CN108231080A - Voice method for pushing, device, smart machine and storage medium - Google Patents
Voice method for pushing, device, smart machine and storage medium Download PDFInfo
- Publication number
- CN108231080A CN108231080A CN201810010957.2A CN201810010957A CN108231080A CN 108231080 A CN108231080 A CN 108231080A CN 201810010957 A CN201810010957 A CN 201810010957A CN 108231080 A CN108231080 A CN 108231080A
- Authority
- CN
- China
- Prior art keywords
- voice
- voice messaging
- push
- alternative
- messaging
- 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
- 238000000034 method Methods 0.000 title claims abstract description 40
- 230000002452 interceptive effect Effects 0.000 claims abstract description 36
- 238000012216 screening Methods 0.000 claims abstract description 25
- 238000012163 sequencing technique Methods 0.000 claims abstract description 20
- 230000015654 memory Effects 0.000 claims description 18
- 238000012545 processing Methods 0.000 claims description 9
- 238000004519 manufacturing process Methods 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 6
- 230000011218 segmentation Effects 0.000 claims description 5
- 230000009467 reduction Effects 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 2
- 230000000694 effects Effects 0.000 abstract description 8
- 238000012546 transfer Methods 0.000 abstract description 6
- 241000287828 Gallus gallus Species 0.000 description 14
- 238000005516 engineering process Methods 0.000 description 13
- 230000006870 function Effects 0.000 description 7
- 208000025174 PANDAS Diseases 0.000 description 5
- 208000021155 Paediatric autoimmune neuropsychiatric disorders associated with streptococcal infection Diseases 0.000 description 5
- 240000004718 Panda Species 0.000 description 5
- 235000016496 Panda oleosa Nutrition 0.000 description 5
- 241000282326 Felis catus Species 0.000 description 4
- 238000004891 communication Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 230000037213 diet Effects 0.000 description 2
- 235000005911 diet Nutrition 0.000 description 2
- 239000002245 particle Substances 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 241001269238 Data Species 0.000 description 1
- 241000282323 Felidae Species 0.000 description 1
- 241001465754 Metazoa Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 241000282443 Ursidae Species 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 239000004615 ingredient Substances 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000003607 modifier Substances 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/08—Speech classification or search
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/28—Constructional details of speech recognition systems
- G10L15/30—Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/55—Push-based network services
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/08—Speech classification or search
- G10L2015/088—Word spotting
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/223—Execution procedure of a spoken command
Landscapes
- Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The invention discloses voice method for pushing, device, smart machine and storage mediums.This method includes：Text region result is obtained from interactive voice instruction by speech recognition；The corresponding Alternative voice information of the Text region result is inquired according to voice messaging matching rule；The push voice messaging for meeting ranking condition is confirmed from the Alternative voice information based on preset screening and sequencing rule；The push voice messaging is sent to the counterpart terminal of the interactive voice instruction, the push voice messaging selected for counterpart terminal broadcasting according to user speech selection instruction.The present invention passes through default screening and sequencing rule, it solves the problems, such as that push voice is not consistent with user demand, realizes for different voice demands, different voice answer-back services is provided, by judging different demand types in user semantic, and then transfer the effect of the desired content under demand type.
Description
Technical field
The present embodiments relate to internet arena technology more particularly to voice method for pushing, device, smart machine and
Storage medium.
Background technology
With the development of Internet technology, the information on internet increases with surprising rapidity.Believe in face of magnanimity
Breath, people increasingly require intelligent terminal preferentially to push oneself interested information.
Existing push technology is largely to carry out keyword retrieval for text information, can be adulterated in retrieval result wide
It accuses chain to run in front, moreover, different web pages search rule is also different, and obtained result is also different.
It is worthless that directly the ordering strategy of text search, which is indiscriminately imitated on voice, because people are to the sensitivity of word
Degree is high, and the time cost for excluding unrelated option is also very low.If the rational retrieval ordering side for voice push is not formulated
Formula can not then avoid advertisement well, also can not be personalized provide information to the user.
Invention content
The present invention provides voice method for pushing, device, smart machine and storage medium, is provided more accurately with realizing
Resource responds service.
To include in a first aspect, an embodiment of the present invention provides a kind of voice method for pushing：
Text region result is obtained from interactive voice instruction by speech recognition；
The corresponding Alternative voice information of the Text region result is inquired according to voice messaging matching rule；
The push voice for meeting ranking condition is confirmed from the Alternative voice information based on preset screening and sequencing rule
Information；
The push voice messaging is sent to the counterpart terminal of the interactive voice instruction, for the counterpart terminal
Play the push voice messaging selected according to user speech selection instruction.
Second aspect, the embodiment of the present invention additionally provide a kind of voice pusher, including：
Sound identification module obtains Text region result for passing through speech recognition from interactive voice instruction；
Alternative voice generation module, it is corresponding for inquiring the Text region result according to voice messaging matching rule
Alternative voice information；
Speech production module is pushed, is confirmed from the Alternative voice information for being based on preset screening and sequencing rule
Meet the push voice messaging of ranking condition；
Voice playing module, for the push voice messaging to be sent to the counterpart terminal of the interactive voice instruction,
The push voice messaging selected for counterpart terminal broadcasting according to user speech selection instruction：
The third aspect, the embodiment of the present invention additionally provide a kind of smart machine, including：
One or more processors；
Memory, for storing one or more programs；
Microphone, for acquiring voice messaging；
Loudspeaker, for playing voice messaging
When one or more of programs are performed by one or more of processors so that one or more of places
The method for managing the voice push that device is realized as described in embodiment is any.
Fourth aspect, the embodiment of the present invention additionally provide a kind of computer readable storage medium, are stored thereon with computer
Program, the method that the voice push as described in embodiment is any is realized when which is executed by processor.
The present invention solves the problems, such as that push voice is not consistent with user demand, realizes needle by default screening and sequencing rule
To different voice demands, different voice answer-back services is provided, by judging different demand types in user semantic, and then
Transfer the effect of the desired content under demand type.
