlation with the search content of the target user may also be displayed in front of the recommendation information with a lower degree of correlation with the search content of the target user, for example: after the target user initiates the search of the commodity D, when the recommendation information of the shopping type determined based on the historical network behavior of the shopping category of the whole-network user comprises an E-commerce website B, a commodity A, a commodity B and a commodity C, if the commodity D is a mother-infant commodity, the E-commerce website B is a shopping website for selling clothes, the commodity A is a dress-type commodity, and the commodity B and the commodity C are mother-infant commodities. Therefore, the recommendation information with high relevance to the target user search content is displayed at the most striking position and pushed to the target user, so that the target user can quickly locate interested commodities through the recommendation information, and the user experience is improved.

The shopping information pushing method in the embodiment can lead the shopping demands of the user to predict the next interested commodities and the purchasing intentions of the user after the target user initiates the related queries of the e-commerce website, the commodities and the like, and can greatly improve the query efficiency and the user experience of the search engine.

Referring to fig. 2, a second embodiment of the present invention provides a shopping information pushing method, including:

s201: under the condition that a target user is detected to search for the search content of the shopping type, extracting historical network behavior records of the shopping type of the whole network user;

s202: determining a similar user set similar to the target user based on the historical network behavior record of the shopping type of the whole network user;

s203: determining recommendation information of the shopping type corresponding to the target user based on the information of the shopping type interested by each similar user in the similar user set;

s204: and displaying the recommendation information of the shopping type in a search result page corresponding to the search content of the shopping type.

Specifically, in this embodiment, the shopping information pushing method is mainly applied to a server side of a search engine, and certainly, may also be applied to a client side. When a user inputs search content of a shopping type through a search engine at a client, the search engine transmits the search content of the shopping type to a server of the search engine, and after the server receives the search content of the shopping type, a corresponding search result is retrieved. On the basis, the server can also obtain historical network behavior records of shopping types of the users in the whole network, determine a similar user set similar to the target user, predict the search requirements of potential shopping types of the users according to the historical network behavior records of the shopping types of the similar users in the similar user set, further determine recommendation information of the shopping types related to the users, and display the recommendation information of the shopping types related to the users together when search results are displayed. Therefore, by prepositioning the search requirement of the shopping category of the user when the user initiates the shopping type search, the query efficiency and the user experience of the search engine are greatly improved, personalized search recommendation results are provided, and the showing efficiency and the user stickiness of the search engine are increased.

Further, in this embodiment, in step S201, the search content of the shopping type includes any one or more of a shopping website name, a shopping website link, and a commodity name.

Further, after the shopping information pushing method in this embodiment is triggered, step S201 may be implemented in a specific implementation process by the following steps:

Further, after acquiring the historical network behavior record of the shopping type of the network-wide user, step S202 in this embodiment is executed, and it is required to determine a similar user set similar to the target user based on the historical network behavior record of the shopping type of the network-wide user.

Specifically, in this embodiment, a user whose content is similar to the content of the history search, history click, and/or history browsing of the target user among the users in the whole network may be used as the similar user. Such as: the three items with the largest number of historical searches, historical clicks and/or historical browsing times of the shopping types of the target users are the commodity A, the commodity B, the commodity C and the commodity D. If the most frequent historical search, historical click and/or historical browsing of the user in the whole network comprises any three items of the commodity A, the commodity B, the commodity C and the commodity D, the user can be determined to be a similar user, and a similar user set can be formed in such a way. Or, a similar user set may also be determined by using the method mentioned in the first embodiment, which is not described in detail again, and refer to the foregoing embodiment.

Further, after the similar user set is determined, step S203 is executed to determine recommendation information of the shopping type corresponding to the target user based on the information of the shopping type in which each similar user in the similar user set is interested.

