WO2019095682A1

WO2019095682A1 - Candidate word prediction method and device

Info

Publication number: WO2019095682A1
Application number: PCT/CN2018/091054
Authority: WO
Inventors: 涂畅; 张扬; 王砚峰
Original assignee: 北京搜狗科技发展有限公司
Priority date: 2017-11-16
Filing date: 2018-06-13
Publication date: 2019-05-23
Also published as: CN109799916A; CN109799916B

Abstract

Disclosed in embodiments of the present application are a candidate word prediction method and device. In the method, according to content most recently input on the screen, on-screen content requiring word prediction can be determined; since a word prediction intention can reflect, to a large extent, a user's actual input intention for the on-screen content, if the word prediction intention of the on-screen content can be determined, content that may be continuously input on the screen by the user after the on-screen content can be determined according to the word prediction intention. Therefore, when data corresponding to the word prediction intention is obtained according to a keyword in the on-screen content, and a candidate corresponding to the on-screen content is predicted according to the data, the candidate determined according to the data is more likely to meet the user's input intention. Thus, the input convenience for the user is improved. Moreover, the determined candidate does not need to be generated on the basis of the past input data of the user, and thus, the likelihood and accuracy of the predicted candidate are improved.

Description

Candidate association method and device

The present application claims the priority of the Chinese Patent Application, filed on Nov. 16, 2017, the application Serial No. in.

Technical field

The present application relates to the field of input methods, and in particular to a candidate association method and apparatus.

Background technique

In the input process using the input method, the input method may provide the user with the content that may be associated with the content or the context content in a Lenovo manner according to the content that the user has input through the input method or the context content of the current cursor position. Lenovo candidates save user input costs and increase input efficiency. For example, after the user clicks on the "search dog", it can provide association candidates such as "input method" and "search".

The traditional association method usually uses historical data as the basis for determining the candidate candidate. For example, if the historical data includes: the “sogou input method” input by the user, the user can provide the association candidate after the user “screens the dog”. "Input". In other words, the association candidate for the upper screen content can only be derived from historical data, or can only be generated based on historical data.

It can be seen that the traditional association method has limited the candidate candidates and narrowed the scope of the Lenovo candidate.

Summary of the invention

In order to solve the above technical problem, the present application provides a candidate association method and device, which improves the user's input convenience, and the determined candidate does not need to be generated according to the user's historical input data, thereby improving the association candidate. may.

The embodiment of the present application discloses the following technical solutions:

In a first aspect, an embodiment of the present application provides a candidate association method, where the method includes:

Determining the on-screen content to be associated, the content of the last screen includes the content of the last screen;

Determining a Lenovo intent for the content that has been on the screen;

Acquiring data corresponding to the association intention according to keywords in the already-screened content;

Based on the data, a candidate corresponding to the already-online content is associated.

In a second aspect, an embodiment of the present application provides a candidate association device, where the device includes a first determining unit, a second determining unit, a first acquiring unit, and a Lenovo unit:

The first determining unit is configured to determine the content of the upper screen to be associated, and the content of the last screen includes the content of the last screen;

The second determining unit is configured to determine a association intention for the content that has been on the screen;

The first acquiring unit is configured to acquire data corresponding to the association intention according to a keyword in the uploaded content;

The association unit is configured to associate a candidate corresponding to the screened content according to the data.

In a third aspect, an embodiment of the present application provides a processing device for candidate association, including a memory, and one or more programs, where one or more programs are stored in a memory and configured to be Or the one or more processors executing the one or more programs include instructions for performing the following operations:

Determining a Lenovo intent for the content that has been on the screen;

In a fourth aspect, an embodiment of the present application provides a machine readable medium having stored thereon instructions that, when executed by one or more processors, cause a device to perform a candidate association method as in the first aspect.

It can be seen from the above technical solution that, according to the content of the last screen, the on-screen content to be associated can be determined, and the association intention can largely reflect the actual input intention of the user for the content on the screen. The association intention of the content on the screen can be determined, and the content of the user may continue to be on the screen after the content of the screen is determined according to the association intention. Therefore, when the data corresponding to the association intention is acquired according to the keyword in the content of the upper screen, and the candidate corresponding to the content of the upper screen is associated according to the data, the candidate determined by the data conforms to the user input. The possibility of intention is large, the user's input convenience is improved, and the determined candidate does not need to be generated according to the user's historical input data, which improves the possibility and accuracy of the association candidate.

DRAWINGS

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings to be used in the embodiments or the prior art description will be briefly described below. Obviously, the drawings in the following description are only It is a certain embodiment of the present application, and other drawings can be obtained according to the drawings without any creative labor for those skilled in the art.

1 is a display interface of an on-screen content and a candidate on a mobile terminal device;

2 is a schematic flowchart of a candidate association method according to an embodiment of the present application;

FIG. 3a is a display interface of a candidate corresponding to the upper screen content provided by the embodiment of the present application;

FIG. 3b is a display interface of a candidate corresponding to the upper screen content provided by the embodiment of the present application;

4 is a schematic flowchart of a method for determining an intention determination condition according to an embodiment of the present application;

FIG. 5 is a schematic flowchart diagram of a candidate association method based on an intention sentence pattern according to an embodiment of the present application;

FIG. 6 is a candidate display interface corresponding to the content of the upper screen provided by the embodiment of the present application;

FIG. 7 is a structural diagram of a device of a candidate association device according to an embodiment of the present application;

FIG. 8 is a block diagram of an apparatus for candidate association according to an embodiment of the present application;

FIG. 9 is a block diagram of a server for candidate association according to an embodiment of the present application.

Detailed ways

Embodiments of the present application will be described below with reference to the accompanying drawings.

After displaying the content on the screen, the user often hopes that the input method can associate the candidate with the candidate that may be associated with the screened content, so as to directly select the content to be screened in the candidate, thereby improving the input efficiency of the user. .

