WO2022135339A1

WO2022135339A1 - Message content input method and apparatus, and electronic device

Info

Publication number: WO2022135339A1
Application number: PCT/CN2021/139657
Authority: WO
Inventors: 赵苗苗
Original assignee: 维沃移动通信有限公司
Priority date: 2020-12-25
Filing date: 2021-12-20
Publication date: 2022-06-30
Also published as: CN112596617A

Abstract

Disclosed is an information recommendation method, which belongs to the technical field of communications. The method comprises: when a display interface of an electronic device comprises an input area, acquiring first scene information corresponding to the display interface, wherein the first scene information comprises at least one of an application program to which the display interface belongs, time information included in the display interface, and a geographical position of the electronic device; determining a first recommended word according to the first scene information, and determining a second recommended word corresponding to the first recommended word; and displaying M pieces of target recommendation information on the basis of the first recommended word and the second recommended word.

Description

Input method, device and electronic device for message content

CROSS-REFERENCE TO RELATED APPLICATIONS

This application claims priority to Chinese patent application 202011569076.8 filed on December 25, 2020, the entire contents of which are incorporated herein by reference.

technical field

The present application belongs to the field of communication technologies, and in particular relates to an input method, an apparatus and an electronic device.

Background technique

In many applications in the field of communication, the input of message content will be involved, and users will input the same or similar message content through the same application in a fixed time period and in a fixed scenario, for example, often through lunchtime The chat software inputs "go to dinner", and sends "go to the meeting room for a meeting, time xx, location xx" during the meeting time period. If the user manually enters these same or similar message content every day, the input process will be very cumbersome and the input efficiency will be Low.

In response to this phenomenon, the input engine in the related art adds shortcut phrases or common words. When inputting the content of a message, the user can select the desired input content from the shortcut phrases or common words provided by the input engine, or the user can The actual requirement is to manually add common words, and select the appropriate common words as the message content to be input when inputting the message content.

However, the input method provided by the input engine in the related art either requires the user to manually set the recommendation information, or is fixed recommendation information provided by the system, and the method of the recommendation information is not flexible enough and the accuracy is poor.

SUMMARY OF THE INVENTION

The purpose of the embodiments of the present application is to provide an information recommendation method, which can solve the problems of inflexibility and poor accuracy of content recommended based on an input engine in the related art.

In a first aspect, an embodiment of the present application provides an information recommendation method, which includes:

In the case where the display interface of the electronic device includes an input area, acquire first scene information corresponding to the display interface, where the first scene information includes the application to which the display interface belongs and the time included in the display interface at least one of information, the geographic location of the electronic device;

Determine a first recommended word according to the first scene information, and determine a second recommended word corresponding to the first recommended word;

M pieces of target recommendation information are displayed based on the first recommendation word and the second recommendation word.

In a second aspect, an embodiment of the present application provides an information recommendation device, the device comprising:

A first scene information acquisition module, configured to acquire first scene information corresponding to the display interface when the display interface of the electronic device includes an input area, where the first scene information includes the application to which the display interface belongs at least one of a program, time information contained in the display interface, and a geographic location of the electronic device;

A recommended word determination module, configured to determine a first recommended word according to the first scene information, and determine a second recommended word corresponding to the first recommended word;

A target recommendation information output module, configured to display M pieces of target recommendation information based on the first recommendation word and the second recommendation word.

In a third aspect, embodiments of the present application provide an electronic device, the electronic device includes a processor, a memory, and a program or instruction stored on the memory and executable on the processor, the program or instruction being The processor implements the steps of the method according to the first aspect when executed.

In a fourth aspect, an embodiment of the present application provides a readable storage medium, where a program or an instruction is stored on the readable storage medium, and when the program or instruction is executed by a processor, the steps of the method according to the first aspect are implemented .

In a fifth aspect, an embodiment of the present application provides a chip, the chip includes a processor and a communication interface, the communication interface is coupled to the processor, and the processor is configured to run a program or an instruction, and implement the first aspect the method described.

In the embodiment of the present application, when the display interface of the electronic device includes an input area, the first scene information corresponding to the display interface is obtained, the first recommended word is determined according to the first scene information, and the first recommended word is determined according to the first scene information. The second recommended word corresponding to the first recommended word; M pieces of target recommendation information are displayed based on the first recommended word and the second recommended word, which improves the accuracy and flexibility of information recommendation.

Description of drawings

Fig. 1a is a flowchart of the specific steps of an information recommendation method provided in Embodiment 1 of the present application;

FIG. 1b is a flowchart of the specific steps of another information recommendation method provided in Embodiment 1 of the present application;

FIG. 2 is a flowchart of the specific steps of an information recommendation method provided in Embodiment 2 of the present application;

3 is a display diagram of a second recommended word provided in Embodiment 2 of the present application;

4 is a display diagram of a first recommended word provided in Embodiment 2 of the present application;

5 is a structural diagram of an information recommendation apparatus provided in Embodiment 3 of the present application;

6 is a structural diagram of an information recommendation apparatus provided in Embodiment 4 of the present application;

7 is a structural diagram of an electronic device provided in Embodiment 5 of the present application;

FIG. 8 is a schematic diagram of a hardware structure of an electronic device according to Embodiment 5 of the present application.

Detailed ways

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the protection scope of the present application.

The terms "first", "second" and the like in the description and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It is to be understood that data so used may be interchanged under appropriate circumstances so that embodiments of the application can be practiced in sequences other than those illustrated or described herein. In addition, "and/or" in the description and claims indicates at least one of the connected objects, and the character "/" generally indicates that the associated objects are in an "or" relationship.

The voice control method and voice control apparatus provided by the embodiments of the present application will be described in detail below with reference to the accompanying drawings through specific embodiments and application scenarios thereof.

Example 1

Referring to FIG. 1a, it shows the specific steps of an information recommendation method provided in Embodiment 1 of the present application.

