CN107203611A - Information providing method and device based on picture content - Google Patents
Information providing method and device based on picture content Download PDFInfo
- Publication number
- CN107203611A CN107203611A CN201710359131.2A CN201710359131A CN107203611A CN 107203611 A CN107203611 A CN 107203611A CN 201710359131 A CN201710359131 A CN 201710359131A CN 107203611 A CN107203611 A CN 107203611A
- Authority
- CN
- China
- Prior art keywords
- keyword
- word
- information
- extensive
- image content
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
- G06F16/68—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/683—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
- G06F16/685—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using automatically derived transcript of audio data, e.g. lyrics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
- G06F16/5846—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using extracted text
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/783—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
- G06F16/7844—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using original textual content or text extracted from visual content or transcript of audio data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
- G06V10/443—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components by matching or filtering
Abstract
The invention discloses an information providing method and device based on picture content, wherein the method comprises the following steps: identifying picture content extraction keywords; acquiring generalized words related to the keywords; matching the keywords and the generalization words with database information, calculating a matching result according to a preset strategy to obtain target information matched with the picture, and providing the target information for the user. Therefore, the target information for matching the picture after the identified picture content is further generalized is provided for the user, the convenience and the interestingness of artificial intelligence are improved, and the user experience is improved.
Description
Technical field
The present invention relates to picture recognition technical field, more particularly to a kind of information providing method and dress based on image content
Put.
Background technology
Artificial intelligence (Artificial Intelligence), english abbreviation is AI.It is research, develop for simulating,
Extend and extend a new technological sciences of intelligent theory, method, technology and the application system of people.Artificial intelligence is meter
One branch of calculation machine science, it attempts to understand essence of intelligence, and produce it is a kind of it is new can be with the similar side of human intelligence
The intelligence machine that formula is made a response, the research in the field include robot, speech recognition, image recognition, natural language processing and
Expert system etc..
At present, the identification of picture is only in that the content information for obtaining picture, relatively simple, can not be by picture recognition
It is applied in artificial intelligence.
The content of the invention
The purpose of the present invention is intended at least solve one of technical problem in correlation technique to a certain extent.
Therefore, it is an object of the present invention to propose a kind of information providing method based on image content, for solving
The problem of picture recognition can not being applied in the prior art in artificial intelligence, by the way that the image content after identification is carried out
Go the target information for matching picture to be supplied to user after further extensive processing, improve the convenience and interest of artificial intelligence
Taste, improves Consumer's Experience.
Second object of the present invention is to propose a kind of information provider unit based on image content.
Third object of the present invention is to propose a kind of computer equipment.
Fourth object of the present invention is to propose a kind of non-transitorycomputer readable storage medium.
The 5th purpose of the present invention is to propose a kind of computer program product.
For up to above-mentioned purpose, first aspect present invention embodiment proposes a kind of information providing based on image content
Method, including:Recognize that image content extracts keyword;Obtain the extensive word related to the keyword;By the keyword and institute
State extensive word to be matched with database information, matching result is carried out to calculate acquisition and the picture according to default strategy
The target information of matching, and it is supplied to user.
The information providing method based on image content of the embodiment of the present invention, by recognizing that image content extracts keyword,
And the extensive word related to keyword is obtained, finally keyword and extensive word are matched with database information, according to default
Strategy matching result calculate obtain with the target information of picture match, and be supplied to user, realize after identification
Image content goes the target information for matching picture to be supplied to user after carrying out further extensive processing, improves artificial intelligence
Convenience and interest, improve Consumer's Experience.
In addition, the information providing method based on image content of the embodiment of the present invention, also special with technology additional as follows
Levy:
Alternatively, the acquisition extensive word related to the keyword, including:Inquire about default near synonym storehouse obtain with
The corresponding near synonym of the keyword, and the association dictionary of inquiry training in advance obtain associate corresponding with the keyword
Word.
Alternatively, described method, in addition to:The multiple words of cutting word processing generation are carried out to the information content in sample set
Unit;Dictionary is associated with predetermined threshold value generation according to the co-occurrence number of times between word unit.
Alternatively, the target for calculate acquisition and the picture match to matching result according to default strategy is believed
Breath, including:Obtain corresponding with the keyword the first weight, and the second weight corresponding with the extensive word;According to institute
The first weight is stated matching result is carried out with second weight to calculate the target information obtained with the picture match.
