CN116955759A

CN116955759A - Information display method, information display device, electronic device, storage medium, and program product

Info

Publication number: CN116955759A
Application number: CN202310200328.7A
Authority: CN
Inventors: 于淼; 常庆丰
Original assignee: Beijing Sogou Technology Development Co Ltd
Current assignee: Beijing Sogou Technology Development Co Ltd
Priority date: 2023-02-28
Filing date: 2023-02-28
Publication date: 2023-10-27

Abstract

The application provides an information display method, an information display device, an electronic device, a computer readable storage medium and a computer program product; the method comprises the following steps: responding to the information input operation, and displaying an input text in a first area of the man-machine interaction interface; displaying at least one associated text corresponding to the input text in a second area of the man-machine interaction interface, and displaying at least one recommended information related to the input text in a third area of the man-machine interaction interface; the associated text is a query sentence comprising the input text, the associated text is obtained by carrying out association processing on the input text, the recommendation information is used for introducing recommendation events related to the input text, and the first area, the second area and the third area are mutually separated. The application can optimize the display effect of various information in the man-machine interaction interface.

Description

Information display method, information display device, electronic device, storage medium, and program product

Technical Field

The present application relates to man-machine interaction technology, and in particular, to an information display method, apparatus, electronic device, computer readable storage medium, and computer program product.

Background

In the related art user search scene, the associated text is displayed to the user based on the text input by the user, for example, when 'Zhang three' is input in the search box, the following text 'divorce reason of Zhang three', 'statement of Zhang three' and the like are acquired and displayed, but the associated text obtained by the method still belongs to the query statement, so that the user is difficult to directly see the hot events related to the input text through the query statement, and the man-machine interaction efficiency of the user search and the viewing events is limited.

Disclosure of Invention

The embodiment of the application provides an information display method, an information display device, electronic equipment, a computer readable storage medium and a computer program product, which can optimize the display effect of various information in a human-computer interaction interface.

The technical scheme of the embodiment of the application is realized as follows:

the embodiment of the application provides an information display method, which comprises the following steps:

in response to an information input operation, displaying an input text in a first area of a human-computer interaction interface, wherein the input text is a query sentence for performing search processing;

displaying at least one associated text corresponding to the input text in a second area of the man-machine interaction interface, and displaying at least one recommended information related to the input text in a third area of the man-machine interaction interface;

The associated text is a query sentence comprising the input text, the associated text is obtained by carrying out association processing on the input text, the recommendation information is used for introducing recommendation events related to the input text, and the first area, the second area and the third area are mutually separated.

displaying at least one recommendation information related to the input text in a third area of the man-machine interaction interface;

and responding to the region size change operation aiming at the third region, obtaining a new third region subjected to the region size change, and displaying at least one piece of recommended information in the new third region.

An embodiment of the present application provides an information display apparatus including:

the first input module is used for responding to information input operation and displaying input text in a first area of the human-computer interaction interface, wherein the input text is a query sentence used for executing search processing;

The first display module is used for displaying at least one associated text corresponding to the input text in a second area of the man-machine interaction interface and displaying at least one recommended information related to the input text in a third area of the man-machine interaction interface;

the second input module is used for responding to the information input operation and displaying an input text in a first area of the human-computer interaction interface, wherein the input text is a query sentence used for executing search processing;

the second display module is used for displaying at least one piece of recommended information related to the input text in a third area of the man-machine interaction interface;

and the interaction module is used for responding to the region size change operation aiming at the third region, obtaining a new third region with the region size change, and displaying at least one piece of recommended information in the new third region.

An embodiment of the present application provides an electronic device, including:

a memory for storing computer executable instructions;

and the processor is used for realizing the information display method provided by the embodiment of the application when executing the computer executable instructions stored in the memory.

The embodiment of the application provides a computer readable storage medium, which stores computer executable instructions for causing a processor to execute the information display method provided by the embodiment of the application.

The embodiment of the application provides a computer program product, which comprises a computer program or computer executable instructions, wherein the computer program or the computer executable instructions realize the information display method provided by the embodiment of the application when being executed by a processor.

The embodiment of the application has the following beneficial effects:

the associated text corresponding to the input text and the recommendation information related to the input text are respectively displayed in two different areas based on the input text, so that two different types of information can be clearly displayed to a user in different areas, the user can select to directly view the recommendation information to view a recommendation event, and can also select to search based on the associated text, so that the user can flexibly select according to own search requirements, the reduction of man-machine interaction efficiency caused by the wrong selection is avoided, and the display effect and the man-machine interaction efficiency can be simultaneously considered.

Drawings

Fig. 1 is a schematic diagram of an application mode of an information display method according to an embodiment of the present application;

fig. 2 is a schematic structural diagram of a terminal 400 according to an embodiment of the present application;

fig. 3A is a schematic flow chart of an information display method according to an embodiment of the present application;

fig. 3B is a schematic flow chart of an information display method according to an embodiment of the present application;

fig. 3C is a schematic flow chart of an information display method according to an embodiment of the present application;

fig. 3D is a schematic flow chart of an information display method according to an embodiment of the present application;

fig. 3E is a schematic flow chart of an information display method according to an embodiment of the present application;

fig. 3F is a flowchart of an information display method according to an embodiment of the present application;

FIG. 3G is a flowchart illustrating an information display method according to an embodiment of the present application;

fig. 3H is a schematic flow chart of an information display method according to an embodiment of the present application;

fig. 3I is a schematic flow chart of an information display method according to an embodiment of the present application;

fig. 4 is a flow chart of an information display method according to an embodiment of the present application;

fig. 5A is an interface schematic diagram of an information display method according to an embodiment of the present application;

fig. 5B is an interface schematic diagram of an information display method according to an embodiment of the present application;

Fig. 5C is an interface schematic diagram of an information display method according to an embodiment of the present application;

fig. 5D is an interface schematic diagram of an information display method according to an embodiment of the present application;

fig. 5E is an interface schematic diagram of an information display method according to an embodiment of the present application;

fig. 5F is an interface schematic diagram of an information display method according to an embodiment of the present application;

fig. 6 is a logic schematic diagram of an information display method according to an embodiment of the present application.

Detailed Description

The present application will be further described in detail with reference to the accompanying drawings, for the purpose of making the objects, technical solutions and advantages of the present application more apparent, and the described embodiments should not be construed as limiting the present application, and all other embodiments obtained by those skilled in the art without making any inventive effort are within the scope of the present application.

In the following description, reference is made to "some embodiments" which describe a subset of all possible embodiments, but it is to be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments and can be combined with one another without conflict.

In the following description, the terms "first", "second", "third" and the like are merely used to distinguish similar objects and do not represent a specific ordering of the objects, it being understood that the "first", "second", "third" may be interchanged with a specific order or sequence, as permitted, to enable embodiments of the application described herein to be practiced otherwise than as illustrated or described herein.

Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of the application only and is not intended to be limiting of the application.

Before describing embodiments of the present application in further detail, the terms and terminology involved in the embodiments of the present application will be described, and the terms and terminology involved in the embodiments of the present application will be used in the following explanation.

1) Inputting text: the input text is text that the user inputs into the search box for querying, for example, entering "Zhang Sanu" in the search box, the input text "Zhang Sanu" characterizes information related to the query "Zhang Sanu".

2) Associative text: a query term that associates the input text, which is also used for the query, typically includes characters of the input text, e.g., the input text is "Zhang Sanj", the associated text may be "Zhang Sanj' divorce reason", etc.

3) Recommendation information: the recommended information is information which is released by an individual or an organization account and is displayed for users to read, can be news in text form, can also be news in multimedia form such as video, and is usually used for describing a certain recommended event, such as a recently-occurring event or an event which is most focused by a wide range of users.

The embodiment of the application provides an information display method, an information display device, electronic equipment, a computer readable storage medium and a computer program product, which can optimize the display effect and the human-computer interaction efficiency of various information in a human-computer interaction interface.

The following describes exemplary applications of the electronic device provided by the embodiments of the present application, where the electronic device provided by the embodiments of the present application may be implemented as a notebook computer, a tablet computer, a desktop computer, a set-top box, a mobile device (for example, a mobile phone, a portable music player, a personal digital assistant, a dedicated messaging device, a portable game device), a vehicle-mounted terminal, and other various types of user terminals, and may also be implemented as a server. In the following, an exemplary application when the device is implemented as a terminal or a server will be described.

Referring to fig. 1, fig. 1 is a schematic diagram of an application mode of an information display method according to an embodiment of the present application; by way of example, a server is concerned comprising: database 500, server 200, network 300, and terminal 400. The terminal 400 is connected to the server 200 through the network 300, and the network 300 may be a wide area network or a local area network, or a combination of both.

By way of example, server 200 may be a server of a search engine, the user is a user using a search engine, and database 500 is a news database. The following is a description in connection with the above examples.

