WO2017076073A1 - Method and apparatus for search and recommendation - Google Patents

Abstract

A method and apparatus for search and recommendation, the method for search and recommendation comprising the following steps: receiving a search term inputted by a user (S201); on the basis of the search term, acquiring recommended content (S202); on the basis of historical user behaviour information, predicting a further operation of the user on the recommended content (S203); on the basis of said further operation of the user on the recommended content, adding a candidate operation item to the recommended content, and providing to the user the recommended content with the added candidate operation item (S204). The present method for search and recommendation reduces the user operating steps and waiting time, reduces the user search operations, improves user search efficiency and information recommendation efficiency, and improves the user experience.

Description

Search recommendation method and device

Cross-reference to related applications

The present application claims the priority of the Chinese patent application No. 201510741426.7, filed on November 4, 2015 by the Baidu Online Network Technology (Beijing) Co., Ltd., entitled "Search Recommendation Method and Apparatus".

Technical field

The present invention relates to the field of Internet technologies, and in particular, to a search recommendation method and apparatus.

Background technique

With the rapid development of the Internet, more and more users search for information through search engines. When the user initiates the search, while providing the user with the search result related to the search term, the recommended content stored in a certain relationship with the search result may also be provided. Currently, when the user clicks on the recommended content, the search engine searches for the search term again with the recommended content, and generates a search result interface again for the user. In this way, the user still needs to select the desired result in the newly generated search result interface, the operation is cumbersome, the recommendation efficiency is low, and the user experience is poor.

Summary of the invention

The present invention aims to solve the above technical problems at least to some extent.

To this end, the first object of the present invention is to propose a search recommendation method capable of improving recommendation efficiency.

A second object of the present invention is to provide a search recommendation device.

In order to achieve the above object, a search recommendation method according to an embodiment of the first aspect of the present invention includes the steps of: receiving a search term input by a user; acquiring recommended content according to the search term; and predicting the user according to user historical behavior information. a further operation for the recommended content; and adding a candidate operation item to the recommended content according to the user's further operation for the recommended content, and providing the recommended content after adding the candidate operation item to the user.

The search recommendation method of the embodiment of the present invention may obtain the recommended content according to the search term input by the user, and predict the further operation of the recommended content by the user according to the historical behavior information of the user, and add the further operation as the candidate operation item of the recommended content. Provided to the user, so that the user can directly enter the interface desired by the user by triggering the candidate operation item, instead of starting the search again for the entity corresponding to the recommended content, the operation can be achieved in one operation, and the user operation steps and waiting time are reduced. The user's search operation is reduced, the user search efficiency and the information recommendation efficiency are improved, and the user experience is improved.

The second aspect of the present invention provides a search recommendation apparatus, including: a first receiving module, configured to receive a search term input by the user; an obtaining module, configured to obtain recommended content according to the search term; a prediction module, configured to predict, according to user historical behavior information, a further operation of the user for the recommended content; adding a module, according to the Adding a candidate operation item to the recommended content by the user for the further operation of the recommended content; and a first providing module, configured to provide the recommended content after adding the candidate operation item to the user.

The search recommendation device of the embodiment of the present invention may obtain the recommended content according to the search term input by the user, and predict the further operation of the recommended content by the user according to the historical behavior information of the user, and add the further operation as the candidate operation item of the recommended content. Provided to the user, so that the user can directly enter the interface desired by the user by triggering the candidate operation item, instead of starting the search again for the entity corresponding to the recommended content, the operation can be achieved in one operation, and the user operation steps and waiting time are reduced. The user's search operation is reduced, the user search efficiency and the information recommendation efficiency are improved, and the user experience is improved.

An embodiment of the third aspect of the present invention provides an electronic device comprising: one or more processors; a memory; one or more programs, the one or more programs being stored in the memory when Or when the plurality of processors are executed, the search recommendation method of the first aspect of the present invention is executed.

