CN116701757A

CN116701757A - Active pushing method of search results, switching method and equipment of search pages

Info

Publication number: CN116701757A
Application number: CN202310576103.1A
Authority: CN
Inventors: 黄诗豪
Original assignee: Uc Mobile China Co ltd
Current assignee: Uc Mobile China Co ltd
Priority date: 2023-05-19
Filing date: 2023-05-19
Publication date: 2023-09-05

Abstract

The embodiment of the application provides an active pushing method of search results, a switching method and equipment of search pages, wherein the method comprises the following steps: acquiring user portraits and user behavior information through a preset program; determining a plurality of network search results for enabling active pushing of search information; determining target information for active pushing based on the user portraits, the user behavior information, and the plurality of network search results; and responding to program starting operation input by a user to a preset program, and actively displaying target information in a preset interface. In the embodiment, the user does not need to input the search keyword, but obtains the target information to be pushed based on the user portrait, the user behavior information and the plurality of network search results, so that the active pushing operation of the search information is effectively realized, the target information which is actively pushed not only can meet the personalized requirements of different users, but also can improve the good experience of the user on using the preset program, and further ensures the practicability of the method.

Description

Active pushing method of search results, switching method and equipment of search pages

Technical Field

The present application relates to the field of network technologies, and in particular, to an active pushing method of a search result, and a method and an apparatus for switching a search page.

Background

With the rapid development of network technology, the development of search programs for realizing search functions is becoming more and more mature, and when a user wants to learn certain information, search keywords can be actively input into the search programs, so that the search programs can execute corresponding information search operations based on the search keywords, and after search results are obtained, the search results can be displayed.

The information searching process is realized based on the search keywords, however, because the search requirement of the user may be specific, abstract and not easy to express, and the search result has a strong association relationship with the search keywords, the obtained exploration result may not meet the personalized requirement of the user on the information.

Disclosure of Invention

The embodiment of the application provides an active pushing method of search results, a switching method of search pages and equipment, which can realize the active pushing operation of the search results without inputting search keywords by users, and can meet the personalized requirements of different users.

In a first aspect, an embodiment of the present application provides an active pushing method for search information, including:

acquiring user portraits and user behavior information through a preset program;

determining a plurality of network search results for enabling active pushing of search information;

determining target information for active pushing based on the user portraits, user behavior information and the plurality of network search results;

and responding to program starting operation input by a user to the preset program, and actively displaying the target information in a preset interface.

In a second aspect, an embodiment of the present application provides an active pushing apparatus for searching information, including:

the first acquisition module is used for acquiring user portraits and user behavior information through a preset program;

the first determining module is used for determining a plurality of network search results for realizing active pushing of the search information;

the first determining module is used for determining target information for active pushing based on the user portrait, the user behavior information and the plurality of network search results;

the first processing module is used for responding to the program starting operation input by the user to the preset program and actively displaying the target information in a preset interface.

In a third aspect, an embodiment of the present application provides an electronic device, including: a memory, a processor; the memory is configured to store one or more computer instructions, where the one or more computer instructions when executed by the processor implement the active pushing method of the search information shown in the first aspect.

In a fourth aspect, an embodiment of the present application provides a computer storage medium storing a computer program, where the computer program makes a computer execute the active pushing method of search information shown in the first aspect.

In a fifth aspect, embodiments of the present application provide a computer program product comprising: a computer program which, when executed by a processor of an electronic device, causes the processor to perform the steps of the active pushing method of search information as described in the first aspect above.

In a sixth aspect, an embodiment of the present application provides a method for switching search pages, including:

acquiring search keywords;

determining search results corresponding to the search keywords and associating the search words;

displaying the search result and the associated search term in a preset page;

And responding to the switching operation input by the user aiming at the preset page or the associated search word, and switching and displaying the search result displayed in the preset page and the associated search word.

In a seventh aspect, an embodiment of the present application provides a switching device for a search page, including:

the second acquisition module is used for acquiring the search keywords;

the second determining module is used for determining search results corresponding to the search keywords and associated search words;

the second processing module is used for displaying the search results and the associated search words in a preset page;

and the second processing module is used for responding to the switching operation input by the user aiming at the preset page or the associated search word, and switching and displaying the search result displayed in the preset page and the associated search word.

In an eighth aspect, an embodiment of the present application provides an electronic device, including: a memory, a processor; the memory is configured to store one or more computer instructions, where the one or more computer instructions, when executed by the processor, implement the method for switching search pages shown in the sixth aspect.

In a ninth aspect, an embodiment of the present application provides a computer storage medium storing a computer program, where the computer program causes a computer to implement the method for switching search pages shown in the sixth aspect.

In a tenth aspect, embodiments of the present application provide a computer program product comprising: a computer program which, when executed by a processor of an electronic device, causes the processor to perform the steps in the search page switching method shown in the sixth aspect described above.

According to the active pushing method of the search result, the switching method of the search page and the device, provided by the embodiment of the application, the user portrait and the user behavior information are obtained through obtaining the preset program, a plurality of network search results are determined, then the target information for active pushing is determined based on the user portrait, the user behavior information and the plurality of network search results, when the user starts the program input by the preset program, the target information can be actively displayed in the preset interface based on the program starting operation, and as the target information is not determined by the search keywords input by the user, the active pushing operation of the search information is actively determined based on the user portrait, the user behavior information and the plurality of network search results, so that the active pushing target information can not only meet the personalized requirements of different users, but also improve the good experience of the user on the use of the preset program, further ensure the practicability of the method, and are beneficial to market popularization and application.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are some embodiments of the present application, and other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.

Fig. 1 is a schematic diagram of an active pushing method of a search result according to an embodiment of the present application;

fig. 2 is a flow chart of an active pushing method of a search result according to an embodiment of the present application;

FIG. 3 is a schematic diagram of a process for determining target information for active pushing based on the user representation, user behavior information and the plurality of network search results according to an embodiment of the present application;

FIG. 4 is a second schematic flow chart for determining target information for active pushing based on the user portraits, user behavior information and the plurality of network search results according to an embodiment of the present application;

FIG. 5 is a flowchart of another method for actively pushing search results according to an embodiment of the present application;

FIG. 6 is a schematic diagram of a switching operation for a preset page according to an embodiment of the present application;

FIG. 7 is a schematic diagram of a switching operation of associated search terms according to an embodiment of the present application;

FIG. 8 is a flowchart of another method for actively pushing search results according to an embodiment of the present application;

fig. 9 is a schematic structural diagram of a personalized recommendation system provided by an application embodiment of the present application;

fig. 10 is a schematic diagram of a heuristic search method based on recommendation technology according to an embodiment of the present application;

FIG. 11 is a schematic flow chart of a method for switching search pages according to an embodiment of the present application;

fig. 12 is a schematic structural diagram of an active pushing device for search results according to an embodiment of the present application;

FIG. 13 is a schematic structural diagram of an electronic device corresponding to the active pushing device for search results provided in the embodiment shown in FIG. 12;

fig. 14 is a schematic structural diagram of a switching device for searching pages according to an embodiment of the present application;

fig. 15 is a schematic structural diagram of an electronic device corresponding to the switching device of the search page provided in the embodiment shown in fig. 14.

Detailed Description

For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments of the present application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.

The terminology used in the embodiments of the application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this application and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise, the "plurality" generally includes at least two, but does not exclude the case of at least one.

It should be understood that the term "and/or" as used herein is merely one relationship describing the association of the associated objects, meaning that there may be three relationships, e.g., a and/or B, may represent: a exists alone, A and B exist together, and B exists alone. In addition, the character "/" herein generally indicates that the front and rear associated objects are an "or" relationship.

The words "if", as used herein, may be interpreted as "at … …" or "at … …" or "in response to a determination" or "in response to a detection", depending on the context. Similarly, the phrase "if determined" or "if detected (stated condition or event)" may be interpreted as "when determined" or "in response to determination" or "when detected (stated condition or event)" or "in response to detection (stated condition or event), depending on the context.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a product or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such product or system. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude that an additional identical element is present in a commodity or system comprising the element.

