CN108287930A - A kind of recording searching method, device and electronic equipment - Google Patents
A kind of recording searching method, device and electronic equipment Download PDFInfo
- Publication number
- CN108287930A CN108287930A CN201810191881.8A CN201810191881A CN108287930A CN 108287930 A CN108287930 A CN 108287930A CN 201810191881 A CN201810191881 A CN 201810191881A CN 108287930 A CN108287930 A CN 108287930A
- Authority
- CN
- China
- Prior art keywords
- text
- recording
- content
- search
- data
- 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
- G06F16/63—Querying
- G06F16/632—Query formulation
-
- 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
- G06F16/63—Querying
- G06F16/635—Filtering based on additional data, e.g. user or group profiles
-
- 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
- G06F16/686—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, title or artist information, time, location or usage information, user ratings
Abstract
The present invention relates to recording broadcasting technical fields, more particularly to a kind of recording searching method, device and electronic equipment.Wherein, recording searching method includes：Search data are obtained, described search data include several sections of text search content T arranged according to chronological orderi, i >=1, and i is positive integer, time point is located at the T of iiText search content is located at the T of i+1 earlier than time pointi+1Text search content, and Ti+1Text search content includes TiText search content；According to chronological order, T is selectediText search content searches for the recording content of text that similarity meets preset condition in dictation library, and dictation library includes that multiple recording content of text of text data are translated by recording；According to search result, the output of recording is controlled.Therefore, text search content can be selected to segmented to scan for according to chronological order, so as to rapidly search for out target recording file.
Description
Technical field
The present invention relates to recording broadcasting technical fields, more particularly to a kind of recording searching method, device and electronic equipment.
Background technology
Sound-recording function is the most basic application function of intelligent terminal, and by sound-recording function, user can incite somebody to action whenever and wherever possible
At that time under SoundRec, subsequently to reappear scene of talking at that time.
Traditional technology provides a kind of intelligent terminal, which receives voice data input by user, and according to voice
Data search goes out corresponding recording file.
Inventor in the implementation of the present invention, it is found that traditional technology has at least the following problems：Traditional technology will be used
The voice data of family input is all as search field, and to search for recording file, therefore, intelligent terminal needs to expend relatively more
Time scans for, such as：User requires to look up the recording file for including critical field " here spend sea, really very beautiful ",
Then, intelligent terminal receives voice data input by user " here spend sea, really very beautiful ", and intelligent terminal carefully traverses institute
There is recording file, finds out the target recording file for including critical field " here spend sea, really very beautiful ".Due to intelligent end
End needs to form both keyword section " here spend sea " and " really very beautiful ", and the both keyword section is traversed often one by one
A recording file, relative to the mode for only needing to traverse each recording file according to a critical field, it is clear that closed according to two
The mode that key field traverses each recording file is to expend the relatively more time.
Also, in actual application, perhaps only there are one recording files to include " spending sea " this recording for intelligent terminal
Phrase, user, which only needs to input critical field " here spend sea ", can also be exactly found corresponding recording file, without defeated
Enter both keyword section " here spend sea " to be searched with " really very beautiful ", to save additional search time.
Invention content
One purpose of the embodiment of the present invention is intended to provide a kind of recording searching method, device and electronic equipment, can divide
Segmentation fast search go out target recording file.
In order to solve the above technical problems, the embodiment of the present invention provides following technical scheme：
In a first aspect, the embodiment of the present invention provides a kind of recording searching method, including：
Search data are obtained, described search data include several sections of text search content T arranged according to chronological orderi, i
>=1, and i is positive integer, time point is located at the T of iiText search content is located at the T of i+1 earlier than time pointi+1Text search
Content, and the Ti+1Text search content includes the TiText search content；
According to chronological order, the T is selectediText search content searches for similarity in dictation library and meets preset condition
Recording content of text, the dictation library includes that multiple recording content of text of text data are translated by recording；
According to search result, the output of recording is controlled.
Optionally, described that the output of recording is controlled according to search result, including：
Judge the TiWhether the similarity between text search content and the recording content of text of the dictation library is full
Sufficient preset condition；
If satisfied, statistics meets the quantity of the recording content of text of preset condition；
Judge whether the quantity for the recording content of text for meeting preset condition is more than preset quantity threshold value；
If more than judging Ti+1Whether the similarity between text search content and the recording content of text of dictation library is full
Sufficient preset condition, until the quantity for meeting the recording content of text of preset condition is less than preset quantity threshold value, and it is pre- to export satisfaction
If the corresponding recording of recording content of text of condition；
If being less than, output meets the corresponding recording of recording content of text of preset condition；
If not meeting, judging result is exported.
