CN108052525A

CN108052525A - Obtain method, apparatus, storage medium and the electronic equipment of audio-frequency information

Info

Publication number: CN108052525A
Application number: CN201711087240.XA
Authority: CN
Inventors: 王君龙
Original assignee: Guangdong Oppo Mobile Telecommunications Corp Ltd
Current assignee: Guangdong Oppo Mobile Telecommunications Corp Ltd
Priority date: 2017-11-07
Filing date: 2017-11-07
Publication date: 2018-05-18
Anticipated expiration: 2037-11-07
Also published as: CN108052525B

Abstract

This application discloses a kind of method, apparatus, storage medium and electronic equipments for obtaining audio-frequency information, and the method comprising the steps of：When the loss of learning for recognizing pre-set image is more than default recognition threshold, keyword message and target pattern information are extracted from pre-set image；Using in keyword message and target pattern information, an information is as the first parameter, another information is as the second parameter；Corresponding Object linking data are chosen in the corresponding audio url set of the first parameter according to the second parameter；Obtain the corresponding audio-frequency information of Object linking data.By an acquisition audio url set in keyword message or target pattern information, then screened further according to another, obtain Object linking data, promote the discrimination of the pre-set image few to information.

Description

Obtain method, apparatus, storage medium and the electronic equipment of audio-frequency information

Technical field

The application belong to field of communication technology more particularly to it is a kind of obtain the method, apparatus of audio-frequency information, storage medium and Electronic equipment.

Background technology

Existing point reads equipment and a reading object is identified and determined according to modes such as the coordinate of reading object or codings Position.Wherein coding mode point read mode is the printed codes on books, then identifies coding using talking pen to determine content, Then corresponding audio is played according to content.Wherein coordinated manner point read mode is that the position of point reader is clicked on using talking pen To determine coordinate, the corresponding audio of point reader current page broadcasting is combined after confirming coordinate.It needs by talking pen or point Reading machine could realize the identification and positioning of reading object.

The content of the invention

The application provides a kind of method, apparatus, storage medium and electronic equipment for obtaining audio-frequency information, can be promoted to figure The discrimination of picture, and then obtain accurate audio-frequency information.

In a first aspect, the embodiment of the present application provides a kind of method for obtaining audio-frequency information, applied to electronic equipment, the side Method includes step：

When the loss of learning for recognizing pre-set image is more than default recognition threshold, extracted from the pre-set image crucial Word information and target pattern information；

Using an information in the keyword message and the target pattern information as the first parameter, another information is made For the second parameter；

Corresponding Object linking is chosen in the corresponding audio url set of first parameter according to second parameter Data；

Obtain the corresponding audio-frequency information of the Object linking data.

Second aspect, the embodiment of the present application provide a kind of device for obtaining audio-frequency information, and described device includes：

Character pattern acquiring unit, for when the loss of learning for recognizing pre-set image is more than default recognition threshold, from Keyword message and target pattern information are extracted in the pre-set image；

Parameter setting unit, for using an information in the keyword message and the target pattern information as first Parameter, another information is as the second parameter；

Object linking acquiring unit, for according to second parameter in the corresponding audio url set of first parameter It is middle to choose corresponding Object linking data

Audio acquiring unit obtains the corresponding audio-frequency information of the Object linking data.

The third aspect, the embodiment of the present application provide a kind of storage medium, computer program are stored thereon with, when the calculating When machine program is run on computers so that the method that the computer performs above-mentioned acquisition audio-frequency information.

Fourth aspect, the embodiment of the present application provide a kind of electronic equipment, and including processor and memory, the memory has Computer program, the processor is by calling the computer program, for performing the method for above-mentioned acquisition audio-frequency information.

Method, apparatus, storage medium and the electronic equipment provided by the embodiments of the present application for obtaining audio-frequency information, when recognizing When the loss of learning of pre-set image is more than default recognition threshold, keyword message and target pattern letter are extracted from pre-set image Breath；Using in keyword message and target pattern information, an information is as the first parameter, another information is as the second parameter；Root According to the second parameter corresponding Object linking data are chosen in the corresponding audio url set of the first parameter；Obtain Object linking number According to corresponding audio-frequency information.The application passes through keyword message or target pattern information when realizing that point is read by electronic equipment In one acquisition audio url set, then screened further according to another, obtain Object linking data, promoted to information The discrimination of few pre-set image.

Description of the drawings

In order to illustrate more clearly of the technical solution in the embodiment of the present application, make required in being described below to embodiment Attached drawing is briefly described.It should be evident that the accompanying drawings in the following description is only some embodiments of the present application, for For those skilled in the art, without creative efforts, it can also be obtained according to these attached drawings other attached Figure.

Fig. 1 is the application scenarios schematic diagram of the device of acquisition audio-frequency information provided by the embodiments of the present application；

Fig. 2 is the another application schematic diagram of a scenario of the device of acquisition audio-frequency information provided by the embodiments of the present application；

Fig. 3 is the flow diagram of the method for acquisition audio-frequency information provided by the embodiments of the present application；

Fig. 4 is the flow diagram of the pattern-information of acquisition pre-set image provided by the embodiments of the present application；

Fig. 5 is the flow diagram provided by the embodiments of the present application that pattern-information is obtained according to background colour；

Fig. 6 is the flow diagram of first parameter of selection provided by the embodiments of the present application；

Fig. 7 is the flow diagram of acquisition audio url set provided by the embodiments of the present application；

Fig. 8 is the flow diagram that selection respective objects provided by the embodiments of the present application link data；

Fig. 9 is the first structure diagram of the device of acquisition audio-frequency information provided by the embodiments of the present application；

Figure 10 is second of structure diagram of the device of acquisition audio-frequency information provided by the embodiments of the present application；

Figure 11 is the third structure diagram of the device of acquisition audio-frequency information provided by the embodiments of the present application；

Figure 12 is the 4th kind of structure diagram of the device of acquisition audio-frequency information provided by the embodiments of the present application；

Figure 13 is the 5th kind of structure diagram of the device of acquisition audio-frequency information provided by the embodiments of the present application；

Figure 14 is the 6th kind of structure diagram of the device of acquisition audio-frequency information provided by the embodiments of the present application；

Figure 15 is the 7th kind of structure diagram of the device of acquisition audio-frequency information provided by the embodiments of the present application；

Figure 16 is the structure diagram of electronic equipment provided by the embodiments of the present application；

Figure 17 is another structure diagram of electronic equipment provided by the embodiments of the present application.