In addition, the sequence of steps in the method embodiments described below is only an example and is not strictly limited.

Definition of terms:

heuristic search product: the recommendation set is formed by high-quality search words with better experience in industries such as knowledge, resources and data, and valuable search words and search results are distributed and recommended to users through heuristic recommendation and personalized recommendation technologies and by combining interaction technologies such as front-end smooth sliding.

In order to facilitate understanding of the technical solutions provided by the embodiments of the present application by those skilled in the art, the following briefly describes related technologies:

with the rapid development of network technology, the development of search programs for implementing search functions is becoming mature, and when a user wants to learn certain information, search keywords can be actively input into the search programs, so that the search programs can perform corresponding information search operations based on the search keywords (query), and after obtaining search results, the search results can be displayed.

The information searching process is realized based on the search keywords, however, because the search requirement of the user may be specific or abstract and not easy to express, and the search result has a strong association relationship with the search keywords, namely the dependency of the search result on the search keywords is strong, the search result realized by the search keywords cannot meet the personalized requirement of the user on the information, and the search experience of the user is further reduced.

In order to solve the above technical problems, the present embodiment provides an active pushing method of a search result, a switching method of a search page, and a device thereof, as shown in fig. 1, where an execution body of the active pushing method of a search result is an active pushing device of a search result, the active pushing device of a search result may be implemented as a server, and the server refers to a device capable of providing an active pushing service of a search result in a network virtual environment, and generally refers to a device that performs information planning and active pushing operation of a search result by using a network. In physical implementation, the server may be any device capable of providing computing services and capable of active push services for search results, such as: may be a cluster server, a conventional server, a cloud host, a virtual center, etc. The server mainly comprises a processor, a hard disk, a memory, a system bus and the like, and is similar to a general computer architecture.

The server is implemented as a cloud server, and at this time, the active pushing method of the search result may be executed in the cloud, where a plurality of computing nodes (cloud servers) may be deployed in the cloud, where each computing node has processing resources such as computation and storage. At the cloud, a service may be provided by multiple computing nodes, although one computing node may provide one or more services. The cloud may provide the service by providing a service interface to the outside, and the user invokes the service interface to use the corresponding service. The service interface includes a software development kit (Software Development Kit, abbreviated as SDK), an application program interface (Application Programming Interface, abbreviated as API), and the like.

Aiming at the scheme provided by the embodiment of the invention, the cloud can provide the service interface of the active pushing service with the search result, and the user calls the active pushing interface of the search result through the active pushing device of the search result so as to trigger a request for calling the active pushing interface of the search result to the cloud. And the cloud determines a computing node of the active pushing operation of the search result, and executes the specific processing operation of the active pushing of the search result by utilizing processing resources in the computing node.

In some examples, the active pushing device of the search result may be communicatively connected to a client, in particular, the client may be any programmable computing device having a certain information pushing and information displaying capability, and in particular, the client may be implemented as a mobile phone, a personal computer, a tablet computer, a smart wearable device, or the like. Furthermore, the basic structure of the client may include: at least one processor. The number of processors depends on the configuration and type of client. The client may also include Memory, which may be volatile, such as RAM, or nonvolatile, such as Read-Only Memory (ROM), flash Memory, etc., or both. The memory typically stores an Operating System (OS), one or more application programs, program data, and the like. In addition to the processing unit and the memory, the client comprises some basic configuration, such as a network card chip, an IO bus, a display component, and some peripheral devices. Alternatively, some peripheral devices may include, for example, a keyboard, a mouse, a stylus, a printer, and the like. Other peripheral devices are well known in the art and are not described in detail herein.

In this embodiment, the server may make a network connection with the client, which may be a wireless or wired network connection. If the client is in communication connection with the server, the network system of the mobile network may be any one of 3G (WCDMA, TD-SCDMA, CDMA2000, UTMS), 4G (LTE), 4g+ (lte+), wiMax, 5G, 6G, and the like.

The client is provided with a preset program for realizing search operation, the preset program can realize the function of information search, the preset program has an active pushing function and a passive pushing function for searching information, and the active pushing function can perform pushing operation of search results without searching keywords; the passive pushing function needs to search keywords to perform pushing operation of search results, and specifically, the active pushing function and the passive pushing function can be realized through an active pushing device for searching information.

The active pushing device for searching information is used for acquiring user portraits and user behavior information through a preset program, wherein the user portraits can comprise at least one of the following: the user behavior information may include current behavior of the user and historical behavior of the user, which may include at least one of: historical browsing behavior, historical searching behavior, historical viewing behavior, historical clicking behavior, and the like of the user; in order to enable the active pushing operation of the search information, a plurality of network search results for enabling the active pushing of the search information may be determined, and the plurality of network search results may be all search results available through the network resource.

After the user portrait, the user behavior information and the plurality of network search results are obtained, the user portrait, the user behavior information and the plurality of network search results can be analyzed and processed to determine target information for active pushing, and then when a user starts a preset program input program, the target information can be actively displayed in a preset interface in response to the program starting operation of the user on the preset program input, so that the active pushing operation of the search information is effectively realized. Because the target information is not determined by the search keywords input by the user, but is actively determined based on the user portrait, the user behavior information and a plurality of network search results, the active pushing operation of the search information is effectively realized, the target information which is actively pushed not only can meet the personalized requirements of different users, but also improves the good experience of the users on the use of the preset program, and further ensures the practicability of the method.

Some embodiments of the present invention are described in detail below with reference to the accompanying drawings. In the case where there is no conflict between the embodiments, the following embodiments and features in the embodiments may be combined with each other. In addition, the sequence of steps in the method embodiments described below is only an example and is not strictly limited.

Fig. 2 is a flow chart of an active pushing method of a search result according to an embodiment of the present application; referring to fig. 2, the present embodiment provides an active pushing method of a search result, where the execution body of the method is an active pushing device of the search result, it may be understood that the active pushing device of the search result may be implemented as software, or a combination of software and hardware, and specifically, when the active pushing device of the search result is implemented as hardware, it may be specifically various electronic devices with active pushing capabilities of the search result. When the active pushing device of the search result is implemented as software, it may be installed in the above-mentioned electronic device; specifically, the active pushing method of the search result may include:

step S201: and acquiring user portraits and user behavior information through a preset program.

Step S202: a plurality of network search results for enabling proactive pushing of search information is determined.

Step S203: target information for active pushing is determined based on the user profile, the user behavior information, and the plurality of network search results.

Step S204: and responding to program starting operation input by a user to a preset program, and actively displaying target information in a preset interface.

The specific implementation process and implementation effect of each step are described in detail below:

The active pushing device of the search result can be deployed with a preset program for realizing information search operation, or the active pushing device of the search result can be connected with a client in a communication manner, and the client can be deployed with the preset program for realizing information search operation. In order to realize the active pushing operation of the search information in the preset program, the user portrait and the user behavior information can be obtained through the preset program, wherein the user portrait can comprise at least one of the following: attribute information of the user, user preferences, lifestyle habits, user labels, etc., and the attribute information of the user may include at least one of: male/female, date of birth, industry of the user, etc.; the user behavior information may include at least one of: the current behavior information of the user and the historical behavior information of the user may include current click behavior information of the user, current browsing behavior information of the user, current search behavior information of the user, and the like, and the historical behavior information of the user may include historical click behavior information of the user, historical search behavior information of the user, historical browsing behavior information of the user, historical viewing behavior information of the user, and the like.

The specific obtaining manner of the user portrait and the user behavior information is not limited in this embodiment, in some examples, the user portrait and the user behavior information may be obtained through a user identity, and at this time, obtaining the user portrait and the user behavior information through a preset program may include: the method comprises the steps of obtaining an identity mark corresponding to a user in a preset program, wherein the identity mark can comprise name information of the user, ID information of the user and the like, and accessing a preset area or a preset database for storing user portraits and user behavior information based on the identity mark, so that the user portraits and the user behavior information can be obtained.