The traditional association method can only use historical data as the basis for deciding which candidates, and can not and will not determine the association intention of the content on the screen. In other words, the traditional association method generally compares whether the content already on the screen exists. In the historical data, if the content of the upper screen exists in the historical data, it is possible to obtain the candidate corresponding to the content of the upper screen from the historical data. For example, when the historical data includes the "sogou input method" input by the user, it is possible to associate the "input method" when the content of the upper screen is "sogou". For content that has not been input by the user, the input method is difficult to give a candidate based on the association of the content on the screen, and the user can only input the content to be screened by the input method.

As an example, the historical data includes the "sogou input method", "sogou pinyin", "sogou browser" and "sogou search" that the user has input. If the content of the upper screen is "sogou", then it will be from history. The corresponding candidates are extracted from the data. Specifically, refer to FIG. 1. FIG. 1 is a display interface of the uploaded content and the candidate on the mobile terminal device. When the "search dog" is displayed in the upper screen area 102, wherein the "search dog" is the upper screen content 101, the candidate association 104 can be generated in the candidate display area 103 according to the historical data by using the conventional association method, wherein the candidate 104 can be Including "Input Method", "Pinyin", "Browser" and "Search", the candidate 104 must all come from historical data, and there will be no content that does not exist in the historical data, for example, when the historical data does not include " When you search for a dog map, the map will not be included in the candidate. If the content of the screen is "I am from Tsinghua University", since the content is not included in the historical data, it is difficult for the input method to give a candidate based on the association of the content on the screen. The user can only input the input method. Upper screen content.

For the problem that the association candidate is limited to the historical data, the embodiment of the present application provides a solution to the above-mentioned candidate association situation, so as to determine that the association intention of the already-on-screen content can be determined by the content of the upper screen, thereby determining In the candidate corresponding to the association intention, the candidate can be obtained without relying on the user's historical data, the user's input convenience can be improved, and the range of the association candidate can be increased.

Taking the scene of "I am here from Tsinghua University" input by the user on the screen as an example, the method of this embodiment can first determine the association intention of the content on the screen based on the content of the screen, and obtain the screen. The association intention of the content "I am here from Tsinghua University" may be the association intention of the location distance, and thus the character of the user may be determined according to the association's intention to enter the screen after "I am here from Tsinghua University". The type can be a character that includes distance information. Then, according to the keyword in "I am here from Tsinghua University", the data corresponding to the association intention is obtained. The keyword may be "Tsinghua University", and according to the data, it is associated with "I am from Tsinghua University". The candidate can represent the distance information between the "I" and "Tsinghua University" locations.

The input method mentioned in the embodiment of the present application may be an encoding method adopted for inputting various symbols into an electronic device such as a computer or a mobile phone, and the user may conveniently use the input method to conveniently use a character or a string required by the user. Enter the electronic device. It should be noted that the input method in the embodiment of the present application may include other Chinese input methods (such as pinyin input method, five-stroke input method, phonetic input method, etc.), and may also include input methods in other languages (such as Japanese language). The kana input method, the Korean input method, etc.) do not limit the language of the input method and the input method.

In the embodiment of the present application, the content of the last screen may be included in the content already on the screen. In the case that the content of the last screen is included in the content of the screen, the content of the screen may be the content input by the user through the input method and the content of the screen, or the content of the screen sent by the communication peer. It can also be the context content of the location where the cursor is located. The format of the content on the screen is not limited in the embodiment of the present application, and the format of the content on the screen may include: text, picture, voice, and the like.

If the content of the upper screen is input by the user through the input method and the content of the upper screen is selected, the content of the upper screen may include the last time the character of the upper screen is selected by the input method and the series of consecutive characters before the character of the upper screen is selected by the input method last time. A character, the continuation may mean that there are no symbols such as punctuation or spaces indicating discontinuity between characters. The determination of the content already on the screen will be described in detail later.

Lenovo's intent can reflect to some extent the user's actual input intent for the content on the screen. According to Lenovo's intention, it can reflect what type of content the user may continue to play after inputting the content on the screen. Take the content of the screen as "I am from Tsinghua University" as an example. Generally speaking, after inputting "I am from Tsinghua University", the content that needs to be input is used to indicate the content of the distance information, that is, the The upper screen content has an intent to calculate the distance. Therefore, based on the already-online content, it is possible to determine that the association intention is a association intention with respect to the position distance. Of course, the association intention may also be a association intention regarding a place or the like.

The candidate may be the content that the input method may continue to be on the screen after the content has been determined according to the association intention, that is, the content to be on the screen. The content to be on the screen may be a character string. For example, when the content of the screen is "I am from Tsinghua University," the candidate can be "500 meters." Since the language of the input method is not specifically limited in the embodiment of the present application, the language type corresponding to the candidate generated by the input method is not specifically limited.

Various non-limiting embodiments of the embodiments of the present application are described in detail below with reference to the accompanying drawings.

Referring to FIG. 2, FIG. 2 is a schematic flowchart diagram of a candidate association method according to an embodiment of the present application. The method may include the following steps:

S201. Determine the content of the upper screen to be associated, and the content of the last screen includes the content of the last screen.

Since there may be a lot of content on the screen, the content on the screen may all be used as the content already on the screen, or may be partially used as the content already on the screen. For the reasonable determination, it may be used as the content already on the screen. It includes the last time the screen was uploaded.

For example, if the content of the screen has been input by the user through the input method and the content of the upper screen is selected, the user can select a character string displayed on the screen by using an input method, and the character string may include one character or multiple characters. When the character string includes one character, the screened content is a character displayed on the screen; when the character string includes a plurality of characters, and all the characters in the character string are continuous, that is, The character string is a character, and does not include a symbol such as a punctuation. Then, the screened content is a character string displayed on the screen; when the character string includes a plurality of characters, and the character string includes punctuation And the like, then, the on-screen content is a series of consecutive characters including the character that selected the upper screen by the input method last time and the character that selected the upper screen by the input method last time.