Specific embodiment

Schema is refer to, wherein identical element numbers represent identical component, the principle of the application is to implement one It is illustrated in appropriate computing environment.The following description be according to illustrated the application specific embodiment, should not be by It is considered as limitation the application other specific embodiments not detailed herein.

In the following description, the specific embodiment of the application will be with reference to as the step performed by one or multi-section computer And symbol illustrates, unless otherwise stating clearly.Therefore, these steps and operation will have to mention for several times is performed by computer, this paper institutes The computer execution of finger includes single with computer disposal of the electronic signal of the data in a structuring pattern by representing The operation of member.This operation is converted at the data or the position being maintained in the memory system of the computer, can be matched somebody with somebody again Put or in addition change in a manner of known to the tester of this field the running of the computer.The data knot that the data are maintained Structure is the provider location of the memory, has the specific feature as defined in the data format.But the application principle is with above-mentioned Word illustrates, is not represented as a kind of limitation, this field tester will appreciate that plurality of step as described below and Operation also may be implemented among hardware.

Term as used herein " unit " can regard the software object to be performed in the arithmetic system as.It is as described herein Different components, unit, engine and service can be regarded as the objective for implementation in the arithmetic system.And device as described herein and side Method can be implemented in a manner of software, can also be implemented certainly on hardware, within the application protection domain.

Term " first ", " second " and " the 3rd " in the application etc. is for distinguishing different objects rather than for retouching State particular order.In addition, term " comprising " and " having " and their any deformations, it is intended that cover non-exclusive include. Such as contain the step of process, method, system, product or the equipment of series of steps or unit is not limited to list or Unit, but some embodiments further include the step of not listing or unit or some embodiments further include for these processes, The intrinsic other steps of method, product or equipment or unit.

Referenced herein " embodiment " is it is meant that a particular feature, structure, or characteristic described can wrap in conjunction with the embodiments It is contained at least one embodiment of the application.Each position in the description occur the phrase might not each mean it is identical Embodiment, nor the independent or alternative embodiment with other embodiments mutual exclusion.Those skilled in the art explicitly and Implicitly understand, embodiment described herein can be combined with other embodiments.

, it can be achieved that realizing that point is read by electronic equipment in a kind of embodiment of the application.Electronic equipment can be obtained first A reading sample is taken, it can be picture, photo or coding etc. that point, which reads sample,.Wherein, electronic equipment can be mobile terminal, such as hand Machine, tablet computer, laptop etc., the embodiment of the present application is to this without limiting.

After a reading sample is got, electronic equipment can obtain multimedia sample, and multimedia sample can be audio File or video file etc..Then, the point got can be read sample and multimedia sample by electronic equipment is associated.Example Such as, electronic equipment associates picture A with audio a, and photo B is associated with audio b, and photo C is associated with video c.It is read that will put After sample is associated with multimedia sample, these sample datas can be stored in presetting database by electronic equipment.

It is understood that in some embodiments, point is read be to correspond between sample and multimedia sample Relation or one-to-many relation or many-to-one relation etc., the present embodiment is not specifically limited this.

When using electronic equipment read-on-command function, user can first using mobile electronic device shoot a photo or from A photo is chosen in photograph album or scans some coding.The photo that user shoots either the photo of selection or scans To coding be exactly to need to carry out an object read (treat read an object).After getting needs and carrying out the object read, Electronic equipment can be searched in presetting database carries out a photo or coding for the object matching read with the needs.If pre- If there is the photo or coding that the object matching read is carried out with the needs in database, then electronic equipment can search with Associated multimedia file, and play the multimedia file.

In one embodiment, such as point reads sample as picture A, comprising three sections of words in the photo, per passage All it is associated with a section audio.So, when the photo that user shoots is matched with the picture A in presetting database, due to shining Include three sections of words in piece A, and every section of word is associated with a corresponding section audio, then user can be by specifically choosing The mode of certain section of word in picture A, selection play its corresponding audio.Alternatively, user can not also specifically select, that Electronic equipment can be with the corresponding audio of three sections of words of played in order.

Referring to Fig. 1, for example, user shoots to obtain a photo X using electronic equipment, electronic equipment is in presetting database In find it is matched for picture A with photo X.Three sections of words, wherein first segment character associative audio first are included in picture A, the Two sections of character associative audio second, the 3rd section of character associative audio third.For example, user encloses on the screen has selected second segment word place Region, then electronic equipment can correspond to play audio second.

It is understood that the present embodiment can realize on an electronic device to the text in certain an object (such as photo) into The function that row point is read, this mode have the advantageous effects such as at low cost, convenience is good.

Based on realizing that point is read above by electronic equipment, referring to Fig. 2, Fig. 2 is acquisition sound provided by the embodiments of the present application The another application schematic diagram of a scenario of the device of frequency information.Such as the device acquisition pre-set image of audio-frequency information is obtained (for example, treating a little Read object), the then identification pre-set image, when the loss of learning for recognizing pre-set image is more than default recognition threshold, from pre- If keyword message and target pattern information are extracted in image；Using an information in keyword message and target pattern information as First parameter, another information is as the second parameter；It is selected according to the second parameter in the corresponding audio url set of the first parameter Take corresponding Object linking data；The corresponding audio-frequency information of Object linking data is obtained, finally plays out target audio information It goes.

The embodiment of the present application provides a kind of method for obtaining audio-frequency information, the executive agent of the method for the acquisition audio-frequency information Can be the device of acquisition audio-frequency information provided by the embodiments of the present application or the electricity for the device for being integrated with the acquisition audio-frequency information Sub- equipment, hardware may be employed for the device of the wherein acquisition audio-frequency information or the mode of software is realized.

The embodiment of the present application will be described from the angle for the device for obtaining audio-frequency information, the device of the acquisition audio-frequency information It can specifically integrate in the electronic device.The method of the acquisition audio-frequency information includes：When the loss of learning for recognizing pre-set image During more than default recognition threshold, keyword message and target pattern information are extracted from pre-set image；By keyword message and mesh An information is as the first parameter in mark pattern-information, another information is as the second parameter；According to the second parameter in the first ginseng Corresponding Object linking data are chosen in the corresponding audio url set of number；Obtain the corresponding audio-frequency information of Object linking data.

Referring to Fig. 3, Fig. 3 is the flow diagram of the method for acquisition audio-frequency information provided by the embodiments of the present application.This Shen Please embodiment provide acquisition audio-frequency information method be applied to electronic equipment, idiographic flow can be as follows：

Step 101, when the loss of learning for recognizing pre-set image is more than default recognition threshold, extracted from pre-set image Keyword message and target pattern information.

