CN109325178A - Method and apparatus for handling information - Google Patents
Method and apparatus for handling information Download PDFInfo
- Publication number
- CN109325178A CN109325178A CN201811075460.5A CN201811075460A CN109325178A CN 109325178 A CN109325178 A CN 109325178A CN 201811075460 A CN201811075460 A CN 201811075460A CN 109325178 A CN109325178 A CN 109325178A
- Authority
- CN
- China
- Prior art keywords
- word
- candidate
- degree
- prompt word
- search
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the present application discloses the method and apparatus for handling information.One specific embodiment of this method includes: to obtain desired title text collection, wherein, desired title text corresponds to text message, and desired title text is clicked after inputting search term for user, text message corresponding to clicked desired title text to be presented to user；For the desired title text in desired title text collection, it is based on the desired title text, generates the candidate prompt word for prompting user to search for；It chooses for rendering from candidate prompt word generated to the target prompting word of user.The embodiment enriches the mode of information search, improves the diversity of information processing.
Description
Technical field
The invention relates to field of computer technology, more particularly, to handle the method and apparatus of information.
Background technique
Currently, with the development of science and technology, people can be used the electronic equipments such as mobile phone, computer carry out information search
Rope obtains search result.In general, people can input searching for search in search engine or the search box of application software
Rope word, to carry out information search.Wherein, search term can be vocabulary, phrase or sentence etc..
Summary of the invention
The embodiment of the present application proposes the method and apparatus for handling information.
In a first aspect, the embodiment of the present application provides a kind of method for handling information, this method comprises: obtaining target
Title text set, wherein desired title text corresponds to text message, and desired title text is for point after user's input search term
It hits, text message corresponding to clicked desired title text to be presented to user；For in desired title text collection
Desired title text is based on the desired title text, generates the candidate prompt word for prompting user to search for；From time generated
It selects and is chosen in prompt word for rendering to the target prompting word of user.
In some embodiments, it is based on the desired title text, generates the candidate prompt word for prompting user to search for, packet
Include: the prompt word that the desired title text input is trained in advance generates model, generates result prompt word；Based on knot generated
Fruit prompt word generates the candidate prompt word for prompting user to search for.
In some embodiments, it is based on result prompt word generated, generates the candidate prompt for prompting user to search for
Word, comprising: obtain historical search word corresponding to the desired title text in default historical time section；For history obtained
Historical search word in search term determines the similarity of the historical search word Yu result prompt word generated, wherein similarity
For the numerical value for characterizing the similarity degree between historical search word and result prompt word；It extracts similarity and is more than or equal to default threshold
The historical search word of value is as the candidate prompt word for prompting user to search for.
In some embodiments, it is based on the desired title text, generates the candidate prompt word for prompting user to search for, packet
It includes: the desired title text is segmented, obtain word segmentation result；Based on word segmentation result obtained, generate for prompting to use
The candidate prompt word of family search.
In some embodiments, it is based on word segmentation result obtained, generates the candidate prompt word for prompting user to search for,
It include: that the part of speech of the vocabulary is determined for the vocabulary in word segmentation result obtained；Really based on word segmentation result obtained and institute
Fixed part of speech generates the candidate prompt word for prompting user to search for.
In some embodiments, it is based on word segmentation result obtained, generates the candidate prompt word for prompting user to search for,
It include: that the vocabulary in word segmentation result obtained is determined in word segmentation result obtained, the different degree of the vocabulary,
In, different degree is the numerical value for characterizing the significance level of vocabulary；Based on word segmentation result obtained and identified different degree,
Generate the candidate prompt word for prompting user to search for.
In some embodiments, it is based on the desired title text, generates the candidate prompt word for prompting user to search for, packet
It includes: based on the desired title text, generating the initial candidate prompt word for prompting user to search for；To initial candidate generated
Prompt word is filtered, to remove the vocabulary for meeting preset condition in initial candidate prompt word；Filtered initial candidate is mentioned
Show that word is determined as candidate search word.
In some embodiments, the target prompting word to user for rendering is chosen from candidate prompt word generated,
Include: to be ranked up to candidate prompt word generated, obtains candidate prompt word sequence；From candidate prompt word sequence obtained
The target prompting word of user is given in middle selection for rendering.
In some embodiments, candidate prompt word generated is ranked up, obtains candidate prompt word sequence, comprising:
For the candidate prompt word in candidate prompt word generated, executes the following step that scores: determining candidate's prompt word and the time
Select the degree of correlation of desired title text corresponding to prompt word, wherein the degree of correlation is for characterizing candidate prompt word and target mark
Inscribe the numerical value of the degree of correlation of text；Based on the identified degree of correlation, the superiority and inferiority degree for characterizing candidate's prompt word is determined
Score value；Based on identified score value, candidate prompt word obtained is ranked up, obtains candidate prompt word sequence.
In some embodiments, based on the identified degree of correlation, the superiority and inferiority journey for characterizing candidate's prompt word is determined
Before the score value of degree, score step further include: determines the language fluency degree of candidate's prompt word, wherein language fluency degree is to use
In the numerical value for the language fluency degree for characterizing candidate prompt word；And it based on the identified degree of correlation, determines for characterizing the time
Select the score value of the superiority and inferiority degree of prompt word, comprising: based on the identified degree of correlation and language fluency degree, determine for characterizing the time
Select the score value of the superiority and inferiority degree of prompt word.
Second aspect, the embodiment of the present application provide it is a kind of for handling the device of information, the device include: obtain it is single
Member is configured to obtain desired title text collection, wherein desired title text corresponds to text message, and desired title text is used
It is clicked after user inputs search term, text message corresponding to clicked desired title text to be presented to user；It generates
Unit is configured to be based on the desired title text for the desired title text in desired title text collection, and generation is used for
Prompt the candidate prompt word of user's search；Selection unit is configured to choose for rendering from candidate prompt word generated
To the target prompting word of user.
In some embodiments, generation unit includes: the first generation module, is configured to the desired title text input
Trained prompt word generates model in advance, generates result prompt word；Second generation module is configured to based on result generated
Prompt word generates the candidate prompt word for prompting user to search for.
In some embodiments, generation unit includes: acquisition module, is configured to obtain the mesh in default historical time section
Mark historical search word corresponding to title text；First determining module is configured in historical search word obtained
Historical search word determines the similarity of the historical search word Yu result prompt word generated, wherein similarity is for characterizing
The numerical value of similarity degree between historical search word and result prompt word；Extraction module, be configured to extract similarity be greater than etc.
In preset threshold historical search word as prompt user search for candidate prompt word.
In some embodiments, generation unit includes: word segmentation module, is configured to divide the desired title text
Word obtains word segmentation result；Third generation module is configured to generate based on word segmentation result obtained for prompting user to search
The candidate prompt word of rope.
In some embodiments, third generation module is further configured to: for the word in word segmentation result obtained
It converges, determines the part of speech of the vocabulary；Based on word segmentation result obtained and identified part of speech, generate for prompting user to search for
Candidate prompt word.
In some embodiments, third generation module is further configured to: for the word in word segmentation result obtained
It converges, determines the different degree of the vocabulary in word segmentation result obtained, wherein different degree is the important journey for characterizing vocabulary
The numerical value of degree；Based on word segmentation result obtained and identified different degree, the candidate prompt for prompting user to search for is generated
Word.
In some embodiments, generation unit includes: the 4th generation module, is configured to based on the desired title text,
Generate the initial candidate prompt word for prompting user to search for；Filtering module is configured to prompt initial candidate generated
Word is filtered, to remove the vocabulary for meeting preset condition in initial candidate prompt word；Second determining module is configured to mistake
Initial candidate prompt word after filter is determined as candidate search word.