Specifically, in this embodiment, the information of the shopping types that are commonly interested can be determined according to the information of the shopping types that are interested by each similar user in the set of similar users, and the information of the shopping types that are commonly interested is pushed to the target user. Such as: the similar user set comprises a user 1, a user 2, a user 3 and a user 4, the information of the shopping types interested by the user 1 comprises a shopping website A, a commodity B and a commodity C, the information of the shopping types interested by the user 2 comprises the shopping website A, the commodity B and the commodity D, the information of the shopping types interested by the user 3 comprises the shopping website A, the commodity B and the commodity E, the information of the shopping types interested by the user 4 comprises the shopping website B, the commodity C and the commodity E, and when the same information is interested by the preset number of similar users, the information is determined to be the information recommended to the target user. When the preset number is set to be 2, the information corresponding to the shopping website A, the commodity B, the commodity C and the commodity E is recommendation information of shopping types.

Of course, in the specific implementation process, the recommendation information for determining the similar user set and the shopping type may be set according to actual needs, and the present application is not limited herein.

After the recommendation information of the shopping type is determined, the recommendation information of the shopping type and the search result can be displayed together, and the display mode can refer to the mode in the first embodiment, which is not described in detail herein.

Referring to fig. 3, a third embodiment of the present invention further provides a shopping information pushing device, including:

an obtaining unit 301, configured to extract a historical network behavior record of a shopping type of a user over the whole network when a search content that a target user searches for the shopping type is detected;

a determining unit 302, configured to determine recommendation information of a shopping type corresponding to the target user based on a historical network behavior record of the shopping type of the all-network user;

a presentation unit 303, configured to present the recommendation information of the shopping type in a search result page corresponding to the search content of the shopping type.

Specifically, in this embodiment, the shopping information pushing device may be disposed in a server, or may be disposed in a mobile terminal device, such as a mobile phone, a tablet computer, a notebook computer, or other devices, such as a desktop computer, or other electronic devices, which is not limited in this application. The manner of pushing shopping information by the shopping information pushing device has been described in detail in the foregoing first embodiment, and thus, this embodiment is not described again.

As an alternative embodiment, the determining unit 302 includes:

As an alternative embodiment, the obtaining unit 301 is configured to:

As an alternative embodiment, the first determining module is configured to:

As an alternative embodiment, the third determining module is configured to:

As an alternative embodiment, the fourth determining module is configured to:

As an alternative embodiment, the display unit is configured to:

As an alternative embodiment, the shopping-type search content includes: any one or more of the shopping website name, the shopping website link and the commodity name.

As an alternative embodiment, the display unit is configured to:

As an optional embodiment, the recommendation information of the shopping type specifically includes a commodity object that can be directly ordered by the user, and the apparatus further includes:

Referring to fig. 4, a third embodiment of the present invention further provides a shopping information pushing apparatus, including:

the acquiring unit 401 is configured to extract a historical network behavior record of a shopping type of a whole network user when a search content that a target user searches for the shopping type is detected;

a first determining unit 402, configured to determine a similar user set similar to the target user based on a historical network behavior record of the shopping type of the all-network user;

a second determining unit 402, configured to determine recommendation information of a shopping type corresponding to the target user based on information of a shopping type in which each similar user in the set of similar users is interested;

a display unit 403, configured to display the recommendation information of the shopping type in a search result page corresponding to the search content of the shopping type.

Specifically, in this embodiment, the shopping information pushing device may be disposed in a server, or may be disposed in a mobile terminal device, such as a mobile phone, a tablet computer, a notebook computer, or other devices, such as a desktop computer, or other electronic devices, which is not limited in this application. The manner of pushing shopping information by the shopping information pushing device has been described in detail in the foregoing second embodiment, and details are not described herein again in this embodiment.

For convenience of description, only the parts related to the embodiments of the present invention are shown, and details of the method according to the embodiments of the present invention are not disclosed. The electronic device may be a server, or may be any electronic device including a mobile phone, a tablet computer, a PDA (Personal Digital Assistant), a POS (Point of Sales), a vehicle-mounted computer, and the like, taking the electronic device as a mobile phone as an example:

fig. 5 is a block diagram illustrating a partial structure of a mobile phone related to an electronic device provided by an embodiment of the present invention. Referring to fig. 5, the handset includes: radio Frequency (RF) circuitry 510, memory 520, input unit 530, display unit 540, sensor 550, audio circuitry 560, wireless-fidelity (Wi-Fi) module 570, processor 580, and power supply 590. Those skilled in the art will appreciate that the handset configuration shown in fig. 5 is not intended to be limiting and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components.

