WO2022135474A1

WO2022135474A1 - Information recommendation method and apparatus, and electronic device

Info

Publication number: WO2022135474A1
Application number: PCT/CN2021/140476
Authority: WO
Inventors: 胡双威
Original assignee: 维沃移动通信有限公司
Priority date: 2020-12-25
Filing date: 2021-12-22
Publication date: 2022-06-30
Also published as: CN112631437A

Abstract

Disclosed are an information recommendation method and apparatus, and an electronic device. The method comprises: receiving a first input of a user on a first interface; and in response to the first input, matching a candidate word from a word bank on the basis of a character string corresponding to the first input and the first interface, and displaying the candidate word, wherein the word bank stores a keyword and a mapping relationship between the keyword and the first interface.

Description

Information recommendation method, device and electronic device

CROSS-REFERENCE TO RELATED APPLICATIONS

This application claims priority to Chinese Patent Application No. 202011565318.6 filed in China on Dec. 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 information recommendation method, device and electronic device.

Background technique

With the development of electronic technology, there are more and more scenarios where users input text on electronic devices. At present, when a user inputs a character string, the electronic device can recommend candidate words corresponding to the character string, and the user can select from the candidate words. target candidates.

In the related art, when recommending a candidate word to the user, the electronic device may read the candidate word corresponding to the input string from the thesaurus for recommendation. However, since a large number of words are usually stored in the thesaurus, every time the electronic device recommends candidate words for the user, it needs to traverse the large number of words stored in the whole thesaurus to determine the candidate words corresponding to the input string, resulting in It is less efficient to recommend candidate words for users. In addition, for the same character string input by the user, there may be multiple matching items in the thesaurus, and the electronic device will recommend the multiple matching items as candidate words at this time. In this way, the accuracy of recommending candidate words for the user is low, thereby affecting the input efficiency of the user.

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 complicated steps and long time-consuming in the text input process.

In order to solve the above technical problems, this application is implemented as follows:

In a first aspect, an embodiment of the present application provides an information recommendation method, the method includes: receiving a first input from a user on a first interface; in response to the first input, based on the character string corresponding to the first input and the above The first interface matches candidate words from a thesaurus, and displays the above-mentioned candidate words; wherein, the above-mentioned thesaurus stores keywords and the mapping relationship between the keywords and the first interface.

In a second aspect, an embodiment of the present application provides an information recommendation device, the device includes: the above device includes: a receiving module, a processing module and a display module, wherein: the above-mentioned receiving module is used for receiving the first user's first interface on the first interface. an input; the above-mentioned processing module, in response to the above-mentioned first input received by the above-mentioned receiving module, based on the character string corresponding to the above-mentioned first input and the above-mentioned first interface, matching candidate words from the thesaurus; the above-mentioned display module, used for Display the above-mentioned candidate words matched from the thesaurus by the above-mentioned processing module;

The thesaurus stores keywords and a mapping relationship between the keywords and the first interface.

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 a sixth aspect, an embodiment of the present application provides a computer program product, where the program product is stored in a non-volatile storage medium, and the program product is executed by at least one processor to implement the method described in the first aspect.

In the embodiment of the present application, the electronic device stores keywords and the mapping relationship between the keywords and the first interface in the thesaurus, so that when the user inputs a character string on the first interface, the user can input the character string based on the character string and the first interface. , and determine candidate words matching the character string and the first interface from the thesaurus. In this way, the electronic device can recommend candidate words that match the current input interface for the user, so that the user can recommend candidate words that are more in line with the user's input requirements on the current input interface, and improve the flexibility of recommending candidate words for the user. and accuracy.

Description of drawings

1 is a flowchart of an information recommendation method provided by an embodiment of the present application;

FIG. 2 is one of the schematic structural diagrams of an information recommendation apparatus provided by an embodiment of the present application;

3 is one of the schematic diagrams of the hardware structure of an electronic device provided by an embodiment of the present application;

FIG. 4 is a second schematic diagram of a hardware structure of an electronic device provided by an embodiment 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 the data so used are interchangeable under appropriate circumstances so that the embodiments of the present application can be practiced in sequences other than those illustrated or described herein, and distinguish between "first", "second", etc. The objects are usually of one type, and the number of objects is not limited. For example, the first object may be one or more than one. 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 information recommendation method provided by the embodiments of the present application will be described in detail below through specific embodiments and application scenarios with reference to the accompanying drawings.

The information recommendation method provided by the embodiment of the present application can be applied to the scenario of text input.