The user inputs text in the first area 110 of the search page 140 through the terminal 400, displays the input text in the first area 110, displays associated text associated with the input text in the second area 120, and displays recommendation information for introducing a recommendation event associated with the input text in the third area 130. In response to a triggering operation of the user on the associated text, the terminal 400 transmits a search request carrying the associated text to the server 200, the server 200 acquires a search result corresponding to the associated text from the database based on the search request, and returns the search result to the terminal 400, and the search result corresponding to the associated text is displayed in the terminal 400. In response to a triggering operation of the user on the recommendation information, the terminal 400 sends a page skip request carrying the recommendation information to the server 200, the server 200 acquires the detail page based on the page skip request, and returns the detail page to the terminal 400, and the detail page of the recommendation information is displayed in the terminal 400.

The embodiment of the application can be realized by a block chain technology, the search result and the detail page of the embodiment of the application can be used as the detection result, the detection result is uploaded to the block chain for storage, and the reliability of the detection result is ensured by a consensus algorithm. Blockchains are novel application modes of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanisms, encryption algorithms, and the like. The Blockchain (Blockchain), which is essentially a decentralised database, is a string of data blocks that are generated by cryptographic means in association, each data block containing a batch of information of network transactions for verifying the validity of the information (anti-counterfeiting) and generating the next block. The blockchain may include a blockchain underlying platform, a platform product services layer, and an application services layer.

The embodiment of the application can be realized through a Database technology, and a Database (Database) can be taken as a place where the electronic file cabinet stores electronic files in short, so that a user can perform operations such as adding, inquiring, updating, deleting and the like on the data in the files. A "database" is a collection of data stored together in a manner that can be shared with multiple users, with as little redundancy as possible, independent of the application.

The database management system (Database Management System, DBMS) is a computer software system designed for managing databases, and generally has basic functions of storage, interception, security, backup, and the like. The database management system may classify according to the database model it supports, e.g., relational, XML (Extensible Markup Language ); or by the type of computer supported, e.g., server cluster, mobile phone; or by classification according to the query language used, such as structured query language (SQL, structured Query Language), XQuery; or by performance impact emphasis, such as maximum scale, maximum speed of operation; or other classification schemes. Regardless of the manner of classification used, some DBMSs are able to support multiple query languages across categories, for example, simultaneously.

In some embodiments, the server may be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDNs, basic cloud computing services such as big data and artificial intelligence platforms, and the like. The terminal may be, but is not limited to, a smart phone, a tablet computer, a notebook computer, a desktop computer, a smart speaker, a smart watch, a vehicle-mounted terminal, etc. The terminals and the server can be directly or indirectly connected through wired or wireless communication, and the embodiment of the application is not limited.

The embodiment of the application can also be realized by Cloud Technology, and the Cloud Technology (Cloud Technology) is based on the general terms of network Technology, information Technology, integration Technology, management platform Technology, application Technology and the like applied by a Cloud computing business mode, can form a resource pool, and is used as required, flexible and convenient. Cloud computing technology will become an important support. Background services of technical networking systems require a large amount of computing, storage resources, such as video websites, picture-like websites, and more portals. Along with the advanced development and application of the internet industry and the promotion of requirements of search services, social networks, mobile commerce, open collaboration and the like, each article possibly has a hash code identification mark, the hash code identification mark needs to be transmitted to a background system for logic processing, data of different levels can be processed separately, and various industry data needs strong system rear shield support and can be realized only through cloud computing.

Referring to fig. 2, fig. 2 is a schematic structural diagram of an electronic device provided in an embodiment of the present application, where the electronic device may be a terminal or a server, and a terminal 400 shown in fig. 2 includes: at least one processor 410, a memory 450, at least one network interface 420, and a user interface 430. The various components in terminal 400 are coupled together by a bus system 440. It is understood that the bus system 440 is used to enable connected communication between these components. The bus system 440 includes a power bus, a control bus, and a status signal bus in addition to the data bus. But for clarity of illustration the various buses are labeled in fig. 2 as bus system 440.

The processor 410 may be an integrated circuit chip having signal processing capabilities such as a general purpose processor, such as a microprocessor or any conventional processor, or the like, a digital signal processor (DSP, digital Signal Processor), or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or the like.

The user interface 430 includes one or more output devices 431, including one or more speakers and/or one or more visual displays, that enable presentation of the media content. The user interface 430 also includes one or more input devices 432, including user interface components that facilitate user input, such as a keyboard, mouse, microphone, touch screen display, camera, other input buttons and controls.

Memory 450 may be removable, non-removable, or a combination thereof. Exemplary hardware devices include solid state memory, hard drives, optical drives, and the like. Memory 450 optionally includes one or more storage devices physically remote from processor 410.

Memory 450 includes volatile memory or nonvolatile memory, and may also include both volatile and nonvolatile memory. The non-volatile memory may be read only memory (ROM, read Only Me mory) and the volatile memory may be random access memory (RAM, random Access Memor y). The memory 450 described in embodiments of the present application is intended to comprise any suitable type of memory.

In some embodiments, memory 450 is capable of storing data to support various operations, examples of which include programs, modules and data structures, or subsets or supersets thereof, as exemplified below.

An operating system 451 including system programs, e.g., framework layer, core library layer, driver layer, etc., for handling various basic system services and performing hardware-related tasks, for implementing various basic services and handling hardware-based tasks;

a network communication module 452 for accessing other electronic devices via one or more (wired or wireless) network interfaces 420, the exemplary network interface 420 comprising: bluetooth, wireless compatibility authentication (WiFi), and universal serial bus (USB, universal Serial Bus), etc.;

a presentation module 453 for enabling presentation of information (e.g., a user interface for operating peripheral devices and displaying content and information) via one or more output devices 431 (e.g., a display screen, speakers, etc.) associated with the user interface 430;

an input processing module 454 for detecting one or more user inputs or interactions from one of the one or more input devices 432 and translating the detected inputs or interactions.

In some embodiments, the information display device provided in the embodiments of the present application may be implemented in software, and fig. 2 shows the information display device 455 stored in the memory 450, which may be software in the form of a program, a plug-in, or the like, including the following software modules: the first input module 4551, the first display module 4552 and the discrimination module 4553 are logical, so that any combination or further splitting may be performed according to the functions implemented. The functions of the respective modules will be described hereinafter.

Referring to fig. 3A, fig. 3A is a flowchart of an information display method according to an embodiment of the present application, and the following description will use the terminal 400 in fig. 1 as an execution body, and the steps shown in fig. 3A are described in connection.

In step 101, in response to an information input operation, an input text is displayed in a first area of a human-computer interaction interface.

As an example, the information input operation may be a text input operation through an input method keyboard, the information input operation may also be a voice input operation, text conversion processing is performed on voice obtained through the voice input operation to obtain text corresponding to the voice, the text corresponding to the voice is displayed in a first area as input text, the input text is a query sentence for executing search processing, all information related to the input text is searched in response to a trigger operation for a search control, referring to fig. 5A, an input box 502A is displayed in a human-computer interaction interface 501A, an area occupied by the input box 502A is the first area, the input text shown in the human-computer interaction interface on the left side of fig. 5A is "Zhang san", and the input text shown in the human-computer interaction interface on the right side of fig. 5A is "zhang san", and the input text may be english, chinese, pinyin, or the like. The information display method provided by the embodiment of the application is suitable for multiple languages. For example: english and Chinese.

At step 102, at least one associated text corresponding to the input text is displayed in a second area of the human-machine interface, and at least one recommended information related to the input text is displayed in a third area of the human-machine interface.

As an example, the associated text is a query sentence including the input text, and is obtained by performing an association process on the input text, and the recommended information is used to introduce a recommended event related to the input text, with the first region, the second region, and the third region being separated from each other.

As an example, referring to fig. 5B, an input box 502B is displayed in the human-computer interaction interface 501B, an area occupied by the input box 502B is a first area, an associated text obtained based on the input text is displayed in an area below the input box, that is, a second area 505B for displaying the associated text, the associated text may also be a query sentence for performing a search process, the associated text includes characters of the input text, and the associated text is obtained by performing the associated process on the input text, for example, "three people information", "three public tracks of a letter" and the like, the associated text may be "three people information", "three public tracks of a letter" and the like, an area above a keyboard below the second area in the human-computer interaction interface 501B is a third area, for example, a floating layer 503B in the human-computer interaction interface 501B, recommended information for introducing a recommended event related to the input text is displayed in the third area, the recommended information may be news hot, the recommended information is different from the associated text by performing the associated text, the associated text is a news page is a specific search page, the news page is still triggered in response to the recommended page is still, and the news page is still triggered in response to the recommended page is still, the news page is still displayed as a specific page is triggered.

According to the embodiment of the application, the associative text corresponding to the input text and the recommendation information related to the input text are respectively displayed in two different areas based on the input text, so that two different types of information can be clearly displayed to a user in different areas, the user can select to directly check the recommendation information to check a recommendation event, and can also select to search based on the associative text, so that the user can flexibly select according to own search requirements, the reduction of man-machine interaction efficiency caused by the wrong selection is avoided, and the display effect and the man-machine interaction efficiency can be simultaneously considered. And the lawn effect and the information acquisition efficiency of the user can be improved in a regional separation mode, the lawn effect can be improved to accommodate more valuable information under the same area, and the information acquisition efficiency of the user can be improved to enable the user to acquire the desired content faster.

In some embodiments, referring to fig. 3B, the information input operation in step 101 includes a partial information input operation and a selection operation, and in response to the information input operation in step 101, an input text is displayed in a first area of the human-computer interaction interface, which may be implemented through steps 1011 to 1012 shown in fig. 3B.

