CN105335398A - Service recommendation method and terminal - Google Patents

Abstract

The invention discloses a service recommendation method. The method comprises: obtaining a short message in a terminal; performing language analysis on the short message to identify a potential intention of a user, corresponding to the short message; and according to the potential intention of the user, obtaining a service corresponding to the potential intention of the user. An embodiment of the invention furthermore provides the corresponding terminal. According to the method, the potential intention of the user, corresponding to the short message can be accurately identified by performing the language analysis on the short message, and the service corresponding to the potential intention of the user is obtained, so that the obtained service meets user demands.

Description

A kind of service recommendation method and terminal

Technical field

The present invention relates to areas of information technology, be specifically related to a kind of service recommendation method and terminal.

Background technology

Short message application on mobile terminal has become indispensable application user every day.Short message application is also varied, as traditional SMS (Short Message Service) (SMS, ShortMessageService), Multimedia Message Service (MMS, MultimediaMessagingService) and emerging recently micro-letter, microblogging etc.The content of short message is also comparatively extensive, comprises the interchange between friend, enterprise group sending advertisement, notice that enterprise pushes etc.

Short message on mobile terminal limits due to number of words, and a message can not comprise too many content.But a lot of content all comprises potential user's request behind in short message.The name of firm such as, occurred in short message may relate to potential Products Show service behind, information of discount Push Service; Time may relate to potential schedule service behind; Address may relate to potential map navigation service etc. behind.If the potential demand of user can be identified in limited number of words, and recommendation service pointedly and advertisement, will improve the ease for use of mobile terminal, improve user's viscosity, and increasing service and the specific aim of advertisement pushing and accuracy, reducing user to serving and the dislike of advertisement.

Prior art provides a kind of method based on the keyword recommendation service in short message.The method can comprise: terminal, according to keyword database, identifies the keyword in short message; According to user specific information, filter out from the keyword identified and user-dependent particular keywords; Highlight the keyword showing and filter out; After user selects keyword, according to user specific information, from advertising database, select the advertisement corresponding with the keyword that user selects, and specify the context service corresponding with the keyword that user selects; Show the advertisement selected and the context service of specifying.

To in the research and practice process of prior art, the present inventor finds, different short messages may comprise identical keyword, but the intention of the user corresponding to different short messages may be completely different, therefore only according to the keyword in keyword database identification short message, the advertisement corresponding to user's recommended keywords or context service, easily cause the service of recommendation not mate with the intention of user, and the service of recommendation does not meet the real demand of user.Such as, content of short message is " tomorrow is left Sichuan University's life and finishes ", and according to keyword database, the keyword identified is likely " Sichuan University ", and recommends with the relevant Map Services of Sichuan University.But as can be seen from clause, " Sichuan ", " university " in this short message should separate, therefore, the Map Services that the Sichuan University of recommendation is correlated with just does not meet the demand of user substantially.Also such as, message content " has not interested developer's conference of going to Baidu ", for prior art, probably identify " Baidu ", and recommend the search service etc. that " Baidu " is relevant, in fact be only a complete content from " developer's conference of Baidu " clause, therefore, the search service that " Baidu " of recommendation is relevant does not just meet the demand of user substantially.

As can be seen here, in prior art, there is the intention that the keyword identified accurately can not reflect short message, thus cause the service recommended not meet the demand of user.

Summary of the invention

The object of the present invention is to provide a kind of service recommendation method and terminal, by the inventive method, accurately can identify the potential intention of the user that short message is corresponding, make the service obtained meet the demand of user.

First aspect present invention provides a kind of service recommendation method, and it comprises:

Obtain the short message in terminal;

Described short message is carried out language parse, identifies the potential intention of the user that described short message is corresponding;

According to the potential intention of described user, obtain and be intended to corresponding service with the potential of described user.

In conjunction with first aspect, in the first embodiment of first aspect, described described short message is carried out language parse, obtains the potential intention of user corresponding to described short message, comprising:

Described short message is carried out morphology parsing, obtains the logical relation between the concept of word in described short message, attribute and described word;

The named entity that described word is corresponding is determined according to the concept of described word or attribute;

According to the logical relation between described named entity and described word, determine the potential intention of the user that described short message is corresponding.

In conjunction with the first embodiment of first aspect, in the second embodiment of first aspect, described according to the logical relation between described named entity and described word, before determining the potential intention of the user that described short message is corresponding, also comprise:

Determine the part of speech of described word, the syntactic structure of short message according to the part of speech identification of described word;

Described according to the logical relation between described named entity and described word, determine that the potential intention of the user that described short message is corresponding comprises:

According to the syntactic structure of the logical relation between described named entity, described word and described short message, determine the potential intention of the user that described short message is corresponding.

In conjunction with first aspect, or the first embodiment of first aspect, or the second embodiment of first aspect, in the third embodiment of first aspect, described short message is being carried out language parse, and after obtaining the potential intention of user corresponding to described short message, described method also comprises:

When the potential intention of described short message correspondence at least two, according to intent model, the probability that at least two potential intentions described in acquisition, each potential intention is corresponding; The probability corresponding according to potential intention each in described at least two potential intentions, the potential intention of screening predetermined number.

In conjunction with the third embodiment of first aspect, in the 4th kind of embodiment of first aspect, the intent model that described basis is preset, before the probability that at least two potential intentions described in acquisition, each potential intention is corresponding, described method also comprises:

According to the historical operating data of user, utilize the historical operating data of machine learning method to described user to train, obtain described intent model.

In conjunction with first aspect, or the first embodiment of first aspect, or the second embodiment of first aspect, or the third embodiment of first aspect, or the 4th of first aspect the kind of embodiment, in the 5th kind of embodiment of first aspect, the described potential intention according to described user, obtain and be intended to corresponding service with the potential of described user, specifically comprise:

Determine to obtain the potential parameter be intended to needed for corresponding service with described user, the context sight of short message according to required parameter acquiring;

Potentially corresponding recommendation explanation is intended to described according to described context scenarios generation.

In conjunction with first aspect, or the first embodiment of first aspect, or the second embodiment of first aspect, or the third embodiment of first aspect, or the 4th of first aspect the kind of embodiment, or the 5th of first aspect the kind of embodiment, in the 6th kind of embodiment of first aspect, after described acquisition and described user potential is intended to corresponding service, also comprise: when the quantity of described service is at least two, according to preset service type, described service is merged, obtain first service set;

From described first service set, obtain the service of predetermined number, and be presented on interface after the service of described predetermined number is sorted according to the laminating degree with described short message and select for user.

