CN107123042A - A kind of intelligent sound does tax method, apparatus and system - Google Patents
A kind of intelligent sound does tax method, apparatus and system Download PDFInfo
- Publication number
- CN107123042A CN107123042A CN201710281594.1A CN201710281594A CN107123042A CN 107123042 A CN107123042 A CN 107123042A CN 201710281594 A CN201710281594 A CN 201710281594A CN 107123042 A CN107123042 A CN 107123042A
- Authority
- CN
- China
- Prior art keywords
- tax
- solution
- target
- terminal
- request
- 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 36
- 238000005538 encapsulation Methods 0.000 claims description 17
- 238000004458 analytical method Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 6
- 230000004044 response Effects 0.000 description 4
- 230000015572 biosynthetic process Effects 0.000 description 3
- 230000003993 interaction Effects 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 3
- 238000003786 synthesis reaction Methods 0.000 description 3
- 230000029305 taxis Effects 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 230000004888 barrier function Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000009223 counseling Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 238000009960 carding Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 210000001503 joint Anatomy 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- 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
- G06Q40/123—Tax preparation or submission
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/225—Feedback of the input speech
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/04—Network architectures or network communication protocols for network security for providing a confidential data exchange among entities communicating through data packet networks
- H04L63/0428—Network architectures or network communication protocols for network security for providing a confidential data exchange among entities communicating through data packet networks wherein the data content is protected, e.g. by encrypting or encapsulating the payload
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Physics & Mathematics (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Computational Linguistics (AREA)
- Technology Law (AREA)
- Marketing (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Machine Translation (AREA)
Abstract
Tax method, apparatus and system are done the invention provides a kind of intelligent sound, this method, including：Tax knowledge base is pre-set, the tax knowledge base includes at least one tax solution；Receive the voice request for doing the user that tax terminal is sent；Speech recognition is carried out to the voice request, the corresponding request content of the voice request is obtained；According to the request content, target tax solution is determined from the tax knowledge base；By the target tax solution, return to it is described do tax terminal so that the target tax solution is presented to the user by the tax terminal of doing.Tax method, apparatus and system are done the invention provides a kind of intelligent sound, self-help tax can be more easily realized.
Description
Technical field
The present invention relates to field of computer technology, more particularly to a kind of intelligent sound does tax method, apparatus and system.
Background technology
Current tax system develops many external self-help tax services channels for providing taxpayer, for example can be by certainly
Help and do tax terminal, electronic tax office, handheld terminal etc. and do tax terminal to carry out self-help tax.
In the prior art, various self-help tax services channels are come generally by the mode of figure fixed in advance, word
Auxiliary user does tax terminal using various.When user self-help does tax, if encountered problems, it is necessary to which oneself does tax end by searching
Fixed figure on end, the help information of word solve the problem.
Visible by foregoing description, prior art can only help user to solve by figure fixed in advance, word
The problem of being run into when doing tax, it is relatively difficult when user searches related solution because help information is more.It is logical in user
When crossing the problem of these figures, word can not solve to run into, further solution, existing skill can not also be provided by doing tax terminal
Art is more complicated when realizing self-help tax.
The content of the invention
Tax method, apparatus and system are done the embodiments of the invention provide a kind of intelligent sound, can more easily be realized
Self-help tax.
In a first aspect, tax method is done the embodiments of the invention provide a kind of intelligent sound, including：
Tax knowledge base is pre-set, the tax knowledge base includes at least one tax solution；
Receive the voice request for doing the user that tax terminal is sent；
Speech recognition is carried out to the voice request, the corresponding request content of the voice request is obtained；
According to the request content, target tax solution is determined from the tax knowledge base；
By the target tax solution, return to it is described do tax terminal so that the tax terminal of doing is by the target
Tax solution is presented to the user.