In step 1011, an input character is displayed in a first area of the human-computer interaction interface in response to the partial information input operation, and at least one supplementary word corresponding to the input character is displayed in the first area based on the recommended condition corresponding to each supplementary word.

As an example, the information input operation may be an operation of directly obtaining an input text, for example, an operation of directly inputting "Zhang san", or may be a partial information input operation, that is, an operation of obtaining only a partial character, referring to fig. 5A, where the partial information input operation may be an operation of inputting only "Zhang", and the input character is the input character, and at this time, the associated text corresponding to the input character "Zhang san Li si", "Zhang Sanhan" and the like may be displayed in the second area 505A, and as an alternative of the step 1011, the input character may be displayed in the first area of the human-computer interaction interface in response to the partial information input operation, and at least one supplementary word corresponding to the input character may be displayed directly in the first area, that is, the recommended condition does not affect the display of the supplementary word, so that the response speed of the display of the supplementary word may be effectively improved.

In some embodiments, displaying at least one supplementary word corresponding to the input character in the first area in step 1011 based on the recommended condition corresponding to each supplementary word may be achieved by the following technical scheme: when the recommended index of the input text formed by the input characters and the supplementary words does not meet the recommended condition, displaying the supplementary words based on the first display mode; displaying the supplementary word based on the second display style when the recommended index of the input text formed by the input character and the supplementary word meets the recommended condition; wherein the first display style is less prominent than the second display style. According to the embodiment of the application, the supplementary words corresponding to different input texts can be distinguished and displayed based on the recommended condition corresponding to each supplementary word, so that a user is prompted to select the supplementary word meeting the recommended condition, and the man-machine interaction efficiency is improved.

As an example, referring to fig. 5A, a supplementary word 503A, for example, a supplementary word "three" and a supplementary word "text", is displayed in an input box 502A (first area) in the human-computer interaction interface 501A, and it is obvious that a heat mark (second display style) is displayed near the supplementary word "three", and the heat mark (first display style) is not displayed near the supplementary word "text", and the second display style is more prominent than the first display style, where the input text composed of the input character and the supplementary word is displayed in a split style according to whether the recommended condition is satisfied.

As an example, the recommended condition corresponding to each supplementary word includes at least one of: the recommendation index of the input text formed by the supplementary words and the input characters is not lower than the recommendation index threshold value; the matching degree of an input text formed by the supplementary words and the input characters and any candidate recommendation information is higher than a matching degree threshold, wherein the candidate recommendation information is used for introducing candidate recommendation events; the title of any candidate recommendation information comprises an input text composed of a supplementary word and an input character; the number of candidate recommendation information having a matching degree with an input text composed of a supplementary word and an input character higher than a matching degree threshold is not lower than a number threshold. The recommended index here may be a heat index (e.g., search rate, reading amount, number of people of interest, etc.). The candidate recommendation information is all the hot search news existing in real time, namely the hot search news introducing any recommendation event, the matching degree can be obtained through semantic similarity feature and text similarity feature calculation, and a calculation mode of the matching degree is described in detail later. The title of any candidate recommendation information includes input text and characterizes that at least the title of some candidate recommendation information includes input text. The greater the number of hot news associated with the input text (the degree of matching is greater than the degree of matching threshold) characterizes the greater the degree of hotness of the input text, and thus the supplementary word corresponding to the input text is displayed in the first region of the human-computer interaction interface based on the second display style. The number of candidate recommended information related to the input text (the matching degree is higher than the matching degree threshold) is not lower than the number threshold, the number of hot searches related to the input text is characterized as smaller, for example, the number threshold is 2, but the number of candidate recommended information related to the input text is 1, and then the supplementary word corresponding to the input text is displayed based on the first display style in the first area of the man-machine interaction interface.

In some embodiments, displaying at least one supplementary word corresponding to the input character in the first area in step 1011 may be achieved by: when the number of the at least one supplementary word is a plurality, displaying the plurality of supplementary words in a first order; wherein the first sequence comprises: the recommendation index of the input text composed of the input characters and the supplementary words is in the order from top to bottom. According to the embodiment of the application, the supplementary words are displayed in a sequence manner, so that a user is prompted to preferentially select the supplementary words corresponding to the input text with higher recommendation indexes, and the man-machine interaction efficiency is improved.

As an example, referring to fig. 5A, a plurality of supplementary words are displayed in an input box 502A (first area) in the human-computer interaction interface 501A, where the supplementary words may be displayed from left to right in a first order, where the first order may be an order in which a recommendation index of an input text made up of an input character and the supplementary words is from top to bottom, the higher the recommendation index of the input text is, the more front the position of the supplementary words is, where the recommendation index may be a popularity index (e.g., a search rate, a reading amount, a number of people of interest, etc.), where ranking may be performed by an index related to the number of recommended information, e.g., the number of candidate recommended information related to the input text, where the recommended information may be hot news, and thus the more the hot news related to the input text is, the higher the popularity of the input text is characterized by.

In step 1012, in response to a selection operation for any of the supplemental words, input text composed of the input character and the selected supplemental word is displayed in a first area of the human-machine interaction interface.

As an example, referring to fig. 5A, the supplementary words "three", "five", "text" and "Zhang" are displayed in the input box 502A in the human-computer interaction interface 501A, and in response to a selection operation (which may be a clicking action) for the supplementary word "three", the input text "Zhang three" composed of the input character "Zhang" and the selected supplementary word "three" is displayed in the input box 502A in the human-computer interaction interface 501A (here, the input box 502A is the first area). The embodiment of the application can improve the input efficiency of the user, thereby improving the man-machine interaction efficiency of the user.

In some embodiments, displaying at least one recommended information related to the input text in the third area of the man-machine interface in step 102 may be achieved by the following technical solutions: and when the input text formed by the input characters and the supplementary words meets the recommendation condition, displaying at least one recommendation information related to the input text in a third area of the man-machine interaction interface. According to the embodiment of the application, the display threshold of the recommended information can be set, and the utilization rate of display resources is improved.

As an example, the recommended condition corresponding to each supplementary word includes at least one of: the recommendation index of the input text formed by the supplementary words and the input characters is not lower than the recommendation index threshold value; the matching degree of an input text formed by the supplementary words and the input characters and any candidate recommendation information is higher than a matching degree threshold, wherein the candidate recommendation information is used for introducing candidate recommendation events; the title of any candidate recommendation information comprises an input text composed of a supplementary word and an input character; the number of candidate recommendation information having a matching degree with an input text composed of a supplementary word and an input character higher than a matching degree threshold is not lower than a number threshold. The recommended index here may be a heat index (e.g., search rate, reading amount, number of people of interest, etc.). The candidate recommendation information is all the hot search news existing in real time, namely the hot search news introducing any recommendation event, the matching degree can be obtained through semantic similarity feature and text similarity feature calculation, a calculation mode of the matching degree is described in detail later, and the candidate recommendation information, of the candidate recommendation information, the matching degree of which is higher than a matching degree threshold value with the input text, is used as recommendation information displayed in a third area. The title of any candidate recommendation information includes input text and characterizes that at least the title of some candidate recommendation information includes input text. The greater the number of hot search news associated with the input text (the degree of matching is higher than the degree of matching threshold), the greater the degree of hotness of the input text is characterized, and therefore the recommendation information associated with the input text (i.e., the candidate recommendation information having the degree of matching with the input text higher than the degree of matching threshold among the candidate recommendation information) is displayed in the third region of the human-computer interaction interface. The number of candidate recommendation information related to the input text (the degree of matching is higher than the degree of matching threshold) is lower than the number threshold, and the number of hot searches related to the input text is characterized as smaller, for example, the number threshold is 2, but the number of candidate recommendation information related to the input text is 1, so that the candidate recommendation information related to the input text is not displayed in the third area of the man-machine interaction interface.

In some embodiments, when the input text is displayed in the first area of the human-machine interaction interface, the method further comprises: displaying the associated input text in a first area of the human-computer interaction interface; wherein, the associated input text is a word with an association relation with the input text in the search history data. According to the embodiment of the application, more search options can be provided for the user, so that the search diversity is improved.

As an example, referring to fig. 5A, the input text "Zhang san" is displayed in the input box 502A (first area) of the human-computer interaction interface 501A, and the associated input text, such as "Liqu" or the like, is also displayed in the input box 502A (first area), the associated input text being a word having an association relationship with the input text in the whole-network search history data, and the effect of the associated input text being a query sentence.

In some embodiments, referring to fig. 3C, displaying at least one recommendation information related to the input text in the third area of the human-computer interaction interface in step 102 may be implemented through steps 1021 through 1022 shown in fig. 3C.

In step 1021, when the third area is in a state where the area is fixed, the first number of recommended information is displayed in the third area.

As an example, the display area occupied by each piece of recommended information is inversely related to the first number, the third area in the human-computer interaction interface is in a state that the area of the third area is fixed, the area representing the third area cannot be changed, the first number can be the number of pieces of recommended information, the number of pieces of recommended information can be different for different input texts, the first number is a variable value, and since the area of the third area for displaying the recommended information is fixed, the smaller the display area allocated to each piece of recommended information is, the smaller the first number is allocated to each piece of recommended information.