Second aspect present invention provides a kind of terminal, and it comprises:

Message retrieval unit, for obtaining the short message in terminal;

Intention assessment unit, for described short message is carried out language parse, identifies the potential intention of the user that described short message is corresponding;

Service acquisition unit, for the potential intention according to described user, obtains and is intended to corresponding service with the potential of described user.

In conjunction with second aspect, in the first embodiment of second aspect, described intention assessment unit comprises:

Subelement resolved in morphology, for described short message is carried out morphology parsing, obtains the logical relation between the concept of word in described short message, attribute and described word;

First determines subelement, for determining according to the concept of described word or attribute the named entity that described word is corresponding;

Second determines subelement, for according to the logical relation between described named entity and described word, determines the potential intention of the user that described short message is corresponding.

In conjunction with the first embodiment of second aspect, in the second embodiment of second aspect, described intention assessment unit also comprises:

Syntactic Recognition subelement, for determining the part of speech of described word, the syntactic structure of short message according to the part of speech identification of described word;

Described second determine subelement specifically for,

According to the syntactic structure of the logical relation between described named entity, described word and described short message, determine the potential intention of the user that described short message is corresponding.

In conjunction with second aspect, or the first embodiment of second aspect, or the second embodiment of second aspect, in the third embodiment of second aspect, described terminal also comprises:

Probability acquiring unit, for when the potential intention of the short message correspondence at least two that described service acquisition unit obtains, according to intent model, the probability of each potential intention correspondence at least two potential intentions described in acquisition;

Intention filter element, for the probability corresponding according to potential intention each in described at least two potential intentions, the potential intention of screening predetermined number.

In conjunction with the third embodiment of second aspect, in the 4th kind of embodiment of second aspect, described terminal also comprises:

Model training unit, according to the historical operating data of user, utilizes the historical operating data of machine learning method to described user to train, obtains described intent model;

Described probability acquiring unit, specifically for when the potential intention of the short message correspondence at least two that described service acquisition unit obtains, according to the intent model of described model training module training, the probability that at least two potential intentions described in acquisition, each potential intention is corresponding.

In conjunction with second aspect, or the first embodiment of second aspect, or the second embodiment of second aspect, or the third embodiment of second aspect, or the 4th of second aspect the kind of embodiment, in the 5th kind of embodiment of second aspect, described service acquisition unit comprises:

Sight obtains subelement, for determining to obtain the potential parameter be intended to needed for corresponding service with described user, the context sight of short message according to required parameter acquiring;

Illustrate and generate subelement, for potential being intended to corresponding recommendation explanation according to described context scenarios generation with described.

In conjunction with second aspect, or the first embodiment of second aspect, or the second embodiment of second aspect, or the third embodiment of second aspect, or the 4th of second aspect the kind of embodiment, or the 5th of second aspect the kind of embodiment, in the 6th kind of embodiment of second aspect, described terminal also comprises:

Service merge cells, for when the quantity of the service that described service acquisition unit obtains is at least two, merges described service according to preset service type, obtains first service set;

Service display unit, for obtaining the service of predetermined number from described first service set, and is presented on interface after the service of described predetermined number being sorted according to the laminating degree with described short message and selects for user.

The inventive method, by described short message is carried out language parse, accurately can identify the potential intention of the user that described short message is corresponding, obtains and is intended to corresponding service with the potential of described user, thus make the service of acquisition meet the demand of user.

Accompanying drawing explanation

In order to be illustrated more clearly in the technical scheme of the embodiment of the present invention, below the accompanying drawing used required in describing the embodiment of the present invention is briefly described, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those skilled in the art, other accompanying drawing can also be obtained as these accompanying drawings.

Fig. 1 is an embodiment schematic diagram of service recommendation method provided by the invention;

Fig. 2 is another embodiment schematic diagram of service recommendation method provided by the invention;

Fig. 3 is an embodiment schematic diagram of terminal provided by the invention;

Fig. 4 is another embodiment schematic diagram of terminal provided by the invention;

Fig. 5 is another embodiment schematic diagram of terminal provided by the invention.

Embodiment

Below in conjunction with the accompanying drawing in the embodiment of the present invention, be clearly and completely described the technical scheme in the embodiment of the present invention, obviously, described embodiment is only the present invention's part embodiment, instead of whole embodiments.Based on the embodiment in the present invention, the every other embodiment that those skilled in the art obtain, all belongs to the scope of protection of the invention.

As shown in Figure 1, the embodiment of the present invention provides a kind of service recommendation method, and can be applied to the terminal such as mobile phone, panel computer, it comprises:

101, the short message in terminal is obtained.

Described short message can be the text message that terminal obtains, and text information includes but not limited to information, note, notice etc. that microblogging, Instant Messenger (IM) software are mutual.

102, described short message is carried out language parse, obtain the potential intention of user corresponding to described short message.

Described language parse can comprise morphology parsing, syntax is resolved.Described short message is carried out language parse, the described short message meaning to be expressed can be parsed, thus obtain the potential intention of user corresponding to described short message.

103, according to the potential intention of described user, obtain and be intended to corresponding service with the potential of described user.

Being intended to corresponding service with described user potential can be the service that network provides, and also can be the service that the application that terminal is installed provides.

The method of the service recommendation that the present embodiment provides, by described short message is carried out language parse, accurately can obtain the potential intention of user corresponding to described short message, obtain and be intended to corresponding service with the potential of described user, thus make the service of acquisition meet the demand of user.

Technical scheme for a better understanding of the present invention, below enumerates more detailed embodiment and is described.

As shown in Figure 2, the embodiment of the present invention also provides a kind of method of service recommendation, and it specifically comprises:

201, the short message in terminal is obtained;

Described short message can be the text message that terminal obtains, and it includes but not limited to information, note, notice etc. that microblogging, Instant Messenger (IM) software are mutual.

202, described short message resolved in morphology, obtains concept, the attribute of word in short message, the named entity corresponding according to the word in the concept of word or attribute determination short message;

Concrete, by the one or more sentences in described short message, be cut into one or more word, obtain the logical relation between the concept of word in short message, attribute and word, according to the concept of word or named entity corresponding to attribute determination word, according to the logical relation between named entity and word, determine the potential intention of the user that short message is corresponding.

Such as content of short message " tomorrow leaves Sichuan ", the result of participle can export " tomorrow " and " leave " in " Sichuan ".The named entity that the word determined in short message according to the concept, attribute etc. of word is corresponding, the result of named entity can export " tomorrow-time ", " Sichuan-place (or province) " etc.Terminal according to morphology analytic model and dictionary, can also carry out specification to the word in short message, determines the corresponding relation between they and named entity.Such as, " point in afternoon 4 " specification in short message " afternoon 4, Dian Qu Startbuck sat " changes into xx xx month xx day (date of today) 16:00, corresponding named entity is " time ", " Startbuck " corresponding named entity is " dining room title ", " place name ", " musical designation ", " sitting " corresponding named entity is " event of having dinner ", then according to the logical relation between named entity and word, the potential intention of the user that short message is corresponding is determined.