Description of the drawings
Fig. 1 is the flow chart of a kind of voice method for pushing that the embodiment of the present invention one provides；
Fig. 2 is a kind of flow chart of voice method for pushing provided by Embodiment 2 of the present invention；
Fig. 3 is the flow chart of a kind of voice method for pushing that the embodiment of the present invention three provides；
Fig. 4 is the structure diagram of a kind of voice pusher that the embodiment of the present invention four provides；
Fig. 5 is the structure diagram of a kind of smart machine that the embodiment of the present invention five provides.
Specific embodiment
The present invention is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining the present invention rather than limitation of the invention.It also should be noted that in order to
Convenient for description, part related to the present invention rather than entire infrastructure are illustrated only in attached drawing.
Embodiment one
Fig. 1 is the flow chart of a kind of voice method for pushing that the embodiment of the present invention one provides.This method can be by a kind of language
Sound pusher performs, which can be realized, and be integrated in smart machine by way of software and/or hardware.
The present embodiment by method specifically comprise the following steps：
S110, Text region result is obtained from interactive voice instruction by speech recognition.
Wherein, speech recognition refers to automatic speech recognition (Automatic Speech Recognition, ASR) technology,
Its target is vocabulary Content Transformation in the voice by the mankind for computer-readable input, for example, button, binary coding or
Person's character string.It is different from Speaker Identification and speaker verification, the latter attempt identification or confirm send out voice speaker and
Non- vocabulary content included in it.Interactive voice instruction refers to the voice messaging that microphone receives, and is that ASR technology turns
The target of change.Text region is the result is that the result that interactive voice instruction is converted by ASR technology.Meanwhile interactive voice instruction quilt
After being converted into text information, can keyword be extracted by carry out slicing treatment.As interactive voice instruction " searches for the day of Guangzhou today
Gas is forecast " be converted into text information by ASR technology and carry out slicing treatment after, text results " search ", " extensively can be formed
State ", " today ", " ", " weather forecast ".Retain significant word after slice：" search ", " Guangzhou ", " today ", " weather
Forecast ".The significant word refers generally to the word and modal particle for having physical meaning, in Modern Chinese general sentence into
Dividing has eight kinds, i.e. subject, predicate, object, dynamic language, attribute, the adverbial modifier, complement and head, it is believed that these ingredients included
The all meaningful word of word.Certain modal particles also meaningful word, such as " " can prompt the word of question sentence
It is included into this one kind of significant word.Since the accuracy entirely retrieved, this hair can be related to the choice of significant word
Bright to be not specifically limited herein, determining the mode of significant word can develop according to technology and be continuously improved.
Specifically, the voice messaging that intelligent terminal microphone is received is converted into text information, and by the text information
Slicing treatment is carried out, retains significant word.
S120, the corresponding Alternative voice information of the Text region result is inquired according to voice messaging matching rule.
Wherein, voice messaging matching rule is preset to retaining significant word after each slice into row information
The result matched.Alternative voice information refers to all information for meeting voice messaging matching rule matched.
Specifically, retain the corresponding institute of significant word after being sliced according to the inquiry of default voice messaging matching rule
There is Alternative voice information.
S130, confirmed from the Alternative voice information based on preset screening and sequencing rule and meet pushing away for ranking condition
Sending voice information.
Wherein, screening and sequencing rule includes two steps：Screening rule and ordering rule.Screening rule refers to by one
Fixed mode filters out certain resources not being inconsistent normally in all Alternative voice information, such as bag filter contains sensitive word, has
Damage country, leader, government bodies' image resource or other resources with negative implications (such as commit suiside).Ordering rule
It is that the Alternative voice information showed after screening is ranked up, it can be carried out by searching for temperature and/or resource freshness
Sequence.Ranking condition refers to the quantity of preset voice messaging in the top, because can after being screened and being sorted
Large number of voice messaging can be still had, to these large number of voice messagings are all obtained and may be expended
Many resources.The quantity for only obtaining 5 voice messaging before ranking at this time can be set, at this time the voice messaging of ranking the 6th
Particular content is not obtained in fact, and overview content does not also generate；It is former after the new breath of voice being ranked first is pushed
The voice messaging of the ranking 2-5 come rises to 1-4 successively, and the voice messaging of ranking the 6th originally becomes ranking the 5th, this
When obtain the particular content of the information and overview content again.Push voice messaging refers to the voice after screening and sorting
Information.
Specifically, all Alternative voice information are screened and sorted, and voice messaging is put into according to ranking results
Queue, the forward voice messaging of preferential push sequence.
S140, the counterpart terminal that the push voice messaging is sent to the interactive voice instruction, for the correspondence
The push voice messaging that terminal plays are selected according to user speech selection instruction.
Wherein, the counterpart terminal of interactive voice instruction refers to intelligent terminal, which can be smart mobile phone, put down
Plate computer, intelligent sound or other it is any have microphone, loudspeaker and the smart machine that internet can be accessed, the correspondence
Terminal is not required for being provided simultaneously with receiving and sending function, i.e. the reception terminal of interactive voice instruction and interactive voice instruction
It can be two different terminals to send terminal.User speech selection instruction refers to the voice messaging that user provides terminal
The instruction judged, effective user speech selection instruction are divided into three classes：It is, no and repetition.Terminal is selected according to user speech
It selects and instructs the push voice messaging of selection i.e. according to the forward voice messaging of screening and sequencing rule compositor.
Specifically, by intelligent terminal is sent to according to the forward voice messaging of screening and sequencing rule compositor, intelligent terminal is broadcast
Put received voice messaging.
The present invention solves the problems, such as that push voice is not consistent with user demand, realizes needle by default screening and sequencing rule
To different voice demands, different voice answer-back services is provided, by judging different demand types in user semantic, and then
Transfer the effect of the desired content under demand type.
