CN112201251A - Interaction method and device and earphone - Google Patents
Interaction method and device and earphone Download PDFInfo
- Publication number
- CN112201251A CN112201251A CN202011063546.3A CN202011063546A CN112201251A CN 112201251 A CN112201251 A CN 112201251A CN 202011063546 A CN202011063546 A CN 202011063546A CN 112201251 A CN112201251 A CN 112201251A
- Authority
- CN
- China
- Prior art keywords
- user
- account information
- information
- voice data
- feedback information
- 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 103
- 230000003993 interaction Effects 0.000 title claims abstract description 53
- 238000001514 detection method Methods 0.000 claims description 33
- 238000004590 computer program Methods 0.000 claims description 10
- 230000002452 interceptive effect Effects 0.000 claims description 8
- 238000012550 audit Methods 0.000 abstract description 18
- 230000008569 process Effects 0.000 abstract description 8
- 238000004891 communication Methods 0.000 description 38
- 235000021156 lunch Nutrition 0.000 description 38
- 241000238017 Astacoidea Species 0.000 description 18
- 238000013474 audit trail Methods 0.000 description 18
- 235000021152 breakfast Nutrition 0.000 description 16
- 241000282472 Canis lupus familiaris Species 0.000 description 14
- 238000012545 processing Methods 0.000 description 14
- 230000006870 function Effects 0.000 description 13
- 238000004458 analytical method Methods 0.000 description 12
- 238000010586 diagram Methods 0.000 description 12
- 238000005516 engineering process Methods 0.000 description 12
- 241000251468 Actinopterygii Species 0.000 description 10
- 235000015277 pork Nutrition 0.000 description 10
- 238000012544 monitoring process Methods 0.000 description 7
- 244000291564 Allium cepa Species 0.000 description 6
- 235000012054 meals Nutrition 0.000 description 6
- 230000003287 optical effect Effects 0.000 description 5
- 235000013311 vegetables Nutrition 0.000 description 5
- 230000009471 action Effects 0.000 description 4
- 235000013399 edible fruits Nutrition 0.000 description 4
- 230000005236 sound signal Effects 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 235000001270 Allium sibiricum Nutrition 0.000 description 3
- 241000272525 Anas platyrhynchos Species 0.000 description 3
- 235000013405 beer Nutrition 0.000 description 3
- 235000013305 food Nutrition 0.000 description 3
- 238000007726 management method Methods 0.000 description 3
- 235000013606 potato chips Nutrition 0.000 description 3
- 235000014101 wine Nutrition 0.000 description 3
- 241000272814 Anser sp. Species 0.000 description 2
- 206010041349 Somnolence Diseases 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 239000002537 cosmetic Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008439 repair process Effects 0.000 description 2
- 235000011888 snacks Nutrition 0.000 description 2
- 230000002618 waking effect Effects 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 244000257727 Allium fistulosum Species 0.000 description 1
- 235000008553 Allium fistulosum Nutrition 0.000 description 1
- 241001526681 Alonsoa meridionalis Species 0.000 description 1
- 244000061176 Nicotiana tabacum Species 0.000 description 1
- 235000002637 Nicotiana tabacum Nutrition 0.000 description 1
- 241000282376 Panthera tigris Species 0.000 description 1
- 241000590419 Polygonia interrogationis Species 0.000 description 1
- 244000269722 Thea sinensis Species 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000003796 beauty Effects 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000011982 device technology Methods 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- -1 electricity Substances 0.000 description 1
- 230000001815 facial effect Effects 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 235000021163 supper Nutrition 0.000 description 1
- 235000013616 tea Nutrition 0.000 description 1
Images
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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/12—Accounting
- G06Q40/125—Finance or payroll
-
- 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
- H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
- H04R1/00—Details of transducers, loudspeakers or microphones
- H04R1/10—Earpieces; Attachments therefor ; Earphones; Monophonic headphones
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computational Linguistics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Human Computer Interaction (AREA)
- Artificial Intelligence (AREA)
- Finance (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Accounting & Taxation (AREA)
- General Engineering & Computer Science (AREA)
- Acoustics & Sound (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Multimedia (AREA)
- Databases & Information Systems (AREA)
- Signal Processing (AREA)
- General Health & Medical Sciences (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention provides an interaction method, an interaction device and an earphone, wherein the method comprises the following steps: acquiring user voice data; acquiring account information according to the user voice data; and acquiring feedback information according to the account information, and outputting according to the feedback information. The embodiment of the invention can finish the accounting or checking without the user operating the earphone by hand, and can feed back to the user based on the account information. In the case that the user is inconvenient to operate by hand, the user's billing or audit requirements can be satisfied and the user can be made to perceive feedback. For example, the user can speak the content to be billed at any time when riding, the earphone can complete billing in the riding process, and the user does not need to stop to take out the mobile phone for billing.
Description
Technical Field
The present invention relates to the field of electronic device technologies, and in particular, to an interaction method, an interaction apparatus, and an earphone.
Background
Along with the development of economy and the Internet, the financial consciousness of people is gradually enhanced, more and more people have billing requirements, and more billing software appears on the market based on the requirements.
Currently, users usually use accounting software on electronic devices to perform accounting, but in some scenarios, there are still some limitations on the operation of electronic devices, which are not favorable for users to operate electronic devices. For example, in driving a car, riding, running, etc., it is inconvenient for a user to operate a handheld electronic device.
Disclosure of Invention
In view of the above, embodiments of the present invention are proposed in order to provide an interaction method, an interaction device and a headset that overcome or at least partly solve the above-mentioned problems.
In order to solve the above problem, an embodiment of the present invention discloses an interaction method, which is applied to an earphone, and the method includes:
acquiring user voice data;
acquiring account information according to the user voice data;
and acquiring feedback information according to the account information, and outputting according to the feedback information.
Optionally, the obtaining account information according to the user voice data includes:
carrying out voice recognition on the user voice data to obtain a recognition text;
performing sentence detection on the identification text to obtain at least one sentence;
identifying a user intention corresponding to the at least one statement and determining the statement corresponding to the billing intention;
account information is identified from the statement corresponding to the billing intent.
Optionally, the obtaining feedback information according to the account information includes:
and generating feedback information according to the accounting intention and the account information.
Optionally, the account information includes transaction information and/or amount information.
Optionally, the generating feedback information according to the accounting intention and the account information includes:
and generating feedback information according to a preset expression style, the accounting intention and the account information.
Optionally, the generating feedback information according to the accounting intention and the account information includes:
and generating feedback information according to preset character characteristic information, the bookkeeping intention and the account information.
Optionally, the obtaining account information according to the user voice data includes:
carrying out voice recognition on the user voice data to obtain a recognition text;
performing sentence detection on the identification text to obtain at least one sentence;
recognizing a user intention corresponding to the at least one statement, and determining the statement corresponding to the checking intention;
and searching account information according to the statement corresponding to the account checking intention.
Optionally, the obtaining feedback information according to the account information includes:
and generating feedback information according to the checking intention and the account information.
Optionally, the account information includes transaction information and/or amount information.
Optionally, the generating feedback information according to the checking intention and the account information includes:
and generating feedback information according to a preset expression style, the checking intention and the account information.
Optionally, the generating feedback information according to the checking intention and the account information includes:
and generating feedback information according to preset character characteristic information, the checking intention and the account information.
Optionally, the obtaining account information according to the user voice data includes:
and acquiring account information locally on the earphone according to the user voice data.
Optionally, the headset is in communication with a server; the acquiring of account information according to the user voice data includes:
sending the user voice data to the server so that the server can acquire account information according to the user voice data;
the obtaining feedback information according to the account information includes:
and receiving feedback information generated by the server according to the account information.
Optionally, the headset is in communication with a headset receiving device, the headset receiving device being in communication with a server; the acquiring of account information according to the user voice data includes:
sending the user voice data to the earphone accommodating device so that the earphone accommodating device sends the user voice data to the server, and acquiring account information through the server according to the user voice data; or enabling the earphone accommodating device to perform voice recognition on the user voice data to obtain a voice recognition result, and acquiring account information through the server according to the voice recognition result;
the obtaining feedback information according to the account information includes:
and receiving feedback information sent by the earphone accommodating device, wherein the feedback information is generated by the server according to the account information.
Optionally, the headset is in communication with a headset receiving device; the acquiring of account information according to the user voice data includes:
sending the user voice data to the earphone accommodating device so that the earphone accommodating device can acquire account information according to the user voice data;
the obtaining feedback information according to the account information includes:
and receiving feedback information generated by the earphone accommodating device according to the account information.
Optionally, the headset has a voice assistant to which the interactive method is applied.
Optionally, before the acquiring the user voice data, the method further includes:
and responding to the touch operation acting on the preset touch area of the earphone, and awakening by the voice assistant.
Optionally, before the voice assistant acquires the user voice data, the method further includes:
the voice assistant monitors user voice data;
and when detecting that the voice data of the user contains a preset awakening word, the voice assistant awakens.
The embodiment of the invention discloses an interaction device, which is applied to an earphone, and comprises:
the user voice data acquisition module is used for acquiring user voice data;
the account information acquisition module is used for acquiring account information according to the user voice data;
and the feedback module is used for acquiring feedback information according to the account information and outputting the feedback information.
Optionally, the account information obtaining module includes:
the first recognition text obtaining submodule is used for carrying out voice recognition on the user voice data to obtain a recognition text;
the first sentence obtaining submodule is used for carrying out sentence detection on the identification text to obtain at least one sentence;
the first statement determination submodule is used for identifying the user intention corresponding to the at least one statement and determining the statement corresponding to the accounting intention;
and the first account information identification submodule is used for identifying the account information from the statement corresponding to the accounting intention.
Optionally, the feedback module comprises:
and the first feedback information generation submodule is used for generating feedback information according to the accounting intention and the account information.
Optionally, the account information includes transaction information and/or amount information.
Optionally, the first feedback information generation sub-module includes:
and the first feedback information generating unit is used for generating feedback information according to a preset expression style, the accounting intention and the account information.
Optionally, the first feedback information generation sub-module includes:
and the second feedback information generating unit is used for generating feedback information according to preset character characteristic information, the accounting intention and the account information.
Optionally, the account information obtaining module includes:
the second recognition text obtaining submodule is used for carrying out voice recognition on the user voice data to obtain a recognition text;
the second sentence obtaining submodule is used for carrying out sentence detection on the identification text to obtain at least one sentence;
the second statement determination submodule is used for identifying the user intention corresponding to the at least one statement and determining the statement corresponding to the checking intention;
and the second account information identification submodule is used for searching the account information according to the statement corresponding to the account checking intention.
Optionally, the feedback module comprises:
and the second feedback information generation submodule is used for generating feedback information according to the checking intention and the account information.
Optionally, the account information includes transaction information and/or amount information.
Optionally, the second feedback information generation sub-module includes:
and the third feedback information generating unit is used for generating feedback information according to a preset expression style, the checking intention and the account information.
Optionally, the second feedback information generation sub-module includes:
and the fourth feedback information generating unit is used for generating feedback information according to preset character characteristic information, the checking intention and the account information.
Optionally, the account information obtaining module includes:
and the local acquisition submodule is used for acquiring account information locally on the earphone according to the user voice data.
Optionally, the headset is in communication with a server; the account information acquisition module comprises:
the first sending submodule is used for sending the user voice data to the server so that the server can obtain account information according to the user voice data;
the feedback module includes:
and the first receiving submodule is used for receiving feedback information generated by the server according to the account information.
Optionally, the headset is in communication with a headset receiving device, the headset receiving device being in communication with a server; the account information acquisition module comprises:
the second sending submodule is used for sending the user voice data to the earphone accommodating device so that the earphone accommodating device sends the user voice data to the server, and account information is obtained through the server according to the user voice data; or enabling the earphone accommodating device to perform voice recognition on the user voice data to obtain a voice recognition result, and acquiring account information through the server according to the voice recognition result;
the feedback module includes:
and the second receiving submodule is used for receiving feedback information sent by the earphone accommodating device, and the feedback information is generated by the server according to the account information.