Step 101: In the case that the display interface of the electronic device includes an input area, obtain first scene information corresponding to the display interface.

The information recommendation method in the embodiment of the present application can be applied to electronic equipment, and the electronic equipment can be a mobile terminal, such as a mobile phone, a tablet computer, a notebook computer, a palmtop computer, a vehicle electronic device, a wearable device, an ultra-mobile personal computer (ultra-mobile personal computer) mobile personal computer (UMPC), netbook or personal digital assistant (Personal Digital Assistant, PDA), or the like, or the electronic device may also be a server, a network attached storage (NetworkAttached Storage, NAS), a personal computer (Personal Computer, PC), A non-mobile electronic device such as a television (Television, TV), a teller machine, or a self-service machine is not specifically limited in this embodiment of the present application, and a mobile terminal is used as an example for description in this embodiment of the present application.

In the embodiment of the present application, the display interface of the mobile terminal is detected in real time. If it is detected that the display interface of the mobile terminal includes an input area, it means that the user needs to recommend information, such as word recommendation, sentence recommendation, etc. At this time, the display interface is obtained. information of the first scene. For example, when it is detected that the display interface is a WeChat chat interface and includes a chat input area, first scene information corresponding to the WeChat chat interface is acquired, so as to determine target recommendation information to be recommended according to the first scene information.

The first scene information includes at least one of an application to which the display interface belongs, time information included in the display interface, and a geographic location of the electronic device.

When detecting that the display interface of the electronic device includes an input area, the electronic device can determine the application to which the display interface belongs, for example, determine whether the display interface belongs to the chat interface of chat software, the search interface of the input engine, or the search interface of shopping software Search interface, etc. For different application programs, the content frequently input by the user is also different. Therefore, in this embodiment of the present application, different target recommendation information may be determined according to different application programs to which the display interface belongs. For different time periods, users often enter different content. For example, at around 12:00 noon, users often enter "where to eat", and on Monday morning, users often enter content about meeting notices. Therefore, in this In the application embodiment, when it is determined that the display interface includes an input area, different target recommendation information can be determined for different times by determining the time information included in the display interface. In addition, in different places, the input content of the user will also be different. For example, in a company, users often need to input content related to work, and in a shopping mall, users often input content related to shopping. Therefore, the embodiment of the present application can be used in When the display interface of the electronic device includes an input area, the current location of the user is determined by determining the geographic location of the electronic device, and then different target recommendation information is determined for different locations.

Step 102: Determine a first recommended word according to the first scene information, and determine a second recommended word corresponding to the first recommended word.

The user will input some same or similar content in certain fixed time periods, or fixed scenarios, or in a specific application, for example, send "Go to XXX meeting room for a meeting, time XXX; location every Monday morning. XXX; Participant XXX, topic XXX", at around 12 noon, enter information such as "Let's go to XXX for dinner" through chat software.

In order to prevent the user from frequently inputting a large amount of repetitive content and improve the accuracy of information recommendation, the embodiment of the present application acquires the user's historical up-screen information and the historical up-screen information under the condition that the user's authorization to obtain user information is received. Corresponding second scene information, according to the obtained historical screen information and second scene information, generate the user's recommended thesaurus, the recommended thesaurus includes the preset first recommended word and the second recommended word, and the preset first recommended word and second recommended word. The first recommended word corresponds to the second scene information. Therefore, when it is detected that the display interface includes an input box, the first recommended word corresponding to the second scene information that matches the first scene information corresponding to the display interface and the first recommended word corresponding to the first recommended word can be searched in the recommended vocabulary. Second recommendation.

The first recommended word is determined according to high-frequency sentences that appear in the user's historical on-screen messages and the second scene information corresponding to the high-frequency sentences, and the high-frequency sentences that have the same or similar second scene information The same or semantically similar keywords contained in this application are in the embodiments of the present application. For example, users often send messages such as "I want to eat hot pot", "I want to eat barbecue", "I want to eat crayfish" and so on through chat software on weekend afternoons. , then "want to eat hot pot", "want to eat barbecue", and "want to eat crayfish" are high-frequency sentences in this application, and these high-frequency sentences have the same second scene information "weekend afternoon, chat software", extract The same or semantically similar keywords in these high-frequency sentences are "want to eat", then. "I want to eat" is a first recommendation word of the user corresponding to the second scene information of "weekend afternoon, chat software".

In the embodiment of the present application, high-frequency sentences generally include both the first recommendation word and the second recommendation word, and the second recommendation word is specific content or options corresponding to the first recommendation word. ” and “Crayfish” are the second recommendation words corresponding to the first recommendation word “I want to eat”.

Step 103: Display M pieces of target recommendation information based on the first recommendation word and the second recommendation word.

It can be seen from the foregoing that, in the embodiment of the present application, the first recommendation word and the second recommendation word are extracted from the high-frequency sentences of the user, and the first recommendation word and the second recommendation word alone do not constitute a complete Therefore, the first recommendation word and the second recommendation word that need to be determined are combined according to the corresponding relationship between the two to generate target recommendation information that includes both the first recommendation word and the second recommendation word.

For example, when the obtained first scene information corresponding to the user's calling operation to the input engine is "weekend afternoon, chat software", a second scene matching the first scene information is found in the preset recommended vocabulary The first recommendation word corresponding to the information is "want to eat", and the second recommendation word corresponding to the first recommendation word is "hot pot", "barbecue", "crayfish", then, the first recommendation word "want to eat" Combine "eat" with these second recommendation words to generate target recommendation information "I want to eat hot pot", "I want to eat barbecue", "I want to eat crayfish", and the generated target recommendation information is displayed in the recommendation display area for users to choose. .