In step 1022, when the third area is in a state in which the area is variable, the recommended information of the adaptation number is displayed in the third area.

As an example, the number of adaptations is positively correlated with the area of the third region, and the third region in the human-computer interaction interface is in a state where the area of the third region is variable, and thus, referring to fig. 5B, it can be seen that the area of the third region 503B in fig. 5B is changed from small to large, and the number of recommended information displayed in the third region is also increased, that is, the number of adaptations is positively correlated with the area of the third region. With continued reference to fig. 5B, 4 pieces of recommended information are displayed in the third area expanded on the right side, but the number of recommended information related to the input text may be greater than 4, and when the number of adaptations is smaller than the number of recommended information related to the input text, all the recommended information related to the input text is scroll-displayed in response to the scroll-up operation in the third area. The embodiment of the application can ensure the display area of each piece of information and ensure the display effect of each piece of information.

In some embodiments, referring to fig. 3D, after step 102 is performed, steps 103 through 104 shown in fig. 3D may also be performed.

In step 103, in response to the detail viewing operation for the target recommendation information, a detail page corresponding to the target recommendation information is displayed.

As an example, referring to fig. 5D, in the developed floating layer 502D (the area occupied by the floating layer is the third area) of the man-machine interaction interface 501D, all the hot search news (recommended information) related to the input text "Zhang san" are displayed, and the hot is arranged from top to bottom in the order from top to bottom; for the first hot news (target recommendation information), a title 503D of the hot news, a distribution time, the number of people in attention, and a related video 504D are displayed, and in response to an operation of clicking the title 503D of the hot news by the user, a detail page 505D of the hot news is displayed in the man-machine interaction interface 501D. The detail page comprises a title, a text, a release account number, release time, a recommendation index and a video for introducing the target recommendation information, wherein the target recommendation information is the recommendation information triggered by the triggering operation in at least one recommendation information. With continued reference to fig. 5D, the recommendation index here may be the number of people of interest, for example 271 ten thousand people are paying attention to the recommendation information, and the title may be "four return bracelets, zhang three: the bracelets are burned, the bracelets are not mutually injured any more, the text can be 'Li four request war … …', the release account is 'Li xx', and the video for introducing the target recommendation information is the video in the detail page 2 days before release time. With continued reference to fig. 5D, in addition to displaying the target recommendation information, other candidate recommendation information 506D may be displayed in relation to the target recommendation information. The embodiment of the application can directly jump to the detail page so as to improve the information viewing efficiency.

In step 104, in response to the video page skip operation for the target recommendation information, a source page corresponding to the video in the target recommendation information is displayed.

As an example, referring to fig. 5E, all hot search news (recommended information) related to the input text "Zhang san" are shown in the expanded floating layer 502E (third area) of the man-machine interaction interface 501E, and are arranged from top to bottom in the order of heat from top to bottom; for the first hot news (target recommendation information), a title 503E, a distribution time, the number of people in attention, and related videos 504E of the hot news are displayed, and in response to a trigger operation for the video 504E being played, a video page 505E (source page) corresponding to the video 504E is displayed in the human-computer interaction interface 501E. The source page comprises a video pointed by a video page jumping operation and other videos related to target recommendation information, wherein the target recommendation information is recommendation information triggered by a triggering operation in at least one recommendation information. Referring to FIG. 5E, a video 504E pointed to by the video skip operation, as well as other videos 506E related to the target recommendation information, are displayed in the source page. The embodiment of the application can directly check the video source, thereby improving the man-machine interaction efficiency.

In some embodiments, referring to fig. 3E, displaying at least one recommendation information related to the input text in the third area of the human-computer interaction interface in step 102 may be implemented by step 1023 shown in fig. 3E.

In step 1023, when the number of at least one recommended information is a plurality, the plurality of recommended information is displayed in the third area in the second order.

As an example, referring to fig. 5B, 4 pieces of recommended information are displayed in the human-computer interaction interface, and the recommended information is arranged and displayed according to a second order, that is, the recommended information ordered earlier in the second order is also located at the front display position in the third area, where the second order includes at least one of the following: the order of the recommended indexes of the recommended information from top to bottom (the recommended indexes herein may be heat indexes such as search rate, reading amount, number of attention, etc., and the recommended indexes herein may also be indexes related to the number of recommended information such as the number of recommended information related to the input text); the number of information dimensions of the recommendation information is from top to bottom (only text data is included in some recommendation information, the number of information dimensions is 1, some recommendation information includes text data and image data, the number of information dimensions is 2, and the number of information dimensions is the type number of data formats included in the recommendation information); the order of the release times of the recommended information (here, the recommended information released earlier is displayed at a position earlier).

In some embodiments, displaying the plurality of recommended information in the third area according to the second order in step 1023 may be achieved by the following technical scheme: displaying a title, release time, recommendation indexes and videos for introducing the first recommendation information of the first recommendation information in a third area aiming at the first recommendation information which is ranked at the first position according to the second sequence in the plurality of recommendation information; and displaying the title, the release time, the recommendation index and the thumbnail of the video for introducing the second recommendation information of the second recommendation information in the third area aiming at the second recommendation information which is ranked in a non-first order in the second order in the plurality of recommendation information. According to the embodiment of the application, a plurality of recommended information can be displayed in detail and properly, so that the display efficiency is improved.

As an example, referring to fig. 5B, in the expanded floating layer 503B (the area occupied by the floating layer is the third area) of the man-machine interaction interface 501B, all the hot search news (recommended information) related to the input text "Zhang san" are displayed, and are arranged from top to bottom in the order of heat from top to bottom; for the first hot news (first recommended information), displaying the title of the hot news (Liqu return bracelet, zhang san: the bangles are burned, the bangles are not mutually hurt), the release time (before 3 hours), the recommended index (271 thousands of people pay attention) and the related videos 505B and 506B, continuing to refer to FIG. 5B, displaying all hot news (recommended information) related to the input text Zhang san in the unfolded floating layer 503B (the area occupied by the floating layer is the third area) of the human-computer interaction interface 501B, and arranging from top to bottom according to the sequence of the heat; for non-hot news (second recommended information), titles of the hot news (Zhang Wu generation of three statement of issuing, called four case withdrawal), release time (8 points yesterday), recommended index (190 ten thousand people focused) and thumbnail images of related videos are displayed.

In some embodiments, when the number of videos is plural, the displaying the title of the first recommendation information and the video for introducing the first recommendation information in the third area may be achieved by the following technical solutions: playing any one of a plurality of videos in a first subarea in a third area; the second sub-area in the third area displays thumbnails of other videos than any one video. The embodiment of the application can reasonably display the video, provide the multimedia information display function for the user under the condition of not occupying excessive display resources and computing resources, and improve the resource utilization rate.

In some embodiments, in response to a trigger operation for any one thumbnail, a thumbnail of a video currently playing in the first sub-area is displayed to the second sub-area, and a video corresponding to the triggered thumbnail is switched to the first sub-area for playing.

As an example, referring to fig. 5C, a floating layer 502C of a man-machine interaction interface 501C displays a video 503C being played and a thumbnail 504C of a video to be played, which are related to a first hot search, and in response to a triggering operation for the right thumbnail 504C, the video corresponding to the triggered thumbnail 504C is switched to a left video playing area to be played. According to the embodiment of the application, the video can be switched and played, so that a user can know the recommendation information by watching a plurality of videos under the condition that the user does not enter a detail page, and the information acquisition efficiency of the user is improved.

In some embodiments, referring to fig. 3F, displaying at least one recommendation information related to the input text in the third area of the human-computer interaction interface in step 102 may be implemented by the step 1024 shown in fig. 3F.

In step 1024, when the area of the third area is insufficient to display the entire content of one recommendation information, a title of the first recommendation information and a thumbnail of a video for introducing the first recommendation information are displayed in the third area.

As an example, when the area of the third area is insufficient to display the entire content of one recommended information, referring to fig. 5A, the third area occupied by the floating layer 504A in the human-computer interaction interface 501A is insufficient to completely display the entire content of one recommended information, and at this time, only a part of the content of the first recommended information is displayed in the third area, and with continued reference to fig. 5A, the title of the first recommended information is "four return bracelets: the bracelet is burned and no longer hurts each other and the thumbnail of the video is used to introduce the first recommendation. The first recommendation information is recommendation information which is ranked at the first position according to the second sequence; the second sequence includes at least one of: the order of recommendation indexes of the recommendation information from top to bottom; the number of information dimensions of the recommendation information is in an order from top to bottom; the order of release time of the recommended information, the second order including at least one of: the order of the recommended indexes of the recommended information from top to bottom (the recommended indexes herein may be heat indexes such as search rate, reading amount, number of attention, etc., and the recommended indexes herein may also be indexes related to the number of recommended information such as the number of recommended information related to the input text); the number of information dimensions of the recommendation information is from top to bottom (only text data is included in some recommendation information, the number of information dimensions is 1, some recommendation information includes text data and image data, the number of information dimensions is 2, and the number of information dimensions is the type number of data formats included in the recommendation information); the order of the release times of the recommended information (here, the recommended information released earlier is displayed at a position earlier).