Optionally, the headset is in communication with a headset receiving device; the account information acquisition module comprises:
the third sending submodule is used for sending the user voice data to the earphone accommodating device so that the earphone accommodating device can obtain account information according to the user voice data;
the feedback module includes:
and the third receiving submodule is used for receiving feedback information generated by the earphone accommodating device according to the account information.
Optionally, the headset has a voice assistant disposed on the interactive device.
Optionally, the method further comprises:
and the first awakening module is used for responding to the touch operation of a preset touch area acting on the earphone and awakening the voice assistant.
Optionally, the method further comprises:
the monitoring module is used for monitoring user voice data;
and the second awakening module is used for awakening the voice assistant when detecting that the voice data of the user contains a preset awakening word.
An embodiment of the present invention discloses a headset, comprising a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by one or more processors, the one or more programs comprising instructions for:
acquiring user voice data;
acquiring account information according to the user voice data;
and acquiring feedback information according to the account information, and outputting according to the feedback information.
Optionally, the obtaining account information according to the user voice data includes:
carrying out voice recognition on the user voice data to obtain a recognition text;
performing sentence detection on the identification text to obtain at least one sentence;
identifying a user intention corresponding to the at least one statement and determining the statement corresponding to the billing intention;
account information is identified from the statement corresponding to the billing intent.
Optionally, the obtaining feedback information according to the account information includes:
and generating feedback information according to the accounting intention and the account information.
Optionally, the account information includes transaction information and/or amount information.
Optionally, the generating feedback information according to the accounting intention and the account information includes:
and generating feedback information according to a preset expression style, the accounting intention and the account information.
Optionally, the generating feedback information according to the accounting intention and the account information includes:
and generating feedback information according to preset character characteristic information, the bookkeeping intention and the account information.
Optionally, the obtaining account information according to the user voice data includes:
carrying out voice recognition on the user voice data to obtain a recognition text;
performing sentence detection on the identification text to obtain at least one sentence;
recognizing a user intention corresponding to the at least one statement, and determining the statement corresponding to the checking intention;
and searching account information according to the statement corresponding to the account checking intention.
Optionally, the obtaining feedback information according to the account information includes:
and generating feedback information according to the checking intention and the account information.
Optionally, the account information includes transaction information and/or amount information.
Optionally, the generating feedback information according to the checking intention and the account information includes:
and generating feedback information according to a preset expression style, the checking intention and the account information.
Optionally, the generating feedback information according to the checking intention and the account information includes:
and generating feedback information according to preset character characteristic information, the checking intention and the account information.
Optionally, the obtaining account information according to the user voice data includes:
and acquiring account information locally on the earphone according to the user voice data.
Optionally, the headset is in communication with a server; the acquiring of account information according to the user voice data includes:
sending the user voice data to the server so that the server can acquire account information according to the user voice data;
the obtaining feedback information according to the account information includes:
and receiving feedback information generated by the server according to the account information.
Optionally, the headset is in communication with a headset receiving device, the headset receiving device being in communication with a server; the acquiring of account information according to the user voice data includes:
sending the user voice data to the earphone accommodating device so that the earphone accommodating device sends the user voice data to the server, and acquiring account information through the server according to the user voice data; or enabling the earphone accommodating device to perform voice recognition on the user voice data to obtain a voice recognition result, and acquiring account information through the server according to the voice recognition result;
the obtaining feedback information according to the account information includes:
and receiving feedback information sent by the earphone accommodating device, wherein the feedback information is generated by the server according to the account information.
Optionally, the headset is in communication with a headset receiving device; the acquiring of account information according to the user voice data includes:
sending the user voice data to the earphone accommodating device so that the earphone accommodating device can acquire account information according to the user voice data;
the obtaining feedback information according to the account information includes:
and receiving feedback information generated by the earphone accommodating device according to the account information.
Optionally, the one or more programs include a voice assistant.
Optionally, further comprising instructions for:
and responding to touch operation acting on a preset touch area of the earphone, and awakening the voice assistant.
Optionally, further comprising instructions for:
monitoring voice data of a user;
and when detecting that the voice data of the user contains a preset awakening word, awakening the voice assistant.
The embodiment of the invention discloses a computer readable storage medium, wherein a computer program is stored on the computer readable storage medium, and the computer program is used for realizing the steps of the interaction method when being executed by a processor.
The embodiment of the invention has the following advantages:
in the embodiment of the invention, the earphone can acquire the voice data of the user; acquiring account information according to the user voice data; and acquiring feedback information according to the account information, and outputting according to the feedback information. The user is not required to operate the headset by hand to complete the accounting or checking, and the user can be fed back based on the account information. In the case that the user is inconvenient to operate by hand, the user's billing or audit requirements can be satisfied and the user can be made to perceive feedback. For example, the user can speak the content to be billed at any time when riding, the earphone can complete billing in the riding process, and the user does not need to stop to take out the mobile phone for billing.
Drawings
FIG. 1 is a flow chart of the steps of an interaction method of an embodiment of the present invention;
FIG. 2 is a flow chart of steps of another interaction method of an embodiment of the present invention;
FIG. 3 is a flow chart of steps of another interaction method of an embodiment of the present invention;
FIG. 4 is a flow chart of steps of another interaction method of an embodiment of the present invention;
FIG. 5 is a flow chart of steps of another interaction method of an embodiment of the present invention;
FIG. 6 is a flow chart of steps of another interaction method of an embodiment of the present invention;
FIG. 7 is a flow chart of steps of another interaction method of an embodiment of the present invention;
FIG. 8 is a flow chart of steps of another interaction method of an embodiment of the present invention;
FIG. 9 is a flow chart of steps of another interaction method of an embodiment of the present invention;
FIG. 10 is a flow chart of steps of another interaction method of an embodiment of the present invention;
FIG. 11 is a flow chart of steps of another interaction method of an embodiment of the present invention;
FIG. 12 is a flow chart of steps of another interaction method of an embodiment of the present invention;
FIG. 13 is a block diagram of an interactive apparatus according to an embodiment of the present invention;
fig. 14 is a block diagram of a headset for interaction according to an exemplary embodiment.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
Referring to fig. 1, a flowchart illustrating steps of an interaction method according to an embodiment of the present invention is shown, where the method is applied to a headset, and the method may specifically include the following steps:
The earphone is a portable electronic device frequently used in daily life, and can have a playing function, a sound pickup function and a communication function. The user can listen to the song or communicate over the phone using the headset.
And step 102, acquiring account information according to the user voice data.
The headset may obtain account information from the user voice data. When the user needs to keep accounts, the headset can recognize account information which the user wants to record from the voice data of the user. When the user needs to check the account, the headset can identify from the user voice data what account information the user wants to find.
And 103, acquiring feedback information according to the account information, and outputting according to the feedback information.
The headset may interact with the user by outputting feedback information. After the accounting information is recorded, the user can be informed that the accounting is performed through feedback information. And after the account information is found, informing the user of the found account information through feedback information.
For example, a user wearing a headset speaks: "note the account, 20 yuan has been spent in lunch", the earphone can broadcast: "20-element posted". For another example, the user speaks: "how much money was spent in the week? "the headphones can play: "flower 500 yuan".
In the embodiment of the invention, the earphone can acquire the voice data of the user; acquiring account information according to the user voice data; and acquiring feedback information according to the account information, and outputting according to the feedback information. The user is not required to operate the headset by hand to complete the accounting or checking, and the user can be fed back based on the account information. In the case that the user is inconvenient to operate by hand, the user's billing or audit requirements can be satisfied and the user can be made to perceive feedback. For example, the user can speak the content to be billed at any time when riding, the earphone can complete billing in the riding process, and the user does not need to stop to take out the mobile phone for billing.
Referring to fig. 2, a flowchart illustrating steps of another interaction method according to an embodiment of the present invention is shown, where the method is applied to a headset having a voice assistant, and the method may specifically include the following steps:
at step 201, the voice assistant obtains user voice data.
In the embodiment of the invention, the headset can be provided with a voice assistant, and the voice assistant can be a program which is installed in the headset and runs independently, and can provide various interactive functions, such as an accounting function and an audit function.
The voice assistant may obtain account information from the user's voice data. When the user needs to account, the voice assistant can recognize the account information that the user wants to record from the user voice data. When the user needs to check account, the voice assistant can identify what account information the user wants to find from the user voice data.
And step 203, the voice assistant acquires feedback information according to the account information and outputs the feedback information.
The voice assistant may interact with the user by outputting feedback information. After the accounting information is recorded, the user can be informed that the accounting is performed through feedback information. And after the account information is found, informing the user of the found account information through feedback information.
For example, a user wearing a headset speaks: "note account, lunch 20 yuan", the voice assistant can play: "20-element posted". For another example, the user speaks: "how much money was spent in the week? "the voice assistant can play: "flower 500 yuan".
In the embodiment of the invention, the voice assistant of the earphone can acquire the voice data of the user; acquiring account information according to the user voice data; and acquiring feedback information according to the account information, and outputting according to the feedback information. The user is not required to operate the headset by hand to complete the accounting or checking, and the user can be fed back based on the account information. In the case that the user is inconvenient to operate by hand, the user's billing or audit requirements can be satisfied and the user can be made to perceive feedback. For example, the user can speak the content to be billed at any time when riding, and the voice assistant of the earphone can complete billing in the riding process without stopping the user to take out the mobile phone for billing.
Referring to fig. 3, a flowchart illustrating steps of another interaction method according to an embodiment of the present invention is shown, where the method is applied to a headset, and the method may specifically include the following steps:
The headset may capture user voice data.
The headset may have Speech recognition (asr) functionality. For example, the headset may be provided with a speech recognition chip, or a speech recognition program may be provided in the headset chip.
The voice recognition function of the earphone can be used for carrying out voice recognition on the voice data of the user locally on the earphone to obtain the recognized text.
And performing voice recognition on the user voice data to obtain a recognition text which is a pure text and has no punctuation marks. For example, the user speaks: "35 Yuan lunch, 15 Yuan parking and 200 Yuan shopping". The recognized text obtained by speech recognition of the utterance spoken by the user is "35 yuan for lunch and 15 yuan for shopping and 200 yuan for lunch.
If the recognition text has more contents, the analysis result obtained by directly performing semantic analysis processing on the recognition text cannot accurately reflect the meaning which the user actually wants to express, and the recognition text needs to be subjected to sentence detection to obtain a sentence, and then semantic analysis is performed according to the sentence.
Sentence detection includes sentence break detection and symbol addition. Sentence break detection is the detection of where in the recognized text a sentence break is needed. For example, by performing sentence break detection on the recognition text "35 yuan is spent on 35 yuan parking and 15 yuan shopping is spent on 200 yuan", it can be determined that a sentence break is required after "35 yuan is spent on lunch", and it can be determined that a sentence break is required after "15 yuan is spent on parking". The symbol adding is to add punctuation marks, such as commas, periods, question marks and the like, at the positions of the punctuation. For example, a comma is added after "35 yuan has been spent in lunch" and a comma is added after "15 yuan has been spent in parking". After sentence detection, three sentences are obtained, namely 35 Yuan for lunch, 15 Yuan for parking and 200 Yuan for shopping.
The headset may identify a user intent corresponding to the statement, and upon identifying that the user intent includes an accounting intent, determine the statement corresponding to the accounting intent. In embodiments of the present invention, the headset supports instructions that, in turn, can determine a plurality of statements corresponding to billing intent.
For example, the user speaks: "help me write down account, buy 20 yuan of flower that eat at a glance at noon, eat badly, do not know to buy in the morning". The earphone recognizes that four sentences are 'help me to write down accounts', '20 yuan' for ordering at noon, 'bad eating' and 'not knowing about buying in the morning' according to the voice data of the user. The headset may determine that the user has an accounting intent based on "help me make down" and that "20 dollars spent buying snack at any time at noon" corresponds to the accounting intent. Determining "bad eating", "not knowing to buy early" does not correspond to a billing intent.