The following describes each component of the mobile phone in detail with reference to fig. 5:

RF circuit 510 may be used for receiving and transmitting signals during information transmission and reception or during a call, and in particular, for processing downlink information of a base station after receiving the downlink information to processor 580; in addition, the data for designing uplink is transmitted to the base station. In general, RF circuit 510 includes, but is not limited to, an antenna, at least one amplifier, a transceiver, a coupler, a Low Noise Amplifier (LNA), a duplexer, and the like. In addition, RF circuit 510 may also communicate with networks and other devices via wireless communication. The wireless communication may use any communication standard or protocol, including but not limited to global system for Mobile communications (GSM), General Packet Radio Service (GPRS), Code Division Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), Long Term Evolution (LTE), email, Short Messaging Service (SMS), and the like.

The memory 520 may be used to store software programs and modules, and the processor 580 executes various functional applications and data processing of the mobile phone by operating the software programs and modules stored in the memory 520. The memory 520 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data (such as audio data, a phonebook, etc.) created according to the use of the cellular phone, and the like. Further, the memory 520 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 input unit 530 may be used to receive input numeric or character information and generate key signal inputs related to user settings and function control of the cellular phone. Specifically, the input unit 530 may include a touch panel 531 and other input devices 532. The touch panel 531, also called a touch screen, can collect touch operations of a user on or near the touch panel 531 (for example, operations of the user on or near the touch panel 531 by using any suitable object or accessory such as a finger or a stylus pen), and drive the corresponding connection device according to a preset program. Alternatively, the touch panel 531 may include two parts, a touch detection device and a touch controller. The touch detection device detects the touch direction of a user, detects a signal brought by touch operation and transmits the signal to the touch controller; the touch controller receives touch information from the touch sensing device, converts the touch information into touch point coordinates, and sends the touch point coordinates to the processor 580, and can receive and execute commands sent by the processor 580. In addition, the touch panel 531 may be implemented by various types such as a resistive type, a capacitive type, an infrared ray, and a surface acoustic wave. The input unit 530 may include other input devices 532 in addition to the touch panel 531. In particular, other input devices 532 may include, but are not limited to, one or more of a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, a joystick, and the like.

The display unit 540 may be used to display information input by the user or information provided to the user and various menus of the mobile phone. The display unit 540 may include a display panel 541, and optionally, the display panel 541 may be configured in the form of a Liquid Crystal Display (LCD), an Organic Light-Emitting Diode (OLED), or the like. Further, the touch panel 531 may cover the display panel 541, and when the touch panel 531 detects a touch operation on or near the touch panel 531, the touch panel is transmitted to the processor 580 to determine the type of the touch event, and then the processor 580 provides a corresponding visual output on the display panel 541 according to the type of the touch event. Although the touch panel 531 and the display panel 541 are shown as two separate components in fig. 5 to implement the input and output functions of the mobile phone, in some embodiments, the touch panel 531 and the display panel 541 may be integrated to implement the input and output functions of the mobile phone.

The handset may also include at least one sensor 550, such as a light sensor, motion sensor, and other sensors. Specifically, the light sensor may include an ambient light sensor and a proximity sensor, wherein the ambient light sensor may adjust the brightness of the display panel 541 according to the brightness of ambient light, and the proximity sensor may turn off the display panel 541 and/or the backlight when the mobile phone is moved to the ear. As one of the motion sensors, the accelerometer sensor can detect the magnitude of acceleration in each direction (generally, three axes), can detect the magnitude and direction of gravity when stationary, and can be used for applications of recognizing the posture of a mobile phone (such as horizontal and vertical screen switching, related games, magnetometer posture calibration), vibration recognition related functions (such as pedometer and tapping), and the like; as for other sensors such as a gyroscope, a barometer, a hygrometer, a thermometer, and an infrared sensor, which can be configured on the mobile phone, further description is omitted here.