In some embodiments, referring to fig. 3G, displaying at least one recommendation information related to the input text in the third area of the human-computer interaction interface in step 102 may be implemented by fig. 3G showing steps 1025 to 1026.

In step 1025, when the keyboard is displayed in the human-computer interaction interface, displaying at least one recommendation information related to the input text in a third area having an overlapping edge with an upper edge of the keyboard;

in step 1026, when the keyboard is not displayed in the human-machine interface, at least one recommendation information related to the input text is displayed in a third region having an overlapping edge with the lower edge of the human-machine interface.

As an example, referring to fig. 5F, when the input method keyboard 502F is displayed in the man-machine interface 501F, the floating layer 503F (the area occupied by the floating layer is the third area) is displayed above the keyboard, the lower edge of the floating layer coincides with the upper edge of the keyboard, when the keyboard page is automatically reduced or retracted, the window height needs to be re-acquired, and the window is repositioned in combination with the position of the previous window, and when the input method keyboard is not displayed in the man-machine interface 501F, the floating layer 503F falls from the previous position to the lower edge of the floating layer to coincide with the lower edge of the man-machine interface. The embodiment of the application can adaptively adjust the position of the third area, avoid the position of the third area from being in conflict with the keyboard, and improve the man-machine interaction efficiency of the user.

In some embodiments, referring to fig. 3H, after step 102 is performed, step 105 shown in fig. 3H may also be performed.

In step 105, in response to the region size change operation for the third region, the third region is subjected to a region size change process, a new third region subjected to the region size change is obtained, and at least one recommended information is displayed in the new third region.

As an example, the region size change operation herein may be a trigger operation for a control or a slide operation for a third region, such as a slide operation that triggers the third region to extend upward and a slide operation that triggers the third region to retract downward. And carrying out passive region size change processing on the second region of the human-computer interaction interface to obtain a second region with changed region size. The area of the third area can be flexibly adjusted through the embodiment of the application, so that the display resource of the human-computer interaction interface is effectively utilized, and the resource utilization rate is improved.

In some embodiments, in step 105, in response to the region size change operation for the third region, the region size change processing is performed on the third region, so as to obtain a new third region with a changed region size, which may be implemented by the following technical scheme: displaying at least one of the first control and the second control; responding to the triggering operation of the first control, stretching the third area to obtain a new stretched third area; and responding to the triggering operation of the second control, and performing contraction processing on the third area to obtain a new contracted third area.

As an example, referring to fig. 5B, the human-computer interaction interface 501B displays an input box 502B, in which the input text "Zhang san" is displayed, the input text-related hot search aggregate is presented on the floating layer 503B above the keyboard (the area occupied by the floating layer is the third area), and in response to a trigger operation for the expansion control 504B (the first control), the floating layer 503B is displayed in expansion; in response to a trigger operation by the user for a control 507B (second control) in the float layer 503B, the float layer 503B is contracted, i.e., restored to the state before unexpanded. The area of the third area can be flexibly adjusted through the embodiment of the application, so that the display resource of the human-computer interaction interface is effectively utilized, and the resource utilization rate is improved.

In some embodiments, referring to fig. 3I, steps 106 through 110 shown in fig. 3I may also be performed before step 102 is performed.

In step 106, text-like features of the input text and each candidate recommendation are obtained.

As an example, for a certain candidate recommendation information, the text similarity feature includes at least one of: inputting the respective lengths of the titles of the text and the candidate recommendation information and the term after word segmentation; the number of hits among the items after word segmentation of the input text and the candidate recommendation information title and the hit rate are equal; inputting attributes of items hit by the text and the candidate recommendation information title, such as parts of speech, whether the items are entities and the like; the word bag is adopted to represent word segmentation results of the input text and the candidate recommendation information titles; b m25 similarity of text and candidate recommendation information titles is entered.

In step 107, semantic coding processing is performed on the input text to obtain a first semantic feature of the input text, and semantic coding processing is performed on each candidate recommendation information to obtain a second semantic feature of each candidate recommendation information.

In step 108, semantically similar features of the input text and each candidate recommendation information are determined based on the first semantic features of the input text and the second semantic features of each candidate recommendation information.

As an example, input text and candidate recommendation information are semantically encoded by a pre-training model (e.g., BERT model) to obtain vector representations of the input text and candidate recommendation information, and similarity of the two is calculated to characterize semantically similar features, see equation (1) and equation (2): sim (query, doc) =1-dist (query, doc) (1);

dist(query，doc)＝||emb(query)-emb(doc)|| (2)；

wherein emb (query) is a vector representation (first semantic feature) of the input text, emb (doc) is a vector representation (second semantic feature) of the candidate recommendation information, dist (query, doc) is a distance between the vector representation of the input text and the vector representation of the candidate recommendation information, sim (query, doc) is a semantic similar feature of the input text and the candidate recommendation information.

In step 109, the text similarity feature of the input text and each candidate recommendation information, and the semantic similarity feature of the input text and each candidate recommendation information are combined into relevant features of the input text and each candidate recommendation information.

For example, for candidate recommendation information a, text similar features of the input text and the candidate recommendation information a and semantic similar features of the input text and the candidate recommendation information a are combined to form relevant features of the input text and the candidate recommendation information a, so that a discrimination result is obtained later, and similarity of text characters and similarity of semantics are considered.

In step 110, the relevant features are subjected to a discrimination mapping process to obtain the matching degree of the input text and each candidate recommendation information, and the candidate recommendation information with the matching degree exceeding the matching degree threshold value is used as the recommendation information related to the input text.

As an example, the discriminant mapping process herein is implemented based on a gradient boost decision tree (GBDT, gradient Boosting Decision Tree) model, the relevant feature is the input of the gradient boost decision tree (GBDT, gradient Boosting Decision Tree) model, and the output of the model is the matching of the input text to each candidate recommendation.

In the related art, when the recommended information is searched, the recommended information hit with the input text is usually searched in the candidate recommended information, and the text similarity and the semantic similarity can be considered through the embodiment of the application, so that the method is not limited to text matching, and more comprehensive recommended information can be provided for users.

Referring to fig. 4, fig. 4 is a flowchart of an information display method according to an embodiment of the present application, and the following description will use the terminal 400 in fig. 1 as an execution body, and the steps shown in fig. 4 will be described.

In response to the information input operation, an input text is displayed in a first area of the human-computer interaction interface, wherein the input text is a query sentence for performing a search process in step 201.

In step 202, at least one recommendation information related to the input text is displayed in a third area of the human-machine interaction interface.

In step 203, in response to the region size change operation for the third region, a new third region subjected to the region size change is obtained, and at least one of the recommended information is displayed in the new third region.

As an example, in response to an area size change operation for a third area, an area size change process is performed on the third area, a new third area subjected to the area size change is obtained, and at least one recommended information is displayed in the new third area.

In some embodiments, when the input text is displayed in step 201, step 202 may be performed, and at least one associated text corresponding to the input text may also be displayed in a second area of the human-machine interaction interface; the associated text is a query sentence comprising the input text, the input text is subjected to association processing, and the recommended information is used for introducing recommended events related to the input text, and the first area, the second area and the third area are separated from each other.

The related embodiments of the information display method shown in fig. 3A may be used as the related embodiments of the information display method shown in fig. 4, and the specific implementation of the related embodiments of step 201 to step 203 may refer to the specific implementation of the related embodiments of step 101 to step 102, which are not described herein.

According to the embodiment of the application, the display area (the third area) of the recommended information can be flexibly controlled in response to man-machine interaction operation, so that a user can more conveniently configure a search interface, balance utilization of display resources between the search area and the result display area is realized, and the resource utilization rate is improved.

In the following, an exemplary application of the embodiment of the present application in a practical application scenario will be described.

The user inputs a text in a first area of a search page through the terminal, displays the input text in the first area, displays an associated text associated with the input text in the second area, and displays recommendation information for introducing a recommendation event associated with the input text in the third area. Responding to the triggering operation of the user on the associated text, the terminal sends a search request carrying the associated text to the server, the server obtains a search result corresponding to the associated text from the database based on the search request, returns the search result to the terminal, and displays the search result corresponding to the associated text in the terminal. Responding to the triggering operation of the user for the recommendation information, the terminal sends a page jump request carrying the recommendation information to the server, the server obtains the detail page based on the page jump request, the detail page is returned to the terminal, and the detail page of the recommendation information is displayed in the terminal.

In a search scene of a user, the related technology can recommend based on the inputted words of the user, the associational words with highest click probability are predicted to be displayed according to the search data of the wide user, the associational words are not recommended specifically for the hot search list of the inputted words, the inputted words of the user can be associated with a plurality of hot search news, the hot search news headlines can not comprise the inputted words, and the method and the device for recommending the hot search news based on the inputted words can associate the inputted words with the hot search news, so that the user can be promoted to quickly know the hot news more fully.

In some embodiments, referring to fig. 5A, a human-computer interaction interface 501A displays an input box 502A, in response to an input operation of a user, displays a user input word "Zhang" in the input box 502A, and displays a supplementary word corresponding to the input word below the input word, wherein the supplementary word associated with a plurality of hot searches is marked with heat, in response to a trigger operation for a supplementary word 503A with a heat mark, the human-computer interaction interface 501A displays the input box 502A, displays a word composed of the input word and the supplementary word in the input box 502A, forms a new input word "Zhang three" after the "Zhang", displays a hot search aggregate related to the input word "Zhang three" on a floating layer 504A above a keyboard, and distinguishes the hot list floating layer module from a suggested interest point module, thereby improving a plateau effect and a user acquisition efficiency.