In other examples, the user portraits and user behavior information may be obtained based on user type, and the obtaining of the user portraits and user behavior information by a pre-set program may include: acquiring an identity corresponding to a user in a preset program, wherein the identity can comprise name information of the user, ID information of the user and the like, and determining the type of the user based on the identity corresponding to the user in the preset program; and acquiring user portrait and user behavior information through a preset program based on the user type. The user type can comprise a new user type and an old user type, when the user type is the new user type, the user at the moment is explained to use the preset program for the first time, and then the historical behavior information of the user in the user behavior information can be determined, and the user portrait can be empty, so that when the user portrait and the user behavior information are determined through the user type, the user behavior information determined through the user type only comprises the current behavior information of the user. When the user type is the old user type, the user is indicated to have used the preset program at the moment, and then the current behavior information of the user, the user portrait and the historical behavior information of the user, which are included in the user behavior information, can be determined to be non-empty.

It should be noted that, the user portrait and the user behavior information may not only be obtained through the identity identifier corresponding to the user in the preset program, and the user portrait and the user behavior information may be obtained through man-machine interaction operation, where the obtaining the user portrait and the user behavior information through the preset program may include: in response to the starting operation of the preset program, an information configuration page is displayed, the interactive operation input by the user in the information configuration page is acquired, and the user image and the user behavior information are acquired based on the interactive operation, so that the flexible acquisition operation of the user image and the user behavior information is effectively realized.

For the preset program, in order to enable the active pushing operation of the search information, a plurality of network search results for implementing the active pushing of the search information may be determined, and the plurality of network search results may include: all the search keywords and the search results corresponding to the search keywords, which can be obtained through the network resources, namely the search results included in the plurality of network search results are not limited to the search scenes corresponding to the preset program, but also include other search scenes corresponding to the network resources.

For example, the program 1, the program 2 and the program 3 capable of realizing the search function may be deployed on the client, and when the program 1 is the preset program, the obtained plurality of network search results may include not only the search result obtained by the program 1 but also the search result obtained by the program 2 and the search result obtained by the program 3, so that diversity, sufficiency, and the like of the plurality of network search results are effectively ensured.

Or, a program 1 capable of realizing the search function is deployed on the client, the client is connected with a network device in a communication manner, a program 2 and a program 3 for realizing the search function in the network device, and when the program 1 is the preset program, the obtained plurality of network search results not only comprise the search results obtained by the program 1, but also comprise the search results obtained by the program 2 and the search results obtained by the program 3, so that the diversity, the sufficiency and the like of the plurality of network search results are ensured.

In some examples, for a plurality of network search results, the plurality of network search results may be determined based on historical search results in the network, at which point the determining of the plurality of network search results to enable proactive pushing of search information in the present implementation may include: acquiring a plurality of historical search results in a network and historical query keywords corresponding to the historical search results; determining the richness, the demand satisfaction degree and the relativity between each historical search result and the historical query keywords corresponding to the plurality of historical search results; a plurality of network search results included in the plurality of historical search results is determined based on the relevance, the richness, and the demand satisfaction.

Specifically, since thousands of users can perform information search operation in a network environment (including an application scene corresponding to a preset program and an application scene corresponding to a non-preset program), a plurality of history search results and history query keywords corresponding to the history search results are generated in the network environment, and the plurality of history search results and the history query keywords corresponding to the history search results generated in the network environment can be stored in a preset area or a preset database.

In order to ensure the diversity and richness of the acquisition of the plurality of network search results, the plurality of historical search results and the historical query keywords corresponding to the historical search results in the network can be acquired, and the richness corresponding to the historical search results can be reflected through the data dimension and the data type of the historical search results, so that the accuracy and the reliability of the acquisition of the network search results can be ensured.

In addition, the demand satisfaction degree corresponding to the plurality of historical search results may be represented by feedback information corresponding to the historical search results by the user, where the feedback information may include at least one of the following: the click operation of the user on the historical search results, the time length information of browsing the historical search results by the user, the time length spent by the user on viewing the historical search results, and the like, specifically, the demand satisfaction degree corresponding to the plurality of historical search results may be positively correlated with the feedback information corresponding to the historical search results by the user, for example, when the number of the click operation of the user on the historical search results is larger, the demand satisfaction degree corresponding to the plurality of historical search results is higher; when the browsing time of the user on the historical search results is longer, the demand satisfaction degree corresponding to the historical search results is higher; when the longer the user spends viewing time on the historical search results, the higher the demand satisfaction corresponding to the plurality of historical search results.

In addition, the degree of correlation between each of the history search results and the history query keyword may be represented by the degree of text matching between the history search results and the history query keyword, the degree of intention matching between the history search results and the search intention, and in particular, the degree of correlation may be positively correlated with the degree of text matching and the degree of intention matching, for example, the higher the degree of text matching, the higher the degree of correlation between each of the history search results and the history query keyword; the higher the degree of intent match, the higher the correlation between each historical search result and the historical query keyword.

In other examples, the richness, the demand satisfaction, and the relevance between each of the historical search results and the historical query keyword may be obtained not only by the above manner, but also by a pre-trained machine learning model or a neural network model, where determining the richness, the demand satisfaction, and the relevance between each of the historical search results and the historical query keyword may include: the method comprises the steps of obtaining a pre-trained machine learning model or neural network model, inputting a plurality of obtained historical search results and corresponding historical query keywords into the machine learning model or the neural network model, and obtaining the richness, the demand satisfaction degree and the correlation degree between each historical search result and the historical query keywords corresponding to the plurality of historical search results output by the machine learning model or the neural network model, so that the stability and the reliability of determining the richness, the demand satisfaction degree and the correlation degree are effectively ensured.

After determining the richness and the demand satisfaction corresponding to the plurality of historical search results and the relatedness between each historical search result and the historical query keyword, the relatedness, the richness and the demand satisfaction can be analyzed and processed, so that a plurality of network search results included in the plurality of historical search results can be determined, and in particular, the plurality of network search results are often the historical search results with higher relatedness, richness and demand satisfaction, so that the accuracy and reliability of determining the plurality of network search results are effectively ensured.

It should be noted that the execution sequence between the step S202 and the step S201 in the present embodiment is not limited to the sequence defined by the sequence numbers, and the execution sequence between the step S202 and the step S201 may be adjusted according to a specific application scenario or application requirement, in some examples, the step S202 may be executed before the step S201, or the step S202 and the step S201 may be executed synchronously.

After the user portraits, the user behavior information and the plurality of network search results are acquired, analysis processing can be performed on the user portraits, the user behavior information and the plurality of network search results, so that target information about to be subjected to active pushing operation can be determined. In some examples, the target information may be obtained through a pre-trained machine learning model or a neural network model, at which time determining the target information for active pushing based on the user representation, the user behavior information, and the plurality of network search results may include: the method comprises the steps of obtaining a pre-trained machine learning model or neural network model for determining target information, inputting user images, user behavior information and a plurality of network search results into the machine learning model or the neural network model, and obtaining the target information which is output by the machine learning model or the neural network model and used for active pushing, so that the accuracy and the reliability of determining the target information are effectively ensured.

It is to be noted that, for the target information, in order to be able to secure the diversity of the search information, when the target information is acquired, it is necessary to make the acquired target information satisfy the following conditions: the richness of the target information is larger than or equal to a preset threshold value; specifically, after the target information is obtained, the richness of the target information can be obtained, and when the richness of the target information is greater than or equal to a preset threshold value, the target information is allowed to be displayed; when the richness of the target information is smaller than the preset threshold, the fact that the richness of the obtained target information is lower is indicated, and at the moment, in order to ensure the diversity and richness of the target information acquisition, the obtained target information can be adjusted until the target information with the richness larger than or equal to the preset threshold is obtained.