A fourth aspect of the present invention provides a non-volatile computer storage medium storing one or more programs, when the one or more programs are executed by one device, causing the device A search recommendation method in accordance with an embodiment of the first aspect of the present invention is performed.

The additional aspects and advantages of the invention will be set forth in part in the description which follows.

DRAWINGS

The above and/or additional aspects and advantages of the present invention will become apparent and readily understood from

The above and/or additional aspects and advantages of the present invention will become apparent and readily understood from

1a and 1b are diagrams in a search recommendation process in the related art;

2 is a flow chart of a search recommendation method according to an embodiment of the present invention;

3 is a flow chart of a search recommendation method according to another embodiment of the present invention;

4a-4f are specific illustrations of a search recommendation process in accordance with one embodiment of the present invention;

FIG. 5 is a schematic structural diagram of a search recommendation device according to an embodiment of the present invention; FIG.

FIG. 6 is a schematic structural diagram of a search recommendation according to another embodiment of the present invention.

detailed description

The embodiments of the present invention are described in detail below, and the examples of the embodiments are illustrated in the drawings, wherein the same or similar reference numerals are used to refer to the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are intended to be illustrative of the invention and are not to be construed as limiting.

In the description of the present invention, it is to be understood that the term "plurality" means two or more; the terms "first" and "second" are used for descriptive purposes only and are not to be construed as indicating or implying that they are relatively important. Sex.

The inventor of the present invention has found that, after the search engine provides the recommended content to the user according to the search term input by the user, if the user is interested in the recommended content and needs further operations, clicking the recommended content once again initiates the search, and the search result is obtained from the search result. Find what you need.

For example, as shown in FIG. 1a, when the user searches for "Hong Kong", the search engine also provides the search results of "Movie Port - Trailer" and "Hong Kong (Douban)". - Related film and television works, such as "Going the Egg Tumor Jun", "The Third Love", "Let the Bullets Fly", "Speed and Passion 7" and so on. If the user wants to watch "Let the bullet fly", the user needs to click "Let the bullet fly" to initiate the search again, resulting in the interface shown in Figure 1b. Then, find the online live broadcast of “Let the Bullets Fly” in the interface, click to enter the viewing, and complete your needs.

It can be seen that, in the current way, the user can not achieve the goal by one click, and the path of the user to obtain the desired result is increased, especially for the user of the mobile terminal, so the recommendation efficiency is low. To this end, the present invention proposes a search recommendation method and apparatus.

A search recommendation method and apparatus according to an embodiment of the present invention will be described below with reference to the accompanying drawings.

It should be understood that embodiments of the present invention are preferably applicable to mobile terminals, for example, an IOS operating system (IOS is a handheld operating system developed by Apple), an Android operating system (Android system is a Linux-based free and open source code The operating system), the Windows Phone operating system (Windows Phone is a mobile phone operating system issued by Microsoft Corporation) mobile terminal, of course, is also applicable to personal computers and other smart mobile terminals, the invention is not limited thereto. It should be understood that in the embodiment of the present invention, the mobile terminal may be a hardware device having various operating systems such as a mobile phone, a tablet computer, a personal digital assistant, an e-book, and the like.

In order to solve the above problem, the present invention provides a search recommendation method, including the steps of: receiving a search term input by a user; acquiring recommended content according to the search term; predicting further operation of the user for the recommended content according to the user historical behavior information; The candidate operation item is added to the recommended content for the further operation of the recommended content, and the recommended content after the candidate operation item is added is provided to the user.

2 is a flow chart of a search recommendation method in accordance with one embodiment of the present invention.

As shown in FIG. 2, the search recommendation method according to an embodiment of the present invention includes the following steps.

S201. Receive a search term input by a user.

The search engine can provide a search portal and receive search terms entered by the user through the search portal.

Among them, the search term (ie query) can be characters of various languages (such as text, pinyin, symbols and / or numbers) One of them, or a combination thereof.