Embodiments of the present application provide an information recommendation method, apparatus, and electronic device, because users usually use various symbols to represent text content in input text content with complete semantics (eg, complete sentences or words). Pause and tone of voice. Therefore, when detecting that the content on the screen by the user includes the first symbol, the information recommendation device can perform text splitting on the text entered by the user based on the target character and the first symbol in the text entered by the user, thereby The target text containing the complete words that the user wants to input can be extracted from the text that the user has input, and the complete words contained in the target text can be stored in the thesaurus. So that when the user inputs the keyword again, the keyword can be recommended to the user as a candidate word.

FIG. 1 shows a flowchart of a display method provided by an embodiment of the present application.

As shown in FIG. 1 , the information recommendation method provided by this embodiment of the present application may include the following steps 101 and 102:

Step 101: Receive a first input from a user on a first interface.

In this embodiment of the present application, the above-mentioned first interface may include any one of the following: a conversation window interface, and a text input interface.

Optionally, in this embodiment of the present application, the above-mentioned first interface includes an information input area and an information display area. Exemplarily, the above-mentioned information input area is used for inputting character strings, for example, the above-mentioned information input area may be an input method interface. Exemplarily, the above-mentioned information display area is used to display text information displayed on the screen by the user.

Exemplarily, the above-mentioned first input may be an input of a character string entered by the user in the above-mentioned information input area.

Step 102 : In response to the above-mentioned first input, based on the character string corresponding to the first input and the first interface, match candidate words from the thesaurus, and display the above-mentioned candidate words.

Wherein, the above-mentioned thesaurus stores keywords and a mapping relationship between the keywords and the first interface. It can be understood that a plurality of mapping relationships will be stored in the above thesaurus, one mapping relationship is the mapping relationship between at least one keyword and one interface, and/or one mapping relationship may be between at least one keyword and one interface type. Mapping relations.

In this embodiment of the present application, the information recommendation apparatus may display candidate words in the candidate word display area.

Exemplarily, the above-mentioned candidate word display area may be an area on an input method interface, or the above-mentioned candidate word display area may be a floating window.

In this embodiment of the present application, when the user inputs a character string on the first interface, the information recommendation device may search for keywords that have a mapping relationship with the first interface (that is, keywords associated with the first interface) from the thesaurus ), and use the above keywords as alternative keywords. Then, based on the character string input by the user, the information recommendation apparatus may, from the above keywords (ie, the above candidate keywords) that have a mapping relationship with the first interface, search for keywords that match the character string input by the user as candidate words .

For example, taking the above-mentioned first interface as the conversation interface 1 as an example, if the thesaurus stores the keyword A, the keyword B, the keyword C and the keyword D that have a mapping relationship with the first interface, the When the character string 1 is input in 1, the keyword matching the character string 1 can be determined from the above-mentioned four keywords that have a mapping relationship with the conversation interface 1, and the keyword can be recommended to the user as a candidate word.

Optionally, in this embodiment of the present application, the process for the information recommendation apparatus to determine, from the keywords associated with the first interface, a keyword that matches the character string input by the user includes at least the following three ways:

Method 1: Memory gives priority to words. That is, if the thesaurus includes the same character string as the first character string entered by the user on the first interface (that is, the character string currently entered by the user through the physical keyboard or the virtual keyboard), the information recommendation device can display the candidate words in the candidate word display area. The text corresponding to the character string (that is, the keyword stored in association with the thesaurus and the character string corresponding to the keyword) is displayed in the front position.

For example, if the character string entered by the user on the first interface is "hanyufei", and "Korean Fei" and "hanyufei" are stored in the thesaurus, the information recommendation device obtains the text "Korean Fei" in the thesaurus, And "Korean Fei" is displayed at the front of the candidate word display area, that is, "Korean Fei" is recommended to the user as the first candidate word.

Method 2: Prefix combined with memorized words. That is, when the user types a character string on the first interface, the information recommending device detects that there is a character string in the thesaurus that includes the first character string currently typed by the user, and the information recommending device can display The previous position displays the text corresponding to the string.

For example, if the character string entered by the user on the first interface is "hanyu", and "Hanyufei" and "hanyufei" are associated and stored in the thesaurus, the information recommendation device obtains the text "Korean Fei" in the thesaurus, And "Korean Fei" is displayed at the front of the candidate word display area, that is, "Korean Fei" is recommended to the user as the first candidate word.