In other examples, in order to further improve the practicability of the method, after determining the target information for active pushing, the method in this embodiment may implement a classified storage operation on the target information, where the method in this embodiment may further include: acquiring a query keyword corresponding to target information; and storing the query keywords and the target information in an associated manner.

After the target information is acquired, the target information can be analyzed and processed, so that query keywords corresponding to the target information can be determined and acquired, and note that different target information can be corresponding to the same or different query keywords.

For example, when the target information includes information 1, information 2, information 3, information 4 and information 5, the information 1, information 3 and information 4 correspond to the query keyword 1, the information 2 corresponds to the query keyword 2, the information 5 corresponds to the query keyword 3, and then the accuracy of determining the target information based on the query keyword can be determined, specifically, the query keyword 1 can be associated with the information 1, the information 3 and the information 4, the query keyword 2 can be associated with the information 2, and the query keyword 3 can be associated with the information 5, thereby effectively realizing the classification storage operation of the target information based on the query keyword.

Because the determined target information corresponds to the preset program, after the target information for active pushing is determined, if a program starting operation input by a user to the preset program is obtained, the program starting operation can be a click starting operation, a voice starting operation, a face starting operation and the like, the target information can be actively displayed in a preset interface based on the program starting operation, and thus active pushing operation on the target information is effectively realized.

According to the active pushing method for the search information, the user portrait and the user behavior information are obtained through obtaining the preset program, the plurality of network search results are determined, then the target information for active pushing is determined based on the user portrait, the user behavior information and the plurality of network search results, when the user starts the program input by the preset program, the target information can be actively displayed in the preset interface based on the program starting operation, and as the target information does not need to be determined based on the search keywords input by the user, the active pushing operation for the search information is effectively achieved, the target information for active pushing not only can meet the personalized requirements of different users, but also improves the good experience of the user on the use of the preset program, further ensures the practicability of the method, and is favorable for popularization and application of markets.

FIG. 3 is a schematic diagram of a process for determining target information for active pushing based on user portraits, user behavior information, and a plurality of network search results according to an embodiment of the present application; on the basis of the above embodiment, referring to fig. 3, for target information, the target information may be obtained not only by a machine learning model or a neural network model, but also by sorting a plurality of network search results, and at this time, determining the target information for active pushing based on the user portraits, the user behavior information, and the plurality of network search results may include:

step S301: and performing coarse ranking and fine ranking processing on the plurality of network search results based on the user pictures and the user behavior information to obtain the ranked search results.

After the plurality of network search results are acquired, since the search results in the plurality of network search results may be the network search results with higher search quality or the network search results with lower search quality, in order to ensure the accuracy and reliability of target information acquisition, coarse ranking operation may be performed on the plurality of network search results based on the user picture and the user behavior information, so that coarse ranked results may be obtained.

In some examples, coarse ranking the plurality of network search results based on the user screen and the user behavior information may include: determining the search quality scores corresponding to the network search results based on the user pictures and the user behavior information; and performing coarse ranking on the plurality of network search results based on the search quality scores from high to low, so that coarse ranked results can be obtained.

In other examples, coarse ranking the plurality of network search results based on the user screen and the user behavior information may include: acquiring a coarse-ranking network model for performing coarse-ranking operation on a plurality of network search results; and inputting the user picture, the user behavior information and the plurality of network search results into the coarse-row network model to obtain coarse-row results output by the coarse-row network model.

After the coarse ranked results are obtained, fine ranked processing can be further performed on the coarse ranked results, so that ranked search results can be obtained. In some examples, the fine-ranking operation may be implemented by considering dimensions of fine-ranking parameters such as click volume, residence time, and retention time, where fine-ranking the coarse-ranking result may include: acquiring clicking quantity, stay time and stay time corresponding to the coarse-ranking results respectively; and performing fine ranking treatment on the coarse ranked results based on the click quantity, the stay time and the result stay time which are respectively corresponding to the coarse ranked results to obtain ranked search results, so that after the fine ranking operation, the ranked search results with higher click quantity, longer stay time and longer stay time can be obtained.

It will be appreciated that the fine-ranking operation may also be obtained by a pre-trained fine-ranking network model, and in this case, performing fine-ranking on the coarse-ranking result may include: acquiring a fine-ranking network model for performing fine-ranking operation on the coarse-ranking result; and inputting the coarse ranking result into the fine ranking network model to obtain a ranked search result output by the fine ranking network model.

In addition, in order to further improve accuracy and reliability of acquiring the ranked search results, before performing coarse ranking and fine ranking processing on the plurality of network search results based on the user picture and the user behavior information, the method in this embodiment may further include: recall operation is performed on the plurality of network search results to obtain recall search results, and specifically, a pre-configured recall algorithm may be obtained, where the recall algorithm may include at least one of the following: the entity inspires the recall algorithm, the recall algorithm of the popular query words, the recall algorithm (session i2 i) based on the similarity among the session items, the recall algorithm (u 2u2 i) based on the collaborative filtering of the user, the vector recall algorithm (u 2 i) and the like, and then the recall operation can be carried out on a plurality of network search results based on the recall algorithm of at least one of the above, so that the recall operation of the search results can be stably realized, and the stable reliability of the acquisition of the search results after recall is ensured.

After the recall search results are obtained, coarse ranking and fine ranking processing can be performed on the recall search results based on the user images and the user behavior information, and ordered search results are obtained, so that the accuracy and the reliability of determining the ordered search results are effectively ensured.

Step S302: and determining target information for active pushing based on the ordered search results, wherein the target information comprises search keywords and search results corresponding to the search keywords.

After the ordered search results are obtained, the ordered search results may be analyzed, and in some examples, the target information may be obtained by analyzing the ordered search results through a pre-trained machine learning model or a neural network model, so that target information for active pushing may be determined, where the target information includes a search keyword and a search result corresponding to the search keyword, and the search result corresponding to the search keyword may include a plurality of search information corresponding to the search keyword.

In other examples, the target information may be obtained not only through a pre-trained machine learning model or a neural network model, but also through active push information and extended push information, where determining the target information for active push based on the ranked search results in this embodiment may include: determining active pushing information and exploring pushing information based on the ordered search results, wherein the ordering positions of the active pushing information in the ordered search results are located before the ordering positions of the exploring pushing information in the ordered search results, and the number of the active pushing information is larger than that of the exploring pushing information; and determining target information for the active push based on the active push information and the extended push information.

Specifically, in order to ensure the flexibility and reliability of the active pushing operation of the search information, the target information may include the active pushing information and the exploring pushing information, so after the ordered search results are obtained, the ordered search results may be analyzed and processed to obtain the active pushing information and the exploring pushing information, in some examples, since the recommendation degree of the active pushing information is often higher than the recommendation degree of the exploring pushing information, the search result with the higher recommendation degree in front of the ordered search results may be determined as the active pushing information, and the search result with the lower recommendation degree in back of the ordered search results may be determined as the exploring pushing information.

In other examples, the active push information and the exploratory push information may be determined based on a first parameter defining a quantity of active push information and a second parameter defining a quantity of exploratory push information, at which point determining the active push information and the exploratory push information based on the ranked search results may include: acquiring a first parameter for limiting the number of the active push messages and a second parameter for limiting the number of the explored push messages, wherein the second parameter is smaller than the first parameter; in the ordered search results, determining active pushing information meeting the first parameter; and determining exploration pushing information meeting the second parameter in the non-initiative pushing information in the ordered search results.

The first parameter may be a preconfigured parameter for defining the amount of the active push information, and the first parameter may be stored in a preset area or a preset device, so that the first parameter for defining the amount of the active push information may be obtained by accessing the preset area or the preset device. Alternatively, the first parameter may be obtained through a human-computer interaction interface, and at this time, obtaining the first parameter for defining the amount of the active push information may include: displaying a parameter configuration page, and acquiring configuration operation input by a user in the parameter configuration page to acquire a first parameter. Similarly, for the second parameter, the second parameter for limiting the amount of exploration push information may be acquired in a similar manner as the first parameter.