Embodiment two
Fig. 2 is a kind of flow chart of voice method for pushing provided by Embodiment 2 of the present invention.The present embodiment is in above-mentioned reality
Apply the refinement carried out on the basis of example.How the present embodiment is described in detail by preset inquiry database and network data
Obtain the process of voice messaging.It is specifically, described corresponding according to the voice messaging matching rule inquiry Text region result
Alternative voice information, including：
Text region result progress word segmentation processing is obtained at least one speech polling keyword；
Judge whether the speech polling keyword belongs to preset inquiry database；
If so, the speech polling keyword according to voice messaging matching rule from the inquiry data base querying corresponds to
Alternative voice information；Otherwise, it is corresponded to according to voice messaging matching rule from speech polling keyword described in network data query
Alternative voice information.
With reference to figure 2, specific method provided in this embodiment includes：
S210, Text region result is obtained from interactive voice instruction by speech recognition.
S220, Text region result progress word segmentation processing is obtained at least one speech polling keyword.
Wherein, Text region result refers to the text information for being converted into interactive voice instruction by ASR technology.Participle
Processing, which refers to text information being divided into, has minimum semantic participle, and the word segmentation processing can pass through common existing skill
Art is completed, and this will not be repeated here for the present embodiment.Speech polling keyword refers to the word for having minimum semanteme retained after participle.
Specifically, the voice messaging that intelligent terminal microphone is received is converted into text information, and by the text information
Slicing treatment is carried out, the participle for remaining with minimum semanteme is inquired.
S230, judge whether the speech polling keyword belongs to preset inquiry database.If belonging to, perform
S240；If being not belonging to, S250 is performed.
Wherein, key word of the inquiry is directed to for whole sentence interactive voice information, as long as there are one in interactive voice information
Word belongs to preset inquiry database, then judges that whole sentence belongs to preset inquiry database.Letter in preset inquiry database
Breath possesses higher priority, i.e., in the case of same temperature parameter and/or freshness parameter, can preferentially push preset
Inquiry database in information.There is the types of databases independently built in preset inquiry database, in types of databases
It is stored with the problem of pre-defined answer language material.In addition the database has different classification subregions also directed to identical participle,
It shows the classification that a certain participle is analyzed according to preset matching rule, obtains after classification number from corresponding category database
Recall corresponding resource.That is preserve that there are many respond resource for same participle, in database.By taking " eating chicken " as an example,
For this participle, both belong to " amusement " database, and also belong to " diet " database.
Specifically, interactive voice is instruction morphing text information and to carry out slicing treatment, judge that the word after slice is
It is no to have the word for belonging to preset inquiry database.
S240, the speech polling keyword according to voice messaging matching rule from the inquiry data base querying correspond to
Alternative voice information.
It is S250, corresponding alternative from speech polling keyword described in network data query according to voice messaging matching rule
Voice messaging.
Specifically, after receiving user demand voice, when preset inquiry database is it is impossible to meet during demand, then please
Network data is sought to obtain related data, which is sent to Yin Te by preset inquiry database by the demand data of user
Net, and by preset inquiry database reception information should be needed corresponding to demand data by network-feedback.It is preset after reception
Inquiry database can preserve the information.
S260, confirmed from the Alternative voice information based on preset screening and sequencing rule and meet pushing away for ranking condition
Sending voice information.
S270, the counterpart terminal that the push voice messaging is sent to the interactive voice instruction, for the correspondence
The push voice messaging that terminal plays are selected according to user speech selection instruction.
Exemplary description is carried out to method provided in this embodiment below：
Intelligent terminal receives an interactive voice instruction by microphone：" weather forecast for searching for Guangzhou today ".
After interactive voice instruction is converted into text information and carries out slicing treatment by ASR technology, text results can be formed and " searched
Rope ", " Guangzhou ", " today ", " ", " weather forecast ".Retain significant word after slice：" Guangzhou ", " today ", " weather
Forecast ".Judge whether the speech polling keyword belongs to preset inquiry database, judging result is " Guangzhou ", " the present
My god ", " weather forecast " it is preset inquiry database in, then preferentially from it is described inquiry data base querying described in voice look into
Ask the corresponding Alternative voice information of keyword.But find that inquiry database can not exactly match the participle simultaneously, then from net
The corresponding Alternative voice information of speech polling keyword described in network data query.It will be from inquiry database with being obtained in network data
Voice messaging screened, and the information after screening is ranked up, first information of sorting is pushed to intelligent end
End, intelligent terminal play the voice messaging by loudspeaker.
The present invention solves the problems, such as that push voice is not consistent with user demand, realizes needle by default screening and sequencing rule
To different voice demands, different voice answer-back services is provided, by judging different demand types in user semantic, and then
Transfer the effect of the desired content under demand type.
Embodiment three
Fig. 3 is the flow chart of a kind of voice method for pushing that the embodiment of the present invention three provides.The present embodiment is in above-mentioned reality
Apply the refinement carried out on the basis of example.The process that Alternative voice information is screened and sorted is described in detail in the present embodiment.
Although the present embodiment is the refinement carried out on the flow chart of embodiment one, the present embodiment can in conjunction with the embodiments two flow
Figure uses.Specifically：
It is described to confirm the push for meeting ranking condition from the Alternative voice information based on preset screening and sequencing rule
Voice messaging, including：It will delete to believe the Alternative voice with the voice messaging of filter word storehouse matching in Alternative voice information
Breath is filtered；Weight of the Alternative voice information based on temperature parameter and/or freshness parameter after filtering is ranked up；
The Alternative voice information for confirming the forward predetermined number that sorts is push voice messaging.
Each Alternative voice information includes overview voice messaging and content voice messaging；The overview voice messaging
Confirm for user and play next Alternative voice information of corresponding content voice messaging or broadcasting.
The counterpart terminal that the push voice messaging is sent to the interactive voice instruction, for the correspondence
After the push voice messaging that terminal plays are selected according to user speech selection instruction, further include：In the inquiry data
The library update push temperature parameter of voice messaging and/or freshness parameter.
Further, the update push temperature parameter of voice messaging and/or freshness parameter, including：Institute
It states inquiry database and improves the temperature parameter of the corresponding Alternative voice information of content voice messaging played and/or freshness ginseng
Number；Alternatively, the temperature parameter of the corresponding Alternative voice information of content voice messaging not played in the inquiry database reduction
And/or freshness parameter.