In some embodiments, referring to fig. 5B, a human-computer interaction interface 501B displays an input box 502B, a new input word "Zhang san" composed of an input word and a supplementary word is displayed in the input box 502B, a floating layer 503B related to the new input word "Zhang san" is displayed above a keyboard in a hot search aggregation manner, in response to a trigger operation (a user slides up the floating layer to perform expansion processing on the floating layer) for an expansion control 504B, the floating layer 503B is displayed in an expansion manner, all hot search news related to the new input word "Zhang san" is displayed in the expanded floating layer 503B, and the hot search news is arranged from top to bottom in the order of heat from top to bottom; for the first hot news, the title, the distribution time, the number of people in focus and related videos of the hot news are displayed, the related videos comprise a video 505B being played and a thumbnail 506B of the video to be played, and for the hot news, the title, the distribution time, the number of people in focus and related images are displayed. In response to a trigger operation or a slide-down operation of the control 507B in the floating layer 503B by the user, the floating layer 503B is shrunk and displayed.

In some embodiments, referring to fig. 5C, a floating layer 502C of a man-machine interaction interface 501C displays a video 503C being played and a thumbnail 504C of a video to be played, which are related to a first hot search, and in response to a triggering operation for the right thumbnail 504C, the video corresponding to the triggered thumbnail 504C is switched to a left video playing area for playing.

In some embodiments, referring to fig. 5D, all hot search news related to the new input word "Zhang san" is displayed in the expanded floating layer 502D of the man-machine interaction interface 501D, and the hot search news is arranged from top to bottom in the order of heat from top to bottom; for the first hot news, a title 503D, a distribution time, the number of people in attention, and a related video 504D of the hot news are displayed, and in response to an operation of clicking the title 503D of the hot news by the user, a detail page 505D of the hot news is displayed in the human-computer interaction interface 501D.

In some embodiments, referring to fig. 5E, all hot search news related to the new input word "Zhang san" is displayed in the expanded floating layer 502E of the man-machine interaction interface 501E, and the hot search news is arranged from top to bottom in the order of heat from top to bottom; for the first hot news, a title 503E, a distribution time, the number of people in attention, and related videos 504E of the hot news are displayed, and in response to a trigger operation for the video 504E being played, a video page 505E corresponding to the video 504E is displayed in the human-computer interaction interface 501E.

In some embodiments, referring to fig. 6, fig. 6 shows an overall flow of the information processing method provided by the embodiment of the present application, in step 601, a query sentence input by a user is received, in step 602, a supplementary word is displayed, in step 603, the query sentence and the supplementary word form a new query sentence, and a hot search is searched based on the new query sentence, in step 604, the number of the searched relevant hot searches is determined, when the number is greater than a number threshold, step 605 is executed, in step 605, a label display is performed on the supplementary word corresponding to the new query sentence, after the user inputs the query sentence (search query), a plurality of supplementary words are provided in a search frame, the query sentence and the supplementary word are combined into a new query sentence, in this way, the relevance of the new query sentence and the hot search news is calculated, in this way, when the number of the hot searches related to the new query sentence is greater than the number threshold, the server marks the supplementary word corresponding to the new query sentence, in this way, the terminal marks the supplementary word corresponding to the supplementary search sentence, in this number of the supplementary search sentence, in this step 606, and clicks the full-screen layer, and is displayed in this way, and the full-screen layer is clicked, and the user is clicked on the full-screen layer, and the relevant hot search sentence is displayed when the full-layer is clicked.

In some embodiments, the floating layer is placed at the bottom of the man-machine interface by default, referring to fig. 5F, when the input method keyboard 502F is displayed in the man-machine interface 501F, the floating layer 503F is displayed above the keyboard, when the keyboard page is automatically reduced or retracted, the window height needs to be re-acquired and repositioned in combination with the position of the previous window, and when the subsequent keyboard page pops up, the window height needs to be re-acquired and repositioned in combination with the position of the previous window. And if the left upper corner coordinate of the man-machine interaction interface is (0, 0), the black point coordinate is (0, height 1), and a floating layer with width of width is placed by taking the black point as a reference point. When the keyboard is retracted, the black dot coordinates become (0, height 2), and the floating layer with width is placed again with this dot as a reference. And vice versa.

In some embodiments, the model used to evaluate the relevance between the input word and the hot search is a gradient-lifted decision tree (GBDT, gradient Boosting Decision Tree) model, which is an integrated learning model, using a set of tree-based base models, and summing the base model results to obtain the relevance between the input word and the hot search. The embodiment of the application also uses a pre-training model BERT, pre-trains the pre-training model by using a large-scale corpus, and uses the final result or the intermediate result output by the pre-training model to serve the downstream task on the basis of the trained pre-training model.

In some embodiments, the scheme of obtaining relevant hot searches based on the input word search is as follows, an input query sentence is combined with each supplementary word to obtain a new query sentence corresponding to each supplementary word, the relevance is calculated by using the new query sentence and each hot search result, when the number of hot searches meeting the relevance requirement is greater than or equal to two, hot marks can be displayed on the supplementary word, and the relevant hot search result is used as a hot search for displaying on a subsequent floating layer. The calculation of the correlation is required to be performed based on a correlation discrimination model, wherein the correlation discrimination model is a gradient lifting decision tree model, and the process for obtaining the correlation discrimination model comprises the following steps: sample construction, feature representation, model training, model evaluation.

Firstly, introducing a sample construction stage, wherein a sample consists of < query, doc >, and the query is a new query sentence consisting of a query sentence input by a user and a supplementary word, doc is a hot search, and the sample labeling needs to consider both text relevance of the query and d oc (whether the title of doc contains the query or the main content of the query) and semantic relevance of the query and doc (the title of doc is different from the query in text but the same in meaning). The samples are randomly divided into a training set, a verification set and a test set, wherein the training set is used for training a model, the verification set is used for adjusting parameters of the model, and the test set is used for verifying the performance of the model on unknown data.

The feature representation stage is described below, and in order to satisfy the relevance of both text and semantics, features of both text matching and semantic matching need to be considered in combination. The adoption characteristics mainly comprise the following categories: the length of each of the query and d oc titles and the term after word segmentation; the number of hits and the hit rate of the entries after the query and the doc title are segmented; attributes of items hit each other by query and doc titles, such as part of speech, whether it is an entity, etc.; word bags are adopted to represent word segmentation results of query and doc titles, and bm25 similarity is calculated; semantic relevance of query and doc.

In order to achieve the associative divergence of the hot search, the semantic relevance of the query and doc needs to be calculated, and a pre-training model can be used to obtain a vector representation (embedding) of the query and doc and calculate the similarity of the two to represent the semantic similarity, see formula (3) and formula (4):

sim(query，doc)＝1-dist(query，doc) (3)；

dist(query，doc)＝||emb(query)-emb(doc)|| (4)；

wherein emb (query) is a vector representation of the query, emb (doc) is a vector representation of doc, dist (query, doc) is a distance between the vector representation of the query and the vector representation of doc, sim (query, doc) is a semantic relatedness of the query and doc.

If the vector of "Zhang San", is denoted as [0.1,0.2,0.3], and the vector of "Liqu", is denoted as [0.1,0.3,0.5], dist ("Zhang San", "Liqu") =0.224, sim ("Zhang San", "Liqu) =0.776, the correlation between" Zhang San ", and" Liqu "is strong. If the vector of "antarct" is denoted as [0.9,0.7,0.5], dist ("Zhang San", "antarct") =0.96, sim ("Zhang San", "antarct") =0.04, meaning that the correlation of "Zhang San" and "antarct" is low, new models can also be scored for semantic correlation of query and doc based on distillation of pre-trained models (e.g., bert).

In the model training stage, ACC indexes and AUC indexes are used as label values in model training, and the model can adjust parameters such as iteration number (decision tree number), tree depth, learning rate and the like according to the performance on a verification set. When the number of iterative rounds reaches the number of definition rounds or the model is continuously lifted for multiple rounds on the verification set, training can be completed. To avoid the over-fitting problem, the sampling of samples and features is increased.

The following describes the model evaluation and deployment scheme, and the model evaluation is divided into an offline evaluation and an online evaluation. The index of the model on the test data can be used as an evaluation standard for offline model evaluation, and the AUC index and the ACC index are adopted in the task, and meanwhile, manual evaluation can be performed again. And after the evaluation result reaches the online standard, online deployment can be performed and online experiments can be started. When the model is deployed, an online pre-estimation service of the gradient lifting decision tree model is required to be built, extracted features are input, a pre-estimation scoring result is output, when the pre-estimation scoring result is larger than a scoring threshold, the hot search is considered to be related to an input word, and the scoring threshold can be selected according to the performances of different thresholds on a verification set. The online evaluation can perform online experiments on the models, and evaluate the click rate after the heat mark is added to the supplementary words and the click rate of the subsequent floating layer.