Alternatively, it is described to be matched the keyword and the extensive word with database information, according to default plan
Slightly matching result is carried out to calculate the target information obtained with the picture match, and is supplied to user, including:Closed described
Keyword and the extensive word are matched with the lyrics in library, and carrying out calculating to matching result according to default strategy obtains
Take the target song with the picture match and broadcasting;Or, by the keyword and the extensive word and the text in books storehouse
Chapter content is matched, and matching result is carried out to calculate the target article obtained with the picture match according to default strategy
And play;Or, the keyword and the extensive word are matched with the video content in video library, according to default
Strategy carries out calculating the target video and the broadcasting that obtain with the picture match to matching result.
For up to above-mentioned purpose, second aspect of the present invention embodiment proposes a kind of information based on image content and provides dress
Put, including:Extraction module, for recognizing that image content extracts keyword;Acquisition module, for obtaining and the keyword phase
The extensive word closed;Processing module, for the keyword and the extensive word to be matched with database information, according to pre-
If strategy matching result calculate obtain with the target information of the picture match, and be supplied to user.
The information provider unit based on image content of the embodiment of the present invention, by recognizing that image content extracts keyword,
And the extensive word related to keyword is obtained, finally keyword and extensive word are matched with database information, according to default
Strategy matching result calculate obtain with the target information of picture match, and be supplied to user, realize after identification
Image content goes the target information for matching picture to be supplied to user after carrying out further extensive processing, improves artificial intelligence
Convenience and interest, improve Consumer's Experience.
In addition, the information provider unit based on image content of the embodiment of the present invention, also special with technology additional as follows
Levy:
Alternatively, the acquisition module is used for:Inquire about default near synonym storehouse and obtain nearly justice corresponding with the keyword
Word, and the association dictionary of inquiry training in advance obtain conjunctive word corresponding with the keyword.
Alternatively, the acquisition module is additionally operable to:Cutting word processing generation is carried out to the information content in sample set multiple
Word unit;Dictionary is associated with predetermined threshold value generation according to the co-occurrence number of times between word unit.
Alternatively, the processing module is used for:Obtain corresponding with the keyword the first weight, and with it is described extensive
Corresponding second weight of word;Matching result calculate according to first weight and second weight obtain with it is described
The target information of picture match.
Alternatively, the processing module is used for:The keyword and the extensive word are carried out with the lyrics in library
Matching, carries out calculating the target song and the broadcasting that obtain with the picture match according to default strategy to matching result;Or
Person, the keyword and the extensive word are matched with the article content in books storehouse, according to default strategy to matching
As a result carry out calculating the target article obtained with the picture match and play;Or, by the keyword and the extensive word
Matched with the video content in video library, matching result is carried out to calculate acquisition and the picture according to default strategy
The target video of matching and broadcasting.
For up to above-mentioned purpose, third aspect present invention embodiment proposes a kind of computer equipment, including:Including storage
Device, processor and storage are on a memory and the computer program that can run on a processor, it is characterised in that the processing
When device performs described program, enabling perform a kind of information providing method based on image content, methods described includes:Know
Other image content extracts keyword;Obtain the extensive word related to the keyword;By the keyword and the extensive word with
Database information is matched, and matching result is carried out to calculate the target obtained with the picture match according to default strategy
Information, and it is supplied to user.
To achieve these goals, fourth aspect present invention embodiment proposes a kind of computer-readable storage of non-transitory
Medium, when the instruction in the storage medium is performed by processor, enabling perform a kind of letter based on image content
Offer method is ceased, methods described includes:Recognize that image content extracts keyword;Obtain the extensive word related to the keyword;
The keyword and the extensive word are matched with database information, matching result counted according to default strategy
The target information obtained with the picture match is calculated, and is supplied to user.
To achieve these goals, fifth aspect present invention embodiment proposes a kind of computer program product, when described
When instruction processing unit in computer program product is performed, a kind of information providing method based on image content, the side are performed
Method includes:Recognize that image content extracts keyword;Obtain the extensive word related to the keyword;By the keyword and institute
State extensive word to be matched with database information, matching result is carried out to calculate acquisition and the picture according to default strategy
The target information of matching, and it is supplied to user.
The additional aspect of the present invention and advantage will be set forth in part in the description, and will partly become from the following description
Obtain substantially, or recognized by the practice of the application.