Method 3: Word prefix association combined with memorizing words. That is, the user types a character string on the first interface, selects a candidate word corresponding to the character string on the screen, and after the candidate word is displayed on the input interface, there is a word in the thesaurus including the text input interface that the user has screened this time. The information recommendation device obtains the character in the thesaurus, and displays the characters in the character except the first character in the front position of the candidate word display area.

For example, the user types in "han" and selects "Han" on the upper screen. When the information recommendation device detects that there is "Han Yufei" including the character "Han" in the thesaurus, the information recommendation device can obtain the "Han" in the thesaurus. The text "Korean Philip", and "Yu fei" is displayed at the front of the candidate word display area.

In the information recommendation method provided by this application, the electronic device stores the keyword and the mapping relationship between the keyword and the first interface in the thesaurus, so that when the user inputs a character string on the first interface, the user can input the character string based on the character string. With the first interface, candidate words matching the character string and the first interface are determined from the thesaurus. In this way, the electronic device can recommend candidate words that match the current input interface for the user, so that the user can recommend candidate words that are more in line with the user's input requirements on the current input interface, and improve the flexibility of recommending candidate words for the user. and accuracy.

Optionally, in this embodiment of the present application, the information recommendation device may extract keywords from the target text displayed on the first interface, and save the above keywords and the mapping relationship between the above keywords and the first interface in a in the thesaurus.

Exemplarily, before the above step 101, the information recommendation method provided in this embodiment of the present application further includes the following steps A1 to A3:

Step A1: Obtain the target text when it is detected that the content input on the first interface includes the first symbol.

Step A2: Extract the keywords in the above target text.

Step A3: correspondingly store the above keywords and the above mapping relationships in the thesaurus.

Optionally, in this embodiment of the present application, the content input on the above-mentioned first interface is the text displayed on the screen by the user.

Optionally, in the embodiment of the present application, the above-mentioned target text includes: a character between the target character input by the user and the first symbol; the above-mentioned target character is: the first character input by the user, or, the above-mentioned first symbol The previous second symbol displayed in the first interface.

In an example, when the target character is the first character input by the user, the target text is the text between the first character input by the user and the first symbol currently input. For example, if the text content input by the user is "Tomorrow is Lan Yufei's birthday.", the target text is the text between the word "Ming" and ".".

In another example, when the target character is the second symbol on the screen preceding the first symbol input by the user this time, the target text is the text between the second symbol and the first symbol. For example, the text content entered by the user is "Tomorrow the weather is fine, we are going to help Lanyufei move.", the target text is the text between "," and ".".

It should be noted that, when the information recommendation apparatus detects the first character input by the user and the above-mentioned second character from the input text at the same time, the information recommendation apparatus will determine the second symbol as the target character.

Optionally, in this embodiment of the present application, during the process of text input by the user, the information recommendation apparatus may perform real-time or periodic detection (eg, every 5s) on the content input by the user (that is, the content on the screen this time). check once) to determine whether it contains the first symbol.

Optionally, in this embodiment of the present application, the information recommendation apparatus may determine the first text from the text that the user has entered when it detects that the content on the screen by the user this time includes the first symbol, and then, in the first A target character is detected in the text, where the target character is a character in the first text that satisfies a predetermined condition. Wherein, the above-mentioned first text includes: all texts input by the user, text input by the user within a predetermined time before inputting the first symbol, text composed of a predetermined number of characters input by the user before inputting the first symbol (for example, the user 30 characters entered before the first symbol).

Optionally, in this embodiment of the present application, the information recommendation apparatus may detect in real time whether the text input by the user contains the first character. Therefore, when the user currently inputs (on the screen) a symbol, the information recommendation device will acquire the target text once, so as to ensure that all the content input by the user can be detected.

Optionally, in this embodiment of the present application, both the above-mentioned first symbol and the above-mentioned second symbol belong to target symbols, wherein the above-mentioned target symbols include any one of the following: punctuation marks and separators. Among them, the delimiter includes: newline character, space character.

Usually, in the input text with complete semantics (for example, complete sentences or words), the user uses various symbols to represent the pauses in the text content and the tone to be expressed. In this way, in a text, the text content between the two punctuation marks before and after is usually a sentence or a text containing complete words (such as a person's name or a place name). Among them, different symbols express different meanings.

Example 1: For punctuation, some punctuation marks (such as "," ", "".") are usually used to express pauses in text content, and some punctuation marks (such as "!" "?") are usually used by users to express text content The tone that the corresponding user wants to express.

Example 2: For delimiters, delimiters are often used to separate and split text content. For example, when it is detected that the user is currently inputting a space character, it means that the user has input a complete sentence or a word. The target text to ensure the integrity of the obtained target text.