In the embodiment of the present invention, the earphone may perform semantic analysis on the sentence by using a natural Language understanding (nlu) technology, so as to obtain the user intention. For example, the sentence is semantically analyzed using a semantic analysis model trained in advance.
Corresponding labels can be generated for the sentences by utilizing the natural language understanding technology, and the intentions of the user can be more accurately described according to the labels corresponding to the sentences. For example, the statement: "the 20 yuan flowers are bought at noon and eaten at will", the corresponding tag of the sentence may include: lunch, expenditure, amount.
In an embodiment of the present invention, the step of determining the sentence corresponding to the billing intention may further comprise the sub-steps of:
and a substep S11 of determining a label corresponding to the at least one sentence, and determining the sentence corresponding to the preset label as the sentence corresponding to the accounting intention.
The preset tag may be a tag related to the billing intention. For example, the preset tags associated with the billing intent may include: expenses, incomes, amounts, items, goods, etc.
For example, the user speaks: "help me to write down accounts, buy vegetables today, fish 20, pork 50, have 3 pieces of money scallion still". The sentence recognized by the headset may include: "help me write down account", "buy dish today", "fish 20", "pork 50" and also 3 pieces of chives. Wherein, the label corresponding to the 'buying today' can be time, item and expenditure; the tag corresponding to "fish 20" may be goods, amount; the label corresponding to the pork 50 can be goods and money; the label corresponding to the '3 blocks of scallion' can be goods and money.
The labels are items, expenses and money, and are preset labels related to the accounting intention. Thus, "buy vegetables today", "fish 20", "pork 50", "also 3 pieces of scallion" are all statements corresponding to the billing intention.
And/or, the substep S12, determining the sentence having the preset instruction word as the sentence corresponding to the billing intention.
The preset instruction words can be words which are configured in advance to be related to the accounting intention, and can also be instruction words obtained through training according to a semantic analysis model. Such as "check out", etc. In the above example, "help me to make down" is also a statement corresponding to the bookkeeping intent.
In this embodiment of the present invention, the interaction method may further include:
performing at least one round of conversation according to the statement corresponding to the accounting intention, and acquiring user voice data in the at least one round of conversation; identifying a statement corresponding to the billing intent from the user speech data for the at least one round of conversation.
The headset may conduct at least one dialog according to the statement corresponding to the billing intention, and the headset may issue a query to the user in the at least one dialog to guide the user to speak more billing information.
In an embodiment of the present invention, the step of performing at least one round of dialog according to the statement corresponding to the billing intention may include: and if the statement corresponding to the accounting intention does not exist in the statements corresponding to the preset labels, performing at least one round of conversation according to the statement corresponding to the accounting intention.
For example, the user speaks: "help me to make an account".
The headset may determine that the statement "help me to make a posting" corresponds to the posting intent, but that there is no tag yet present that corresponds to an income or expense, the headset may further query: "what content needs to be billed? ".
The user can say: "flower is 30".
The headset may determine that the tag corresponding to the statement "spending 30" includes a payout, an amount, but no tag corresponding to the event yet exists, the headset may further interrogate: "where 30 flowers are located? ".
The user can say: "flower in lunch".
The headset may determine that the tag corresponding to "having a lunch" is lunch, which is a branch of the event. Thus, the earphone obtains the statements of the labels corresponding to the expenditure, the money amount and the items, the earphone can stop the conversation, and the statements obtained by the conversation are booked by adopting the wheel.
In embodiments of the present invention, the headset may be billed based on different levels of billing detail, which may be divided into three levels in one example.
At the first level of detail, the headset needs to get statements corresponding to the expense or income tagged with the tag and statements corresponding to the amount of the tag to be billed. For example, the headset gets the statement "spending 20" with the label of payout and amount. The headset can get the billing information "cost 20" from the statement because the specific item is unknown and the headset can incorporate this note billing information into other cost categories.
If the sentence obtained by the earphone does not correspond to the label required by the first level of detail, the earphone can carry out at least one round of conversation to guide the user to speak the sentence which can meet the requirement.
At the second level of detail, the headset needs to be billed with statements corresponding to a tag as an expense or income, a tag as an amount, and a tag as an item. For example, the statements obtained by the headset are "spent 40" and "meal", the billing information may be "spent 40", and the headset may incorporate the billing into the classification of breakfast, lunch, and dinner. Billing information if no time information is included, the headset may default that the time for which the billing information corresponds is the current day.
If the sentence obtained by the earphone does not correspond to the label required by the second level of detail, the earphone can carry out at least one round of conversation to guide the user to speak the sentence which can meet the requirement.
At the third level of detail, the headset needs to obtain the statement corresponding to the tag being an expense or income, the statement corresponding to the tag being an amount, the statement corresponding to the tag being an item, and the statement corresponding to the tag being a time, so that the headset can perform billing. For example, the sentence obtained by the headset is "yesterday spent 40" and "eat", the billing information may be "yesterday spent 40", the headset may incorporate the account into the classification of breakfast, lunch and dinner, and the time corresponding to the billing information is yesterday.
If the sentence obtained by the earphone does not correspond to the label required by the third level of detail, the earphone can carry out at least one round of conversation to guide the user to speak the sentence which can meet the requirement.
The above examples describe how the headset performs at least one dialog according to the billing detail level, and in practice, the headset may perform at least one dialog according to other requirement settings, which is not limited by the embodiment of the present invention.
For example, the headset may recognize billing information from the statement "buy 20 dollars spent on click at random": "bought", "flower", "20".
In an embodiment of the present invention, the step of identifying billing information from the sentence corresponding to the billing intention may comprise the sub-steps of:
and a substep S21 of determining text information corresponding to the preset tag from the sentence corresponding to the preset tag.
And a substep S22, determining the text information corresponding to the preset label as the accounting information.
For example, the user says "help me to make a bill, buy dishes today, fish 20, pork 50, and also 3 chives". The sentence recognized by the headset may include: "help me write down account", "buy dish today", "fish 20", "pork 50" and also 3 pieces of chives. The label corresponding to the 'buying vegetables today' can be time, items and expenses; the tag corresponding to "fish 20" may be goods, amount; the label corresponding to the pork 50 can be goods and money; the label corresponding to the '3 blocks of scallion' can be goods and money.
Determining that the label is time from 'buying vegetables today', and the corresponding text is 'today'; determining that the label is a matter, wherein the corresponding text is 'buy dish'; the corresponding text is "buy" as determined by the tag as a payout. From the text corresponding to the tag, billing information may be obtained as "buy vegetables today".
Determining that the tag is goods from the 'fish 20', and the corresponding text is 'fish'; the text corresponding to the tag is determined to be an amount of money, which is "20". From the text corresponding to the tag, billing information may be obtained as "fish 20".
Determining that the label is the goods from the 'pork 50', and the corresponding text is 'pork'; the text corresponding to the label is determined to be an amount of money, and is "50". According to the text corresponding to the label, the billing information can be obtained as the pork 50.
Determining that the label is a cargo from the '3 blocks of scallion' and a corresponding text 'scallion'; text "3" is determined corresponding to the label being the amount of money. Based on the text corresponding to the tag, accounting information may be obtained as "welsh onion 3".
In the embodiment of the present invention, the headset may further record the billing information. The earphone can directly record the accounting information after recognizing the accounting information. Or after the accounting information is identified, whether the accounting information is accurate can be confirmed to the user again, and the accounting information is recorded after the user confirms. For example, the headset may play "whether the billing information is 20 for a bought flower". The headset only records accounting information if the user replies with a confirmation.
In this embodiment of the present invention, the interaction method may further include: and modifying the recorded accounting information according to the user voice data acquired after the accounting information is recorded.
If the user feels that the previously spoken billing information is incorrect, the user may tell the headset that an adjustment is needed. For example, the user speaks: "make an account, dinner spends 30", after the earphone recorded corresponding account information, the user said: "just say wrong, dinner should be 40", the headset can adjust billing information according to the user's spoken words.
In an embodiment of the present invention, the step of recording the billing information may include: and determining the category corresponding to the accounting information, and recording the accounting information according to the category corresponding to the accounting information.
The earphone can automatically classify the accounting information without the need of the user to select the category, so that the time spent by the user for accounting can be reduced.
For example, the billing information is "lunch 50" and can be included in the category of breakfast, lunch and dinner. The billing information is "spent 40" and may be included in the category of other expenses since it is unclear where it is spent.
If the user feels that the headset does not fit into the category identified for the billing information, the user can modify the category into which the billing information is incorporated by voice.
For example, the headset incorporates the billing information "game top-up 100" into the category of leisure play, the user can say: "remember game top-up to category of electronic game". If the headset previously had the category of electronic games, the headset may incorporate the game top-up 100 "directly into the category of electronic games. If the headset does not previously have the category of the video game, the headset may set the category of the video game and then include the billing information "game top-up 100" into the category of the video game.
In the embodiment of the invention, the user can directly speak the category in which the accounting information is included, and the earphone can recognize the category specified by the user from the sentence. For example, the user says "dog search and listen to words, account is recorded, lunch takes 500 yuan, and brings in love.
In this embodiment of the present invention, the step of determining the category corresponding to the billing information may include: and determining the category corresponding to the accounting information according to the preset label corresponding to the accounting information.
For example, the billing information "lunch 20", the corresponding tag may include lunch. The billing information "lunch 20" can be included into the category of breakfast, lunch and dinner according to the label lunch.
Multiple categories may be divided by matter, and some of the categories may be further subdivided. The categories may include earphone default settings or may be set by the user through voice.
For example, categories may include two broad categories: expenditure and income.
The categories of expenses can be subdivided into:
food wine: breakfast, lunch and supper, food materials, fruits, snacks, tobacco, wine and tea.
Clothes ornament: clothes, trousers, shoes, hats, bags and cosmetics.
And (3) traffic: public transportation, taxi taking, private car fee, refueling, car repair, car insurance, highway toll, violation fine, and parking fee.
Household property: daily articles, tenants, water, electricity, gas, property management and maintenance.
Communication: fixed phone fee, mobile phone fee, Internet fee and postal fee.
And (3) leisure and entertainment: sports fitness, putrefactive party, leisure and recreation, travel vacation, pet treasure.
Study and repair: books, newspapers, magazines, training, repairing and digital equipment.
The human situation comes and goes: sending a gift to ask for guests, mourning parents, returning money, charitable donation and red and white happiness.
Medical insurance: medicine fee, health care fee, beauty fee and treatment fee.
And (4) financial insurance: bank procedures, investment loss, mortgage repayment, tax consumption, interest expenditure, compensation fine and fund subscription.
Other miscellaneous items: other expenses, unexpected losses, bad account losses.
The income categories can be subdivided into:
occupational income: payroll income, bonus income, interest income, overtime income, investment income and part-time income.
Other revenues: operation result, winning income, unexpected money, gift income and donation by parents.
And step 306, acquiring feedback information according to the account information, and outputting according to the feedback information.
The headset may interact with the user by outputting feedback information. The feedback information may include text, and the headset may generate and play speech corresponding To the text using text-To-speech (tts To speech) technology.
In this embodiment of the present invention, the step of obtaining feedback information according to the account information may include: and generating feedback information according to the accounting intention and the account information.
The earphone can generate feedback information according to the accounting intention and the account information, then the feedback information is played in a voice mode, and the user is informed of accounting through the feedback information.
For example, the user speaks: "dog searching listens to words, accounts, lunch has 20 yuan", the earphone can play: "trapped in noon? Trapped words my shoulders can be lent to you, 20-dollars posted ".
The headset may also inform the user in the feedback information about the category in which the billing information is included. For example, the headset may output: "lunch 20 Yuan is included in the morning, noon and evening meal category".
In an embodiment of the present invention, the account information may include transaction information and/or amount information. The transaction information may describe a transaction that needs to be billed or checked out, and the transaction may be divided into a plurality of categories. The amount information may describe the amount of money corresponding to the items that need to be billed or checked.