203, the part of speech of word in short message is determined, according to the syntactic structure of the part of speech identification short message of word;

In specific implementation, first can carry out participle to short message, identify the part of speech of each word in short message, part of speech comprises verb, noun, adjective, measure word, pronoun, adverbial word etc., with the syntactic structure of the part of speech identification short message according to word.Such as short message " afternoon 4, Dian Qu Startbuck sat ", " ROOT-> goes (verb); remove (adverbial modifier)-> point in afternoon 4 (time noun); go to (object)-> Startbuck (place noun), removes (coordination)-> seat ".

204, according to the syntactic structure of the logical relation between described named entity, described word and short message, the potential intention of the user that short message is corresponding is determined;

It should be noted that, after the named entity that the word identified in short message in step 203 is corresponding, according to the logical relation between named entity and word, the potential intention of the user that short message is corresponding can be determined.If can not determine the potential intention of the user that short message is corresponding according to the logical relation between named entity with word, then determine the syntactic structure of short message in step 204 after, according to the syntactic structure of the logical relation between named entity, word and short message, jointly determine the potential intention of the user that short message is corresponding.

205, according to the historical operating data of user, utilize the historical operating data of machine learning method to user to train, obtain intent model;

In the present embodiment, can according to the historical operating data of user, the habits and customs of the semantic structure of unified with nature language, society and individual subscriber, utilize the historical operating data of machine learning method to user to train, obtain intent model.Such as, for " apple " word, can fruit be referred to, also may refer to electronic product trade (brand) name.When the short message in terminal is " today has bought individual apple ", singly see the words, cannot determine that " apple " that user says is fruit or electronic product, now just need the historical operating data according to user, utilize machine learning method to determine.Such as, when " apple " in the words refers to fruit, in the historical operating data of user, the weight (" two jin " to fruit may be there is, " five jin "), the word that carries out limiting such as the kind of fruit (Fuji apple, gold hat), just can determine the true intention of user according to these determiners; And when " apple " in the words refers to electronic product, the model to electronic product may be there is in the historical operating data of user, the parameters such as configuration carry out the word limited.Such as content of short message " go to Startbuck to sit in the afternoon " again, according to the historical operating data of user, when such as, there is " seat " this word in usual terminal, user can search place of having dinner, it can thus be appreciated that " seat " is herein more prone to user and will goes to have dinner, also can learn that " seat " herein refers to have dinner more with reference to natural language expressing custom in addition, so just accurately can know the true intention of user, thus obtain intent model.

206, according to intent model, obtain the probability that each potential intention is corresponding, the probability corresponding according to each potential intention, obtains the potential intention of predetermined number;

Such as, when content of short message is " go to Startbuck to sit in the afternoon ", may have " reward voucher obtaining Startbuck " according to the potential intention of step 202 to 204 users determined, " check the menu of Startbuck ", " route of Startbuck is removed in inquiry " etc., and according to intent model, when terminal there is above-mentioned message at every turn, user can apply for the reward voucher of Startbuck, sometimes the menu of Startbuck can also be looked over, the probability of so each potential intention correspondence will be: " recommending reward voucher-Startbuck " > " recommendation menu-Startbuck " > " recommended route-Startbuck ".

If the potential intention quantity that short message is corresponding is more, probability that so can be corresponding according to each potential intention, only obtains the potential intention that the probability of predetermined number is higher, with the real demand making obtained potential intention more be close to the users.

207, obtain the context sight of short message, based on context scenarios generation is potentially intended to corresponding recommendation explanation with described;

When after the potential intention determining the user that short message is corresponding, determine to obtain the potential parameter be intended to needed for corresponding service with user, according to the context sight of required parameter acquiring short message, the recommendation explanation corresponding according to the context scenarios generation of short message.Such as, when the service recommended for user for go down circuit time, just need to be defined as the parameter that user recommends needed for this service, specifically in current example, parameter at least comprises departure place and destination.In the present embodiment, the context sight of short message can be the key words in short message, also can be other the user profile relevant to the content of short message, also can be the information of prompting user input.Such as when short message is " 6 pm on Startbuck doorway etc. I ", the potential intention of the user determined has " arranging prompting-6 pm at xx such as Startbuck doorways ", " circuit of Startbuck is removed in inquiry "." arranged at xx such as Startbuck doorways prompting-6 pm " for potential intention, the key words " 6 pm " in short message, " Startbuck ", " waiting xx " can be extracted, then generate in conjunction with the year, month, day equal time information on the same day of terminal self display and potentially with this be intended to corresponding recommendation and illustrate " for you arrange the event notification of xx xx month xx 6 pm day at xx such as Startbuck "; For potential intention " circuit of Startbuck is removed in inquiry ", then the context sight of short message can be the current positional information xx of user, this positional information can be obtained by the GPS location of user terminal, also can obtain from user according to the information of prompting input, what generate is potentially intended to corresponding recommendation with this and is illustrated as " for you inquire about the route from xx to Startbuck ".

In addition, when the context sight of short message is other the user profile relevant to the content of short message, this user profile can also be kept at the user data on tag memory or memory device, include but not limited to other short messages, address list, p.m.entry, remind item, photo, application, video, audio frequency, mail, bookmark, web page browsing record, the purchaser record of commodity/service, hotel reservation record, air ticket purchaser record, some preferences of user are arranged, user profile can also be the relevant information of the terminal that user uses in addition, the hardware information of such as terminal and software information, include but not limited to date and clock information, positional information (such as GPS, country, city etc.), by the information that sensor produces, the software that the operating system of terminal and terminal are run, process, the state of service and event etc.

208, the recommendation selected according to user illustrates, obtains and is intended to corresponding service with the potential of user;

In the present embodiment, the key words being used for generating recommendations explanation in short message can be done Special display, the corresponding one or more potential intention of each key words, each potential intention has corresponding recommendation explanation, when user pays close attention to a certain key words, just for user shows corresponding recommendation explanation.