For example, assuming that the text that the user has entered is "The weather will be fine tomorrow, we will meet at Pujun East Road at 10 o'clock and go to Guigongfang for morning tea together." Since there are "," and "." in the text, it means that in the There is a complete sentence between "," and ".", therefore, the information recommending apparatus regards the text between "," and "." as the target text, thereby obtaining a sentence.

Optionally, in the embodiment of the present application, in the case of obtaining the target text in the text input by the user, the information recommendation device may perform word segmentation or semantic recognition on the target text, extract keywords in the target text, and obtain the target text. at least one keyword in .

Exemplarily, the above keywords may be phrases or phrases containing specific semantics in the target text, and the above keywords include at least one of the following: a person's name, a place name, an institution name, and a proper noun.

It should be noted that, the information recommendation apparatus may extract one or more keywords from the target text, which is not limited in this embodiment of the present application.

In this way, the information recommendation apparatus can extract keywords with complete semantics from the target text input by the user on the first interface. Since the keyword is extracted from the first interface, it is more in line with the user's input intention on the first interface.

Optionally, in the embodiment of the present application, in the case where keywords are extracted from the target text of the first interface, the information recommendation apparatus may establish a mapping relationship between the above-mentioned first interface and keywords.

Exemplarily, the information recommendation apparatus may automatically establish a mapping relationship between the above-mentioned first interface and keywords, or may be triggered by a user to establish a mapping relationship between the above-mentioned first interface and keywords.

For example, taking the above-mentioned first interface as a conversation interface as an example, if the above-mentioned keywords include keyword A, keyword B, keyword C and keyword B, the information recommending device can store the above-mentioned 4 keywords in the thesaurus , and generate the mapping relationship between each of the above four keywords and the conversation interface, obtain four mapping relationships, and store the four mapping relationships in the thesaurus respectively.

In this way, the information recommendation device can save the mapping relationship between the keywords extracted from the target text of the first interface and the first interface in the thesaurus. When the user inputs a character string on the first interface, the information recommendation device can The mapping relationship between the first interface and the keywords recommends candidate words for the user that conform to the user's input habit on the first interface.

Further optionally, in the embodiment of the present application, in the above step A3, the keywords are stored in the thesaurus, including the following step B1:

Step B1: Associate the keywords with the character strings corresponding to the keywords and store them in the thesaurus.

Exemplarily, after extracting the keyword from the target text, the information recommendation device may obtain the character string (eg, pinyin) corresponding to the keyword, and then, the corresponding relationship between the character string and the character string corresponding to the keyword. stored in the thesaurus. In this way, the information recommendation apparatus can find the keyword corresponding to the character string in the thesaurus based on the corresponding relationship, so as to display the keyword as a candidate word to the user, thereby improving the recommendation efficiency of the candidate word.

Exemplarily, the character string corresponding to the above keyword may include at least one of the following: the pinyin of the keyword, the pinyin that is more similar to the pinyin of the keyword (for example, if the pinyin of the keyword is "lanyufei", it is the same as the key word. The pinyin of the word close to the pinyin can be "hanyufei" or lanyuwei, etc.), the foreign language translation of the keyword (for example, the keyword is "Blue Yufei", the English translation of the keyword can be obtained and saved, for example, "Lanyufei") .

Further optionally, in this embodiment of the present application, the foregoing step A2 includes the following steps C1 to C3:

Step C1: Perform word segmentation on the target text to obtain N candidate word segmentations.

Step C2: Receive a second input from the user for the target candidate word segmentation among the N candidate word segmentations.

Step C3: In response to the second input, use the target candidate word segmentation as a keyword.

Exemplarily, the above-mentioned first input includes: any feasible input, such as touch input, gesture input, and voice input.

Exemplarily, the information recommendation apparatus may perform word segmentation operations on the target text by using word segmentation methods such as character matching, comprehension method, or statistical method, to obtain N candidate word segmentations, and based on the user's input operation on the target candidate word segmentation among the N candidate word segmentations, The target candidate word segmentation is determined as a keyword.

Further, the information recommendation device can display the above N candidate word segmentations in the keyword display area, and the user can select (eg, check) the required candidate word segmentation in the keyword selection area, and then the information recommendation device can select the candidate word segmentation selected by the user. Participles are identified as keywords.