For example, the input string has been selected to display the string displayed on the screen as "I am from Tsinghua University", where "Yes" is the last character selected by the input method on the screen, because "I am from Tsinghua University here. "The Chinese characters are continuous. Therefore, "I have a place from Tsinghua University" can be used as the content on the screen. The above-mentioned content on the screen is the string "I am here from Tsinghua University", including All the characters in "I am from Tsinghua University".

In another example, all the characters displayed on the screen have been selected by the input method as "the weather is very good today, I am on the way to Tsinghua University, I am from Tsinghua University", among them, "Yes" is the most recent input method. Choosing the characters on the screen, because "the weather is very good today, I am on the way to Tsinghua University, I have a lot of characters from Tsinghua University here, and there is a comma between the characters "good" and "I", in " There is a comma between "Up" and "I". In this case, select the last character that has been selected by the input method last time to select the upper screen characters "Yes" and "Yes" until the comma appears. The content of the above screen is "I am from Tsinghua University", and the content on the screen includes "The weather is very good today, I am on the way to Tsinghua University, I am from Tsinghua University" character.

In the embodiment of the present application, the screen can be regarded as a display screen of an electronic device such as a mobile terminal, and is a carrier for content display such as a character string, and the input method panel can also be displayed on the screen.

S202. Determine a association intention for the content that has been on the screen.

Based on the content of the screen already on, the association intention for the content of the screen can be determined. The association intention may reflect the content that the user may input after inputting the content on the screen, that is, the content to be on the screen.

Lenovo's intent can be a association intent with respect to positional distance. For example, the content on the screen is “I am from Tsinghua University.” In general, after the content has been uploaded, the next possible input is “Tsinghua University” and “I” when the screen is on the screen. The distance information between the locations, then the association intention determined according to the already-screened content is the associative intent regarding the location distance.

Lenovo's intent can be a Lenovo intent about the place. For example, the content of the screen has been "I am". In general, after the content has been uploaded, the next possible input content is the location of the "I" when the screen content has been screened, then, according to the above The association intention determined by the screen content is the association intention of the place.

In determining the association intention for the already-on-screen content, one implementation is to determine the association intention according to the intention determination condition, and the on-screen content has different associations when the upper screen content satisfies different intent determination conditions. intention. Specifically, the content of the upper screen is matched with the intention determination condition. If the content of the upper screen meets the intention determination condition, it may be determined that the content of the upper screen has a corresponding content corresponding to the intention determination condition. Lenovo's intentions. The intention judgment condition, and the correspondence relationship between the intention judgment condition and the association intention may be predetermined, different intention judgment conditions may correspond to different association intentions, and the same association intention may correspond to a plurality of intention judgment conditions. When the association is intended to be a association intention with respect to the positional distance, the intention determination condition determination method will be described in detail later.

It should be noted that the intent determination condition may include an intent keyword or an intent sentence pattern.

The intent keyword may be a text that reflects the user's next input intention. When the association intention is determined according to the intent keyword, the on-screen content may be matched with the intent keyword, for example, whether the in-the-top keyword or the text similar to the intent keyword is included in the upper screen content, if The screen content includes the intent keyword or a text similar to the intent keyword, and it may be determined that the uploaded content has a association intent corresponding to the intent keyword.

For example, the intent keyword includes "off" and "yes", and the intent keyword reflects that the user's next input intention is to input the text indicating the distance information, and the content of the screen has been "I am from Tsinghua University" and will be on the screen. The screen content is matched with the intent keyword. Since the on-screen content includes the intent keywords "off" and "yes", the on-screen content satisfies the intent keyword, and then the screened content can be determined to satisfy the The intention determination condition that the on-screen content has a association intention corresponding to the intent keyword, that is, the user next inputs a text intended to input distance information.

The intent sentence can be organized into a sentence according to a certain pattern to reflect the user's input intention. This mode is called an intent sentence. For example, "I am here from ..." is an intent sentence, where "..." can refer to a place, and the intention sentence adopts "I am here..... There is a "model" to reflect the user's input intent is to enter the distance information between the location of "I" and a certain location. Another example is "I am..." is an intent sentence, where "..." can refer to a place, and the intention sentence adopts "I am..." The pattern reflects the user's input intent is to enter the location where "I" is located. When the association intention is determined according to the intent sentence pattern, the content of the screen can be matched with the intention sentence pattern, for example, whether the sentence pattern of the screen content is consistent or similar to the intention sentence pattern, if they are consistent or similar, Determining that the on-screen content satisfies the intent sentence pattern, having a association intent corresponding to the intent sentence pattern.

For example, the intent sentence includes "I am here from ...", and the content on the screen is "I am from Tsinghua University", and the content of the screen has been matched with the intent sentence. The sentence form of the screen content is also "I am here from ...", consistent with the intent sentence pattern, then the already-on-screen content satisfies the intent sentence pattern, and has a Lenovo intent corresponding to the intent sentence pattern. .

S203. Acquire data corresponding to the association intention according to keywords in the already-screened content.

The keyword may be a text indicating an object of interest to the user in the already-screened content. Take the content of the screen as "I am here from Tsinghua University". The user's concern is "Tsinghua University". Then, "Tsinghua University" can be the content of the screen. "I have a place from Tsinghua University." Keywords.

When the association is intended to be a association intention with respect to a position distance, the keyword includes a first location, and the first location may identify location information of a location indicated by the keyword, for example, when the keyword is Tsinghua University, Then, the first position included in the keyword may be location information of Tsinghua University, such as GPS (Global Positioning System) coordinates. In this way, the first distance information between the first position and the second position may be determined according to the first position and the second position corresponding to when the upper screen content is on the screen, and the first distance information is used as the Data corresponding to the associative intent of the positional distance. The second location may be a location where the user is located when the user has put the upper screen content on the screen through the character input device.