The embodiment of the application has the advantages that the user input words and the hot search list are associated, so that the hot list news related to the user and the search intention is recommended, the limitation of recommending the associated words in the related technology can be broken through, more comprehensive news hotspots surrounding the input words can be quickly and deeply known, the core business index is improved from the data level, and the search quantity is improved.

It will be appreciated that in the embodiments of the present application, related data such as user information is involved, and when the embodiments of the present application are applied to specific products or technologies, user permissions or agreements need to be obtained, and the collection, use and processing of related data need to comply with relevant laws and regulations and standards of relevant countries and regions.

Continuing with the description below of an exemplary structure of the information display device 455 implemented as a software module provided by an embodiment of the present application, in some embodiments, as shown in fig. 2, the software module stored in the information display device 455 of the memory 450 may include: a first input module 4551 for displaying an input text in a first region of a human-computer interaction interface in response to an information input operation, wherein the input text is a query sentence for performing a search process; the first display module 4552 is configured to display at least one associated text corresponding to the input text in a second region of the human-computer interaction interface, and display at least one recommendation information related to the input text in a third region of the human-computer interaction interface; the associated text is a query sentence comprising the input text, the input text is subjected to association processing, and the recommended information is used for introducing recommended events related to the input text, and the first area, the second area and the third area are separated from each other.

In some embodiments, the information input operation includes a partial information input operation and a selection operation, and the first input module 4551 is further configured to display an input character in a first region of the human-computer interaction interface in response to the partial information input operation, and display at least one supplementary word corresponding to the input character in the first region based on a recommended condition corresponding to each supplementary word; in response to a selection operation for any of the supplemental words, an input text composed of the input character and the selected supplemental word is displayed in a first area of the human-machine interaction interface.

In some embodiments, the first input module 4551 is further configured to display at least one recommendation information related to the input text in a third region of the human-computer interaction interface when the recommendation index of the input text composed of the input character and the supplementary word satisfies the recommendation condition.

In some embodiments, the first input module 4551 is further configured to display a supplementary word based on the first display style when the input text formed by the input character and the supplementary word does not satisfy the recommended condition; displaying the supplementary word based on the second display style when the input text composed of the input character and the supplementary word meets the recommended condition; wherein the first display style is less prominent than the second display style.

In some embodiments, the recommended conditions for each supplemental word include at least one of: the recommendation index of the input text formed by the supplementary words and the input characters is not lower than the recommendation index threshold value; the matching degree of an input text formed by the supplementary words and the input characters and any candidate recommendation information is higher than a matching degree threshold, wherein the candidate recommendation information is used for introducing candidate recommendation events; the title of any candidate recommendation information comprises an input text composed of a supplementary word and an input character; the number of candidate recommendation information having a matching degree with an input text composed of a supplementary word and an input character higher than a matching degree threshold is not lower than a number threshold.

In some embodiments, the first input module 4551 is further configured to display the plurality of supplemental words in a first order when the number of the at least one supplemental word is a plurality; wherein the first sequence comprises: the recommendation index of the input text composed of the input characters and the supplementary words is in the order from top to bottom.

In some embodiments, when the input text is displayed in the first area of the human-machine interface, the first input module 4551 is further configured to display the associated input text in the first area of the human-machine interface; wherein, the associated input text is a word with an association relation with the input text in the search history data.

In some embodiments, the first display module 4552 is further configured to display a first number of recommended information in the third region when the third region is in a fixed-region state, where the display area occupied by each recommended information is inversely related to the first number; and displaying recommended information of the adaptation number in the third region when the third region is in a region-variable state, wherein the adaptation number is positively correlated with the area of the third region.

In some embodiments, the first display module 4552 is further configured to display, in response to a detail view operation for the target recommendation information, a detail page corresponding to the target recommendation information, where the detail page includes a title, a body, a posting account number, a posting time, a recommendation index, and a video for introducing the target recommendation information, and the target recommendation information is recommendation information triggered by a trigger operation in at least one recommendation information; and responding to the video page skip operation aiming at the target recommendation information, and displaying a source page corresponding to the video in the target recommendation information, wherein the source page comprises the video pointed by the video page skip operation and other videos related to the target recommendation information, and the target recommendation information is recommendation information triggered by a triggering operation in at least one recommendation information.

In some embodiments, the first display module 4552 is further configured to display the plurality of recommendation information in the third region in the second order when the number of the at least one recommendation information is a plurality; wherein the second sequence comprises at least one of: the order of recommendation indexes of the recommendation information from top to bottom; the number of information dimensions of the recommendation information is in an order from top to bottom; the order of the release time of the recommended information.

In some embodiments, the first display module 4552 is further configured to display, for a first recommendation information that is ranked first in the second order among the plurality of recommendation information, a title, a release time, a recommendation index, and a video for introducing the first recommendation information of the first recommendation information in the third area; and displaying the title, the release time, the recommendation index and the thumbnail of the video for introducing the second recommendation information of the second recommendation information in the third area aiming at the second recommendation information which is ranked in a non-first order in the second order in the plurality of recommendation information.

In some embodiments, when the number of videos is multiple, the first display module 4552 is further configured to play any one of the multiple videos in the first sub-region in the third region; the second sub-area in the third area displays thumbnails of other videos than any one video.

In some embodiments, the first display module 4552 is further configured to, in response to a trigger operation for any one thumbnail, display a thumbnail of a video currently playing in the first sub-area to the second sub-area, and switch a video corresponding to the triggered thumbnail to the first sub-area for playing.

In some embodiments, the first display module 4552 is further configured to display a title of the first recommendation information and a thumbnail of a video for introducing the first recommendation information in the third area when the area of the third area is insufficient to display the entire content of one recommendation information; the first recommendation information is recommendation information which is ranked at the first position according to the second sequence; the second sequence includes at least one of: the order of recommendation indexes of the recommendation information from top to bottom; the number of information dimensions of the recommendation information is in an order from top to bottom; the order of the release time of the recommended information.

In some embodiments, the first display module 4552 is further configured to display, when the keyboard is displayed in the human-computer interaction interface, at least one recommendation information related to the input text in a third region having an overlapping edge with an upper edge of the keyboard; and when the keyboard is not displayed in the human-computer interaction interface, displaying at least one piece of recommended information related to the input text in a third area with an overlapped edge with the lower edge of the human-computer interaction interface.

In some embodiments, the first display module 4552 is further configured to perform a region size change process on the third region in response to a region size change operation for the third region, obtain a new third region that has undergone a region size change, and display at least one of the recommended information in the new third region.

In some embodiments, the first display module 4552 is further configured to display at least one of the first control and the second control; responding to the triggering operation of the first control, stretching the third area to obtain a new stretched third area; and responding to the triggering operation of the second control, and performing contraction processing on the third area to obtain a new contracted third area.

In some embodiments, the apparatus further includes a discriminating module 4553, where the discriminating module 4553 is further configured to obtain text similarity characteristics of the input text and each candidate recommendation information; carrying out semantic coding processing on the input text to obtain a first semantic feature of the input text, and carrying out semantic coding processing on each candidate recommendation information to obtain a second semantic feature of each candidate recommendation information; determining semantic similar features of the input text and each candidate recommendation information based on the first semantic features of the input text and the second semantic features of each candidate recommendation information; the text similar characteristics of the input text and each candidate recommendation information and the semantic similar characteristics of the input text and each candidate recommendation information are formed into relevant characteristics of the input text and each candidate recommendation information; and carrying out discrimination mapping processing on the related features to obtain the matching degree of the input text and each candidate recommendation information, and taking the candidate recommendation information with the matching degree exceeding the matching degree threshold value as the recommendation information related to the input text.

Continuing with the description below of exemplary structures implemented as software modules of the information display device provided by embodiments of the present application, in some embodiments, the software modules stored in the information display device of the memory may include: the second input module is used for responding to keyword input operation and displaying the input keywords in a first area of the human-computer interaction interface, wherein the input text is a query sentence used for executing search processing; the second display module is used for displaying at least one piece of recommended information related to the keywords in a second area of the man-machine interaction interface, wherein the first area and the second area are mutually independent; and the interaction module is used for responding to the region size change operation aiming at the second region and displaying at least one piece of recommended information in a third region of the man-machine interaction interface, wherein the third region is obtained by responding to the change of the man-machine interaction operation on the second region.

Embodiments of the present application provide a computer program product comprising a computer program or computer-executable instructions stored in a computer-readable storage medium. The processor of the electronic device reads the computer-executable instructions from the computer-readable storage medium, and executes the computer-executable instructions, so that the electronic device performs the information display method according to the embodiment of the present application.

Embodiments of the present application provide a computer-readable storage medium storing computer-executable instructions that, when executed by a processor, cause the processor to perform an information display method provided by embodiments of the present application, for example, an information display method as shown in fig. 3A.

In some embodiments, the computer readable storage medium may be FRAM, ROM, PROM, EP ROM, EEPROM, flash memory, magnetic surface memory, optical disk, or CD-ROM; but may be a variety of devices including one or any combination of the above memories.

In some embodiments, computer-executable instructions may be written in any form of programming language, including compiled or interpreted languages, or declarative or procedural languages, in the form of programs, software modules, scripts, or code, and they may be deployed in any form, including as stand-alone programs or as modules, components, subroutines, or other units suitable for use in a computing environment.