For example, assuming that the target text is "Han Yufei eats hot pot at restaurant A", the information recommendation device can perform a syntactic understanding analysis on the target text, and obtain candidate word segmentations such as "Korean Fei", "A restaurant" and "hot pot", and display them in the keywords. If these candidate word segments are displayed in the area, the user can click or tick the candidate word segment "Korean Philip" among them to determine the candidate word segment as a keyword. In this way, the information recommendation apparatus can determine the keywords based on the user's selection operation on the candidate word segmentation, so as to obtain the keywords required by the user.

Exemplarily, the word storage device may perform word segmentation operations on the target text by using word segmentation methods such as character matching, comprehension, or statistical methods, obtain word units in the target text, and then establish a machine learning model based on a machine learning algorithm, and use the word units in the target text. The word features and sentence features of the word unit are extracted, and the keywords in the target text are extracted. Further, the text storage device can acquire the word feature of the word unit, the sentence feature of the word unit in the corresponding target text, and the word feature of the word unit refers to the part-of-speech feature and the named entity feature of the word unit.

It should be noted that the part-of-speech feature of the word unit above refers to the part-of-speech of the word unit, such as a noun or a verb. It can be understood that, under normal circumstances, word units of certain part-of-speech features are more likely to become keywords, for example, word units of noun features. The named entity feature of the word unit above refers to whether the word unit is a named entity. Generally, a word unit that is generally a named entity is more likely to become a keyword.

Further, the sentence feature of the above-mentioned word unit in the corresponding target text refers to the feature of the word unit in the target text, for example, the part-of-speech feature of the front compound word, the part-of-speech feature of the rear compound word, and the sentence position feature of the word unit in the target text. and dependencies, etc.

For example, assuming that the target text is "Korean Fei eats hot pot at restaurant A", the information recommendation device can perform a syntactic analysis on the target text, and obtain the word units "Korean Fei", "in", "restaurant A", "eat" and "hot pot" , and according to part-of-speech analysis and named entity recognition, the word features of these word units (for example, "Korean Fei" is a person's name, "A restaurant" is a place name, and "eat" is a verb) and sentence features (for example, "hot pot" is Noun object, "Korean Fei" as the subject, "Korean Fei" and "eat" as the subject-predicate relationship), and then based on the established machine learning model, using the word features and sentence features of the word unit to extract keywords in the target text , ie, "Korean Fei" and "A Restaurant". In this way, the text storage device can automatically and intelligently extract keywords in the target text, which improves the efficiency of keyword extraction.

Further optionally, in the embodiment of the present application, after the above step A2, the display method provided by the embodiment of the present application further includes the following steps D1 and D2:

Step D1: Display keywords.

Step D2: Receive the third input of the keyword by the user.

In conjunction with the above-mentioned step D2, in the above-mentioned step A3, storing the above-mentioned keywords in the thesaurus includes the following steps D3:

Step D3: In response to the above-mentioned second input, the keywords are stored in the thesaurus.

Exemplarily, after extracting at least one keyword from the target text, the information recommending apparatus may display the at least one keyword in a predetermined display manner. The above predetermined display manner includes at least one of the following: displaying at least one keyword above the target text, highlighting or highlighting at least one keyword in the target text, and displaying the at least one keyword in the keyword display interface.

Exemplarily, the information recommendation apparatus may, after displaying the above at least one keyword, the user may check or click on any keyword in the above at least one keyword (ie, the third input), and the above at least one keyword may be selected. Store any keywords in the thesaurus into the thesaurus. In this way, the user can store keywords in a targeted manner according to requirements, which improves the flexibility of storing keywords, further ensures that the keywords stored in the thesaurus can be effectively used, and at the same time saves the storage space of the thesaurus.

In the information recommendation method provided by the embodiments of the present application, since the user usually uses various symbols in the input text content with complete semantics (for example, complete sentences or words) to indicate the pause of the text content and the desired expression tone. Therefore, when detecting that the content on the screen by the user includes the first symbol, the information recommendation device can perform text splitting on the text entered by the user based on the target character and the first symbol in the text entered by the user, thereby The target text containing the complete words that the user wants to input can be extracted from the text that the user has input, and the complete words contained in the target text can be stored in the thesaurus. So that when the user inputs the keyword again, the keyword can be recommended to the user as a candidate word.

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 information recommending device provided by the embodiment of the present application is described by taking the information recommending device executing the information recommending method as an example.

