CN109947541A - Task executing method and device, the device for task execution - Google Patents
Task executing method and device, the device for task execution Download PDFInfo
- Publication number
- CN109947541A CN109947541A CN201711397288.0A CN201711397288A CN109947541A CN 109947541 A CN109947541 A CN 109947541A CN 201711397288 A CN201711397288 A CN 201711397288A CN 109947541 A CN109947541 A CN 109947541A
- Authority
- CN
- China
- Prior art keywords
- target
- analysis result
- target object
- intention
- intended
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- User Interface Of Digital Computer (AREA)
Abstract
The embodiment of the invention provides a kind of task executing method and devices, wherein, the described method includes: recognition target image, determine the target object for including in the target image, according to the attribute information of the target object, it determines and is intended to analysis result, it executes and is intended to the corresponding goal task of analysis result, realize the intention that user is determined according to target image, the automatic function of executing respective objects task, solves the problem of execution complex steps such as lookup application program or input external information, low efficiency.
Description
Technical field
The present invention relates to technical field of data processing, fill more particularly to a kind of task executing method, a kind of task execution
It sets and a kind of device for task execution.
Background technique
People rely increasingly upon smart machine production and living in daily life.For example, by scanning the two-dimensional code
To realize that mobile-phone payment, addition concern number obtain interested information, the ordering number being manually entered on billboard is dialed
Or storage etc..
In the implementation of the present invention, inventor's discovery faces the various information in the external world, corresponding in order to execute
Task, user need to open corresponding application program in smart machine manually, or manually complete input network address, phone
The operation of the information such as number.Due to including many application programs in intelligent terminal, application program required for searching can be more numerous
It is trivial, and input external information is also time-consuming more, all there are problems that low efficiency.
Summary of the invention
In view of the above problems, the embodiment of the present invention proposes one kind and overcomes the above problem or at least be partially solved above-mentioned
Task executing method, task execution device and the device for task execution of problem, the embodiment of the present invention are able to solve lookup
The problem of execution complex steps such as application program or input external information, low efficiency.
To solve the above-mentioned problems, the invention discloses a kind of task executing methods, comprising:
Recognition target image determines the target object for including in the target image；
According to the attribute information of the target object, determines and be intended to analysis result；
Execute the corresponding goal task of the intention analysis result.
Optionally, the identification target object determines that the target object for including in the target image includes:
Based on the identification model being pre-created, the target object for including in the target image is determined.
Optionally, the object type includes at least one of information coding, Function Identification, kind of object.
Optionally, the attribute information includes object type, the attribute information according to the target object, determines meaning
Map analysis result includes:
According to the object type that the target object belongs to, determine that intention corresponding with the object type analyzes result.
Optionally, the attribute information according to the target object determines that being intended to analysis result includes:
In conjunction with historical behavior data relevant to the target object, the corresponding intention analysis knot of the target object is determined
Fruit.
Optionally, when in the target image including multiple target objects, the attribute according to the target object
Information determines that being intended to analysis result includes:
In conjunction with the attribute information of the multiple target object, determines and be intended to analysis result.
Optionally, the attribute information of the multiple target object of the combination determines that being intended to analysis result includes:
According to the attribute information of the first object object, intent classifier is determined；
Determine the associated objects object of the first object object；
It is searched in the intent classifier and analyzes result with the intention of the associated objects object matching.
Optionally, when in the target image including multiple target objects, before the determining intention analysis result,
The method also includes:
For the multiple target object, the first object object for meeting default screening conditions is determined；Wherein, described default
Screening conditions include that the priority of affiliated object type meets setting priority requirement, position in the target image meets setting
Status requirement, area accounting in the target image meet at least one condition in setting area requirements.
Optionally, the corresponding goal task of the intention analysis result that executes includes:
Open the corresponding application program of the intention analysis result；
The goal task is executed in the application program.
Optionally, the method also includes:
Submit target object associated with the goal task to the application program.
Optionally, before the associated objects object to the application program for submitting the goal task, the side
Method further include:
According to the presets of the application program, target object associated with the goal task is converted.
Optionally, the intention analysis result includes multiple, executes the corresponding target of the intention analysis result described
Before task, the method also includes:
There is provided the multiple intention analysis result corresponding intention option；
Goal task is determined according to the selection result for being intended to option.
The embodiment of the present application also discloses a kind of task execution device, comprising:
Object Identification Module, target image, determines the target object for including in the target image for identification；
It is intended to determining module, for the attribute information according to the target object, determines and be intended to analysis result；
Task execution module, for executing the corresponding goal task of the intention analysis result.
Optionally, the Object Identification Module, specifically for determining the target figure based on the identification model being pre-created
The target object for including as in.
Optionally, the object type includes at least one of information coding, Function Identification, kind of object.
Optionally, the attribute information includes object type, the intention determining module, is specifically used for according to the target
The object type of object ownership determines that intention corresponding with the object type analyzes result.
Optionally, the intention determining module includes:
History combination submodule, for determining the target in conjunction with historical behavior data relevant to the target object
The corresponding intention of object analyzes result.
Optionally, when in the target image including multiple target objects, the intention determining module includes:
In conjunction with submodule, for combining the attribute information of the multiple target object, determines and be intended to analysis result.
Optionally, the combination submodule includes:
Determination unit of classifying determines intent classifier for the attribute information according to the first object object；
Affiliated partner determination unit, for determining the associated objects object of the first object object；
As a result searching unit is analyzed for searching in the intent classifier with the intention of the associated objects object matching
As a result.
Optionally, when in the target image including multiple target objects, described device further include:
First object determining module, for it is described it is determining be intended to analysis result before, for the multiple target object,
Determine the first object object for meeting default screening conditions；Wherein, the default screening conditions include the excellent of affiliated object type
First grade meets setting priority requirement, position in the target image meets setting position requirement, area in the target image
Accounting meets at least one condition in setting area requirements.
Optionally, the task execution module includes:
Submodule is opened in service, for opening the corresponding application program of the intention analysis result；
Task execution submodule, for executing the goal task in the application program.