Specifically, with reference to figure 3, method provided in this embodiment specifically includes：
S310, Text region result is obtained from interactive voice instruction by speech recognition.
S320, the corresponding Alternative voice information of the Text region result is inquired according to voice messaging matching rule.
Specifically, the step for can be refined according to embodiment two.
S330, it will delete to believe the Alternative voice with the voice messaging of filter word storehouse matching in Alternative voice information
Breath is filtered.
It is the pre-set dictionary containing sensitive word to filter dictionary.The dictionary can in use, dynamic change,
It can increase or delete sensitive word.
Specifically, certain resources not being inconsistent normally are filtered out, such as bag filter contains by pre-set filtering dictionary
Sensitive word, damage country, leader, government bodies' image resource or other with negative implications (such as commit suiside etc.) no
Meet regulation, the resource information of morals.
S340, weight of the Alternative voice information based on temperature parameter and/or freshness parameter after filtering is arranged
Sequence.
Wherein, temperature parameter is based on the searched frequency of a certain participle, and freshness parameter is based on a certain participle
The time that the last time is searched.A kind of calculation of temperature parameter that can be for reference is provided：Pass through real-time reception user's needle
The task of speaker is handled and feedack, in the range of certain time, statistics receives feedback record, in original data
It is added on the basis of record and calculates parameter value.If a certain voice messaging is originally that temperature parameter is 500/8000 ratio,
The later voice messaging receives 1000 user feedback datas, wherein being operated by 100 positive feedbacks about the voice messaging
Record, then hot value is updated to 600/9000.Freshness parameter can also be calculated with reference to this mode.Heat is enabled when simultaneously
When spending parameter and freshness parameter as sort by, different databases is directed to, different weight settings can be designed.
50% can respectively such as be accounted for " amusement " database, temperature parameter and freshness parameter；And for " diet " database, it can be by temperature
Parameter setting is higher than freshness parameter, and if temperature parameter is 60%, freshness parameter is accounts for 40%.
Specifically, the Alternative voice information after filtering is ranked up, sort by is：Temperature parameter and/or freshness
Parameter and the weight being pre-designed for disparate databases.
S350, confirm the Alternative voice information for the forward predetermined number that sorts to push voice messaging.
Wherein, Alternative voice information includes overview voice messaging and content voice messaging, and overview voice messaging is by voice
The information that pusher generates, (may be set to the voice messaging more than 50 words or 100 words), to it when voice messaging is long
Generate overview voice messaging.Overview voice messaging confirms for user plays corresponding content voice messaging or next of broadcasting
Alternative voice information.Overview voice messaging is sent to intelligent terminal simultaneously with content voice messaging.Intelligent terminal plays overview
Voice messaging, if user's confirmation overview voice messaging, broadcasting content voice messaging, if user does not approve overview voice messaging,
Then stop broadcasting content voice messaging and play next overview voice messaging.Since user can usually carry out a certain problem
It questions closely, so the present invention provides two schemes for relevant information：Dereferenced is pushed with being associated with push.Dereferenced push refers to：
The problem of may being questioned closely for user, does not match in advance, after user's proposition problem, is looked into according to general fashion
It askes, matching, push.Association push refers to that the same information for being once sent to intelligent terminal includes two parts, and a part is push language
Message breath, a part are association voice messagings, and association voice messaging is added interior with push voice messaging using overview voice messaging
The mode for holding voice messaging preserves.Specifically, being pushed according to dereferenced, when user's inquiry, " panda is cat" after, intelligence
Energy terminal eventually receives a push voice messaging, which includes the overview voice messaging and content that panda is not cat
Voice messaging.It is pushed according to association, when user's inquiry, " panda is cat" after, intelligent terminal eventually receives several
(to greatest extent can be by user's sets itself) pushes voice messaging, and the information is in addition to including the overview voice letter that panda is not cat
Outside breath and content voice messaging, further include panda why be Ursidae, cat family include which animal etc. overview voice messaging and
Content voice messaging.
Specifically, the Alternative voice information for confirming the forward predetermined number that sorts is push voice messaging, and will push language
Message breath is sent to intelligent terminal.
S360, the counterpart terminal that the push voice messaging is sent to the interactive voice instruction, for the correspondence
The push voice messaging that terminal plays are selected according to user speech selection instruction.
S370, judge to push whether voice is user demand voice.If so, perform S380；If it is not, it then performs
S390。
Specifically, the overview voice messaging of push voice messaging that intelligent terminal broadcasting receives.Can have at this time following
Several methods for receiving user feedback：It is received when receiving or play after broadcasting.It receives and refers to after broadcasting：Intelligent terminal plays
After the profile information for pushing voice messaging, suggestion voice is sent out, such as " needs to play detailed voice messaging for you" send out and carry
Start to receive and parse through the voice messaging of user after showing voice.It receives and refers to during broadcasting：Push voice letter is played in intelligent terminal
During the profile information of breath, while receive user and send out voice messaging, if be resolved to user speech information be have it is apparent indicative
Voice then suspends broadcasting profile information, while asks whether to need detailed voice messaging.
S380, the temperature that the corresponding Alternative voice information of content voice messaging played is improved in the inquiry database
Parameter and/or freshness parameter.
Specifically, when profile information or content voice messaging obtain customer acceptance, then improve this and push voice messaging
Temperature parameter, and the freshness parameter of more this voice messaging.
S390, the heat of the corresponding Alternative voice information of content voice messaging not played in the inquiry database reduction
Spend parameter and/or freshness parameter.
Specifically, when profile information or content voice messaging do not obtain customer acceptance, then reduce this and push voice letter
The temperature parameter of breath, and the freshness parameter of more this voice messaging.It can set when a certain information is not easily accepted by a user
When, this is not chosen into the time of voice as the reference time of freshness parameter.
It is described below for the citing of the present embodiment：
By taking family of three as an example, respectively user A, B, C, intelligent terminal is intelligent sound, which is in networking shape
State.