To sum up, in this embodiment of the present application, when the display interface includes an input area, the first scene information corresponding to the display interface is obtained, the first recommended word is determined according to the first scene information, and the first recommended word is determined according to the first scene information. Describe the second recommendation word corresponding to the first recommendation word; M pieces of target recommendation information are displayed based on the first recommendation word and the second recommendation word, and the target recommendation information can be determined according to the scene information, which improves the determined target recommendation information. real-time and accurate.

After the target recommendation information is displayed, input may be made based on the target recommendation information. Referring to FIG. 1b, after step 103, it may further include:

Step 104 , in response to the triggering operation on the target recommendation information, generate target information according to the target recommendation information.

If the user's triggering operation on the displayed target recommendation information is received, it is determined that the target recommendation information meets the actual needs of the user, and then the target information can be generated according to the first recommendation word and the second recommendation word contained in the target recommendation information. For example, after receiving the user's trigger operation on the target recommendation information "I want to eat hot pot", the target information "I want to eat hot pot" can be directly generated, and the user's behavioral habits can be further analyzed. According to the user's behavioral habits, such as the commonly used tone Words, emoticons, etc., further optimize the target recommendation information to generate target information, such as "I really want to eat hot pot". It is also possible to obtain nearby businesses that meet the user's needs according to the user's current location, and include business information or business locations in the generated target information, for example, "I really want to eat the hot pot in Zhongmao Plaza".

Step 105, in the case of receiving the confirmation operation for the target information, input the target information.

In generating the target information, it is further judged whether the generated target information meets the user's requirements, and if a user's confirmation operation on the target information is received, the target information is used for input. For example, the generated target information is "I really want to eat hot pot in China Trade Plaza", but the user wants to go to other places, then the user can modify the generated target information, for example, to "I really want to eat Wanda Plaza's hot pot" "Hotpot", the target information is input only when the user's confirmation operation on the target information is received, so as to prevent the input target information from not meeting the user's expectations. Thus, the efficiency and accuracy of information input are improved.

It should be noted that, in the information recommendation method provided by the embodiments of the present application, the execution subject may be an information recommendation device, or a control module in the information recommendation device for executing the information recommendation method. In the embodiment of the present application, the method provided by the embodiment of the present application is described by taking the information recommending apparatus executing the information recommending method as an example.

Embodiment 2

Referring to FIG. 2 , it shows the specific steps of an information recommendation method provided in Embodiment 2 of the present application.

Step 201, according to the user's historical on-screen information and the second scene information corresponding to the historical on-screen information, generate a recommended thesaurus corresponding to the user, and the recommended thesaurus includes a preset first recommended word and a second recommended word, where the preset first recommended word corresponds to the second scene information.

In the embodiment of the present application, in the case of receiving the permission authorized by the user to obtain user information, the user's historical screen information and the second scene information corresponding to the historical screen information are obtained, and according to the obtained historical screen information screen information and second scene information, and generate a recommended word bank for the user. The recommended word bank includes preset first recommended words and second recommended words, and the preset first recommended words correspond to the second scene information . Therefore, when the user's calling operation to the input engine is received, the first recommended word corresponding to the second scene information that matches the first scene information corresponding to the calling operation, and the first recommended word corresponding to the first recommended word can be searched in the recommended word database. The corresponding second recommendation word.

In an optional embodiment of the present application, in step 201, according to the historical screen information of the user and the second scene information corresponding to the historical screen information, a recommended vocabulary corresponding to the user is generated, including: :

Step S11, determining at least two high-frequency sentences of the user according to the screen-on-screen frequency of the user's historical screen-on-screen information;

Step S12, clustering the at least two high-frequency sentences according to the second scene information corresponding to the high-frequency sentences to obtain a high-frequency sentence group;

Step S13, determining the first recommended words corresponding to the at least two high-frequency sentences according to the high-frequency sentence group and the preset similarity condition;

Step S14, extracting the second inferred word corresponding to the first recommended word in the at least two high-frequency sentences;

Step S15: Generate a recommended word database corresponding to the user according to the first recommended word and the second recommended word.

It should be clear that the embodiments of the present application are aimed at users who often need to input some same or similar content in certain fixed time periods, or in fixed scenarios, or in specific application programs, in order to improve the input The real-time and accuracy of the content recommended by the engine provides an information recommendation method. The recommended words in the embodiments of the present application are all frequently used by the user. Therefore, before determining the recommended word database of the user, it is necessary to determine the high-frequency sentences used by the user.

Specifically, according to the frequency of the user's previous screen information, find at least two historical screen information whose screen access frequency exceeds a preset frequency threshold from the user's historical screen information, and select the at least two previous screen information. The historical on-screen information whose frequency exceeds the preset frequency threshold is taken as at least two high-frequency sentences of the user. Each high-frequency sentence corresponds to a second scene information, and at least two high-frequency sentences are clustered according to the second scene information corresponding to the high-frequency sentence to obtain a high-frequency sentence group. For example, according to the user's screen-on-screen frequency in history, the user's high-frequency sentences are "go to the conference room for a meeting", "want to eat hot pot", "want to eat barbecue", "want to eat crayfish" . Among them, the second scene information corresponding to "going to the conference room for a meeting" is Monday morning, and the second scene information corresponding to "I want to eat hot pot", "I want to eat barbecue", and "I want to eat crayfish" all include weekend afternoons. Cluster these high-frequency sentences according to the second scene information corresponding to the high-frequency sentences, and obtain two high-frequency sentence groups. , "I really want to eat barbecue", "I really want to eat crayfish" belong to another high-frequency sentence group. The first recommended word is determined according to the obtained high-frequency sentence group and the preset similarity condition, and the second keyword corresponding to the first keyword in at least two high-frequency sentences is extracted. Specifically, each high-frequency sentence included in the high-frequency sentence group may be split first to obtain multiple keywords, and these multiple keywords form a keyword set corresponding to the high-frequency sentence group, and the obtained keywords are calculated respectively. The similarity between each keyword in the set, that is, the similarity between each two keywords is calculated, and the keywords whose similarity exceeds the preset similarity threshold are combined, and the combined keyword is the high-frequency sentence. The first recommended word corresponding to the group, replace the keyword with the preset similarity threshold in the keyword set with the combined keyword, that is, the first recommended word, to obtain an updated keyword set, the updated keyword set , is either the keyword of the first recommended word, or the second recommended word corresponding to the high-frequency sentence group. According to the combination of the first keyword and the second keyword in the high-frequency sentence group in the high-frequency sentence group, the obtained corresponding relationship between each first keyword and each second keyword is determined.