An embodiment of the present application provides an information recommendation device. As shown in FIG. 2 , the information recommendation device includes: a receiving module 401 , a processing module 402 and a display module 403 , wherein: the above-mentioned receiving module 401 is used to receive the user's first interface The above-mentioned processing module 402, in response to the above-mentioned first input received by the above-mentioned receiving module 401, based on the character string corresponding to the above-mentioned first input and the above-mentioned first interface, matching candidate words from the vocabulary; the above-mentioned The display module 403 is configured to display the candidate words matched from the thesaurus by the processing module 402; wherein the thesaurus stores keywords and the mapping relationship between the keywords and the first interface.

In the information recommendation device provided by the embodiment of the present application, the electronic device stores the keyword and the mapping relationship between the keyword and the first interface in the thesaurus, so that when the user inputs a character string on the first interface, the user can input the character string based on the character string. With the first interface, candidate words matching the character string and the first interface are determined from the thesaurus. In this way, the electronic device can recommend candidate words that match the current input interface for the user, so that the user can recommend candidate words that are more in line with the user's input requirements on the current input interface, and improve the flexibility of recommending candidate words for the user. and accuracy.

Optionally, in this embodiment of the present application, the above-mentioned apparatus further includes: an acquisition module 404 and a storage module 405, wherein: the above-mentioned acquisition module 404 is configured to detect that the content input on the above-mentioned first interface includes the first symbol , obtain the target text; the above target text includes: the character between the target character input by the user and the above-mentioned first symbol; the above-mentioned target character is: the first character input by the user, or, the previous one of the above-mentioned first symbol is in the above-mentioned first symbol The second symbol displayed in an interface; the above-mentioned processing module 402 is also used to extract the keywords in the above-mentioned target text obtained by the above-mentioned acquisition module 404; the above-mentioned storage module 405 is used to extract the above-mentioned keywords and The above-mentioned mapping relationship is correspondingly stored in the above-mentioned thesaurus.

Optionally, in this embodiment of the present application, both the above-mentioned first symbol and the above-mentioned second symbol belong to target symbols; wherein, the above-mentioned target symbols include any one of the following: punctuation marks and separators. Among them, the delimiter includes: newline character, space character.

Optionally, in this embodiment of the present application, the above-mentioned storage module 405 is specifically configured to associate and store the above-mentioned keywords and the character strings corresponding to the above-mentioned keywords in the thesaurus.

Optionally, in this embodiment of the present application, the above-mentioned processing module 402 is specifically configured to perform word segmentation on the above-mentioned target text to obtain N candidate word segmentations; the above-mentioned receiving module 401 is further configured to receive the above-mentioned information obtained by the above-mentioned processing module 402 from the user. The second input of the target candidate word segmentation in the N candidate word segmentations; the above-mentioned processing module 402 is specifically configured to use the above-mentioned target candidate word segmentation as a keyword in response to the second input received by the above-mentioned receiving module 401 .

Optionally, in this embodiment of the present application, the above-mentioned display module 403 is further configured to display the above-mentioned keywords; the above-mentioned receiving module 401 is further configured to receive a third input from the user on the keywords displayed by the above-mentioned display module 403; the above-mentioned storage The module 405 is specifically configured to store the above-mentioned keywords in the thesaurus in response to the above-mentioned third input received by the above-mentioned receiving module 401 .

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.

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 this embodiment of the present application can implement each process implemented by the method embodiment in FIG. 1 , and to avoid repetition, details are not described here.

Optionally, as shown in FIG. 3 , an embodiment of the present application further provides an electronic device 500, including a processor 501, a memory 502, a program or instruction stored in the memory 502 and executable on the processor 501, When the program or instruction is executed by the processor 501, each process of the above-mentioned information recommendation method embodiment 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. 4 is a schematic diagram of a hardware structure of an electronic device implementing an embodiment of the present application.

The electronic device 100 includes but is not limited to: a radio frequency unit 101, a network module 102, an audio output unit 103, an input unit 104, a sensor 105, a display unit 106, a user input unit 107, an interface unit 108, a memory 109, and a processor 110, etc. part.

Those skilled in the art can understand that the electronic device 100 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 110 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. 4 does not constitute a limitation to 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. .

The above-mentioned user input unit 107 is used for receiving the first input of the user on the first interface; the above-mentioned processor 110 is used for responding to the above-mentioned first input received by the above-mentioned user input unit 107, based on the corresponding first input The character string and the above-mentioned first interface match candidate words from the thesaurus; the above-mentioned display unit 106 is used to display the above-mentioned candidate words matched by the above-mentioned processor 110 from the thesaurus; wherein, the above-mentioned thesaurus stores keywords and the above-mentioned key words The mapping relationship between the word and the above-mentioned first interface.