Brief description of the drawings
Fig. 1 is the flow chart of the information providing method based on image content provided according to one embodiment of the invention;
Fig. 2 is the picture sample schematic diagram provided according to one embodiment of the invention;
Fig. 3 is that the information based on image content provided according to a further embodiment of the invention provides schematic diagram;
Fig. 4 is the structural representation of the information provider unit based on image content provided according to one embodiment of the invention
Figure;
Fig. 5 is the structural representation of the information provider unit based on image content provided according to a further embodiment of the invention
Figure.
Embodiment
Embodiments of the invention are described below in detail, the example of the embodiment is shown in the drawings, wherein from beginning to end
Same or similar label represents same or similar element or the element with same or like function.Below with reference to
The embodiment of accompanying drawing description is exemplary, it is intended to for explaining the present invention, and be not considered as limiting the invention.
Below with reference to the accompanying drawings the information providing method based on image content and device of the embodiment of the present invention described.
Fig. 1 is the flow chart of the information providing method based on image content provided according to one embodiment of the invention.
It should be noted that the information providing method based on image content of the embodiment of the present application can be applied
In the equipment (mobile phone, flat board, apparatus such as computer) of the systems such as Android, IOS, PC.
Specifically, image content identification refers to explain picture, can identify the object included in picture, picture
Photographed scene etc..Usual image content recognizing method be object detection method i.e. by defining a series of templates, make each template
Catch certain certain types of object.
However, the results contrast that above-mentioned identification is obtained is single, it is impossible to applied in the picture recognition technology of artificial intelligence.
In order to further improve the convenience and interest of artificial intelligence, the present invention proposes that a kind of information based on image content is provided
Method, by going the target information for matching picture to be supplied to after the image content after identification is carried out into further extensive processing
User.It is specific as follows:
Comprise the following steps as shown in figure 1, being somebody's turn to do the information providing method based on image content:
Step 101, identification image content extracts keyword.
Step 102, the extensive word related to keyword is obtained.
Specifically, picture can be handled by modes such as picture recognition software or algorithms to recognize in picture
Hold, and processing is carried out to image content and extract keyword.It is understood that extracting the word of several representative picture contents
Converge or phrase is used as keyword.
It is possible to further obtain the extensive word related to keyword by a variety of modes, a kind of example, inquiry are used as
Default near synonym storehouse obtains near synonym corresponding with keyword, and the association dictionary of inquiry training in advance is obtained and keyword pair
The conjunctive word answered.
For example, by the picture shown in Fig. 2 being identified contents extraction keyword for " girl ", " woman " etc.,
Then inquiry and the corresponding near synonym such as " girl ", " woman " such as " schoolgirl ", " goddess ", " good in default near synonym storehouse
People " etc., then inquire about the association dictionary of training in advance, such as " schoolgirl " correspondence " lovely ", " sprout and rattle away " etc., it is possible thereby to obtain
To the near synonym such as " goddess ", " schoolgirl ", " model ", " beautiful woman ", " lovely ", " beautiful ", " Mei Mei rattles away ", " beauty ", " sprout and rattle away "
And conjunctive word is used as the extensive word related to keyword.
Wherein, near synonym storehouse is pre-set, such as " beauty " " girl " is near synonym;" severity ", " well done " are
Near synonym etc., near synonym storehouse, which can be adjusted, as needed increases or reduces the quantity of near synonym.Near synonym storehouse
In in store multiple near synonym correlation (its form can be the forms such as mapping table), such as can be looked into by keyword X
Corresponding mapping table (can also be and the mode such as calculate by related algorithm) is looked for find its near synonym Y, Z, or more nearly justice
Word.
It should be noted that association dictionary can be trained by a variety of modes, as a kind of example, in sample set
The information content carry out the multiple word units of cutting word processing generation, generated according to the co-occurrence number of times between word unit and predetermined threshold value
Associate dictionary.I.e. can by being estimated to the relevance between big measure word unit, such as what two word units occurred together
Number of times is more than predetermined threshold value such as 10 times, then the two word units are set into conjunctive word is stored in association dictionary.
Step 103, keyword and extensive word are matched with database information, according to default strategy to matching result
Carry out calculating the target information obtained with picture match, and be supplied to user.
Specifically, the crucial and extensive word of acquisition is matched in database information, it is to be understood that matching
As a result being one either multiple, when there is multiple matching results, can be obtained by relevant way with matching degree most
High corresponding matching result, to ensure to improve more accurate target information to user.
