WO2017000513A1

WO2017000513A1 - Information pushing method and apparatus based on user search behavior, storage medium, and device

Info

Publication number: WO2017000513A1
Application number: PCT/CN2015/097574
Authority: WO
Inventors: 徐昭吉; 赵秀慧; 王薇薇; 史岩芳; 张振平; 谢嘉伦; 郭珠城; 杜旭; 李树超; 马川; 叶璐; 张素萍; 叶晨晖; 赵海磊; 郑喜英; 周文娟; 张旭祥
Original assignee: 百度在线网络技术（北京）有限公司
Priority date: 2015-06-30
Filing date: 2015-12-16
Publication date: 2017-01-05
Also published as: CN104933172A

Abstract

An information pushing method and apparatus based on a user search behavior, a storage medium, and a device. The method comprises: acquiring a query of a user (S110); analyzing the query, so as to determine product association features (S120); matching the product association features and product features (S130); and providing matched product association information for the user, and displaying the information (S140). The technical solution can establish a connection between user search and a product subject when a user performs search, and provide association information for the user, thereby providing an auxiliary decision for the user, and improving the user experience.

Description

Information push method, device, storage medium and device based on user search behavior

This patent application claims to be submitted on June 30, 2015, the application number is 201510373611.5, the applicant is Baidu Online Network Technology (Beijing) Co., Ltd., and the invention name is "a method and device for information push based on user search behavior". Priority of the patent application, the entire contents of which is hereby incorporated by reference.

Technical field

The embodiments of the present invention relate to a network search technology, and in particular, to an information push method, apparatus, storage medium, and device based on user search behavior.

Background technique

In the current network authentication system, the user can obtain the authentication information of the merchant as an auxiliary reference information for the purchase decision.

However, the way to obtain the merchant authentication information can only be to search for the merchant's authentication information by using the merchant company name and the website name as a search term.

The acquisition method of the above scheme is single, and in the case that the user is uncertain about the name of the merchant company and the website, the merchant with the certification qualification cannot be inquired.

Summary of the invention

The embodiment of the invention provides an information push method, device, storage medium and device based on user search behavior, so as to solve the problem that the user has a single means for retrieving and acquiring information, and cannot accurately query when the user is uncertain of the search term. .

In a first aspect, an embodiment of the present invention provides an information pushing method based on a user search behavior, including:

Get the user's search term;

The search terms are analyzed to determine product association characteristics;

Matching the product association feature with the product feature;

The associated information of the matched product is provided to the user for display.

In a second aspect, the embodiment of the present invention further provides an information pushing apparatus based on a user search behavior, including:

a search word acquisition unit for acquiring a search term of the user;

An association feature determining unit, configured to analyze the search term to determine a product association feature;

a feature matching unit, configured to match the product association feature with a product feature;

The associated information display unit is configured to provide related information of the matched product to the user for display.

In a third aspect, an embodiment of the present invention provides a non-volatile computer storage medium, where the computer storage medium stores one or more modules, when the one or more modules are executed by a user-based search behavior. When the device of the push method is executed, the device is caused to perform the following operations:

Get the user's search term;

The search terms are analyzed to determine product association characteristics;

Matching the product association feature with the product feature;

In a fourth aspect, an embodiment of the present invention provides an apparatus, including:

One or more processors;

Memory

One or more programs, the one or more programs being stored in the memory, and when executed by the one or more processors, performing the following operations:

Get the user's search term;

The search terms are analyzed to determine product association characteristics;

Matching the product association feature with the product feature;

The information pushing method, device, storage medium and device based on user search behavior provided by the embodiments of the present invention analyzes the search words of the user, establishes a relationship between the user search and the product features, and Displaying the associated information to the user can provide assistance to the user and improve the user experience.

DRAWINGS

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings to be used in the description of the embodiments will be briefly described below. Of course, the drawings in the following description are only some embodiments of the present invention, Those skilled in the art can also modify and replace these drawings without paying any creative work.