S202. Acquire a recommended content according to the search term.

After receiving the search term, the search engine can obtain the search result according to the search term and obtain the related recommended content. Specifically, when the search engine obtains the recommended content, the relevance of the content in the database and the search result may be scored according to a preset algorithm, and the recommended content is obtained from the plurality of data according to the score result.

The present invention does not limit the form of the recommended content. For example, the recommended content may include a map, an entity name, and the like.

S203. Predict the user's further operation for the recommended content according to the user historical behavior information.

In an embodiment of the present invention, the user historical behavior information may include one or more of historical search information, historical browsing information, historical click information, and the like. It should be understood that the user history behavior in the embodiment of the present invention may be obtained by recording historical search information, historical browsing information, historical click information, and the like of a plurality of users in advance.

In one embodiment of the present invention, further operations by the user for the recommended content may be obtained by search engine mining.

That is to say, the search engine can analyze and mine large data such as historical search information, historical browsing information, and historical click information of a plurality of users, thereby determining what is the most likely further operation of the user for the recommended content.

Specifically, in an embodiment of the present invention, S203 may specifically include: determining a category of the recommended content; analyzing an operation tendency of the user for the category of the recommended content according to the user historical behavior information, and determining, according to the operation tendency, the user further for the recommended content. operating.

That is, the search engine can first determine the category of the recommended content. For example, film and television, institutions (such as medical institutions, financial institutions, educational institutions, etc.), people, and things (for example, may include animals, plants, attractions, commodities, etc.). Then, the search engine can analyze the big data such as the user's historical search information, historical browsing information, historical click information, and the user's tendency to operate on the category of the recommended content, that is, the category of the recommended content recommended by most users. Further operations and as a further action by the user for the recommended content.

For example, if the user's historical behavior information is obtained: in the search result corresponding to the movie that has been offline, most users click on it to watch immediately, and in the search result corresponding to the hot movie, most users are from the user. Clicking on the seated purchase ticket, in the recommended content corresponding to the "Hong Kong", the further operation corresponding to the offline movie is "Immediately Watch", and the further operation corresponding to the hot movie is "Selection Ticket Purchase" .

According to the user historical behavior information: for the pet category search results, most users choose to view the recommended pet picture or purchase the pet, then in the recommended content of the pet category, the further operation corresponding to the recommended content is "pet picture" and / Or "purchase."

If the user historical behavior information is obtained: for the search result of the organization class, most users select the appointment registration number, and in the recommendation content of the organization class, the further operation corresponding to the recommendation content is “reservation registration”.

According to the user historical behavior information: for the search result of the character class, most users choose to view the latest dynamics of the recommended person or the circle of contacts, then in the recommended content of the character class, the further operation corresponding to the recommended content is "What's new" and / or "people circles."

S204. Add a candidate operation item to the recommended content according to a further operation of the user for the recommended content, and provide the recommended content after the candidate operation item is added to the user.

Wherein, each recommended content may correspond to one or more candidate operation items. The candidate operation item is an operation entry corresponding to the recommended content for realizing the user's purpose. That is, the user can directly enter the interface desired by the user by triggering or clicking on the candidate action item. Therefore, after the recommended content after the candidate operation item is added is provided to the user, the user can directly enter the required interface by clicking the candidate operation item, and does not need to initiate the search again for the entity corresponding to the recommended content, as shown in FIG. 1 . For example, the user can achieve the goal in one operation, reducing the user steps and waiting time.

The search recommendation method of the embodiment of the present invention may obtain the recommended content according to the search term input by the user, and predict the further operation of the recommended content by the user according to the historical behavior information of the user, and add the further operation as the candidate operation item of the recommended content. Provided to the user, so that the user can directly enter the interface desired by the user by triggering the candidate operation item, instead of starting the search again for the entity corresponding to the recommended content, the operation can be achieved in one operation, and the user operation steps and waiting time are reduced. The user's search operation is reduced, the user search efficiency and the information recommendation efficiency are improved, and the user experience is improved.