Optionally, described device further include:
Object submits module, for submitting target object associated with the goal task to the application program.
Optionally, described device further include:
Object converting module, for the associated objects object for submitting the goal task to the application program it
Before, according to the presets of the application program, convert target object associated with the goal task.
Optionally, the intention analysis result includes multiple, described device further include:
Option provides module, for providing institute before the corresponding goal task of the execution intention analysis result
State multiple intention options for being intended to analysis result；
Task determining module, for determining goal task according to the selection result for being intended to option.
The embodiment of the present application also discloses a kind of device for task execution, which is characterized in that and it include memory, with
And one perhaps more than one program one of them or more than one program be stored in memory, and be configured to by
It includes the instruction for performing the following operation that one or more than one processor, which execute the one or more programs:
Recognition target image determines the target object for including in the target image；
According to the attribute information of the target object, determines and be intended to analysis result；
Execute the corresponding goal task of the intention analysis result.
Optionally, the identification target object determines that the target object for including in the target image includes:
Based on the identification model being pre-created, the target object for including in the target image is determined.
Optionally, the object type includes at least one of information coding, Function Identification, kind of object.
Optionally, the attribute information includes object type, the attribute information according to the target object, determines meaning
Map analysis result includes:
According to the object type that the target object belongs to, determine that intention corresponding with the object type analyzes result.
Optionally, the attribute information according to the target object determines that being intended to analysis result includes:
In conjunction with historical behavior data relevant to the target object, the corresponding intention analysis knot of the target object is determined
Fruit.
Optionally, when in the target image including multiple target objects, the attribute according to the target object
Information determines that being intended to analysis result includes:
In conjunction with the attribute information of the multiple target object, determines and be intended to analysis result.
Optionally, the attribute information of the multiple target object of the combination determines that being intended to analysis result includes:
According to the attribute information of the first object object, intent classifier is determined；
Determine the associated objects object of the first object object；
It is searched in the intent classifier and analyzes result with the intention of the associated objects object matching.
Optionally, when in the target image including multiple target objects, before the determining intention analysis result,
The method also includes:
For the multiple target object, the first object object for meeting default screening conditions is determined；Wherein, described default
Screening conditions include that the priority of affiliated object type meets setting priority requirement, position in the target image meets setting
Status requirement, area accounting in the target image meet at least one condition in setting area requirements.
Optionally, the corresponding goal task of the intention analysis result that executes includes:
Open the corresponding application program of the intention analysis result；
The goal task is executed in the application program.
Optionally, the method also includes:
Submit target object associated with the goal task to the application program.
Optionally, before the associated objects object to the application program for submitting the goal task, the side
Method further include:
According to the presets of the application program, target object associated with the goal task is converted.
Optionally, the intention analysis result includes multiple, executes the corresponding target of the intention analysis result described
Before task, the method also includes:
There is provided the multiple intention analysis result corresponding intention option；
Goal task is determined according to the selection result for being intended to option.
The embodiment of the present invention includes following advantages:
The embodiment of the present invention can determine the target object for including in the target image, root by recognition target image
According to the attribute information of the target object, determine that being intended to analysis is intended to the corresponding goal task of analysis result as a result, executing, and realizes
Determine the intention of user according to target image, the automatic function of executing respective objects tasks, solve search application program or
The problem of execution complex steps such as person's input external information, low efficiency.
Detailed description of the invention
Fig. 1 shows a kind of step flow chart of task executing method embodiment one of the invention；
Fig. 2 shows a kind of step flow charts of task execution method embodiment two of the invention；
Fig. 3 shows a kind of structural block diagram of task execution device embodiment of the invention；
Fig. 4 is a kind of block diagram of device for task execution shown according to an exemplary embodiment.
Specific embodiment
In order to make the foregoing objectives, features and advantages of the present invention clearer and more comprehensible, with reference to the accompanying drawing and specific real
Applying mode, the present invention is described in further detail.
The embodiment of the present invention can be applied during carrying out intention assessment and performance objective task based on camera,
By recognition target image, the target object for including in target image is determined, according to the attribute information of target object to user's
Intention identified, determine be intended to analysis as a result, and according to be intended to the corresponding system service of analysis call by result, application program or
Network address etc. realizes the intention for determining user according to target image, executes respective objects automatically to execute corresponding goal task
The function of task helps user to solve to search the execution complex steps such as application program or input external information, and low efficiency is asked
Topic.
Referring to Fig.1, a kind of step flow chart of task executing method embodiment one of the invention is shown, specifically can wrap
Include following steps:
Step 101, recognition target image determines the target object for including in the target image.
In embodiments of the present invention, target image include shot by camera, from network downloading obtain,
Saved in picture library etc. the obtained image of the image that gets of various modes or any other applicable mode, the present invention
Embodiment is without limitation.
In embodiments of the present invention, target object be image in can with identified content, may include number, text,
Image etc. or any other applicable form, the embodiment of the present invention are without limitation.For example, target image is camera
The image of the billboard taken, target object are the telephone number on billboard；Or target image takes for camera
Artificial people dress shoes；Or target image is the image of the dog of some kind of camera shooting, target object is figure
Dog as in.
In embodiments of the present invention, when being identified to target image, can according to identification model identify target object or
Person can use OCR (Optical Character Recognition, optical character identification) technology identification target object, or
Any other applicable picture recognition technology of person, the embodiment of the present invention are without limitation.For example, utilizing identification target object
Classifier identifies target image, determines at least one target object in target image, or using OCR technique to target
Image is identified, the word content in target image is obtained, and is analyzed rule digital in word content, is therefrom extracted as electricity
Talk about the target object of number.
May include in target image one or more can identified target object, for example, when camera alignment be printed on
When the printed article of two dimensional code, the target image of acquisition is identified, recognizing has two dimensional code, payment platform in target image
The target objects such as mark；When the opposite dining room billboard for being printed on ordering number of camera, the target image of acquisition is known
Not, recognizing in target image has the target objects such as telephone number, dining room title；When a pair of that camera is worn against someone is high
When with shoes, the target image of acquisition is identified, recognizing in target image has " shoes " target object.