1 is a schematic flowchart of a method for pushing information based on user search behavior according to Embodiment 1 of the present invention;

2A is a flowchart of a method for pushing information based on user search behavior according to Embodiment 2 of the present invention;

2B is a diagram showing a page recommendation information display method of an information push method based on a user search behavior according to Embodiment 2 of the present invention;

3 is a schematic structural diagram of an information pushing apparatus based on user search behavior according to Embodiment 3 of the present invention;

FIG. 4 is a schematic diagram of a hardware structure of an apparatus for performing an information push method based on a user search behavior according to Embodiment 5 of the present invention.

detailed description

The technical solutions in the embodiments of the present invention are clearly and completely described in the following with reference to the accompanying drawings. Rather than limiting the invention to these specific embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative efforts are within the scope of the present invention.

Embodiment 1

FIG. 1 is a schematic flowchart of a method for pushing information based on user search behavior according to Embodiment 1 of the present invention. This embodiment is applicable to a user searching through a search window in a browser or software. condition. The method can be performed by an information push device based on user search behavior, the device being implemented by software and/or hardware. The device can be configured on a search engine server.

Referring to FIG. 1 , an information pushing method based on user search behavior provided by this embodiment specifically includes:

S110. Obtain a search term of the user.

The user's search behavior may be that the user needs to know or purchase a certain product or service, and enter a search term related to the product or service in the browser search bar.

S120. Analyze the search term to determine a product association feature.

The search term is analyzed, and operations such as expanding or mining can be performed to determine the product association feature of the search term, that is, the feature related to the search term and related to the product.

The specific analysis of the above operations may include semantic analysis of the search words, obtaining the analysis results, and then querying the analysis results in the set product keyword library, and querying the obtained keywords as product association features. If the directly corresponding keyword cannot be found during the query, the keywords that are similar to the search result analysis result are used as product association features, and the similarities may be similar or similar.

In the process of querying, the product feature keyword library used may be one or more of the following libraries: a requirement type keyword library, an industry name keyword library, a company name keyword library, a product name keyword library, and a management Regional keyword library; these keyword libraries are the keyword libraries that have been set in the server.

S130. Match the product association feature with the product feature.

In order to finally provide users with reliable and practical information, it is necessary to match the product association features and user characteristics with the product features, and comprehensively match to obtain the associated information. Before matching the product association feature and the user's attribute feature with the product feature, the user feature can be obtained by:

Obtaining historical behavior data of the user, determining attribute characteristics of the user according to the historical behavior data, and the historical behavior data may be one or more of the following: search behavior data, purchase behavior data, and exercise behavior data, exemplary The search behavior data may be a keyword with a relatively high frequency that has been recently searched, and the purchase data may be a related product or service purchased by the user;

Alternatively, the current state of the user is obtained as an attribute feature, and the current state may be one or more of the following: a user location, a user gender, and a user age.

Of course, in the process of feature matching, the product association feature can be matched only with the product feature, or only the user feature and the product feature can be matched to obtain the associated information.

S140. Provide related information of the matched product to the user for display.

The above operation is to display the related information of the matched product, and can be displayed to the user in the search page of the user or on the interface of the software, and provide the user with the auxiliary decision of the purchase to improve the user experience.

The associated information of the matched product is the information recommended to the user. The recommended information may be the name of the certified enterprise that operates the product, and may also include the following information: the business scope of the certified enterprise, the credit rating of the certified enterprise, and the qualification of the certified enterprise. A brief introduction to related products and other information.

In a specific implementation manner of the embodiment, S140 specifically displays related information of the matched product in a search result page of the search engine as a search result or recommendation information.

For example, if the relevant search words that need to be searched are input in the search bar, and the processing of S110 to S130 is performed, the recommended information is directly displayed, and the search result information is displayed in the search result display column, and the search result information may include the recommended information. The information of the recommended information is displayed in another recommended information display column. The recommended information in the search result display column and the recommended information in the recommended information display column may be the same or different, such as displaying the same product related information in two columns or Different product related information.

In the above technical solution, the S140 may specifically: in the matched products, perform screening according to the order of the products, and provide related information of the filtered products to the user for display. Exemplarily, the ordering of the products can be performed according to the feature matching degree of the products. The higher the matching degree, the higher the ranking; the ranking can be sorted according to the enterprise evaluation reputation related to the product, and the higher the reputation, the higher the ranking. .