In some embodiments, selection unit includes: sorting module, is configured to carry out candidate prompt word generated
Sequence obtains candidate prompt word sequence；Module is chosen, is configured to choose from candidate prompt word sequence obtained for being in
Now give the target prompting word of user.
In some embodiments, sorting module is further configured to: for the candidate in candidate prompt word generated
Prompt word executes the following step that scores: determining desired title text corresponding to candidate's prompt word and candidate's prompt word
The degree of correlation, wherein the degree of correlation is the numerical value for characterizing the degree of correlation of candidate prompt word and desired title text；Based on really
The fixed degree of correlation determines the score value for characterizing the superiority and inferiority degree of candidate's prompt word；Based on identified score value, to being obtained
Candidate prompt word be ranked up, obtain candidate prompt word sequence.
In some embodiments, based on the identified degree of correlation, the superiority and inferiority journey for characterizing candidate's prompt word is determined
Before the score value of degree, score step further include: determines the language fluency degree of candidate's prompt word, wherein language fluency degree is to use
In the numerical value for the language fluency degree for characterizing candidate prompt word；And it based on the identified degree of correlation, determines for characterizing the time
Select the score value of the superiority and inferiority degree of prompt word, comprising: based on the identified degree of correlation and language fluency degree, determine for characterizing the time
Select the score value of the superiority and inferiority degree of prompt word.
The third aspect, the embodiment of the present application provide a kind of electronic equipment, comprising: one or more processors；Storage dress
Set, be stored thereon with one or more programs, when one or more programs are executed by one or more processors so that one or
The method that multiple processors realize any embodiment in the above-mentioned method for handling information.
Fourth aspect, the embodiment of the present application provide a kind of computer-readable medium, are stored thereon with computer program, should
The method of any embodiment in the above-mentioned method for handling information is realized when program is executed by processor.
Method and apparatus provided by the embodiments of the present application for handling information, by obtaining desired title text collection,
Wherein, desired title text corresponds to text message, and desired title text is clicked after inputting search term for user, to be in user
Text message corresponding to existing clicked desired title text, then for the desired title text in desired title text collection
This, is based on the desired title text, generates the candidate prompt word for prompting user to search for, finally from candidate prompt generated
It chooses in word for rendering to the target prompting word of user, is generated for rendering to efficiently use desired title text collection
User can be prompted to search for target prompting word before user's input search term scans for this to the target prompting word of user
Indicated content enriches the mode of information search, improves the diversity of information processing.
Detailed description of the invention
By reading a detailed description of non-restrictive embodiments in the light of the attached drawings below, the application's is other
Feature, objects and advantages will become more apparent upon:
Fig. 1 is that one embodiment of the application can be applied to exemplary system architecture figure therein；
Fig. 2 is the flow chart according to one embodiment of the method for handling information of the application；
Fig. 3 is the schematic diagram according to an application scenarios of the method for handling information of the embodiment of the present application；
Fig. 4 is the flow chart according to another embodiment of the method for handling information of the application；
Fig. 5 is the structural schematic diagram according to one embodiment of the device for handling information of the application；
Fig. 6 is adapted for the structural schematic diagram for the computer system for realizing the electronic equipment of the embodiment of the present application.
Specific embodiment
The application is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining related invention, rather than the restriction to the invention.It also should be noted that in order to
Convenient for description, part relevant to related invention is illustrated only in attached drawing.
It should be noted that in the absence of conflict, the features in the embodiments and the embodiments of the present application can phase
Mutually combination.The application is described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
Fig. 1 is shown can be using the method for handling information of the application or the implementation of the device for handling information
The exemplary system architecture 100 of example.
As shown in Figure 1, system architecture 100 may include terminal device 101,102,103, network 104 and server 105.
Network 104 between terminal device 101,102,103 and server 105 to provide the medium of communication link.Network 104 can be with
Including various connection types, such as wired, wireless communication link or fiber optic cables etc..
User can be used terminal device 101,102,103 and be interacted by network 104 with server 105, to receive or send out
Send message etc..Various telecommunication customer end applications can be installed, such as web browser is answered on terminal device 101,102,103
With, shopping class application, searching class application, instant messaging tools, mailbox client, social platform software etc..
Terminal device 101,102,103 can be hardware, be also possible to software.When terminal device 101,102,103 is hard
When part, it can be the various electronic equipments with display screen and supported web page browsing, including but not limited to smart phone, plate
Computer, E-book reader, MP3 player (Moving Picture Experts Group Audio Layer III, dynamic
Image expert's compression standard audio level 3), MP4 (Moving Picture Experts Group Audio Layer IV, move
State image expert's compression standard audio level 4) player, pocket computer on knee and desktop computer etc..When terminal is set
Standby 101,102,103 when being software, may be mounted in above-mentioned cited electronic equipment.Its may be implemented into multiple softwares or
Software module (such as providing multiple softwares of Distributed Services or software module), also may be implemented into single software or soft
Part module.It is not specifically limited herein.
Server 105 can be to provide the server of various services, such as to the mesh that terminal device 101,102,103 is sent
The netscape messaging server Netscape that mark title text set is handled.Netscape messaging server Netscape can be to the desired title text received
The data such as this set carry out the processing such as analyzing, and obtain processing result (such as target prompting word).
It should be noted that the method provided by the embodiment of the present application for handling information can be held by server 105
Row, can also be executed by terminal device 101,102,103；Correspondingly, it can be set for handling the device of information in server
In 105, also it can be set in terminal device 101,102,103.
It should be noted that server can be hardware, it is also possible to software.When server is hardware, may be implemented
At the distributed server cluster that multiple servers form, individual server also may be implemented into.It, can when server is software
It, can also be with to be implemented as multiple softwares or software module (such as providing multiple softwares of Distributed Services or software module)
It is implemented as single software or software module.It is not specifically limited herein.
It should be understood that the number of terminal device, network and server in Fig. 1 is only schematical.According to realization need
It wants, can have any number of terminal device, network and server.In desired title text collection or generate target prompting
Used data do not need in the case where long-range obtain during word, and above system framework can not include network, and
Only include terminal device or server.
With continued reference to Fig. 2, the process of one embodiment of the method for handling information according to the application is shown
200.The method for being used to handle information, comprising the following steps:
Step 201, desired title text collection is obtained.
In the present embodiment, can lead to for handling the executing subject (such as server shown in FIG. 1) of the method for information
Cross wired connection mode or radio connection from local or communicate connection electronic equipment it is (such as shown in FIG. 1
Terminal device) obtain desired title text collection.Wherein, desired title text is for being handled it to obtain target and mention
Show the title text of word.Target prompting word is vocabulary, phrase or the sentence for prompting user to search for.Desired title text pair
It is clicked after answering text message, desired title text to input search term for user, clicked desired title to be presented to user
Text message corresponding to text.Desired title text is used to describe the content of corresponding text message.Search term is user
Vocabulary, phrase or sentence input, for search.
In practice, a large amount of text message can store in above-mentioned executing subject or above-mentioned electronic equipment.And text message
Corresponding title text can predefine.In addition, title text can correspond to clicking rate.Clicking rate is in preset time period
Probability interior, that title text is clicked.In turn, optionally, above-mentioned executing subject can be according to clicking rate, from predetermined mark
It inscribes and obtains title text in text collection as desired title text.Specifically, above-mentioned executing subject can be from title text collection
Corresponding clicking rate is obtained in conjunction is more than or equal to the title text of preset threshold as desired title text；Alternatively, above-mentioned hold
Row main body can be descending according to corresponding clicking rate sequence, from title text set obtain preset quantity title
Text is as preset quantity desired title text.