The step of generating feedback information according to the accounting intention and the account information may include: and generating feedback information according to the accounting intention, the item information and/or the amount information.
In one example, the feedback information can be generated from the event information in the event that the user is determined to have billing intent.
For example, the user speaks: "listen to words, make an account, 1200 yuan ticket" for dog search. Wherein the event information may include an air ticket. The headset can play: "do you spend 1200 yuan buying a flight ticket and want to do a natural and unrestrained? Neither call me |! "where" again to do a natural and unrestrained? Neither call me |! "is feedback information generated by the headset for the event information.
In this example, the headset may generate analytic or constructive feedback information from the event information in the event that the user is determined to have billing intent.
For example, the user speaks: the dog searching and listening is carried out, accounts are recorded, beer, spicy crayfish, duck neck and potato chips are spotted at night, and the total amount of the beer, spicy crayfish, duck neck and potato chips is 230 yuan. The item information can comprise beer, spicy crayfish, duck neck and potato chips. The headset can play: "the heat of these things is high based on my years of experience, and 230 yuan eaten," wherein "the heat of these things is high based on my years of experience," is constructive feedback information generated by the headset for the event information.
In this example, the headset may generate interesting feedback information from the event information upon determining that the user has billing intent.
For example, the user speaks: the dog searching listens to words, accounts are recorded, and 20 Yuan is spent in lunch. The headset can play: "trapped in noon? Trapped words my shoulders can be lent to you, 20-dollars posted ". Wherein "sleepy in noon? The shoulders of the sleepy words can borrow you' from the interesting feedback information generated according to the event information.
In another example, feedback information may be generated from the amount information in the event that the user is determined to have billing intent.
For example, the user speaks: 'listening to the voice of dog searching, 18 Yuan lunch'. The headset determines that the user has a monthly payment of less than 1000 dollars for the month, and the headset can play: the 18 yuan lunch has been paid into account, and the frugal lunch is a piece of property per se. Wherein the frugal property is feedback information generated by the earphone based on the money amount information.
For another example, the user speaks: "searching dog and listening to talk, buy 350 yuan facial mask flower". The headset may determine that the monthly expenditure on the cosmetic accessories exceeds 30% of the monthly expenditure. The headset can play: the ' buying mask 350 yuan has been registered, the ' flower-moon appearance, the ' wild goose, the ' mimosa-closed ' is said to be you ', wherein the ' flower-moon appearance, the ' wild goose, the ' mimosa-closed ' is said to be you ', and the ' earphone ' is feedback information generated based on the amount information.
In this example, the headset may generate analytic or constructive feedback information from the monetary information upon determining that the user has billing intent.
For example, the user speaks: "when searching dog, the buyer spends 60000 yuan". The earphone analyzes that the expense is the single highest expense, and the earphone can output: "buyer has 60000-dollars posted for a single debit, with the highest cost since history! ". For another example, the user speaks: "listen to the words when searching for a dog, massage 100 Yuan on the sole". The earphone analysis obtains the highest expenditure of the single day, and the earphone can output: "Palma massage 100 Yuan has been paid into account, the accumulated expenditure of 600 Yuan this day, and create a new record of expenditure on a single day! ".
In this example, the headset may generate interesting feedback information from the amount information upon determining that the user has billing intent. For example, the user speaks: "listen to the words, make an account, buy the fruit flower 350". The headset can recognize that buying the fruit flower 350 is a significant overhead, and the headset can output: "do you buy 350 yuan in the fruit in brother? ". For another example, the user speaks: the dog searching hears the words, accounts recording and sales are carried out in 5 ten thousand yuan. The headset recognizes a large income, and the headset may output: "the more severe and the more money can be earned, the sale is promoted to 5 ten thousand yuan already in account".
In yet another example, in the event that the user is determined to have billing intent, feedback information may be generated from the event information and the amount information.
For example, the user speaks: the crayfish with spicy crayfish flowers eating the crayfish in 700 yuan by listening to the voice of dog searching. The earphone can compare the amount of the spicy crayfish with other products. The headset can play: the 700 yuan spicy crayfish is equivalent to 8 jin of road tiger for discovering the god, and the crayfish can be further away from the luxury vehicle when eating less crayfish! ", this is feedback information that the headset generates based on the transaction information and the amount information.
In an example of the embodiment of the present invention, the step of generating feedback information according to the accounting intent and the account information may include: and generating feedback information according to a preset expression style, the accounting intention and the account information.
In the event that the user is determined to have the accounting intent, the headset may generate feedback information based on the preset expression style for the account information. The preset expression style may include: fun, humour, elegant, gentle, occupational, and the like. The expression style used by the headset may be set by the user or may be set by the headset based on user information, for example, based on a user's historical speech history.
The earphone can be provided with a sentence library, preset sentences with various expression styles can be stored in the sentence library, and the preset sentences can be generated manually or based on a machine training model. The earphone can search corresponding preset sentences from the sentence library according to the selected expression style to serve as feedback information or generate new sentences serving as feedback information based on the corresponding preset sentences in the sentence library.
In another example of the embodiment of the present invention, the step of generating feedback information according to the accounting intent and the account information may include: and generating feedback information according to preset character characteristic information, the bookkeeping intention and the account information.
In the case where it is determined that the user has the accounting intention, the headset may generate feedback information based on preset character feature information with respect to account information.
The preset character feature information may include preset character characters, character images, character appearances, character professions, and the like. The earphone can store various character models, the character models can be character models of actual characters or virtual characters, and the earphone can simulate speaking modes according to the character models. For example, the character feature information is set to the preset character appearance, and the headphone may generate the feedback information based on the feature information of the preset character appearance.
In the embodiment of the invention, the earphone can acquire the voice data of the user; carrying out voice recognition on the user voice data to obtain a recognition text; performing sentence detection on the identification text to obtain at least one sentence; identifying a user intention corresponding to the at least one statement and determining the statement corresponding to the billing intention; identifying account information from the statement corresponding to the billing intent; and outputting according to the feedback information. The embodiment of the invention can finish the accounting or checking without the user operating the earphone by hand, and can feed back to the user based on the account information. In the case that the user is inconvenient to operate by hand, the user's billing or audit requirements can be satisfied and the user can be made to perceive feedback.
Referring to fig. 4, a flowchart illustrating steps of another interaction method according to an embodiment of the present invention is shown, where the method is applied to a headset having a voice assistant, and the method may specifically include the following steps:
In the embodiment of the invention, the voice assistant can obtain the voice data of the user after waking up.
In the embodiment of the invention, the voice assistant can obtain the voice data of the user after waking up.
The manner in which the voice assistant wakes up may include: and responding to the touch operation acting on the preset touch area of the earphone, and awakening by the voice assistant. The preset touch area can be arranged on one side of the earphone, which is back to the earphone, and a user can wake up a voice assistant of the earphone by double-clicking the preset touch area.
The manner in which the voice assistant wakes up may also include: the voice assistant monitors user voice data; and when detecting that the voice data of the user contains a preset awakening word, the voice assistant awakens.
When the voice assistant monitors that the user speaks the wake-up word, the voice assistant wakes up itself. For example, the user speaks: the voice assistant monitors that the user speaks the awakening word ' listening to the dog ' to awaken the user's own voice.
After the voice assistant is awakened, if the user voice data is not acquired within a preset time period, the voice assistant may re-enter the sleep mode.
The voice assistant can perform voice recognition on the voice data of the user locally on the earphone through the voice recognition function of the earphone to obtain a recognized text.
And 403, the voice assistant performs sentence detection on the recognition text to obtain at least one sentence.
At step 404, the voice assistant identifies a user intent corresponding to the at least one statement and determines the statement corresponding to the billing intent.
The voice assistant can recognize the user intention corresponding to the statement, and when the user intention including the billing intention is recognized, the statement corresponding to the billing intention is determined. In embodiments of the present invention, the voice assistant supports instructions that, in conjunction with the utterance, may determine a plurality of statements corresponding to billing intent.
In an embodiment of the present invention, the step of determining the sentence corresponding to the billing intention may further comprise the sub-steps of:
and a substep S31, determining the label corresponding to the at least one sentence by the voice assistant, and determining the sentence corresponding to the preset label as the sentence corresponding to the accounting intention.
And/or, sub-step S32, the voice assistant determines the sentence with the preset instruction word as the sentence corresponding to the billing intention.
In this embodiment of the present invention, the interaction method may further include: the voice assistant carries out at least one round of conversation according to the statement corresponding to the accounting intention and acquires user voice data in the at least one round of conversation; the voice assistant identifies statements corresponding to the billing intent from the user voice data of the at least one round of conversation.
The voice assistant may conduct at least one round of dialog according to the statement corresponding to the billing intent, in which the voice assistant may issue a query to the user directing the user to speak more billing information.
In an embodiment of the present invention, the step of the voice assistant conducting at least one round of dialog according to the statement corresponding to the billing intention may include: and if the statement corresponding to the accounting intention does not exist in the statements corresponding to the preset tags, the voice assistant carries out at least one round of conversation according to the statement corresponding to the accounting intention.
At step 405, the voice assistant identifies account information from the statement corresponding to the billing intent.
In an embodiment of the present invention, the step of the voice assistant identifying billing information from the statement corresponding to the billing intent may comprise the sub-steps of:
and a substep S41, the voice assistant determines text information corresponding to the preset tag from the sentence corresponding to the preset tag.
And a substep S42, determining the text information corresponding to the preset label as the accounting information by the voice assistant.
In the embodiment of the present invention, the headset may further record the billing information. The earphone can directly record the accounting information after recognizing the accounting information. Or after the accounting information is identified, whether the accounting information is accurate can be confirmed to the user again, and the accounting information is recorded after the user confirms.
In this embodiment of the present invention, the interaction method may further include: and the voice assistant modifies the recorded accounting information according to the user voice data acquired after the accounting information is recorded.
In an embodiment of the present invention, the step of recording the billing information may include: and the voice assistant determines the type corresponding to the accounting information and records the accounting information according to the type corresponding to the accounting information.
The voice assistant can automatically classify the billing information without the need of the user to select the category, so that the time spent by the user for billing can be reduced.
In this embodiment of the present invention, the step of the voice assistant determining the category corresponding to the billing information may include: and the voice assistant determines the category corresponding to the accounting information according to the preset label corresponding to the accounting information.
And step 406, the voice assistant acquires feedback information according to the account information and outputs the feedback information.
The voice assistant may interact with the user by outputting feedback information.
In this embodiment of the present invention, the step of the voice assistant acquiring the feedback information according to the account information may include: and the voice assistant generates feedback information according to the accounting intention and the account information.
The voice assistant can generate feedback information according to the accounting intention and the account information, then play the feedback information in voice, and inform the user that the accounting is performed through the feedback information.
The step of the voice assistant generating feedback information according to the accounting intention and the account information may include: and the voice assistant generates feedback information according to the accounting intention, the item information and/or the amount information.
In an example of the embodiment of the present invention, the step of the voice assistant generating feedback information according to the accounting intention and the accounting information may include: and the voice assistant generates feedback information according to a preset expression style, the accounting intention and the account information.
In another example of the embodiment of the present invention, the step of the voice assistant generating feedback information according to the accounting intention and the accounting information may include: and the voice assistant generates feedback information according to preset character characteristic information, the accounting intention and the account information.
In the embodiment of the invention, the voice assistant can acquire the voice data of the user; carrying out voice recognition on the user voice data to obtain a recognition text; performing sentence detection on the identification text to obtain at least one sentence; identifying a user intention corresponding to the at least one statement and determining the statement corresponding to the billing intention; identifying account information from the statement corresponding to the billing intent; and outputting according to the feedback information. The embodiment of the invention can finish the accounting or checking without the user operating the earphone by hand, and can feed back to the user based on the account information. In the case that the user is inconvenient to operate by hand, the user's billing or audit requirements can be satisfied and the user can be made to perceive feedback.