It should be noted that, in order to ensure that the pushed target information may meet the requirement of the user as much as possible, the obtained second parameter may be smaller than the first parameter, for example: the first parameter may be 8 and the second parameter may be 2; alternatively, the first parameter may be 9, the second parameter may be 1, and so on. After the first parameter and the second parameter are acquired, determining active pushing information meeting the first parameter in the ordered search result; similarly, among the inactive push information in the ranked search results, the exploratory push information satisfying the second parameter may be determined.

For example, when the first parameter is 5 and the second parameter is 1, the ordered search results may sequentially include search result 1, search result 2, search result 3, search result 4, search result 5, search result 6, search result 7, search result 8, search result 9, and search result 10, and since the first parameter is 5, the search result with the order of the top 5 bits in the ordered search results may be determined as the active push information; and determining inactive push information in the sorted search results, wherein the inactive push information can comprise a search result 6, a search result 7, a search result 8, a search result 9 and a search result 10, and then 1 piece of exploration push information can be determined in the inactive push information, and specifically, the exploration push information can be any one of the inactive push information, so that stable acquisition of the active push information and the exploration push information is effectively realized.

After the active push information and the extended push information are obtained, the active push information and the extended push information may be analyzed, so that target information for active push may be determined, and in some examples, determining, based on the active push information and the extended push information, the target information for active push may include: and acquiring an information mixed arrangement algorithm, and sequencing the active push information and the extended push information by using the information mixed arrangement algorithm, so that the target information can be acquired. Or, the active push information and the extended push information can be randomly ordered to obtain the target information.

In this embodiment, coarse ranking and fine ranking are performed on a plurality of network search results based on user images and user behavior information, so as to obtain a ranked search result, and then target information for active pushing is determined based on the ranked search result, so that accuracy and reliability in determining the target information are effectively ensured, and stability in active pushing of the target information is improved.

FIG. 4 is a second schematic flow chart for determining target information for active pushing based on user portraits, user behavior information and a plurality of network search results according to an embodiment of the present application; on the basis of the above embodiment, referring to fig. 4, the present embodiment may determine the technical solution of the target information in combination with the scenario information, and at this time, determining, based on the user portrait, the user behavior information, and the multiple network search results, the target information for active pushing may include:

step S401: and acquiring the corresponding scene information when the user uses the preset program.

Since the target information to be displayed in different scenes is often different, for example, when a user works, the user often wants to view knowledge, information, news, or the like related to the work content; at rest, users often want to view information or news related to entertainment content, etc. In order to ensure the flexibility and reliability of acquiring the target information, the scenario information corresponding to the user using the preset program may be acquired, in some examples, the scenario information may be determined by the operation time corresponding to the user using the preset program, and at this time, acquiring the current scenario information corresponding to the user using the preset program may include: acquiring time information corresponding to a user using a preset program; scene information is determined based on the user portrayal and the time information.

Specifically, a time timer is configured in the preset program, when the user uses the preset program, the time information corresponding to the user using the preset program can be acquired through the time timer, and after the time information is acquired, the user portrait and the time information can be analyzed and processed, so that the scene information can be acquired. In some examples, the mapping relation between the time information, the user portrait and the scene type is obtained, the user portrait and the time information are analyzed and processed based on the mapping relation to obtain the scene information, for example, when the time information is 9 am to 5 pm and the user portrait is an engineer, the scene information can be determined to be a working scene; when the time information is from 6 pm to 9 am and the user portrait is an engineer, the scene information can be determined to be a leisure scene; when the time information is 9 am to 5 pm and the user portrait is a train maintainer or an airplane maintainer, the scene information at the moment can be determined to be a leisure scene, when the time information is 6 pm to 9 am and the user portrait is a train maintainer or an airplane maintainer, the scene information can be determined to be a working scene, and the like, so that the accuracy and the reliability of determining the scene information are effectively realized.

It should be noted that, the context information may be determined not only by a preset mapping relationship, but also by a pre-trained context model, and at this time, determining the context information based on the user portrait and the time information may include: acquiring a scene model for determining scene information; and inputting the user portrait and the time information into the scene model to obtain the scene information output in the scene model.

Step S402: target information for active pushing is determined based on the context information, the user portraits, the user behavior information, and the plurality of network search results.

Because different scene information can correspond to different types of target information with different preferences, after the scene information is acquired, analysis processing can be carried out on the scene information, the user portrait, the user behavior information and a plurality of network search results, so that the target information for active pushing can be determined; the determination manner of the target information in this embodiment may be similar to the specific implementation manner and implementation effect of step S203 in the above embodiment, and specific reference may be made to the above statement, which is not repeated here.

In the embodiment, the target information for active pushing is determined based on the scene information, the user portrait, the user behavior information and a plurality of network search results by acquiring the scene information corresponding to the preset program used by the user, so that different target information can be determined by combining different scene information, the flexible reliability of determining the target information is further ensured, and the practicability of the method is further improved.

FIG. 5 is a flowchart of another method for actively pushing search results according to an embodiment of the present application; on the basis of any one of the foregoing embodiments, referring to fig. 5, an operation of switching a displayed search result page may also be implemented in this embodiment, where the method in this embodiment may further include:

step S501: and displaying a preset page, wherein the preset page comprises search results corresponding to the search keywords and associated search words.

When a user uses a preset program, a preset page can be displayed in the preset program, the preset page can be a program head page, a program homepage or a search page of the preset program, the preset page can comprise search results corresponding to search keywords and associated search words, it is to be noted that the associated search words can comprise other search words with association relations among the search keywords displayed in the preset page, and the number of the associated search words can be one or more. Specifically, when the preset page is displayed, the search result corresponding to the search keyword may be displayed in the middle of the preset page, and the associated search word may be displayed at the bottom of the preset page.

Step S502: and responding to the switching operation input by the user aiming at the preset page or the associated search word, and displaying the associated search result and the associated search word corresponding to the switching operation in the preset page.

After the preset page is displayed, when the information displayed in the preset page does not meet the requirement of the user, the user may perform a switching operation on the information displayed in the preset page, in some examples, referring to fig. 6, when the information displayed in the preset page does not meet the requirement of the user, the user may input a switching operation for the preset page, where the switching operation may be a sliding operation or a double-click operation, a triple-click operation, or the like, to obtain a switched page, and an associated search result and an associated search word corresponding to the switching operation may be displayed in the switched page, thereby effectively implementing the page switching operation.

In other examples, referring to fig. 7, when the information displayed in the preset page does not meet the requirement of the user, the user may input a switching operation for the associated search word displayed in the preset page, so that the current search word displayed in the preset page may be switched to obtain the associated search word, and the associated search result corresponding to the associated search word may be displayed in the preset page, thereby effectively implementing the search word switching operation.

In the embodiment, by displaying the preset page, in response to the switching operation of the user for the preset page or the input of the related search word, the related search result and the related search word corresponding to the switching operation are displayed in the preset page, and when the information displayed in the preset page does not meet the user requirement, the information displayed in the preset page can be subjected to the switching operation through the switching operation, so that the display requirements of different pages corresponding to different users are met, and the flexibility and reliability of the method are further improved.

FIG. 8 is a flowchart of another method for actively pushing search results according to an embodiment of the present application; on the basis of any one of the above embodiments, referring to fig. 8, the present embodiment may further implement active man-machine interaction, where the method in this embodiment may further include:

step S801: and displaying a preset page, wherein the preset page comprises at least one operation control.

When a user uses a preset program, a preset page can be displayed in the preset program, the preset page can be a program front page, a program homepage or a search page of the preset program, the preset page can comprise at least one operation control for realizing man-machine interaction operation, and the at least one operation control can comprise at least one of the following: the system comprises a collection control for realizing collection operation, a comment control for realizing comment operation and a sharing control for realizing information sharing operation; the at least one operation control can be displayed in a preset page in a floating window mode, a floating mode or a magnetic attraction mode.