Optionally, the recording content of text includes several frame recording datas；
The output meets the corresponding recording of recording content of text of preset condition, including：
Frame recording data corresponding with text search content matching is determined from the recording content of text for meet preset condition；
It is to play starting point, playback with the frame recording data corresponding with text search content matching.
Optionally, data are searched in the acquisition, including：
The voice data of input is received, the voice data includes several sections of voices arranged according to chronological order；
According to fuzzy neural network algorithm, the voice data is translated into speech text data, and the voice is literary
Notebook data is as search data.
Optionally, the method further includes：
When the total duration for detecting described search data is less than 1, determine that the total duration of described search data is equal to 1.
In second aspect, the embodiment of the present invention provides a kind of recording searcher, including：
Acquisition module, for obtaining search data, described search data include several sections of texts arranged according to chronological order
This search content Ti, i >=1, and i is positive integer, time point is located at the T of iiText search content is located at i+1's earlier than time point
Ti+1Text search content, and the Ti+1Text search content includes the TiText search content；
Selecting module, for according to chronological order, selecting the TiText search content is searched for similar in dictation library
Degree meets the recording content of text of preset condition, and the dictation library includes that multiple recording texts of text data are translated by recording
Content；
Control module, for according to search result, controlling the output of recording.
Optionally, the control module includes：
First judging unit, for judging the TiThe recording content of text of text search content and the dictation library it
Between similarity whether meet preset condition；
Statistic unit, for if satisfied, statistics meets the quantity of the recording content of text of preset condition；
Second judgment unit, for judging whether the quantity for the recording content of text for meeting preset condition is more than preset quantity
Threshold value；
First output unit is used for if more than T is judgedi+1The recording content of text of text search content and dictation library it
Between similarity whether meet preset condition, until meet preset condition recording content of text quantity be less than preset quantity threshold
Value, and the corresponding recording of recording content of text for meeting preset condition is exported, if being less than, output meets the recording text of preset condition
The corresponding recording of this content；
If second output unit exports judging result for not meeting.
Optionally, the recording content of text includes several frame recording datas；
First output unit is specifically used for：The determining and text search from the recording content of text for meet preset condition
The correspondence frame recording data of content matching；It is to play to originate with the frame recording data corresponding with text search content matching
Point, playback.
Optionally, the acquisition module includes：
Receiving unit, the voice data for receiving input, if the voice data includes being arranged according to chronological order
Dry section voice；
Translation unit, for according to fuzzy neural network algorithm, the voice data to be translated into speech text data, and
Using the speech text data as search data.
Optionally, described device further includes：
Determining module, for when the total duration for detecting described search data is less than 1, determining the total of described search data
Duration is equal to 1.
In the third aspect, the embodiment of the present invention provides a kind of electronic equipment, including：
At least one processor；
And the memory being connect at least one processor communication；Wherein, be stored with can be by institute for the memory
The instruction that at least one processor executes is stated, described instruction is executed by least one processor, so that described at least one
Processor can be used in executing any one of them recording searching method.
In recording searching method, device and the electronic equipment that each embodiment of the present invention provides, first, searched by obtaining
Rope data, search data include several sections of text search content T arranged according to chronological orderi, i >=1, and i is positive integer, when
Between point positioned at i TiText search content is located at the T of i+1 earlier than time pointi+1Text search content, and Ti+1Text is searched
Rope content includes TiText search content.Secondly, according to chronological order, T is selectediText search content is searched in dictation library
Rope similarity meets the recording content of text of preset condition, and dictation library includes that multiple recording text of text data is translated by recording
This content.Finally, according to search result, the output of recording is controlled.Therefore, it can be selected to segmented according to chronological order
Text search content scans for, so as to rapidly search for out target recording file.
Description of the drawings
One or more embodiments are illustrated by the picture in corresponding attached drawing, these exemplary theorys
The bright restriction not constituted to embodiment, the element with same reference numbers label is expressed as similar element in attached drawing, removes
Non- to have special statement, composition does not limit the figure in attached drawing.