Referring to fig. 5, a flowchart illustrating steps of another interaction method according to an embodiment of the present invention is shown, where the method is applied to a headset, and the method may specifically include the following steps:
The headset may recognize a user intention corresponding to the statement, and when it is recognized that the user intention includes an audit trail, determine the statement corresponding to the audit trail. In the embodiment of the invention, the earphone supports the instruction, and a plurality of sentences corresponding to the checking intention can be determined.
For example, the user speaks: to help me to check the account, the crayfish with the last five Zhang three spends money and wants to eat one more. The earphone can recognize three sentences, namely 'helping me to check account of the crayfish', 'how much money is spent by eating crayfish in the last friday and the third yearn', and 'one ideal sentence is eaten again' according to the voice data of the user. The earphone can determine that the user has the checking intention according to 'help me check and release account', determine that 'how much money is spent on last friday and three-piece crayfish' corresponds to the checking intention, 'who wants to eat one more' does not correspond to the checking intention.
In the embodiment of the invention, the earphone can perform semantic analysis on the sentences by using a Natural Language Understanding (NLU) technology, so as to obtain the intention of the user. For example, the sentence is semantically analyzed using a semantic analysis model trained in advance.
Corresponding labels can be generated for the sentences by utilizing the natural language understanding technology, and the intentions of the user can be more accurately described according to the labels corresponding to the sentences. For example, "how much money was spent on crayfish eaten in last friday and three," the corresponding label of the sentence may include: meals, expenses, and money amounts.
In an embodiment of the present invention, the step of determining the statement corresponding to the checking intention may include the following sub-steps:
and a substep S51, determining a label corresponding to the at least one statement, and determining the statement corresponding to the preset label as the statement corresponding to the checking intention.
The preset tag may be a tag related to the checking intention. For example, the preset tags associated with the audit intent may include: expenses, income, dollars, goods, breakfast, lunch, night falls, and the like.
For example, the user speaks: "how much was a breakfast flower after a look-up? How much the lunch was spent? How much a night flower? ". The sentence recognized by the headset may include: "look after", "how much is breakfast spent? "," how much the lunch flowers? "," how much the night flower? ". Wherein "how much was bloomed for breakfast? "corresponding tags may include breakfast, expenditure; "how much the lunch flowers? "corresponding tags may include lunch, expenditures; how much a night flower? "corresponding tags may include overnight, spending.
Wherein, breakfast, lunch, dinner and expenditure are all preset labels related to the checking intention. Thus "how much was breakfast? "," how much the lunch flowers? "," how much the night flower? "are statements that correspond to an audit trail.
And/or, in sub-step S52, determining the sentence with the preset instruction word as the sentence corresponding to the checking intention.
The preset instruction words can be words which are configured in advance to be related to the accounting intention, and can also be instruction words obtained through training according to a semantic analysis model. For example, "check account", etc.
In this embodiment of the present invention, the interaction method may further include: performing at least one round of conversation according to the statement corresponding to the account checking intention, and acquiring user voice data in the at least one round of conversation; and identifying sentences corresponding to the checking intention from the user voice data of the at least one round of conversation.
The headset may conduct at least one session in accordance with the statement corresponding to the audit trail, in which the headset may issue a query to the user, directing the user to speak more audit information.
In an embodiment of the present invention, the step of performing at least one round of dialog according to the statement corresponding to the audit trail may include: and if the statement corresponding to the account checking intention does not exist in the statements corresponding to the preset tags, performing at least one round of conversation according to the statement corresponding to the account checking intention.
For example, the user speaks: "help me check account.
The headset may determine that the statement "help me check down" corresponds to a checking intent, but that there is not yet a corresponding income or expense tag, the headset may further query: "what content needs to be queried? ".
The user speaks: "cost for the previous week".
The headset may determine that the tag corresponding to "spending last week" includes time, expense. But there is no tag corresponding to the event yet, the headset may further interrogate: "is the total cost of the last week to be queried or a certain cost? ".
The user speaks: to have a meal.
The headset may determine that the tag corresponding to "eat" is a meal, which is a branch of an event. Thus, the earphone obtains the statements corresponding to the labels of time, expense and items, the earphone can stop the conversation, and the obtained statements are checked by adopting the conversation.
And 505, searching account information according to the statement corresponding to the account checking intention.
The headset may look up account information in terms of statements corresponding to the audit trail.
For example, the user says "how much yesterday night is spent", the headset may look up the yesterday night's account information "night-time cost 200". For another example, the user speaks: to help me check out what amount of lunch in the month's morning, the headset can look for the expenses in this category of lunch in the month's morning.
In an embodiment of the present invention, the step of searching for account information according to the statement corresponding to the checking intention may include: and searching account information according to the label corresponding to the statement corresponding to the account checking intention.
For example, the user speaks: to help me to check the account, the crayfish with the last five Zhang three spends money and wants to eat one more. The sentence recognized by the headset may include: "help me check account", "five days in the upper week have spent money with three crayfish", "want to eat one more". The label corresponding to how much money was spent on eating crayfish in the last friday and zhang san can include time and events. The event may belong to a payment category, and the headset may search the recorded account information for account information corresponding to the time and the event.
The earphone may generate feedback information according to the account information, and the feedback information may include the found account information and other information. The feedback information may include text, and the headset may generate and play speech corresponding to the text using text-to-speech TTS technology.
In this embodiment of the present invention, the step of obtaining feedback information according to the account information may include: and generating feedback information according to the checking intention and the account information.
The earphone can generate feedback information according to the checking intention and the account information, then the feedback information is played in a voice mode, and the user is informed of the found account information through the feedback information.
For example, the user speaks: "how much to look up an account, total revenue this year? ". The headset can play: "Total revenue 14.7 ten thousand yuan".
In an embodiment of the present invention, the account information includes transaction information and/or amount information. The transaction information may describe a transaction that needs to be billed or checked out, and the transaction may be divided into a plurality of categories. The amount information may describe the amount of money corresponding to the items that need to be billed or checked.
The step of generating feedback information according to the checking intention and the account information may include: and generating feedback information according to the checking intention, the item information and/or the amount information.
In one example, where it is determined that the user has an audit trail, feedback information may be generated from the transaction information.
For example, the user speaks: "how much money spent in the week was spent in listening to the dog and checking accounts? ", wherein the event information includes eating. The headset can play: the 'eating of the meal in the week is 500 yuan, no breakfast is taken for two days, the breakfast is required to be eaten completely and cannot fall off later', wherein the 'eating of the breakfast is not taken for two days, the breakfast is required to be eaten completely and cannot fall off later' is feedback information generated aiming at matters.
In this example, the headset may generate analytic or constructive feedback information from the event information in the event that the user is determined to have billing intent.
In this example, the headset may generate interesting feedback information from the event information upon determining that the user has billing intent.
For example, the user speaks: "how much to look up an account, total revenue this year? ", wherein the event information may be total revenue. The headset can play: "is the total income 14.7 ten thousand yuan, is the big brother enough to flower? "wherein," 14.7 ten thousand yuan of total income "is the account information played by the earphone," is big money enough to flower? ' is interesting feedback information played by the earphone.
In another example, where it is determined that the user has an audit intent, feedback information may be generated from the amount information.
For example, the user speaks: "how much money was spent in this month? "wherein the event information may be a monthly expenditure. The headphone can determine that the monthly expenditure distance exceeds 1000 yuan, and the headphone can play: and the distance exceeding is 1000 yuan, and the month control is not wrong, wherein the distance exceeding is 1000 yuan, and the month control is not wrong feedback information generated based on the money amount information.
In this example, the headset may generate analytic or constructive feedback information from the monetary information upon determining that the user has billing intent.
For example, the user speaks: "how much money was spent on the last week after checking account? ". The headset can play: "cost 2000 for last week, 500 out of arms". Where "last week cost 2000" is the account information played by the headphones and "overburdened 500" is the analytical feedback information generated based on the amount information.
In this example, the headset may generate interesting feedback information from the amount information upon determining that the user has billing intent.
The user speaks: "the first few items that spend most money in the month when searching dogs and listening? ", the headset may play: the shopping is to cut hands, home property, food, wine and water, the cost is the most, 8000 yuan, 5500 yuan and 2000 yuan are respectively spent, the month is 2400 yuan more than the last month, the upper limit is more than 1300 yuan, and the flowers are spent again, and the mines of the Zan families are all lost. Among them, "spending so much, the mines of the host are all lost by you" is interesting feedback information generated based on the money amount information.
In yet another example, in the case where it is determined that the user has an audit trail, the feedback information may be generated from the matter information and the amount information.
In an example of the embodiment of the present invention, the step of generating feedback information according to the checking intention and the account information may include: and generating feedback information according to a preset expression style, the checking intention and the account information.
In the event that it is determined that the user has an audit trail, the headset may generate feedback information based on a preset expression style for account information.
In another example of the embodiment of the present invention, the step of generating feedback information according to the checking intention and the account information may include: and generating feedback information according to preset character characteristic information, the checking intention and the account information.
In the case where it is determined that the user has the checking intention, the headset may generate feedback information based on preset character feature information with respect to account information.
In the embodiment of the invention, the earphone can acquire the voice data of the user; carrying out voice recognition on user voice data to obtain a recognition text; performing sentence detection on the identification text to obtain at least one sentence; recognizing a user intention corresponding to at least one statement, and determining the statement corresponding to the checking intention; searching account information according to the statement corresponding to the account checking intention; and acquiring feedback information according to the account information, and outputting according to the feedback information. The embodiment of the invention can finish the accounting or checking without the user operating the earphone by hand, and can feed back to the user based on the account information. In the case that the user is inconvenient to operate by hand, the user's billing or audit requirements can be satisfied and the user can be made to perceive feedback.
Referring to fig. 6, a flowchart illustrating steps of another interaction method according to an embodiment of the present invention is shown, where the method is applied to a headset having a voice assistant, and the method may specifically include the following steps:
The voice assistant can recognize the user intention corresponding to the statement, and when the user intention including the checking intention is recognized, the statement corresponding to the checking intention is determined. In embodiments of the present invention, the voice assistant supports instructions that, in conjunction with the utterance, may determine a plurality of statements corresponding to the audit trail.
In the embodiment of the invention, the voice assistant can perform semantic analysis on the sentences by using a Natural Language Understanding (NLU) technology so as to obtain the user intention. For example, the sentence is semantically analyzed using a semantic analysis model trained in advance.
In an embodiment of the present invention, the step of determining the statement corresponding to the checking intention may include the following sub-steps:
and a substep S61, the voice assistant determines the label corresponding to the at least one sentence, and determines the sentence corresponding to the preset label as the sentence corresponding to the checking intention.
And/or, in sub-step S62, the voice assistant determines the sentence with the preset instruction word as the sentence corresponding to the checking intention.
In this embodiment of the present invention, the interaction method may further include: the voice assistant carries out at least one round of conversation according to the statement corresponding to the account checking intention and acquires user voice data in the at least one round of conversation; and identifying sentences corresponding to the checking intention from the user voice data of the at least one round of conversation.
The voice assistant may perform at least one round of dialog according to the statement corresponding to the audit trail, and the voice assistant may issue a query to the user in the at least one round of dialog, so as to guide the user to speak more audit trail information.
In an embodiment of the present invention, the step of the voice assistant performing at least one round of dialog according to the statement corresponding to the audit trail may include: and if the statement corresponding to the account checking intention does not exist in the statements corresponding to the preset tags, the voice assistant performs at least one round of conversation according to the statement corresponding to the account checking intention.
The voice assistant may look up account information according to the statement corresponding to the checking intent.
In an embodiment of the present invention, the step of the voice assistant searching for account information according to the statement corresponding to the checking intention may include: and the voice assistant searches account information according to the label corresponding to the statement corresponding to the account checking intention.
And 606, the voice assistant acquires feedback information according to the account information and outputs the feedback information.
The voice assistant may generate feedback information according to the account information, and the feedback information may include the found account information and other information. The feedback information may include text and the voice assistant may generate and play speech corresponding to the text using text-to-speech TTS techniques.