Such as, for short message " 6 pm on Startbuck doorway etc. I ", the key words in short message is done Special display can for " 6 pm? startbuckdoorway etc. I ", wherein the potential intention of " 6 pm " respective user " arranges prompting ", the potential intention " route of Startbuck is removed in inquiry " of " Startbuck " respective user, " menu of inquiry Startbuck ", " reward voucher of inquiry Startbuck " etc.Terminal can the behavior of monitor user ', when monitoring user and clicking default a certain key words such as " Startbuck ", for user shows corresponding recommendation explanation.Specifically in current example, when user clicks " Startbuck ", with above-mentioned three by for user's display potentially be intended to corresponding recommendation and illustrates, the display that this recommendation illustrates can show by each probability size priority being intended to correspondence.

After user selects a certain recommendation to illustrate, to obtain and this recommendation illustrates and corresponding is potentially intended to corresponding service.

This service can be some application of calling terminal self, such as, reminder application in terminal, alarm clock application, or p.m.entry application etc., also can be obtain from third party, such as server, other-end etc.

Certainly, in the above example, also can select to recommend to illustrate without user, after recommendation illustrates to rest on the time preset on terminal demonstration interface, automatic acquisition illustrates corresponding service with all recommendation.

209, the service of acquisition is merged, obtain first service set, from first service set, obtain the service of predetermined number, and the service of predetermined number is presented on interface selects for user.

Obtain after being intended to corresponding service with user potential, merging can be carried out to service content and obtain first service set, the object done like this removes the service repeated, and the interface being presented at terminal after laggard line ordering of then service in first service set can being sorted according to the laminating degree with described short message is selected for user.

Service and the laminating degree of short message can be serve the laminating degree with the key words in short message, such as, when short message is " having a meal near evening to Shangdi ", here a key words " near Shangdi " is had, be intended to corresponding service with user potential and may have dining room near the Shangdi of recommending for user, so the laminating degree of nearer dining room, distance Shangdi and short message is higher, therefore, to can be presented on terminal interface after service ranking according to the order from high to low of the laminating degree with short message, select to facilitate user.In addition, service also can include but not limited to the laminating degree of short message the condition significance level that the unified understanding that daily life is formed judges, such as in recommendation coupon service, " favourable price " may more preferably than " expired time ", and the laminating degree of service and short message can also judge according to the custom of user and historical record data.

In the present embodiment, the potential intention of user is determined by language parse, generate and be intended to corresponding recommendation explanation with potential, select for user, then for user provides corresponding service, improve the dirigibility of service recommendation, make the service for user's recommendation be the service meeting user's potential demand most, thus facilitate user to select to meet the service of demand.

Introduce the terminal that the embodiment of the present invention provides below, described terminal, for performing all methods of above statement, refers to Fig. 3, and the terminal 300 of the present embodiment comprises:

Message retrieval unit 301, for obtaining the short message in terminal;

Intention assessment unit 302, carries out language parse for the described short message got by message retrieval unit 301, obtains the potential intention of user corresponding to described short message;

Service acquisition unit 303, for the potential intention of the described user according to described intention assessment unit 302 acquisition, obtains and is intended to corresponding service with the potential of described user.

In this enforcement, intention assessment unit is by carrying out language parse by described short message, accurately can identify the potential intention of the user that described short message is corresponding, service acquisition unit obtains and is intended to corresponding service with the potential of described user, thus makes the service of acquisition meet the demand of user.

For ease of understanding, be described the terminal of the embodiment of the present invention further below, refer to Fig. 4, the terminal 400 of the present embodiment comprises:

Message retrieval unit 401, for obtaining the short message in terminal;

Intention assessment unit 402, carries out language parse for the short message obtained by message retrieval unit 401, obtains the potential intention of user corresponding to described short message;

Model training unit 403, for the historical operating data according to user, utilizes the historical operating data of machine learning method to described user to train, and obtains intent model;

Probability acquiring unit 404, for when the potential intention of described short message correspondence at least two, according to the intent model that model training unit 403 is trained, obtains the probability of each potential intention correspondence at least two potential intentions;

Intention filter element 405, for the probability that potential intention each at least two potential intentions according to probability acquiring unit 404 acquisition is corresponding, the potential intention of screening predetermined number;

Service acquisition unit 406, for the potential intention according to described user, obtains and is intended to corresponding service with the potential of described user;

Service merge cells 407, for when the quantity of described service is at least two, merges described service according to preset service type, obtains first service set;

Service display unit 408, for obtaining the service of predetermined number from described first service set, and is presented on interface after the service of described predetermined number being sorted according to the laminating degree with short message and selects for user.

In addition, intention assessment unit 402 specifically comprises:

Subelement 4021 resolved in morphology, for described short message is carried out morphology parsing, obtains the logical relation between the concept of word in described short message, attribute and described word;

First determines subelement 4022, for determining according to the concept of described word or attribute the named entity that described word is corresponding;

Syntactic Recognition subelement 4023, for determining the part of speech of described word, the syntactic structure of short message according to the part of speech identification of described word;

Second determines subelement 4024, for the syntactic structure according to the logical relation between described named entity, described word and described short message, determines the potential intention of the user that described short message is corresponding.

Service acquisition unit 406 specifically comprises:

Sight obtains subelement 4061, for determining to obtain the potential parameter be intended to needed for corresponding service with user, the context sight of short message according to required parameter acquiring;

Illustrate and generate subelement 4062, for potential being intended to corresponding recommendation explanation according to described context scenarios generation with described.

For further understanding, with a practical application scene, the interactive mode between each unit of the terminal 400 in the present embodiment is described below:

First, message retrieval unit 401 obtains the short message in terminal, and described short message can be the text message that terminal obtains, and it includes but not limited to information, note, notice etc. that microblogging, Instant Messenger (IM) software are mutual.

Morphology resolves subelement 4021 by the one or more sentences in described short message, be cut into one or more word, obtain the logical relation between the concept of word in short message, attribute and word, first determines that subelement 4022 is according to the concept of word or named entity corresponding to attribute determination word, according to the logical relation between named entity and word, determine the potential intention of the user that short message is corresponding.

Such as content of short message is " tomorrow leaves Sichuan ", and the result that subelement 4021 participle resolved in morphology can export " tomorrow " and " leave " in " Sichuan ".First determines the named entity that word that subelement 4022 is determined in short message according to the concept, attribute etc. of word is corresponding, and the result of named entity can export " tomorrow-time ", " Sichuan-place (or province) " etc.In addition, subelement 4021 resolved in morphology according to morphology analytic model and dictionary, can also carry out specification to the word in short message, determines the corresponding relation between they and named entity.Such as, " point in afternoon 4 " specification in short message " afternoon 4, Dian Qu Startbuck sat " changes into xx xx month xx day (date of today) 16:00, corresponding named entity is " time ", " Startbuck " corresponding named entity is " dining room title ", " place name ", " musical designation ", " sitting " corresponding named entity is " event of having dinner ", then second determines that subelement 4024 is according to the logical relation between named entity and word, determines the potential intention of the user that short message is corresponding.