Step 102, it according to the attribute information of the target object, determines and is intended to analysis result.
In embodiments of the present invention, it is intended that analysis result is used to reflect the intention that user is directed to target image, for example, dialing
Phone, addition address list, barcode scanning payment, shopping, vehicle model search, search of animal varieties etc., can specifically include any
Applicable intention is analyzed as a result, the embodiment of the present invention is without limitation.It is ordered for example, user opens one dining room of camera alignment
Meal billboard, identifies to include the texts such as telephone number, dining room title in target image, then may determine that being intended to for user
It makes a phone call, or addition telephone number is into address list.
In embodiments of the present invention, attribute information includes the object type of target object ownership, position locating for target object
Set, the data content of target object etc. or any other applicable information, the embodiment of the present invention it is without limitation.In root
, can be according to the object type of target object when determining intention analysis result according to target object, determination is corresponding with object type
It is intended to analysis as a result, can be determining corresponding with target object and location according to the location of target object
Intention analysis as a result, can be according to the data content of target object itself, the determining data content with target object
The intention analysis matched as a result, any other applicable mode determine and be intended to analysis as a result, the embodiment of the present invention does not do this
Limitation.
In embodiments of the present invention, the target object identified from target image can have one or more.In one kind
In implementation, various attribute informations or a combination thereof can analyze result with various intentions and pre-establish corresponding relationship, with reality
Now the analysis of corresponding intention is determined according to the attribute information of target object as a result, any other applicable mode determine meaning
Map analysis is as a result, the embodiment of the present invention is without limitation.
For example, the scene for a pair of high-heeled shoes that camera above-mentioned is worn against someone, recognizes the mesh in target image
Marking object includes shoes, then is shoes according to object type, and obtain the position being presently in, knot by mobile phone positioning function
Object type and two attribute information of present position are closed, if being currently at market, it is determined that being intended to analysis result is to open shopping
Application program, and search for commodity identical with the shoes；If being currently in family, it is determined that being intended to analysis result is that opening is second-hand
Transaction application programs, and search for commodity identical with the shoes.
In embodiments of the present invention, optionally, it according to the attribute information of the target object, determines and is intended to analysis result
A kind of implementation may include: the object type belonged to according to the target object, and determination is corresponding with the object type
It is intended to analysis result.
Object type includes the classification of the objects in images obtained according to preset mode classification, for example, two dimensional code, phone
Number, express delivery odd numbers, shirt, shoes, vehicle model, dog kind etc. or any other applicable classification, the present invention implemented
Example is without limitation.
In embodiments of the present invention, optionally, object type include information coding, Function Identification, in kind of object at least
It is a kind of.Information coding is to arrange certain character or special pattern according to certain rules to record a kind of coding mode of information, example
Such as, telephone number, express delivery odd numbers, one-dimension code, two dimensional code etc. or any other applicable form, the embodiment of the present invention is to this
With no restrictions.Function Identification includes the various forms such as character or figure, for example, title, the pattern identification of application etc. of application,
Or any other applicable form, the embodiment of the present invention are without limitation.Kind of object includes according to default mode classification
Classification results to the object shown on image, for example, shirt, shoes, automobile model, dog kind etc. or any other
Applicable type, the embodiment of the present invention are without limitation.
It may include one or more target objects in target image, multiple target objects can belong to identical object class
Do not belong to different object type or respectively, can specifically be determined according to the object type that can be identified, the embodiment of the present invention pair
This is with no restrictions.
Object type or a combination thereof can preset corresponding relationship, a kind of intention analysis result with analysis result is intended to
One-to-one mapping relations can be established with a kind of object type, one-to-many mapping can also be established with a variety of object type
Relationship, pre-set corresponding relationship can be stored on local or server, for searching.The object type of target object can
To be determined when target object in recognition target image.When target object has one, according to the object of a target object
Classification can directly determine corresponding intention analysis result.When target object has it is multiple when, can therefrom choose a target pair
As determining that corresponding intention analyzes result according to the object type of selection target object；Or according to each target pair
As corresponding intention being determined according to respective object type respectively, by multiple intentions as intention analysis result；Or it can be with
In conjunction with the object type of multiple target objects, determine corresponding intention analysis as a result, any other applicable mode, this hair
Bright embodiment is without limitation.
For example, the scene of the image of the dog of some kind of camera shooting above-mentioned, recognizes the mesh in target image
Marking object includes dog, then is animal according to object type, determines that being intended to analysis result is to search in animal varieties search engine
With the kind of dog in image.
In embodiments of the present invention, optionally, it according to the attribute information of the target object, determines and is intended to analysis result
A kind of implementation can also include: to determine the target object in conjunction with historical behavior data relevant to the target object
Corresponding intention analyzes result.
According to the attribute information of target object, obtain being intended in analysis result may include one or more intentions.When having
It when multiple intentions, can be combined with historical behavior data relevant to target object, further determine and be intended to from multiple intentions
Analysis is as a result, for example, the common property of the intention according to user, takes notice of in map analysis result the intention often occurred being ordered into phase
Before the intention infrequently occurred, it perhaps can only retain one of intention or any other applicable mode determines
It is intended to analysis as a result, the embodiment of the present invention is without limitation.
For example, camera above-mentioned recognizes in target image against the scene for the dining room billboard for being printed on ordering number
Target object include telephone number, the intention for corresponding to user may be to make a phone call or add address list two, in conjunction with
Historical behavior data, analyze the telephone number that user obtains shooting, and common is intended to addition address list, it is determined that meaning
Map analysis result is addition address list.
Step 103, the corresponding goal task of the intention analysis result is executed.
In embodiments of the present invention, goal task is held needed for referring to complete to be intended to the intention of the user of analysis result reflection
Capable task identifies target image in the object class of target object for example, user, which opens camera, is directed at the shoes that other people wear
Not Wei shoes, determine therefrom that user has shopping to be intended to, it is intended that analysis result is article in purchase figure, and corresponding goal task includes
Shopping application is opened, and opens the picture searching page in shopping application, the shoes picture extracted from target image is uploaded, searches
Rigging has the same money shoes of identical appearance, and shows result of page searching.