Fig. 1 is the structural schematic diagram that the embodiment of the present invention provides a kind of electronic equipment；
Fig. 2 is that the embodiment of the present invention provides a kind of flow diagram of recording searching method；
Fig. 3 is that the embodiment of the present invention provides a kind of form schematic diagram of text search content；
Fig. 4 is the flow diagram of step 021 in Fig. 2；
Fig. 5 is the oscillogram of voice data；
Fig. 6 is that the embodiment of the present invention provides a kind of structural schematic diagram of recording searcher；
Fig. 7 is the structural schematic diagram of control module in Fig. 6；
Fig. 8 is the structural schematic diagram of acquisition module in Fig. 6；
Fig. 9 is that another embodiment of the present invention provides a kind of structural schematic diagram of recording searcher.
Specific implementation mode
In order to make the purpose , technical scheme and advantage of the present invention be clearer, with reference to the accompanying drawings and embodiments, right
The present invention is further elaborated.It should be appreciated that described herein, specific examples are only used to explain the present invention, not
For limiting the present invention.
Recording searching method provided in an embodiment of the present invention, can in any suitable type, have user interaction means and
It is executed in the electronic equipment of the processor of operational capability, such as desktop computer, smart mobile phone, tablet computer and other users
In terminal.
The recording searcher of the embodiment of the present invention can be used as one of software or hardware function units, independently set
It sets in above-mentioned electronic equipment, can also be used as integration one of in the processor function module, execute the present invention and implement
The recording searching method of example.
Electronic equipment can be smart mobile phone, computer, palm PC (Personal Digital Assistant,
PDA), tablet computer, smartwatch, e-book etc..
Electronic equipment supports the installation of various multipads, one in such as following multipad or more
A multipad：Recording application program, drawing application program, demonstration applications, word-processing application, electronic watch
Lattice application program, telephony application, videoconference application, email application, disappears at game application immediately
Cease application program, application program, photo management application program, digital camera application program, digital video recorder application are supported in training
Program, web page browsing application program, digital music player application, video frequency player application program and etc..
Referring to Fig. 1, electronic equipment 100 includes memory 11, at least one processor 12 and bus system.Wherein,
At least one processor 12 is connected with memory 11 by bus system.
Memory 11 can be non-volatile computer readable storage medium storing program for executing, for storage computer executable instructions.
Computer executable instructions can also be stored and/or be transmitted in any non-volatile computer readable storage medium storing program for executing, so as to by
Instruction execution system, device or equipment use, or instruction execution system, device or equipment is combined to use, and the wherein instruction is held
Row system, device or equipment such as computer based system, the system comprising processor can be from instruction execution system, dresses
It sets or equipment acquisition instruction and the other systems for executing the instruction.For the purpose of this document, " non-volatile computer is readable to be deposited
Storage media " can be visibly include or storage computer executable instructions any medium, which can
For being used by instruction execution system, equipment or system or instruction execution system, device or equipment being combined to use.It is non-volatile
The computer-readable medium of depositing of property can include but is not limited to magnetic, light and/or semiconductor storage.These storage devices
Example include disk, the CD based on CD, DVD or Blue-Ray technology and persistence solid-state memory (such as, flash memory, solid-state
Driver etc.).
Processor 12 can be central processing unit (Central Processing Unit, referred to as " CPU ").At this
Reason device can also be other general processors, digital signal processor (DSP), application-specific integrated circuit (ASIC), ready-made programmable
Gate array (FPGA) either other programmable logic device, discrete gate or transistor logic, discrete hardware components etc..It is logical
With processor can be microprocessor or the processor can also be any conventional processor etc..
The bus system can also include that power bus, controlling bus and status signal are total in addition to including data/address bus
Line etc..But for the sake of clear explanation, various buses are all designated as bus system in figure.
Electronic equipment 100 further includes power supply module, which provides electric power for the various assemblies of electronic equipment 100.
Power supply module may include power-supply management system, one or more power supplys and other with for electronic equipment 100 generate, management and
Distribute the associated component of electric power.
Electronic equipment 100 further includes communication component, the communication component be used for for ease of electronic equipment 100 and other equipment it
Between carry out wired or wireless way communication.The electronic equipment 100 can access the wireless network based on communication standard, such as
WiFi, 2G or 3G or 4G or 5G or combination thereof.In some embodiments, communication component comes from via broadcast channel reception
The broadcast singal or broadcast related information of external broadcasting management system.In one exemplary embodiment, the communication component is also
Including NFC module (Near Field Communication, near-field communication), to promote short range communication.For example, in NFC module
It can be based on RFID (Radio Frequency Identification, radio frequency identification) technology, IrDA (Infra-red Data
Association, Infrared Data Association) technology, UWB (Ultra Wideband, ultra wide band) technology, BT (Bluetooth, it is blue
Tooth) technology and other technologies realize.