In this embodiment of the present invention, the step of the voice assistant acquiring the feedback information according to the account information may include: and the voice assistant generates feedback information according to the checking intention and the account information.
The voice assistant can generate feedback information according to the checking intention and the account information, then voice plays the feedback information, and informs the user of the found account information through the feedback information.
In an embodiment of the present invention, the account information includes transaction information and/or amount information.
The step of the voice assistant generating feedback information according to the checking intention and the account information may include: and the voice assistant generates feedback information according to the checking intention, the item information and/or the amount information.
In one example, the voice assistant may generate feedback information from the transaction information in the event that the user is determined to have an audit trail. In this example, the voice assistant may generate analytic or constructive feedback information from the event information in the event that the user is determined to have billing intent. In this example, the voice assistant may generate interesting feedback information from the event information upon determining that the user has billing intent.
In another example, the voice assistant may generate feedback information based on the amount information in the event that the user is determined to have an audit trail. In this example, the voice assistant may generate analytic or constructive feedback information from the amount information in the event that the user is determined to have billing intent. In this example, the voice assistant may generate interesting feedback information from the amount information upon determining that the user has billing intent.
In yet another example, the voice assistant may generate feedback information from the transaction information and the amount information in the event that the user is determined to have an audit trail.
In an example of the embodiment of the present invention, the step of the voice assistant generating feedback information according to the checking intention and the account information may include: and the voice assistant generates feedback information according to a preset expression style, the checking intention and the account information.
In the event that the user is determined to have an accounting intent, the voice assistant may generate feedback information based on a preset expression style for the account information.
In another example of the embodiment of the present invention, the step of the voice assistant generating feedback information according to the checking intention and the account information may include: and the voice assistant generates feedback information according to preset character characteristic information, the checking intention and the account information.
In the case that the user is determined to have the checking intention, the voice assistant may generate feedback information based on preset character feature information for account information.
In the embodiment of the invention, the voice assistant of the earphone can acquire the voice data of the user; carrying out voice recognition on user voice data to obtain a recognition text; performing sentence detection on the identification text to obtain at least one sentence; recognizing a user intention corresponding to at least one statement, and determining the statement corresponding to the checking intention; searching account information according to the statement corresponding to the account checking intention; and acquiring feedback information according to the account information, and outputting according to the feedback information. The embodiment of the invention can finish the accounting or checking without the user operating the earphone by hand, and can feed back to the user based on the account information. In the case that the user is inconvenient to operate by hand, the user's billing or audit requirements can be satisfied and the user can be made to perceive feedback.
Referring to fig. 7, a flow chart of steps of another interactive method of an embodiment of the present invention is shown, the method being applied to a headset, the headset communicating with a server; the method may specifically comprise the steps of:
The headset may capture user voice data.
The headset may send the user voice data to the server to enable the server to obtain account information from the user voice data.
In the embodiment of the invention, the server can perform voice recognition on the user voice data to obtain a recognition text; performing sentence detection on the identification text to obtain at least one sentence; identifying a user intention corresponding to the at least one statement and determining the statement corresponding to the billing intention; account information is identified from the statement corresponding to the billing intent.
The step of the server obtaining the feedback information according to the account information may include: and the server generates feedback information according to the accounting intention and the account information.
The account information comprises item information and/or amount information; the step of generating, by the server, feedback information according to the accounting intention and the account information may include: and the server generates feedback information according to the accounting intention, the item information and/or the amount information.
In one example, the step of generating, by the server, feedback information from the accounting intent and the account information may include: and the server generates feedback information according to a preset expression style, the accounting intention and the account information.
In another example, the step of generating, by the server, feedback information according to the billing intention, the event information and/or the amount information may include: and the server generates feedback information according to preset character characteristic information, the accounting intention and the account information.
In the embodiment of the invention, the server can perform voice recognition on the user voice data to obtain a recognition text; performing sentence detection on the identification text to obtain at least one sentence; recognizing a user intention corresponding to the at least one statement, and determining the statement corresponding to the checking intention; and searching account information according to the statement corresponding to the account checking intention.
The step of the server obtaining the feedback information according to the account information may include: and the server generates feedback information according to the checking intention and the account information.
The step of generating, by the server, feedback information according to the checking intention and the account information may include: and the server generates feedback information according to the checking intention, the item information and/or the amount information.
In one example, the step of generating, by the server, feedback information according to the checking intention and the account information may include: and the server generates feedback information according to a preset expression style, the checking intention and the account information.
In another example, the step of generating, by the server, feedback information according to the checking intention and the account information may include: and the server generates feedback information according to preset character characteristic information, the checking intention and the account information.
The server can generate feedback information after acquiring the account information and send the feedback information to the headset.
In the embodiment of the invention, the earphone can acquire the voice data of the user; sending the user voice data to a server so that the server can acquire account information according to the user voice data; receiving feedback information generated by the server according to the account information; and outputting according to the feedback information. The user is not required to operate the headset by hand to complete the accounting or checking, and the user can be fed back based on the account information. In the case that the user is inconvenient to operate by hand, the user's billing or audit requirements can be satisfied and the user can be made to perceive feedback.
Referring to fig. 8, a flowchart illustrating steps of another interaction method according to an embodiment of the present invention is shown, where the method is applied to a headset, where the headset communicates with a server, and the headset has a voice assistant, and the method may specifically include the following steps:
The voice assistant may obtain user voice data.
The voice assistant may send the user voice data to the server, so that the server obtains account information according to the user voice data.
The server can generate feedback information after acquiring the account information and send the feedback information to the earphone, and the voice assistant can receive the feedback information.
And step 804, the voice assistant outputs according to the feedback information.
In the embodiment of the invention, the voice assistant can acquire the voice data of the user; sending the user voice data to the server so that the server can acquire account information according to the user voice data; receiving feedback information generated by the server according to the account information; and outputting according to the feedback information. The user is not required to operate the headset by hand to complete the accounting or checking, and the user can be fed back based on the account information. In the case that the user is inconvenient to operate by hand, the user's billing or audit requirements can be satisfied and the user can be made to perceive feedback.
Referring to fig. 9, a flow chart of steps of another interaction method of an embodiment of the present invention is shown, the method being applied to a headset, the headset being in communication with a headset receiving device, the headset receiving device being in communication with a server; the method may specifically comprise the steps of:
The headset may capture user voice data.
A headset storage device is a device that is used in conjunction with a headset, and is generally used to store and charge a wireless headset. In the embodiment of the invention, the earphone accommodating device has a networking function, so that the earphone accommodating device can communicate with the server.
In one example, the headset may send the voice data to the headset receiving device, so that the headset receiving device sends the user voice data to the server, and the server obtains the account information according to the user voice data.
In another example, the headset may send the voice data to the headset receiving device, so that the headset receiving device performs voice recognition on the user voice data to obtain a voice recognition result, and obtains the account information according to the voice recognition result through the server.
After the server acquires the account information, feedback information can be generated according to the account information, and then the feedback information is sent to the earphone storage device, and the earphone storage device can send the feedback information to the earphone.
The manner in which the server obtains the account information and generates the feedback information according to the account information may be referred to in the above embodiments, and details are not described herein.
And 904, outputting according to the feedback information.
In the embodiment of the invention, the earphone can acquire the voice data of the user; sending user voice data to the earphone receiving device so that the earphone receiving device sends the user voice data to the server, and obtaining account information through the server according to the user voice data; or, the earphone receiving device performs voice recognition on the user voice data to obtain a voice recognition result, and the server acquires account information according to the voice recognition result; the earphone can receive feedback information sent by the earphone containing device, and the feedback information is generated by the server according to the account information; the earphone can output according to the feedback information. The embodiment of the invention can finish the accounting or checking without the user operating the earphone by hand, and can feed back to the user based on the account information. In the case that the user is inconvenient to operate by hand, the user's billing or audit requirements can be satisfied and the user can be made to perceive feedback.
Referring to fig. 10, a flow chart of steps of another interaction method of an embodiment of the present invention is shown, the method being applied to a headset, the headset being in communication with a headset receiving device, the headset receiving device being in communication with a server, the headset having a voice assistant; the method may specifically comprise the steps of:
at step 1001, the voice assistant obtains user voice data.
The voice assistant can acquire the voice data of the user
In one example, the voice assistant may send the voice data to the headset receiving device, so that the headset receiving device sends the user voice data to the server, and the server obtains the account information according to the user voice data.
In another example, the voice assistant may send the voice data to the headset receiving device, so that the headset receiving device performs voice recognition on the user voice data to obtain a voice recognition result, and the server obtains the account information according to the voice recognition result.
After the server acquires the account information, feedback information can be generated according to the account information, and then the feedback information is sent to the earphone storage device, and the earphone storage device can send the feedback information to the earphone.
The manner in which the server obtains the account information and generates the feedback information according to the account information may be referred to in the above embodiments, and details are not described herein.
In the embodiment of the invention, the voice assistant of the earphone can acquire the voice data of the user; sending user voice data to the earphone receiving device so that the earphone receiving device sends the user voice data to the server, and obtaining account information through the server according to the user voice data; or, the earphone receiving device performs voice recognition on the user voice data to obtain a voice recognition result, and the server acquires account information according to the voice recognition result; the voice assistant can receive feedback information sent by the earphone containing device, and the feedback information is generated by the server according to the account information; the voice assistant may output based on the feedback information. The embodiment of the invention can finish the accounting or checking without the user operating the earphone by hand, and can feed back to the user based on the account information. In the case that the user is inconvenient to operate by hand, the user's billing or audit requirements can be satisfied and the user can be made to perceive feedback.
Referring to fig. 11, a flow chart of steps of another interactive method of an embodiment of the present invention is shown, the method being applied to a headset, the headset being in communication with a headset receiving device; the method may specifically comprise the steps of:
The headset may capture user voice data.
The headset can send the user voice data to the headset receiving device, so that the headset receiving device can acquire account information according to the user voice data.
In the embodiment of the invention, the earphone storage device can perform voice recognition on the user voice data to obtain a recognition text; performing sentence detection on the identification text to obtain at least one sentence; identifying a user intention corresponding to the at least one statement and determining the statement corresponding to the billing intention; account information is identified from the statement corresponding to the billing intent.
The step of the headset receiving device acquiring feedback information according to the account information may include: and the earphone accommodating device generates feedback information according to the accounting intention and the account information.
The account information comprises item information and/or amount information; the step of generating feedback information by the headset storage device according to the accounting intention and the account information may include: and the earphone accommodating device generates feedback information according to the accounting intention, the item information and/or the amount information.
In one example, the step of generating feedback information by the headset receiving device according to the accounting intent and the account information may include: and the earphone storage device generates feedback information according to a preset expression style, the accounting intention and the account information.
In another example, the step of generating feedback information by the headset receiving device according to the accounting intent and the account information may include: the earphone storage device generates feedback information according to preset character characteristic information, the accounting intention and the account information.
In the embodiment of the invention, the earphone accommodating device can perform voice recognition on the voice data of the user to obtain the recognition text; performing sentence detection on the identification text to obtain at least one sentence; recognizing a user intention corresponding to the at least one statement, and determining the statement corresponding to the checking intention; and searching account information according to the statement corresponding to the account checking intention.
The step of the headset receiving device acquiring feedback information according to the account information may include: and the earphone accommodating device generates feedback information according to the checking intention and the account information.
The step of generating feedback information by the headset receiving device according to the checking intention and the account information may include: and the earphone accommodating device generates feedback information according to the checking intention, the item information and/or the amount information.
In one example, the step of generating feedback information by the headset receiving device according to the checking intention and the account information may include: the earphone storage device generates feedback information according to a preset expression style, the checking intention and the account information.
In another example, the step of generating feedback information by the headset receiving device according to the checking intention and the account information may include: the earphone storage device generates feedback information according to preset character characteristic information, the checking intention and the account information.