For example, for the high-frequency sentence group to which "go to the meeting room for a meeting", the first keyword may be "go to the meeting room", the second keyword may be "meeting", or the first keyword may be "meeting", The second keyword is "going to the conference room". Since this high-frequency sentence group contains only one high-frequency sentence, the first and second recommended words corresponding to the high-frequency sentence group are in one-to-one correspondence. For the high-frequency sentence groups to which "I want to eat hot pot", "I want to eat barbecue", and "I want to eat crayfish", the keywords whose similarity exceeds the preset threshold are "I want to eat". Therefore, "Good "Want to eat" is the first recommendation word of the high-frequency sentence group, then, in each high-frequency sentence, "hot pot", "barbecue", and "crayfish" that appear in combination with "want to eat" are the first recommendation. The second recommended word corresponding to the word.

A recommended word library corresponding to the user is generated according to the obtained first recommended word and second recommended word. In the user's recommended word database, the first recommended word corresponds to the second scene information, and the second recommended word corresponds to the first recommended word.

Step 202 , in the case that the display interface of the electronic device includes an input area, obtain first scene information corresponding to the display interface.

The first scene information includes at least one of an application to which the display interface belongs, time information included in the display interface, and a geographic location of the electronic device where the display interface is located.

For this step, reference may be made to step 101, which is not further described in this embodiment of the present application.

Step 203: Search the recommended word database for a first recommended word corresponding to the second scene information that matches the first scene information, and a second recommended word corresponding to the first recommended word.

When it is detected that the display interface includes an input area, the recommended word database can be searched for the first recommended word corresponding to the second scene information that matches the first scene information corresponding to the display interface, and the first recommended word corresponding to the first recommended word Two recommendation words.

For example, users often send messages such as "I want to eat hot pot", "I want to eat barbecue", "I want to eat crayfish" and other messages through chat software on weekend afternoons, then "I want to eat hot pot", "I want to eat barbecue", "I want "Eat crayfish" is the high-frequency sentence in this application, and these high-frequency sentences have the same second scene information "weekend afternoon, chat software", and the same or semantically similar keywords in these high-frequency sentences are extracted as "I want to eat." ",So. "I want to eat" is the user's first recommendation word corresponding to the second scene information of "weekend afternoon, chat software", and "hot pot", "barbecue", and "crayfish" are the first recommendation words. The second recommendation word corresponding to "I want to eat".

When the acquired first scene information corresponding to the display interface is "weekend afternoon, chat software", find the first recommended word corresponding to the second scene information that matches the first scene information in the preset recommended word database It is "good to eat", and the second recommendation words corresponding to the first recommendation words are "hot pot", "barbecue", and "crayfish".

Step 204, displaying M pieces of target recommendation information based on the first recommendation word and the second recommendation word.

In the embodiment of the present application, the first recommended word and the second recommended word are extracted from high-frequency sentences of the user, and the first recommended word and the second recommended word alone do not constitute a completed sentence. Therefore, The first recommended word and the second recommended word to be determined are combined according to the corresponding relationship between the two to generate target recommendation information including both the first recommended word and the second recommended word.

Combining the first recommendation word "want to eat" determined in step 203 and the second recommendation words "hot pot", "barbecue" and "crayfish" to generate target recommendation information "want to eat hot pot" and "want to eat barbecue". "I really want to eat crayfish", the generated target recommendation information is displayed in the recommendation display area for users to choose.

In an optional embodiment of the present application, the number of the second recommended words corresponding to the first recommended word is greater than 1, and the first recommended word and the second recommended word are combined in step 204. Generate target recommendation information, including:

Step S21, in at least two second recommendation words corresponding to the first recommendation word, determine a default second recommendation word;

Step S22: Combine the first recommended word and the default second recommended word to generate target recommendation information.

Specifically, when the number of second recommended words corresponding to the first recommended word is greater than 1, according to the user's historical on-screen messages within a preset period, the usage of the second recommended word, and the user's retrieval information on the search engine , browsing information, etc. to determine the weight of the second recommended word, and use the second recommended word with the largest weight value as the default second recommended word. For example, if a user viewed the recommended dishes and user reviews of hot pot a day ago, but has not browsed the relevant information about barbecue and crayfish recently, the second recommendation word "hot pot" corresponding to the first recommendation word "good to eat", Among "barbecue" and "crawfish", "hot pot" has the largest weight value, and "hot pot" is used as the default second recommendation word, and the first recommendation word "good to eat" and the default second recommendation word "hot pot" are compared. The combination generates the target recommendation information "I really want to eat hot pot".

Step 205, in response to the triggering operation on the target recommendation information, generate target information according to the target recommendation information.

In an optional embodiment of the present application, in step 205, in response to the triggering operation on the target recommendation information, target information is generated according to the first recommendation word and the second recommendation word included in the target recommendation word, including :

In response to the confirming operation for the target recommendation information, target information is generated according to the first recommendation word and the default second recommendation word.