Further, the tax knowledge base further comprises：At least one problem is described, and each described problem
Description and the corresponding relation of at least one tax solution；
It is described that target tax solution is determined from the tax knowledge base according to the request content, including：
Determine the similarity that the request content is described with each described problem；
According to the corresponding relation, determine that similarity highest target problem describes the corresponding target tax solution party
Case.
Further, the similarity for determining the request content and the description of each described problem, including：
Request keyword is extracted from the request content；
Description keyword is extracted from the description of each described problem；
The description keyword and the request keyword described according to each described problem, is calculated described similar
Degree.
Further, it is described by the target tax solution, return to it is described do tax terminal, including：
Message encapsulation is carried out to the target tax solution, the target tax solution after encapsulation is added
It is close, the ciphertext obtained after encryption is sent to and described does tax terminal.
Second aspect, tax device is done the embodiments of the invention provide a kind of intelligent sound, including：
Tax knowledge base, for preserving at least one tax solution；
Receiving unit, the voice request for the user that tax terminal is sent is done for receiving；
Recognition unit, for carrying out speech recognition to the voice request, is obtained in the corresponding request of the voice request
Hold；
Determining unit, for according to the request content, target tax solution to be determined from the tax knowledge base；
Returning unit, for by the target tax solution, return to it is described do tax terminal so that described, to do tax whole
The target tax solution is presented to the user by end.
Further, the tax knowledge base further comprises：At least one problem is described, and each described problem
Description and the corresponding relation of at least one tax solution；
The determining unit, for determining the similarity that the request content is described with each described problem, according to described
Corresponding relation, determines that similarity highest target problem describes the corresponding target tax solution.
Further, the determining unit, for extracting request keyword from the request content, from each described
Description keyword is extracted in problem description, the description keyword described according to each described problem and the request are crucial
Word, calculates the similarity.
Further, the returning unit, for carrying out message encapsulation to the target tax solution, after encapsulation
Target tax solution encryption, the ciphertext obtained after encryption is sent to and described does tax terminal.
The third aspect, tax system is done the embodiments of the invention provide a kind of intelligent sound, including：
Any described intelligent sound does tax device in second aspect and at least one does tax terminal；
It is described to do tax terminal, the target tax solution that tax device is sent is done for receiving the intelligent sound, by institute
State target tax solution and be presented to user.
Further, the intelligent sound does the returning unit of tax device, for entering to the target tax solution
Row message is encapsulated, and the target tax solution after encapsulation is encrypted, and the ciphertext obtained after encryption is sent into described do
Tax terminal；
It is described to do tax terminal, for receiving the ciphertext, the ciphertext is decrypted, the message that decryption is obtained is carried out
Decapsulation, obtains the target tax solution.
Further, it is described to do tax terminal, for by the target tax solution in the form of text and/or voice
It is presented to the user.
In embodiments of the present invention, tax knowledge base is pre-set, can basis when receiving the voice request of user
The voice request of user finds target tax solution from tax knowledge base, and target tax solution is returned to and does tax
Terminal so that user can handle relevant tax business according to target tax solution, and user is without searching related help
Information, can more easily realize self-help tax.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
There is the accompanying drawing used required in technology description to be briefly described, it should be apparent that, drawings in the following description are the present invention
Some embodiments, for those of ordinary skill in the art, on the premise of not paying creative work, can also basis
These accompanying drawings obtain other accompanying drawings.
Fig. 1 is the flow chart that a kind of intelligent sound that one embodiment of the invention is provided does tax method；
Fig. 2 is the flow chart that another intelligent sound that one embodiment of the invention is provided does tax method；
Fig. 3 is the schematic diagram that a kind of intelligent sound that one embodiment of the invention is provided does tax device；
Fig. 4 is the schematic diagram that a kind of intelligent sound that one embodiment of the invention is provided does tax system.
Embodiment
To make the purpose, technical scheme and advantage of the embodiment of the present invention clearer, below in conjunction with the embodiment of the present invention
In accompanying drawing, the technical scheme in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment is
A part of embodiment of the present invention, rather than whole embodiments, based on the embodiment in the present invention, those of ordinary skill in the art
The every other embodiment obtained on the premise of creative work is not made, belongs to the scope of protection of the invention.