Step 202, for the desired title text in desired title text collection, it is based on the desired title text, is generated
Candidate prompt word for prompting user to search for.
In the present embodiment, above-mentioned for the desired title text in desired title text collection obtained in step 201
Executing subject can be based on the desired title text, generate the candidate prompt word for prompting user to search for using various methods.
Wherein, candidate prompt word can be used for generating target prompting word, can be vocabulary, phrase or sentence, for example, phrase " today
Weather ".
In some optional implementations of the present embodiment, for the desired title text in desired title text collection
This, above-mentioned executing subject can be based on the desired title text, generate the candidate for prompting user to search for by following steps
Prompt word: firstly, above-mentioned executing subject can segment the desired title text, word segmentation result is obtained.Then, above-mentioned to hold
Row main body can be based on word segmentation result obtained, generate the candidate prompt word for prompting user to search for.
Wherein, word segmentation result includes the vocabulary that participle obtains.Specifically, as an example, word segmentation result can be to segment
Sequence of words composed by the vocabulary arrived.Vocabulary in sequence of words can be suitable according to the arrangement of the vocabulary in desired title text
Sequence arrangement.
Specifically, above-mentioned executing subject can segment the desired title text using various methods, segmented
As a result.For example, using maximum forward matching algorithm, maximum reverse matching algorithm etc. based on dictionary, to the desired title text
It is segmented, obtains word segmentation result.
It should be noted that segmentation methods are the well-known techniques studied and applied extensively at present, details are not described herein again.
In this implementation, above-mentioned executing subject can be based on word segmentation result obtained, be generated using various methods
Candidate prompt word for prompting user to search for.
In some optional implementations of the present embodiment, above-mentioned executing subject can be tied based on participle obtained
Fruit generates the candidate prompt word for prompting user to search for by following steps: firstly, in word segmentation result obtained
Vocabulary, above-mentioned executing subject can determine the part of speech of the vocabulary.Then, above-mentioned executing subject can be tied based on participle obtained
Fruit and identified part of speech generate the candidate prompt word for prompting user to search for.For example, above-mentioned executing subject can be from being obtained
In vocabulary included by the word segmentation result obtained, obtains the vocabulary that part of speech is noun and prompted as the candidate for prompting user to search for
Word；Alternatively, above-mentioned executing subject can obtain the vocabulary that part of speech is noun from vocabulary included by word segmentation result obtained
It is the vocabulary of verb with part of speech, and forms phrase using acquired noun and verb, using composed phrase as being used to mention
Show the candidate prompt word of user's search.
It should be noted that the method for determining the part of speech of vocabulary is the well-known technique studied and applied extensively at present, herein
It repeats no more.
In some optional implementations of the present embodiment, it is based on word segmentation result obtained, above-mentioned executing subject is also
The candidate prompt word for prompting user to search for can be generated by following steps: firstly, in word segmentation result obtained
Vocabulary, above-mentioned executing subject can determine in word segmentation result obtained, the different degree of the vocabulary, wherein different degree is
For characterizing the numerical value of the significance level of vocabulary.Then, above-mentioned executing subject can be true based on word segmentation result obtained and institute
Fixed different degree generates the candidate prompt word for prompting user to search for.
Herein, for the vocabulary in word segmentation result obtained, above-mentioned executing subject can be determined using various methods
In word segmentation result obtained, the different degree of the vocabulary.For example, above-mentioned executing subject can obtain pre-set text collection first
It closes.Wherein, pre-set text is the text of the default different degree collecting, for determining vocabulary of technical staff.Then, for being obtained
The vocabulary in word segmentation result obtained, above-mentioned executing subject can determine the number that the vocabulary occurs in pre-set text set, and
Identified number is determined as to the different degree of the vocabulary；Alternatively, technical staff can pre-establish the important of vocabulary and vocabulary
The mapping table of degree, and then above-mentioned executing subject can determine the different degree of the vocabulary by searching for above-mentioned mapping table.
In this implementation, above-mentioned executing subject can be based on word segmentation result obtained and institute really using various methods
Fixed different degree generates the candidate prompt word for prompting user to search for.Specifically, as an example, above-mentioned executing subject can be with
From vocabulary included by word segmentation result obtained, the vocabulary that corresponding different degree is more than or equal to preset threshold is obtained, benefit
Candidate prompt word is formed with acquired vocabulary；Alternatively, above-mentioned executing subject can be descending according to different degree sequence, from
Preset quantity vocabulary is obtained in vocabulary included by word segmentation result obtained, utilizes acquired preset quantity vocabulary group
At candidate prompt word.
In some optional implementations of the present embodiment, for the desired title text in desired title text collection
This, above-mentioned executing subject is also based on the desired title text, generates the time for prompting user to search for by following steps
Select prompt word: firstly, above-mentioned executing subject can generate the initial time for prompting user to search for based on the desired title text
Select prompt word.Then, above-mentioned executing subject can be filtered initial candidate prompt word generated, to remove initial candidate
Meet the vocabulary of preset condition in prompt word.Finally, above-mentioned executing subject can determine filtered initial candidate prompt word
For candidate search word.
Herein, above-mentioned executing subject can generate initial wait using the above-mentioned various methods for generating candidate prompt word
Prompt word is selected, details are not described herein again.
Preset condition can be the predetermined condition of technical staff, such as vocabulary belongs to preset bad lexical set,
Or vocabulary is name entity.Wherein, bad vocabulary is the vocabulary for being unfavorable for display that technical staff specifies.Name entity refers to
It is name, mechanism name, place name and other all entities with entitled mark.Herein, entity refers to vocabulary.
In this implementation, above-mentioned executing subject can be proposed initial candidate using various methods according to preset condition
Show that word is filtered.For example, above-mentioned preset condition is " vocabulary belongs to preset bad lexical set ", then above-mentioned executing subject can
To be matched to initial candidate prompt word and bad lexical set, whether to determine in initial candidate prompt word including bad word
It converges；If including bad vocabulary included by initial candidate prompt word being removed, to realize the mistake to initial candidate prompt word
Filter.
Step 203, it chooses for rendering from candidate prompt word generated to the target prompting word of user.
In the present embodiment, based on candidate's prompt word obtained in step 202, above-mentioned executing subject can be from generated
It is chosen in candidate prompt word for rendering to the target prompting word of user.
Herein, above-mentioned executing subject can be chosen for rendering from candidate prompt word generated using various methods
To the target prompting word of user.For example, being chosen for rendering using the method randomly selected to the target prompting word of user.
In some optional implementations of the present embodiment, above-mentioned executing subject can be by following steps from being generated
Candidate prompt word in choose for rendering give user target prompting word: firstly, above-mentioned executing subject can be to generated
Candidate prompt word is ranked up, and obtains candidate prompt word sequence.Then, above-mentioned executing subject can be from candidate prompt obtained
It is chosen in word sequence for rendering to the target prompting word of user.
Herein, above-mentioned executing subject can be ranked up candidate prompt word generated using various methods, obtain
Candidate's prompt word sequence.
In some optional implementations of the present embodiment, for the candidate prompt in candidate prompt word generated
Word, above-mentioned executing subject can execute following scoring step:
Step 2031, the degree of correlation of desired title text corresponding to candidate's prompt word and candidate's prompt word is determined.