3 is a flow chart of a search recommendation method in accordance with another embodiment of the present invention.

As shown in FIG. 3, the search recommendation method in the embodiment of the present invention includes the following steps:

S301. Receive a search term input by a user.

The search engine can provide a search portal and receive search terms entered by the user through the search portal.

The search term (ie, query) may be one of characters (such as characters, pinyin, symbols, and/or numbers, etc.) in various languages or a combination thereof.

S302. Acquire a recommended content according to the search term.

After receiving the search term, the search engine can obtain the search result according to the search term and obtain the related recommended content. Specifically, when the search engine obtains the recommended content, the relevance of the content in the database and the search result may be scored according to a preset algorithm, and the recommended content is obtained from the plurality of data according to the score result.

The present invention does not limit the form of the recommended content. For example, the recommended content may include a map, an entity name, and the like.

S303. Predict the user's further operation for the recommended content according to the user historical behavior information.

In an embodiment of the present invention, the user historical behavior information may include one or more of historical search information, historical browsing information, historical click information, and the like. It should be understood that the user history behavior in the embodiment of the present invention may be obtained by recording historical search information, historical browsing information, historical click information, and the like of a plurality of users in advance.

In one embodiment of the present invention, further operations by the user for the recommended content may be obtained by search engine mining.

In other words, the search engine can search historical information, historical browsing information, and historical click information for many users. The big data is analyzed and mined to determine what the user is most likely to do for the recommended content.

Specifically, in an embodiment of the present invention, S303 may specifically include: determining a category of the recommended content; analyzing an operation tendency of the user for the category of the recommended content according to the user historical behavior information, and determining, according to the operation tendency, the user further for the recommended content. operating.

That is, the search engine can first determine the category of the recommended content. For example, film and television, institutions (such as medical institutions, financial institutions, educational institutions, etc.), people, and things (for example, may include animals, plants, attractions, commodities, etc.). Then, the search engine can analyze the big data such as the user's historical search information, historical browsing information, historical click information, and the user's tendency to operate on the category of the recommended content, that is, the category of the recommended content recommended by most users. Further operations and as a further action by the user for the recommended content.

S304. Add a candidate operation item to the recommended content according to a further operation of the user for the recommended content, and provide the recommended content after the candidate operation item is added to the user.

Wherein, each recommended content may correspond to one or more candidate operation items. The candidate operation item is an operation entry corresponding to the recommended content for realizing the user's purpose. That is, the user can directly enter the interface desired by the user by triggering or clicking on the candidate action item. Therefore, after the recommended content after the candidate operation item is added is provided to the user, the user can directly enter the required interface by clicking the candidate operation item, and does not need to initiate the search again for the entity corresponding to the recommended content, as shown in FIG. 1 . For example, the user can achieve the goal in one operation, reducing the user steps and waiting time.

S305. Receive a trigger instruction of the user on the candidate operation item.

The triggering command may be a mouse click, a touch operation, a voice instruction, or the like.

S306. Acquire a corresponding resource according to the triggering instruction, and provide the corresponding resource to the user.

For example, as shown in FIG. 4a, when a user searches for a movie-like query, such as "Hong Kong", the search engine can recommend "Hong Kong 囧 _ related film and television works" for the user, including movies that are being displayed like Hong Kong ( ( Such as getting out of the tumor and the third kind of love) and the same wonderful film and television works as Hong Kong (such as letting bullets fly and speed and passion 7). In addition, the search engine can also provide users with a "seat ticket purchase" entry for the movie being shown, as well as an "immediate view" entry for other movies. When the user clicks on the "Read Now" entry of "Let the bullet fly", the user can directly enter the video playing interface shown in Figure 4b, which improves the user experience.