Pre-set image can be shot with the camera of electronic equipment and be obtained, and can also receive the pre-set image of other equipment transmission It obtains.Pre-set image can also be stored in advance in electronic equipment, then be called by application software and show pre-set image.

Identification pre-set image obtains the information of pre-set image, when the loss of learning is more than default recognition threshold so that can not It is quickly found out corresponding audio-frequency information.For example, the pre-set image obtained is imperfect, the textbook page such as obtained by camera is endless It is whole, a part of textbook page is only obtained, which only accounts for 60%, and default recognition threshold can be set to whole textbook page 70%.Can also be that the pre-set image of acquisition is unintelligible, it is handshaking to cause pre-set image when shooting textbook page by camera Fuzzy, segment word or pattern None- identified arrive, when can not be quickly found out corresponding audio-frequency information so as to the information recognized, in advance If recognition threshold can be Text region rate 60%, that is, the word recognized accounts for the 60% of total word.When pre-set image has soon During fast identification information such as digital coding, Quick Response Code, then it is more than default recognition threshold directly to judge loss of learning.

When the loss of learning for recognizing pre-set image is more than default recognition threshold, keyword letter is extracted from pre-set image Breath and target pattern information.

Before the step of keyword message and target pattern information are extracted from pre-set image, first carried from pre-set image Take text information and pattern-information.

Also referring to Fig. 4, Fig. 4 is the flow signal of the pattern-information of acquisition pre-set image provided by the embodiments of the present application Figure.In the present embodiment, the method for obtaining the pattern-information of pre-set image, comprises the following steps：

Step 201, pre-set image is divided into multiple regions.Pre-set image is divided into enough regions, it can be with equal proportion Be divided into multiple regions.

Step 202, multiple sampled points on each region are set, multiple color cards are obtained according to multiple sampled points. All areas all set multiple sampled points, then obtain color card by these sampled points.Sampled point is more, and effect is better.

Step 203, background colour is determined according to the quantity of the color card of a variety of colors.

The color card of acquisition includes multiple color, if the ratio shared by one of color card quantity is more than centainly Ratio, such as 50%, then it is background colour to assert the color card.If pre-set image is colour picture, and has been used a large amount of It is progressive coloured, then if the ratio shared by color card quantity in certain color gamut is more than certain proportion, such as 60%, then It is background colour to assert the color card in the color gamut.It can also be according to the ratio shared by color card and location determination background Color, such as it is more than certain proportion, such as 55% in the ratio shared by the one of color card quantity in the top of pre-set image, Ratio shared by another color card quantity of the lower part of pre-set image is more than certain proportion, such as 55%, then assert that this is default Image includes two background colours.

Step 204, pattern-information is obtained according to background colour.

Pattern-information can include the position of background colour and background colour.Background colour region in pre-set image is removed, Remaining region is divided into multiple subregions by the spacing distance between region, is a pattern-information per sub-regions.

Step 205, target pattern information is extracted from pattern-information.

By pattern-information compared with the pre-stored patterns in database, if identical, pattern-information is set to target pattern.

Pre-stored patterns are stored in the database in advance, then by pattern-information compared with pre-stored patterns, if identical, Pattern-information is set to target pattern, wherein there are many identical criterion, such as both similarity reach 70% and recognize To be identical.

Illustrate please refer to fig. 5, Fig. 5 is the flow provided by the embodiments of the present application that pattern-information is obtained according to background colour Figure.In the present embodiment, pattern-information is obtained according to background colour to comprise the following steps：

Step 2041, if the sampled point in region obtains color card and is less than preset ratio threshold value for the ratio of background colour, Region is then determined to take graph region.

In one region, the ratio that color card accounts for all sampled points in whole region for the sampled point of background colour is more than one Certainty ratio such as 90%, it is determined that the region is background colour region, and the follow-up pattern-information that obtains then skips the region.

In one region, the ratio that color card accounts for all sampled points in whole region for the sampled point of background colour is less than in advance If proportion threshold value such as 60%, it is determined that take graph region, the follow-up pattern-information that obtains then obtains in the region in the region.

Step 2042, color that each display point is obtained in graph region is being taken, and is being correspondingly formed matrix data table.

Each color for showing point is obtained in graph region taking, display point can be pixel.Then a display is formed These color data values are formed a matrix data table by the corresponding color data values of point.

Step 2043, in matrix data table, color is set to first for the corresponding audio url of display point of background colour Color is not that the corresponding audio url of display point of background colour is set to the second data, obtains matrix data table to be selected by data.

In matrix data table, each color data values correspond to the color of a display point, if color data values are the back of the body The color data values are then set to the first data by scenery, such as the corresponding audio url of white, if color is not background colour, The color data values are set to the first data, such as the corresponding audio url of black, so as to obtain a matrix data table to be selected.It will It changes into image, then is the image of white background black line, eliminates many interference.It at this point it is possible to will by matrix data table to be selected Some edge datas are rejected, and the figure with edge lines such as is obtained by the first data, outside the figure also with some second Data, unwanted picture when the second data of this part is obtain pre-set image, can be rejected at this time.

Step 2044, in matrix data table to be selected, matrix data table to be selected is divided into multiple figures according to the first data Case region, according to the position acquisition pattern-information of the second data in area of the pattern.

In matrix data table to be selected, matrix data table to be selected is divided into multiple area of the pattern, the first number can be passed through According to division, because the corresponding image of the first data is background color, if the first data both sides all have the second data, two second numbers The first data between are above certain width, such as the 5% of the equidirectional width of whole region, are then demarcated, passed through Matrix data table to be selected is divided into multiple area of the pattern by this method.Then area of the pattern is changed into figure, by the second data pair The point answered links up, and forms a figure, then the figure is pattern-information.

Keyword message is extracted from text information, text information and word can be obtained from pre-set image first The font size of each word and the location information in pre-set image in information；If the corresponding font size of each word is included extremely It is two kinds few, then the word of largest font is set to preset keyword；If the quantity of preset keyword is not above default number of words, Preset keyword is directly set to keyword message；If the quantity of preset keyword is more than default number of words, according to default key The location information of word is screened, and obtains keyword message.For example, the position of preset keyword is at the edge of pre-set image, then It is rejected.Preset keyword is better than in the top of pre-set image in the lower section of pre-set image.

Keyword message further includes page number information, according to the storage location of page number information, as general image bottom among, The centre etc. of bottom outside, outer side edges, if the number is set to keyword message, and is to number in these region recognitions The keyword message of page number information.

In some embodiments, keyword message is extracted from text information, can by the word in text information with The word that prestores in database compares, if identical, word is arranged to keyword message.Storage prestores in the database in advance Word, which can determine the corresponding content of pre-set image in the scope of one, such as Chinese language, mathematics, first Volume, story-book etc..The word that prestores can also be obtained by network.Then by prestoring in the word and database that recognize before Word compares, if identical, word is arranged to keyword message.