Wherein, the degree of correlation is the numerical value for characterizing the degree of correlation of candidate prompt word and desired title text.Numerical value is got over
Greatly, degree of correlation can be higher.
Specifically, above-mentioned executing subject can determine the degree of correlation using various methods.For example, above-mentioned executing subject can be right
Desired title text corresponding to candidate prompt word and candidate's prompt word carries out similarity calculation, and calculated result is determined as
The degree of correlation of desired title text corresponding to candidate's prompt word and candidate's prompt word；Alternatively, technical staff can be preparatory
First degree of correlation for characterizing high degree of correlation and second degree of correlation for characterizing low degree of correlation are set.In turn,
The method that above-mentioned executing subject can be primarily based on part-of-speech tagging determines the noun in desired title text.Then, above-mentioned to hold
Row main body can determine whether candidate's prompt word includes noun in desired title text；If including related by above-mentioned first
Degree is determined as the degree of correlation of desired title text corresponding to candidate's prompt word and candidate's prompt word；It, will be upper if not including
State the degree of correlation that second degree of correlation is determined as desired title text corresponding to candidate's prompt word and candidate's prompt word.
It should be noted that similarity calculating method and part-of-speech tagging method are the known skills studied and applied extensively at present
Art, details are not described herein again.
In some optional implementations of the present embodiment, above-mentioned executing subject can also determine candidate's prompt word
Language fluency degree.Wherein, language fluency degree is the numerical value for characterizing the language fluency degree of candidate prompt word.Numerical value is bigger,
Language fluency degree can be higher.
As an example, language fluency degree corresponding to candidate prompt word " today, weather was very good " can be 10；Candidate's prompt
Language fluency degree corresponding to word " weather very good today " can be 8.The language stream of i.e. candidate prompt word " today, weather was very good "
Smooth degree is higher than candidate prompt word " weather very good today ".
In this implementation, above-mentioned executing subject can use language fluency degree model trained in advance and determine the candidate
The language fluency degree of prompt word.Specifically, candidate's prompt word can be inputted above-mentioned language fluency degree mould by above-mentioned executing subject
Type obtains the language fluency degree of candidate's prompt word.Wherein, language fluency degree model can be for based on language model
(Language Modeling, LM) or neural network (Neural Network, NN) training obtain, for characterizing text
With the model of the corresponding relationship of the language fluency degree of text.
It should be noted that the method that training obtains language fluency degree model is the known skill of extensive research and application at present
Art, details are not described herein again.
Step 2032, based on the identified degree of correlation, the score value for characterizing the superiority and inferiority degree of candidate's prompt word is determined.
Herein, the identified degree of correlation can directly be determined as being used to characterize candidate's prompt word by above-mentioned executing subject
Superiority and inferiority degree score value, the degree of correlation can also be handled, obtain processing result, and then processing result is determined as being used for
Characterize the score value of the superiority and inferiority degree of candidate's prompt word.As an example, can to the degree of correlation obtained and default value (such as
100) quadrature processing is carried out, and quadrature processing result is determined as to be used to characterize the score value of the superiority and inferiority degree of candidate's prompt word.
In some optional implementations of the present embodiment, when the language fluency for determining candidate's prompt word is spent,
Above-mentioned executing subject is also based on the identified degree of correlation and language fluency degree, determines for characterizing the excellent of candidate's prompt word
The score value of bad degree.
Specifically, above-mentioned executing subject can use various methods, based on the identified degree of correlation and language fluency degree, really
Determine the score value for characterizing the superiority and inferiority degree of candidate's prompt word.For example, can be directly to the identified degree of correlation and language stream
Smooth degree is summed, and summed result is determined as to be used to characterize the score value of the superiority and inferiority degree of candidate's prompt word；Alternatively, above-mentioned
The available technical staff of executing subject is the weight of the degree of correlation and the distribution of language fluency degree in advance, and to the degree of correlation and language stream
Smooth degree is weighted summation, obtains weighted sum value, and then be determined as weighted sum value obtained to be used to characterize the candidate
The score value of the superiority and inferiority degree of prompt word.
As an example, it is 0.7 that technical staff, which is previously determined weight corresponding to the degree of correlation, corresponding to language fluency degree
Weight is 0.3.Above-mentioned executing subject determine candidate prompt word " neural network " and desired title text " neural network is shallowly said:
From neuron to deep learning " the degree of correlation be 9；The language fluency degree of candidate prompt word " neural network " is 10.It is then above-mentioned to hold
Row main body can be based on predetermined weight " 0.7 " and " 0.3 ", be weighted to the degree of correlation " 9 " and language fluency degree " 10 "
Summation, obtain weighted sum value " 9.3 " (9.3=0.7 × 9+0.3 × 10), in turn, above-mentioned executing subject can will determined by
Weighted sum value " 9.3 " is determined as the score value of the superiority and inferiority degree for characterizing candidate prompt word " neural network ".
Step 2033, based on identified score value, candidate prompt word obtained is ranked up, candidate prompt word is obtained
Sequence.
Specifically, above-mentioned executing subject can (descending sequence be ascending according to the size order of score value
Sequence, candidate prompt word obtained is ranked up, candidate prompt word sequence is obtained.
With continued reference to the signal that Fig. 3, Fig. 3 are according to the application scenarios of the method for handling information of the present embodiment
Figure.In the application scenarios of Fig. 3, the desired title text collection of the transmission of terminal device 302 available first of server 301
303.Wherein, desired title text corresponds to text message, and desired title text is clicked after inputting search term for user, with to
Text message corresponding to clicked desired title text is presented in family, and here, desired title text collection includes desired title
Text (such as " neural network is from principle to realization ") 3031 and desired title text (such as " natural language general introduction ") 3032.So
Afterwards, for the desired title text 3031 in desired title text collection 303, it is based on the desired title text, server 301 can
To generate the candidate prompt word (such as " neural network ") 3041 for prompting user to search for.For desired title text collection
Desired title text 3032 in 303, is based on the desired title text, and server 301 can be generated for prompting user to search for
Candidate prompt word (such as " Language Overview ") 3042.Finally, server 301 can from candidate prompt word 3041 generated,
It is chosen in 3042 for rendering to the target prompting word 305 (such as " neural network ") of user.
The application method provided by the above embodiment effective use desired title text collection generate for rendering to
The target prompting word of user can prompt user to search for target prompting word institute with this before user's input search term scans for
The content of instruction enriches the mode of information search, improves the diversity of information processing.
With further reference to Fig. 4, it illustrates the processes 400 of another embodiment of the method for handling information.The use
In the process 400 of the method for processing information, comprising the following steps:
Step 401, desired title text collection is obtained.
In the present embodiment, can lead to for handling the executing subject (such as server shown in FIG. 1) of the method for information
Cross wired connection mode or radio connection from local or communicate connection electronic equipment it is (such as shown in FIG. 1
Terminal device) obtain desired title text collection.Wherein, desired title text is for being handled it to obtain target and mention
Show the title text of word.Target prompting word is vocabulary, phrase or the sentence for prompting user to search for.Desired title text pair
It is clicked after answering text message, desired title text to input search term for user, clicked desired title to be presented to user
Text message corresponding to text.Desired title text is used to describe the content of corresponding text message.Search term is user
Vocabulary, phrase or sentence input, for search.
Step 402, for the desired title text in desired title text collection, the desired title text input is preparatory
Trained prompt word generates model, generates result prompt word.
