[go: up one dir, main page]

CN105426409B - Data query method and device - Google Patents

Data query method and device Download PDF

Info

Publication number
CN105426409B
CN105426409B CN201510732088.0A CN201510732088A CN105426409B CN 105426409 B CN105426409 B CN 105426409B CN 201510732088 A CN201510732088 A CN 201510732088A CN 105426409 B CN105426409 B CN 105426409B
Authority
CN
China
Prior art keywords
user
mouth
query result
result
query
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.)
Expired - Fee Related
Application number
CN201510732088.0A
Other languages
Chinese (zh)
Other versions
CN105426409A (en
Inventor
王务志
王军
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Qihoo Technology Co Ltd
Qizhi Software Beijing Co Ltd
Original Assignee
Beijing Qihoo Technology Co Ltd
Qizhi Software Beijing Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing Qihoo Technology Co Ltd, Qizhi Software Beijing Co Ltd filed Critical Beijing Qihoo Technology Co Ltd
Priority to CN201510732088.0A priority Critical patent/CN105426409B/en
Publication of CN105426409A publication Critical patent/CN105426409A/en
Application granted granted Critical
Publication of CN105426409B publication Critical patent/CN105426409B/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90Details of database functions independent of the retrieved data types
    • G06F16/95Retrieval from the web
    • G06F16/955Retrieval from the web using information identifiers, e.g. uniform resource locators [URL]

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)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The present invention provides a kind of data query method and apparatus, this method comprises: the shape of the mouth as one speaks variation to user carries out feature extraction, obtains shape of the mouth as one speaks variation characteristic;According to shape of the mouth as one speaks variation characteristic and semantic information library, corresponding first semantic information of shape of the mouth as one speaks variation characteristic is determined;Wherein, which includes the corresponding relationship of each shape of the mouth as one speaks variation characteristic and each semantic information;Search index is determined according to the first semantic information, and the corresponding query result of search index is obtained from network server according to search index and is shown, so that user improves convenient degree when user query content without being manually entered.