As shown in figure 1, doing tax method the embodiments of the invention provide a kind of intelligent sound, this method can include following step
Suddenly：
Step 101：Tax knowledge base is pre-set, the tax knowledge base includes at least one tax solution；
Step 102：Receive the voice request for doing the user that tax terminal is sent；
Step 103：Speech recognition is carried out to the voice request, the corresponding request content of the voice request is obtained；
Step 104：According to the request content, target tax solution is determined from the tax knowledge base；
Step 105：By the target tax solution, return to it is described do tax terminal so that the tax terminal of doing will
The target tax solution is presented to the user.
In embodiments of the present invention, tax knowledge base is pre-set, can basis when receiving the voice request of user
The voice request of user finds target tax solution from tax knowledge base, and target tax solution is returned to and does tax
Terminal so that user can handle relevant tax business according to target tax solution, and user is without searching related help
Information, can more easily realize self-help tax.
In an embodiment of the present invention, the tax knowledge base further comprises：At least one problem is described, and often
Individual described problem description and the corresponding relation of at least one tax solution；
It is described that target tax solution is determined from the tax knowledge base according to the request content, including：
Determine the similarity that the request content is described with each described problem；
According to the corresponding relation, determine that similarity highest target problem describes the corresponding target tax solution party
Case.
In embodiments of the present invention, described by problem and the similarity of request content can determine that what user ran into asks
Topic, and then optimal solution can be provided the user.
In an embodiment of the present invention, it is described to determine the similarity that the request content is described with each described problem, bag
Include：
Request keyword is extracted from the request content；
Description keyword is extracted from the description of each described problem；
The description keyword and the request keyword described according to each described problem, is calculated described similar
Degree.
In embodiments of the present invention, similarity problem request content and problem described, is converted in order in request problem
Request keyword and problem description in description keyword between the problem of, what can be more prone to determines what user ran into
Problem.For example, user is when sending voice request, may add the information of many redundancies, and some are incoherent
Information, when directly calculating the similarity described with problem using request content, amount of calculation is larger, moreover, the degree of accuracy is relatively low.
And similarity is calculated according to request keyword, and the emphasis of problem can be caught, amount of calculation is smaller, and the degree of accuracy is also higher.
It is in an embodiment of the present invention, described by the target tax solution in order to ensure the safety of information, return
Tax terminal is done to described, including：
Message encapsulation is carried out to the target tax solution, the target tax solution after encapsulation is added
It is close, the ciphertext obtained after encryption is sent to and described does tax terminal.
In embodiments of the present invention, encapsulation, encryption have been carried out to target tax solution, has improved information transfer
Security.
In embodiments of the present invention, security protocol, the data transfer association of unified access service platform can be pre-established
View, business interface specification etc., when carrying out relevant treatment, can be handled according to corresponding agreement or specification, it is possible to increase
Treatment effeciency.
As shown in Fig. 2 doing tax method the embodiments of the invention provide a kind of intelligent sound, this method can include following step
Suddenly：
Step 201：Tax knowledge base is pre-set, wherein, tax knowledge base includes：At least one problem is described, with
And each problem description and the corresponding relation of at least one tax solution.
Specifically, the passage description for the problem of problem description refers to be likely encountered user, for example：The related political affairs of consulting
Plan, handle affairs guide, various FAQs etc..
For example, problem is described as consulting policy A, and the problem describes the phase that corresponding tax solution is policy A
Close information.
In embodiments of the present invention, by tax-related service knowledge according to service handling channel, business scope, business scenario, specially
The fields such as industry word carry out knowledge combing, and business operation flow, business of the depth analysis taxpayer during self-help tax
Scene and FAQs, and then generate the tax knowledge base.The tax knowledge base can be preserved based on suitable for self-help tax
Professional knowledge.