In the present embodiment, above-mentioned for the desired title text in desired title text collection obtained in step 401
The prompt word that the desired title text input is trained in advance can be generated model by executing subject, generate result prompt word.As a result
Prompt word is the output result that prompt word generates model.Prompt word generates model for characterizing title text and result prompt word
Corresponding relationship.Herein, prompt word generate model can be based on predetermined initial model (such as Seq2seq model,
Convolutional neural networks (Convolutional Neural Network, CNN) etc.) train obtained model.
Specifically, as an example, above-mentioned prompt word generation model can be obtained by following steps training:
Firstly, obtaining training sample set.Wherein, training sample includes sample titles text and sample results prompt word.
It should be noted that sample titles text can be pre-stored title text.Sample results prompt word can be with
To click the search term that the user of sample titles text is inputted.
It is then possible to using the sample titles text of training sample concentration as the input of predetermined initial model, it will
Sample results prompt word corresponding to the sample titles text inputted is right using the method for machine learning as desired output
Above-mentioned initial model is trained, and is obtained prompt word and is generated model.
Step 403, it is based on result prompt word generated, generates the candidate prompt word for prompting user to search for.
In the present embodiment, above-mentioned executing subject can use various methods, based on the result prompt generated in step 402
Word generates the candidate prompt word for prompting user to search for.For example, above-mentioned executing subject can be by result prompt word generated
It is determined directly as candidate prompt word.
In some optional implementations of the present embodiment, above-mentioned executing subject can be prompted based on result generated
Word generates the candidate prompt word for prompting user to search for by following steps:
Firstly, history corresponding to the desired title text is searched in the above-mentioned available default historical time section of executing subject
Rope word.Wherein, historical search word corresponding to the desired title text is in default historical time section, and user is clicking the mesh
Mark the search term inputted before title text.
Then, for the historical search word in historical search word obtained, above-mentioned executing subject can determine the history
The similarity of search term and result prompt word generated, wherein similarity is to prompt for characterizing historical search word and result
The numerical value of similarity degree between word.
It is used as more than or equal to the historical search word of preset threshold for mentioning finally, above-mentioned executing subject can extract similarity
Show the candidate prompt word of user's search.
In this implementation, it is mentioned using the historical search word that user inputs to determine that candidate can be improved in candidate prompt word
Show the language fluency degree of word.
Step 404, it chooses for rendering from candidate prompt word generated to the target prompting word of user.
In the present embodiment, based on candidate's prompt word obtained in step 403, above-mentioned executing subject can be from generated
It is chosen in candidate prompt word for rendering to the target prompting word of user.
Herein, above-mentioned executing subject can be chosen for rendering from candidate prompt word generated using various methods
To the target prompting word of user.For example, being chosen for rendering using the method randomly selected to the target prompting word of user.
Above-mentioned steps 401, step 404 are consistent with step 201, the step 203 in previous embodiment respectively, above with respect to step
Rapid 201 and the description of step 203 be also applied for step 401 and step 403, details are not described herein again.
Figure 4, it is seen that the method for handling information compared with the corresponding embodiment of Fig. 2, in the present embodiment
Process 400 highlight using prompt word generate model generate desired title text corresponding to candidate prompt word the step of.By
This, present embodiments provides another scheme for generating candidate prompt word, improves the diversity of information processing, and utilize prompt
Word generates model and generates candidate prompt word, and the accuracy of information processing can be improved.
With further reference to Fig. 5, as the realization to method shown in above-mentioned each figure, this application provides one kind for handling letter
One embodiment of the device of breath, the Installation practice is corresponding with embodiment of the method shown in Fig. 2, which can specifically answer
For in various electronic equipments.
As shown in figure 5, the present embodiment includes: acquiring unit 501, generation unit 502 for handling the device 500 of information
With selection unit 503.Wherein, acquiring unit 501 is configured to obtain desired title text collection, wherein desired title text
Corresponding text message, desired title text is clicked after inputting search term for user, clicked target mark to be presented to user
Inscribe text message corresponding to text；Generation unit 502 is configured to for the desired title text in desired title text collection
This, is based on the desired title text, generates the candidate prompt word for prompting user to search for；Selection unit 503 be configured to from
It chooses for rendering in candidate's prompt word generated to the target prompting word of user.
In the present embodiment, for handle information device 500 acquiring unit 501 can by wired connection mode or
Person's radio connection from local or communicate connection electronic equipment (such as terminal device shown in FIG. 1) obtain target
Title text set.Wherein, desired title text is for being handled it to obtain the title text of target prompting word.Mesh
Mark prompt word is vocabulary, phrase or the sentence for prompting user to search for.Desired title text corresponds to text message, target mark
Topic text is clicked after inputting search term for user, the letter of text corresponding to clicked desired title text to be presented to user
Breath.Desired title text is used to describe the content of corresponding text message.Search term is word that user inputs, for search
Remittance, phrase or sentence.
In the present embodiment, the desired title text in desired title text collection obtained for acquiring unit 501, it is raw
It can be based on the desired title text at unit 502, generate the candidate prompt word for prompting user to search for using various methods.
Wherein, candidate prompt word can be used for generating target prompting word, can be vocabulary, phrase or sentence, for example, phrase " today
Weather ".
In the present embodiment, the candidate prompt word obtained based on generation unit 502, selection unit 503 can be from being generated
Candidate prompt word in choose for rendering give user target prompting word.
Herein, selection unit 503 can be chosen for rendering from candidate prompt word generated using various methods
To the target prompting word of user.For example, being chosen for rendering using the method randomly selected to the target prompting word of user.
In some optional implementations of the present embodiment, generation unit 502 may include: the first generation module (figure
In be not shown), the prompt word that is configured in advance train the desired title text input generates model, generates result prompt
Word；Second generation module (not shown) is configured to generate based on result prompt word generated for prompting user to search
The candidate prompt word of rope.
In some optional implementations of the present embodiment, generation unit 502 may include: to obtain module (in figure not
Show), it is configured to obtain historical search word corresponding to the desired title text in default historical time section；First determines mould
Block (not shown) is configured to determine the historical search word for the historical search word in historical search word obtained
With the similarity of result prompt word generated, wherein similarity is for characterizing between historical search word and result prompt word
Similarity degree numerical value；Extraction module (not shown) is configured to extract similarity going through more than or equal to preset threshold
History search term is as the candidate prompt word for prompting user to search for.
In some optional implementations of the present embodiment, generation unit 502 may include: word segmentation module (in figure not
Show), it is configured to segment the desired title text, obtains word segmentation result；Third generation module (not shown),
It is configured to generate the candidate prompt word for prompting user to search for based on word segmentation result obtained.
In some optional implementations of the present embodiment, third generation module can be further configured to: for
Vocabulary in word segmentation result obtained determines the part of speech of the vocabulary；Based on word segmentation result obtained and identified part of speech,
Generate the candidate prompt word for prompting user to search for.
In some optional implementations of the present embodiment, third generation module can be further configured to: for
Vocabulary in word segmentation result obtained determines the different degree of the vocabulary, wherein different degree in word segmentation result obtained
For the numerical value of the significance level for characterizing vocabulary；Based on word segmentation result obtained and identified different degree, generation is used for
Prompt the candidate prompt word of user's search.
In some optional implementations of the present embodiment, generation unit 502 may include: the 4th generation module (figure
In be not shown), be configured to generate the initial candidate prompt word for prompting user to search for based on the desired title text；It crosses
Module (not shown) is filtered, is configured to be filtered initial candidate prompt word generated, be mentioned with removing initial candidate
Show the vocabulary for meeting preset condition in word；Second determining module (not shown) is configured to filtered initial candidate
Prompt word is determined as candidate search word.