Description

Data query method and apparatus
Technical field
The present invention relates to Internet technical field more particularly to a kind of data query method and apparatus.
Background technique
Currently, search engine has become research tool indispensable in people's life, people can be by various each The search engine of sample is from obtaining required for oneself on network server or the content inquired.For example, Baidu, 360 search, Google search, there are also some map searches etc..
In general, people obtain relevant content by search engine from network server, it is by search engine Input frame in be manually entered corresponding search index, then click search after, from the background can according to the search index from network take It is engaged in obtaining various webpages corresponding to the search index in the database of device.
But it is above-mentioned shown in this way of search, need user to be manually entered, be inconvenient to be manually entered in some users Scene under, user can not just obtain required content in time, therefore the convenient degree of user query data is not high.
Summary of the invention
The present invention provides a kind of data query method and apparatus, solving current some user's inconvenience manual queries Required inquiry content can not be obtained in time, the technical problem for causing the convenient degree of user query data not high.
In a first aspect, the present invention provides a kind of data query method, comprising:
Feature extraction is carried out to the shape of the mouth as one speaks variation of user, obtains shape of the mouth as one speaks variation characteristic;
According to shape of the mouth as one speaks variation characteristic and semantic information library, corresponding first semantic information of shape of the mouth as one speaks variation characteristic is determined;Wherein, The semantic information library includes the corresponding relationship of each shape of the mouth as one speaks variation characteristic and each semantic information;
Search index is determined according to the first semantic information, and the inquiry rope is obtained from network server according to the search index Draw corresponding query result and shows.
Optionally, the corresponding query result of search index is being obtained from network server according to search index and is showing it Afterwards, the above method further include:
Acquisition judgement operation is executed, judging result is obtained;Wherein, acquisition judgement operation includes: acquisition user for inquiry As a result the first behavior act triggered, and judge the first behavior act whether with it is dynamic in preset first user behavior set It matches;
If judging result is that the first behavior act is matched with the movement in the first user behavior set, it is determined that query result Correctly.
To after determining that query result is correct, further includes:
Correlation inquiry result and the first behavior act obtain related information;
Related information is stored to caching.
Optionally, the above method further include: if judging result is in the first behavior act and the first user behavior set Movement mismatches, then judges whether the first behavior act matches with the movement in second user behavior set;
If so, determining that query result is initial query as a result, and indicating that user inputs depth relevant to search index Search index;
According to depth search index and initial query as a result, obtaining new query result;
Acquisition judgement operation is executed to new query result, until new query result is correct or executes acquisition judgement behaviour Until the number of work meets preset times.
Optionally, the above method further include: if the movement in the first behavior act and second user behavior set mismatches, It determines inquiry failure, exits inquiry.
Second aspect, the present invention provide a kind of data query device, comprising:
Image capture module carries out feature extraction for the shape of the mouth as one speaks variation to user, obtains shape of the mouth as one speaks variation characteristic;
Image processing module, shape of the mouth as one speaks variation characteristic and semantic information library for being obtained according to image capture module determine Corresponding first semantic information of shape of the mouth as one speaks variation characteristic, and search index is determined according to the first semantic information;Wherein, the semantic information Library includes the corresponding relationship of each shape of the mouth as one speaks variation characteristic and each semantic information;
Enquiry module, the search index for being determined according to image processing module obtain the search index from network server Corresponding query result is simultaneously shown.
Optionally, above-mentioned data query device further include:
First judgment module, for corresponding from network server acquisition search index according to search index in enquiry module After query result and display, acquisition judgement operation, acquisition judging result are executed;Wherein, acquisition judgement operation includes: that acquisition is used Family is directed to the first behavior act for being triggered of query result, and judge the first behavior act whether with preset first user behavior Movement matching in set;
First determining module, the judging result for obtaining in first judgment module are the first behavior act and the first user When movement in behavior set matches, determine that query result is correct.
Optionally, above-mentioned data query device further include:
Relating module, for after the first determining module determines that query result is correct, correlation inquiry result and the first row For movement, related information is obtained;
Memory module, the related information for storing relating module acquisition extremely cache.
Optionally, above-mentioned data query device further include:
Second judgment module is the first behavior act and the first user behavior for the judging result in first judgment module When movement in set mismatches, judge whether the first behavior act matches with the movement in second user behavior set;