In the electronic device provided in the embodiment of the present application, the electronic device stores the keyword and the mapping relationship between the keyword and the first interface in the thesaurus, so that when the user inputs a character string on the first interface, the user can In the first interface, candidate words matching the character string and the first interface are determined from the thesaurus. In this way, the electronic device can recommend candidate words that match the current input interface for the user, so that the user can recommend candidate words that are more in line with the user's input requirements on the current input interface, and improve the flexibility of recommending candidate words for the user. and accuracy.

Optionally, in this embodiment of the present application, the above-mentioned processor 110 is configured to obtain the target text when it is detected that the content input on the above-mentioned first interface includes the first symbol; the above-mentioned target text includes: the target entered by the user The character between the character and the above-mentioned first symbol; the above-mentioned target character is: the first character input by the user, or the second symbol displayed in the above-mentioned first interface before the above-mentioned first symbol; the above-mentioned processor 110, also is used to extract the keywords in the target text; the memory 109 is used to store the keywords extracted by the processor 110 and the mapping relationship in the thesaurus correspondingly.

Optionally, in the embodiment of the present application, both the above-mentioned first symbol and the above-mentioned second symbol belong to target symbols; wherein, the above-mentioned target symbols include any one of the following: punctuation marks and separators. Among them, the delimiter includes: newline character, space character.

Optionally, in this embodiment of the present application, the above-mentioned memory 109 is specifically configured to associate and store the above-mentioned keywords and the character strings corresponding to the above-mentioned keywords in the thesaurus.

Optionally, in this embodiment of the present application, the above-mentioned processor 110 is specifically configured to perform word segmentation on the above-mentioned target text to obtain N candidate word segmentations; the above-mentioned user input unit 107 is further configured to receive the user's input on the above-mentioned processor 110 obtained by the above-mentioned processor 110. The second input of the target candidate word segmentation in the above N candidate word segmentations; the processor 110 is specifically configured to use the above target candidate word segmentation as a keyword in response to the second input received by the user input unit 107 .

Optionally, in this embodiment of the present application, the above-mentioned display unit 106 is further configured to display the above-mentioned keywords; the above-mentioned user input unit 107 is also used to receive a third user input on the keywords displayed by the above-mentioned display unit 106; the above-mentioned The memory 109 is specifically configured to store the above-mentioned keywords in the thesaurus in response to the above-mentioned third input received by the above-mentioned user input unit 107 .

For the beneficial effects of the various implementations in this embodiment, reference may be made to the beneficial effects of the corresponding implementations in the above method embodiments, which are not repeated here to avoid repetition. It should be understood that, in this embodiment of the present application, the input unit 104 may include a graphics processor (Graphics Processing Unit, GPU) 1041 and a microphone 1042. Such as camera) to obtain still pictures or video image data for processing. The display unit 106 may include a display panel 1061, which may be configured in the form of a liquid crystal display, an organic light emitting diode, or the like. The user input unit 107 includes a touch panel 1071 and other input devices 1072 . The touch panel 1071 is also called a touch screen. The touch panel 1071 may include two parts, a touch detection device and a touch controller. Other input devices 1072 may include, but are not limited to, physical keyboards, function keys (such as volume control keys, switch keys, etc.), trackballs, mice, and joysticks, which will not be repeated here. Memory 109 may be used to store software programs as well as various data including, but not limited to, application programs and operating systems. The processor 110 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, and the like, and the modem processor mainly processes wireless communication. It can be understood that, the above-mentioned modulation and demodulation processor may not be integrated into the processor 110 .

The embodiments of the present application further provide a readable storage medium, where a program or an instruction is stored on the readable storage medium. When the program or instruction is executed by a processor, each process of the foregoing storage method embodiment can be implemented, and the same can be achieved. The technical effect, in order to avoid repetition, will not be repeated here.

Wherein, the processor is the processor in the electronic device described in the foregoing embodiments. The readable storage medium includes a computer-readable storage medium, such as a computer read-only memory (Read-Only Memory, ROM), a random access memory (Random Access Memory, RAM), a magnetic disk or an optical disk, and the like.

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 the above information recommendation method embodiment. Each process can achieve the same technical effect. In order to avoid repetition, it will not be repeated here.

An embodiment of the present application provides a computer program product, where the program product is stored in a non-volatile storage medium, and the program product is executed by at least one processor to implement the method according to the first aspect.