Electronic equipment 100 further includes input module, such as power key, volume down button, and volume adds button, camera assembly with
And etc..User can activate electronic equipment 100, or the operation interface of locking electronic equipment 100, Ke Yitong by power key
It crosses volume down/plus button adjusts volume.
Electronic equipment 100 further includes user input interface, such as the user input interface can be touch sensitive surface, this is touch-sensitive
Surface can be touch-screen display, can be touch tablet.Input interface of the touch sensitive surface as user's operation, can detect use
Operation of the family on touch sensitive surface, the operation can to the click, double click, slide of touch sensitive surface, long-press, towing and etc..
The each operation of user generates certain intensity of pressure in touch sensitive surface, which can use various methods and various biographies
The combination of sensor or various sensors detects.For example, the variation of the capacitance by detecting touch sensitive surface in touch sensitive surface is big
It is small, alternatively, the variation size of the resistance of detection touch sensitive surface, alternatively, the capacitance variations size of detection touch sensitive surface and resistance become
Change size, and etc..In above process, the intensity of pressure that touch sensitive surface generates is converted to by electric signal by sensor.
Optionally, assortment of keys can also be set on 100 touch sensitive surface of electronic equipment, the input for responding user is grasped
Make.For example, can be arranged menu touch key-press, return touch key-press and etc..
Fig. 2 is that the embodiment of the present invention provides a kind of flow diagram of recording searching method.As shown in Fig. 2, recording search
Method 200 includes：
Step 021 obtains search data；
It searches for data to record for searching for, search data include text data or voice data.In some embodiments, electric
The recording application program of sub- equipment includes text input window mouth, and user is inputted word and formed with this and searched by text input window
Rope data.Alternatively, recording application program further includes voice load button, when user's long-press voice load button, electronic equipment
Voice collecting unit just acquires the voice signal that user sends out and forms search data with this.
It includes several sections of text search content T arranged according to chronological order to search for datai, i >=1, and i is positive integer,
Time point is located at the T of iiText search content is located at the T of i+1 earlier than time pointi+1Text search content, and Ti+1Text
It includes T to search for contentiText search content.For example, referring to Fig. 3, user inputted in 3 seconds voice " spend sea, it is beautiful, in vain
Cloud " search recording, 1 second T1Text search content is " spending sea ", 2 seconds T2Text search content be " spending sea, beautiful ", 3
The T of second3Text search content is " spending sea, beautiful, white clouds ".
Step 023, according to chronological order, select TiIt is default that text search content searches for similarity satisfaction in dictation library
The recording content of text of condition, dictation library include that multiple recording content of text of text data are translated by recording；
Step 025, according to search result, control the output of recording.
Therefore, text search content can be selected to segmented to scan for, so as to quickly according to chronological order
Ground searches out target recording file.
In the present embodiment, when electronic equipment is according to chronological order, the text search content at sequentially selection corresponding time point i
When being searched in dictation library, search result is divided into two classes：On the one hand, electronic equipment is according to TiText search content is in dictation library
It inside has not been able to search the recording content of text that similarity meets preset condition, on the other hand, electronic equipment is according to TiText
Search content can search the recording content of text that similarity meets preset condition in dictation library.Therefore, electronic equipment can
According to search result, to control the output of recording.
For example：Electronic equipment during the output for controlling recording, according to dichotomy, is sentenced according to search result
Disconnected TiWhether the similarity between text search content and the recording content of text of dictation library meets preset condition, if satisfied,
Statistics meets the quantity of the recording content of text of preset condition；If not meeting, judging result is exported.
In the present embodiment, preset condition can be by User Defined, for example, it is that " similarity is more than to meet preset condition
Or it is equal to 70% ", alternatively, " similarity is greater than or equal to 80% " etc..
Similarity is for describing TiEqual probabilities between text search content and the recording content of text of dictation library.One
As, it records for one whole section, which includes all kinds of expression phrases or wording, what search data input by user occurred
Although wording is included in recording, which is not necessarily the recording that user it is expected search, and but, user it is expected the record of search
Sound to this whole section recording there are similar, such as：User it is expected that the recording of search clearly includes " spending sea " this phrase, this whole section record
The practical recording substance of sound is " trumpet flower is grown in ... far from sea ... ", it is clear that in the practical recording of this whole section recording
It includes " flower " and " sea " the two wordings to hold.