Second determining module, for determining when the first behavior act is matched with the movement in second user behavior set Query result is initial query as a result, and indicating that user inputs depth search index relevant to search index;
Module is obtained, depth search index and the initial query for obtaining according to the second determining module are as a result, obtain new Query result;
First judgment module is also used to execute new query result acquisition judgement operation, until new query result is just Really or execution acquires until judging that the number of operation meets preset times.
Optionally, above-mentioned second determining module is also used to dynamic in the first behavior act and second user behavior set When mismatching, determines inquiry failure, exit inquiry.
Data query method and apparatus provided by the invention carry out feature by the shape of the mouth as one speaks variation to user and obtain shape of the mouth as one speaks change Change feature, and corresponding first semanteme of the shape of the mouth as one speaks variation characteristic is determined according to the shape of the mouth as one speaks variation characteristic and preset semantic information library Information, to obtain query result from network server according to the corresponding search index of the first semantic information and be shown to use Family, so that user improves convenient degree when user query content without being manually entered;On the other hand, the embodiment of the present invention Method only can get query result by the shape of the mouth as one speaks variation characteristic of user, input voice without user, for vocal cords by Damage even part disabled person is also suitable, and it greatly improves the scope of applications of data query, more improve user and use just Prompt degree.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is this hair Bright some embodiments for those of ordinary skill in the art without any creative labor, can be with It obtains other drawings based on these drawings.
Fig. 1 is the flow diagram of data query embodiment of the method one provided by the invention;
Fig. 2 is the flow diagram of data query embodiment of the method two provided by the invention;
Fig. 3 is the flow diagram of data query embodiment of the method three provided by the invention;
Fig. 4 is the structural schematic diagram of data query device embodiment one provided by the invention;
Fig. 5 is the structural schematic diagram of data query device embodiment two provided by the invention;
Fig. 6 is the structural schematic diagram of data query device embodiment three provided by the invention.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art Every other embodiment obtained without creative efforts, shall fall within the protection scope of the present invention.
The present embodiments relate to method, can be adapted for any one search engine, to solve in the prior art Way of search be unable to satisfy some users can not manual queries scene so that user can not obtain the interior of inquiry in time Hold, the technical problem for causing user query convenient degree not high.
The executing subject of the present embodiment can be data query device, which can integrate in various terminals In, which can be mobile phone, personal digital assistant, tablet computer, vehicle mounted guidance etc., realization of the embodiment of the present invention to terminal Form and without limitation.
Technical solution of the present invention is described in detail with specifically embodiment below.These specific implementations below Example can be combined with each other, and the same or similar concept or process may be repeated no more in some embodiments.
Fig. 1 is the flow diagram of data query embodiment of the method one provided by the invention.What is involved is logical for the present embodiment It crosses to be changed according to the shape of the mouth as one speaks of user and determines search index, and the specific mistake of the inquiry content according to needed for search index acquisition user Journey.As shown in Figure 1, this method comprises:
S101: feature extraction is carried out to the shape of the mouth as one speaks variation of user, obtains shape of the mouth as one speaks variation characteristic.
Specifically, inquiring data on network and user is current is inconvenient to be manually entered search index when user needs to inquire When, search index can be transferred to data query device, optionally, the oral expression by user by way of oral expression Mode can be the noiseless shape of the mouth as one speaks expression of user, can also be the sound shape of the mouth as one speaks expression of user, the embodiment of the present invention is to user's The decibel value and without limitation of shape of the mouth as one speaks expression.
Data query device, which can change the shape of the mouth as one speaks of above-mentioned user, carries out feature extraction, obtains shape of the mouth as one speaks variation characteristic.It can Choosing, the process that this feature is extracted is actually that the process of feature modeling is carried out to the shape of the mouth as one speaks of people, for example, can use geometry spy The method of sign.Since face is locally to be made of eyes, nose, mouth, chin etc., and the variation of mouth can involve face face Variation, the variation of face features caused by each shape of the mouth as one speaks can correspond to a kind of semantic information.That is, user is each A kind of corresponding shape of the mouth as one speaks variation characteristic of shape of the mouth as one speaks variation, the corresponding semantic information of each shape of the mouth as one speaks variation characteristic.Optionally, above-mentioned mouth Type variation characteristic can be one, be also possible to it is multiple, number according to user shape of the mouth as one speaks change frequency depending on.
S102: according to shape of the mouth as one speaks variation characteristic and semantic information library, the corresponding first semantic letter of the shape of the mouth as one speaks variation characteristic is determined Breath;Wherein, which includes the corresponding relationship of each shape of the mouth as one speaks variation characteristic and each semantic information.