If the user's confirmation operation on the displayed target recommendation information is received, it is determined that the target recommendation information meets the actual needs of the user, and then the target information can be generated according to the first recommendation word and the second recommendation word contained in the target recommendation information. For example, after receiving the user's confirmation operation on the target recommendation information "I want to eat hot pot", the target message "I want to eat" can be directly generated with the target information including the first recommendation word "I want to eat" and the default second recommendation word "Hotpot" "Hotpot" can also further analyze the user's behavioral habits, and further optimize the target recommendation information according to the user's behavioral habits, such as commonly used tone words, emoticons, etc., to generate target information, such as "I really want to eat hotpot". It is also possible to obtain nearby businesses that meet the user's needs according to the user's current location, and include business information or business locations in the generated target information, for example, "I really want to eat the hot pot in Zhongmao Plaza".

In an optional embodiment of the present application, in step 205, in response to the triggering operation on the target recommendation information, target information is generated according to the first recommendation word and the second recommendation word included in the target recommendation information, including :

Step S31, displaying at least two second recommendation words corresponding to the first recommendation word in the target recommendation information in response to the triggering operation on the default second recommendation word in the target recommendation information;

Step S32, determining the target second recommended word in response to the selection operation on the at least two second recommended words;

Step S33: Generate target information according to the first recommended word and the target second recommended word.

In this embodiment of the present application, if the user is not satisfied with the default second recommended word provided by the input engine, the user can perform a trigger operation on the default second recommended word, for example, click the default second recommended word, and the input engine responds to the user's response to the default second recommended word. The triggering operation of the second recommendation word is to display all the second recommendation words corresponding to the first recommendation word in the target recommendation information in the recommendation display area for the user to select. According to the user's selection operation, the target second recommended word is determined, and the target information is generated according to the first recommended word and the target second recommended word.

Referring to FIG. 3 , a presentation diagram of a second recommended word provided by an embodiment of the present application is shown. As shown in Fig. 2, suppose that when the determined first recommended word is "good to eat", according to the weight value of each second recommended word, the determined default second recommended word is "hot pot", according to the first recommended word and The default recommendation word generates target recommendation information and displays it in the recommendation display area. If the user is not satisfied with the provided default second recommended word "hot pot", the user can perform a trigger operation on the default second recommended word, for example, click the default recommended word "hot pot", the input engine will display the first recommended word in the recommendation display area Other second recommendation words corresponding to "I want to eat", such as "barbecue", "crayfish", "seafood". The display order of the second recommended words is determined according to the weight value corresponding to each second recommended word. Specifically, the weight of the second recommended word may be determined according to the user's historical on-screen messages within a preset period, the usage of the second recommended word, the user's retrieval information on the search engine, browsing information, and the like.

Optionally, in this embodiment of the present application, there may also be multiple first recommended words determined according to the first scene information. When the number of first recommended words is greater than 1, the default first recommended word is determined according to the weight value of the first recommended word. A recommended word, and target recommendation information is generated and displayed according to the default first recommended word and the second recommended word. Wherein, the weight value of the first recommendation word may be determined according to the degree of matching between the second scene information corresponding to the first recommendation word and the first scene information, the user's historical screen information, and the like. If the user is not satisfied with the displayed target recommendation information, a trigger operation can be performed on the target recommendation information containing the default first recommendation word, and the input engine responds to the user's trigger operation and displays each first recommendation word and second recommendation word in the recommendation display area. Target recommendation information generated by the combination of recommended words for users to choose.

Referring to FIG. 4 , a presentation diagram of a first recommended word provided by an embodiment of the present application is shown. Suppose it is determined that the default first recommendation word is "together", and the target recommendation information "Let's go to eat together" containing the default first recommendation word "together" is displayed in the recommendation display area. If the user is not satisfied with the displayed target recommendation information, you can click More options corresponding to the target recommendation information "Let's go to eat together", so as to view the target recommendation information generated by the combination of each first recommendation word and second recommendation word matching the first scene information.

Wherein, if the first scene information corresponds to a plurality of first recommended words, and there exists at least one first recommended word corresponding to a plurality of second recommended words, the first display order of the first recommended words is determined according to the weight value of each first recommended word , and then determine the second display order of the second recommendation word corresponding to the first recommendation word according to the weight value of each second recommendation word corresponding to the first recommendation word, and determine each first recommendation word according to the first display order and the second display order. The display order of the target recommendation information generated by the combination of the recommended word and the second recommended word.

Optionally, in this embodiment of the present application, if the user is not satisfied with the target recommendation information displayed in the display area, the user can also directly input the message content in the input box, and the input engine filters the target recommendation information according to the message content input by the user, The filtered target recommendation information is displayed in the display area, or the target information is directly generated according to the content of the message input by the user.

Step 206, in the case of receiving the confirmation operation for the target information, input the target information.

In generating the target information, it is further judged whether the generated target information meets the user's requirements, and if the user's confirmation operation on the target information is received, the target information is used for input. For example, the generated target information is "I really want to eat hot pot in China Trade Plaza", but the user wants to go to other places, then the user can modify the generated target information, for example, to "I really want to eat Wanda Plaza's hot pot" "Hotpot", the target information is input only when the user's confirmation operation for the target information is received, so as to prevent the input target information from not meeting the user's expectations.

Optionally, after step 206, the method further includes: updating the recommended vocabulary corresponding to the user according to the input target information and the first scene information.

In the application embodiment, the user's recommended word database may also be updated according to the matching situation between the input target information and the target recommended words provided by the input engine, and the first scene information corresponding to the target information. Specifically, if the user generates the target information according to the target recommendation information, the second scene information corresponding to the first recommendation word included in the target recommendation information in the recommendation word database is updated according to the first scene information.

To sum up, in this embodiment of the present application, when the display interface includes an input area, the first scene information corresponding to the display interface is obtained, the first recommended word is determined according to the first scene information, and the first recommended word is determined according to the first scene information. describe the second recommendation word corresponding to the first recommendation word; display M pieces of target recommendation information based on the first recommendation word and the second recommendation word; the target recommendation information can be determined according to the scene information, which improves the accuracy of information recommendation and real-time.