It should be noted that, when determining data corresponding to the association intent of the location distance, the first distance information between the first location and the second location may be calculated according to the third-party data interface, where the third-party data interface may be, for example, a map. interface. Specifically, when the upper screen content is on the screen, the position of the user when the upper screen content is on the screen can be obtained by using the GPS, that is, the second position corresponding to the upper screen content when the screen is on the screen. When the input method determines that the association intention of the content of the upper screen is a association intention with respect to the position distance, the input method may determine that the first position identifying the position indicated by the keyword is determined according to the keyword in the content of the upper screen, and according to The first location and the second location corresponding to when the upper screen content is on the screen, the first distance information between the first location and the second location is obtained from the map interface as a association intention with the location distance Corresponding data.

Taking the content of the screen as "I am from Tsinghua University" as an example, when the upper screen content is on the screen, the GPS module can obtain the position where the user is located when the upper screen content is on the screen as the second position. If the input method determines that the association intention of the content on the screen is the association intention of the position distance, the input method can determine "Tsinghua University" as the keyword indicating the first position from "I am from Tsinghua University", and automatically based on "Tsinghua University" and the location where the user has been on the screen when the screen is on the screen, and obtain the first distance information between the location of the user and the location where the user has been on the screen when the screen content is on the screen interface. The data corresponding to the association intent of the position distance.

The first distance information may be expressed in the form of a distance, for example, “500 meters”; or may be expressed in a time form, for example, “a distance of 5 minutes”.

S204. Associate a candidate corresponding to the uploaded content according to the data.

In the embodiment of the present application, the data may be directly used as a candidate corresponding to the content already on the screen. If the first distance information is data corresponding to the association intention with respect to the position distance, the input method may use the first distance information as a candidate corresponding to the already-screened content. It is also possible to process the data to obtain candidates corresponding to the content of the upper screen.

Continue to use the above-mentioned content on the screen as "I am from Tsinghua University". Lenovo intends to use the association intention of the location distance as an example. The input method obtains the position between the user of Tsinghua University and the user who has already screened the screen. The distance of the first distance information is 500 meters, and "500 meters" can be used as a candidate corresponding to the content already on the screen.

Wherein, the first distance information is represented by a distance form such as “500 meters”, and may also be expressed in a time form, for example “5 minutes distance”, then “5 minutes distance” may be used as the above-mentioned screen The candidate corresponding to the content. Of course, it is also possible to use "500 meters" and "5 minutes of distance" as candidates for the above-mentioned upper screen content, so that the user can select the upper screen. FIG. 3a shows a display interface of candidates corresponding to the content of the upper screen in the embodiment.

In Figure 3a, "I am from Tsinghua University" is the on-screen content 301, corresponding to 101 in Figure 1, "500 meters" and "5 minutes of distance" are candidates 302, corresponding to Figure 1 104.

It can be seen from the above technical solution that, according to the content of the last screen, the on-screen content to be associated can be determined, and the Lenovo's intention can largely reflect the user's actual input intention for the already-screened content. If the association intention of the content on the screen is determined, the content of the user may continue to be uploaded after the content of the screen is determined according to the association intention. Therefore, when the data corresponding to the association intention is acquired according to the keyword in the content of the upper screen, and the candidate corresponding to the content of the upper screen is associated according to the data, the candidate determined by the data conforms to the user input. The possibility of intention is large, the user's input convenience is improved, and the determined candidate does not need to be generated according to the user's historical input data, which improves the possibility of the association candidate.

It can be understood that, when the input method displays the candidate, the candidate may include, according to the data obtained by S204, the candidate corresponding to the uploaded content according to the data, and may also include the traditional method. Alternatively, the candidate candidates obtained by S204 associating the candidate corresponding to the uploaded content according to the data as the input candidate may be displayed before other candidates.

That is to say, in addition to the two candidates including "500 meters" and "5 minutes of distance", the candidate 302 in FIG. 3a may include other candidates obtained by a conventional method, such as other candidates, for example, A candidate generated based on the history of the previous screen content. For example, the history has been on the screen as "I am far away from Tsinghua University", then the history has been on the screen as "I am far away from Tsinghua University" can generate candidates "very far away" , the candidate display interface is shown in Figure 3b.

In Figure 3b, "I am from Tsinghua University" is the on-screen content 301, corresponding to 101 in Figure 1, "500 meters", "5 minutes away" and "very far away" as candidates 302 , corresponding to 104 in FIG. Among them, the candidates "500 meters" and "5 minutes of distance" are generated according to the method of the present embodiment, and the candidate "far away distance" is generated according to the conventional method.

Since the input method can determine the association intention according to the intention judgment condition, the on-screen content may have different associative intentions when the upper screen content satisfies different intent determination conditions. Therefore, the input method may first determine the intention determination condition, so that when the association intention for the already-screened content is determined, the already-screened content may be matched with the intention determination condition, thereby determining the content for the already-on-screen content according to the matching situation. Lenovo's intentions.

The manner in which the intent determination condition is determined will be described in detail below with reference to the accompanying drawings in the case where Lenovo intends to associate the intention with respect to the positional distance.

Referring to FIG. 4, FIG. 4 is a schematic flowchart diagram of a method for determining an intent determination condition, where the method includes:

S401. Acquire a history of the on-screen content including the location information and the distance information.

In the embodiment of the present application, when determining the intent determination condition, the input data may include, according to the input data of the user, the user has selected the upper screen content of the upper screen through the input method, that is, the history has been on the screen. Since the embodiment of the present application mainly determines the association intention with respect to the position distance, the history has already included information related to the position distance, such as location information and distance information, wherein the location information may refer to a clear location. Character content, such as "Tsinghua University", "Sogou headquarters" and so on. The distance information may be a character content indicating a distance, such as "500m", "10 minutes away", and the like.