In some embodiments, in the database, setting looks into keyword message set and looks into pattern set, the inside soon soon The keyword message and pattern of storage can quickly find corresponding audio url set, and in the audio url set Data volume is less, keyword message and pattern such as title, author's name, price, logo figure, Quick Response Code etc..

Step 102, using an information in keyword message and target pattern information as the first parameter, another information is made For the second parameter.

Also referring to Fig. 6, Fig. 6 is the flow diagram of first parameter of selection provided by the embodiments of the present application.In this reality It applies in example, chooses the first parameter and comprise the following steps：

Step 3021, when acquisition keyword message and target pattern acquisition of information correspond to the history of link information set respectively It is long；

Step 3022, using the shorter information of history duration in keyword message and target pattern information as the first parameter.

The history duration of information aggregate is correspondingly connected with by keyword message and target pattern acquisition of information, is selected in the two One be the first parameter.Corresponding audio url is obtained according to keyword message, and forms an audio url set, equally , according to the corresponding audio url of target pattern acquisition of information, and an audio url set is formed, then obtained according to the two The history duration of respective audio link set, is set to the first parameter, another is set to the second parameter by one of them.

Can multiple keywords can be included with keyword message, the probability of each keyword can be prestored, then The duration of the multiple keywords required to look up is calculated, likewise, target pattern information can include multiple pattern-informations, it can be pre- The probability of each pattern-information is first stored, the duration of the multiple target patterns required to look up is then calculated, then keyword is set One in information and target pattern information is the first parameter.

It can also start simultaneously at according to keyword message and target pattern acquisition of information corresponding data set, when one of them Data acquisition system first searches completion, then corresponding keyword message or target pattern information is set to the first parameter, another is Two parameters.

Step 103, corresponding Object linking is chosen in the corresponding audio url set of the first parameter according to the second parameter Data.

First according to the corresponding audio url set of the first parameter acquiring, then according to the second parameter in audio url set It is screened, obtains corresponding target connection data, need not search in the database again.

Also referring to Fig. 7, Fig. 7 is the flow diagram of acquisition audio url set provided by the embodiments of the present application. In the present embodiment, the first parameter includes multiple subparameters, the corresponding audio url set of the first parameter is obtained, including following step Suddenly：

Step 301, the search efficiency value of each subparameter is obtained, multiple subparameters according to search efficiency value are set and are searched for Sequentially.

Search efficiency value includes search database and obtains the quantity of corresponding audio url, time etc..For example, the first parameter For keyword message, keyword message is multiple keywords, then obtains the search efficiency value of each keyword message, search effect Rate value can be that search database obtains the quantity of corresponding audio url.Then multiple keyword roots evidence is obtained into corresponding sound The quantity of frequency link sets search order.

Step 302, it is more than the subparameter of default ranking using ranking in search order, search in the database is corresponded to Audio url, and form initial link set.

It is more than the subparameter of default ranking the such as the 3rd using ranking in search order, is utilized respectively ranking the in the database One and second subparameter search for obtain corresponding audio url, and form initial link set.

Step 303, the subparameter using ranking in search order under default ranking, carries out in initial link set Screening, obtains audio url set.

Then using other subparameters, screened in initial link set, audio url set obtained by screening, The data volume of initial link set is considerably less than database, can improve search efficiency.

Also referring to Fig. 8, Fig. 8 is the flow signal that selection respective objects provided by the embodiments of the present application link data Figure.In the present embodiment, corresponding Object linking is chosen in the corresponding audio url set of the first parameter according to the second parameter Data comprise the following steps：

Step 311, screened in audio url set according to the second parameter, obtain multiple data to be selected.

Step 312, by multiple data displays to be selected.

Step 313, according to instruction is confirmed, determine to confirm the corresponding Object linking data of instruction from multiple data to be selected.

Object linking data can not be also accurately obtained by being screened in audio url set according to the second parameter, but Multiple data to be selected relatively have been arrived, then by this multiple data display to be selected, have such as been shown by display screen, then according to Confirm instruction, determine to confirm the corresponding Object linking data of instruction from multiple data to be selected.The click commands of user are such as connected to, Click coordinate is the coordinate of one of them data to be selected, then confirms the data to be selected for Object linking data, while the two is closed Connection.

In some embodiments, it is specifically by multiple data displays to be selected, if the quantity of multiple data to be selected is more than Predetermined number then according to the similarity of the weight of keyword message and target pattern information in each data to be selected, obtains each The weighted value of data to be selected；The data to be selected that predetermined number weighted value maximum is selected from multiple data to be selected are shown.

Such as keyword message includes the keyword message of different fonts size, then the weight of the big keyword message of font The keyword message small more than font, the weight of the keyword message among pre-set image are more than the key of pre-set image side The weight of word information, in neighbouring keyword message, the weight of keyword message above is more than following keyword and believes The weight of breath.Then according to the similarity of the weight of keyword message and target pattern information in data to be selected, by a certain percentage Such as the weighted value of each 50% composition data to be selected, predetermined number such as 5 weighted value maximums are finally selected from multiple data to be selected Data to be selected be shown.

Step 104, according to Object linking data acquisition target audio information.

Object linking data are the address of corresponding target audio information, then obtain target audio information according to the address Storage location, then by the way that playout software is called to play the target audio information.The corresponding audio-frequency information of target connection data It can include multiple audios, when pre-set image includes multiple reading fields, multiple audios are corresponded with multiple reading fields.Example Such as, there are some cards, have text information and picture information on card, can also there is unique number coding, bar code or Quick Response Code Etc. quick identification information, then shooting the card by electronic equipment such as smart mobile phone obtains card image, then according to quick Identification information finds the audio message coincideing with the card from database, when text information or picture information are clicked, Play corresponding audio.When child takes smart mobile phone shooting card, because the reasons such as shooting angle or hand shaking, cause to lack Quick identification information or None- identified go out quick identification information, at this time by obtaining the keyword message and target of card image Pattern-information, then finds the corresponding audio-frequency information of card from database, and audio-frequency information includes corresponding multiple click on area Audio, then according to click location, the corresponding audio in region being wherein clicked is determined from multiple audios.