Specifically, being looked into preset semantic information library after data query device obtains above-mentioned shape of the mouth as one speaks variation characteristic Ask corresponding first semantic information of the shape of the mouth as one speaks variation characteristic.It should be noted that the semantic information library includes each shape of the mouth as one speaks variation Corresponding relationship between feature and each semantic information can be research staff and be previously integrated in data query device, can also Being stored in data query device by continuous self study.
S103: search index is determined according to the first semantic information, and obtaining according to the search index from network server should The corresponding query result of search index is simultaneously shown.
Specifically, being looked into after data query device has determined the first semantic information according to first semantic information determination Index is ask, optionally, can be and format first semantic information, be converted into meeting the format of search index, it can Choosing, it can also be and first semantic information is parsed again, obtain the keyword in first semantic information, by the pass Key word is as search index.Later, identified search index can be sent to network server, network clothes by data query device Business device searches query result corresponding with the search index according to the search index from database, and returns to data query dress It sets, and then data query device shows the query result of above-mentioned acquisition.
It should be noted that above-mentioned search index can be level-one index, if found using level-one index comprising looking into The set for asking result, can be inquired using the even more advanced index of secondary index again, until needed for user can find Precise contents, this part may refer to the description of following embodiments.
Data query method provided in an embodiment of the present invention carries out feature by the shape of the mouth as one speaks variation to user and obtains shape of the mouth as one speaks change Change feature, and corresponding first semanteme of the shape of the mouth as one speaks variation characteristic is determined according to the shape of the mouth as one speaks variation characteristic and preset semantic information library Information, to obtain query result from network server according to the corresponding search index of the first semantic information and be shown to use Family, so that user improves convenient degree when user query content without being manually entered;On the other hand, the embodiment of the present invention Method only can get query result by the shape of the mouth as one speaks variation characteristic of user, input voice without user, for vocal cords by Damage even part disabled person is also suitable, and it greatly improves the scope of applications of data query, more improve user and use just Prompt degree.
Fig. 2 is the flow diagram of data query embodiment of the method two provided by the invention.On the basis of above-described embodiment On, the present embodiment what is involved is data query device according to the behavior act of user determine query result whether correctly specific mistake Journey.Further, after above-mentioned S103, this method can also include:
S201: acquisition judgement operation is executed, judging result is obtained;Wherein, acquisition judgement operation includes: acquisition user's needle To the first behavior act that above-mentioned query result is triggered, and judge first behavior act whether with preset first user row For the movement matching in set.
Specifically, after query result is pushed to user by data query device, timely triggering collection judgement operation, with Obtain judging result, it may be assumed that after user knows the query result, the first behavior act can be made for the query result, thus Data query device can acquire the first behavior act of user, and judge first behavior act whether with the first user behavior collection Movement matching in conjunction.It should be noted that movement included in the first user behavior set, is for when inquiry knot The movement appointed when fruit is correct, for example, may include the number of user's blink, that user nods, user touches left ear etc. is dynamic Make, it is correct that these movements are used to characterization query result.
S202: if above-mentioned judging result is that the first behavior act is matched with the movement in the first user behavior set, really Fixed above-mentioned query result is correct.
Specifically, when data query device determines any action in the first behavior act and the first user behavior set Timing, so that it may determine that the query result is correct.It should be noted that the first behavior act mentioned here and first user's row For set in any action matching, can be movement it is identical, can also be that similarity reaches a certain preset threshold, this hair Bright embodiment is to judging matched mode and without limitation.
Optionally, after above-mentioned S202, the above method can also include: S203: be associated with above-mentioned query result and first Behavior act obtains related information, and stores the related information to caching.
Specifically, the first behavior of correct query result and user are moved after determining that above-mentioned query result is correct It is associated with to obtain related information, and then the related information is stored to caching, can user be inquired next time in this way When identical content, as long as detecting that user makes the first behavior act for query result, data query device can be fast It is correctly, without redefining from the first user behavior set, to improve the response of inquiry that speed, which reflects the query result, Speed.