The technical solution provided by the embodiment is: when the user performs the search, establishing a connection between the user search and the product body, and providing the related information to the user, providing the user with the auxiliary decision at the time of purchase, and improving the user experience.

Embodiment 2

2A is a flowchart of a method for pushing information based on user search behavior according to Embodiment 2 of the present invention. This embodiment provides a preferred embodiment of the method based on the foregoing embodiment. The method includes:

S210. Obtain a search term of a user.

Referring to FIG. 2B, enter a search term in the search field of the search page, such as inputting "air purifier" to search.

S220: Perform semantic analysis on the search term, and query the semantic analysis result in the set product feature keyword library to determine a corresponding keyword as the associated feature;

The product feature keyword library includes at least one of the following: a demand type keyword library, an industry name keyword library, a company name keyword library, a product name keyword library, and a business region keyword library.

Taking "air purifying agent" as an example, through semantic analysis and matching in the enterprise name keyword database, the product association characteristics are determined, such as the specific enterprises of the purifying agent.

For each company, you can first analyze the company's industry, business scope, and business location, and store it in the keyword database.

S230. Match the product association feature with the product feature.

Specifically, it can be matched to know which companies produce and sell air purifiers. In addition, it is also possible to combine user attributes, for example, to obtain the geographic location of the user, and then consider information such as the sales geographic location of the product as a match.

S240. Provide related information of the matched product to the user for display.

As shown in FIG. 2B, the related results of the search are displayed in the search result page on the left side, and the related information of the matching product is displayed in the recommended information display column on the right side. In this example, the certified enterprise is displayed. The name, for example, the result of "air purifying agent" is the name of the company that produces and sells the air purifying agent in the endorsement of the company at the bottom right of the page.

The technical solution provided by the embodiment can establish a connection between the user search and the product feature when the user searches, display the authentication enterprise information to the user for reference, provide an auxiliary decision when the user purchases, and improve the user experience.

Embodiment 3

FIG. 3 is a schematic structural diagram of an information pushing apparatus based on user search behavior according to Embodiment 3 of the present invention. Referring to Figure 3, the specific structure of the device is as follows:

a search word obtaining unit 310, configured to acquire a search term of the user;

The association feature determining unit 320 is configured to analyze the search term to determine a product association Levy

Feature matching unit 330, configured to match the product association feature with a product feature;

The associated information display unit 340 is configured to provide related information of the matched product to the user for display.

The association feature determining unit 320 is specifically configured to perform semantic analysis on the search term, and query the semantic analysis result in the set product feature keyword library to determine a corresponding keyword as the association feature;

The product feature keyword library includes one or more of the following: a demand type keyword library, an industry name keyword library, an enterprise name keyword library, a product name keyword library, and a business region keyword library.

The device further includes an attribute feature determining unit 350.

The attribute feature determining unit 350 is configured to acquire historical behavior data of the user, and determine attribute characteristics of the user according to the historical behavior data;

The historical behavior data may be one or more of the following: search behavior data, purchase behavior data, and exercise behavior data;

or,

The attribute feature determining unit 350 is configured to acquire a current state of the user as an attribute feature;

The current status may be one or more of the following: a user location, a user gender, a user age, and the like.

The feature matching unit 330 is specifically configured to match the attribute feature of the user determined by the product association feature and the attribute feature determining unit with the product feature.

The associated information display unit 340 is specifically configured to:

The related information of the matched product is displayed as a search result or recommendation information in the search result page of the search engine.

Alternatively, the associated information display unit 340 is specifically configured to:

In matching products, screening according to the order of products;

The associated information of the filtered product is provided to the user for display.

The technical solution provided by this embodiment: when the user searches, establish a user search and product The relationship between the subjects, and the associated information is provided to the user, providing the user with an auxiliary decision at the time of purchase, thereby improving the user experience.

Therefore, the technical solution can solve the problem that the user has a single means for retrieving the acquired information, and the user cannot be accurately queried without the user being sure of the search term.