In some optional implementations of the present embodiment, selection unit 503 may include: sorting module (in figure not
Show), it is configured to be ranked up candidate prompt word generated, obtains candidate prompt word sequence；Choose module (in figure not
Show), it is configured to choose for rendering from candidate prompt word sequence obtained to the target prompting word of user.
In some optional implementations of the present embodiment, sorting module can be further configured to: for giving birth to
At candidate prompt word in candidate prompt word, execute the following step that scores: determining candidate's prompt word and candidate's prompt word
The degree of correlation of corresponding desired title text, wherein the degree of correlation is for characterizing candidate prompt word and desired title text
The numerical value of degree of correlation；Based on the identified degree of correlation, the score value for characterizing the superiority and inferiority degree of candidate's prompt word is determined；Base
In identified score value, candidate prompt word obtained is ranked up, obtains candidate prompt word sequence.
In some optional implementations of the present embodiment, based on the identified degree of correlation, determine for characterizing this
Before the score value of the superiority and inferiority degree of candidate prompt word, scoring step can also comprise determining that the language fluency of candidate's prompt word
Degree, wherein language fluency degree is the numerical value for characterizing the language fluency degree of candidate prompt word；And based on identified phase
Guan Du determines the score value for characterizing the superiority and inferiority degree of candidate's prompt word, comprising: based on the identified degree of correlation and language stream
Smooth degree, determines the score value for characterizing the superiority and inferiority degree of candidate's prompt word.
It is understood that all units recorded in the device 500 and each step phase in the method with reference to Fig. 2 description
It is corresponding.As a result, above with respect to the operation of method description, the beneficial effect of feature and generation be equally applicable to device 500 and its
In include unit, details are not described herein.
The device provided by the above embodiment 500 of the application efficiently uses desired title text collection and generates for rendering
User can be prompted to search for target prompting word before user's input search term scans for this to the target prompting word of user
Indicated content enriches the mode of information search, improves the diversity of information processing.
Below with reference to Fig. 6, it is (such as shown in FIG. 1 that it illustrates the electronic equipments for being suitable for being used to realize the embodiment of the present application
Terminal device or server) computer system 600 structural schematic diagram.Electronic equipment shown in Fig. 6 is only an example,
Should not function to the embodiment of the present application and use scope bring any restrictions.
As shown in fig. 6, computer system 600 includes central processing unit (CPU) 601, it can be read-only according to being stored in
Program in memory (ROM) 602 or be loaded into the program in random access storage device (RAM) 603 from storage section 608 and
Execute various movements appropriate and processing.In RAM 603, also it is stored with system 600 and operates required various programs and data.
CPU 601, ROM 602 and RAM 603 are connected with each other by bus 604.Input/output (I/O) interface 605 is also connected to always
Line 604.
I/O interface 605 is connected to lower component: the importation 606 including keyboard, mouse etc.；It is penetrated including such as cathode
The output par, c 607 of spool (CRT), liquid crystal display (LCD) etc. and loudspeaker etc.；Storage section 608 including hard disk etc.；
And the communications portion 609 of the network interface card including LAN card, modem etc..Communications portion 609 via such as because
The network of spy's net executes communication process.Driver 610 is also connected to I/O interface 605 as needed.Detachable media 611, such as
Disk, CD, magneto-optic disk, semiconductor memory etc. are mounted on as needed on driver 610, in order to read from thereon
Computer program be mounted into storage section 608 as needed.
Particularly, in accordance with an embodiment of the present disclosure, it may be implemented as computer above with reference to the process of flow chart description
Software program.For example, embodiment of the disclosure includes a kind of computer program product comprising be carried on computer-readable medium
On computer program, which includes the program code for method shown in execution flow chart.In such reality
It applies in example, which can be downloaded and installed from network by communications portion 609, and/or from detachable media
611 are mounted.When the computer program is executed by central processing unit (CPU) 601, limited in execution the present processes
Above-mentioned function.It should be noted that computer-readable medium described herein can be computer-readable signal media or
Computer readable storage medium either the two any combination.Computer readable storage medium for example can be --- but
Be not limited to --- electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor system, device or device, or any above combination.
The more specific example of computer readable storage medium can include but is not limited to: have one or more conducting wires electrical connection,
Portable computer diskette, hard disk, random access storage device (RAM), read-only memory (ROM), erasable type may be programmed read-only deposit
Reservoir (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), light storage device, magnetic memory
Part or above-mentioned any appropriate combination.In this application, computer readable storage medium, which can be, any include or stores
The tangible medium of program, the program can be commanded execution system, device or device use or in connection.And
In the application, computer-readable signal media may include in a base band or the data as the propagation of carrier wave a part are believed
Number, wherein carrying computer-readable program code.The data-signal of this propagation can take various forms, including but not
It is limited to electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be computer
Any computer-readable medium other than readable storage medium storing program for executing, the computer-readable medium can send, propagate or transmit use
In by the use of instruction execution system, device or device or program in connection.Include on computer-readable medium
Program code can transmit with any suitable medium, including but not limited to: wireless, electric wire, optical cable, RF etc., Huo Zheshang
Any appropriate combination stated.
Flow chart and block diagram in attached drawing are illustrated according to the system of the various embodiments of the application, method and computer journey
The architecture, function and operation in the cards of sequence product.In this regard, each box in flowchart or block diagram can generation
A part of one module, program segment or code of table, a part of the module, program segment or code include one or more use
The executable instruction of the logic function as defined in realizing.It should also be noted that in some implementations as replacements, being marked in box
The function of note can also occur in a different order than that indicated in the drawings.For example, two boxes succeedingly indicated are actually
It can be basically executed in parallel, they can also be executed in the opposite order sometimes, and this depends on the function involved.Also it to infuse
Meaning, the combination of each box in block diagram and or flow chart and the box in block diagram and or flow chart can be with holding
The dedicated hardware based system of functions or operations as defined in row is realized, or can use specialized hardware and computer instruction
Combination realize.
Being described in unit involved in the embodiment of the present application can be realized by way of software, can also be by hard
The mode of part is realized.Described unit also can be set in the processor, for example, can be described as: a kind of processor packet
Include acquiring unit, generation unit and selection unit.Wherein, the title of these units is not constituted under certain conditions to the unit
The restriction of itself, for example, acquiring unit is also described as " obtaining the unit of desired title text collection ".
As on the other hand, present invention also provides a kind of computer-readable medium, which be can be
Included in electronic equipment described in above-described embodiment；It is also possible to individualism, and without in the supplying electronic equipment.
Above-mentioned computer-readable medium carries one or more program, when said one or multiple programs are held by the electronic equipment
When row, so that the electronic equipment: obtaining desired title text collection, wherein desired title text corresponds to text message, target mark
Topic text is clicked after inputting search term for user, the letter of text corresponding to clicked desired title text to be presented to user
Breath；For the desired title text in desired title text collection, it is based on the desired title text, is generated for prompting user to search
The candidate prompt word of rope；It chooses for rendering from candidate prompt word generated to the target prompting word of user.
Above description is only the preferred embodiment of the application and the explanation to institute's application technology principle.Those skilled in the art
Member is it should be appreciated that invention scope involved in the application, however it is not limited to technology made of the specific combination of above-mentioned technical characteristic
Scheme, while should also cover in the case where not departing from foregoing invention design, it is carried out by above-mentioned technical characteristic or its equivalent feature
Any combination and the other technical solutions formed.Such as features described above has similar function with (but being not limited to) disclosed herein
Can technical characteristic replaced mutually and the technical solution that is formed.