Data query method provided in an embodiment of the present invention is directed to the first behavior that query result is made by acquisition user Movement, and determine whether the query result for being pushed to user is correct according to first behavior act and the first user behavior set, Improve the intelligence of data query, and when determining that query result is correct, the first behavior act of timely association user and Query result, and related information is stored to caching, so that user is when inquiring identical content next time, as long as detecting use The first behavior act is made for query result in family, and it is correct that data query device, which can reflect rapidly the query result, , without redefining from the first user behavior set, improve the response speed of inquiry.
Fig. 3 is the flow diagram of data query embodiment of the method three provided by the invention.In the base of above-described embodiment two On plinth, what is involved is data query devices to judge moving in the first behavior act and the first user behavior set for the present embodiment When mismatching, the detailed process of depth inquiry is carried out.Further, after above-mentioned S201, this method can also include:
S301: judge whether the first behavior act matches with the movement in second user behavior set.If so, executing S302, if it is not, then executing S305.
Specifically, when data query device determines that the first behavior act and any action in the first user behavior set are equal When mismatch, data query device judge again first behavior act whether with the movement in second user behavior set Match.Movement in the second user behavior set is arranged when for query result being initial query result, which can be with Including some movements different from movement in the first user behavior set, the number shaken the head for example including user, eyes of user One opens out.
S302: determine that above-mentioned query result is initial query as a result, and indicating that user's input is related to above-mentioned search index Depth search index.
Specifically, when data query device determine it is any dynamic in above-mentioned first behavior act and second user behavior set When matching, it is determined that above-mentioned query result is initial query as a result, for example, user query " motor vehicle ", data query device Be pushed to user is chained address (chained address of car, the chained address of offroad vehicle, the truck of multiple motor vehicle types Chained address, chained address of sport car etc.), then when user sees that query result is these above-mentioned chained addresses, user is made The movement (i.e. the first behavior act) that eyes one are opened out, then data query device judges that first behavior act and first is used Movement in family behavior set mismatches, but matches with the movement in second user behavior set, therefore data query device Determine that above-mentioned query result is initial query as a result, it further indicates that user inputs depth relevant to " motor vehicle " and inquires rope Draw, such as " car of XX brand ".Therefore user can make the variation of the corresponding shape of the mouth as one speaks again so that data query device according to The shape of the mouth as one speaks that family is made again changes the depth search index for determining that user is inputted.
S303: according to depth search index and initial query as a result, obtaining new query result.
S304: above-mentioned acquisition judgement operation is executed to the new query result, until new query result is correct or holds Until the number of row acquisition judgement operation meets preset times.
Specifically, after data query device obtains user and inputs depth search index again, in conjunction with above-mentioned initial query As a result, determining new query result.Then data query device executes acquisition judgement operation to the new query result again, i.e., Judge the first new behavior act that user makes for the new query result whether with it is dynamic in the first user behavior set It matches;If matching, it is determined that the new query result is correct, if mismatching, judges the first new behavior act again Whether matched with the movement in second user behavior set, if matching, illustrates that the new query result is still one new Initial query as a result, then data query device again indicates that user inputs new depth search index, and so on, until really Until fixed new query result is correct or until the number of the above-mentioned acquisition judgement operation of execution meets preset times.
S305: it if the movement in the first behavior act and second user behavior set mismatches, determines inquiry failure, exits Inquiry.
It can cite a plain example herein, completely to illustrate the technical solution of the embodiment of the present invention:
For example, when user is when kitchen is cooked, when user currently needs to inquire some menus, but because both hands are occupied And when can not be manually entered search index, user by the shape of the mouth as one speaks change input information for example " way of so-and-so dish " (search index, It is properly termed as level-one index), then data query device will push needed for user to user is related to " way of so-and-so dish " Webpage (query result);
(current web page includes multiple subquery results, is not user institute when the content needed for current web page has user The accurate query result needed), user can blink (the first behavior act), data query by tapping head or eyes Device mismatched according to the first behavior act for judging active user and the first user behavior set but with second user behavior collection Matching is closed, then knows that current web page is an initial query as a result, then user continues to inform the data query device with the shape of the mouth as one speaks How depth inquiry to be carried out, such as user can input " the X connection for opening the webpage " again (depth search index, can be with Referred to as secondary index), data query device shows user institute to user according to the webpage of the depth search index and above-mentioned determination The content (new query result) needed, under then user moves two by two followings of point or eyes (the first new behavior act), Data query device judgement current new the first behavior act and the first user behavior sets match, then know current inquiry knot Fruit is correct, and later, the level-one index of user is associated with query result and records by data query device, secondary index is looked into new It askes result to be associated and record, to improve the response speed of subsequent query.