Goal task may include calling system service, open third-party application, open the concrete function in applying, open
It links corresponding webpage etc. or any other applicable task or a series of tasks, the embodiment of the present invention is without limitation.
In embodiments of the present invention, optionally, when it includes multiple for being intended to analysis result, the intention point is executed described
It can also include: that multiple intention options for being intended to analysis result are provided, according to the meaning before analysing the corresponding goal task of result
The selection result of figure option determines goal task.
When being intended to analysis result has multiple, it can all be supplied to user and select, determine user according to the user's choice
It is true to be intended to, then determine that goal task is executed.It may include that text is aobvious for the various intention options for being intended to provide
Show option, voice broadcast prompt, the mark of corresponding application program, preview interface of corresponding application program etc. or other
The applicable form of meaning, the embodiment of the present invention are without limitation.
For example, recognizing includes telephone number in target image, it is intended that analysis result may include making a phone call or adding
Adding address list two, pops up prompting frame according to two intention analysis results, user selects, the true intention of user is obtained,
Determine that choosing result to correspond to goal task is to make a phone call, or add address list.
In conclusion according to an embodiment of the present invention, by recognition target image, determining the mesh for including in the target image
Object is marked, according to the attribute information of the target object, determines that being intended to analysis is intended to the corresponding target of analysis result as a result, executing
Task, realizes the intention that user is determined according to target image, and the automatic function of executing respective objects task solves lookup and answers
Complex steps are executed with program or input external information etc., the problem of low efficiency.
Referring to Fig. 2, a kind of step flow chart of task executing method embodiment two of the invention is shown, specifically can wrap
Include following steps:
Step 201, based on the identification model being pre-created, the target object for including in the target image is determined.
In embodiments of the present invention, identification model may include one or more identification models, specifically can be any suitable
For model or classifier of the invention, target image can be identified, obtain the target object in target image.Identification
Model includes the identification model for identifying the various target objects in target image, or the identification mould including multiple object type
Type can identify the target object of corresponding objects classification respectively.
In order to create the identification model that can identify target object, need using the mode of learning for having supervision, according to
For the object type of image pattern label, the image recognition model that can identify object type is obtained.By machine learning algorithm,
The identification model of creation identification target object, is denoted as identification model, is based further on the identification model and identifies that other are to be identified
Target object in image.
In embodiments of the present invention, identification model can the object type based on multiple images sample and correspondence markings,
Identification model can be created.Image pattern includes the multiple images obtained in advance, can specifically be selected from existing all images
It takes all images as sample, perhaps randomly selects parts of images as sample or according to certain rule and choose image conduct
Sample, specifically can image pattern determine according to actual needs, the embodiment of the present invention to this with no restriction.
For multiple images sample, it can be judged according to the content of image pattern, for image pattern label ownership
Object type or image pattern are obtained according to object type respectively in advance, be marked in advance object type or other
Any suitable mode, the embodiment of the present invention are without limitation.
In embodiments of the present invention, identification model may include multiple two classifiers for single object type, can also
To include for the multi-categorizer of multiple object type or any other applicable classifier or image recognition model, this hair
Bright embodiment is without limitation.
It in embodiments of the present invention, can be right using the identification model of creation or any other applicable identification technology
Target image is identified, the target object for belonging to object type is obtained.
Step 202, it in conjunction with the attribute information of the multiple target object, determines and is intended to analysis result.
It in embodiments of the present invention, can be in conjunction with multiple target objects when the target object identified includes multiple
Attribute information obtains being intended to analysis result to analyze the intention of user.It specifically can be according to the data content of multiple target objects
Combination is intended to determine, intention or any other can be perhaps determined according to the combination of the object type of multiple target objects
Applicable combination, the embodiment of the present invention are without limitation.
For example, user above-mentioned opens the scene that camera alignment is printed on the printed article of two dimensional code, target image is recognized
In target object include " payment platform A " near two dimensional code and two dimensional code mark text, then combine two dimensional code and
The two attribute information of mark of payment platform, the intention for corresponding to user may be for by carrying out barcode scanning payment, intentional map analysis
It as a result include barcode scanning payment, and corresponding " payment platform A ".
In embodiments of the present invention, optionally, the multiple target object of the combination determines and is intended to the one of analysis result
Kind implementation may include: to determine intent classifier according to the attribute information of the first object object, determine first mesh
The associated objects object for marking object is searched to analyze with the intention of the associated objects object matching in the intent classifier and be tied
Fruit.
By a target object in multiple target objects, it is denoted as first object object, specifically can arbitrarily choose one
Target object perhaps chooses a target object according to certain condition or any other applicable mode determines the first mesh
Object is marked, the embodiment of the present invention is without limitation.Intent classifier is to a variety of classifications for being intended to divide, in each intent classifier
It may include a variety of intentions, for example, the intention for including, which has, " carries out barcode scanning by payment platform A in intent classifier " barcode scanning payment "
Payment ", " barcode scanning payment is carried out by payment platform B " etc..
According to the attribute information of first object object, after determining intent classifier, then determine and the in multiple target objects
The associated associated objects object of one target object, according to the attribute information of associated objects object, the lookup in the intent classifier
The intention analysis result matched, wherein associated objects object may include one or more, and the embodiment of the present invention does not limit this
System.
For example, the object type " two dimensional code for payment " of first object object, determines therefrom that intent classifier is " barcode scanning
Payment " determines that associated objects object is " mark of payment platform A ", searches and " mark of payment platform A " in intent classifier
Matched intention analysis result " barcode scanning payment is carried out by payment platform A ".
In embodiments of the present invention, optionally, when in target image including multiple target objects, in the determining intention
It can also include: to determine the first object pair for meeting default screening conditions for the multiple target object before analyzing result
As.Intention analysis can be individually determined as a result, or combining other target objects true together in the first object object filtered out
It is fixed be intended to analysis as a result, any other applicable purposes, the embodiment of the present invention it is without limitation.