As shown in FIG. 4c, when the user searches for a pet class query, such as "Golden Hair", the search engine may recommend "Golden Hair_Related Animals" for the user, and the user may be interested in these recommended cute pet pictures, and may also want to purchase one. Only cute pets. Therefore, the search engine can provide two entries of "pet picture" and/or "purchase" to the recommendation card. When the user clicks on the shopping cart icon below the Hucks in Figure 4c, the "Siberian Husky Online Purchase" interface shown in Figure 4d can be accessed. Therefore, the user can avoid the search again and enter the pet picture or purchase the cute pet interface in advance, thereby improving the user search efficiency.

As shown in FIG. 4e, when a user searches for a mechanism type query, such as "child research institute", the search engine can recommend "child" for the user. Research institutes_related institutions, such as similar hospitals that can be recommended: Beijing Children's Hospital, etc. When users are interested in recommended hospitals, it is very likely that they will need to hang these hospital numbers. Therefore, search engines can register for appointments. The portal is provided to the recommendation card. When the user clicks on the "reservation registration" in Fig. 4e, the appointment registration interface including the doctor list shown in Fig. 4f can be accessed.

For another example, when the user searches for a character class query such as an artist "Zhang", the search engine can recommend "Zhang _ related artist" Li and Wang. Most users may want to know the latest developments of artists and/or complex connections. Therefore, search engines can provide the latest developments and connections of Lee and Wang to the recommended cards to satisfy the most clicks of users. I want the information needs. When the user clicks on Lee's latest news or connections, he can display Lee's latest news or contacts.

The search recommendation method of the embodiment of the present invention may obtain the recommended content according to the search term input by the user, and predict the further operation of the recommended content by the user according to the historical behavior information of the user, and add the further operation as the candidate operation item of the recommended content. Provided to the user, so that the user can directly enter the interface desired by the user by triggering the candidate operation item, instead of starting the search again for the entity corresponding to the recommended content, the operation can be achieved in one operation, and the user operation steps and waiting time are reduced. The user's search operation is reduced, the user search efficiency and the information recommendation efficiency are improved, and the user experience is improved.

In order to implement the above embodiment, the present invention also proposes a search recommendation device.

A search recommendation device includes: a first receiving module, configured to receive a search term input by a user; an obtaining module, configured to obtain recommended content according to the search term; and a prediction module, configured to predict, according to the historical behavior information of the user, the user for the recommended content a further operation; adding a module, configured to add a candidate operation item to the recommended content according to a further operation of the user for the recommended content; and a first providing module, configured to provide the recommended content after the candidate operation item is added to the user.

FIG. 5 is a schematic structural diagram of a search recommendation device according to an embodiment of the present invention.

As shown in FIG. 5, the search recommendation apparatus according to the embodiment of the present invention includes: a first receiving module 10, an obtaining module 20, a prediction module 30, an adding module 40, and a first providing module 50.

Specifically, the first receiving module 10 is configured to receive a search term input by a user.

The first receiving module 10 can provide a search portal and receive a search term input by the user through the search portal.

The search term (ie, query) may be one of characters (such as characters, pinyin, symbols, and/or numbers, etc.) in various languages or a combination thereof.

The obtaining module 20 is configured to obtain recommended content according to the search term.

After the first receiving module 10 receives the search term, the obtaining module 20 may obtain the search result according to the search term and obtain related recommended content. Specifically, when acquiring the recommended content, the obtaining module 20 may score the relevance of the content in the database and the search result according to a preset algorithm, and obtain the recommended content from the plurality of data according to the score result.

The present invention does not limit the form of the recommended content. For example, the recommended content may include a map, an entity name, and the like.

The prediction module 30 is configured to predict further operations of the user for the recommended content according to the user historical behavior information.

In an embodiment of the present invention, the user historical behavior information may include one or more of historical search information, historical browsing information, historical click information, and the like. It should be understood that the user history behavior in the embodiment of the present invention may be obtained by recording historical search information, historical browsing information, historical click information, and the like of a plurality of users in advance.