The earphone receiving device can generate feedback information after acquiring account information and send the feedback information to the earphone.
And 1104, outputting according to the feedback information.
In the embodiment of the invention, the earphone can acquire the voice data of the user; sending user voice data to the earphone accommodating device so that the earphone accommodating device can acquire account information according to the user voice data; receiving feedback information generated by the earphone accommodating device according to the account information; and outputting according to the feedback information. The user is not required to operate the headset by hand to complete the accounting or checking, and the user can be fed back based on the account information. In the case that the user is inconvenient to operate by hand, the user's billing or audit requirements can be satisfied and the user can be made to perceive feedback.
Referring to fig. 12, a flow chart of steps of another interaction method of an embodiment of the present invention is shown, the method being applied to a headset, the headset being in communication with a headset receiving device, the headset having a voice assistant; the method may specifically comprise the steps of:
The voice assistant can send the user voice data to the headset receiving device, so that the headset receiving device can acquire account information according to the user voice data.
The earphone storage device can generate feedback information after acquiring account information and send the feedback information to the earphone, and the voice assistant can receive the feedback information.
And step 1204, the voice assistant outputs according to the feedback information.
In the embodiment of the invention, the voice assistant of the earphone can acquire the voice data of the user; sending user voice data to the earphone accommodating device so that the earphone accommodating device can acquire account information according to the user voice data; receiving feedback information generated by the earphone accommodating device according to the account information; and outputting according to the feedback information. The user is not required to operate the headset by hand to complete the accounting or checking, and the user can be fed back based on the account information. In the case that the user is inconvenient to operate by hand, the user's billing or audit requirements can be satisfied and the user can be made to perceive feedback.
It should be noted that, for simplicity of description, the method embodiments are described as a series of acts or combination of acts, but those skilled in the art will recognize that the present invention is not limited by the illustrated order of acts, as some steps may occur in other orders or concurrently in accordance with the embodiments of the present invention. Further, those skilled in the art will appreciate that the embodiments described in the specification are presently preferred and that no particular act is required to implement the invention.
Referring to fig. 13, a block diagram of a structure of an interaction apparatus according to an embodiment of the present invention is shown, where the interaction apparatus is applied to a headset, and the interaction apparatus may specifically include the following modules:
a user voice data obtaining module 1301, configured to obtain user voice data;
an account information obtaining module 1302, configured to obtain account information according to the user voice data;
and the feedback module 1303 is configured to obtain feedback information according to the account information, and output the feedback information according to the feedback information.
In this embodiment of the present invention, the account information obtaining module 1302 may include:
the first recognition text obtaining submodule is used for carrying out voice recognition on the user voice data to obtain a recognition text;
the first sentence obtaining submodule is used for carrying out sentence detection on the identification text to obtain at least one sentence;
the first statement determination submodule is used for identifying the user intention corresponding to the at least one statement and determining the statement corresponding to the accounting intention;
and the first account information identification submodule is used for identifying the account information from the statement corresponding to the accounting intention.
In this embodiment of the present invention, the feedback module 1303 may include:
and the first feedback information generation submodule is used for generating feedback information according to the accounting intention and the account information.
In an embodiment of the present invention, the account information includes transaction information and/or amount information.
In this embodiment of the present invention, the first feedback information generating sub-module may include:
and the first feedback information generating unit is used for generating feedback information according to a preset expression style, the accounting intention and the account information.
In this embodiment of the present invention, the first feedback information generating sub-module may include:
and the second feedback information generating unit is used for generating feedback information according to preset character characteristic information, the accounting intention and the account information.
In this embodiment of the present invention, the account information obtaining module 1302 may include:
the second recognition text obtaining submodule is used for carrying out voice recognition on the user voice data to obtain a recognition text;
the second sentence obtaining submodule is used for carrying out sentence detection on the identification text to obtain at least one sentence;
the second statement determination submodule is used for identifying the user intention corresponding to the at least one statement and determining the statement corresponding to the checking intention;
and the second account information identification submodule is used for searching the account information according to the statement corresponding to the account checking intention.
In this embodiment of the present invention, the feedback module 1303 may include:
and the second feedback information generation submodule is used for generating feedback information according to the checking intention and the account information.
In an embodiment of the present invention, the account information includes transaction information and/or amount information.
In this embodiment of the present invention, the second feedback information generating sub-module may include:
and the third feedback information generating unit is used for generating feedback information according to a preset expression style, the checking intention and the account information.
In this embodiment of the present invention, the second feedback information generating sub-module may include:
and the fourth feedback information generating unit is used for generating feedback information according to preset character characteristic information, the checking intention and the account information.
In this embodiment of the present invention, the account information obtaining module 1302 may include:
and the local acquisition submodule is used for acquiring account information locally on the earphone according to the user voice data.
In an embodiment of the invention, the headset communicates with a server; the account information obtaining module 1302 may include:
the first sending submodule is used for sending the user voice data to the server so that the server can obtain account information according to the user voice data;
the feedback module includes:
and the first receiving submodule is used for receiving feedback information generated by the server according to the account information.
In an embodiment of the invention, the headset communicates with a headset receiving device, which communicates with a server; the account information obtaining module 1302 may include:
the second sending submodule is used for sending the user voice data to the earphone accommodating device so that the earphone accommodating device sends the user voice data to the server, and account information is obtained through the server according to the user voice data; or enabling the earphone accommodating device to perform voice recognition on the user voice data to obtain a voice recognition result, and acquiring account information through the server according to the voice recognition result;
the feedback module includes:
and the second receiving submodule is used for receiving feedback information sent by the earphone accommodating device, and the feedback information is generated by the server according to the account information.
In an embodiment of the invention, the headset communicates with a headset receiving device; the account information obtaining module 1302 may include:
the third sending submodule is used for sending the user voice data to the earphone accommodating device so that the earphone accommodating device can obtain account information according to the user voice data;
the feedback module includes:
and the third receiving submodule is used for receiving feedback information generated by the earphone accommodating device according to the account information.
In an embodiment of the invention, the headset has a voice assistant deployed to the interactive device.
In this embodiment of the present invention, the apparatus may further include:
and the first awakening module is used for responding to the touch operation of a preset touch area acting on the earphone and awakening the voice assistant.
In this embodiment of the present invention, the apparatus may further include:
the monitoring module is used for monitoring user voice data;
and the second awakening module is used for awakening the voice assistant when detecting that the voice data of the user contains a preset awakening word.
The embodiment of the invention also discloses another interaction device, which is applied to an earphone, wherein the earphone is provided with a voice assistant, the voice assistant is arranged on the interaction device, and the interaction device can comprise:
the user voice data acquisition module is used for acquiring user voice data;
the account information acquisition module is used for acquiring account information according to the user voice data;
and the feedback module is used for acquiring feedback information according to the account information and outputting the feedback information.
Fig. 14 is a block diagram illustrating a structure of a headset 1400 for interaction according to an exemplary embodiment. Referring to fig. 14, the headset 1400 may include one or more of the following components: a processing component 1402, a memory 1404, a power component 1406, a multimedia component 1408, an audio component 1410, an input/output (I/O) interface 1412, a sensor component 1414, and a communication component 1416.
The processing component 1402 generally controls the overall operation of the headset 1400, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing element 1402 may include one or more processors 1420 to execute instructions to perform all or a portion of the steps of the methods described above. Further, processing component 1402 can include one or more modules that facilitate interaction between processing component 1402 and other components. For example, the processing component 1402 can include a multimedia module to facilitate interaction between the multimedia component 1408 and the processing component 1402.
The memory 1404 is configured to store various types of data to support operation at the headset 1400. Examples of such data include instructions for any application or method operating on the headset 1400, contact data, phonebook data, messages, pictures, videos, and so forth. The memory 1404 may be implemented by any type of volatile or non-volatile storage device or combination of devices, such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks.
The multimedia component 1408 includes a screen that provides an output interface between the headset 1400 and the user. In some embodiments, the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive an input signal from a user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 1408 includes a front-facing camera and/or a rear-facing camera. The front camera and/or the rear camera may receive external multimedia data when the headset 1400 is in an operating mode, such as a shooting mode or a video mode. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.
The audio component 1410 is configured to output and/or input audio signals. For example, the audio component 1410 includes a Microphone (MIC) configured to receive external audio signals when the headset 1400 is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals may further be stored in the memory 1404 or transmitted via the communication component 1416. In some embodiments, audio component 1410 further includes a speaker for outputting audio signals.
I/O interface 1412 provides an interface between processing component 1402 and peripheral interface modules, which may be keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to: a home button, a volume button, a start button, and a lock button.
The sensor component 1414 includes one or more sensors for providing various aspects of state assessment for the headset 1400. For example, the sensor component 1414 can detect an open/closed state of the headset 1400, the relative positioning of components, such as a display and keypad of the headset 1400, the sensor component 1414 can also detect a change in the position of the headset 1400 or a component of the headset 1400, the presence or absence of user contact with the headset 1400, orientation or acceleration/deceleration of the headset 1400, and a change in the temperature of the headset 1400. The sensor assembly 1414 may include a proximity sensor configured to detect the presence of a nearby object in the absence of any physical contact. The sensor assembly 1414 may also include a photosensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 1414 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.
The communication component 1416 is configured to facilitate wired or wireless communication between the headset 1400 and other devices. The headset 1400 may access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication section 1414 receives a broadcast signal or broadcast related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communications component 1414 further includes a Near Field Communication (NFC) module to facilitate short-range communications. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, Ultra Wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.
In an exemplary embodiment, the headset 1400 may be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, micro-controllers, microprocessors or other electronic components for performing the above-described methods.
In an exemplary embodiment, a non-transitory computer readable storage medium is also provided, such as the memory 1404 that includes instructions executable by the processor 1420 of the headset 1400 to perform the above-described methods. For example, the non-transitory computer readable storage medium may be a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.
Also disclosed in an embodiment of the present invention is a headset comprising a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors comprises instructions for:
acquiring user voice data;
acquiring account information according to the user voice data;
and acquiring feedback information according to the account information, and outputting according to the feedback information.
Optionally, the obtaining account information according to the user voice data includes:
carrying out voice recognition on the user voice data to obtain a recognition text;
performing sentence detection on the identification text to obtain at least one sentence;
identifying a user intention corresponding to the at least one statement and determining the statement corresponding to the billing intention;
account information is identified from the statement corresponding to the billing intent.
Optionally, the obtaining feedback information according to the account information includes:
and generating feedback information according to the accounting intention and the account information.
Optionally, the account information includes transaction information and/or amount information.
Optionally, the generating feedback information according to the accounting intention and the account information includes:
and generating feedback information according to a preset expression style, the accounting intention and the account information.
Optionally, the generating feedback information according to the accounting intention and the account information includes:
and generating feedback information according to preset character characteristic information, the bookkeeping intention and the account information.
Optionally, the obtaining account information according to the user voice data includes:
carrying out voice recognition on the user voice data to obtain a recognition text;
performing sentence detection on the identification text to obtain at least one sentence;
recognizing a user intention corresponding to the at least one statement, and determining the statement corresponding to the checking intention;
and searching account information according to the statement corresponding to the account checking intention.
Optionally, the obtaining feedback information according to the account information includes:
and generating feedback information according to the checking intention and the account information.
Optionally, the account information includes transaction information and/or amount information.
Optionally, the generating feedback information according to the checking intention and the account information includes:
and generating feedback information according to a preset expression style, the checking intention and the account information.
Optionally, the generating feedback information according to the checking intention and the account information includes:
and generating feedback information according to preset character characteristic information, the checking intention and the account information.
Optionally, the obtaining account information according to the user voice data includes:
and acquiring account information locally on the earphone according to the user voice data.
Optionally, the headset is in communication with a server; the acquiring of account information according to the user voice data includes:
sending the user voice data to the server so that the server can acquire account information according to the user voice data;
the obtaining feedback information according to the account information includes:
and receiving feedback information generated by the server according to the account information.