Claims (22)
1. a kind of method for handling information, comprising:
Obtain desired title text collection, wherein desired title text corresponds to text message, and desired title text is defeated for user
It is clicked after entering search term, text message corresponding to clicked desired title text to be presented to user；
For the desired title text in the desired title text collection, it is based on the desired title text, is generated for prompting
The candidate prompt word of user's search；
It chooses for rendering from candidate prompt word generated to the target prompting word of user.
2. according to the method described in claim 1, wherein, described to be based on the desired title text, generation is for prompting user to search
The candidate prompt word of rope, comprising:
The prompt word that the desired title text input is trained in advance generates model, generates result prompt word；
Based on result prompt word generated, the candidate prompt word for prompting user to search for is generated.
3. according to the method described in claim 2, wherein, described to be based on result prompt word generated, generation is used for prompting
The candidate prompt word of family search, comprising:
Obtain historical search word corresponding to the desired title text in default historical time section；
For the historical search word in historical search word obtained, the historical search word and result prompt word generated are determined
Similarity, wherein similarity is numerical value for characterizing the similarity degree between historical search word and result prompt word；
It extracts similarity and is more than or equal to the historical search word of preset threshold as the candidate prompt word for prompting user to search for.
4. according to the method described in claim 1, wherein, described to be based on the desired title text, generation is for prompting user to search
The candidate prompt word of rope, comprising:
The desired title text is segmented, word segmentation result is obtained；
Based on word segmentation result obtained, the candidate prompt word for prompting user to search for is generated.
5. according to the method described in claim 4, wherein, described to be based on word segmentation result obtained, generation is for prompting user
The candidate prompt word of search, comprising:
For the vocabulary in word segmentation result obtained, the part of speech of the vocabulary is determined；
Based on word segmentation result obtained and identified part of speech, the candidate prompt word for prompting user to search for is generated.
6. according to the method described in claim 4, wherein, described to be based on word segmentation result obtained, generation is for prompting user
The candidate prompt word of search, comprising:
For the vocabulary in word segmentation result obtained, determine in word segmentation result obtained, the different degree of the vocabulary,
In, different degree is the numerical value for characterizing the significance level of vocabulary；
Based on word segmentation result obtained and identified different degree, the candidate prompt word for prompting user to search for is generated.
7. according to the method described in claim 1, wherein, described to be based on the desired title text, generation is for prompting user to search
The candidate prompt word of rope, comprising:
Based on the desired title text, the initial candidate prompt word for prompting user to search for is generated；
Initial candidate prompt word generated is filtered, to remove the word for meeting preset condition in initial candidate prompt word
It converges；
Filtered initial candidate prompt word is determined as candidate search word.
8. method described in one of -7 according to claim 1, wherein described to choose from candidate prompt word generated for being in
Now give the target prompting word of user, comprising:
Candidate prompt word generated is ranked up, candidate prompt word sequence is obtained；
It chooses for rendering from candidate prompt word sequence obtained to the target prompting word of user.
9. according to the method described in claim 8, wherein, described to be ranked up to candidate prompt word generated, acquisition is candidate
Prompt word sequence, comprising:
For the candidate prompt word in candidate prompt word generated, execute the following step that scores: determine the candidate prompt word and
The degree of correlation of desired title text corresponding to candidate's prompt word, wherein the degree of correlation is for characterizing candidate prompt word and mesh
Mark the numerical value of the degree of correlation of title text；Based on the identified degree of correlation, the superiority and inferiority for characterizing candidate's prompt word is determined
The score value of degree；
Based on identified score value, candidate prompt word obtained is ranked up, obtains candidate prompt word sequence.
10. according to the method described in claim 9, wherein, described based on the identified degree of correlation, determining for characterizing the time
Before the score value of superiority and inferiority degree for selecting prompt word, the scoring step further include:
Determine the language fluency degree of candidate's prompt word, wherein language fluency degree is the language stream for characterizing candidate prompt word
The numerical value of smooth degree；And
It is described based on the identified degree of correlation, determine the score value for characterizing the superiority and inferiority degree of candidate's prompt word, comprising:
Based on the identified degree of correlation and language fluency degree, the score value for characterizing the superiority and inferiority degree of candidate's prompt word is determined.
11. a kind of for handling the device of information, comprising:
Acquiring unit is configured to obtain desired title text collection, wherein desired title text corresponds to text message, target
Title text is clicked after inputting search term for user, text corresponding to clicked desired title text to be presented to user
Information；
Generation unit is configured to be based on the desired title for the desired title text in the desired title text collection
Text generates the candidate prompt word for prompting user to search for；
Selection unit is configured to choose for rendering from candidate prompt word generated to the target prompting word of user.
12. device according to claim 11, wherein the generation unit includes:
First generation module, the prompt word for being configured in advance train the desired title text input generate model, generate knot
Fruit prompt word；
Second generation module is configured to be generated the candidate for prompting user to search for based on result prompt word generated and mentioned
Show word.
13. device according to claim 12, wherein the generation unit includes:
Module is obtained, is configured to obtain historical search word corresponding to the desired title text in default historical time section；
First determining module is configured to determine the historical search for the historical search word in historical search word obtained
The similarity of word and result prompt word generated, wherein similarity be for characterize historical search word and result prompt word it
Between similarity degree numerical value；
Extraction module, the historical search word for being configured to extract similarity more than or equal to preset threshold are used as prompting user to search
The candidate prompt word of rope.
14. device according to claim 11, wherein the generation unit includes:
Word segmentation module is configured to segment the desired title text, obtains word segmentation result；
Third generation module is configured to generate the candidate prompt for prompting user to search for based on word segmentation result obtained
Word.
15. device according to claim 14, wherein the third generation module is further configured to:
For the vocabulary in word segmentation result obtained, the part of speech of the vocabulary is determined；
Based on word segmentation result obtained and identified part of speech, the candidate prompt word for prompting user to search for is generated.
16. device according to claim 14, wherein the third generation module is further configured to:
For the vocabulary in word segmentation result obtained, determine in word segmentation result obtained, the different degree of the vocabulary,
In, different degree is the numerical value for characterizing the significance level of vocabulary；
Based on word segmentation result obtained and identified different degree, the candidate prompt word for prompting user to search for is generated.
17. device according to claim 11, wherein the generation unit includes:
4th generation module is configured to be generated the initial candidate for prompting user to search for based on the desired title text and mentioned
Show word；
Filtering module is configured to be filtered initial candidate prompt word generated, to remove in initial candidate prompt word
Meet the vocabulary of preset condition；
Second determining module is configured to filtered initial candidate prompt word being determined as candidate search word.
18. device described in one of 1-17 according to claim 1, wherein the selection unit includes:
Sorting module is configured to be ranked up candidate prompt word generated, obtains candidate prompt word sequence；
Module is chosen, is configured to choose for rendering from candidate prompt word sequence obtained to the target prompting of user
Word.
19. device according to claim 18, wherein the sorting module is further configured to:
For the candidate prompt word in candidate prompt word generated, execute the following step that scores: determine the candidate prompt word and
The degree of correlation of desired title text corresponding to candidate's prompt word, wherein the degree of correlation is for characterizing candidate prompt word and mesh
Mark the numerical value of the degree of correlation of title text；Based on the identified degree of correlation, the superiority and inferiority for characterizing candidate's prompt word is determined
The score value of degree；
Based on identified score value, candidate prompt word obtained is ranked up, obtains candidate prompt word sequence.