In embodiments of the present invention, the foundation and maintenance of tax knowledge base, is that the industry of tax tax-related service is being done to taxpayer
Business flow, business scenario and tax-related service knowledge deeply understand to be carried out combing what is drawn after analysis, and the carding process is constantly complete
Process that is kind, updating, is the process of an iteration.
Step 202：Receive the voice request for doing the user that tax terminal is sent.
Specifically, user is by doing the microphone input voice request of tax terminal.For example：Inquiry policy A.
Step 203：Speech recognition is carried out to voice request, the corresponding request content of voice request is obtained.
Specifically, when carrying out speech recognition, linguistic context understanding is carried out with reference to context, request is generated after semantic analysis
Content, the request content is content of text.
Specifically, ESA (Explicit Semantic Analysis, Precise Semantics analysis) semantic analysis mould can be passed through
Type carries out speech recognition.Request content can be obtained by semantic vector operation.
Step 204：Determine the similarity that request content is described with each problem.
Specifically, the knowledge of request content and tax knowledge base is carried out into semantic similarity to be calculated.
Step 205：According to corresponding relation, determine that similarity highest target problem describes corresponding target tax solution party
Case.
Specifically, optimal tax solution, that is, the mesh are found by the description of similarity highest target problem
Mark tax solution.
Step 206：By target tax solution, return to and do tax terminal, solve the target tax so as to do tax terminal
Scheme is presented to user.
Specifically, user can be presented to by target tax solution in the form of voice and/or text by doing tax terminal,
It is easy to user to become apparent from clear carry out subsequent operation.
As shown in figure 3, tax device is done the embodiments of the invention provide a kind of intelligent sound, including：
Tax knowledge base 301, for preserving at least one tax solution；
Receiving unit 302, the voice request for the user that tax terminal is sent is done for receiving；
Recognition unit 303, for carrying out speech recognition to the voice request, obtains the corresponding request of the voice request
Content；
Determining unit 304, for according to the request content, target tax solution party to be determined from the tax knowledge base
Case；
Returning unit 305, for by the target tax solution, return to it is described do tax terminal so that described do
The target tax solution is presented to the user by tax terminal.
In an embodiment of the present invention, the tax knowledge base further comprises：At least one problem is described, and often
Individual described problem description and the corresponding relation of at least one tax solution；
The determining unit, for determining the similarity that the request content is described with each described problem, according to described
Corresponding relation, determines that similarity highest target problem describes the corresponding target tax solution.
In an embodiment of the present invention, the determining unit, for extracting request keyword from the request content,
Description keyword is extracted from the description of each described problem, the description keyword described according to each described problem and institute
Request keyword is stated, the similarity is calculated.
In an embodiment of the present invention, the returning unit, for carrying out message envelope to the target tax solution
Dress, the target tax solution after encapsulation is encrypted, and the ciphertext obtained after encryption is sent to and described does tax terminal.
Tax system is done the embodiments of the invention provide a kind of intelligent sound, including：
Any described intelligent sound does tax device in the embodiment of the present invention and at least one does tax terminal；
It is described to do tax terminal, the target tax solution that tax device is sent is done for receiving the intelligent sound, by institute
State target tax solution and be presented to user.
As shown in figure 4, tax system is done the embodiments of the invention provide a kind of intelligent sound, including：
Any intelligent sound does tax device 401 in the embodiment of the present invention and three are done tax terminal 402；
Tax terminal 402 each is done, the target tax solution that tax device 401 is sent is done for receiving intelligent sound, will
Target tax solution is presented to user.
In embodiments of the present invention, intelligent sound is done tax device and can provided for the various tax terminals of doing for doing tax services channels
Unified voice answer-back service interface, the device passes through the Data Transport Protocol, safety authentication protocol and service interaction that define
Agreement is received from the various voice requests for doing the transmission of tax terminal.