Wherein, the default screening conditions are for screening target object as first object object, including generic
Priority meets setting priority requirement, position in the target image meets setting position requirement, face in the target image
Product accounting meets at least one condition in setting area requirements.The excellent of setting can be set for the generic of target object
First grade, meeting setting priority requirement may include the forward one or more target objects of priority.Setting position requires
The sets requirement of the position of target object in the target image, for example, position in the target image distance center proximal most position or
Person position is required in a certain range of central area or any other applicable setting position in the target image, the present invention
Embodiment is without limitation.Set the sets requirement of the occupied area of area requirements in the target image as target object, example
Such as, the area ratio is more than half to area in the target image for occupied area ratio maximum or area in the target image,
Or any other applicable sets requirement, the embodiment of the present invention are without limitation.
It, can be according to it when whether having the first object object for meeting default screening conditions in judging multiple target objects
A kind of middle condition is judged, can also be judged that the embodiment of the present invention is without limitation in conjunction with multiple conditions.
Step 203, the corresponding application program of the intention analysis result is opened.
In embodiments of the present invention, application program is for completing goal task, including system service, third party application
And service or any other applicable service that the specific function or access network address wherein provided is obtained from network,
The embodiment of the present invention is without limitation.
According to be intended to analysis result can determine corresponding application program, can specifically pre-save intention analysis result and
The corresponding relationship of application program is perhaps intended in analysis result include required application program or any other applicable side
Formula determines that application program, the embodiment of the present invention are without limitation.
Step 204, the goal task is executed in the application program.
In embodiments of the present invention, after opening application program, goal task is completed using application program, for example, opening system
The service of system made a phone call completes the clothes of addition address list to complete to make a phone call or the Directory service of open system
Business.
It in embodiments of the present invention, optionally, can also include: to submit target object associated with the goal task
To the application program.
, can be before performance objective task if necessary to target object when completing goal task, it will be related to goal task
The target object of connection, is committed to application program.Target object associated with goal task can include determining that goal task
Target object also may include other target objects in target image, specifically can according to the data needed for goal task from
It is searched in multiple target objects or any other applicable mode determines target object associated with goal task, this hair
Bright embodiment is without limitation.
In embodiments of the present invention, optionally, it is answered in the associated objects object for submitting the goal task to described
It can also include: to convert mesh associated with the goal task according to the presets of the application program before program
Mark object.
Presets include application program in processing target task, the sequence of the data format, data of required data, number
According to size specification etc. or any other applicable substantive requirements of form, the embodiment of the present invention it is without limitation.Associated objects pair
As can be arbitrary form, if not meeting presets required by application program, need before submitting target object, it will
Target data is converted to the data of presets, then submits to application program.
For example, shopping application program is when carrying out the processing according to input picture searching commodity, it is desirable that the picture of input is
PNG (Portable Network Graphics, portable network figure) format, and file is less than 1M, is submitting target pair
As preceding, the picture file of target object need to be converted to the picture for meeting presets by format conversion and compression processing
File.
In conclusion according to an embodiment of the present invention, by determining the target image based on the identification model being pre-created
In include target object determine and be intended to analysis as a result, opening the intention in conjunction with the attribute information of the multiple target object
The corresponding application program of result is analyzed, executes the goal task in the application, realizes and determines to use according to target image
The intention at family automatically turns on application program, and executes the function of respective objects task, solves and searches application program or input
The problem of execution complex steps such as external information, low efficiency.
It should be noted that for simple description, therefore, it is stated as a series of movement is dynamic for embodiment of the method
It combines, but those skilled in the art should understand that, the embodiment of the present invention is not by the limit of described athletic performance sequence
System, because according to an embodiment of the present invention, some steps may be performed in other sequences or simultaneously.Secondly, art technology
Personnel also should be aware of, and embodiment described in this description belongs to alternative embodiment, and related athletic performance is simultaneously different
It surely is necessary to the embodiment of the present invention.
Referring to Fig. 3, a kind of structural block diagram of task execution device embodiment of the invention is shown, can specifically include:
Object Identification Module 301, target image, determines the target object for including in the target image for identification；
It is intended to determining module 302, for the attribute information according to the target object, determines and be intended to analysis result；
Task execution module 303, for executing the corresponding goal task of the intention analysis result.
In embodiments of the present invention, optionally, the Object Identification Module, specifically for based on the identification mould being pre-created
Type determines the target object for including in the target image.
In embodiments of the present invention, optionally, the object type includes information coding, Function Identification, in kind of object
It is at least one.
In embodiments of the present invention, optionally, the attribute information includes object type, the intention determining module, tool
Body is used for the object type belonged to according to the target object, determines that intention corresponding with the object type analyzes result.
In embodiments of the present invention, optionally, the intention determining module includes:
History combination submodule, for determining the target in conjunction with historical behavior data relevant to the target object
The corresponding intention of object analyzes result.
In embodiments of the present invention, optionally, described to be intended to really when in the target image including multiple target objects
Cover half block includes:
In conjunction with submodule, for combining the attribute information of the multiple target object, determines and be intended to analysis result.
In embodiments of the present invention, optionally, the combination submodule includes:
Determination unit of classifying determines intent classifier for the attribute information according to the first object object；
Affiliated partner determination unit, for determining the associated objects object of the first object object；
As a result searching unit is analyzed for searching in the intent classifier with the intention of the associated objects object matching
As a result.
In embodiments of the present invention, optionally, when in the target image including multiple target objects, described device is also
Include:
First object determining module, for it is described it is determining be intended to analysis result before, for the multiple target object,
Determine the first object object for meeting default screening conditions；Wherein, the default screening conditions include the excellent of affiliated object type
First grade meets setting priority requirement, position in the target image meets setting position requirement, area in the target image
Accounting meets at least one condition in setting area requirements.