Again for example：For another whole section record, it is another whole section recording practical recording substance be " ... flower piece piece
Vast sea is opened ..., is the stage ... of hawk ", the practical recording substance of another whole section of recording includes " flower " and " sea "
The two wordings, therefore, there are similarities with whole section of above-mentioned recording for another whole section of recording.
As TiSimilarity between text search content and the recording content of text of dictation library does not meet preset condition, electricity
Sub- equipment exports judging result, wherein the judging result can be by User Defined, for example, the judging result can be word
Display " temporarily nothing, which inquires, meets recording ".
As TiSimilarity between text search content and the recording content of text of dictation library meets preset condition, electronics
Device statistics meet the quantity of the recording content of text of preset condition.For example, as previously mentioned, when user it is expected search recording,
When one whole section of recording and the arbitrary similarity between the two of another whole section of recording are more than 70%, then, meet the record of preset condition
The quantity of sound content of text is 3, in real process, when prestoring multiple recording for some users, meets and presets item
The quantity of the recording content of text of part can exceed that 3.
And then, electronic equipment judges whether the quantity for the recording content of text for meeting preset condition is more than preset quantity threshold
Value.If more than judging Ti+1It is default whether the similarity between text search content and the recording content of text of dictation library meets
Condition until the quantity for meeting the recording content of text of preset condition is less than preset quantity threshold value, and exports and meets preset condition
The corresponding recording of recording content of text.In the present embodiment, although according to TiThe recording text that text search content search goes out
This content meets preset condition, and then reduces search range, but still since quantity is relatively more, and user still can not can be fast
Speed finds expectation recording, as previously mentioned, being searched for by the first round, the recording that similarity meets preset condition has 3, for example, the
T1Text search content is " spending sea ".
Then, user reduces search range again, and electronic equipment judges T againi+1The record of text search content and dictation library
Whether the similarity between sound content of text meets preset condition, if satisfied, electronic equipment judges the recording for meeting preset condition
Whether the quantity of content of text is more than preset quantity threshold value.For example, T2Text search content is " spending sea, beautiful ".If more than,
Electronic equipment judges T againi+2It is default whether the similarity between text search content and the recording content of text of dictation library meets
Condition, and so on, until the quantity for meeting the recording content of text of preset condition is less than preset quantity threshold value, and export satisfaction
The corresponding recording of recording content of text of preset condition.For example, T3Text search content is " spending sea, beautiful, white clouds ".
Again and then, if being less than, electronic equipment exports the corresponding recording of recording content of text for meeting preset condition.Its
In, preset quantity threshold value is by User Defined, for example, preset quantity threshold value can be 1 or 2 or 3 etc..
Therefore, by the above-mentioned means, by segmented searching for, electronic equipment can high efficiency rapidly search for target
Recording.
As previously mentioned, dictation library includes translating into multiple recording content of text of text data by recording, in the present embodiment
In, all recording to prestore can be converted into recording content of text by electronic equipment, and is stored in electronic equipment, so as to user
When search recording, the input of user can be quickly responded.When electronic equipment has new recording to increase every time, electronic equipment is automatically more
New dictation library.
In general, user exports " spending sea " this impressive word first, the more desirable recording found of user can
The position playback first appeared from " spending sea " avoids user from wasting the plenty of time from verbosely recording to determine herein
Whether " spending sea " is that oneself is really desired.Therefore, in some embodiments, recording content of text includes several frame recording numbers
According to.For electronic equipment during output meets the recording content of text corresponding recording of preset condition, electronic equipment is from satisfaction
Corresponding with text search content matching frame recording data is determined in the recording content of text of preset condition, with in text search
It is to play starting point, playback to hold matched corresponding frame recording data.
Therefore, electronic equipment can not only be quickly found out recording, but also specific broadcast can be quickly navigated in recording
Position is put to play out.
As previously mentioned, search data can also be converted by voice data.In some embodiments, as shown in figure 4, step
Rapid 021 includes：
Step 0211, the voice data for receiving input, voice data includes several sections of voices arranged according to chronological order；
Step 0212, according to fuzzy neural network algorithm, voice data is translated into speech text data, and by voice text
Notebook data is as search data.
In the present embodiment, first, voice data is converted into pure wave shape by electronic equipment according to fuzzy neural network algorithm
File, as shown in Figure 5.Secondly, electronic equipment carries out framing to voice signal in pure wave shape files, and it is small that voice signal is cut into one
Section is a bit of, and often a bit of is a frame, can be realized by mobile window function.Again, electronic equipment is special by extracting MFCC
Each frame waveform, is become a multi-C vector by sign processing.Finally, each multi-C vector is become speech text by electronic equipment
Data, and using speech text data as search data.