The history of the on-screen content acquired in S401 may be one or more, wherein each history-on-screen content may include at least one type of information, and each of the at least one type of information may be location information, distance Information, time information, weather information, and more. Since the association in the present embodiment is intended to be a association intention with respect to the positional distance, in order to obtain an intention determination condition that can determine the association intention, the history regarding the positional distance can be obtained from the history of the upper screen content. The content, that is, the history of the acquired screen content may be the history of the screen content including the location information and the distance information.

For example, history has been screened including: "I am 500 meters away from Tsinghua University", "I am 5 minutes away from Peking University", "Tsinghua University's teaching building is 50 meters high", "now Beijing time 5 o'clock, from the above history, the content of the screen has been selected to include the location information and distance information. The history of the screen has been: "I am 500 meters away from Tsinghua University", "I am 5 minutes away from Peking University." “Tour distance” and “Tsinghua University’s teaching building is 50 meters high”.

The history-over screen content including the location information and the distance information may be obtained through S401, but there may be a case where the history has been on the screen content although the location information and the distance information are included, but the history has been on the screen content and about The associative intent of the positional distance may not be relevant, in which case the historically screened content that is not related to the associative intent of the positional distance may be eliminated to obtain an intent judgment condition regarding the associative intention of the positional distance, thereby Improve the accuracy of the intent to judge the condition of the association intention of the position distance. For the culling method, refer to S402-S403.

For example, the history of the location information and the distance information has been on the screen. The height of the teaching building of Tsinghua University is 50 meters. The height of the teaching building of Tsinghua University is 50 meters, although the location information "Tsinghua University" is included. "Teaching Building" and distance information "50 meters", but "Tsinghua University's teaching building height is 50 meters" just reflects the height of a building, and does not reflect the Lenovo's intention of the distance of location, that is, the history has been on the screen " The height of the teaching building of Tsinghua University is 50 meters. It is not related to the association intention of the distance of the position. It cannot be used to determine the intent judgment condition of the association intention of the position distance. Therefore, it needs to be obtained from S401 and includes the position information. And the history of distance information has been removed from the screen content.

S402. Determine second distance information according to the location information included in the history of the upper screen content and the location information corresponding to the history when the upper screen content is on the screen.

It can be understood that when the association is intended to be a association intention with respect to the position distance, the data corresponding to the association intention may be determined according to the first position and the second position corresponding to when the upper screen content is on the screen, so that the location information is included. And the history of the distance information has been related to the association intention of the on-screen content to be associated with the association, and correspondingly, the distance information including the position information and the distance information has been displayed in the upper screen content, and the content may be on the screen according to the history. The included location information and the location information corresponding to the history when the upper screen content is on the screen are determined. In other words, if the location information included in the upper screen content of the history and the location information corresponding to the screen when the history has been on the screen is determined, the second distance information is the same as the distance information included in the historical screen content. Or similar, then, it can be considered that the history of the on-screen content is related to the associative intention of the on-screen content to be associated, and the history of the on-screen content can be used as the basis for determining the intent judgment condition regarding the association intention of the position distance.

The second distance information may be in the form of a distance, such as "500 meters", or may be in the form of time, such as "5 minutes of travel."

S403. If the second distance information and the distance information included in the history of the on-screen content meet the preset threshold, determine an intent determination condition for the association intention of the position distance according to the history of the upper screen content. .

In this embodiment, in order to determine whether the second distance information and the distance information included in the history of the upper screen content are the same or similar, the threshold value may be implemented by using a preset threshold. The preset threshold may be manually set.

If the second distance information and the distance information included in the history of the upper screen content meet the preset threshold, the second distance information may be considered to be relatively close to the distance information included in the historical screen content. The history-over-screen content can determine an intent judgment condition for the association intention regarding the position distance. The satisfying the preset threshold may be, for example, that the second distance information is within 10% of the distance information included in the historical screen content. If the second distance information and the distance information included in the historical screen content do not satisfy the preset threshold, the second distance information may be considered to be different from the distance information included in the historical screen content. The history-over-screen content cannot determine the intent determination condition for the association intention of the location distance, and the history-over-screen content may be excluded from the history-over-screen content acquired by S401.

For example, the history has been on the screen as “the height of the teaching building of Tsinghua University is 50 meters”, and the preset threshold is 10%. The location information is “Tsinghua University” and the distance information is “50 meters”. The second distance information is determined according to the position information corresponding to the location information "Tsinghua University" and "the height of the teaching building of Tsinghua University is 50 meters", and the second distance information is 500 meters. At this time, the second distance information "500" "M" is different from the distance information "50 meters" by more than 10%. It can be considered that the second distance information is different from the distance information included in the history of the upper screen content, and the content of the screen cannot be determined according to the history. The intent determination condition regarding the association intention of the position distance may be removed from the historical on-screen content including the position information and the distance information.

For another example, the history has been screened as “I am 500 meters away from Tsinghua University” and the default threshold is 10%. The location information is “Tsinghua University” and the distance information is “500 meters”. The second distance information is determined according to the location information corresponding to the location information "Tsinghua University" and "I am 500 meters away from Tsinghua University", and the second distance information is 500 meters. At this time, the second distance information is "500 meters. The same as the distance information "500 meters", that is, within 10% of the difference, it can be considered that the intention determination condition for the associative intention regarding the position distance can be determined based on the history of the upper screen content.

In this embodiment, after the historical on-screen content related to the association intention regarding the position distance is determined from the history-over-screen content including the position information and the distance information, the history-on-screen content may be processed. , to obtain an intent judgment condition regarding the association intention of the position distance.