Audio circuitry 560, speaker 561, and microphone 562 may provide an audio interface between a user and a cell phone. The audio circuit 560 may transmit the electrical signal converted from the received audio data to the speaker 561, and convert the electrical signal into a sound signal by the speaker 561 for output; on the other hand, the microphone 562 converts the collected sound signals into electrical signals, which are received by the audio circuit 560 and converted into audio data, which are then processed by the audio data output processor 580, and then passed through the RF circuit 510 to be sent to, for example, another cellular phone, or output to the memory 520 for further processing.

WiFi belongs to short distance wireless transmission technology, and the mobile phone can help the user to send and receive e-mail, browse web pages, access streaming media, etc. through the WiFi module 570, which provides wireless broadband internet access for the user. Although fig. 5 shows the WiFi module 570, it is understood that it does not belong to the essential constitution of the handset, and can be omitted entirely as needed within the scope not changing the essence of the invention.

The processor 580 is a control center of the mobile phone, connects various parts of the entire mobile phone by using various interfaces and lines, and performs various functions of the mobile phone and processes data by operating or executing software programs and/or modules stored in the memory 520 and calling data stored in the memory 520, thereby performing overall monitoring of the mobile phone. Alternatively, processor 580 may include one or more processing units; preferably, the processor 580 may integrate an application processor, which mainly handles operating systems, user interfaces, application programs, etc., and a modem processor, which mainly handles wireless communications. It will be appreciated that the modem processor described above may not be integrated into processor 580.

The handset also includes a power supply 590 (e.g., a battery) for powering the various components, which may preferably be logically coupled to the processor 580 via a power management system, such that the power management system may be used to manage charging, discharging, and power consumption.

Although not shown, the mobile phone may further include a camera, a bluetooth module, etc., which are not described herein.

In this embodiment of the present invention, the processor 580 further has the following functions:

In an embodiment of the present invention, the search content of the shopping type includes: any one or more of the shopping website name, the shopping website link and the commodity name.

In this embodiment of the present invention, the recommendation information of the shopping type specifically includes a commodity object that can be directly purchased by a user, and the processor 580 further has the following functions:

A sixth embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, wherein the functional unit integrated with the shopping information pushing apparatus in the third and fourth embodiments of the present invention can be stored in a computer-readable storage medium if it is implemented in the form of a software functional unit and sold or used as a stand-alone product. Based on such understanding, all or part of the processes in the shopping information pushing method according to the first and second embodiments of the present invention may also be implemented by a computer program, which may be stored in a computer readable storage medium and used for implementing the steps of the above method embodiments when being executed by a processor. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying said computer program code, medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, etc. It should be noted that the computer readable medium may contain content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media does not include electrical carrier signals and telecommunications signals as is required by legislation and patent practice.

While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.

It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.

Claims

1. A shopping information pushing method is characterized by comprising the following steps:

2. The method of claim 1, wherein determining recommendation information for a shopping type corresponding to the target user based on historical network behavior records for the shopping types of the network-wide users comprises:

3. The method of claim 1 or 2, wherein the obtaining historical network behavior records of network-wide users comprises:

4. The method of any of claims 1-3, wherein determining candidate items based on historical network behavior records of the shopping types of the network-wide users comprises:

5. The method of any one of claims 1-4, wherein said determining a set of neighbor users of the network-wide users that are similar to the target user based on the scoring matrix comprises:

6. A shopping information pushing method is characterized by comprising the following steps:

7. A shopping information pushing apparatus, comprising:

8. A shopping information pushing apparatus, comprising:

9. An electronic device, comprising a processor and a memory:

the memory is used for storing a program for executing the method of any one of claims 1 to 6;

the processor is configured to execute programs stored in the memory.

10. A computer storage medium for storing computer software instructions for the shopping information pushing apparatus, comprising program for executing the above aspect designed for the shopping information pushing apparatus.