The method provided by the embodiments of the present application for obtaining audio-frequency information, when the loss of learning for recognizing pre-set image is more than pre- If during recognition threshold, keyword message and target pattern information are extracted from pre-set image；By keyword message and target pattern An information is as the first parameter in information, another information is as the second parameter；It is corresponded to according to the second parameter in the first parameter Audio url set in choose corresponding Object linking data；Obtain the corresponding audio-frequency information of Object linking data.Pass through pass An acquisition audio url set in key word information or target pattern information, is then screened further according to another, is obtained Object linking data promote the discrimination of the pre-set image few to information, improve recognition efficiency.

For ease of preferably implementing the method for acquisition audio-frequency information provided by the embodiments of the present application, the embodiment of the present application also carries For a kind of device for obtaining audio-frequency information.Wherein the meaning of noun is identical with the method for above-mentioned acquisition audio-frequency information, specific implementation Details may be referred to the explanation in embodiment of the method.

Referring to Fig. 9, Fig. 9 is the first structural representation of the device of acquisition audio-frequency information provided by the embodiments of the present application Figure.Wherein the device of the acquisition audio-frequency information is applied to electronic equipment, and the device 500 of the acquisition audio-frequency information includes character pattern Acquiring unit 501, parameter setting unit 502, Object linking acquiring unit 503 and audio acquiring unit 504.Wherein：

Character pattern acquiring unit 501, for when the loss of learning for recognizing pre-set image is more than default recognition threshold, Keyword message and target pattern information are extracted from pre-set image.

Pre-set image can be shot with the camera of electronic equipment and be obtained, and can also receive the pre-set image of other equipment transmission It obtains.Receiving that other equipment transmission pre-set image obtains can wirelessly or wired mode.Wireless mode include bluetooth, The modes such as NFC, WIFI network and mobile network, mobile network's networks such as including 2G, 3G and 4G.Wired mode includes passing through number Pre-set image is obtained according to line connection other equipment.Pre-set image can also be stored in advance in electronic equipment, then by answering Pre-set image is shown with software transfer.

Referring to Fig. 10, Figure 10 is second of structural representation of the device of acquisition audio-frequency information provided by the embodiments of the present application Figure.In the present embodiment, character pattern acquiring unit 501 includes division subelement 5011, sampling subelement 5012, background colour Obtain subelement 5013, pattern-information obtains subelement 5014 and target pattern acquisition of information subelement 5015.Wherein：

Subelement 5011 is divided, for pre-set image to be divided into multiple regions.Pre-set image is divided into enough regions, Can multiple regions be divided into equal proportion.

Subelement 5012 is sampled, for setting multiple sampled points on each region, is obtained according to multiple sampled points multiple Color card.Multiple sampled points are all set in all areas, then obtain color card by these sampled points.Sampled point is got over More, effect is better.

Background colour obtains subelement 5013, and the quantity for the color card according to a variety of colors determines background colour；

Pattern-information obtains subelement 5014, for obtaining pattern-information according to background colour.

Pattern-information can include the position of background colour and background colour.Background colour region in pre-set image is removed, Spacing distance between remaining region clearance is divided into multiple subregions, is a pattern-information per sub-regions.

Target pattern acquisition of information subelement 5015, for extracting target pattern information from pattern-information.

Please refer to Fig.1 the third structural representation for the device that 1, Figure 11 is acquisition audio-frequency information provided by the embodiments of the present application Figure.In the present embodiment, pattern-information obtains subelement 5014 and includes graph region determining module 541, the first matrix is taken to be formed Module 542, the second matrix form module 543 and pattern-information acquisition module 544.Wherein：

Graph region determining module 541 is taken, if it is small for the ratio of background colour to obtain color card for the sampled point in region In preset ratio threshold value, it is determined that region is to take graph region.

First matrix forms module 542, for taking the color that each display point is obtained in graph region, and is correspondingly formed square Battle array tables of data.

Second matrix forms module 543, for being the corresponding sound of display point of background colour by color in matrix data table Frequency link is set to the first data, is not that the corresponding audio url of display point of background colour is set to the second data by color, is treated Select matrix data table.

In matrix data table, each color data values correspond to the color of a display point, if color data values are the back of the body The color data values are then set to the first data by scenery, such as the corresponding audio url of white, if color is not background colour, The color data values are set to the first data, such as the corresponding audio url of black, so as to obtain a matrix data table to be selected.It will It changes into image, then is the image of white background black line, eliminates many interference.It at this point it is possible to will by matrix data table to be selected Some edge datas are rejected, and the figure with edge lines such as is obtained by the first data, outside the figure also with some second Data, unwanted picture when the second data of this this part is obtain pre-set image, can be rejected at this time.

Pattern-information acquisition module 544, in matrix data table to be selected, according to the scope of the first data by square to be selected Battle array tables of data is divided into multiple area of the pattern, according to the position acquisition pattern-information of the second data in area of the pattern.

Please refer to Fig.1 the 4th kind of structural representation of the device that 2, Figure 12 is acquisition audio-frequency information provided by the embodiments of the present application Figure.In the present embodiment, character pattern acquiring unit 501 includes text information acquisition subelement 5016, preset keyword obtains Subelement 5017 and keyword message is taken to screen subelement 5018.Wherein：

Text information obtains subelement 5016, each in text information and text information for being obtained from pre-set image The font size of a word and the location information in pre-set image；

Preset keyword obtains subelement 5017, if including at least two for the corresponding font size of each word, The word of largest font is set to preset keyword；

Keyword message screens subelement 5018, if being more than default number of words for the quantity of preset keyword, according to pre- If the location information of keyword is screened, keyword message is obtained.

For example, the position of preset keyword at the edge of pre-set image, is then rejected.Preset keyword is in pre-set image Top be better than in the lower section of pre-set image.

Keyword message further includes page number information, according to the storage location of the page number, as general image bottom among, bottom The number is then set to keyword message in these region recognitions to number, and is the pass of the page number by outside, the centre etc. of outer side edges Key word information.

In some embodiments, character pattern acquiring unit 501 can also be by the word and database in text information In the word that prestores compare, if identical, word is arranged to keyword message.Store the word that prestores in the database in advance, The word that prestores can determine the corresponding content of pre-set image in the scope of one, such as Chinese language, mathematics, first, event Thing book etc..The word that prestores can also be obtained by network.Then by the word that prestores in the word and database that recognize before Compare, if identical, word is arranged to keyword message.

In some embodiments, character pattern acquiring unit 501 can also be by pattern-information and prestoring in database Pattern compares, if identical, pattern-information is set to target pattern.

In some embodiments, character pattern acquiring unit 501 is additionally operable to, and in the database, keyword is looked into setting soon Information aggregate and pattern set is looked into soon, the keyword message and pattern of the inside storage can quickly find corresponding audio url Set, and the data volume in the audio url set is less, keyword message and pattern such as title, author's name, price, vehicle It marks on a map shape, Quick Response Code etc..