More specifically, the target that can calculate acquisition and picture match to matching result according to default strategy is believed
Breath, wherein default strategy can need to carry out selection setting, such as the matching knot most matched with extensive word according to practical application
Fruit is used as target information etc..
As a kind of example, the first weight corresponding with keyword, and the second weight corresponding with extensive word, root are obtained
Matching result is carried out to calculate the target information obtained with picture match according to the first weight and the second weight.I.e. user can root
Need to give keyword the weight different with extensive word according to practical application, such as corresponding first weight of keyword is 0.4;It is general
It is 0.6 etc. to change corresponding second weight of word.
It should be noted that the target information in the present embodiment can be song, article (modern times in ancient times poem, lines, book
Nationality etc.) and video etc..It is understood that different target informations is supplied to the result of user different, illustrate such as
Under:
The first example, keyword and extensive word are matched with the lyrics in library, right according to default strategy
Matching result carries out calculating target song and the broadcasting obtained with picture match.
As a kind of Scene realization, user uploads that a pictures such as Fig. 3 (a) is shown, can be with Auto-matching most close song
Word is simultaneously played shown in target song such as Fig. 3 (b).Thus, the interest of artificial intelligence is further improved.
It should be noted that can also further improve convenience that user uses can by such as Fig. 3 (b) thus two
Dimension code position sets Quick Response Code to point out user by scanning Quick Response Code with the picture of upload user oneself or other can like
Picture and broadcasting target song corresponding with the picture that user uploads.
Second of example, keyword and the extensive word are matched with the article content in books storehouse, according to default
Strategy to matching result carry out calculate obtain and picture match target article and play.
The third example, keyword and extensive word is matched with the video content in video library, according to default plan
Slightly matching result is carried out to calculate the target video and the broadcasting that obtain with picture match.
In summary, the information providing method based on image content of the embodiment of the present invention, by recognizing that image content is carried
Keyword is taken, and obtains the extensive word related to keyword, finally by keyword and extensive word and database information progress
Match somebody with somebody, matching result is carried out to calculate the target information obtained with picture match according to default strategy, and be supplied to user, it is real
Go the target information for matching picture to be supplied to user after the image content after identification now is carried out into further extensive processing, carry
The convenience and interest of high artificial intelligence, improve Consumer's Experience.
In order to realize above-described embodiment, the present invention proposes a kind of information provider unit based on image content.
Fig. 4 is the structural representation of the information provider unit based on image content provided according to one embodiment of the invention
Figure.
As shown in figure 4, being somebody's turn to do the information provider unit based on image content includes:Extraction module 11, acquisition module 12 and place
Manage module 13.
Wherein, extraction module 11, for recognizing that image content extracts keyword.
Acquisition module 12, for obtaining the extensive word related to keyword.
Processing module 13 is right according to default strategy for keyword and extensive word to be matched with database information
Matching result carries out calculating the target information obtained with picture match, and is supplied to user.
Further, acquisition module 12, near synonym corresponding with keyword are obtained for inquiring about default near synonym storehouse, with
And the association dictionary of inquiry training in advance obtains conjunctive word corresponding with keyword.
Further, acquisition module 12, are additionally operable to multiple to the information content progress cutting word processing generation in sample set
Word unit;Dictionary is associated with predetermined threshold value generation according to the co-occurrence number of times between word unit.
Further, processing module 13, for obtaining the first weight corresponding with keyword, and it is corresponding with extensive word
Second weight;Matching result is carried out to calculate the target information obtained with picture match according to the first weight and the second weight.
Further, processing module 13, for keyword and extensive word to be matched with the lyrics in library, according to
Default strategy carries out calculating the target song and the broadcasting that obtain with picture match to matching result;Or, by keyword and general
Change word to be matched with the article content in books storehouse, matching result is carried out to calculate acquisition and picture according to default strategy
The target article of matching is simultaneously played;Or, keyword and extensive word are matched with the video content in video library, according to
Default strategy carries out calculating the target video and the broadcasting that obtain with picture match to matching result.
It should be noted that the foregoing explanation to the information providing method embodiment based on image content is also applied for
The information provider unit based on image content of the embodiment, here is omitted.