In one embodiment of the present invention, further operations by the user for the recommended content may be obtained by search engine mining.

That is to say, the prediction module 30 can analyze and mine large data such as historical search information, historical browsing information, and historical click information of a plurality of users, thereby determining what is the most likely further operation of the user for the recommended content.

Specifically, in an embodiment of the present invention, the prediction module 30 may be specifically configured to: determine a category of the recommended content; analyze an operation tendency of the user for the category of the recommended content according to the user historical behavior information, and determine, according to the operation tendency, the user for the recommendation Further manipulation of the content.

That is, prediction module 30 may first determine the category of recommended content. For example, film and television, institutions (such as medical institutions, financial institutions, educational institutions, etc.), people, and things (for example, may include animals, plants, attractions, commodities, etc.). Then, the prediction module 30 can analyze big data such as historical search information, historical browsing information, and historical click information of the user, and dig out the user's operation tendency for the category of the recommended content, that is, most users for the determined recommended content. Further manipulation of the category and as a further action by the user for the recommended content.

The adding module 40 is configured to add a candidate operation item to the recommended content according to a further operation of the user for the recommended content.

Wherein, each recommended content may correspond to one or more candidate operation items. The candidate operation item is an operation entry corresponding to the recommended content for realizing the user's purpose. That is, the user can directly enter the interface desired by the user by triggering or clicking on the candidate action item. Therefore, after the recommended content after the candidate operation item is added is provided to the user, the user can directly enter the required interface by clicking the candidate operation item, and does not need to initiate the search again for the entity corresponding to the recommended content, as shown in FIG. 1 . For example, the user can achieve the goal in one operation, reducing the user steps and waiting time.

The first providing module 50 is configured to provide the recommended content after adding the candidate operation item to the user.

The search recommendation device of the embodiment of the present invention may obtain the recommended content according to the search term input by the user, and predict the further operation of the recommended content by the user according to the historical behavior information of the user, and add the further operation as the candidate operation item of the recommended content. Provided to the user, so that the user can directly enter the interface desired by the user by triggering the candidate operation item, instead of starting the search again for the entity corresponding to the recommended content, the operation can be achieved in one operation, and the user operation steps and waiting time are reduced. The user's search operation is reduced, the user search efficiency and the information recommendation efficiency are improved, and the user experience is improved.

FIG. 6 is a schematic structural diagram of a search recommendation according to another embodiment of the present invention.

As shown in FIG. 6, the search recommendation apparatus according to the embodiment of the present invention includes: a first receiving module 10, an obtaining module 20, a prediction module 30, an adding module 40, a first providing module 50, and a second receiving module 60. Second providing module 70

Specifically, the first receiving module 10, the obtaining module 20, the predicting module 30, the adding module 40, and the first providing module 50 can refer to the embodiment shown in FIG. 5, and details are not described herein again.

The second receiving module 60 is configured to receive a trigger instruction of the user for the candidate operation item.

The triggering command may be a mouse click, a touch operation, a voice instruction, or the like.

The second providing module 70 is configured to acquire a corresponding resource according to the triggering instruction and provide the same to the user.

For example, as shown in FIG. 4a, when the user searches for a movie-type query, such as "Hong Kong", the first providing module 50 can recommend "Hong Kong 囧 _ related film and television works" for the user, including being hot like the port. The film (such as the egg and the third love) and the same wonderful film and television works as the Hong Kong (such as let the bullets fly and speed and passion 7). In addition, the first providing module 50 can also provide the user with a "seat ticket purchase" entry for the movie being displayed, and an "immediate view" entry for other movies. When the user clicks on the "Read Now" entry of "Let the bullet fly", the second providing module 70 can provide the video playing interface shown in FIG. 4b, which improves the user experience.