Analysis is accustomed to by voice collecting before and user, there is basic information as shown in Table 1, wherein the first concern
To the 4th concern carried out by temperature parameter and/or freshness parameter and the weight being pre-designed for disparate databases
The data generated after statistics：
| User | First concern | Second concern | Third is paid close attention to | 4th concern |
| A | Culinary art | News | It is military | Politics |
| B | Star | Shopping | Makeups | Tourism |
| C | Game | It is military | Movement | Tourism |
Table one
When intelligent sound by microphone receives the instruction of interactive voice, " I wants to eat chicken tonight" first, by the language
Message breath is handled by ASR technology, and processing includes two parts：One) voice is converted into computer-readable input；
Two) which user difference voice messaging belongs to.Secondly, will the text information be subjected to slicing treatment, and will retain significant word
" I " " tonight " " thinking " " eating chicken ".Retrieval result has as follows：
1. how to cook chicken；
2. confidential restaurant opens for business so-and-so star recently, chicken is mainly eaten；
3. so-and-so star indulges " eating chicken " game in the recent period；
4. the video of " eating chicken " game is broadcast live in main broadcaster；
" 5. eating chicken " game is plug-in by killing；
6. so-and-so gives a discount at supermarket's chicken
For the user preference of different user, push result as shown in Table 2 can be generated：
Table two
By taking user B as an example, if its " confidential restaurant opens for business 2. so-and-so stars recently, mainly eats chicken " to push,
" 3. so-and-so stars indulge ' eating chicken ' game in the recent period ", " video of ' eating chicken ' game is broadcast live in 4. main broadcasters " provide negative evaluation, and
It is interested in " 6. so-and-so supermarket's chicken giving a discount ", the scoring of its focus " star " may be caused to reduce and the scoring of " shopping "
Increase.After adjustment, table three, the focus of identity user B are generated：
| User | First concern | Second concern | Third is paid close attention to | 4th concern |
| B | Shopping | Star | Makeups | Tourism |
Table three
After adjusting focus, if user B inputs interactive voice instruction again, " I wants to eat chicken tonight" when, obtained push
Voice messaging such as table four：
Table four
The present invention solves the problems, such as that push voice is not consistent with user demand, realizes needle by default screening and sequencing rule
To different voice demands, different voice answer-back services is provided, by judging different demand types in user semantic, and then
Transfer the effect of the desired content under demand type.
Example IV
Fig. 4 is the structure diagram of a kind of voice pusher that the embodiment of the present invention four provides.The device specifically wraps
It includes：Sound identification module 41, Alternative voice generation module 42, push speech production module 43 and voice playing module 44.Its
In：
Sound identification module 41 obtains Text region result for passing through speech recognition from interactive voice instruction；Alternatively
Speech production module 42 is believed for inquiring the corresponding Alternative voice of the Text region result according to voice messaging matching rule
Breath；Speech production module 43 is pushed, confirms satisfaction for being based on preset screening and sequencing rule from the Alternative voice information
The push voice messaging of ranking condition；Voice playing module 44 is handed over for the push voice messaging to be sent to the voice
The counterpart terminal mutually instructed, the push voice selected for counterpart terminal broadcasting according to user speech selection instruction
Information.
The present invention solves the problems, such as that push voice is not consistent with user demand, realizes needle by default screening and sequencing rule
To different voice demands, different voice answer-back services is provided, by judging different demand types in user semantic, and then
Transfer the effect of the desired content under demand type.
On the basis of above-described embodiment, further include：Alternative voice generation module 42 is specifically used for：The word is known
Other result carries out word segmentation processing and obtains at least one speech polling keyword；Judge whether the speech polling keyword belongs to
Preset inquiry database；If so, the speech polling according to voice messaging matching rule from the inquiry data base querying closes
The corresponding Alternative voice information of key word；Otherwise, it is closed according to voice messaging matching rule from speech polling described in network data query
The corresponding Alternative voice information of key word.
On the basis of above-described embodiment, further include：Push speech production module 43 is specifically used for：Alternative voice is believed
It deletes to be filtered the Alternative voice information with the voice messaging of filter word storehouse matching in breath；It will be alternative after filtering
Weight of the voice messaging based on temperature parameter and/or freshness parameter is ranked up；Confirm the standby of forward predetermined number of sorting
Voice messaging is selected as push voice messaging.Wherein, each Alternative voice information includes overview voice messaging and content voice
Information；The overview voice messaging confirms for user plays next Alternative voice of corresponding content voice messaging or broadcasting
Information.
On the basis of above-described embodiment, further include：Parameter updating device, in the inquiry database update institute
State the push temperature parameter of voice messaging and/or freshness parameter.
On the basis of above-described embodiment, further include：The parameter updating device is specifically used for：In the inquiry data
Improve the temperature parameter and/or freshness parameter of the corresponding Alternative voice information of content voice messaging played in library；Alternatively,
The temperature parameter of the corresponding Alternative voice information of content voice messaging that the inquiry database reduction does not play and/or fresh
Spend parameter.
Voice pusher provided in this embodiment can be used for performing the voice push side that any of the above-described embodiment provides
Method has corresponding function and advantageous effect.
Embodiment five
Fig. 5 is the structure diagram of a kind of smart machine that the embodiment of the present invention five provides.As shown in figure 5, the intelligence is set
It is standby to include processor 50, memory 51, communication module 52, input unit 53 and output device 54；Processor 50 in smart machine
Quantity can be one or more, in Fig. 5 by taking a processor 50 as an example；Processor 50, memory in smart machine
51st, communication module 52, input unit 53 can be connected with output device 54 by bus or other modes, with by total in Fig. 5
For line connection.
Memory 51 is used as a kind of computer readable storage medium, and journey is can perform available for storage software program, computer
Sequence and module, if the corresponding module of a kind of voice method for pushing in the present embodiment is (for example, in a kind of voice pusher
Sound identification module 41, Alternative voice generation module 42, push speech production module 43 and voice playing module 44).Processing
Device 50 is stored in software program, instruction and module in memory 51 by operation, so as to perform the various work(of smart machine
It can apply and data processing, that is, the method for realizing a kind of above-mentioned voice push.