Those of ordinary skill in the art will appreciate that: realize that all or part of the steps of above-mentioned each method embodiment can lead to The relevant hardware of program instruction is crossed to complete.Program above-mentioned can be stored in a computer readable storage medium.The journey When being executed, execution includes the steps that above-mentioned each method embodiment to sequence;And storage medium above-mentioned include: ROM, RAM, magnetic disk or The various media that can store program code such as person's CD.
Fig. 4 is the structural schematic diagram of data query device embodiment one provided by the invention.The data query device can be with It is integrated in any one terminal.As shown in figure 4, the data query device includes: image capture module 10, image processing module 11 and enquiry module 12.
Specifically, image capture module 10, carries out feature extraction for the shape of the mouth as one speaks variation to user, it is special to obtain shape of the mouth as one speaks variation Sign;
Image processing module 11, the shape of the mouth as one speaks variation characteristic and semanteme for being obtained according to described image acquisition module 10 Information bank determines corresponding first semantic information of the shape of the mouth as one speaks variation characteristic, and according to first semantic information determination Search index;Wherein, institute's semantic information library includes the corresponding relationship of each shape of the mouth as one speaks variation characteristic and each semantic information;
Enquiry module 12, the search index for being determined according to described image processing module 11 are obtained from network server It takes the corresponding query result of the search index and shows.
Data query device provided in an embodiment of the present invention can execute above-mentioned embodiment of the method shown in FIG. 1, realize Principle is similar with technical effect, and details are not described herein.
Fig. 5 is the structural schematic diagram of data query device embodiment two provided by the invention.In above-mentioned embodiment illustrated in fig. 4 On the basis of, further, above-mentioned data query device can also include: first judgment module 13, the first determining module 14, can Choosing, can also include relating module 15 and memory module 16.
Specifically, first judgment module 13, in the enquiry module 12 according to the search index from network service After device obtains the corresponding query result of the search index and shows, acquisition judgement operation is executed, judging result is obtained;Its In, the acquisition judgement operation includes: to acquire user to be directed to the first behavior act that the query result is triggered, and judge institute State whether the first behavior act matches with the movement in preset first user behavior set.
First determining module 14, the judging result for obtaining in the first judgment module 13 are the first row When matching for movement with the movement in the first user behavior set, determine that the query result is correct;
Relating module 15 is used for after first determining module 14 determines that the query result is correct, described in association Query result and first behavior act obtain related information;
Memory module 16 is extremely cached for storing the related information that the relating module 15 obtains.
Data query device provided in an embodiment of the present invention can execute above-mentioned embodiment of the method shown in Fig. 2, realize Principle is similar with technical effect, and details are not described herein.
Fig. 6 is the structural schematic diagram of data query device embodiment three provided by the invention.In above-mentioned embodiment illustrated in fig. 5 On the basis of, further, above-mentioned data query device can also include: the second judgment module 17,18 and of the second determining module Obtain module 19.
Specifically, the second judgment module 17, is the first row for the judging result in the first judgment module 13 When mismatching to act with the movement in the first user behavior set, judge whether first behavior act is used with second Movement matching in family behavior set;
Second determining module 18, for being matched in first behavior act with the movement in second user behavior set When, determine that the query result is initial query as a result, and indicating that user inputs depth inquiry relevant to the search index Index;
Obtain module 19, the depth search index and the primary for obtaining according to second determining module 18 Query result obtains new query result;
The first judgment module 13 is also used to execute the new query result acquisition judgement operation, until Until the new query result is correct or the execution acquisition judges that the number of operation meets preset times.
Optionally, above-mentioned second determining module 18 is also used in first behavior act and second user behavior set In movement mismatch when, determine inquiry failure, exit inquiry.
Data query device provided in an embodiment of the present invention can execute above-mentioned embodiment of the method shown in Fig. 3, realize Principle is similar with technical effect, and details are not described herein.
Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention., rather than its limitations;To the greatest extent Pipe present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: its according to So be possible to modify the technical solutions described in the foregoing embodiments, or to some or all of the technical features into Row equivalent replacement;And these are modified or replaceed, various embodiments of the present invention technology that it does not separate the essence of the corresponding technical solution The range of scheme.