Therefore, after the history-on-screen content is obtained, the location information and the distance information included in the history-on-screen content may be removed, and then the intent keyword or the identifier may be determined according to the remaining characters in the history-upper screen content. An intent sentence pattern, and the intent keyword or the intent sentence sentence is used as an intent judgment condition for the associative intention regarding the position distance, for determining a association intention for the already-screened content.

It should be noted that, after the location information and the distance information included in the history of the upper screen content are removed, the intent keyword may include some of the remaining characters. For example, the history has been screened as "I am 500 meters away from Tsinghua University", in which the location information is "Tsinghua University" and the distance information is "500 meters". After removing the location information and the distance information included in the history of the upper screen content, the remaining characters "I am away from here" are obtained, wherein "off" and "yes" can be used as intent keywords for determining that the above is on The association intent of the screen content.

It should be noted that, in order to determine the intent sentence pattern, the location information included in the content of the upper screen may be replaced by replacing the location information with a common symbol, thereby obtaining an intended sentence pattern, for example, the general symbol may be "###", "..." and other symbols.

According to the above history, the content of the screen is "I am 500 meters away from Tsinghua University". According to this method, after removing the location information and distance information included in the history of the screen, I get "I am here ###有有" Forming an intent sentence for determining a association intent for the content that has been on the screen.

In the following, the intent judgment condition is an intentional sentence formula, and the intention sentence sentence includes "I am here from ###有", and the association intention corresponding to the intention sentence pattern is a association intention regarding the position distance, and the content of the upper screen is "I am here from the Sohu Network Building" as an example, how to use the intentional sentence to determine the candidate. Among them, the location information is "Sohu Network Building".

Referring to FIG. 5, FIG. 5 is a schematic flowchart diagram of a candidate association method based on an intentional sentence pattern, where the method includes:

S501. Determine that the content on the screen is "I am from the Sohu Network Building."

S502, processing the content of the screen "I am away from Sohu Network Building", and obtaining the sentence pattern corresponding to the content of the upper screen.

For example, the location information “Sohu Network Building” in the content of the upper screen can be replaced by a universal symbol, and the universal symbol can be “###”, for example, so that “I am away from ###” corresponding to the content of the upper screen. There are "sentences."

S503. Match a sentence pattern corresponding to the content of the upper screen to the intent sentence pattern, and if the sentence pattern corresponding to the content of the upper screen satisfies the intention sentence pattern, determine that the content of the upper screen has the meaning sentence corresponding to The stated intent of the association.

By matching the sentence pattern corresponding to the content of the upper screen with the intention sentence pattern, it is known that the sentence pattern corresponding to the content of the upper screen happens to be the sentence pattern "I am here from ###有" which appears in the aforementioned intention sentence pattern. According to this, it is determined that the association content of the content of the screen "I am from the Sohu Network Building" is the association intention of the position distance, that is, the content that needs to select the upper screen is the content including the location distance association intention.

S504. The input method may obtain the “Sohu Network Building” and the second location by using a map interface according to a keyword “Sohu Network Building” in the content of the upper screen and a second position corresponding to when the upper screen content is on the screen. One distance information is 850 meters and 10 minutes away.

The second position corresponding to the upper screen content on the screen may be the location of the user when the upper screen content is on the screen.

For example, the map interface is 850 meters away from the "Sohu Network Building" and the second location, and the map interface determines that the "Sohu Network Building" is 10 minutes away from the second location, then the first distance Information can be 850 meters and 10 minutes away.

S505. The first distance information is 850 meters and 10 minutes as the candidate for "I am from Sohu Network Building".

According to S501-S505, the candidate for "I have a place from Sohu.com" is 850 meters and 10 minutes. The candidate display interface can be as shown in Figure 6.

In Figure 6, "I am from Sohu Network Building" is the upper screen content 601, corresponding to 101 in Figure 1, "850 meters" and "10 minutes of distance" as candidate 602, corresponding to Figure 1 104.

It can be seen from the above technical solution that, according to the content of the last screen, the on-screen content to be associated can be determined, and the association intention can largely reflect the actual input intention of the user for the content on the screen. The association intention of the content on the screen can be determined, and the character type of the user may continue to be on the screen after the content of the screen has been determined according to the association intention. Therefore, when the data corresponding to the association intention is acquired according to the keyword in the content of the upper screen, and the candidate corresponding to the content of the upper screen is associated according to the data, the candidate determined by the data conforms to the user input. The possibility of intention is large, the user's input convenience is improved, and the determined candidate does not need to be generated according to the user's historical input data, which improves the possibility of the association candidate.

FIG. 7 is a candidate association device according to an embodiment of the present disclosure. The device includes a first determining module 701, a second determining module 702, a first obtaining module 703, and a Lenovo module 704:

The first determining module 701 is configured to determine the content of the upper screen to be associated, and the content of the last screen includes the content of the last screen;

The second determining module 702 is configured to determine a Lenovo intent for the content that has been on the screen;

The first obtaining module 703 is configured to acquire data corresponding to the association intention according to keywords in the uploaded content;

The association module 704 is configured to associate a candidate corresponding to the uploaded content according to the data.

Optionally, the second determining module includes: a matching module and a first determining module:

The matching module is configured to match the content of the screen that has been on the screen with the intention determination condition;

The first determining module is configured to determine that the uploaded content has the association intent corresponding to the intent determination condition, if the uploaded content satisfies the intent determination condition.

Optionally, the intent judgment condition includes an intent keyword or an intent sentence pattern.

Optionally, the association intention includes a association intent regarding the location distance.

Optionally, the keyword includes a first location, and the first acquiring module is further configured to determine the first location according to the first location and a second location corresponding to when the upper screen content is on the screen The first distance information between the second positions, and the first distance information is used as the data corresponding to the association intention of the position distance.

Optionally, the Lenovo module is further configured to use the first distance information as a candidate corresponding to the screened content.