Step S802: and responding to the interactive operation input by the user for any operation control in the preset page, and executing the data processing operation corresponding to the operation control.

After displaying the preset page, the user can perform interactive operation with any operation control input in the preset page according to requirements, for example: the interaction operation with the collection control, the interaction operation with the comment control, the interaction operation with the sharing control and the like can be performed, after the interaction operation input by the user for any operation control is acquired, the data processing operation corresponding to the operation control can be performed based on the interaction operation, for example: when the user clicks the collection control, search and collection operation can be performed on the network search results displayed in the preset page; when a user clicks the sharing control, sharing operation can be performed on the network search results displayed in the preset page; when the user clicks the comment control, comment operation can be performed on the network search result displayed in the preset page.

Note that, in this embodiment, the comment operation performed on the web search result displayed in the preset page may include: displaying a comment interaction interface for inputting comment content; acquiring content input operation input by a user aiming at a comment interaction interface; acquiring comment content input by a user based on content input operation; compliance examination is carried out on the comment content, and specifically, the validity and compliance examination operation can be carried out on the comment content by using an examination algorithm; after the comment content passes through the compliance review operation, the comment content can be posted; and after the comment content does not pass the compliance review operation, the comment content is forbidden to be published, so that the validity and the compliance of the published data on the network are effectively ensured.

In the embodiment, by displaying the preset page, the data processing operation corresponding to the operation control is executed in response to the interactive operation input by the user for any operation control in the preset page, so that the man-machine interactive operation is effectively realized, different application requirements of different users can be met, and the use flexibility and reliability of the method are further improved.

In a specific application, referring to fig. 9 to fig. 10, the embodiment of the application provides a personalized recommendation system, which may recommend a good quality search result page of interest to a user through a heuristic search recommendation technique and an interaction method for switching a search recommendation scene through a sliding gesture, and specifically, the personalized recommendation system may include:

the offline & quality unit is used for acquiring a plurality of historical search results and historical query keywords corresponding to the historical search results in the network, determining the richness and the demand satisfaction corresponding to the historical search results and the relatedness between the historical search results and the historical query keywords, and determining a plurality of network search results from the historical search results based on the relatedness, the demand satisfaction and the richness, wherein the network search results are high-quality search results in the historical search results.

And the recall unit can carry out recall operation on the plurality of network search results by using the recall unit after the plurality of network search results are acquired, so as to obtain recall results, and particularly, the recall unit can carry out recall operation on the plurality of network search results by using recall algorithms such as session dimension recall, user object dimension recall, entity heuristic dimension recall, query word dimension recall and the like, thereby effectively ensuring the stability and reliability of recall operation.

A ranking unit comprising: the coarse ranking model is used for acquiring a recall result obtained through the recall unit, performing coarse ranking operation on the recall result to obtain a coarse ranking result, sending the coarse ranking result to the fine ranking model, and performing fine ranking processing on the coarse ranking result from the dimensions of the click quantity of a user on the network search result, the browsing time of the user on the network search result, the retention time of the user on the network search result and the like after the fine ranking model acquires the coarse ranking result, so that the fine ranking result can be obtained.

The fine-pitch model can be obtained through training of positive samples and negative samples, and specifically, the positive samples can comprise sample information clicked by a user, sample information with long browsing time length for the user and sample information with higher retention; the negative samples can comprise sample information which is not clicked by a user, sample information which is browsed by the user and sample information which is not subjected to retention operation, and after the positive samples and the negative samples are acquired, model training operation can be performed based on the positive samples and the negative samples to obtain a fine-pitch model for realizing fine-pitch operation.

A mixing unit comprising: the system comprises a cold start module, a search utilization module, a scene mixed arrangement module, a diversity mixed arrangement module and the like, wherein the cold start module is used for identifying whether a user using a search program is a new user, and when the user is determined to be the new user, the preset program does not comprise user portraits and user behavior information corresponding to the user, namely, the obtained user portraits and user behavior information can be blank information, the active recommendation operation of the search information can be performed by adopting a cold start mode, and particularly, the actively recommended search information can be the search information of the current hot, the knowledge information of the current hot or the news information of the current hot, and the like; when the user is determined to be an old user, then target information for active pushing may be determined based on the user profile, the current behavior of the user, and the historical behavior of the user and the plurality of network search results.

The exploration utilization module is used for determining target information, wherein the determined target information can comprise not only the active pushing information, but also the exploration pushing information, and the active pushing information can be information which is needed to be checked or is interesting to a user who wants to recommend recently or currently, and the exploration pushing information can be information which is possibly interesting to the user who explores in the future, so as to realize the active pushing operation of the search information and ensure the quality and effect of pushing. Specifically, after the post-fine-discharge result is obtained, a first parameter for limiting the number of active push information and a second parameter for limiting the number of exploratory push information may be obtained first, where the second parameter is smaller than the first parameter; and then, the active pushing information meeting the first parameter can be determined in the refined pushing result, the exploration pushing information meeting the second parameter is determined in the non-active pushing information in the ordered searching result, and the active pushing information and the exploration pushing information are randomly mixed and arranged, so that the target information required to be actively pushed can be obtained.

The scene mixed arranging module can determine target information corresponding to the scene information when determining target information to be actively pushed, specifically, when a user uses a search program, the current scene corresponding to the search program can be determined based on the time of the user using the search program, the network IP address, the user portrait and other information, and as different scenes often need to be checked for different types of information, after the current scene is acquired, the target information for the user to realize active pushing can be determined based on the current scene, the user portrait, the user behavior information and the fine arranging result. For example, when the current scenario is a working scenario, the pushed target information may mainly include relatively strict knowledge information; when the current scenario is a leisure scenario, the pushed target information may mainly include leisure information, for example: novel information, comic information, and the like.

The diversity mixed arrangement module is used for guaranteeing diversity and richness of the obtained target information, the diversity and richness of the target information can be embodied through dimensions such as types of the target information and corresponding search word queries, so that satisfaction of users on viewing the target information can be met, and specifically, the number of search word queries corresponding to the determined target information can be multiple, or search words corresponding to any two target information are completely different or not completely the same, and the like.

In addition, the interaction method for switching the search recommendation scene through the sliding gesture in the embodiment may include the following steps:

step 1: and acquiring search keywords input by a user in a search program.

Step 2: search results corresponding to the search keywords are determined, and the search words are associated.

Wherein after the search keyword is acquired, by performing analysis processing on the search keyword, an associated search word corresponding to the search keyword may be acquired, and the associated search word may include Query1, query2, query3, etc., for example, when the search keyword input by the user is "why the three bodies are so on, by analyzing the above-mentioned search keywords, it can be determined that the associated search words corresponding to the search keywords may include the following" three-in-one "," comment of three-in-one "," three-in-one novel "," deep-analysis three-in-one ", and the like.

Step 3: and displaying the obtained search results corresponding to the search keywords in a preset page of the search program, and displaying the associated search words at the bottom of the search results.

Step 4: when a user inputs a sliding operation (left sliding operation and right sliding operation) for a preset page, switching the search results displayed in the preset page, wherein the switched page comprises the switched associated search words and associated search results corresponding to the associated search words.

Specifically, the sliding operation input in the preset page is used as a trigger point to switch the recommended content in the preset page, so that the personalized requirements of users for viewing different search results can be met.

Step 5: when a user inputs a sliding operation (left sliding operation and right side operation) aiming at the associated keywords at the bottom of the preset page, switching the search results displayed in the preset page, wherein the switched page comprises the switched associated search words and associated search results corresponding to the associated search words.