In summary, the information provider unit based on image content of the embodiment of the present invention, by recognizing that image content is carried
Keyword is taken, and obtains the extensive word related to keyword, finally by keyword and extensive word and database information progress
Match somebody with somebody, matching result is carried out to calculate the target information obtained with picture match according to default strategy, and be supplied to user, it is real
Go the target information for matching picture to be supplied to user after the image content after identification now is carried out into further extensive processing, carry
The convenience and interest of high artificial intelligence, improve Consumer's Experience.
Fig. 5 is the structural representation of the information provider unit based on image content provided according to a further embodiment of the invention
Figure.As shown in figure 5, being somebody's turn to do the information provider unit based on image content includes:
Memory 21, processor 22 and it is stored in the computer program that can be run on memory 21 and on processor 22.
Processor 22 realizes the information providing based on image content provided in above-described embodiment when performing described program
Method.
Further, the information provider unit based on image content also includes:
Communication interface 23, for the communication between memory 21 and processor 22.
Memory 21, for depositing the computer program that can be run on processor 22.
Memory 21 may include high-speed RAM memory, it is also possible to also including nonvolatile memory (non-volatile
Memory), for example, at least one magnetic disk storage.
Processor 22, realizes that the information based on image content described in above-described embodiment is provided for performing during described program
Method.
If memory 21, processor 22 and the independent realization of communication interface 23, communication interface 21, memory 21 and place
Reason device 22 can be connected with each other by bus and complete mutual communication.The bus can be industry standard architecture
(Industry Standard Architecture, referred to as ISA) bus, external equipment interconnection (Peripheral
Component, referred to as PCI) bus or extended industry-standard architecture (Extended Industry Standard
Architecture, referred to as EISA) bus etc..The bus can be divided into address bus, data/address bus, controlling bus etc..
For ease of representing, only represented in Fig. 5 with a thick line, it is not intended that only one bus or a type of bus.
Optionally, on implementing, if memory 21, processor 22 and communication interface 23, are integrated in chip piece
Upper to realize, then memory 21, processor 22 and communication interface 23 can complete mutual communication by internal interface.
Processor 22 is probably a central processing unit (Central Processing Unit, referred to as CPU), or
It is specific integrated circuit (Application Specific Integrated Circuit, referred to as ASIC), or quilt
It is configured to implement one or more integrated circuits of the embodiment of the present invention.
In order to realize above-described embodiment, the present invention also proposes computer equipment, it is characterised in that including memory, processing
Device and storage are on a memory and the computer program that can run on a processor, it is characterised in that the computing device institute
When stating program, enabling perform a kind of information providing method based on image content, methods described includes:Recognize in picture
Hold and extract keyword;Obtain the extensive word related to keyword;Keyword and extensive word are matched with database information,
Matching result is carried out to calculate the target information obtained with picture match according to default strategy, and is supplied to user.
In order to realize above-described embodiment, the present invention also proposes a kind of non-transitorycomputer readable storage medium, when described
When instruction in storage medium is performed by processor, enabling perform a kind of information providing method based on image content,
Methods described includes:Recognize that image content extracts keyword;Obtain the extensive word related to keyword;By keyword and extensive
Word is matched with database information, and matching result is carried out to calculate the target obtained with picture match according to default strategy
Information, and it is supplied to user.
In order to realize above-described embodiment, the present invention also proposes a kind of computer program product, when computer program production
When instruction processing unit in product is performed, enabling perform a kind of information providing method based on image content, methods described bag
Include:Recognize that image content extracts keyword;Obtain the extensive word related to keyword;By keyword and extensive word and database
Information is matched, and matching result is carried out to calculate the target information obtained with picture match according to default strategy, and provide
To user.
In addition, term " first ", " second " are only used for describing purpose, and it is not intended that indicating or implying relative importance
Or the implicit quantity for indicating indicated technical characteristic.Thus, define " first ", the feature of " second " can express or
Person implicitly includes at least one this feature.In the description of the invention, " multiple " are meant that at least two, such as two,
Three etc., unless otherwise specifically defined.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means to combine specific features, structure, material or the spy that the embodiment or example are described
Point is contained at least one embodiment of the present invention or example.In this manual, to the schematic representation of above-mentioned term not
Identical embodiment or example must be directed to.Moreover, specific features, structure, material or the feature of description can be with office
Combined in an appropriate manner in one or more embodiments or example.In addition, in the case of not conflicting, this area
Technical staff can be carried out the feature of the not be the same as Example described in this specification or example and non-be the same as Example or example
With reference to and combination.