When information input is required, in response to the triggering operation on the target recommendation information, target information is generated according to the first recommendation word and the second recommendation word contained in the target recommendation information; after receiving the confirmation of the target information In the case of operation, the target information is used for input, thereby improving the efficiency and accuracy of information input.

Embodiment 3

Referring to FIG. 5 , it shows a structural diagram of an information recommendation apparatus provided in Embodiment 3 of the present application, which specifically includes:

The first scene information obtaining module 301 is configured to obtain first scene information corresponding to the display interface when the display interface of the electronic device includes an input area.

Wherein, the first scene information includes at least one item of time, location, and application program corresponding to the display interface.

The recommended word determination module 302 is configured to determine a first recommended word according to the first scene information, and determine a second recommended word corresponding to the first recommended word.

The target recommendation word output module 303 is configured to display M pieces of target recommendation information based on the first recommendation word and the second recommendation word.

The information recommendation apparatus in the embodiment of the present application may be an apparatus, or may be a component, an integrated circuit, or a chip in a terminal. The apparatus may be a mobile electronic device or a non-mobile electronic device. Exemplarily, the mobile electronic device may be a mobile phone, a tablet computer, a notebook computer, a palmtop computer, an in-vehicle electronic device, a wearable device, an ultra-mobile personal computer (UMPC), a netbook, or a personal digital assistant (Personal Digital Assistant). Assistant, PDA), etc., or, the electronic device can also be a server, a network attached storage (Network Attached Storage, NAS), a personal computer (Personal Computer, PC), a television (Television, TV), a teller machine or a self-service machine, etc. , the embodiments of the present application are not specifically limited.

The information recommendation device in the embodiment of the present application may be a device with an operating system. The operating system may be an Android (Android) operating system, an ios operating system, or other possible operating systems, which are not specifically limited in the embodiments of the present application.

The information recommendation apparatus provided in the embodiments of the present application can implement each process implemented by the apparatus in the method embodiments of FIG. 1 to FIG. 2 , and to avoid repetition, details are not repeated here.

In the embodiment of the present application, when the display interface of the electronic device includes an input area, the first scene information corresponding to the display interface is obtained, the first recommended word is determined according to the first scene information, and the first recommended word is determined according to the first scene information. Describe the second recommendation word corresponding to the first recommendation word; display M pieces of target recommendation information based on the first recommendation word and the second recommendation word, and the target recommendation information can be determined according to the scene information, which improves the real-time performance of information recommendation and accuracy.

Embodiment 4

Referring to FIG. 6 , it shows a structural diagram of an information recommendation apparatus provided in Embodiment 4 of the present application, which specifically includes:

The recommended thesaurus generating module 401 is configured to generate a recommended thesaurus corresponding to the user according to the historical on-screen information of the user and the second scene information corresponding to the historical on-screen information, and the recommended thesaurus includes pre-recommended thesaurus. The preset first recommended word and the second recommended word, the preset first recommended word corresponds to the second scene information.

Optionally, the recommended thesaurus generating module 401 includes:

High-frequency sentence determination sub-module 4011, configured to determine at least two high-frequency sentences of the user according to the screen-on-screen frequency of the user's historical screen-on-screen information;

Clustering sub-module 4012, configured to cluster the at least two high-frequency sentences according to the second scene information corresponding to the high-frequency sentences to obtain a high-frequency sentence group;

The first recommended word determination sub-module 4013 is configured to determine the first recommended words corresponding to the at least two high-frequency sentences according to the high-frequency sentence group and the preset similarity condition;

The second recommended word determination sub-module 4014 is configured to extract the second inferred word corresponding to the first recommended word in the at least two high-frequency sentences;

A recommended thesaurus generating sub-module 4015 is configured to generate a recommended thesaurus corresponding to the user according to the first recommended word and the second recommended word.

The first scene information acquisition module 402 is configured to acquire first scene information corresponding to the display interface when the display interface includes an input area, where the first scene information includes the time, place, and belonging to the display interface. At least one of the applications.

The recommended word determination module 403 is configured to determine a first recommended word according to the first scene information, and determine a second recommended word corresponding to the first recommended word.

Optionally, the recommended word determination module 403 includes:

The recommended word determination sub-module 4031 is used to search the recommended word database for the first recommended word corresponding to the second scene information that matches the first scene information, and the first recommended word corresponding to the first recommended word. Two recommendation words.

The target recommendation word output module 404 is configured to display M pieces of target recommendation information based on the first recommendation word and the second recommendation word.

Optionally, the number of the second recommendation words corresponding to the first recommendation words is greater than 1, and the target recommendation information output module 404 includes:

The default second recommended word determination sub-module 4041 is configured to determine a default second recommended word among at least two second recommended words corresponding to the first recommended word;

The recommended word module generation sub-module 4042 is used to combine the first recommended word and the default second recommended word to generate target recommendation information;

The target message generating module 405 is configured to generate target information according to the target recommendation information in response to a triggering operation on the target recommendation information.

Optionally, the target information generation module 405 includes:

The first target information generation sub-module 4051 is configured to generate target information according to the first recommended word and the default second recommended word in response to the confirmation operation for the target recommendation information.

Optionally, the target information generation module 405 includes:

Second recommendation word display sub-module 4052, configured to display at least two second recommendation words corresponding to the first recommendation word in the target recommendation information in response to a triggering operation on the default second recommendation word in the target recommendation information word of recommendation;

The target second recommended word determination sub-module 4053 is configured to determine the target second recommended word in response to the selection operation on the at least two second recommended words;

The second target message generation sub-module 4054 is configured to generate target information according to the first recommendation word and the target second recommendation word;

The target information recommendation module 406 is configured to input the target information in the case of receiving the confirmation operation for the target information.