Claims (6)

1. a kind of data query method characterized by comprising
Feature extraction is carried out to the shape of the mouth as one speaks variation of user, obtains shape of the mouth as one speaks variation characteristic;
According to the shape of the mouth as one speaks variation characteristic and semantic information library, corresponding first semantic information of the shape of the mouth as one speaks variation characteristic is determined; Wherein, institute's semantic information library includes the corresponding relationship of each shape of the mouth as one speaks variation characteristic and each semantic information;
Search index is determined according to first semantic information, and is looked into described in obtaining from network server according to the search index It askes and indexes corresponding query result and show;
Acquisition judgement operation is executed, judging result is obtained;Wherein, the acquisition judgement operation includes: acquisition user for described The first behavior act that query result is triggered, and judge first behavior act whether with preset first user behavior collection Movement matching in conjunction;
If the judging result is that first behavior act is matched with the movement in the first user behavior set, it is determined that The query result is correct;
If the judging result is that the movement in the first behavior act and the first user behavior set mismatches, institute is judged State whether the first behavior act matches with the movement in second user behavior set;
If so, determining that the query result is initial query as a result, and indicating that user's input is relevant to the search index Depth search index;
According to the depth search index and the initial query as a result, obtaining new query result;
The acquisition judgement operation is executed to the new query result, until the new query result is correct or executes institute State acquisition judgement operation number meet preset times until.
2. the method according to claim 1, wherein after the determination query result is correct, further includes:
It is associated with the query result and first behavior act, obtains related information;
The related information is stored to caching.
3. the method according to claim 1, wherein the method also includes:
If the movement in first behavior act and second user behavior set mismatches, determines inquiry failure, exit inquiry.
4. a kind of data query device characterized by comprising
Image capture module carries out feature extraction for the shape of the mouth as one speaks variation to user, obtains shape of the mouth as one speaks variation characteristic;
Image processing module, the shape of the mouth as one speaks variation characteristic and semantic information library for being obtained according to described image acquisition module, It determines corresponding first semantic information of the shape of the mouth as one speaks variation characteristic, and search index is determined according to first semantic information;Its In, institute's semantic information library includes the corresponding relationship of each shape of the mouth as one speaks variation characteristic and each semantic information;
Enquiry module, for according to described image processing module determine the search index from network server obtain described in look into It askes and indexes corresponding query result and show;
First judgment module, for obtaining the inquiry rope from network server according to the search index in the enquiry module After drawing corresponding query result and showing, acquisition judgement operation is executed, judging result is obtained;Wherein, the acquisition judgement behaviour Work includes: to acquire user to be directed to the first behavior act that the query result is triggered, and judge that first behavior act is The no movement with preset first user behavior set matches;
First determining module, the judging result for being obtained in the first judgment module be first behavior act with When movement in the first user behavior set matches, determine that the query result is correct;
Second judgment module is the first behavior act and described first for the judging result in the first judgment module When movement in user behavior set mismatches, judge first behavior act whether with moving in second user behavior set It matches;
Second determining module, for determining when first behavior act is matched with the movement in second user behavior set The query result is initial query as a result, and indicating that user inputs depth search index relevant to the search index;
Obtain module, the depth search index and the initial query knot for obtaining according to second determining module Fruit obtains new query result;
The first judgment module is also used to execute the new query result acquisition judgement operation, until described new Query result it is correct or execute until the number of the acquisition judgement operation meets preset times.
5. data query device according to claim 4, which is characterized in that the data query device further include:
Relating module, for being associated with the query result after first determining module determines that the query result is correct With first behavior act, related information is obtained;
Memory module is extremely cached for storing the related information that the relating module obtains.
6. data query device according to claim 4, which is characterized in that second determining module is also used in institute When stating the movement mismatch in the first behavior act and second user behavior set, determines inquiry failure, exit inquiry.
CN201510732088.0A 2015-11-02 2015-11-02 Data query method and device Expired - Fee Related CN105426409B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201510732088.0A CN105426409B (en) 2015-11-02 2015-11-02 Data query method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201510732088.0A CN105426409B (en) 2015-11-02 2015-11-02 Data query method and device