Optionally, the association is intended to include a association intention with respect to a location distance, and the apparatus further includes: a second acquisition module, a third determination module, and a fourth determination module:

The second acquiring module is configured to acquire historical on-screen content including location information and distance information;

The third determining module is configured to determine the second distance information according to the location information included in the history of the upper screen content and the location information corresponding to the history when the upper screen content is on the screen;

The fourth determining module is configured to: if the second distance information and the distance information included in the history of the on-screen content meet the preset threshold, determine, according to the history, the content of the upper screen, The intent of the association's intention to judge the condition.

Optionally, the fourth determining module includes: a removing module and a second determining module:

The removing module is configured to remove location information and distance information included in the historical screen content;

The second determining module is configured to determine an intent keyword or an intended sentence according to the remaining characters in the history of the upper screen content, and use the intent keyword or the intention sentence as the target distance The intention of the association's intention to judge the condition.

FIG. 8 is a block diagram of an apparatus 800 for speech synthesis, according to an exemplary embodiment. For example, device 800 can be a robot, a mobile phone, a computer, a digital broadcast terminal, a messaging device, a gaming console, a tablet device, a medical device, a fitness device, a personal digital assistant, and the like.

Referring to Figure 8, device 800 can include one or more of the following components: processing component 802, memory 804, power component 806, multimedia component 808, audio component 810, input/output (I/O) interface 812, sensor component 814, And a communication component 816.

Processing component 802 typically controls the overall operation of device 800, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. Processing component 802 can include one or more processors 820 to execute instructions to perform all or part of the steps of the above described methods. Moreover, processing component 802 can include one or more modules to facilitate interaction between component 802 and other components. For example, processing component 802 can include a multimedia module to facilitate interaction between multimedia component 808 and processing component 802.

Memory 804 is configured to store various types of data to support operation at device 800. Examples of such data include instructions for any application or method operating on device 800, contact data, phone book data, messages, pictures, videos, and the like. The memory 804 can be implemented by any type of volatile or non-volatile storage device, or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read only memory (EEPROM), erasable. Programmable Read Only Memory (EPROM), Programmable Read Only Memory (PROM), Read Only Memory (ROM), Magnetic Memory, Flash Memory, Disk or Optical Disk.

Power component 806 provides power to various components of device 800. Power component 806 can include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power for device 800.

The multimedia component 808 includes a screen between the device 800 and the user that provides an output interface. In some embodiments, the screen can include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen can be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, slides, and gestures on the touch panel. The touch sensor may sense not only the boundary of the touch or sliding action, but also the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 808 includes a front camera and/or a rear camera. When the device 800 is in an operation mode, such as a shooting mode or a video mode, the front camera and/or the rear camera can receive external multimedia data. Each front and rear camera can be a fixed optical lens system or have focal length and optical zoom capabilities.

The audio component 810 is configured to output and/or input an audio signal. For example, the audio component 810 includes a microphone (MIC) that is configured to receive an external audio signal when the device 800 is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signal may be further stored in memory 804 or transmitted via communication component 816. In some embodiments, the audio component 810 also includes a speaker for outputting an audio signal.

The I/O interface 812 provides an interface between the processing component 802 and the peripheral interface module, which may be a keyboard, a click wheel, a button, or the like. These buttons may include, but are not limited to, a home button, a volume button, a start button, and a lock button.

Sensor assembly 814 includes one or more sensors for providing device 800 with a status assessment of various aspects. For example, sensor assembly 814 can detect an open/closed state of device 800, relative positioning of components, such as the display and keypad of device 800, and sensor component 814 can also detect a change in position of one component of device 800 or device 800. The presence or absence of user contact with device 800, device 800 orientation or acceleration/deceleration, and temperature variation of device 800. Sensor assembly 814 can include a proximity sensor configured to detect the presence of nearby objects without any physical contact. Sensor assembly 814 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 814 can also include an acceleration sensor, a gyro sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

Communication component 816 is configured to facilitate wired or wireless communication between device 800 and other devices. The device 800 can access a wireless network based on a communication standard, such as WiFi, 2G or 8G, or a combination thereof. In an exemplary embodiment, communication component 816 receives broadcast signals or broadcast associated information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 816 also includes a near field communication (NFC) module to facilitate short range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

In an exemplary embodiment, device 800 may be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable A gate array (FPGA), controller, microcontroller, microprocessor, or other electronic component implementation for performing the above methods.

In an exemplary embodiment, there is also provided a non-transitory computer readable storage medium comprising instructions, such as a memory 804 comprising instructions executable by processor 820 of apparatus 800 to perform the above method. For example, the non-transitory computer readable storage medium may be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, and an optical data storage device.

A non-transitory computer readable storage medium, when instructions in the storage medium are executed by a processor of a mobile terminal, enabling the mobile terminal to perform a candidate association method, the method comprising: determining that the association to be associated The upper screen content, the content of the last screen includes the content of the last screen; determining the association intention for the content of the screen; and obtaining the correspondence corresponding to the association intention according to the keyword in the screen content Data; based on the data, a candidate corresponding to the already-online content is associated.

9 is a schematic structural diagram of a server in some embodiments of the present application. The server 900 can vary considerably depending on configuration or performance, and can include one or more central processing units (CPUs) 922 (eg, one or more processors) and memory 932, one or one The storage medium 930 storing the application 942 or the data 944 (for example, one or one storage device in Shanghai). Among them, the memory 932 and the storage medium 930 may be short-term storage or persistent storage. The program stored on storage medium 930 may include one or more modules (not shown), each of which may include a series of instruction operations in the server. Still further, central processor 922 can be configured to communicate with storage medium 930, executing a series of instruction operations in storage medium 930 on server 900.

Server 900 may also include one or more power supplies 924, one or more wired or wireless network interfaces 950, one or more input and output interfaces 958, one or more keyboards 954, and/or one or more operating systems 941. For example, Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, etc.