Any process described otherwise above or method description are construed as in flow chart or herein, represent to include
The modules of one or more codes for being used for executable instruction the step of realize custom logic function or process, fragment or
Part, and the scope of the preferred embodiment of the present invention includes other realization, wherein can not be by shown or discussion
Sequentially, including according to involved function by it is basic simultaneously in the way of or in the opposite order, carry out perform function, this should be by this
The embodiment person of ordinary skill in the field of invention is understood.
Represent in flow charts or logic and/or step described otherwise above herein, for example, being considered use
In the order list for the executable instruction for realizing logic function, it may be embodied in any computer-readable medium, for
Instruction execution system, device or equipment (such as computer based system including the system of processor or other can be from instruction
The system of execution system, device or equipment instruction fetch and execute instruction) use, or combine these instruction execution systems, device or
Equipment and use.For the purpose of this specification, " computer-readable medium " can any can be included, store, communicating, propagating
Or transmission procedure uses for instruction execution system, device or equipment or with reference to these instruction execution systems, device or equipment
Device.The more specifically example (non-exhaustive list) of computer-readable medium includes following:With one or more wirings
Electrical connection section (electronic installation), portable computer diskette box (magnetic device), random access memory (RAM), read-only storage
(ROM), erasable edit read-only storage (EPROM or flash memory), fiber device, and portable optic disk are read-only
Memory (CDROM).In addition, computer-readable medium, which can even is that, to print the paper of described program or other conjunctions thereon
Suitable medium, because can then enter edlin, interpretation or necessary for example by carrying out optical scanner to paper or other media
When handled electronically to obtain described program with other suitable methods, be then stored in computer storage
In.
It should be appreciated that each several part of the present invention can be realized with hardware, software, firmware or combinations thereof.Above-mentioned
In embodiment, multiple steps or method can with storage in memory and by suitable instruction execution system perform it is soft
Part or firmware are realized.Such as, if realized with hardware with another embodiment, can be with well known in the art
Any one of row technology or their combination are realized:With the gate electricity for realizing logic function to data-signal
The discrete logic on road, the application specific integrated circuit with suitable combinational logic gate circuit, programmable gate array (PGA) is existing
Field programmable gate array (FPGA) etc..
Those skilled in the art are appreciated that to realize all or part of step that above-described embodiment method is carried
Rapid to can be by program to instruct the hardware of correlation to complete, described program can be stored in a kind of computer-readable storage
In medium, the program upon execution, including one or a combination set of the step of embodiment of the method.
In addition, each functional unit in each embodiment of the invention can be integrated in a processing module, can also
That unit is individually physically present, can also two or more units be integrated in a module.Above-mentioned integrated mould
Block can both be realized in the form of hardware, it would however also be possible to employ the form of software function module is realized.The integrated module is such as
Fruit is realized using in the form of software function module and as independent production marketing or in use, can also be stored in a calculating
In machine read/write memory medium.
Storage medium mentioned above can be read-only storage, disk or CD etc..Although having been shown and retouching above
Embodiments of the invention are stated, it is to be understood that above-described embodiment is exemplary, it is impossible to be interpreted as the limit to the present invention
System, one of ordinary skill in the art above-described embodiment can be changed, changed within the scope of the invention, replaced and
Modification.
Claims (10)
1. a kind of information providing method based on image content, it is characterised in that comprise the following steps:
Recognize that image content extracts keyword;
Obtain the extensive word related to the keyword;
The keyword and the extensive word are matched with database information, matching result carried out according to default strategy
The target information obtained with the picture match is calculated, and is supplied to user.
2. the method as described in claim 1, it is characterised in that the acquisition extensive word related to the keyword, including:
Inquire about default near synonym storehouse and obtain near synonym corresponding with the keyword, and
The association dictionary for inquiring about training in advance obtains conjunctive word corresponding with the keyword.
3. method as claimed in claim 2, it is characterised in that also include:
The multiple word units of cutting word processing generation are carried out to the information content in sample set;
Dictionary is associated with predetermined threshold value generation according to the co-occurrence number of times between word unit.
4. the method as described in claim 1, it is characterised in that described to be obtained according to default strategy to matching result progress calculating
The target information with the picture match is taken, including:
Obtain corresponding with the keyword the first weight, and the second weight corresponding with the extensive word;
Matching result is carried out to calculate the target obtained with the picture match according to first weight and second weight
Information.