Publications (2)

Publication Number Publication Date
CN105426409A CN105426409A (en) 2016-03-23
CN105426409B true CN105426409B (en) 2019-02-22

Family

ID=55504621

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201510732088.0A Expired - Fee Related CN105426409B (en) 2015-11-02 2015-11-02 Data query method and device

Country Status (1)

Country Link
CN (1) CN105426409B (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102223609A (en) * 2011-05-31 2011-10-19 福建物联天下信息科技有限公司 System for triggering information sending through actions
CN102332203A (en) * 2011-05-31 2012-01-25 福建物联天下信息科技有限公司 System for operating and controlling other apparatuses through motion behavior
CN104199545A (en) * 2014-08-28 2014-12-10 青岛海信移动通信技术股份有限公司 Method and device for executing preset operations based on mouth shapes
CN104965592A (en) * 2015-07-08 2015-10-07 苏州思必驰信息科技有限公司 Voice and gesture recognition based multimodal non-touch human-machine interaction method and system
CN104992156A (en) * 2015-07-07 2015-10-21 济南大学 Gesture control method based on flexible mapping between gesture and multiple meanings

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10444979B2 (en) * 2011-01-31 2019-10-15 Microsoft Technology Licensing, Llc Gesture-based search
US20140046922A1 (en) * 2012-08-08 2014-02-13 Microsoft Corporation Search user interface using outward physical expressions

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102223609A (en) * 2011-05-31 2011-10-19 福建物联天下信息科技有限公司 System for triggering information sending through actions
CN102332203A (en) * 2011-05-31 2012-01-25 福建物联天下信息科技有限公司 System for operating and controlling other apparatuses through motion behavior
CN104199545A (en) * 2014-08-28 2014-12-10 青岛海信移动通信技术股份有限公司 Method and device for executing preset operations based on mouth shapes
CN104992156A (en) * 2015-07-07 2015-10-21 济南大学 Gesture control method based on flexible mapping between gesture and multiple meanings
CN104965592A (en) * 2015-07-08 2015-10-07 苏州思必驰信息科技有限公司 Voice and gesture recognition based multimodal non-touch human-machine interaction method and system

Also Published As

Publication number Publication date
CN105426409A (en) 2016-03-23

Similar Documents

Publication Publication Date Title
JP6987814B2 (en) Visual presentation of information related to natural language conversation
US11314370B2 (en) Method for extracting salient dialog usage from live data
CN114254158B (en) Video generation method and device, and neural network training method and device
CN112840335B (en) User-centric contextual information for browsers
US10628506B2 (en) Using log data to train for automated sourcing
JP6657124B2 (en) Session context modeling for conversation understanding system
US20200372421A1 (en) User-centric browser location
CN113468302A (en) Combining parameters of multiple search queries sharing an interrogation line
JP6361351B2 (en) Method, program and computing system for ranking spoken words
US20180352091A1 (en) Recommendations based on feature usage in applications
CN107943998A (en) A kind of human-machine conversation control system and method for knowledge based collection of illustrative plates
JP2019501466A (en) Method and system for search engine selection and optimization
CN109145204A (en) The generation of portrait label and application method and system
WO2020056621A1 (en) Learning method and apparatus for intention recognition model, and device
CN106886567A (en) Microblogging incident detection method and device based on semantic extension
US20240045904A1 (en) System and method of providing search and replace functionality for videos
US20200027064A1 (en) Task execution based on activity clusters
WO2021147421A1 (en) Automatic question answering method and apparatus for man-machine interaction, and intelligent device
CN113190746B (en) Recommended model evaluation methods, devices and electronic equipment
WO2023246719A1 (en) Method and apparatus for processing meeting record, and device and storage medium
WO2020233381A1 (en) Speech recognition-based service request method and apparatus, and computer device
CN119557462A (en) Information retrieval method, device, equipment, readable storage medium and program product
CN105426409B (en) Data query method and device
TW202316291A (en) Patent search system and method thereof
US20130231918A1 (en) Splitting term lists recognized from speech

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant
CF01 Termination of patent right due to non-payment of annual fee
CF01 Termination of patent right due to non-payment of annual fee

Granted publication date: 20190222

Termination date: 20211102