In the present embodiment, the pronunciation of word is made of phoneme, and the general directly whole initial consonants of Chinese and simple or compound vowel of a Chinese syllable are as phoneme
Frame identification is become state by collection, electronic equipment, is phoneme combinations of states, phoneme is formed word or man, with text data
Form be stored in system.
In some embodiments, the total duration of voice data input by user is often below 1 second, at this point, electronic equipment exists
When detecting that the total duration of search data is less than 1, determine that the total duration of search data is equal to 1.
In above-mentioned each embodiment, memory 11 is stored with the instruction that can be executed by least one processor 12, instruction
It is executed by least one processor 12, so that at least one processor 12 can be used in execution any one of them recording and search
Suo Fangfa.
As the another aspect of the embodiment of the present invention, the embodiment of the present invention provides a kind of recording searcher.Please refer to figure
6, recording searcher 600 include：Acquisition module 61, selecting module 62 and control module 63.
For acquisition module 61 for obtaining search data, search data include being searched according to several sections of texts that chronological order arranges
Rope content Ti, i >=1, and i is positive integer, time point is located at the T of iiText search content is located at the of i+1 earlier than time point
Ti+1Text search content, and Ti+1Text search content includes TiText search content.
Selecting module 62 is used to, according to chronological order, select TiIt is full that text search content searches for similarity in dictation library
The recording content of text of sufficient preset condition, dictation library include that multiple recording content of text of text data are translated by recording.
Control module 63 is used to, according to search result, control the output of recording.
Therefore, text search content can be selected to segmented to scan for, so as to quickly according to chronological order
Ground searches out target recording file.
Referring to Fig. 7, control module 63 includes：First judging unit 631, statistic unit 632, second judgment unit 633,
First output unit 634 and the second output unit 635.
First judging unit 631 is for judging TiPhase between text search content and the recording content of text of dictation library
Whether meet preset condition like degree；
Statistic unit 632 is used for if satisfied, statistics meets the quantity of the recording content of text of preset condition；
Whether the quantity that second judgment unit 633 is used to judge to meet the recording content of text of preset condition is more than present count
Measure threshold value；
First output unit 634 is used to judge Ti+1The recording content of text of text search content and dictation library
Between similarity whether meet preset condition, until meet preset condition recording content of text quantity be less than preset quantity
Threshold value, and the corresponding recording of recording content of text for meeting preset condition is exported, if being less than, output meets the recording of preset condition
The corresponding recording of content of text；
If the second output unit 635 exports judging result for not meeting.
In some embodiments, recording content of text includes several frame recording datas；First output unit 634 is specifically used
In：Frame recording data corresponding with text search content matching is determined from the recording content of text for meet preset condition；With institute
It is to play starting point, playback to state frame recording data corresponding with text search content matching.
In some embodiments, referring to Fig. 8, acquisition module 61 includes：Receiving unit 611 and translation unit 612.
Receiving unit 611 is used to receive the voice data of input, and the voice data includes being arranged according to chronological order
Several sections of voices；
Translation unit 612 is used to, according to fuzzy neural network algorithm, the voice data is translated into speech text data,
And using the speech text data as search data.
In some embodiments, referring to Fig. 9, recording searcher 600 further includes determining module 64.Determining module 64 is used
In when detecting that the total duration of search data is less than 1, the total duration of determining search data is equal to 1.
Since device embodiment and embodiment of the method are to be based on same design, under the premise of content does not conflict mutually, dress
The content for setting embodiment can be with quoting method embodiment, and this will not be repeated here.
Finally it should be noted that：The above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；At this
It under the thinking of invention, can also be combined between the technical characteristic in above example or different embodiment, step can be with
It is realized with random order, and there are many other variations of different aspect present invention as described above, for simplicity, they do not have
Have and is provided in details；Although the present invention is described in detail referring to the foregoing embodiments, the ordinary skill people of this field
Member should understand that：It still can be with technical scheme described in the above embodiments is modified, or to which part skill
Art feature carries out equivalent replacement；And these modifications or replacements, each reality of the application that it does not separate the essence of the corresponding technical solution
Apply the range of a technical solution.
Claims (11)
1. a kind of recording searching method, which is characterized in that including：
Search data are obtained, described search data include several sections of text search content T arranged according to chronological orderi, i >=1,
And i is positive integer, time point is located at the T of iiText search content is located at the T of i+1 earlier than time pointi+1In text search
Hold, and the Ti+1Text search content includes the TiText search content；
According to chronological order, the T is selectediText search content searches for the record that similarity meets preset condition in dictation library
Sound content of text, the dictation library include that multiple recording content of text of text data are translated by recording；
According to search result, the output of recording is controlled.