Parameter setting unit 502, for using an information in keyword message and target pattern information as the first parameter, Another information is as the second parameter.

Please refer to Fig.1 the 5th kind of structural representation of the device that 3, Figure 13 is acquisition audio-frequency information provided by the embodiments of the present application Figure.In the present embodiment, parameter setting unit 502 includes history duration acquisition subelement 5021 and parameter setting subelement 5022.Wherein：

History duration obtains subelement 5021, and chain is corresponded to for obtaining keyword message and target pattern acquisition of information respectively Connect the history duration of information aggregate；

Parameter setting subelement 5022, for by the shorter information of history duration in keyword message and target pattern information As the first parameter.

The history duration of information aggregate is correspondingly connected with by keyword message and target pattern acquisition of information, is selected in the two One be the first parameter.

Corresponding audio url is obtained according to keyword message, and forms an audio url set, likewise, according to mesh The corresponding audio url of case of marking on a map acquisition of information, and an audio url set is formed, data acquisition system is then obtained according to the two Duration, one of them is set to the first parameter, another is set to the second parameter.For example, it starts simultaneously at according to keyword message With target pattern acquisition of information corresponding data set, when one of data acquisition system first searches completion, then by corresponding keyword Information or target pattern information are set to the first parameter, another is the second parameter.

Object linking acquiring unit 503, for being selected according to the second parameter in the corresponding audio url set of the first parameter Take corresponding Object linking data.

Please refer to Fig.1 the 6th kind of structural representation of the device that 4, Figure 14 is acquisition audio-frequency information provided by the embodiments of the present application Figure.In the present embodiment, Object linking acquiring unit 503 includes order setting subelement 5031,5032 and of search subelement First screening subelement 5033.Wherein：

Order sets subelement 5031, for obtaining the search efficiency value for multiple subparameters that the first parameter includes, and will Multiple subparameters set search order according to search efficiency value.

Subelement 5032 is searched for, for being more than the subparameter of default ranking using ranking in search order, in the database Search obtains corresponding audio url, and forms initial link set.

First screening subelement 5033, for the subparameter using ranking in search order under default ranking, first Begin to be screened in link set, obtain audio url set.

Please refer to Fig.1 the 7th kind of structural representation of the device that 5, Figure 15 is acquisition audio-frequency information provided by the embodiments of the present application Figure.In the present embodiment, Object linking acquiring unit 503 includes the second screening subelement 5034,5035 and of displaying subelement Determination subelement 5036.Wherein：

Second screening subelement 5034, for being screened in audio url set according to the second parameter, obtains multiple Data to be selected；

Subelement 5035 is shown, for by multiple data displays to be selected；

Determination subelement 5036 instructs corresponding mesh for according to instruction is confirmed, determining to confirm from multiple data to be selected Mark link data.

In some embodiments, subelement is shown, if the quantity for being additionally operable to multiple data to be selected is more than predetermined number, According to the similarity of the weight of keyword message and target pattern information in each data to be selected, the power of each data to be selected of acquisition Weight values；The data to be selected that predetermined number weighted value maximum is selected from multiple data to be selected are shown.

Audio acquiring unit 504, for according to Object linking data acquisition target audio information.

The device provided by the embodiments of the present application for obtaining audio-frequency information, when the loss of learning for recognizing pre-set image is more than pre- If during recognition threshold, keyword message and target pattern information are extracted from pre-set image；By keyword message and target pattern An information is as the first parameter in information, another information is as the second parameter；It is corresponded to according to the second parameter in the first parameter Audio url set in choose corresponding Object linking data；Obtain the corresponding audio-frequency information of Object linking data.Pass through pass An acquisition audio url set in key word information or target pattern information, is then screened further according to another, is obtained Object linking data promote the discrimination of the pre-set image few to information, improve recognition efficiency.

It when it is implemented, Yi Shang modules can be independent entity to realize, can also be combined, be made It is realized for same or several entities, the specific implementation of more than modules can be found in the embodiment of the method for front, herein not It repeats again.

In the embodiment of the present application, the method category of the acquisition audio-frequency information in the device and foregoing embodiments of audio-frequency information is obtained In same design, any provided in the embodiment of the method for obtaining audio-frequency information can be run on the device for obtaining audio-frequency information Method, specific implementation process refer to the embodiment for the method for obtaining audio-frequency information, and details are not described herein again.

The embodiment of the present application also provides a kind of electronic equipment.Please refer to Fig.1 6, electronic equipment 600 include processor 601 with And memory 602.Wherein, processor 601 is electrically connected with memory 602.

Processor 600 is the control centre of electronic equipment 600, utilizes various interfaces and the entire electronic equipment of connection Various pieces computer program in memory 602 and are called by operation or load store and are stored in memory 602 Interior data perform the various functions of electronic equipment 600 and handle data, so as to carry out integral monitoring to electronic equipment 600.

Memory 602 can be used for storage software program and unit, and processor 601 is stored in memory 602 by operation Computer program and unit, so as to perform various functions application and data processing.Memory 602 can mainly include storage Program area and storage data field, wherein, storing program area can storage program area, the computer program needed at least one function (such as sound-playing function, image player function etc.) etc.；Storage data field can be stored to be created according to using for electronic equipment Data etc..In addition, memory 602 can include high-speed random access memory, nonvolatile memory can also be included, A for example, at least disk memory, flush memory device or other volatile solid-state parts.Correspondingly, memory 602 is gone back It can include Memory Controller, to provide access of the processor 601 to memory 602.

In the embodiment of the present application, the processor 601 in electronic equipment 600 can be according to the steps, by one or one The corresponding instruction of process of a above computer program is loaded into memory 602, and is stored in by the operation of processor 601 Computer program in reservoir 602, it is as follows so as to fulfill various functions：

When the loss of learning for recognizing pre-set image is more than default recognition threshold, keyword letter is extracted from pre-set image Breath and target pattern information；

Using an information in keyword message and target pattern information as the first parameter, another information is as the second ginseng Number；

Corresponding Object linking data are chosen in the corresponding audio url set of the first parameter according to the second parameter；

Obtain the corresponding audio-frequency information of Object linking data.

In some embodiments, processor 601 is additionally operable to perform following steps：

Keyword message is obtained respectively and target pattern acquisition of information corresponds to the history duration of link information set；

Using the shorter information of history duration in keyword message and target pattern information as the first parameter.