5. the method as described in claim 1, it is characterised in that described to believe the keyword and the extensive word with database
Breath is matched, and matching result is carried out to calculate the target information obtained with the picture match according to default strategy, and carry
User is supplied, including:
The keyword and the extensive word are matched with the lyrics in library, according to default strategy to matching result
Carry out calculating target song and the broadcasting obtained with the picture match;Or,
The keyword and the extensive word are matched with the article content in books storehouse, according to default strategy to matching
As a result carry out calculating the target article obtained with the picture match and play;Or,
The keyword and the extensive word are matched with the video content in video library, according to default strategy to matching
As a result carry out calculating target video and the broadcasting obtained with the picture match.
6. a kind of information provider unit based on image content, it is characterised in that including:
Extraction module, for recognizing that image content extracts keyword;
Acquisition module, for obtaining the extensive word related to the keyword;
Processing module, for the keyword and the extensive word to be matched with database information, according to default strategy
Matching result is carried out to calculate the target information obtained with the picture match, and is supplied to user.
7. device as claimed in claim 6, it is characterised in that the acquisition module is used for:
Inquire about default near synonym storehouse and obtain near synonym corresponding with the keyword, and
The association dictionary for inquiring about training in advance obtains conjunctive word corresponding with the keyword.
8. a kind of computer equipment, it is characterised in that including memory, processor and store on a memory and can be in processor
The computer program of upper operation, it is characterised in that during the computing device described program, is realized as appointed in claim 1-5
Method described in one.
9. a kind of non-transitorycomputer readable storage medium, is stored thereon with computer program, it is characterised in that the program quilt
The method as any one of claim 1-5 is realized during computing device.
10. a kind of computer program product, when the instruction in the computer program product is by computing device, is performed as weighed
Profit requires the method any one of 1-5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710359131.2A CN107203611A (en) | 2017-05-19 | 2017-05-19 | Information providing method and device based on picture content |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710359131.2A CN107203611A (en) | 2017-05-19 | 2017-05-19 | Information providing method and device based on picture content |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107203611A true CN107203611A (en) | 2017-09-26 |
Family
ID=59905334
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710359131.2A Pending CN107203611A (en) | 2017-05-19 | 2017-05-19 | Information providing method and device based on picture content |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107203611A (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107506498A (en) * | 2017-09-28 | 2017-12-22 | 合肥博力生产力促进中心有限公司 | A kind of intellectual property data collection system of processing and method |
CN107862003A (en) * | 2017-10-24 | 2018-03-30 | 珠海市魅族科技有限公司 | Video contents search method, apparatus, terminal and readable storage medium storing program for executing |
CN109063076A (en) * | 2018-07-24 | 2018-12-21 | 维沃移动通信有限公司 | A kind of Picture Generation Method and mobile terminal |
CN109896374A (en) * | 2017-12-11 | 2019-06-18 | 日立楼宇技术(广州)有限公司 | Elevator screen methods of exhibiting and system |
CN110378716A (en) * | 2018-04-13 | 2019-10-25 | 北京三快在线科技有限公司 | Preferential strategy-generating method, device, electronic equipment and computer-readable medium |
CN110413820A (en) * | 2019-07-12 | 2019-11-05 | 深兰科技(上海)有限公司 | A kind of acquisition methods and device of picture description information |
CN111063443A (en) * | 2019-10-31 | 2020-04-24 | 望海康信(北京)科技股份公司 | Medical entity retrieval method, device, computer equipment and storage medium |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102572573A (en) * | 2010-12-30 | 2012-07-11 | 上海无戒空间信息技术有限公司 | Method for pushing information according to played content |
CN103478668A (en) * | 2013-09-09 | 2014-01-01 | 北京工商大学 | Preparation method of essence base material for improving milk flavor intensity of dairy product |
CN103995895A (en) * | 2014-06-04 | 2014-08-20 | 北京奇虎科技有限公司 | Image recognition method and device based on image |