If second determines that subelement 4024 is according to the logical relation between named entity and word, can not determine the potential intention of the user that short message is corresponding, then determined the part of speech of word in short message by Syntactic Recognition subelement 4023, according to the syntactic structure of the part of speech identification short message of word.Particularly, Syntactic Recognition subelement 4023 first can carry out participle to short message, identify the part of speech of each word in short message, part of speech comprises verb, noun, adjective, measure word, pronoun, adverbial word etc., with the syntactic structure of the part of speech identification short message according to word.Such as short message " afternoon 4, Dian Qu Startbuck sat ", " ROOT-> goes (verb); remove (adverbial modifier)-> point in afternoon 4 (time noun); go to (object)-> Startbuck (place noun), removes (coordination)-> seat ".

Second determines that subelement 4024 determines according to first the described named entity that subelement 4022 is determined, the syntactic structure of the short message that the logical relation between the described word that morphology parsing subelement 4021 parses and Syntactic Recognition subelement 4023 identify, determines the potential intention of the user that short message is corresponding jointly.

After second determines that the potential intention of user determined by subelement 4024, model training unit 403, according to the historical operating data of user, utilizes the historical operating data of machine learning method to user to train, and obtains intent model.In specific implementation, model training unit 403 can according to the historical operating data of user, and the habits and customs of the semantic structure of unified with nature language, society and individual subscriber, utilize the historical operating data of machine learning method to user to train, obtain intent model.Such as, for " apple " word, can fruit be referred to, also may refer to electronic product trade (brand) name.When the short message in terminal is " today has bought individual apple ", singly see the words, cannot determine that " apple " that user says is fruit or electronic product, now just need the historical operating data according to user, utilize machine learning method to determine.Such as, when " apple " in the words refers to fruit, in the historical operating data of user, the word that the kind (Fuji apple, gold hat) etc. of the weight (" two jin ", " five jin ") to fruit, fruit carries out limiting may be there is; And when " apple " in the words refers to electronic product, the model to electronic product may be there is in the historical operating data of user, the parameters such as configuration carry out the word limited.Such as content of short message " go to Startbuck to sit in the afternoon " again, according to the historical operating data of user, when such as, there is " seat " this word in usual terminal, user can search place of having dinner, it can thus be appreciated that " seat " is herein more prone to user and will goes to have dinner, also can learn that " seat " herein refers to have dinner more with reference to natural language expressing custom in addition, so just accurately can know the true intention of user, thus obtain intent model.

The intent model that probability acquiring unit 404 is trained according to model training unit 403, obtains the probability that each potential intention is corresponding, and the probability corresponding according to each potential intention, obtains the potential intention of predetermined number.Such as, when content of short message is " go to Startbuck to sit in the afternoon ", second determines that the potential intention of the user that subelement 4024 is determined may have " obtaining the reward voucher of Startbuck ", " check the menu of Startbuck ", " route of Startbuck is removed in inquiry " etc., and according to intent model, when terminal there is above-mentioned message at every turn, user can apply for the reward voucher of Startbuck, sometimes the menu of Startbuck can also be looked over, the probability of so each potential intention correspondence will be: " recommending reward voucher-Startbuck " > " recommends menu-Startbuck ", and > " inquires about map-Startbuck ".

If the potential intention quantity that short message is corresponding is more, so be intended to the probability that filter element 405 can be corresponding according to each potential intention, only obtain the potential intention that the probability of predetermined number is higher, with the real demand making obtained potential intention more be close to the users.

Following sight obtains subelement 4061 and determines to obtain the potential parameter be intended to needed for corresponding service with user, and according to the context sight of required parameter acquiring short message, based on context scenarios generation is potentially intended to corresponding recommendation explanation with described.Such as, when the service recommended for user for go down circuit time, just need to be defined as the parameter that user recommends needed for this service, specifically in current example, parameter at least comprises departure place and destination.In the present embodiment, the context sight of short message can be the key words in short message, also can be other the user profile relevant to the content of short message, also can be the information of prompting user input.Such as when short message is " 6 pm on Startbuck doorway etc. I ", the potential intention of the user determined has " arranging prompting-6 pm at xx such as Startbuck doorways ", " circuit of Startbuck is removed in inquiry "." arranged at xx such as Startbuck doorways prompting-6 pm " for potential intention, sight obtains subelement 4061 can extract key words " 6 pm " in short message, " Startbuck ", " waiting xx ", then illustrate the year, month, day equal time information generation that generates the same day that subelement 4062 show in conjunction with terminal self and this be potentially intended to corresponding recommendation and illustrate " for you arrange the event notification of xx xx month xx 6 pm day at xx such as Startbuck "; For potential intention " circuit of Startbuck is removed in inquiry ", then sight obtains the context sight of short message that subelement 4061 obtains can be the current positional information xx of user, this positional information can be obtained by the GPS location of user terminal, also can obtain from user according to the information of prompting input, what illustrates that generation subelement 4062 generates is potentially intended to corresponding recommendation with this and is illustrated as " for you inquire about the route from xx to Startbuck ".

In addition, when the context sight of short message is other the user profile relevant to the content of short message, this user profile can also be kept at the user data on tag memory or memory device, include but not limited to other short messages, address list, p.m.entry, remind item, photo, application, video, audio frequency, mail, bookmark, web page browsing record, the purchaser record of commodity/service, hotel reservation record, air ticket purchaser record, some preferences of user are arranged, user profile can also be the relevant information of the terminal that user uses in addition, the hardware information of such as terminal and software information, include but not limited to date and clock information, positional information (such as GPS, country, city etc.), by the information that sensor produces, the software that the operating system of terminal and terminal are run, process, the state of service and event etc.

In the present embodiment, illustrate that generating subelement 4062 can do Special display by the key words being used for generating recommendations explanation in short message, the corresponding one or more potential intention of each key words, each potential intention has corresponding recommendation explanation, when user pays close attention to a certain key words, just for user shows corresponding recommendation explanation.

Such as, for short message " 6 pm on Startbuck doorway etc. I ", illustrate generate subelement 4062 key words in short message is done Special display can for " 6 pm? startbuckdoorway etc. I ", wherein the potential intention of " 6 pm " respective user " arranges prompting ", the potential intention " route of Startbuck is removed in inquiry " of " Startbuck " respective user, " menu of inquiry Startbuck ", " reward voucher of inquiry Startbuck " etc.Illustrate generate subelement 4062 can the behavior of monitor user ', when monitoring user and clicking default a certain key words such as " Startbuck ", for user shows corresponding recommendation explanation.Specifically in current example, when user clicks " Startbuck ", with above-mentioned three by for user's display potentially be intended to corresponding recommendation and illustrates, the display that this recommendation illustrates can show by each probability size priority being intended to correspondence.