20. device according to claim 19, wherein described based on the identified degree of correlation, determine for characterizing this
Before the score value of the superiority and inferiority degree of candidate prompt word, the scoring step further include:
Determine the language fluency degree of candidate's prompt word, wherein language fluency degree is the language stream for characterizing candidate prompt word
The numerical value of smooth degree；And
It is described based on the identified degree of correlation, determine the score value for characterizing the superiority and inferiority degree of candidate's prompt word, comprising:
Based on the identified degree of correlation and language fluency degree, the score value for characterizing the superiority and inferiority degree of candidate's prompt word is determined.
21. a kind of electronic equipment, comprising:
One or more processors；
Storage device is stored thereon with one or more programs,
When one or more of programs are executed by one or more of processors, so that one or more of processors are real
The now method as described in any in claim 1-10.
22. a kind of computer-readable medium, is stored thereon with computer program, wherein the realization when program is executed by processor
Method as described in any in claim 1-10.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811075460.5A CN109325178A (en) | 2018-09-14 | 2018-09-14 | Method and apparatus for handling information |
| PCT/CN2018/115954 WO2020052061A1 (en) | 2018-09-14 | 2018-11-16 | Method and device for processing information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811075460.5A CN109325178A (en) | 2018-09-14 | 2018-09-14 | Method and apparatus for handling information |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109325178A true CN109325178A (en) | 2019-02-12 |
Family
ID=65265345
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811075460.5A Pending CN109325178A (en) | 2018-09-14 | 2018-09-14 | Method and apparatus for handling information |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN109325178A (en) |
| WO (1) | WO2020052061A1 (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111339399A (en) * | 2020-01-20 | 2020-06-26 | 腾讯科技（深圳）有限公司 | Object processing method, object processing apparatus, object processing device, and medium |
| CN111783395A (en) * | 2020-04-17 | 2020-10-16 | 北京沃东天骏信息技术有限公司 | Method and device for outputting text |
| CN112434127A (en) * | 2020-11-03 | 2021-03-02 | 咪咕文化科技有限公司 | Text information searching method, text information searching equipment and readable storage medium |
| CN112579875A (en) * | 2019-09-29 | 2021-03-30 | 百度在线网络技术（北京）有限公司 | Method, device, equipment and medium for generating release information title |
| CN113392265A (en) * | 2021-02-05 | 2021-09-14 | 腾讯科技（深圳）有限公司 | Multimedia processing method, device and equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102929925A (en) * | 2012-09-20 | 2013-02-13 | 百度在线网络技术（北京）有限公司 | Search method and device based on browsing content |
| CN105095440A (en) * | 2015-07-23 | 2015-11-25 | 百度在线网络技术（北京）有限公司 | Search recommendation method and device |
| CN107220386A (en) * | 2017-06-29 | 2017-09-29 | 北京百度网讯科技有限公司 | Information-pushing method and device |
| CN108241667A (en) * | 2016-12-26 | 2018-07-03 | 百度在线网络技术（北京）有限公司 | For the method and apparatus of pushed information |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107544982B (en) * | 2016-06-24 | 2022-12-02 | 中兴通讯股份有限公司 | Text information processing method and device and terminal |
| CN106970910B (en) * | 2017-03-31 | 2020-03-27 | 北京奇艺世纪科技有限公司 | Keyword extraction method and device based on graph model |
-
2018
- 2018-09-14 CN CN201811075460.5A patent/CN109325178A/en active Pending
- 2018-11-16 WO PCT/CN2018/115954 patent/WO2020052061A1/en active Application Filing
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102929925A (en) * | 2012-09-20 | 2013-02-13 | 百度在线网络技术（北京）有限公司 | Search method and device based on browsing content |
| CN105095440A (en) * | 2015-07-23 | 2015-11-25 | 百度在线网络技术（北京）有限公司 | Search recommendation method and device |
| CN108241667A (en) * | 2016-12-26 | 2018-07-03 | 百度在线网络技术（北京）有限公司 | For the method and apparatus of pushed information |
| CN107220386A (en) * | 2017-06-29 | 2017-09-29 | 北京百度网讯科技有限公司 | Information-pushing method and device |
Non-Patent Citations (1)
| Title |
|---|
| 最高人民法院知识产权审判庭编: "《中国知识产权指导案例评注 中国法院知识产权司法保护10大案件、10大创新性案件和50件典型案例全文及评述 第6辑》", 31 May 2015 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112579875A (en) * | 2019-09-29 | 2021-03-30 | 百度在线网络技术（北京）有限公司 | Method, device, equipment and medium for generating release information title |
| CN111339399A (en) * | 2020-01-20 | 2020-06-26 | 腾讯科技（深圳）有限公司 | Object processing method, object processing apparatus, object processing device, and medium |
| CN111783395A (en) * | 2020-04-17 | 2020-10-16 | 北京沃东天骏信息技术有限公司 | Method and device for outputting text |
| CN111783395B (en) * | 2020-04-17 | 2023-12-08 | 北京沃东天骏信息技术有限公司 | Method and device for outputting text |
| CN112434127A (en) * | 2020-11-03 | 2021-03-02 | 咪咕文化科技有限公司 | Text information searching method, text information searching equipment and readable storage medium |
| CN112434127B (en) * | 2020-11-03 | 2023-10-17 | 咪咕文化科技有限公司 | Text information searching method, apparatus and readable storage medium |
| CN113392265A (en) * | 2021-02-05 | 2021-09-14 | 腾讯科技（深圳）有限公司 | Multimedia processing method, device and equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2020052061A1 (en) | 2020-03-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110287479B (en) | Named entity recognition method, electronic device and storage medium | |
| CN109325178A (en) | Method and apparatus for handling information | |
| CN111428010B (en) | Man-machine intelligent question-answering method and device | |
| CN107491547A (en) | Searching method and device based on artificial intelligence | |
| CN109460514A (en) | Method and apparatus for pushed information | |
| CN108121800A (en) | Information generating method and device based on artificial intelligence | |
| CN109190124B (en) | Method and apparatus for participle | |
| CN107679039A (en) | The method and apparatus being intended to for determining sentence | |
| CN109325148A (en) | The method and apparatus for generating information | |
| CN108388674A (en) | Method and apparatus for pushed information | |
| CN107273503A (en) | Method and apparatus for generating the parallel text of same language | |
| CN107301170A (en) | The method and apparatus of cutting sentence based on artificial intelligence | |
| CN111753551B (en) | Information generation method and device based on word vector generation model | |
| CN107862058B (en) | Method and apparatus for generating information | |
| CN109299477A (en) | Method and apparatus for generating text header | |
| US20230084055A1 (en) | Method for generating federated learning model | |
| CN107145485A (en) | Method and apparatus for compressing topic model | |
| CN108491421A (en) | A kind of method, apparatus, equipment and computer storage media generating question and answer | |
| CN109920431A (en) | Method and apparatus for output information | |
| CN109242043A (en) | Method and apparatus for generating information prediction model | |
| CN113421551B (en) | Speech recognition method, speech recognition device, computer readable medium and electronic equipment | |
| CN110059172A (en) | The method and apparatus of recommendation answer based on natural language understanding | |
| CN110516261A (en) | Resume appraisal procedure, device, electronic equipment and computer storage medium | |
| CN114841142A (en) | Text generation method and device, electronic equipment and storage medium | |
| CN109190123A (en) | Method and apparatus for output information |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190212 |
|
| RJ01 | Rejection of invention patent application after publication |