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 methods of the above embodiments can be implemented by means of software plus a necessary general hardware platform, and of course hardware can also be used, 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 the prior art, and the computer software products are stored in a storage medium (such as ROM/RAM, magnetic disk, CD-ROM), including several instructions to make a terminal (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) 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, the method comprising:

receiving the first input from the user on the first interface;

In response to the first input, based on the character string corresponding to the first input and the first interface, matching candidate words from the thesaurus, and displaying the candidate words;

Wherein, the thesaurus stores keywords and the mapping relationship between the keywords and the first interface.
The method according to claim 1, wherein before the receiving the first input from the user on the first interface, the method further comprises:

In the case where it is detected that the content input on the first interface includes the first symbol, obtain the target text; the target text includes: the character between the target character input by the user and the first symbol; the target character is : the first character input by the user, or the second symbol displayed in the first interface before the first symbol;

extracting keywords in the target text;

The keywords and the mapping relationship are correspondingly stored in the thesaurus.
The method of claim 2, wherein both the first symbol and the second symbol belong to a target symbol;

The target symbol includes any one of the following: punctuation, separator; wherein, the separator includes: newline, space character.
The method according to claim 2, wherein the storing the keywords in the thesaurus comprises:

The keyword and the character string corresponding to the keyword are associated and stored in the thesaurus.
The method according to claim 2, wherein the extracting the keywords in the target text comprises:

Perform word segmentation on the target text to obtain N candidate word segmentations;

receiving a second input from the user to the target candidate word segmentation in the N candidate word segmentations;

In response to the second input, the target candidate word segmentation is used as a keyword.
The method according to claim 2 or 4, wherein after extracting the keywords in the target text, the method further comprises:

displaying the keyword;

receiving a third input of the keyword from the user;

The storing of the keywords in the thesaurus includes:

In response to the third input, the keywords are stored in the thesaurus.
An information recommendation device, the device includes: a receiving module, a processing module and a display module, wherein:

The receiving module is configured to receive the first input of the user on the first interface;

The processing module is configured to, in response to the first input received by the receiving module, match candidate words from the lexicon based on the character string corresponding to the first input and the first interface;

The display module is used to display the candidate words matched from the thesaurus by the processing module;

Wherein, the thesaurus stores keywords and the mapping relationship between the keywords and the first interface.
The apparatus according to claim 7, wherein the apparatus further comprises: an acquisition module and a storage module, wherein:

The obtaining module is configured to obtain target text when it is detected that the content input on the first interface includes a first symbol; the target text includes: the target character that has been input by the user to the first symbol. character; the target character is: the first character input by the user, or the second symbol displayed in the first interface before the first symbol;

The processing module is further configured to extract keywords in the target text obtained by the obtaining module;

The storage module is configured to store the keywords and the mapping relationship extracted by the processing module in the thesaurus correspondingly.
The apparatus of claim 8, wherein both the first symbol and the second symbol belong to a target symbol;

The target symbol includes any one of the following: punctuation, separator; wherein, the separator includes: newline, space character.
The apparatus of claim 8, wherein,

The storage module is specifically configured to associate and store the keyword and the character string corresponding to the keyword into the thesaurus.
The apparatus of claim 8, wherein,

The processing module is specifically configured to perform word segmentation on the target text to obtain N candidate word segmentations;

The receiving module is further configured to receive a second input from the user to the target candidate word segmentation in the N candidate word segmentations obtained by the processing module;

The processing module is specifically configured to use the target candidate word segmentation as a keyword in response to the second input received by the receiving module.
An apparatus according to claim 8 or 10, wherein,

The display module is further configured to display the keyword;

The receiving module is further configured to receive a third input from the user to the keyword displayed by the display module;

The storage module is specifically configured to store the keyword in the thesaurus in response to the third input received by the receiving module.
An electronic device, characterized in that it includes a processor, a memory, and a program or instruction stored on the memory and executable on the processor, and the program or instruction is executed by the processor to achieve the right Steps of the information recommendation method described in any one of requirements 1-6.
A computer-readable storage medium, characterized in that a program or an instruction is stored on the readable storage medium, and when the program or instruction is executed by a processor, the information recommendation method according to any one of claims 1-6 is implemented A step of.
An information recommendation apparatus, characterized in that the apparatus is configured to execute the information recommendation method according to any one of claims 1 to 6.
A computer program product, characterized in that, the program product is executed by at least one processor to implement the information recommendation method according to any one of claims 1 to 6.
A chip, characterized in that the chip includes a processor and a communication interface, the communication interface is coupled to the processor, and the processor is used to run a program or an instruction to implement any one of claims 1 to 6 The described information recommendation method.