The technical scheme provided by the application embodiment realizes the method of recommending the interested high-quality search result page to the user through the heuristic search recommendation technology, and compared with the traditional search technical scheme, the method can more autonomously distribute search information and content flow, for example: the user can search more valuable answers to questions, public network resources (documents, novels, videos) and the like, and the user experience can be better along with the development of a search program; in addition, with the continuous development of the search program, the browsing amount (Page View, PV for short) of the web Page search Page is greatly increased, and the income corresponding to the search program is multiplied, so that the viscosity of a user can be increased, the daily activity and the retention of the search program can be increased in an auxiliary manner, the consumption time of the user can be prolonged, the demand can be created for the user, the flow consumption can be promoted, the practicability of the method can be further improved, and the popularization and the application of the market can be facilitated.

FIG. 11 is a schematic flow chart of a method for switching search pages according to an embodiment of the present application; referring to fig. 11, this embodiment provides a method for switching a search page, where the execution body of the method is a switching device for a search page, and it can be understood that the switching device for a search page may be implemented as software, or a combination of software and hardware, and specifically, when the switching device for a search page is implemented as hardware, it may be specifically various electronic devices with switching capabilities for a search page. When the switching means of the search page is implemented as software, it may be installed in the above-described electronic device; specifically, the method for switching the search page may include:

step S1101: and obtaining a search keyword.

The device for switching the search page can provide an information search function, when a user has an information search requirement, the device for switching the search page can obtain a search keyword, and specifically, the method for obtaining the search keyword can include: displaying a search interaction page; acquiring keyword input operation input by a user in a search interactive page; and acquiring a search keyword based on the keyword input operation, wherein the search keyword is used for realizing the information search operation.

Step S1102: search results corresponding to the search keywords are determined, and the search words are associated.

After the search keyword is obtained, analysis processing may be performed on the search keyword, and a search result and an associated search word corresponding to the search keyword may be determined, where the search result and the associated search word may be obtained by performing analysis processing on the search keyword through a pre-trained machine learning model or a neural network model, and a degree of association between the obtained associated search word and the search keyword may be greater than or equal to a preset threshold.

Step S1103: and displaying the search results and the associated search words in the preset page.

After the search results and the associated search words are obtained, the search results and the associated search words can be displayed in a preset page, specifically, the preset page can be a first page, a homepage and the like in a search program, after the search results and the associated search words are obtained, the search results can be displayed in the middle of the preset page, and the associated search words can be displayed at the bottom of the preset page, so that a user can see the search results and the associated search words through the preset page.

Step S1104: and responding to the switching operation of the user input aiming at the preset page or the associated search word, and switching and displaying the search results and the associated search word displayed in the preset page.

After the search results and the associated search terms are displayed in the preset page, when the search results displayed in the preset page do not meet the requirements of the user, the user can perform switching operation on the information displayed in the preset page, in some examples, when the information displayed in the preset page does not meet the requirements of the user, the user can input switching operation for the preset page, the switching operation can be sliding operation or the like, the switched page is obtained, the associated search results and the associated search terms corresponding to the switching operation can be displayed in the switched page, and thus the switching display operation on the search results and the associated search terms displayed in the preset page is effectively realized.

In other examples, when the information displayed in the preset page does not meet the requirement of the user, the user can input a switching operation aiming at the associated search word displayed in the preset page, so that the search result displayed in the preset page can be synchronously switched along with the switched associated search word, and the switching display of the search result and the associated search word displayed in the preset page is realized.

It should be noted that the method in this embodiment may also include the method in the embodiment shown in fig. 2 to 10, and reference is made to the relevant description of the embodiment shown in fig. 2 to 10 for the part of this embodiment that is not described in detail. The implementation process and the technical effect of this technical solution are described in the embodiments shown in fig. 2 to 10, and are not described herein.

Fig. 12 is a schematic structural diagram of an active pushing device for search results according to an embodiment of the present application; referring to fig. 12, the present embodiment provides an active pushing device for a search result, where the active pushing device for a search result may perform the active pushing information for a search result shown in fig. 2, and specifically the active pushing device for a search result may include:

a first obtaining module 11, configured to obtain a user portrait and user behavior information through a preset program;

a first determining module 12, configured to determine a plurality of network search results for implementing active pushing of search information;

a first determining module 12, configured to determine target information for active pushing based on the user profile, the user behavior information, and a plurality of network search results;

the first processing module 13 is configured to actively display the target information in the preset interface in response to a program start operation input by the user to the preset program.

In some examples, when the first determining module 12 determines a plurality of network search results for implementing active pushing of search information, the first determining module 12 is configured to perform: acquiring a plurality of historical search results in a network and historical query keywords corresponding to the historical search results; determining the richness, the demand satisfaction degree and the relativity between each historical search result and the historical query keywords corresponding to the plurality of historical search results; a plurality of network search results included in the plurality of historical search results is determined based on the relevance, the richness, and the demand satisfaction.

In some examples, when the first determining module 12 determines the target information for active pushing based on the user representation, the user behavior information, and the plurality of network search results, the first determining module 12 is configured to perform: coarse ranking and fine ranking are carried out on a plurality of network search results based on the user pictures and the user behavior information, and ranked search results are obtained; and determining target information for active pushing based on the ordered search results, wherein the target information comprises search keywords and search results corresponding to the search keywords.

In some examples, when the first determining module 12 determines the target information for active pushing based on the ranked search results, the first determining module 12 is configured to perform: determining active pushing information and exploring pushing information based on the ordered search results, wherein the ordering positions of the active pushing information in the ordered search results are located before the ordering positions of the exploring pushing information in the ordered search results, and the number of the active pushing information is larger than that of the exploring pushing information; and determining target information for the active push based on the active push information and the extended push information.

In some examples, when the first determination module 12 determines active push information and explores push information based on the ranked search results, the first determination module 12 is to perform: acquiring a first parameter for limiting the number of the active push messages and a second parameter for limiting the number of the explored push messages, wherein the second parameter is smaller than the first parameter; in the ordered search results, determining active pushing information meeting the first parameter; and determining exploration pushing information meeting the second parameter in the non-initiative pushing information in the ordered search results.

In some examples, when the first determining module 12 determines the target information for active pushing based on the user representation, the user behavior information, and the plurality of network search results, the first determining module 12 is configured to perform: acquiring corresponding scene information when a user uses a preset program; target information for active pushing is determined based on the context information, the user portraits, the user behavior information, and the plurality of network search results.

In some examples, when the first determining module 12 obtains the current context information corresponding to the user using the preset program, the first determining module 12 is configured to perform: acquiring time information corresponding to a user using a preset program; scene information is determined based on the user portrayal and the time information.

In some examples, the richness of the target information is greater than or equal to a preset threshold.

In some examples, the first processing module 13 in this embodiment is configured to perform the following steps: displaying a preset page, wherein the preset page comprises search results corresponding to the search keywords and associated search words; and responding to the switching operation input by the user aiming at the preset page or the associated search word, and displaying the associated search result and the associated search word corresponding to the switching operation in the preset page.

In some examples, the first processing module 13 in this embodiment is configured to perform the following steps: displaying a preset page, wherein the preset page comprises at least one operation control; and responding to the interactive operation input by the user for any operation control in the preset page, and executing the data processing operation corresponding to the operation control.

In some examples, after determining the target information for active pushing, the first acquisition module 11 and the first processing module 13 in this embodiment are configured to perform the following steps:

a first obtaining module 11, configured to obtain a query keyword corresponding to the target information;

the first processing module 13 is configured to store the query keyword in association with the target information.

The active pushing device for search results shown in fig. 12 may perform the method of the embodiment shown in fig. 2 to 10, and for the part of this embodiment that is not described in detail, reference may be made to the related description of the embodiment shown in fig. 2 to 10. The implementation process and the technical effect of this technical solution are described in the embodiments shown in fig. 2 to 10, and are not described herein.