As an example, computer-executable instructions may, but need not, correspond to files in a file system, may be stored as part of a file that holds other programs or data, such as in one or more scripts in a hypertext markup language (HTML, hyper Text Markup Language) document, in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files that store one or more modules, sub-programs, or portions of code).

As an example, computer-executable instructions may be deployed to be executed on one electronic device or on multiple electronic devices located at one site or, alternatively, on multiple electronic devices distributed across multiple sites and interconnected by a communication network.

In summary, the associative text corresponding to the input text and the recommendation information related to the input text are displayed in two different areas based on the input text, so that two different types of information can be clearly displayed to the user in different areas, the user can select to directly view the recommendation information to view the recommendation event, and can also select to search based on the associative text, so that the user can flexibly select according to own search requirements, the reduction of man-machine interaction efficiency caused by the wrong selection is avoided, and the display effect and the man-machine interaction efficiency can be simultaneously considered.

The foregoing is merely exemplary embodiments of the present application and is not intended to limit the scope of the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and scope of the present application are included in the protection scope of the present application.

Claims

1. An information display method, characterized in that the method comprises:

2. The method of claim 1, wherein the information input operation comprises a partial information input operation and a selection operation, and wherein the displaying the input text in the first area of the human-machine interaction interface in response to the information input operation comprises:

responding to the partial information input operation, displaying input characters in a first area of the man-machine interaction interface, and displaying at least one supplementary word corresponding to the input characters in the first area based on recommended conditions corresponding to each supplementary word;

And responding to the selection operation of any supplementary word, and displaying input text composed of the input characters and the selected supplementary word in a first area of the man-machine interaction interface.

3. The method of claim 2, wherein said displaying at least one of said supplementary words corresponding to said input character in said first area comprises:

displaying a plurality of the supplementary words in a first order when the number of the at least one of the supplementary words is a plurality;

wherein the first sequence comprises: and the recommendation index of the input text formed by the input characters and the supplementary words is in the order from top to bottom.

4. The method of claim 2, wherein the step of determining the position of the substrate comprises,

the displaying at least one recommendation information related to the input text in a third area of the man-machine interaction interface comprises the following steps:

when the input text formed by the input characters and the supplementary words meets the recommended condition, displaying at least one piece of recommended information related to the input text in a third area of the man-machine interaction interface;

the displaying at least one of the supplementary words corresponding to the input character in the first area based on the recommended condition corresponding to each supplementary word includes:

When the input text formed by the input characters and the supplementary words does not meet the recommended condition, displaying the supplementary words based on a first display style;

when the input text formed by the input characters and the supplementary words meets recommended conditions, displaying the supplementary words based on a second display mode;

wherein the first display style is less prominent than the second display style.

5. The method according to any one of claim 2 to 4, wherein,

the recommended condition corresponding to each supplementary word comprises at least one of the following:

the recommended index of the input text formed by the supplementary words and the input characters is not lower than a recommended index threshold;

the matching degree of the input text formed by the supplementary words and the input characters and any candidate recommendation information is higher than a matching degree threshold, wherein the candidate recommendation information is used for introducing candidate recommendation events;

the title of any candidate recommendation information comprises an input text composed of the supplementary words and the input characters;

the number of candidate recommendation information having a matching degree with an input text composed of the supplemental word and the input character higher than the matching degree threshold is not lower than a number threshold.

6. The method of claim 1, wherein displaying at least one recommendation information related to the input text in a third area of the human-machine interaction interface comprises:

displaying a first number of recommended information in the third region when the third region is in a region-fixed state, wherein the display area occupied by each recommended information is inversely related to the first number;

and displaying recommended information of an adaptation number in the third region when the third region is in a region-variable state, wherein the adaptation number is positively correlated with the area of the third region.

7. The method according to claim 1, wherein the method further comprises:

responding to a detail viewing operation aiming at target recommendation information, displaying a detail page corresponding to the target recommendation information, wherein the detail page comprises a title, a text, a release account number, release time, recommendation indexes and a video for introducing the target recommendation information, and the target recommendation information is recommendation information triggered by the triggering operation in the at least one recommendation information;

And responding to the video page skip operation aiming at the target recommendation information, and displaying a source page corresponding to the video in the target recommendation information, wherein the source page comprises the video pointed by the video page skip operation and other videos related to the target recommendation information, and the target recommendation information is the recommendation information triggered by the triggering operation in the at least one recommendation information.

8. The method of claim 1, wherein displaying at least one recommendation information related to the input text in a third area of the human-machine interaction interface comprises:

displaying a plurality of the recommended information in the third area in a second order when the number of the at least one recommended information is a plurality;

wherein the second sequence comprises at least one of: the recommendation indexes of the recommendation information are in the sequence from top to bottom; the number of information dimensions of the recommendation information is in an order from top to bottom; and the sequence of the release time of the recommendation information.

9. The method of claim 8, wherein the displaying the plurality of recommended information in the third area in the second order comprises:

Displaying a title, release time, recommendation indexes and videos for introducing the first recommendation information of the first recommendation information in the third area aiming at the first recommendation information which is ranked at the first position in the second order in the plurality of recommendation information;

and displaying the title, the release time, the recommendation index and the thumbnail of the video for introducing the second recommendation information of the second recommendation information in the third area aiming at the second recommendation information which is ranked at the non-first position in the second sequence in the plurality of recommendation information.

10. The method of claim 9, wherein when the number of videos is a plurality, the displaying the title of the first recommendation information and the video for introducing the first recommendation information in the third area comprises:

playing any one of a plurality of videos in a first subarea in the third area;

and displaying thumbnails of other videos except the arbitrary one in a second subarea in the third area.

11. The method according to claim 10, wherein the method further comprises:

and responding to the triggering operation of any one thumbnail, displaying the thumbnail of the video currently playing in the first subarea to the second subarea, and switching the video corresponding to the triggered thumbnail to the first subarea for playing.

12. The method of claim 1, wherein displaying at least one recommendation information related to the input text in a third area of the human-machine interaction interface comprises:

displaying a title of first recommendation information and a thumbnail of a video for introducing the first recommendation information in the third area when the area of the third area is insufficient to display the entire content of one of the recommendation information;

the first recommendation information is recommendation information which is ranked at the first position according to a second sequence; the second sequence includes at least one of: the recommendation indexes of the recommendation information are in the sequence from top to bottom; the number of information dimensions of the recommendation information is in an order from top to bottom; and the sequence of the release time of the recommendation information.

13. The method of claim 1, wherein displaying at least one recommendation information related to the input text in a third area of the human-machine interaction interface comprises:

when a keyboard is displayed in the man-machine interaction interface, displaying at least one piece of recommended information related to the input text in a third area with an overlapped edge with the upper edge of the keyboard;

And when the keyboard is not displayed in the man-machine interaction interface, displaying at least one piece of recommended information related to the input text in a third area with an overlapped edge with the lower edge of the man-machine interaction interface.

14. The method according to any one of claims 1 to 13, further comprising:

and responding to the region size change operation aiming at the third region, carrying out region size change processing on the third region to obtain a new third region subjected to region size change, and displaying at least one piece of recommended information in the new third region.

15. The method of claim 14, wherein said performing a region size change process on said third region in response to a region size change operation on said third region, results in a new third region that has undergone a region size change, comprises:

displaying at least one of the first control and the second control;

responding to the triggering operation of the first control, stretching the third area to obtain a new stretched third area;

and responding to the triggering operation of the second control, and performing contraction processing on the third area to obtain a new contracted third area.

16. The method according to claim 1, wherein the method further comprises:

acquiring text similar characteristics of the input text and each candidate recommendation information;

carrying out semantic coding processing on the input text to obtain first semantic features of the input text, and carrying out semantic coding processing on each candidate recommendation information to obtain second semantic features of each candidate recommendation information;

determining semantic similar features of the input text and each candidate recommendation information based on the first semantic features of the input text and the second semantic features of each candidate recommendation information;

forming relevant characteristics of the input text and each candidate recommendation information by using text similar characteristics of the input text and each candidate recommendation information and semantic similar characteristics of the input text and each candidate recommendation information;

and carrying out discrimination mapping processing on the related features to obtain the matching degree of the input text and each candidate recommendation information, and taking the candidate recommendation information with the matching degree exceeding a matching degree threshold value as recommendation information related to the input text.

17. An information display method, characterized in that the method comprises:

18. The method of claim 17, wherein the method further comprises:

displaying at least one associated text corresponding to the input text in a second area of the man-machine interaction interface;

19. An information display device, characterized in that the device comprises:

20. An information display device, characterized in that the device comprises:

21. An electronic device, the electronic device comprising:

a memory for storing computer executable instructions;

a processor for implementing the information display method of any one of claims 1 to 16 or claims 17 to 18 when executing computer executable instructions or computer programs stored in the memory.

22. A computer-readable storage medium storing computer-executable instructions or a computer program, wherein the computer-executable instructions, when executed by a processor, implement the information display method of any one of claims 1 to 16 or claims 17 to 18.

23. A computer program product comprising a computer program or computer-executable instructions which, when executed by a processor, implement the information display method of any one of claims 1 to 16 or 17 to 18.