Optionally, the device further includes:

The recommended thesaurus updating module 407 is configured to update the recommended thesaurus corresponding to the user according to the inputted target information and the first scene information.

The information recommendation device in the embodiment of the present application may be a device, or may be a component, an integrated circuit, or a chip in a terminal. The apparatus may be a mobile electronic device or a non-mobile electronic device. Exemplarily, the mobile electronic device may be a mobile phone, a tablet computer, a notebook computer, a palmtop computer, an in-vehicle electronic device, a wearable device, an ultra-mobile personal computer (UMPC), a netbook, or a personal digital assistant (personal digital assistant). assistant, PDA), etc., non-mobile electronic devices can be servers, network attached storage (Network Attached Storage, NAS), personal computer (personal computer, PC), television (television, TV), teller machine or self-service machine, etc., this application Examples are not specifically limited.

In the embodiment of the present application, when the display interface of the electronic device includes an input box, the first scene information corresponding to the display interface is obtained, the first recommended word is determined according to the first scene information, and the first recommended word is determined according to the first scene information. describe the second recommendation word corresponding to the first recommendation word; display M pieces of target recommendation information based on the first recommendation word and the second recommendation word; the target recommendation information can be determined according to the scene information, which improves the determined target recommendation information real-time and accurate.

Embodiment 5

Optionally, as shown in FIG. 7 , an embodiment of the present application further provides an electronic device 700, including a processor 701, a memory 702, a program or instruction stored in the memory 702 and executable on the processor 701, When the program or instruction is executed by the processor 701, the operation of any one of the above-mentioned information recommendation methods is implemented, and the same technical effect can be achieved. To avoid repetition, details are not repeated here.

It should be noted that the electronic devices in the embodiments of the present application include the aforementioned mobile electronic devices and non-mobile electronic devices.

FIG. 8 is a schematic diagram of a hardware structure of an electronic device implementing an embodiment of the present application.

The electronic device 800 includes but is not limited to: a radio frequency unit 801, a network module 802, an audio output unit 803, an input unit 804, a sensor 805, a display unit 806, a user input unit 807, an interface unit 808, a memory 809, and a processor 810, etc. part.

Those skilled in the art can understand that the electronic device 800 may also include a power source (such as a battery) for supplying power to various components, and the power source may be logically connected to the processor 810 through a power management system, so as to manage charging, discharging, and power management through the power management system. consumption management and other functions. The structure of the electronic device shown in FIG. 8 does not constitute a limitation on the electronic device. The electronic device may include more or less components than the one shown, or combine some components, or arrange different components, which will not be repeated here. .

Embodiment 6

Embodiments of the present application further provide a readable storage medium, where a program or an instruction is stored on the readable storage medium, and when the program or instruction is executed by a processor, the operation of any one of the foregoing information recommendation methods is implemented, and The same technical effect can be achieved, and in order to avoid repetition, details are not repeated here.

Wherein, the processor is the processor in the electronic device described in the foregoing embodiments. Examples of the readable storage medium include tangible (non-transitory) computer-readable storage media such as electronic circuits, semiconductor memory devices, computer read-only memory (ROM), erasable ROM (EROM), Random Access Memory (RAM), flash memory, floppy disk, CD-ROM, hard disk, magnetic disk or optical disk, etc.

Embodiment 7

An embodiment of the present application further provides a chip, where the chip includes a processor and a communication interface, the communication interface is coupled to the processor, and the processor is configured to run a program or an instruction to implement any one of the above information recommendation methods The operation of this embodiment can achieve the same technical effect. In order to avoid repetition, details are not repeated here.

It should be understood that the chip mentioned in the embodiments of the present application may also be referred to as a system-on-chip, a system-on-chip, a system-on-a-chip, or a system-on-a-chip, or the like.

It should be noted that, herein, the terms "comprising", "comprising" or any other variation thereof are intended to encompass non-exclusive inclusion, such that a process, method, article or device comprising a series of elements includes not only those elements, It also includes other elements not expressly listed or inherent to such a process, method, article or apparatus. Without further limitation, an element qualified by the phrase "comprising a..." does not preclude the presence of additional identical elements in a process, method, article or apparatus that includes the element. In addition, it should be noted that the scope of the methods and apparatus in the embodiments of the present application is not limited to performing the functions in the order shown or discussed, but may also include performing the functions in a substantially simultaneous manner or in the reverse order depending on the functions involved. To perform functions, for example, the described methods may be performed in an order different from that described, and various steps may also be added, omitted, or combined. Additionally, features described with reference to some examples may be combined in other examples.

From the description of the above embodiments, those skilled in the art can clearly understand that the method of the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is better implementation. Based on this understanding, the technical solutions of the present application can be embodied in the form of software products in essence or the parts that make contributions to related technologies, and the computer software products are stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) ), including several instructions to enable a terminal (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in the various embodiments of this application.

The embodiments of the present application have been described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific embodiments, which are merely illustrative rather than restrictive. Under the inspiration of this application, without departing from the scope of protection of the purpose of this application and the claims, many forms can be made, which all fall within the protection of this application.