Embodiment 4

The embodiment provides a non-volatile computer storage medium storing one or more modules when the one or more modules are executed by a device that performs an information push method based on a user search behavior , causing the device to perform the following operations:

Get the user's search term;

The search terms are analyzed to determine product association characteristics;

Matching the product association feature with the product feature;

When the module stored in the foregoing storage medium is executed by the device, analyzing the search term to determine a product association feature may include:

Performing semantic analysis on the search term, and querying the semantic analysis result in the set product feature keyword library to determine a corresponding keyword as the associated feature;

When the module stored in the storage medium is executed by the device, the matching feature is matched with the product feature, and the method may include:

Matching the product association feature and the user's attribute characteristics with the product features.

When the module stored in the storage medium is executed by the device, the product association feature and the attribute feature of the user are matched with the product feature, and may further include:

Obtaining historical behavior data of the user, and determining attribute characteristics of the user according to the historical behavior data; wherein the historical behavior data includes at least one of the following: search behavior data, purchase behavior data, and exercise behavior data;

or,

Obtaining a current state of the user as an attribute feature; wherein the current state includes at least one of the following Item: User location, user gender, and user age.

When the module stored in the storage medium is executed by the device, the related information of the matched product is provided to the user for display, which may include:

When the module stored in the storage medium is executed by the device, the related information of the matched product is provided to the user for display, including:

In matching products, screening according to the order of products;

Through the above description of the embodiments, those skilled in the art can clearly understand that the present invention can be implemented by software and necessary general hardware, and can also be implemented by hardware, but in many cases, the former is a better implementation. . Based on such understanding, the technical solution of the present invention, which is essential or contributes to the prior art, may be embodied in the form of a software product, which may be stored in a computer readable storage medium, such as a floppy disk of a computer. , Read-Only Memory (ROM), Random Access Memory (RAM), Flash (FLASH), hard disk or optical disk, etc., including a number of instructions to make a computer device (can be a personal computer) The server, or network device, etc.) performs the methods described in various embodiments of the present invention.

Embodiment 5

FIG. 4 is a schematic structural diagram of hardware of a device for performing an information push method based on a user search behavior according to Embodiment 5 of the present invention. Referring to FIG. 4, the device includes, including:

One or more processors 410, one processor 410 is taken as an example in FIG. 4;

Memory 420; and one or more modules.

The device may also include an input device 430 and an output device 440. The processor 410, the memory 420, the input device 430, and the output device 440 in the device may be connected by a bus or other means, and the connection through the bus is taken as an example in FIG.

The memory 420 is used as a computer readable storage medium, and can be used for storing a software program, a computer executable program, and a module, such as an information push method based on user search behavior in the embodiment of the present invention. Corresponding program instructions/modules (for example, search term acquisition unit 310, association feature determination unit 320, feature matching unit 330, association information display unit 340, and attribute features in the information push device based on user search behavior shown in FIG. Determination unit 340). The processor 410 executes various function applications and data processing of the server by executing software programs, instructions, and modules stored in the memory 420, that is, the information push method based on the user search behavior in the foregoing method embodiments.

The memory 420 may include a storage program area and an storage data area, wherein the storage program area may store an operating system, an application required for at least one function; the storage data area may store data created according to usage of the terminal device, and the like. Moreover, memory 420 can include high speed random access memory, and can also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some examples, memory 420 can further include memory remotely located relative to processor 410, which can be connected to the terminal device over a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

Input device 430 can be used to receive input digital or character information and to generate key signal inputs related to user settings and function control of the terminal. Output device 440 can include a display device such as a display screen.

The one or more modules are stored in the memory 420, and when executed by the one or more processors 410, perform the following operations:

Get the user's search term;

The search terms are analyzed to determine product association characteristics;

Matching the product association feature with the product feature;

Further, analyzing the search term to determine product association characteristics may include:

Further, matching the associated feature with the product feature may include:

Further, matching the product association feature and the user attribute feature with the product feature Previously, it could also include:

or,

Obtaining a current state of the user as an attribute feature; wherein the current state includes at least one of the following: a user location, a user gender, and a user age.