As shown in FIG. 4c, when the user searches for a pet class query, such as "golden hair", the first providing module 50 may recommend "golden hair_related animals" for the user, and the user may be interested in these recommended cute pet pictures, and may also be interested. I want to buy a cute pet. Accordingly, the first providing module 50 can provide two entries of "pet picture" and/or "purchase" to the recommendation card. When the user clicks on the shopping cart icon below the Hacks in Figure 4c, the second providing module 70 can provide the "Siberian Husky Online Purchase" interface shown in Figure 4d. Therefore, the user can avoid the search again and enter the pet picture or purchase the cute pet interface in advance, thereby improving the user search efficiency.

As shown in FIG. 4e, when the user searches for a mechanism type query, such as "child research institute", the first providing module 50 can recommend "children institutes_related institutions" for the user, such as a similar hospital that can be recommended: Beijing Children's Hospital, etc. . When users are interested in the recommended hospitals, it is very likely that they will need to hang these hospital numbers. Therefore, the first providing module 50 can provide the "reservation registration" entry to the recommendation card. When the user clicks on "reservation registration" in FIG. 4e, the second providing module 70 can provide the appointment registration interface including the doctor list shown in FIG. 4f.

For another example, when the user searches for a character class query such as an artist "Zhang", the first providing module 50 can recommend "Zhang _ related artist" Li and Wang. Most users may want to know the latest developments of artists and/or complex circle of contacts. Therefore, the first providing module 50 can provide the latest dynamics and connections of Li and Wang to the recommended cards to satisfy the user. The key gets the most wanted information. When the user clicks on the latest news or network circle of Lee, the second providing module 70 can provide the latest news or personal information of Lee.

The search recommendation device of the embodiment of the present invention may obtain the recommended content according to the search term input by the user, and predict the further operation of the recommended content by the user according to the historical behavior information of the user, and add the further operation as the candidate operation item of the recommended content. Provided to the user, so that the user can directly enter the interface desired by the user by triggering the candidate operation item, instead of starting the search again for the entity corresponding to the recommended content, the operation can be achieved in one operation, and the user operation steps and waiting time are reduced. The user's search operation is reduced, the user search efficiency and the information recommendation efficiency are improved, and the user experience is improved.

In the description of the present specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" and the like means a specific feature described in connection with the embodiment or example. A structure, material or feature is included in at least one embodiment or example of the invention. In the present specification, the schematic representation of the above terms is not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in a suitable manner in any one or more embodiments or examples. In addition, various embodiments or examples described in the specification, as well as features of various embodiments or examples, may be combined and combined.

Moreover, the terms "first" and "second" are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, features defining "first" or "second" may include at least one of the features, either explicitly or implicitly. In the description of the present invention, the meaning of "a plurality" is two or more unless specifically and specifically defined otherwise.

Any process or method description in the flowcharts or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a particular logical function or process. And the scope of the preferred embodiments of the invention includes additional implementations, in which the functions may be performed in a substantially simultaneous manner or in an opposite order depending on the functions involved, in the order shown or discussed. It will be understood by those skilled in the art to which the embodiments of the present invention pertain.

The logic and/or steps represented in the flowchart or otherwise described herein, for example, may be considered as an ordered list of executable instructions for implementing logical functions, and may be embodied in any computer readable medium, Used in conjunction with, or in conjunction with, an instruction execution system, apparatus, or device (eg, a computer-based system, a system including a processor, or other system that can fetch instructions and execute instructions from an instruction execution system, apparatus, or device) Or use with equipment. For the purposes of this specification, a "computer-readable medium" can be any apparatus that can contain, store, communicate, propagate, or transport a program for use in an instruction execution system, apparatus, or device, or in conjunction with the instruction execution system, apparatus, or device. More specific examples (non-exhaustive list) of computer readable media include the following: electrical connections (electronic devices) having one or more wires, portable computer disk cartridges (magnetic devices), random access memory (RAM), Read only memory (ROM), erasable editable read only memory (EPROM or flash memory), fiber optic devices, and portable compact disk read only memory (CDROM). In addition, the computer readable medium may even be a paper or other suitable medium on which the program can be printed, as it may be optically scanned, for example by paper or other medium, followed by editing, interpretation or, if appropriate, other suitable The method is processed to obtain the program electronically and then stored in computer memory.