Memory 51 can mainly include storing program area and storage data field, wherein, storing program area can store operation system
Application program needed for system, at least one function；Storage data field can be stored uses created data according to smart machine
Deng.In addition, memory 51 can include high-speed random access memory, nonvolatile memory can also be included, for example, at least
One disk memory, flush memory device or other non-volatile solid state memory parts.In some instances, memory 51 can
Further comprise that, relative to the remotely located memory of processor 50, these remote memories can pass through network connection to intelligence
It can equipment.The example of above-mentioned network includes but not limited to internet, intranet, LAN, mobile radio communication and its group
It closes.
Communication module 52 connects for being established with display screen, and realizes the data interaction with display screen.Input unit 53
Generally microphone or other numbers that can be used for receiving input or character information and generation and the user of smart machine set
It puts and the input of key signals that function control is related.Output device 54 is generally loudspeaker, may also include the equipment such as speaker, also may be used
It can be used for the device of output including other.
A kind of smart machine provided in this embodiment, the voice push side provided available for performing any of the above-described embodiment
Method has corresponding function and advantageous effect.
Embodiment six
The embodiment of the present invention six also provides a kind of storage medium for including computer executable instructions, and the computer can
When being performed by computer processor for performing a kind of method of voice push, this method includes execute instruction：
Text region result is obtained from interactive voice instruction by speech recognition；
The corresponding Alternative voice information of the Text region result is inquired according to voice messaging matching rule；
The push voice for meeting ranking condition is confirmed from the Alternative voice information based on preset screening and sequencing rule
Information；
The push voice messaging is sent to the counterpart terminal of the interactive voice instruction, for the counterpart terminal
Play the push voice messaging selected according to user speech selection instruction.
Certainly, a kind of storage medium for including computer executable instructions that the embodiment of the present invention is provided, computer
The method operation that executable instruction is not limited to the described above, can also be performed the voice that any embodiment of the present invention is provided and pushes away
Relevant operation in the method sent.
By the description above with respect to embodiment, it is apparent to those skilled in the art that, the present invention
It can be realized by software and required common hardware, naturally it is also possible to which by hardware realization, but the former is more in many cases
Good embodiment.Based on such understanding, what technical scheme of the present invention substantially in other words contributed to the prior art
Part can be embodied in the form of software product, which can be stored in computer-readable storage medium
In matter, floppy disk, read-only memory (Read-Only Memory, ROM), random access memory (Random such as computer
Access Memory, RAM), flash memory (FLASH), hard disk or CD etc., including some instructions with so that a computer is set
Standby (can be personal computer, server or the network equipment etc.) performs the method described in each embodiment of the present invention.
It is worth noting that, in the embodiment of the device of above-mentioned voice push, included each unit and module are
It is divided according to function logic, but is not limited to above-mentioned division, as long as corresponding function can be realized；Separately
Outside, the specific name of each functional unit is also only to facilitate mutually distinguish, the protection domain being not intended to restrict the invention.
Note that it above are only presently preferred embodiments of the present invention and institute's application technology principle.Those skilled in the art can manage
Solution, the present invention is not limited to specific embodiments described here, can carry out various apparent changes for a person skilled in the art
Change, readjust and substitute without departing from protection scope of the present invention.Therefore, although by above example to the present invention
It is described in further detail, but the present invention is not limited only to above example, in the situation for not departing from present inventive concept
Under, other more equivalent embodiments can also be included, and the scope of the present invention is determined by scope of the appended claims.
Claims (10)
1. a kind of voice method for pushing, which is characterized in that including：
Text region result is obtained from interactive voice instruction by speech recognition；
The corresponding Alternative voice information of the Text region result is inquired according to voice messaging matching rule；
The push voice messaging for meeting ranking condition is confirmed from the Alternative voice information based on preset screening and sequencing rule；
The push voice messaging is sent to the counterpart terminal of the interactive voice instruction, so that the counterpart terminal plays root
The push voice messaging selected according to user speech selection instruction.
2. according to the method described in claim 1, it is characterized in that, described inquire the word according to voice messaging matching rule
The corresponding Alternative voice information of recognition result, including：
Text region result progress word segmentation processing is obtained at least one speech polling keyword；
Judge whether the speech polling keyword belongs to preset inquiry database；
If so, the speech polling keyword according to voice messaging matching rule from the inquiry data base querying is corresponding alternative
Voice messaging；Otherwise, it is corresponding alternative from speech polling keyword described in network data query according to voice messaging matching rule
Voice messaging.
3. according to the method described in claim 1, it is characterized in that, it is described based on preset screening and sequencing rule from described alternative
The push voice messaging for meeting ranking condition is confirmed in voice messaging, including：
It will delete to be filtered the Alternative voice information with the voice messaging of filter word storehouse matching in Alternative voice information；
Weight of the Alternative voice information based on temperature parameter and/or freshness parameter after filtering is ranked up；
The Alternative voice information for confirming the forward predetermined number that sorts is push voice messaging.
4. according to the method described in claim 3, it is characterized in that, each Alternative voice information includes overview voice messaging
With content voice messaging；
The overview voice messaging confirms to play corresponding content voice messaging or play next Alternative voice for user and believe
Breath.
5. according to the method described in claim 4, it is characterized in that, described be sent to the voice by the push voice messaging
The counterpart terminal of interactive instruction, the push voice selected for counterpart terminal broadcasting according to user speech selection instruction
After information, further include：
In the push temperature parameter of voice messaging and/or freshness parameter described in the inquiry database update.
6. the according to the method described in claim 5, it is characterized in that, temperature parameter of the update push voice messaging
And/or freshness parameter, including：
In the temperature parameter for inquiring the corresponding Alternative voice information of content voice messaging that database raising plays and/or newly
Freshness parameter；
Alternatively, the temperature parameter of the corresponding Alternative voice information of content voice messaging not played in the inquiry database reduction
And/or freshness parameter.