In embodiments of the present invention, optionally, the task execution module includes:
Submodule is opened in service, for opening the corresponding application program of the intention analysis result；
Task execution submodule, for executing the goal task in the application program.
In embodiments of the present invention, optionally, described device further include:
Object submits module, for submitting target object associated with the goal task to the application program.
In embodiments of the present invention, optionally, described device further include:
Object converting module, for the associated objects object for submitting the goal task to the application program it
Before, according to the presets of the application program, convert target object associated with the goal task.
In embodiments of the present invention, optionally, the intention analysis result includes multiple, described device further include:
Option provides module, for providing institute before the corresponding goal task of the execution intention analysis result
State multiple intention options for being intended to analysis result；
Task determining module, for determining goal task according to the selection result for being intended to option.
In conclusion according to an embodiment of the present invention, by recognition target image, determining the mesh for including in the target image
Object is marked, according to the attribute information of the target object, determines that being intended to analysis is intended to the corresponding target of analysis result as a result, executing
Task, realizes the intention that user is determined according to target image, and the automatic function of executing respective objects task solves lookup and answers
Complex steps are executed with program or input external information etc., the problem of low efficiency.
For device embodiment, since it is basically similar to the method embodiment, related so being described relatively simple
Place illustrates referring to the part of embodiment of the method.
Fig. 4 is a kind of block diagram of device 400 for task execution shown according to an exemplary embodiment.For example, dress
Setting 400 can be mobile phone, computer, digital broadcasting terminal, messaging device, game console, tablet device, medical treatment
Equipment, body-building equipment, personal digital assistant etc..
Referring to Fig. 4, device 400 may include following one or more components: processing component 402, memory 404, power supply
Component 406, multimedia component 408, audio component 410, the interface 412 of input/output (I/O), sensor module 414, and
Communication component 416.
The integrated operation of the usual control device 400 of processing component 402, such as with display, telephone call, data communication, phase
Machine operation and record operate associated operation.Processing element 402 may include that one or more processors 420 refer to execute
It enables, to perform all or part of the steps of the methods described above.In addition, processing component 402 may include one or more modules, just
Interaction between processing component 402 and other assemblies.For example, processing component 402 may include multi-media module, it is more to facilitate
Interaction between media component 408 and processing component 402.
Memory 404 is configured as storing various types of data to support the operation in equipment 400.These data are shown
Example includes the instruction of any application or method for operating on device 400, contact data, and telephone book data disappears
Breath, picture, video etc..Memory 404 can be by any kind of volatibility or non-volatile memory device or their group
It closes and realizes, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM) is erasable to compile
Journey read-only memory (EPROM), programmable read only memory (PROM), read-only memory (ROM), magnetic memory, flash
Device, disk or CD.
Power supply module 406 provides electric power for the various assemblies of device 400.Power supply module 406 may include power management system
System, one or more power supplys and other with for device 400 generate, manage, and distribute the associated component of electric power.
Multimedia component 408 includes the screen of one output interface of offer between described device 400 and user.One
In a little embodiments, screen may include liquid crystal display (LCD) and touch panel (TP).If screen includes touch panel, screen
Curtain may be implemented as touch screen, to receive input signal from the user.Touch panel includes one or more touch sensings
Device is to sense the gesture on touch, slide, and touch panel.The touch sensor can not only sense touch or sliding action
Boundary, but also detect and touched or the relevant duration and pressure of taxi operation with described.In some embodiments, more matchmakers
Body component 408 includes a front camera and/or rear camera.When equipment 400 is in operation mode, such as screening-mode or
When video mode, front camera and/or rear camera can receive external multi-medium data.Each front camera and
Rear camera can be a fixed optical lens system or have focusing and optical zoom capabilities.
Audio component 410 is configured as output and/or input audio signal.For example, audio component 410 includes a Mike
Wind (MIC), when device 400 is in operation mode, when such as call mode, recording mode, and voice recognition mode, microphone is matched
It is set to reception external audio signal.The received audio signal can be further stored in memory 404 or via communication set
Part 416 is sent.In some embodiments, audio component 410 further includes a loudspeaker, is used for output audio signal.
I/O interface 412 provides interface between processing component 402 and peripheral interface module, and above-mentioned peripheral interface module can
To be keyboard, click wheel, button etc..These buttons may include, but are not limited to: home button, volume button, start button and lock
Determine button.
Sensor module 414 includes one or more sensors, and the state for providing various aspects for device 400 is commented
Estimate.For example, sensor module 414 can detecte the state that opens/closes of equipment 400, and the relative positioning of component, for example, it is described
Component is the display and keypad of device 400, and sensor module 414 can be with 400 1 components of detection device 400 or device
Position change, the existence or non-existence that user contacts with device 400,400 orientation of device or acceleration/deceleration and device 400
Temperature change.Sensor module 414 may include proximity sensor, be configured to detect without any physical contact
Presence of nearby objects.Sensor module 414 can also include optical sensor, such as CMOS or ccd image sensor, at
As being used in application.In some embodiments, which can also include acceleration transducer, gyro sensors
Device, Magnetic Sensor, pressure sensor or temperature sensor.
Communication component 416 is configured to facilitate the communication of wired or wireless way between device 400 and other equipment.Device
400 can access the wireless network based on communication standard, such as WiFi, 2G or 3G or their combination.In an exemplary implementation
In example, communication component 416 receives broadcast singal or broadcast related information from external broadcasting management system via broadcast channel.
In one exemplary embodiment, the communication component 416 further includes near-field communication (NFC) module, to promote short range communication.Example
Such as, NFC module can be based on radio frequency identification (RFID) technology, Infrared Data Association (IrDA) technology, ultra wide band (UWB) technology,
Bluetooth (BT) technology and other technologies are realized.
In the exemplary embodiment, device 400 can be believed by one or more application specific integrated circuit (ASIC), number
Number processor (DSP), digital signal processing appts (DSPD), programmable logic device (PLD), field programmable gate array
(FPGA), controller, microcontroller, microprocessor or other electronic components are realized, for executing the above method.