After user selects a certain recommendation to illustrate, service acquisition unit 406 obtains and this recommendation illustrates and corresponding is potentially intended to corresponding service.

The service that service acquisition unit 406 obtains can be some application of calling terminal self, such as, reminder application in terminal, alarm clock application, or p.m.entry application etc., also can be the service obtained from third party, third party's such as server, other-end etc.

Certainly, in the above example, also can wait for that user selects to recommend to illustrate, after recommendation illustrates to rest on the time preset on terminal demonstration interface, service acquisition unit 406 automatic acquisition illustrates corresponding service with all recommendation.

After service acquisition unit 406 obtains corresponding service, the service of acquisition merges by service merge cells 407, obtain first service set, the object done like this removes the service repeated, then serve display unit 408 service in first service set can be sorted according to the laminating degree with described short message be presented at terminal after laggard line ordering interface on select for user.

Service and the laminating degree of short message can be serve the laminating degree with the key words in short message, such as, when short message is " having a meal near evening to Shangdi ", here a key words " near Shangdi " is had, be intended to corresponding service with user potential and may have dining room near the Shangdi of recommending for user, so the laminating degree of nearer dining room, distance Shangdi and short message is higher, therefore, service display unit 408 will can be presented on terminal interface according to the order from high to low of the laminating degree with short message after service ranking, select to facilitate user.In addition, service also can include but not limited to the laminating degree of short message the condition significance level that the unified understanding that daily life is formed judges, such as in recommendation coupon service, " favourable price " may more preferably than " expired time ", and the laminating degree of service and short message can also judge according to the custom of user and historical record data.

In the present embodiment, intention assessment unit determines the potential intention of user by language parse, illustrate that generation unit generates and be intended to corresponding recommendation explanation with potential, select for user, then service acquisition unit provides corresponding service for user, improve the dirigibility of service recommendation, make the service for user's recommendation be the service meeting user's potential demand most, thus facilitate user to select to meet the service of demand.

Refer to Fig. 5 below, Fig. 5 provides another embodiment schematic diagram of terminal of the present invention, and the terminal 500 of the present embodiment may be used for implementing the service recommendation method that above-described embodiment provides, in actual applications, terminal 500 can be the electronic equipments such as mobile phone, notebook computer.Specifically:

Terminal 500 can comprise RF (RadioFrequency, radio frequency) circuit 510, the storer 520 including one or more computer-readable recording mediums, input block 530, display unit 540, sensor 550, voicefrequency circuit 560, WiFi (wirelessfidelity, Wireless Fidelity) module 570, include the parts such as processor 580 and power supply 590 that more than or processes core.It will be understood by those skilled in the art that the restriction of the not structure paired terminal 500 of the structure shown in Fig. 5, the parts more more or less than diagram can be comprised, or combine some parts, or different parts are arranged.Wherein:

RF circuit 510 can be used in messaging or communication process, the reception of signal and transmission, especially, after being received by the downlink information of base station, transfers to more than one or one processor 580 to process; In addition, base station is sent to by relating to up data.Usually, RF circuit 510 includes but not limited to antenna, at least one amplifier, tuner, one or more oscillator, subscriber identity module (SIM) card, transceiver, coupling mechanism, LNA (LowNoiseAmplifier, low noise amplifier), diplexer etc.In addition, RF circuit 510 can also by radio communication and network and other devices communicatings.Described radio communication can use arbitrary communication standard or agreement, include but not limited to GSM (GlobalSystemofMobilecommunication, global system for mobile communications), GPRS (GeneralPacketRadioService, general packet radio service), CDMA (CodeDivisionMultipleAccess, CDMA), WCDMA (WidebandCodeDivisionMultipleAccess, Wideband Code Division Multiple Access (WCDMA)), LTE (LongTermEvolution, Long Term Evolution), Email, SMS (ShortMessagingService, Short Message Service) etc.

Storer 520 can be used for storing software program and module, and processor 580 is stored in software program and the module of storer 520 by running, thus performs the application of various function and data processing.Storer 520 mainly can comprise storage program district and store data field, and wherein, storage program district can store operating system, application program (such as sound-playing function, image player function etc.) etc. needed at least one function; Storage data field can store and create data (such as voice data, phone directory etc.) according to the use of memory device.In addition, storer 520 can comprise high-speed random access memory, can also comprise nonvolatile memory, such as at least one disk memory, flush memory device or other volatile solid-state parts.Correspondingly, storer 520 can also comprise Memory Controller, to provide the access of processor 580 and input block 530 pairs of storeies 520.

Input block 530 can be used for the numeral or the character information that receive input, and produces and to arrange with user and function controls relevant keyboard, mouse, control lever, optics or trace ball signal and inputs.Particularly, input block 530 can comprise Touch sensitive surface 531 and other input equipments 532.Touch sensitive surface 531, also referred to as touch display screen or Trackpad, user can be collected or neighbouring touch operation (such as user uses any applicable object or the operations of annex on Touch sensitive surface 531 or near Touch sensitive surface 531 such as finger, stylus) thereon, and drive corresponding coupling arrangement according to the formula preset.Optionally, Touch sensitive surface 531 can comprise touch detecting apparatus and touch controller two parts.Wherein, touch detecting apparatus detects the touch orientation of user, and detects the signal that touch operation brings, and sends signal to touch controller; Touch controller receives touch information from touch detecting apparatus, and converts it to contact coordinate, then gives processor 580, and the order that energy receiving processor 580 is sent also is performed.In addition, the polytypes such as resistance-type, condenser type, infrared ray and surface acoustic wave can be adopted to realize Touch sensitive surface 531.Except Touch sensitive surface 531, input block 530 can also comprise other input equipments 532.Particularly, other input equipments 532 can include but not limited to one or more in physical keyboard, function key (such as volume control button, switch key etc.), trace ball, mouse, control lever etc.