In some embodiments, the first parameter includes multiple subparameters, and processor 601 is additionally operable to perform following steps：

The search efficiency value of each subparameter is obtained, multiple subparameters are set into search order according to search efficiency value；

It is more than the subparameter of default ranking using ranking in search order, search in the database obtains corresponding audio chain It connects, and forms initial link set；

Using subparameter of the ranking in search order under default ranking, screened, obtained in initial link set To audio url set.

It is screened in audio url set according to the second parameter, obtains multiple data to be selected；

By multiple data displays to be selected；

It is instructed according to confirming, determines to confirm the corresponding Object linking data of instruction from multiple data to be selected.

Pre-set image is divided into multiple regions；

Multiple sampled points on each region are set, multiple color cards are obtained according to multiple sampled points；

Background colour is determined according to the quantity of the color card of a variety of colors；

Pattern-information is obtained according to background colour；

Target pattern information is extracted from pattern-information.

If the sampled point in region obtains color card is less than preset ratio threshold value for the ratio of background colour, it is determined that region To take graph region；

Each color for showing and putting is obtained in graph region taking, and is correspondingly formed matrix data table；

In matrix data table, color is set to the first data for the corresponding audio url of display point of background colour, by face Color is not that the corresponding audio url of display point of background colour is set to the second data, obtains matrix data table to be selected；

In matrix data table to be selected, matrix data table to be selected is divided into multiple area of the pattern, root according to the first data According to the position acquisition pattern-information of the second data in area of the pattern.

The font size of each word is obtained in text information and text information from pre-set image and in pre-set image Location information；

If the corresponding font size of each word includes at least two, the word of largest font is set to default key Word；

If the quantity of preset keyword is more than default number of words, is screened, obtained according to the location information of preset keyword To keyword message.

It can be seen from the above, electronic equipment provided by the embodiments of the present application, when the loss of learning for recognizing pre-set image is more than During default recognition threshold, keyword message and target pattern information are extracted from pre-set image；By keyword message and target figure An information is as the first parameter in case information, another information is as the second parameter；According to the second parameter in the first parameter pair Corresponding Object linking data are chosen in the audio url set answered；Obtain the corresponding audio-frequency information of Object linking data.Pass through An acquisition audio url set in keyword message or target pattern information, is then screened further according to another, is obtained To Object linking data, the discrimination of the pre-set image few to information is promoted.

Also referring to Figure 17, in some embodiments, electronic equipment 600 can also include：Display 603, radio frequency Circuit 604, voicefrequency circuit 605 and power supply 606.Wherein, wherein, display 603, radio circuit 604, voicefrequency circuit 605 with And power supply 606 is electrically connected respectively with processor 601.

Display 603 is displayed for by information input by user or is supplied to the information of user and various figures to use Family interface, these graphical user interface can be made of figure, text, icon, video and its any combination.Display 603 Can include display panel, in some embodiments, may be employed liquid crystal display (Liquid Crystal Display, LCD) or the forms such as Organic Light Emitting Diode (Organic Light-Emitting Diode, OLED) configure display surface Plate.

Radio circuit 604 can be used for transceiving radio frequency signal, to be set by wireless communication and the network equipment or other electronics It is standby to establish wireless telecommunications, the receiving and transmitting signal between the network equipment or other electronic equipments.

Voicefrequency circuit 605 can be used for providing the audio interface between user and electronic equipment by loud speaker, microphone.

Power supply 606 is used to all parts power supply of electronic equipment 600.In some embodiments, power supply 606 can With logically contiguous by power-supply management system and processor 601, thus charged, discharged by power-supply management system realization management, And the functions such as power managed.

Although not shown in Figure 17, electronic equipment 600 can also include camera, bluetooth unit etc., and details are not described herein.

The embodiment of the present application also provides a kind of storage medium, and storage medium is stored with computer program, works as computer program When running on computers so that computer performs the application program management-control method in any of the above-described embodiment, such as：Work as identification Loss of learning to pre-set image is more than when presetting recognition threshold, and keyword message and target pattern letter are extracted from pre-set image Breath；Using in keyword message and target pattern information, an information is as the first parameter, another information is as the second parameter；Root According to the second parameter corresponding Object linking data are chosen in the corresponding audio url set of the first parameter；Obtain Object linking number According to corresponding audio-frequency information.

In the embodiment of the present application, storage medium can be magnetic disc, CD, read-only memory (Read Only Memory, ) or random access memory (Random Access Memory, RAM) etc. ROM.

In the above-described embodiments, all emphasize particularly on different fields to the description of each embodiment, there is no the portion being described in detail in some embodiment Point, it may refer to the associated description of other embodiment.

It should be noted that for the method for the acquisition audio-frequency information of the embodiment of the present application, this field common test people Member is appreciated that realize all or part of flow for the method that the embodiment of the present application obtains audio-frequency information, is that can pass through computer Program controls relevant hardware to complete, and computer program can be stored in a computer read/write memory medium, such as stores It performs in the memory of electronic equipment, and by least one processor in the electronic equipment, may include in the process of implementation Such as obtain the flow of the embodiment of the method for audio-frequency information.Wherein, storage medium can be magnetic disc, CD, read-only memory, with Machine access/memory body etc..

For the device of the acquisition audio-frequency information of the embodiment of the present application, each functional unit can be integrated in a processing In chip or unit is individually physically present, can also two or more units integrate in a unit. The form that hardware had both may be employed in above-mentioned integrated unit is realized, can also be realized in the form of SFU software functional unit.It is integrated If unit realized in the form of SFU software functional unit and be independent production marketing or in use, one can also be stored in In a computer read/write memory medium, storage medium is for example read-only memory, disk or CD etc..

Method, apparatus, storage medium and the electronics of a kind of acquisition audio-frequency information provided above the embodiment of the present application Equipment is described in detail, and the principle and implementation of this application are described for specific case used herein, with The explanation of upper embodiment is only intended to help to understand the present processes and its core concept；Meanwhile for the technology of this field Personnel, according to the thought of the application, there will be changes in specific embodiments and applications, in conclusion this theory Bright book content should not be construed as the limitation to the application.

Claims

1. a kind of method for obtaining audio-frequency information, applied to electronic equipment, which is characterized in that the method includes the steps：

When the loss of learning for recognizing pre-set image is more than default recognition threshold, keyword letter is extracted from the pre-set image Breath and target pattern information；

Using an information in the keyword message and the target pattern information as the first parameter, another information is as Two parameters；

Corresponding Object linking data are chosen in the corresponding audio url set of first parameter according to second parameter；

2. the method according to claim 1 for obtaining audio-frequency information, which is characterized in that it is described by the keyword message and A step of information is as the first parameter in the target pattern information, including；

The keyword message is obtained respectively and the target pattern acquisition of information corresponds to the history duration of link information set；

Using the shorter information of history duration in the keyword message and the target pattern information as the first parameter.