In the exemplary embodiment, a kind of non-transitorycomputer readable storage medium including instruction, example are additionally provided
It such as include the memory 404 of instruction, above-metioned instruction can be executed by the processor 420 of device 400 to complete the above method.For example,
The non-transitorycomputer readable storage medium can be ROM, random access memory (RAM), CD-ROM, tape, floppy disk
With optical data storage devices etc..
A kind of non-transitorycomputer readable storage medium, when the instruction in the storage medium is by device (intelligent terminal
Or server) processor execute when, enable a device to execute a kind of task executing method, which comprises
Recognition target image determines the target object for including in the target image；
According to the attribute information of the target object, determines and be intended to analysis result；
Execute the corresponding goal task of the intention analysis result.
Optionally, the identification target object determines that the target object for including in the target image includes:
Based on the identification model being pre-created, the target object for including in the target image is determined.
Optionally, the object type includes at least one of information coding, Function Identification, kind of object.
Optionally, the attribute information includes object type, the attribute information according to the target object, determines meaning
Map analysis result includes:
According to the object type that the target object belongs to, determine that intention corresponding with the object type analyzes result.
Optionally, the attribute information according to the target object determines that being intended to analysis result includes:
In conjunction with historical behavior data relevant to the target object, the corresponding intention analysis knot of the target object is determined
Fruit.
Optionally, when in the target image including multiple target objects, the attribute according to the target object
Information determines that being intended to analysis result includes:
In conjunction with the attribute information of the multiple target object, determines and be intended to analysis result.
Optionally, the attribute information of the multiple target object of the combination determines that being intended to analysis result includes:
According to the attribute information of the first object object, intent classifier is determined；
Determine the associated objects object of the first object object；
It is searched in the intent classifier and analyzes result with the intention of the associated objects object matching.
Optionally, when in the target image including multiple target objects, before the determining intention analysis result,
The method also includes:
For the multiple target object, the first object object for meeting default screening conditions is determined；Wherein, described default
Screening conditions include that the priority of affiliated object type meets setting priority requirement, position in the target image meets setting
Status requirement, area accounting in the target image meet at least one condition in setting area requirements.
Optionally, the corresponding goal task of the intention analysis result that executes includes:
Open the corresponding application program of the intention analysis result；
The goal task is executed in the application program.
Optionally, the method also includes:
Submit target object associated with the goal task to the application program.
Optionally, before the associated objects object to the application program for submitting the goal task, the side
Method further include:
According to the presets of the application program, target object associated with the goal task is converted.
Optionally, the intention analysis result includes multiple, executes the corresponding target of the intention analysis result described
Before task, the method also includes:
There is provided the multiple intention analysis result corresponding intention option；
Goal task is determined according to the selection result for being intended to option.
Those skilled in the art are considering specification and after practicing application disclosed herein, will readily occur to of the invention its
Its embodiment.The present invention is directed to cover any variations, uses, or adaptations of the invention, these modifications, purposes or
Person's adaptive change follows general principle of the invention and including the undocumented common knowledge in the art of the disclosure
Or conventional techniques.The description and examples are only to be considered as illustrative, and true scope and spirit of the invention are by following
Claim is pointed out.
It should be understood that the present invention is not limited to the precise structure already described above and shown in the accompanying drawings, and
And various modifications and changes may be made without departing from the scope thereof.The scope of the present invention is limited only by the attached claims.
The foregoing is merely presently preferred embodiments of the present invention, is not intended to limit the invention, it is all in spirit of the invention and
Within principle, any modification, equivalent replacement, improvement and so on be should all be included in the protection scope of the present invention.
A kind of task executing method provided by the present invention, a kind of task execution device and one kind are held for task above
Capable device, is described in detail, and specific case used herein explains the principle of the present invention and embodiment
It states, the above description of the embodiment is only used to help understand the method for the present invention and its core ideas；Meanwhile for this field
Those skilled in the art, according to the thought of the present invention, there will be changes in the specific implementation manner and application range, to sum up institute
It states, the contents of this specification are not to be construed as limiting the invention.
Claims (14)
1. a kind of task executing method characterized by comprising
Recognition target image determines the target object for including in the target image；
According to the attribute information of the target object, determines and be intended to analysis result；
Execute the corresponding goal task of the intention analysis result.
2. the method according to claim 1, wherein the identification target object, determines in the target image
Including target object include:
Based on the identification model being pre-created, the target object for including in the target image is determined.
3. according to the method described in claim 2, it is characterized in that, the object type includes information coding, Function Identification, object
At least one of body type.
4. described according to institute the method according to claim 1, wherein the attribute information includes object type
The attribute information of target object is stated, determines that being intended to analysis result includes:
According to the object type that the target object belongs to, determine that intention corresponding with the object type analyzes result.
5. the method according to claim 1, wherein the attribute information according to the target object, determines
Being intended to analysis result includes:
In conjunction with historical behavior data relevant to the target object, the corresponding intention analysis result of the target object is determined.
6. the method according to claim 1, wherein when in the target image include multiple target objects when,
The attribute information according to the target object determines that being intended to analysis result includes:
In conjunction with the attribute information of the multiple target object, determines and be intended to analysis result.
7. according to the method described in claim 6, it is characterized in that, the attribute information of the multiple target object of the combination,
Determine that being intended to analysis result includes:
According to the attribute information of the first object object, intent classifier is determined；
Determine the associated objects object of the first object object；
It is searched in the intent classifier and analyzes result with the intention of the associated objects object matching.
8. method according to claim 1 or claim 7, which is characterized in that when in the target image include multiple target objects
When, before the determining intention analysis result, the method also includes:
For the multiple target object, the first object object for meeting default screening conditions is determined；Wherein, the default screening
Condition includes that the priority of affiliated object type meets setting priority requirement, position in the target image meets setting position
It is required that, area accounting in the target image meet at least one condition in setting area requirements.
9. the method according to claim 1, wherein the corresponding target of the intention analysis result that executes is appointed
Business includes:
Open the corresponding application program of the intention analysis result；
The goal task is executed in the application program.