Display unit 540 can be used for the various graphical user interface showing information or the information being supplied to user and the terminal inputted by user, and these graphical user interface can be made up of figure, text, icon, video and its combination in any.Display unit 540 can comprise display panel 541, optionally, the form such as LCD (LiquidCrystalDisplay, liquid crystal display), OLED (OrganicLight-EmittingDiode, Organic Light Emitting Diode) can be adopted to configure display panel 541.Further, Touch sensitive surface 531 can cover display panel 541, when Touch sensitive surface 531 detects thereon or after neighbouring touch operation, send processor 580 to determine the type of touch event, on display panel 541, provide corresponding vision to export with preprocessor 580 according to the type of touch event.Although in Figure 5, Touch sensitive surface 531 and display panel 541 be as two independently parts realize input and input function, in certain embodiments, can by Touch sensitive surface 531 and display panel 541 integrated and realize input and output function.

Terminal 500 also can comprise at least one sensor 550, such as optical sensor, motion sensor and other sensors.Particularly, optical sensor can comprise ambient light sensor and proximity transducer, and wherein, ambient light sensor the light and shade of environmentally light can regulate the brightness of display panel 541, proximity transducer when terminal 500 moves in one's ear, can cut out display panel 541 and/or backlight.As the one of motion sensor, Gravity accelerometer can detect the size of all directions (are generally three axles) acceleration, size and the direction of gravity can be detected time static, can be used for the application (such as horizontal/vertical screen switching, dependent game, magnetometer pose calibrating) of identification terminal attitude, Vibration identification correlation function (such as passometer, knock) etc.; As for terminal 500 also other sensors such as configurable gyroscope, barometer, hygrometer, thermometer, infrared ray sensor, do not repeat them here.

Voicefrequency circuit 560, loudspeaker 561, microphone 562 can provide the audio interface between user and device.Voicefrequency circuit 560 can by receive voice data conversion after electric signal, be transferred to loudspeaker 561, by loudspeaker 561 be converted to voice signal export; On the other hand, the voice signal of collection is converted to electric signal by microphone 562, voice data is converted to after being received by voicefrequency circuit 560, after again voice data output processor 580 being processed, through RF circuit 510 to send to such as another terminal, or export voice data to storer 520 to process further.Voicefrequency circuit 560 also may comprise earphone jack, to provide the communication of peripheral hardware earphone and terminal.

WiFi belongs to short range wireless transmission technology, and terminal 500 can help user to send and receive e-mail by WiFi module 570, browse webpage and access streaming video etc., and its broadband internet wireless for user provides is accessed.Although Fig. 5 shows WiFi module 570, be understandable that, it does not belong to must forming of device, can omit in the scope of essence not changing invention as required completely.

Processor 580 is control centers of the off-grid device of prediction user, utilize the various piece of various interface and the whole device of connection, software program in storer 520 and/or module is stored in by running or performing, and call the data be stored in storer 520, perform various function and the process data of memory device, thus integral monitoring is carried out to memory device.Optionally, processor 580 can comprise one or more process core; Optionally, processor 580 accessible site application processor and modem processor, wherein, application processor mainly processes operating system, user interface and application program etc., and modem processor mainly processes radio communication.Be understandable that, above-mentioned modem processor also can not be integrated in processor 580.

Terminal 500 also comprises the power supply 590 (such as battery) of powering to all parts, optionally, power supply can be connected with processor 580 logic by power-supply management system, thus realizes the functions such as management charging, electric discharge and power managed by power-supply management system.Power supply 590 can also comprise one or more direct current or AC power, recharging system, power failure detection circuit, power supply changeover device or the random component such as inverter, power supply status indicator.

Although not shown, terminal 500 can also comprise camera, bluetooth module etc., does not repeat them here.Specifically in the present embodiment, terminal 500 includes storer 520, and one or more than one program, one of them or more than one program are stored in storer 520, and are configured to perform above-mentioned more than one or one routine package containing the instruction for carrying out following operation by more than one or one processor 580:

Obtain the short message in terminal;

Described short message is carried out language parse, obtains the potential intention of user corresponding to described short message;

According to the potential intention of described user, obtain and be intended to corresponding service with the potential of described user.

Optionally, described short message is carried out language parse, obtains the potential intention of user corresponding to described short message, comprising:

Described short message is carried out morphology parsing, obtains the logical relation between the concept of word in described short message, attribute and described word;

The named entity that described word is corresponding is determined according to the concept of described word or attribute;

According to the logical relation between described named entity and described word, determine the potential intention of the user that described short message is corresponding.

Optionally, described according to the logical relation between described named entity and described word, before determining the potential intention of the user that described short message is corresponding, also comprise:

Determine the part of speech of described word, the syntactic structure of short message according to the part of speech identification of described word;

Described according to the logical relation between described named entity and described word, determine that the potential intention of the user that described short message is corresponding comprises:

According to the syntactic structure of the logical relation between described named entity, described word and described short message, determine the potential intention of the user that described short message is corresponding.

Optionally, described short message is being carried out language parse, after obtaining the potential intention of user corresponding to described short message, described method also comprises:

When the potential intention of described short message correspondence at least two, according to intent model, the probability that at least two potential intentions described in acquisition, each potential intention is corresponding;

The probability corresponding according to potential intention each in described at least two potential intentions, the potential intention of screening predetermined number.

Optionally, the intent model that described basis is preset, before the probability that at least two potential intentions described in acquisition, each potential intention is corresponding, described method also comprises:

According to the historical operating data of user, utilize the historical operating data of machine learning method to described user to train, obtain described intent model.

Optionally, the described potential intention according to described user, obtains and is intended to corresponding service with the potential of described user, specifically comprise:

Determine to obtain the potential parameter be intended to needed for corresponding service with described user, the context sight of short message according to required parameter acquiring;

Potentially corresponding recommendation explanation is intended to described according to described context scenarios generation.

Optionally, described acquisition and described user potential also comprises after being intended to corresponding service:

When the quantity of described service is at least two, according to preset service type, described service is merged, obtain first service set;

From described first service set, obtain the service of predetermined number, and be presented on interface after the service of described predetermined number is sorted according to the laminating degree with described short message and select for user.

It should be noted that the terminal 500 that the embodiment of the present invention provides can also be used for other function realized in said apparatus embodiment, not repeat them here.

In several embodiments that the application provides, should be understood that, disclosed device, the mode by other realizes.Such as, device embodiment described above is only schematic, the such as division of described unit, be only a kind of logic function to divide, actual can have other dividing mode when realizing, such as multiple unit or assembly can in conjunction with or another system can be integrated into, or some features can be ignored, or do not perform.Another point, shown or discussed coupling each other or direct-coupling or communication connection can be by some interfaces, and the indirect coupling of device or unit or communication connection can be electrical or other form.

The described unit illustrated as separating component or can may not be and physically separates, and the parts as unit display can be or may not be physical location, namely can be positioned at a place, or also can be distributed in multiple network element.Some or all of unit wherein can be selected according to the actual needs to realize the object of the present embodiment scheme.

In addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, also can be that the independent physics of unit exists, also can two or more unit in a unit integrated.Above-mentioned integrated unit both can adopt the form of hardware to realize, and the form of SFU software functional unit also can be adopted to realize.

If described integrated unit using the form of SFU software functional unit realize and as independently production marketing or use time, can be stored in a computer read/write memory medium.Based on such understanding, the part that technical scheme of the present invention contributes to prior art in essence in other words or all or part of of this technical scheme can embody with the form of software product, this computer software product is stored in a storage medium, comprises all or part of step of some instructions in order to make a computer equipment (can be personal computer, server or the network equipment etc.) perform method described in each embodiment of the present invention.And aforesaid storage medium comprises: USB flash disk, ROM (read-only memory) (ROM, Read-OnlyMemory), random access memory (RAM, RandomAccessMemory), portable hard drive, magnetic disc or CD etc. various can be program code stored medium.

The above, above embodiment only in order to technical scheme of the present invention to be described, is not intended to limit; Although with reference to previous embodiment to invention has been detailed description, those of ordinary skill in the art is to be understood that: it still can be modified to the technical scheme described in foregoing embodiments, or carries out equivalent replacement to wherein portion of techniques feature; And these amendments or replacement, do not make the essence of appropriate technical solution depart from the spirit and scope of various embodiments of the present invention technical scheme.

Claims (14)

1. a service recommendation method, is characterized in that, comprising:

Obtain the short message in terminal;

Described short message is carried out language parse, obtains the potential intention of user corresponding to described short message;

According to the potential intention of described user, obtain and be intended to corresponding service with the potential of described user.

2. method according to claim 1, is characterized in that, described short message is carried out language parse, obtains the potential intention of user corresponding to described short message, comprising:

Described short message is carried out morphology parsing, obtains the logical relation between the concept of word in described short message, attribute and described word;

The named entity that described word is corresponding is determined according to the concept of described word or attribute;

According to the logical relation between described named entity and described word, determine the potential intention of the user that described short message is corresponding.

3. method according to claim 2, is characterized in that, described according to the logical relation between described named entity and described word, before determining the potential intention of the user that described short message is corresponding, also comprises:

Determine the part of speech of described word, the syntactic structure of short message according to the part of speech identification of described word;

Described according to the logical relation between described named entity and described word, determine that the potential intention of the user that described short message is corresponding comprises:

According to the syntactic structure of the logical relation between described named entity, described word and described short message, determine the potential intention of the user that described short message is corresponding.

4., according to the arbitrary described method of claims 1 to 3, it is characterized in that, described short message is being carried out language parse, and after obtaining the potential intention of user corresponding to described short message, described method also comprises:

When the potential intention of described short message correspondence at least two, according to intent model, the probability that at least two potential intentions described in acquisition, each potential intention is corresponding;

The probability corresponding according to potential intention each in described at least two potential intentions, the potential intention of screening predetermined number.

5. method according to claim 4, is characterized in that, the intent model that described basis is preset, and before the probability that at least two potential intentions described in acquisition, each potential intention is corresponding, described method also comprises:

According to the historical operating data of user, utilize the historical operating data of machine learning method to described user to train, obtain described intent model.

6., according to the arbitrary described method of claim 1 to 5, it is characterized in that, the described potential intention according to described user, obtain and be intended to corresponding service with the potential of described user, specifically comprise:

Determine to obtain the potential parameter be intended to needed for corresponding service with described user, the context sight of short message according to required parameter acquiring;

Potentially corresponding recommendation explanation is intended to described according to described context scenarios generation.

7. according to the arbitrary described method of claim 1 to 6, it is characterized in that, described acquisition and described user potential also comprises after being intended to corresponding service:

When the quantity of described service is at least two, according to preset service type, described service is merged, obtain first service set;

From described first service set, obtain the service of predetermined number, and be presented on interface after the service of described predetermined number is sorted according to the laminating degree with described short message and select for user.

8. a terminal, is characterized in that, comprising:

Message retrieval unit, for obtaining the short message in terminal;

Intention assessment unit, for described short message is carried out language parse, obtains the potential intention of user corresponding to described short message;

Service acquisition unit, for the potential intention according to described user, obtains and is intended to corresponding service with the potential of described user.

9. terminal according to claim 8, is characterized in that, described intention assessment unit comprises:

Subelement resolved in morphology, for described short message is carried out morphology parsing, obtains the logical relation between the concept of word in described short message, attribute and described word;

First determines subelement, for determining according to the concept of described word or attribute the named entity that described word is corresponding;

Second determines subelement, for according to the logical relation between described named entity and described word, determines the potential intention of the user that described short message is corresponding.

10. terminal according to claim 9, is characterized in that, described intention assessment unit also comprises:

Syntactic Recognition subelement, for determining the part of speech of described word, the syntactic structure of short message according to the part of speech identification of described word;

Described second determine subelement specifically for,

According to the syntactic structure of the logical relation between described named entity, described word and described short message, determine the potential intention of the user that described short message is corresponding.

Terminal described in 11. according to Claim 8 to 10 any one, it is characterized in that, described terminal also comprises:

Probability acquiring unit, for when the potential intention of the short message correspondence at least two that described service acquisition unit obtains, according to intent model, the probability of each potential intention correspondence at least two potential intentions described in acquisition;

Intention filter element, for the probability corresponding according to potential intention each in described at least two potential intentions, the potential intention of screening predetermined number.

12. terminals according to claim 11, is characterized in that, described terminal also comprises:

Model training unit, according to the historical operating data of user, utilizes the historical operating data of machine learning method to described user to train, obtains described intent model;

Described probability acquiring unit, specifically for when the potential intention of the short message correspondence at least two that described service acquisition unit obtains, according to the intent model of described model training module training, the probability that at least two potential intentions described in acquisition, each potential intention is corresponding.

Terminal described in 13. according to Claim 8 to 12 are arbitrary, it is characterized in that, described service acquisition unit comprises:

Sight obtains subelement, for determining to obtain the potential parameter be intended to needed for corresponding service with described user, the context sight of short message according to required parameter acquiring;

Illustrate and generate subelement, for potential being intended to corresponding recommendation explanation according to described context scenarios generation with described.

Terminal described in 14. according to Claim 8 to 13 any one, it is characterized in that, described terminal also comprises:

Service merge cells, for when the quantity of the service that described service acquisition unit obtains is at least two, merges described service according to preset service type, obtains first service set;

Service display unit, for obtaining the service of predetermined number from described first service set, and is presented on interface after the service of described predetermined number being sorted according to the laminating degree with described short message and selects for user.