7. a kind of voice pusher, which is characterized in that including：
Sound identification module obtains Text region result for passing through speech recognition from interactive voice instruction；
Alternative voice generation module, for inquiring the corresponding alternative language of the Text region result according to voice messaging matching rule
Message ceases；
Speech production module is pushed, confirms satisfaction row for being based on preset screening and sequencing rule from the Alternative voice information
The push voice messaging of name condition；
Voice playing module, for the push voice messaging to be sent to the counterpart terminal of the interactive voice instruction, for
The push voice messaging that the counterpart terminal broadcasting is selected according to user speech selection instruction.
8. device according to claim 7, which is characterized in that including：
Parameter updating device, in the push temperature parameter of voice messaging described in the inquiry database update and/or fresh
Spend parameter.
9. a kind of smart machine, which is characterized in that including：
One or more processors；
Memory, for storing one or more programs；
Microphone, for acquiring voice messaging；
Loudspeaker, for playing voice messaging
When one or more of programs are performed by one or more of processors so that one or more of processors are real
The now method of the voice push as described in claim 1-6 is any.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is by processor
The method that the voice push as described in claim 1-6 is any is realized during execution.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810010957.2A CN108231080A (en) | 2018-01-05 | 2018-01-05 | Voice method for pushing, device, smart machine and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810010957.2A CN108231080A (en) | 2018-01-05 | 2018-01-05 | Voice method for pushing, device, smart machine and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108231080A true CN108231080A (en) | 2018-06-29 |
Family
ID=62645251
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810010957.2A Pending CN108231080A (en) | 2018-01-05 | 2018-01-05 | Voice method for pushing, device, smart machine and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108231080A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108962233A (en) * | 2018-07-26 | 2018-12-07 | 苏州思必驰信息科技有限公司 | Voice dialogue processing method and system for voice dialogue platform |
| CN109087110A (en) * | 2018-08-24 | 2018-12-25 | 深圳市云之音科技有限公司 | A kind of intelligence marketing method, device and terminal device |
| CN109561130A (en) * | 2018-10-19 | 2019-04-02 | 深圳点猫科技有限公司 | A kind of cloud storage platform and application method programming works for storing teenager |
| CN109816423A (en) * | 2018-12-14 | 2019-05-28 | 深圳壹账通智能科技有限公司 | Product programming method and server based on speech recognition |
| CN113157236A (en) * | 2020-01-22 | 2021-07-23 | 阿里巴巴集团控股有限公司 | Data processing method and device, electronic equipment and computer storage medium |
| CN113421565A (en) * | 2021-07-19 | 2021-09-21 | 北京百度网讯科技有限公司 | Search method, search device, electronic equipment and storage medium |
| CN114490981A (en) * | 2022-01-21 | 2022-05-13 | 珠海格力电器股份有限公司 | Information feedback method, system, storage medium and electronic device |
| US11438313B2 (en) | 2020-05-07 | 2022-09-06 | Mastercard International Incorporated | Privacy filter for internet-of-things (IOT) devices |
| CN115544607A (en) * | 2022-12-02 | 2022-12-30 | 广东时谛智能科技有限公司 | Shoe body design method and device based on voice recognition |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101075435A (en) * | 2007-04-19 | 2007-11-21 | 深圳先进技术研究院 | Intelligent chatting system and its realizing method |
| CN101499080A (en) * | 2008-02-01 | 2009-08-05 | 网秦无限（北京）科技有限公司 | Method and system for fast acquiring information service on mobile terminal |
| CN103279508A (en) * | 2012-12-31 | 2013-09-04 | 威盛电子股份有限公司 | Method for voice response correction and natural language conversational system |
| CN103365959A (en) * | 2013-06-03 | 2013-10-23 | 深圳市爱渡飞科技有限公司 | Voice search method and voice search device |
| CN104239459A (en) * | 2014-09-02 | 2014-12-24 | 百度在线网络技术（北京）有限公司 | Voice search method, voice search device and voice search system |
| CN104462262A (en) * | 2014-11-21 | 2015-03-25 | 北京奇虎科技有限公司 | Method and device for achieving voice search and browser client side |
| CN104572717A (en) * | 2013-10-18 | 2015-04-29 | 腾讯科技（深圳）有限公司 | Information searching method and device |
| CN104636434A (en) * | 2014-12-31 | 2015-05-20 | 百度在线网络技术（北京）有限公司 | Search result processing method and device |
| CN105279259A (en) * | 2015-10-21 | 2016-01-27 | 无锡天脉聚源传媒科技有限公司 | Search result determination method and apparatus |
| CN105469787A (en) * | 2015-12-02 | 2016-04-06 | 百度在线网络技术（北京）有限公司 | Information displaying method and device |
| CN105681318A (en) * | 2016-02-03 | 2016-06-15 | 百度在线网络技术（北京）有限公司 | Information push method and device based on voice recognition of artificial intelligence |
| CN106462617A (en) * | 2014-06-30 | 2017-02-22 | 苹果公司 | Intelligent automated assistant for tv user interactions |
| CN106776872A (en) * | 2016-11-29 | 2017-05-31 | 暴风集团股份有限公司 | Defining the meaning of one's words according to voice carries out the method and system of phonetic search |
| CN107222757A (en) * | 2017-07-05 | 2017-09-29 | 深圳创维数字技术有限公司 | A kind of voice search method, set top box, storage medium, server and system |
-
2018
- 2018-01-05 CN CN201810010957.2A patent/CN108231080A/en active Pending
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101075435A (en) * | 2007-04-19 | 2007-11-21 | 深圳先进技术研究院 | Intelligent chatting system and its realizing method |
| CN101499080A (en) * | 2008-02-01 | 2009-08-05 | 网秦无限（北京）科技有限公司 | Method and system for fast acquiring information service on mobile terminal |
| CN103279508A (en) * | 2012-12-31 | 2013-09-04 | 威盛电子股份有限公司 | Method for voice response correction and natural language conversational system |