Claims

An information recommendation method, applied to an electronic device, the method comprising:

In the case where the display interface of the electronic device includes an input area, acquire first scene information corresponding to the display interface, where the first scene information includes the application to which the display interface belongs and the time included in the display interface at least one of information, the geographic location of the electronic device;

Determine a first recommended word according to the first scene information, and determine a second recommended word corresponding to the first recommended word;

M pieces of target recommendation information are displayed based on the first recommendation word and the second recommendation word.
The method according to claim 1, wherein before the determining the first recommended word according to the first scene information and determining the second recommended word corresponding to the first recommended word, the method further comprises:

According to the user's historical on-screen information and the second scene information corresponding to the historical on-screen information, a recommended thesaurus corresponding to the user is generated, and the recommended thesaurus includes a preset first recommended word and a second recommended word recommendation words, the preset first recommendation words correspond to the second scene information;

The determining a first recommended word according to the first scene information, and determining a second recommended word corresponding to the first recommended word, includes:

A first recommended word corresponding to the second scene information matching the first scene information and a second recommended word corresponding to the first recommended word are searched in the recommended word database.
The method according to claim 2, wherein the generating a recommended vocabulary corresponding to the user according to the user's historical on-screen information and the second scene information corresponding to the historical on-screen information, comprising:

Determine at least two high-frequency sentences of the user according to the screen-on-screen frequency of the user's historical on-screen information;

Clustering the at least two high-frequency sentences according to the second scene information corresponding to the high-frequency sentences to obtain a high-frequency sentence group;

Determine the first recommended words corresponding to the at least two high-frequency sentences according to the high-frequency sentence group and the preset similarity condition;

extracting the second inferred word corresponding to the first recommended word in the at least two high-frequency sentences;

A recommended word database corresponding to the user is generated according to the first recommended word and the second recommended word.
The method according to claim 1, wherein the number of the second recommended words corresponding to the first recommended word is greater than 1, and the target recommendation is generated by combining the first recommended word and the second recommended word information, including:

Among the at least two second recommended words corresponding to the first recommended word, determine a default second recommended word;

M pieces of target recommendation information are displayed based on the first recommendation word and the default second recommendation word.
The method according to claim 4, wherein after the displaying M pieces of target recommendation information based on the first recommendation word and the second recommendation word, the method further comprises:

In response to a triggering operation on the target recommendation information, a target message is generated according to the target recommendation information.
The method according to claim 5, wherein generating the target message according to the target recommendation information in response to a triggering operation on the target recommendation information comprises:

In response to a triggering operation on the default second recommended word in the target recommendation information, displaying at least two second recommended words corresponding to the first recommended word in the target recommendation information;

determining a target second recommended word in response to the selection operation on the at least two second recommended words;

Target information is generated according to the first recommended word and the target second recommended word.
An information recommendation apparatus, applied to electronic equipment, wherein the apparatus includes:

A first scene information acquisition module, configured to acquire first scene information corresponding to the display interface when the display interface of the electronic device includes an input area, where the first scene information includes the application to which the display interface belongs at least one of a program, time information contained in the display interface, and a geographic location of the electronic device;

A recommended word determination module, configured to determine a first recommended word according to the first scene information, and determine a second recommended word corresponding to the first recommended word;

A target recommendation information output module, configured to display M pieces of target recommendation information based on the first recommendation word and the second recommendation word.
The apparatus of claim 7, wherein the apparatus further comprises:

A recommended thesaurus generation module, configured to generate a recommended thesaurus corresponding to the user according to the user's historical on-screen information and the second scene information corresponding to the historical on-screen information, and the recommended thesaurus includes preset The first recommended word and the second recommended word, the preset first recommended word corresponds to the second scene information;

The recommended word determination module includes:

A recommended word determination submodule, configured to search the recommended word database for a first recommended word corresponding to the second scene information that matches the first scene information, and a second recommended word corresponding to the first recommended word Recommended words.
The device according to claim 8, wherein the recommended word library generation module comprises:

a high-frequency sentence determination submodule, configured to determine at least two high-frequency sentences of the user according to the screen-on-screen frequency of the user's historical screen-on-screen information;

a clustering submodule, configured to cluster the at least two high-frequency sentences according to the second scene information corresponding to the high-frequency sentences to obtain a high-frequency sentence group;

a first recommended word determination submodule, configured to determine the first recommended words corresponding to the at least two high-frequency sentences according to the high-frequency sentence group and the preset similarity condition;

A second recommended word determination submodule, configured to extract the second recommended word corresponding to the first recommended word in the at least two high-frequency sentences;

A recommended thesaurus generating sub-module is configured to generate a recommended thesaurus corresponding to the user according to the first recommended word and the second recommended word.
The device according to claim 7, wherein the number of the second recommendation words corresponding to the first recommendation words is greater than 1, and the target recommendation information output module comprises:

A default second recommended word determination submodule, configured to determine a default second recommended word among at least two second recommended words corresponding to the first recommended word;

The recommended word module generating sub-module is configured to display M pieces of target recommendation information based on the first recommended word and the default second recommended word.
The apparatus of claim 10, wherein the apparatus further comprises:

A target message generation module, configured to generate a target message according to the target recommendation information in response to the confirmation operation for the target recommendation information.
The apparatus according to claim 10, wherein the target message generation module comprises:

A second recommendation word display sub-module, configured to display at least two second recommendations corresponding to the first recommendation word in the target recommendation information in response to a triggering operation on the default second recommendation word in the target recommendation information word;

a target second recommended word determination submodule, configured to determine the target second recommended word in response to the selection operation on the at least two second recommended words;

A second target message generating submodule is configured to generate target information according to the first recommendation word and the target second recommendation word.
An electronic device, comprising a processor, a memory, and a program or instruction stored on the memory and executable on the processor, the program or instruction being executed by the processor to achieve as claimed in claims 1 to 6 Any of the steps of the information recommendation method.
A readable storage medium on which programs or instructions are stored, and when the programs or instructions are executed by a processor, implement the steps of the information recommendation method according to any one of claims 1 to 6.
A chip, comprising a processor and a communication interface, wherein the communication interface is coupled with the processor, and the processor is used to run a program or an instruction to implement the steps of the information recommendation method according to any one of claims 1 to 6 .
A computer program product, the computer program product being stored in a non-volatile storage medium, the program product being executed by at least one processor to implement the information recommendation method according to any one of claims 1 to 6 step.
An information recommendation device configured to perform the steps of the information recommendation method according to any one of claims 1 to 6.