2. according to the method described in claim 1, it is characterized in that, described control the output of recording according to search result, packet
It includes：
Judge the TiIt is default whether the similarity between text search content and the recording content of text of the dictation library meets
Condition；
If satisfied, statistics meets the quantity of the recording content of text of preset condition；
Judge whether the quantity for the recording content of text for meeting preset condition is more than preset quantity threshold value；
If more than judging Ti+1It is pre- whether the similarity between text search content and the recording content of text of dictation library meets
If condition, until the quantity for meeting the recording content of text of preset condition is less than preset quantity threshold value, and exports satisfaction and preset item
The corresponding recording of recording content of text of part；
If being less than, output meets the corresponding recording of recording content of text of preset condition；
If not meeting, judging result is exported.
3. according to the method described in claim 2, it is characterized in that, the recording content of text includes several frame recording datas；
The output meets the corresponding recording of recording content of text of preset condition, including：
Frame recording data corresponding with text search content matching is determined from the recording content of text for meet preset condition；
It is to play starting point, playback with the frame recording data corresponding with text search content matching.
4. method according to any one of claims 1 to 3, which is characterized in that data are searched in the acquisition, including：
The voice data of input is received, the voice data includes several sections of voices arranged according to chronological order；
According to fuzzy neural network algorithm, the voice data is translated into speech text data, and by the speech text number
According to as search data.
5. according to the method described in claim 4, it is characterized in that, the method further includes：
When the total duration for detecting described search data is less than 1, determine that the total duration of described search data is equal to 1.
6. a kind of recording searcher, which is characterized in that including：
Acquisition module, for obtaining search data, described search data include being searched according to several sections of texts that chronological order arranges
Rope content Ti, i >=1, and i is positive integer, time point is located at the T of iiText search content is located at the of i+1 earlier than time point
Ti+1Text search content, and the Ti+1Text search content includes the TiText search content；
Selecting module, for according to chronological order, selecting the TiText search content searches for similarity satisfaction in dictation library
The recording content of text of preset condition, the dictation library include that multiple recording content of text of text data are translated by recording；
Control module, for according to search result, controlling the output of recording.
7. device according to claim 6, which is characterized in that the control module includes：
First judging unit, for judging the TiBetween text search content and the recording content of text of the dictation library
Whether similarity meets preset condition；
Statistic unit, for if satisfied, statistics meets the quantity of the recording content of text of preset condition；
Second judgment unit, for judging whether the quantity for the recording content of text for meeting preset condition is more than preset quantity threshold
Value；
First output unit is used for if more than T is judgedi+1Between text search content and the recording content of text of dictation library
Whether similarity meets preset condition, until the quantity for meeting the recording content of text of preset condition is less than preset quantity threshold value,
And the corresponding recording of recording content of text for meeting preset condition is exported, if being less than, output meets the recording text of preset condition
The corresponding recording of content；
If second output unit exports judging result for not meeting.
8. device according to claim 7, which is characterized in that the recording content of text includes several frame recording datas；
First output unit is specifically used for：It is determined and text search content from the recording content of text for meet preset condition
Matched corresponding frame recording data；It is to play starting point with the frame recording data corresponding with text search content matching, broadcasts
It plays a record.
9. according to claim 6 to 8 any one of them device, which is characterized in that the acquisition module includes：
Receiving unit, the voice data for receiving input, the voice data includes several sections arranged according to chronological order
Voice；
The voice data is translated into speech text data for according to fuzzy neural network algorithm by translation unit, and by institute
Predicate sound text data is as search data.
10. device according to claim 9, which is characterized in that described device further includes：
Determining module, for when the total duration for detecting described search data is less than 1, determining the total duration of described search data
Equal to 1.