3. the method according to claim 1 for obtaining audio-frequency information, which is characterized in that first parameter includes multiple sons Parameter, the step of obtaining first parameter corresponding audio url set, include：

The search efficiency value of each subparameter is obtained, multiple subparameters according to described search efficiency value are set and are searched for Sequentially；

It is more than the subparameter of default ranking using ranking in described search order, search in the database obtains corresponding sound Frequency links, and forms initial link set；

Using the subparameter of the ranking in described search order under default ranking, carried out in the initial link set Screening, obtains the audio url set.

4. the method according to claim 1 for obtaining audio-frequency information, which is characterized in that described to be existed according to second parameter The step of corresponding Object linking data being chosen in the corresponding audio url set of first parameter, including：

It is screened in the audio url set according to second parameter, obtains multiple data to be selected；

By the multiple data display to be selected；

It is instructed according to confirming, determines that the confirmation instructs corresponding Object linking data from the multiple data to be selected.

5. the method according to claim 1 for obtaining audio-frequency information, which is characterized in that extract mesh from the pre-set image The step of marking pattern-information, including：

The pre-set image is divided into multiple regions；

Multiple sampled points are set on each region, multiple color cards are obtained according to the multiple sampled point；

Pattern-information is obtained according to the background colour；

Target pattern information is extracted from the pattern-information.

6. the method according to claim 5 for obtaining audio-frequency information, which is characterized in that described to be obtained according to the background colour The step of pattern-information, including：

If the sampled point in the region obtains color card is less than preset ratio threshold value for the ratio of the background colour, it is determined that The region is to take graph region；

In the color for taking and each display being obtained in graph region and is put, and it is correspondingly formed matrix data table；

In the matrix data table, color is set to the first number for the corresponding audio url of the display point of the background colour According to, by color be the background colour the corresponding audio url of the display point be set to the second data, obtain matrix function to be selected According to table；

In the matrix data table to be selected, the matrix data table to be selected is divided into multiple patterns according to first data Region, according to the position acquisition pattern-information of second data in the area of the pattern.

7. the method according to claim 1 for obtaining audio-frequency information, which is characterized in that described to be carried from the pre-set image The step of taking keyword message, including：

The font size of each word is obtained in text information and the text information from the pre-set image and described The location information of pre-set image；

If the quantity of the preset keyword is more than default number of words, sieved according to the location information of the preset keyword Choosing, obtains keyword message.

8. a kind of device for obtaining audio-frequency information, which is characterized in that described device includes：

Character pattern acquiring unit, for when the loss of learning for recognizing pre-set image is more than default recognition threshold, from described Keyword message and target pattern information are extracted in pre-set image；

Parameter setting unit, for using an information in the keyword message and the target pattern information as the first ginseng Number, another information is as the second parameter；

Object linking acquiring unit, for being selected according to second parameter in the corresponding audio url set of first parameter Take corresponding Object linking data

9. the device according to claim 8 for obtaining audio-frequency information, which is characterized in that the parameter setting unit includes：

History duration obtains subelement, and chain is corresponded to for obtaining the keyword message and the target pattern acquisition of information respectively Connect the history duration of information aggregate；

Parameter setting subelement, for by the shorter information of history duration in the keyword message and the target pattern information As the first parameter.

10. the device according to claim 8 for obtaining audio-frequency information, which is characterized in that the Object linking acquiring unit Including：

Order sets subelement, for obtaining the search efficiency value for multiple subparameters that first parameter includes, and will Multiple subparameters set search order according to described search efficiency value；

Subelement is searched for, for being more than the subparameter of default ranking using ranking in described search order, in the database Search obtains corresponding audio url, and forms initial link set；

First screening subelement, for the subparameter using ranking in described search order under default ranking, in institute It states and is screened in initial link set, obtain the audio url set.

11. the device according to claim 8 for obtaining audio-frequency information, which is characterized in that the Object linking acquiring unit Including：

Second screening subelement, for being screened in the audio url set according to second parameter, obtains multiple Data to be selected；

Subelement is shown, for by the multiple data display to be selected；

Determination subelement, for according to instruction is confirmed, determining that the confirmation instructs corresponding mesh from the multiple data to be selected Mark link data.

12. the device according to claim 8 for obtaining audio-frequency information, which is characterized in that the character pattern acquiring unit Including：

Subelement is divided, for the pre-set image to be divided into multiple regions；

Subelement is sampled, for setting multiple sampled points on each region, is obtained according to the multiple sampled point multiple Color card；

Background colour obtains subelement, and the quantity for the color card according to a variety of colors determines background colour；

Pattern-information obtains subelement, for obtaining pattern-information according to the background colour；

Target pattern acquisition of information subelement, for extracting target pattern information from the pattern-information.

13. the device according to claim 12 for obtaining audio-frequency information, which is characterized in that it is single that the pattern-information obtains son Member includes：

Graph region determining module is taken, if it is small for the ratio of the background colour to obtain color card for the sampled point in the region In preset ratio threshold value, it is determined that the region is to take graph region；

First matrix forms module, for taking the color that each display is obtained in graph region and is put described, and is correspondingly formed matrix Tables of data；

Second matrix forms module, for being the display point pair of the background colour by color in the matrix data table The audio url answered is set to the first data, is not that the corresponding audio url of the display point of the background colour is set to the by color Two data obtain matrix data table to be selected；

Pattern-information acquisition module, in the matrix data table to be selected, according to first data by the square to be selected Battle array tables of data is divided into multiple area of the pattern, according to the position acquisition pattern-information of second data in the area of the pattern.

14. the device according to claim 8 for obtaining audio-frequency information, which is characterized in that the character pattern acquiring unit Including：

Text information obtains subelement, each in text information and the text information for being obtained from the pre-set image The font size of a word and the location information in the pre-set image；

Preset keyword obtains subelement, if including at least two for the corresponding font size of each word, by word The word of body maximum is set to preset keyword；

Keyword message screens subelement, if being more than default number of words for the quantity of the preset keyword, according to described pre- If the location information of keyword is screened, keyword message is obtained.

15. a kind of storage medium, is stored thereon with computer program, which is characterized in that when the computer program is in computer During upper operation so that the computer performs the method as described in any one of claim 1 to 7 for obtaining audio-frequency information.

16. a kind of electronic equipment, including processor and memory, the memory has computer program, which is characterized in that described Processor is by calling the computer program, for performing acquisition audio-frequency information as described in any one of claim 1 to 7 Method.