It should be understood that portions of the invention may be implemented in hardware, software, firmware or a combination thereof. In the above-described embodiments, multiple steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be used in the art. Any one of the column technologies or a combination thereof: discrete logic circuits with logic gates for implementing logic functions on data signals, application specific integrated circuits with suitable combinational logic gates, programmable gate arrays (PGA) ), field programmable gate array (FPGA), etc.

One of ordinary skill in the art can understand that all or part of the steps carried by the method of implementing the above embodiments can be completed by a program to instruct related hardware, and the program can be stored in a computer readable storage medium. When executed, one or a combination of the steps of the method embodiments is included.

In addition, each functional unit in each embodiment of the present invention may be integrated into one processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above integrated modules can be implemented in the form of hardware or in the form of software functional modules. The integrated modules, if implemented in the form of software functional modules and sold or used as stand-alone products, may also be stored in a computer readable storage medium.

The above mentioned storage medium may be a read only memory, a magnetic disk or an optical disk or the like. Although the embodiments of the present invention have been shown and described, it is understood that the above-described embodiments are illustrative and are not to be construed as limiting the scope of the invention. The embodiments are subject to variations, modifications, substitutions and variations.

Claims (12)

A search recommendation method, comprising the steps of: Receiving search terms entered by the user; Obtaining recommended content according to the search term; Predicting further operations of the user for the recommended content based on user historical behavior information; Adding a candidate operation item to the recommended content according to the further operation of the user for the recommended content, and providing the recommended content after adding the candidate operation item to the user. The search recommendation method according to claim 1, further comprising: Receiving a trigger instruction of the user to the candidate operation item; Corresponding resources are obtained according to the triggering instruction and provided to the user. The search recommendation method according to claim 1, wherein the user historical behavior information comprises one or more of historical search information, historical browsing information, and historical click information. The search recommendation method according to claim 1, wherein the further operation of predicting the user for the recommended content according to the user historical behavior information comprises: Determining the category of the recommended content; And analyzing, according to the user historical behavior information, an operation tendency of the user for the category of the recommended content, and determining, according to the operation tendency, the further operation of the user for the recommended content. The search recommendation method according to claim 1, wherein the further operation of the recommended content by the user is obtained by a search engine. A search recommendation device, comprising: a first receiving module, configured to receive a search term input by a user; An obtaining module, configured to obtain recommended content according to the search term; a prediction module, configured to predict, according to user historical behavior information, a further operation of the user for the recommended content; Adding a module, configured to add a candidate operation item to the recommended content according to the user's further operation for the recommended content; The first providing module is configured to provide the recommended content after adding the candidate operation item to the user. The search recommendation device of claim 6, further comprising: a second receiving module, configured to receive a trigger instruction of the candidate operation item by the user; And a second providing module, configured to acquire a corresponding resource according to the triggering instruction, and provide the same to the user. The search recommendation device according to claim 6, wherein the user historical behavior information comprises one or more of historical search information, historical browsing information, and historical click information. The search recommendation device according to claim 6, wherein the prediction module is specifically configured to: Determining the category of the recommended content; And analyzing, according to the user historical behavior information, an operation tendency of the user for the category of the recommended content, and determining, according to the operation tendency, the further operation of the user for the recommended content. The search recommendation device according to claim 6, wherein the further operation of the recommended content by the user is obtained by a search engine. An electronic device, comprising: One or more processors; Memory One or more programs, the one or more programs being stored in the memory, when executed by the one or more processors, performing the search recommendation method according to any one of claims 1-5. A non-volatile computer storage medium, characterized in that the computer storage medium stores one or more programs, when the one or more programs are executed by a device, causing the device to perform as claimed in claim 1. The search recommendation method described in any of the above.

Images