| US20140188477A1 (en) * | 2012-12-31 | 2014-07-03 | Via Technologies, Inc. | Method for correcting a speech response and natural language dialogue system |
| CN103365959A (en) * | 2013-06-03 | 2013-10-23 | 深圳市爱渡飞科技有限公司 | Voice search method and voice search device |
| CN104572717A (en) * | 2013-10-18 | 2015-04-29 | 腾讯科技（深圳）有限公司 | Information searching method and device |
| CN106462617A (en) * | 2014-06-30 | 2017-02-22 | 苹果公司 | Intelligent automated assistant for tv user interactions |
| CN104239459A (en) * | 2014-09-02 | 2014-12-24 | 百度在线网络技术（北京）有限公司 | Voice search method, voice search device and voice search system |
| CN104462262A (en) * | 2014-11-21 | 2015-03-25 | 北京奇虎科技有限公司 | Method and device for achieving voice search and browser client side |
| CN104636434A (en) * | 2014-12-31 | 2015-05-20 | 百度在线网络技术（北京）有限公司 | Search result processing method and device |
| CN105279259A (en) * | 2015-10-21 | 2016-01-27 | 无锡天脉聚源传媒科技有限公司 | Search result determination method and apparatus |
| CN105469787A (en) * | 2015-12-02 | 2016-04-06 | 百度在线网络技术（北京）有限公司 | Information displaying method and device |
| CN105681318A (en) * | 2016-02-03 | 2016-06-15 | 百度在线网络技术（北京）有限公司 | Information push method and device based on voice recognition of artificial intelligence |
| CN106776872A (en) * | 2016-11-29 | 2017-05-31 | 暴风集团股份有限公司 | Defining the meaning of one's words according to voice carries out the method and system of phonetic search |
| CN107222757A (en) * | 2017-07-05 | 2017-09-29 | 深圳创维数字技术有限公司 | A kind of voice search method, set top box, storage medium, server and system |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108962233A (en) * | 2018-07-26 | 2018-12-07 | 苏州思必驰信息科技有限公司 | Voice dialogue processing method and system for voice dialogue platform |
| CN108962233B (en) * | 2018-07-26 | 2020-11-17 | 苏州思必驰信息科技有限公司 | Voice conversation processing method and system for voice conversation platform |
| CN109087110A (en) * | 2018-08-24 | 2018-12-25 | 深圳市云之音科技有限公司 | A kind of intelligence marketing method, device and terminal device |
| CN109561130A (en) * | 2018-10-19 | 2019-04-02 | 深圳点猫科技有限公司 | A kind of cloud storage platform and application method programming works for storing teenager |
| CN109816423A (en) * | 2018-12-14 | 2019-05-28 | 深圳壹账通智能科技有限公司 | Product programming method and server based on speech recognition |
| CN113157236A (en) * | 2020-01-22 | 2021-07-23 | 阿里巴巴集团控股有限公司 | Data processing method and device, electronic equipment and computer storage medium |
| CN113157236B (en) * | 2020-01-22 | 2024-06-14 | 阿里巴巴集团控股有限公司 | Data processing method, device, electronic equipment and computer storage medium |
| US11438313B2 (en) | 2020-05-07 | 2022-09-06 | Mastercard International Incorporated | Privacy filter for internet-of-things (IOT) devices |
| CN113421565A (en) * | 2021-07-19 | 2021-09-21 | 北京百度网讯科技有限公司 | Search method, search device, electronic equipment and storage medium |
| CN114490981A (en) * | 2022-01-21 | 2022-05-13 | 珠海格力电器股份有限公司 | Information feedback method, system, storage medium and electronic device |
| CN115544607A (en) * | 2022-12-02 | 2022-12-30 | 广东时谛智能科技有限公司 | Shoe body design method and device based on voice recognition |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108231080A (en) | Voice method for pushing, device, smart machine and storage medium | |
| CN108769772B (en) | Direct broadcasting room display methods, device, equipment and storage medium | |
| CN107797984B (en) | Intelligent interaction method, equipment and storage medium | |
| CN106919702B (en) | Keyword pushing method and device based on document | |
| CN107273489B (en) | Content delivery method, electronic equipment and computer storage medium | |
| CN108733766B (en) | Data query method and device and readable medium | |
| US8843470B2 (en) | Meta classifier for query intent classification | |
| CN102929873B (en) | Method and device for extracting searching value terms based on context search | |
| US20230043174A1 (en) | Method for pushing anchor information, computer device, and storage medium | |
| CN109190017B (en) | Method and device for determining hotspot information, server and storage medium | |
| CN107885745B (en) | Song recommendation method and device | |
| CN105045875B (en) | Personalized search and device | |
| US11080323B2 (en) | Search method and apparatus | |
| WO2017097231A1 (en) | Topic processing method and device | |
| CN109902235B (en) | User preference clustering collaborative filtering recommendation algorithm based on bat optimization | |
| JP2009211697A (en) | Information distribution system and information distribution method | |
| CN106326391A (en) | Method and device for recommending multimedia resources | |
| US20130110626A1 (en) | Folksonomy Weighted Search and Advertisement Placement System and Method | |
| US20160308795A1 (en) | Method, system and apparatus for configuing a chatbot | |
| CN112597396A (en) | Search recall ranking method, system and computer readable storage medium | |
| CN113901226A (en) | Real-time live broadcast data processing method and computer storage medium | |
| CN108319646A (en) | Vehicle source searching method and device based on user's history behavior | |
| CN115470344A (en) | Video barrage and comment theme fusion method based on text clustering | |
| CN111666513A (en) | Page processing method and device, electronic equipment and readable storage medium | |
| CN111160699A (en) | Expert recommendation method and system |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20190128 Address after: 100085 East District, Second Floor, 33 Xiaoying West Road, Haidian District, Beijing Applicant after: BEIJING KINGSOFT INTERNET SECURITY SOFTWARE Co.,Ltd. Address before: 511400 Tian'an Science and Technology Industrial Building, Panyu Energy-saving Science Park, 555 North Panyu Avenue, Donghuan Street, Panyu District, Guangzhou City, Guangdong Province Applicant before: GUANGZHOU LANBO INTELLIGENT TECHNOLOGY CO.,LTD. |
|
| TA01 | Transfer of patent application right | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180629 |
|
| RJ01 | Rejection of invention patent application after publication |