11. a kind of electronic equipment, which is characterized in that including：
At least one processor；
And the memory being connect at least one processor communication；Wherein, the memory be stored with can by it is described extremely
The instruction that a few processor executes, described instruction is executed by least one processor, so that at least one processing
Device can be used in perform claim and require 1 to 5 any one of them recording searching method.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810191881.8A CN108287930A (en) | 2018-03-08 | 2018-03-08 | A kind of recording searching method, device and electronic equipment |
| PCT/CN2018/120238 WO2019169921A1 (en) | 2018-03-08 | 2018-12-11 | Record searching method and apparatus, and electronic device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810191881.8A CN108287930A (en) | 2018-03-08 | 2018-03-08 | A kind of recording searching method, device and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108287930A true CN108287930A (en) | 2018-07-17 |
Family
ID=62833131
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810191881.8A Pending CN108287930A (en) | 2018-03-08 | 2018-03-08 | A kind of recording searching method, device and electronic equipment |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN108287930A (en) |
| WO (1) | WO2019169921A1 (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019169921A1 (en) * | 2018-03-08 | 2019-09-12 | 珠海格力电器股份有限公司 | Record searching method and apparatus, and electronic device |
| WO2020034538A1 (en) * | 2018-08-15 | 2020-02-20 | 平安科技（深圳）有限公司 | Audio keyword quality inspection method and apparatus, computer device, and storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103838724A (en) * | 2012-11-20 | 2014-06-04 | 百度在线网络技术（北京）有限公司 | Image search method and device |
| CN104078044A (en) * | 2014-07-02 | 2014-10-01 | 深圳市中兴移动通信有限公司 | Mobile terminal and sound recording search method and device of mobile terminal |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040024751A1 (en) * | 2002-08-05 | 2004-02-05 | Petrisor Greg C. | User-prioritized search system |
| CN108287930A (en) * | 2018-03-08 | 2018-07-17 | 珠海格力电器股份有限公司 | A kind of recording searching method, device and electronic equipment |
-
2018
- 2018-03-08 CN CN201810191881.8A patent/CN108287930A/en active Pending
- 2018-12-11 WO PCT/CN2018/120238 patent/WO2019169921A1/en active Application Filing
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103838724A (en) * | 2012-11-20 | 2014-06-04 | 百度在线网络技术（北京）有限公司 | Image search method and device |
| CN104078044A (en) * | 2014-07-02 | 2014-10-01 | 深圳市中兴移动通信有限公司 | Mobile terminal and sound recording search method and device of mobile terminal |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019169921A1 (en) * | 2018-03-08 | 2019-09-12 | 珠海格力电器股份有限公司 | Record searching method and apparatus, and electronic device |
| WO2020034538A1 (en) * | 2018-08-15 | 2020-02-20 | 平安科技（深圳）有限公司 | Audio keyword quality inspection method and apparatus, computer device, and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2019169921A1 (en) | 2019-09-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10074365B2 (en) | Voice control method, mobile terminal device, and voice control system | |
| CN108432190B (en) | Response message recommendation method and equipment thereof | |
| KR101798269B1 (en) | Adaptive audio feedback system and method | |
| US9754581B2 (en) | Reminder setting method and apparatus | |
| WO2019149026A1 (en) | Method and device for generating link for application page, storage medium, and electronic apparatus | |
| CN108287918B (en) | Music playing method and device based on application page, storage medium and electronic equipment | |
| CN108363792A (en) | Link generation method, device, storage medium and the electronic equipment of five application page | |
| TW201322014A (en) | Input method for searching in circling manner and system thereof | |
| CN104331503B (en) | The method and device of information push | |
| CN107527619A (en) | The localization method and device of Voice command business | |
| CN109582882A (en) | Search result shows method, apparatus and electronic equipment | |
| CN105786976A (en) | Mobile terminal and application search method thereof | |
| CN108073606A (en) | A kind of news recommends method and apparatus, a kind of device recommended for news | |
| WO2023087934A1 (en) | Voice control method, apparatus, device, and computer storage medium | |
| CN111028828A (en) | Voice interaction method based on screen drawing, screen drawing and storage medium | |
| CN108287930A (en) | A kind of recording searching method, device and electronic equipment | |
| KR20130080713A (en) | Mobile terminal having function of voice recognition and method for providing search results thereof | |
| CN111800445B (en) | Message pushing method and device, storage medium and electronic equipment | |
| CN108447478A (en) | A kind of sound control method of terminal device, terminal device and device | |
| CN108334623A (en) | Display methods, the device and system of song | |
| JP2018537737A (en) | Cumulative search processing method and apparatus, terminal, and storage medium | |
| CN110309324A (en) | A kind of searching method and relevant apparatus | |
| CN110119461B (en) | Query information processing method and device | |
| US20220059074A1 (en) | Method for evaluating satisfaction with voice interaction, device, and storage medium | |
| CN108614830A (en) | A kind of methods of exhibiting and device of search result |
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: 20180717 |
|
| RJ01 | Rejection of invention patent application after publication |