CN105069037A (en) * | 2015-07-22 | 2015-11-18 | 无锡天脉聚源传媒科技有限公司 | Search content display method and apparatus |
CN105912722A (en) * | 2016-05-04 | 2016-08-31 | 广州酷狗计算机科技有限公司 | Song sending method and apparatus |
-
2017
- 2017-05-19 CN CN201710359131.2A patent/CN107203611A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102572573A (en) * | 2010-12-30 | 2012-07-11 | 上海无戒空间信息技术有限公司 | Method for pushing information according to played content |
CN103478668A (en) * | 2013-09-09 | 2014-01-01 | 北京工商大学 | Preparation method of essence base material for improving milk flavor intensity of dairy product |
CN103995895A (en) * | 2014-06-04 | 2014-08-20 | 北京奇虎科技有限公司 | Image recognition method and device based on image |
CN105069037A (en) * | 2015-07-22 | 2015-11-18 | 无锡天脉聚源传媒科技有限公司 | Search content display method and apparatus |
CN105912722A (en) * | 2016-05-04 | 2016-08-31 | 广州酷狗计算机科技有限公司 | Song sending method and apparatus |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107506498A (en) * | 2017-09-28 | 2017-12-22 | 合肥博力生产力促进中心有限公司 | A kind of intellectual property data collection system of processing and method |
CN107862003A (en) * | 2017-10-24 | 2018-03-30 | 珠海市魅族科技有限公司 | Video contents search method, apparatus, terminal and readable storage medium storing program for executing |
CN109896374A (en) * | 2017-12-11 | 2019-06-18 | 日立楼宇技术(广州)有限公司 | Elevator screen methods of exhibiting and system |
CN109896374B (en) * | 2017-12-11 | 2021-08-03 | 日立楼宇技术(广州)有限公司 | Elevator screen display method and system |
CN110378716A (en) * | 2018-04-13 | 2019-10-25 | 北京三快在线科技有限公司 | Preferential strategy-generating method, device, electronic equipment and computer-readable medium |
CN109063076A (en) * | 2018-07-24 | 2018-12-21 | 维沃移动通信有限公司 | A kind of Picture Generation Method and mobile terminal |
CN109063076B (en) * | 2018-07-24 | 2021-07-13 | 维沃移动通信有限公司 | Picture generation method and mobile terminal |
CN110413820A (en) * | 2019-07-12 | 2019-11-05 | 深兰科技(上海)有限公司 | A kind of acquisition methods and device of picture description information |
CN110413820B (en) * | 2019-07-12 | 2022-03-29 | 深兰科技(上海)有限公司 | Method and device for acquiring picture description information |
CN111063443A (en) * | 2019-10-31 | 2020-04-24 | 望海康信(北京)科技股份公司 | Medical entity retrieval method, device, computer equipment and storage medium |
CN111063443B (en) * | 2019-10-31 | 2023-08-18 | 望海康信(北京)科技股份公司 | Medical entity retrieval method, medical entity retrieval device, computer equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107203611A (en) | Information providing method and device based on picture content | |
CN107025312A (en) | Information providing method and device based on video content | |
CN107122492A (en) | Lyric generation method and device based on picture content | |
CN110188350B (en) | Text consistency calculation method and device | |
US20180182377A1 (en) | Method and device for extracting speech feature based on artificial intelligence | |
CN104281699B (en) | Method and device is recommended in search | |
US20180336193A1 (en) | Artificial Intelligence Based Method and Apparatus for Generating Article | |
US20210193108A1 (en) | Voice synthesis method, device and apparatus, as well as non-volatile storage medium | |
CN109658938A (en) | The method, apparatus of voice and text matches, equipment and computer-readable medium | |
US10157619B2 (en) | Method and device for searching according to speech based on artificial intelligence | |
CN110021308A (en) | Voice mood recognition methods, device, computer equipment and storage medium | |
CN108170859A (en) | Method, apparatus, storage medium and the terminal device of speech polling | |
CN107330750B (en) | A kind of recommended products figure method and device, electronic equipment | |
WO2019084810A1 (en) | Information processing method and terminal, and computer storage medium | |
CN107679033A (en) | Text punctuate location recognition method and device | |
CN110210021A (en) | Read understanding method and device | |
CN107679564A (en) | Sample data recommends method and its device | |
CN107193941A (en) | Story generation method and device based on picture content | |
CN108985133B (en) | Age prediction method and device for face image | |
CN110399488A (en) | File classification method and device | |
CN109902233A (en) | Smart object recommended method, device, equipment and storage medium | |
CN114612290B (en) | Training method of image editing model and image editing method | |
CN106557554A (en) | Display packing and device based on the Search Results of artificial intelligence | |
CN109992781A (en) | Processing, device, storage medium and the processor of text feature | |
CN107748802A (en) | Polymerizable clc method and device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170926 |
|
RJ01 | Rejection of invention patent application after publication |