10. according to the method described in claim 9, it is characterized in that, the method also includes:
Submit target object associated with the goal task to the application program.
11. according to the method described in claim 10, it is characterized in that, in the associated objects pair for submitting the goal task
As to before the application program, the method also includes:
According to the presets of the application program, target object associated with the goal task is converted.
12. the method according to claim 1, wherein the intention analysis result include it is multiple, in the execution
Before the intention analyzes the corresponding goal task of result, the method also includes:
There is provided the multiple intention analysis result corresponding intention option；
Goal task is determined according to the selection result for being intended to option.
13. a kind of task execution device characterized by comprising
Object Identification Module, target image, determines the target object for including in the target image for identification；
It is intended to determining module, for the attribute information according to the target object, determines and be intended to analysis result；
Task execution module, for executing the corresponding goal task of the intention analysis result.
14. a kind of device for task execution, which is characterized in that include memory and one or more than one
Program, perhaps more than one program is stored in memory and is configured to by one or more than one processing for one of them
It includes the instruction for performing the following operation that device, which executes the one or more programs:
Recognition target image determines the target object for including in the target image；
According to the attribute information of the target object, determines and be intended to analysis result；
Execute the corresponding goal task of the intention analysis result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711397288.0A CN109947541A (en) | 2017-12-21 | 2017-12-21 | Task executing method and device, the device for task execution |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711397288.0A CN109947541A (en) | 2017-12-21 | 2017-12-21 | Task executing method and device, the device for task execution |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109947541A true CN109947541A (en) | 2019-06-28 |
Family
ID=67006136
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711397288.0A Pending CN109947541A (en) | 2017-12-21 | 2017-12-21 | Task executing method and device, the device for task execution |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109947541A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110909183A (en) * | 2019-10-29 | 2020-03-24 | 联想(北京)有限公司 | Multimedia data processing method, device and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101359370A (en) * | 2007-08-01 | 2009-02-04 | 鸿富锦精密工业（深圳）有限公司 | Method and apparatus for recognising target object in image |
| CN104156694A (en) * | 2014-07-18 | 2014-11-19 | 百度在线网络技术（北京）有限公司 | Method and device for identifying target object of image |
| CN106919308A (en) * | 2017-03-17 | 2017-07-04 | 北京奇虎科技有限公司 | A kind of image processing method and mobile terminal |
| US20170249128A1 (en) * | 2016-02-29 | 2017-08-31 | Red Hat, Inc. | Maintaining build secrets in a build container |
| CN107291560A (en) * | 2016-03-31 | 2017-10-24 | 北京三星通信技术研究有限公司 | A kind of content of smart machine determines method and apparatus |
| CN107341185A (en) * | 2017-06-05 | 2017-11-10 | 北京小米移动软件有限公司 | The method and device of presentation of information |
| CN107368335A (en) * | 2017-07-24 | 2017-11-21 | 奇酷互联网络科技（深圳）有限公司 | A kind of method and apparatus and mobile terminal of Quick Response Code identification |
-
2017
- 2017-12-21 CN CN201711397288.0A patent/CN109947541A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101359370A (en) * | 2007-08-01 | 2009-02-04 | 鸿富锦精密工业（深圳）有限公司 | Method and apparatus for recognising target object in image |
| CN104156694A (en) * | 2014-07-18 | 2014-11-19 | 百度在线网络技术（北京）有限公司 | Method and device for identifying target object of image |
| US20170249128A1 (en) * | 2016-02-29 | 2017-08-31 | Red Hat, Inc. | Maintaining build secrets in a build container |
| CN107291560A (en) * | 2016-03-31 | 2017-10-24 | 北京三星通信技术研究有限公司 | A kind of content of smart machine determines method and apparatus |
| CN106919308A (en) * | 2017-03-17 | 2017-07-04 | 北京奇虎科技有限公司 | A kind of image processing method and mobile terminal |
| CN107341185A (en) * | 2017-06-05 | 2017-11-10 | 北京小米移动软件有限公司 | The method and device of presentation of information |
| CN107368335A (en) * | 2017-07-24 | 2017-11-21 | 奇酷互联网络科技（深圳）有限公司 | A kind of method and apparatus and mobile terminal of Quick Response Code identification |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110909183A (en) * | 2019-10-29 | 2020-03-24 | 联想(北京)有限公司 | Multimedia data processing method, device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104753766B (en) | Expression sending method and device | |
| CN104615769B (en) | Picture classification method and device | |
| CN104572905B (en) | Print reference creation method, photo searching method and device | |
| EP2494496B1 (en) | Sensor-based mobile search, related methods and systems | |
| CN105528786B (en) | Image processing method and device | |
| CN104717366B (en) | The recommendation method and device of contact head image | |
| CN107341185A (en) | The method and device of presentation of information | |
| CN105335712A (en) | Image recognition method, device and terminal | |
| CN105488025A (en) | Template construction method and apparatus and information identification method and apparatus | |
| CN105302315A (en) | Image processing method and device | |
| CN111506758B (en) | Method, device, computer equipment and storage medium for determining article name | |
| CN107193983A (en) | Image search method and device | |
| CN104463103B (en) | Image processing method and device | |
| CN108038102A (en) | Recommendation method, apparatus, terminal and the storage medium of facial expression image | |
| CN106126592B (en) | Processing method and device for search data | |
| CN104731880A (en) | Image ordering method and device | |
| CN107230137A (en) | Merchandise news acquisition methods and device | |
| CN105335714B (en) | Photo processing method, device and equipment | |
| CN105204356A (en) | Application display method, device and terminal | |
| CN109727208A (en) | Filter recommended method, device, electronic equipment and storage medium | |
| CN105139033A (en) | Classifier construction method and device and image processing method and device | |
| CN111526287A (en) | Image shooting method, image shooting device, electronic equipment, server, image shooting system and storage medium | |
| CN107330391A (en) | Product information reminding method and device | |
| CN108320208A (en) | Vehicle recommends method and device | |
| CN104166692A (en) | Method and device for adding labels on photos |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190628 |