Optionally, the headset is in communication with a headset receiving device, the headset receiving device being in communication with a server; the acquiring of account information according to the user voice data includes:
sending the user voice data to the earphone accommodating device so that the earphone accommodating device sends the user voice data to the server, and acquiring account information through the server according to the user voice data; or enabling the earphone accommodating device to perform voice recognition on the user voice data to obtain a voice recognition result, and acquiring account information through the server according to the voice recognition result;
the obtaining feedback information according to the account information includes:
and receiving feedback information sent by the earphone accommodating device, wherein the feedback information is generated by the server according to the account information.
Optionally, the headset is in communication with a headset receiving device; the acquiring of account information according to the user voice data includes:
sending the user voice data to the earphone accommodating device so that the earphone accommodating device can acquire account information according to the user voice data;
the obtaining feedback information according to the account information includes:
and receiving feedback information generated by the earphone accommodating device according to the account information.
Optionally, the one or more programs include a voice assistant.
Optionally, further comprising instructions for:
and responding to touch operation acting on a preset touch area of the earphone, and awakening the voice assistant.
Optionally, further comprising instructions for:
monitoring voice data of a user;
and when detecting that the voice data of the user contains a preset awakening word, awakening the voice assistant.
Also disclosed in an embodiment of the present invention is an earpiece comprising a memory, and a voice assistant, wherein the voice assistant is stored in the memory and configured to be executed by one or more processors, the voice assistant comprising instructions for:
acquiring user voice data;
acquiring account information according to the user voice data;
and acquiring feedback information according to the account information, and outputting according to the feedback information.
Also disclosed in an embodiment of the present invention is a non-transitory computer readable storage medium, wherein instructions in the storage medium, when executed by a processor of a headset, enable the headset to perform a billing method, the method may include:
acquiring user voice data;
acquiring account information according to the user voice data;
and acquiring feedback information according to the account information, and outputting according to the feedback information.
Optionally, the obtaining account information according to the user voice data includes:
carrying out voice recognition on the user voice data to obtain a recognition text;
performing sentence detection on the identification text to obtain at least one sentence;
identifying a user intention corresponding to the at least one statement and determining the statement corresponding to the billing intention;
account information is identified from the statement corresponding to the billing intent.
Optionally, the obtaining feedback information according to the account information includes:
and generating feedback information according to the accounting intention and the account information.
Optionally, the account information includes transaction information and/or amount information.
Optionally, the generating feedback information according to the accounting intention and the account information includes:
and generating feedback information according to a preset expression style, the accounting intention and the account information.
Optionally, the generating feedback information according to the accounting intention and the account information includes:
and generating feedback information according to preset character characteristic information, the bookkeeping intention and the account information.
Optionally, the obtaining account information according to the user voice data includes:
carrying out voice recognition on the user voice data to obtain a recognition text;
performing sentence detection on the identification text to obtain at least one sentence;
recognizing a user intention corresponding to the at least one statement, and determining the statement corresponding to the checking intention;
and searching account information according to the statement corresponding to the account checking intention.
Optionally, the obtaining feedback information according to the account information includes:
and generating feedback information according to the checking intention and the account information.
Optionally, the account information includes transaction information and/or amount information.
Optionally, the generating feedback information according to the checking intention and the account information includes:
and generating feedback information according to a preset expression style, the checking intention and the account information.
Optionally, the generating feedback information according to the checking intention and the account information includes:
and generating feedback information according to preset character characteristic information, the checking intention and the account information.
Optionally, the obtaining account information according to the user voice data includes:
and acquiring account information locally on the earphone according to the user voice data.
Optionally, the headset is in communication with a server; the acquiring of account information according to the user voice data includes:
sending the user voice data to the server so that the server can acquire account information according to the user voice data;
the obtaining feedback information according to the account information includes:
and receiving feedback information generated by the server according to the account information.
Optionally, the headset is in communication with a headset receiving device, the headset receiving device being in communication with a server; the acquiring of account information according to the user voice data includes:
sending the user voice data to the earphone accommodating device so that the earphone accommodating device sends the user voice data to the server, and acquiring account information through the server according to the user voice data; or enabling the earphone accommodating device to perform voice recognition on the user voice data to obtain a voice recognition result, and acquiring account information through the server according to the voice recognition result;
the obtaining feedback information according to the account information includes:
and receiving feedback information sent by the earphone accommodating device, wherein the feedback information is generated by the server according to the account information.
Optionally, the headset is in communication with a headset receiving device; the acquiring of account information according to the user voice data includes:
sending the user voice data to the earphone accommodating device so that the earphone accommodating device can acquire account information according to the user voice data;
the obtaining feedback information according to the account information includes:
and receiving feedback information generated by the earphone accommodating device according to the account information.
Optionally, the headset has a voice assistant.
Optionally, the method further comprises:
and responding to touch operation acting on a preset touch area of the earphone, and awakening the voice assistant.
Optionally, the method further comprises:
monitoring voice data of a user;
and when detecting that the voice data of the user contains a preset awakening word, awakening the voice assistant.
The embodiments in the present specification are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, apparatus, or computer program product. Accordingly, embodiments of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
Embodiments of the present invention are described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing terminal to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing terminal to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing terminal to cause a series of operational steps to be performed on the computer or other programmable terminal to produce a computer implemented process such that the instructions which execute on the computer or other programmable terminal provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications of these embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the embodiments of the invention.
Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or terminal that comprises the element.
The interaction method, the interaction device and the earphone provided by the invention are described in detail above, and the principle and the implementation of the invention are explained in the present document by applying specific examples, and the description of the above examples is only used to help understanding the method and the core idea of the invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (10)
1. An interactive method, applied to a headset, the method comprising:
acquiring user voice data;
acquiring account information according to the user voice data;
and acquiring feedback information according to the account information, and outputting according to the feedback information.
2. The method of claim 1, wherein the obtaining account information from the user voice data comprises:
carrying out voice recognition on the user voice data to obtain a recognition text;
performing sentence detection on the identification text to obtain at least one sentence;
identifying a user intention corresponding to the at least one statement and determining the statement corresponding to the billing intention;
account information is identified from the statement corresponding to the billing intent.
3. The method of claim 2, wherein the obtaining feedback information according to the account information comprises:
and generating feedback information according to the accounting intention and the account information.
4. The method of claim 3, wherein the accounting information comprises transaction information and/or amount information.
5. The method of claim 4, wherein generating feedback information from the billing intent and the accounting information comprises:
and generating feedback information according to a preset expression style, the accounting intention and the account information.
6. The method of claim 4, wherein generating feedback information from the billing intent and accounting information comprises:
and generating feedback information according to preset character characteristic information, the bookkeeping intention and the account information.
7. The method of claim 1, wherein the obtaining account information from the user voice data comprises:
carrying out voice recognition on the user voice data to obtain a recognition text;
performing sentence detection on the identification text to obtain at least one sentence;
recognizing a user intention corresponding to the at least one statement, and determining the statement corresponding to the checking intention;
and searching account information according to the statement corresponding to the account checking intention.
8. An interaction device, applied to a headset, comprising:
the user voice data acquisition module is used for acquiring user voice data;
the account information acquisition module is used for acquiring account information according to the user voice data;
and the feedback module is used for acquiring feedback information according to the account information and outputting the feedback information.
9. A headset comprising a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by one or more processors the one or more programs including instructions for:
acquiring user voice data;
acquiring account information according to the user voice data;
and acquiring feedback information according to the account information, and outputting according to the feedback information.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the interaction method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011063546.3A CN112201251A (en) | 2020-09-30 | 2020-09-30 | Interaction method and device and earphone |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011063546.3A CN112201251A (en) | 2020-09-30 | 2020-09-30 | Interaction method and device and earphone |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112201251A true CN112201251A (en) | 2021-01-08 |
Family
ID=74013581
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011063546.3A Pending CN112201251A (en) | 2020-09-30 | 2020-09-30 | Interaction method and device and earphone |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112201251A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107977183A (en) * | 2017-11-16 | 2018-05-01 | 百度在线网络技术（北京）有限公司 | voice interactive method, device and equipment |
| CN108255469A (en) * | 2017-12-12 | 2018-07-06 | 广东广业开元科技有限公司 | A kind of establishment can voice and analysis account artificial intelligence accounting system method |
| US20200005772A1 (en) * | 2018-06-28 | 2020-01-02 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Interactive method and device of robot, and device |
| CN110659970A (en) * | 2018-06-12 | 2020-01-07 | 百度在线网络技术（北京）有限公司 | Account information processing method and device based on voice recognition and electronic equipment |
| CN111696553A (en) * | 2020-06-05 | 2020-09-22 | 北京搜狗科技发展有限公司 | Voice processing method and device and readable medium |
-
2020
- 2020-09-30 CN CN202011063546.3A patent/CN112201251A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107977183A (en) * | 2017-11-16 | 2018-05-01 | 百度在线网络技术（北京）有限公司 | voice interactive method, device and equipment |
| CN108255469A (en) * | 2017-12-12 | 2018-07-06 | 广东广业开元科技有限公司 | A kind of establishment can voice and analysis account artificial intelligence accounting system method |
| CN110659970A (en) * | 2018-06-12 | 2020-01-07 | 百度在线网络技术（北京）有限公司 | Account information processing method and device based on voice recognition and electronic equipment |
| US20200005772A1 (en) * | 2018-06-28 | 2020-01-02 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Interactive method and device of robot, and device |
| CN111696553A (en) * | 2020-06-05 | 2020-09-22 | 北京搜狗科技发展有限公司 | Voice processing method and device and readable medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10313279B2 (en) | Live video-chat function within text messaging environment | |
| US20200125322A1 (en) | Systems and methods for customization of augmented reality user interface | |
| CN110140168A (en) | Context hot word | |
| US8571851B1 (en) | Semantic interpretation using user gaze order | |
| US10176511B2 (en) | System and method for wireless ordering using speech recognition | |
| US20180077096A1 (en) | Messaging environment for mobile device with multitask toolbar, search engine and keyboard control access to apps and centralized functionality | |
| CN105427121B (en) | The system and method for natural language processing selection presentation of advertisements based on phonetic entry | |
| CN110427472A (en) | The matched method, apparatus of intelligent customer service, terminal device and storage medium | |
| US9418657B2 (en) | Communication system and method for an ear worn communication device | |
| US20150379989A1 (en) | Voice-controlled information exchange platform, such as for providing information to supplement advertising | |
| CN109102802A (en) | System for handling user spoken utterances | |
| CN106062868A (en) | Providing pre-computed hotword models | |
| CN104969289A (en) | Voice trigger for a digital assistant | |
| CN109308334B (en) | Information recommendation method and device and search engine system | |
| CN112185389A (en) | Voice generation method and device, storage medium and electronic equipment | |
| CN110020009A (en) | Online answering method, apparatus and system | |
| CN110634336A (en) | Method and device for generating audio electronic book | |
| CN111739530A (en) | Interaction method and device, earphone and earphone storage device | |
| CN110322760A (en) | Voice data generation method, device, terminal and storage medium | |
| CN109285548A (en) | Information processing method, system, electronic equipment and computer storage medium | |
| US20160259996A1 (en) | Interactive text recognition by a head-mounted device | |
| US20230336694A1 (en) | Tagging Characteristics of an Interpersonal Encounter Based on Vocal Features | |
| CN109994106A (en) | A kind of method of speech processing and equipment | |
| CN110110317A (en) | It is suitable for the grammar for natural language of interactive experience | |
| CN109754277B (en) | Rights acquisition operation object processing method and device and electronic equipment |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20210702 Address after: 100084 Room 802, 8th floor, building 9, yard 1, Zhongguancun East Road, Haidian District, Beijing Applicant after: Beijing Sogou Intelligent Technology Co.,Ltd. Address before: 100084. Room 9, floor 01, cyber building, building 9, building 1, Zhongguancun East Road, Haidian District, Beijing Applicant before: BEIJING SOGOU TECHNOLOGY DEVELOPMENT Co.,Ltd. |