Further, providing the associated information of the matched product to the user for display may include:

In matching products, screening according to the order of products;

It should be noted that, in the foregoing embodiment of the information pushing apparatus based on the user search behavior, each unit and module included is only divided according to functional logic, but is not limited to the above-mentioned division, as long as the corresponding function can be implemented. In addition, the specific names of the respective functional units are only for convenience of distinguishing from each other, and are not intended to limit the scope of protection of the present invention.

The above is only a specific embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily think of changes or substitutions within the technical scope of the present disclosure. All should be covered by the scope of the present invention. Therefore, the scope of the invention should be determined by the scope of the appended claims.

Claims

An information pushing method based on user search behavior, characterized in that it comprises:

Get the user's search term;

The search terms are analyzed to determine product association characteristics;

Matching the product association feature with the product feature;

The associated information of the matched product is provided to the user for display.
The method of claim 1 wherein analyzing the search term to determine product association characteristics comprises:

Performing semantic analysis on the search term, and querying the semantic analysis result in the set product feature keyword library to determine a corresponding keyword as the associated feature;

The product feature keyword library includes at least one of the following: a demand type keyword library, an industry name keyword library, a company name keyword library, a product name keyword library, and a business region keyword library.
The method of claim 1 wherein matching the associated feature to a product feature comprises:

Matching the product association feature and the user's attribute characteristics with the product features.
The method according to claim 3, wherein before the matching the product association feature and the user attribute feature with the product feature, the method further comprises:

Obtaining historical behavior data of the user, and determining attribute characteristics of the user according to the historical behavior data; wherein the historical behavior data includes at least one of the following: search behavior data, purchase behavior data, and exercise behavior data;

or,

Obtaining a current state of the user as an attribute feature; wherein the current state includes at least one of the following: a user location, a user gender, and a user age.
The method according to claim 1, wherein the providing the associated information of the matched product to the user for display comprises:

The related information of the matched product is displayed as a search result or recommendation information in the search result page of the search engine.
The method according to claim 1, wherein the providing the associated information of the matched product to the user for display comprises:

In matching products, screening according to the order of products;

The associated information of the filtered product is provided to the user for display.
An information pushing device based on user search behavior, comprising:

a search word acquisition unit for acquiring a search term of the user;

An association feature determining unit, configured to analyze the search term to determine a product association feature;

a feature matching unit, configured to match the product association feature with a product feature;

The associated information display unit is configured to provide related information of the matched product to the user for display.
The device according to claim 7, wherein the association feature determining unit is specifically configured to:

Performing semantic analysis on the search term, and querying the semantic analysis result in the set product feature keyword library to determine a corresponding keyword as the associated feature;

The product feature keyword library includes at least one of the following: a demand type keyword library, an industry name keyword library, a company name keyword library, a product name keyword library, and a business region keyword library.
The device according to claim 7, wherein the feature matching unit is specifically configured to:

Matching the product association feature and the user's attribute characteristics with the product features.
The device according to claim 9, further comprising: an attribute feature determining unit, configured to match the product association feature and the user attribute feature with the product feature

Obtaining historical behavior data of the user, and determining attribute characteristics of the user according to the historical behavior data;

The historical behavior data includes at least one of the following: search behavior data, purchase behavior data, and exercise behavior data;

or,

Get the current state of the user as an attribute feature;

The current status includes at least one of the following: a user location, a user gender, a user age, and the like.
The device according to claim 7, wherein the associated information display unit is specifically configured to:

The associated information of the matching product will be used as the search result in the search result page of the search engine. Or recommend information for display.
The device according to claim 7, wherein the associated information display unit is specifically configured to:

In matching products, screening according to the order of products;

The associated information of the filtered product is provided to the user for display.
A non-volatile computer storage medium storing one or more modules, wherein when the one or more modules are executed by a device that performs an information push method based on a user search behavior , causing the device to perform the following operations:

Get the user's search term;

The search terms are analyzed to determine product association characteristics;

Matching the product association feature with the product feature;

The associated information of the matched product is provided to the user for display.
An apparatus, comprising:

One or more processors;

Memory

One or more programs, the one or more programs being stored in the memory, and when executed by the one or more processors, performing the following operations:

Get the user's search term;

The search terms are analyzed to determine product association characteristics;

Matching the product association feature with the product feature;

The associated information of the matched product is provided to the user for display.