In one possible design, the structure of the active pushing device for search results shown in fig. 12 may be implemented as an electronic device. Referring to fig. 13, the active pushing device of the search result in this embodiment may be implemented as an electronic device, and in some examples, the active pushing device of the search result may be implemented as a handheld terminal, a tablet computer, an intelligent terminal, a vehicle-mounted display screen, or the like; specifically, the electronic device may include: a first processor 21 and a first memory 22. The first memory 22 is used for storing a program for executing the active pushing method of the search result provided in the embodiment shown in fig. 2 by the corresponding electronic device, and the first processor 21 is configured to execute the program stored in the first memory 22.

The program comprises one or more computer instructions, wherein the one or more computer instructions, when executed by the first processor 21, are capable of performing the steps of: acquiring user portraits and user behavior information through a preset program; determining a plurality of network search results for enabling active pushing of search information; determining target information for active pushing based on the user portraits, the user behavior information, and the plurality of network search results; and responding to program starting operation input by a user to a preset program, and actively displaying target information in a preset interface.

Further, the first processor 21 is further configured to perform all or part of the steps in the embodiment shown in fig. 2. The electronic device may further include a first communication interface 23 in a structure for the electronic device to communicate with other devices or a communication network.

In addition, an embodiment of the present application provides a computer storage medium, configured to store computer software instructions for an electronic device, where the computer storage medium includes a program related to an active pushing method for executing the search result in the method embodiment shown in fig. 2.

Furthermore, an embodiment of the present application provides a computer program product comprising: a computer program which, when executed by a processor of an electronic device, causes the processor to perform the active pushing method of search results in the method embodiment shown in fig. 2.

Fig. 14 is a schematic structural diagram of a switching device for searching pages according to an embodiment of the present application; referring to fig. 14, the present embodiment provides a switching device for a search page, where the switching device for a search page in the present embodiment is used to execute the above-mentioned switching method for a search page shown in fig. 11, and specifically, the switching device for a search page may include:

A second obtaining module 31, configured to obtain a search keyword;

a second determining module 32, configured to determine a search result corresponding to the search keyword and an associated search term;

the second processing module 33 is configured to display the search result and the associated search term in a preset page;

and the second processing module 34 is configured to perform a switching display on the search result and the associated search term displayed in the preset page in response to a switching operation performed by the user for the preset page or the associated search term input.

The switching device for the search page shown in fig. 14 may perform the method of the embodiment shown in fig. 11, and reference is made to the related description of the embodiment shown in fig. 11 for a part not described in detail in this embodiment. The implementation process and the technical effect of this technical solution are described in the embodiment shown in fig. 11, and are not described herein.

In one possible design, the structure of the switching device for the search page shown in fig. 14 may be implemented as an electronic device. Referring to fig. 15, the switching device of the search page in this embodiment may be implemented as an electronic device, and specifically, the electronic device may include: a second processor 41 and a second memory 42. Wherein the second memory 42 is used for storing a program for the corresponding electronic device to execute the method of switching search pages provided in the embodiment shown in fig. 11 described above, and the second processor 41 is configured for executing the program stored in the second memory 42.

The program comprises one or more computer instructions, wherein the one or more computer instructions, when executed by the second processor 41, are capable of performing the steps of: acquiring search keywords; determining search results corresponding to the search keywords and associating the search words; displaying the search result and the associated search term in a preset page; and responding to the switching operation of the user input aiming at the preset page or the associated search word, and switching and displaying the search results and the associated search word displayed in the preset page.

Further, the second processor 41 is further configured to perform all or part of the steps in the embodiment shown in fig. 11. The electronic device may further include a second communication interface 43 in the structure of the electronic device, for communicating with other devices or a communication network.

In addition, an embodiment of the present invention provides a computer storage medium storing computer software instructions for an electronic device, which includes a program for executing the method for switching search pages in the method embodiment shown in fig. 11.

Furthermore, an embodiment of the present invention provides a computer program product comprising: a computer program which, when executed by a processor of an electronic device, causes the processor to perform the method of switching search pages in the method embodiment shown in fig. 11.

It should be noted that, the user information (including but not limited to user equipment information, user personal information, etc.) and the data (including but not limited to data for analysis, stored data, presented data, etc.) related to the present application are information and data authorized by the user or fully authorized by each party, and the collection, use and processing of the related data need to comply with the related laws and regulations and standards of the related country and region, and provide corresponding operation entries for the user to select authorization or rejection.

The apparatus embodiments described above are merely illustrative, wherein elements illustrated as separate elements may or may not be physically separate, and elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present application without undue burden.

From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by adding necessary general purpose hardware platforms, or may be implemented by a combination of hardware and software. Based on such understanding, the foregoing aspects, in essence and portions contributing to the art, may be embodied in the form of a computer program product, which may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks. These computer program instructions may also be loaded onto a computer or other programmable apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory. The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.

Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement data storage by any method or technology. The data may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store data that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.

Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present application, and not for limiting the same; although the application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the application.

Claims

1. An active pushing method for searching information is characterized by comprising the following steps:

2. The method of claim 1, wherein determining a plurality of network search results for enabling proactive pushing of search information comprises:

Acquiring a plurality of historical search results in a network and historical query keywords corresponding to the historical search results;

determining the richness, the demand satisfaction degree and the relativity between each historical search result and the historical query keywords corresponding to the plurality of historical search results;

a plurality of network search results included in the plurality of historical search results is determined based on the relevance, the richness, and the demand satisfaction.

3. The method of claim 1, wherein determining target information for active pushing based on the user representation, user behavior information, and the plurality of network search results comprises:

coarse ranking and fine ranking are carried out on a plurality of network search results based on the user pictures and the user behavior information, and ranked search results are obtained;

and determining target information for active pushing based on the ordered search results, wherein the target information comprises search keywords and search results corresponding to the search keywords.

4. The method of claim 3, wherein determining target information for active pushing based on the ranked search results comprises:

Determining active push information and exploring push information based on the ordered search results, wherein the ordering positions of the active push information in the ordered search results are located before the ordering positions of the exploring push information in the ordered search results, and the number of the active push information is larger than that of the exploring push information;

and determining target information for active pushing based on the active pushing information and the extended pushing information.

5. The method of claim 4, wherein determining proactive push information and exploring push information based on the ranked search results comprises:

acquiring a first parameter used for limiting the number of the active push messages and a second parameter used for limiting the number of the explored push messages, wherein the second parameter is smaller than the first parameter;

in the ordered search results, determining active pushing information meeting the first parameter;

and determining exploration pushing information meeting the second parameter in the inactive pushing information in the ordered search results.

6. The method of claim 1, wherein determining target information for active pushing based on the user representation, user behavior information, and the plurality of network search results comprises:

Acquiring corresponding scene information when a user uses the preset program;

and determining target information for active pushing based on the context information, the user portrait, the user behavior information and a plurality of network search results.

7. The method of claim 6, wherein obtaining current context information corresponding to the user using the preset program comprises:

acquiring time information corresponding to the use of the preset program by a user;

the context information is determined based on the user representation and the time information.

8. The method according to any one of claims 1-7, further comprising:

displaying a preset page, wherein the preset page comprises search results corresponding to the search keywords and associated search words;

and responding to the switching operation input by the user aiming at the preset page or the associated search word, and displaying the associated search result and the associated search word corresponding to the switching operation in the preset page.

9. The method according to any one of claims 1-7, further comprising:

displaying a preset page, wherein the preset page comprises at least one operation control;

And responding to the interactive operation input by the user for any operation control in the preset page, and executing the data processing operation corresponding to the operation control.

10. The method according to any of claims 1-7, wherein after determining the target information for active pushing, the method further comprises:

acquiring a query keyword corresponding to the target information;

and storing the query keywords and the target information in an associated mode.

11. The switching method of the search page is characterized by comprising the following steps:

acquiring search keywords;

displaying the search result and the associated search term in a preset page;

12. An electronic device, comprising: a memory, a processor; wherein the memory is configured to store one or more computer instructions, wherein the one or more computer instructions, when executed by the processor, implement the method of any of claims 1-11.