It is to be noted that the various embodiments in the present specification are described in a progressive manner, and the same similar parts between the various embodiments may be referred to each other, and each embodiment focuses on different embodiments from other embodiments. At the office. In particular, for the device and the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the description of the method embodiment. The apparatus and system embodiments described above are merely illustrative, wherein the units illustrated as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, ie may be located A place, or it can be distributed to multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the embodiment. Those of ordinary skill in the art can understand and implement without any creative effort.

The foregoing is only one specific embodiment of the present application, but the scope of protection of the present application is not limited thereto, and any person skilled in the art can easily think of changes or within the technical scope disclosed in the present application. Replacement should be covered by the scope of this application. Therefore, the scope of protection of the present application should be determined by the scope of protection of the claims.

Claims

A candidate association method, characterized in that the method comprises:

Determining the on-screen content to be associated, the content of the last screen includes the content of the last screen;

Determining a Lenovo intent for the content that has been on the screen;

Acquiring data corresponding to the association intention according to keywords in the already-screened content;

Based on the data, a candidate corresponding to the already-online content is associated.
The method according to claim 1, wherein said determining a association intention for said on-screen content comprises:

Matching the already-screened content with the intent determination condition;

And if the content of the on-screen content satisfies the intention determination condition, determining that the content of the upper screen has the association intention corresponding to the intention determination condition.
The method of claim 2, wherein the intent determination condition comprises an intent keyword or an intent sentence pattern.
The method according to any one of claims 1 to 3, characterized in that the associative intent comprises a association intent with respect to a positional distance.
The method according to claim 4, wherein the keyword includes a first location, and the acquiring data corresponding to the association intent according to a keyword in the uploaded content includes:

Determining first distance information between the first location and the second location according to the first location and a second location corresponding to when the upper screen content is on the screen, and using the first distance information as a location The data corresponding to the associative intent of the positional distance is described.
The method according to claim 5, wherein the associating the candidate corresponding to the uploaded content according to the data comprises:

The first distance information is used as a candidate corresponding to the already-screened content.
The method of claim 2, wherein the associative intent comprises a association intent with respect to a location distance, the method further comprising:

Obtaining the history of the screen that includes location information and distance information;

Determining the second distance information according to the location information included in the history of the upper screen content and the location information corresponding to the history when the upper screen content is on the screen;

And if the distance information included in the second distance information and the history-over screen content meets a preset threshold, determining an intent determination condition for the association intention regarding the position distance according to the history-over screen content.
The method according to claim 7, wherein the determining the intent determination condition for the association intention regarding the position distance according to the history of the on-screen content comprises:

Removing location information and distance information included in the history of the upper screen content;

The intent keyword or the intention sentence pattern is determined based on the remaining characters in the history of the upper screen content, and the intention keyword or the intention sentence sentence is used as an intention judgment condition for the associative intention regarding the position distance.
A candidate association device, characterized in that the device comprises a first determining module, a second determining module, a first obtaining module and a Lenovo module:

The first determining module is configured to determine the content of the upper screen to be associated, and the content of the last screen includes the content of the last screen;

The second determining module is configured to determine a Lenovo intent for the content that has been on the screen;

The first obtaining module is configured to acquire data corresponding to the association intention according to a keyword in the screened content;

The association module is configured to associate a candidate corresponding to the uploaded content according to the data.
The apparatus according to claim 9, wherein the second determining module comprises: a matching module and a first determining module:

The matching module is configured to match the content of the screen that has been on the screen with the intention determination condition;

The first determining module is configured to determine that the uploaded content has the association intent corresponding to the intent determination condition, if the uploaded content satisfies the intent determination condition.
The apparatus according to claim 10, wherein said intention determination condition comprises an intention keyword or an intention sentence pattern.
Apparatus according to any of claims 9-11, wherein the association intent comprises a association intent with respect to the location distance.
The device according to claim 12, wherein the keyword includes a first location, and the first obtaining module is further configured to: according to the first location and the corresponding content when the screen content is on the screen The second position determines first distance information between the first position and the second position, and uses the first distance information as data corresponding to the association intention with respect to the position distance.
The device according to claim 13, wherein the association module is further configured to use the first distance information as a candidate corresponding to the screened content.
The apparatus according to claim 10, wherein the association intention comprises a association intention with respect to a position distance, the apparatus further comprising: a second acquisition module, a third determination module, and a fourth determination module:

The second acquiring module is configured to acquire historical on-screen content including location information and distance information;

The third determining module is configured to determine the second distance information according to the location information included in the history of the upper screen content and the location information corresponding to the history when the upper screen content is on the screen;

The fourth determining module is configured to: if the second distance information and the distance information included in the history of the on-screen content meet the preset threshold, determine, according to the history, the content of the upper screen, The intent of the association's intention to judge the condition.
The apparatus according to claim 15, wherein the fourth determining module comprises: a removing module and a second determining module:

The removing module is configured to remove location information and distance information included in the historical screen content;

The second determining module is configured to determine an intent keyword or an intended sentence according to the remaining characters in the history of the upper screen content, and use the intent keyword or the intention sentence as the target distance The intention of the association's intention to judge the condition.
A processing device for candidate associations, comprising: a memory, and one or more programs, wherein one or more programs are stored in the memory and configured to be executed by one or more processors The one or more programs include instructions for performing the following operations:

Determining the on-screen content to be associated, the content of the last screen includes the content of the last screen;

Determining a Lenovo intent for the content that has been on the screen;

Acquiring data corresponding to the association intention according to keywords in the already-screened content;

Based on the data, a candidate corresponding to the already-online content is associated.
A machine readable medium having stored thereon instructions that, when executed by one or more processors, cause a device to perform the candidate association method of one or more of claims 1-8.