In embodiments of the present invention, intelligent sound, which does tax device, can provide unified knowledge maintenance, speech recognition, semanteme
The interface services such as analysis, semantic understanding, phonetic synthesis and voice answer-back, so that various tax terminals of doing can use the interface to take
Business.
In embodiments of the present invention, the maintenance that tax device carries out tax knowledge base can be done by intelligent sound, by examining
Knowledge after core does the unified issue of tax device by intelligent sound, realizes the unified management of each business channel knowledge.
In embodiments of the present invention, intelligent sound does tax device when receiving the voice request for doing the transmission of tax terminal, enters
After row associated safety certification, carry out the natural language understanding technologies such as semantic understanding, linguistic context understanding with reference to contextual information and judge to use
Family is intended to, and is calculated with the knowledge progress semantic similarity of tax knowledge base, and optimal tax solution is returned to
Do tax terminal.
In embodiments of the present invention, intelligent sound, which does tax device, can include repository services, speech-recognition services, semanteme
Analysis Service, semantic understanding service, KBS, voice answer-back service, Security Authentication Service, load balancing service and resource
Dispatch service etc. is serviced.The voice request received that can be achieved a butt joint by load balancing service and scheduling of resource service is closed
The distribution of reason, it is to avoid for the load excessive for the physical equipment for handling voice request.
In embodiments of the present invention, doing tax terminal can include：Self-help tax service terminal, electronic tax office, mobile terminal etc..
In an embodiment of the present invention, the intelligent sound does the returning unit of tax device, for the target tax
Solution carries out message encapsulation, and the target tax solution after encapsulation is encrypted, and the ciphertext obtained after encryption is sent out
Tax terminal is done described in giving；
It is described to do tax terminal, for receiving the ciphertext, the ciphertext is decrypted, the message that decryption is obtained is carried out
Decapsulation, obtains the target tax solution.
In an embodiment of the present invention, it is described to do tax terminal, for by the target tax solution with text and/or
The form of voice is presented to the user.
In embodiments of the present invention, tax solution can not be returned to by doing tax device in intelligent sound, or, the tax of return
When business solution does not meet user's request, manual service can be connected for user by doing tax terminal, be user by manual service
Solution is provided.
In embodiments of the present invention, using artificial intelligence, speech recognition, semantic understanding, ESA semantic analyses model, voice
The technology such as synthesis and knowledge base realizes intelligent response, and unified interface service is provided for self-help tax channel, is finally taxpayer
In operation exist using when obstacle or operation disruption there is provided timely, intelligent guide service, it is to avoid taxpayer is again
The consulting of secondary race business hall or the worry of telephone counseling, allow taxpayer enjoy in the case of unmanned instruct intelligent interaction easily from
Help and do tax service.
In embodiments of the present invention, the self-help tax pattern for doing tax device based on the intelligent sound can effectively solve to receive
Tax people can not clearly understand how progress subsequently grasps when running into operating barrier or operating process interruption during business handling
The problem of making, effectively improves the ease for use, intelligent of self-aided terminal, improves the convenience of self-help tax and the company of business
Coherence, mitigates the operating pressure that live tax staff teaches.
The embodiment of the present invention ensure that each does the security of the data of tax channel, uniformity, be provided more for taxpayer
Easily intelligent response service, the intelligence degree and taxpayer for improving concerning taxes application does tax efficiency and satisfaction.
The contents such as the information exchange between each unit, implementation procedure in said apparatus, due to implementing with the inventive method
Example is based on same design, and particular content can be found in the narration in the inventive method embodiment, and here is omitted.
The embodiments of the invention provide a kind of computer-readable recording medium, including execute instruction, when the computing device of storage control
During the execute instruction, the storage control performs any one intelligent sound provided in an embodiment of the present invention and does tax method.
The embodiments of the invention provide a kind of storage control, including：Processor, memory and bus；
The memory is used to store execute instruction, and the processor is connected with the memory by the bus, when
During the storage control operation, the execute instruction of memory storage described in the computing device, so that the storage
Controller performs any one intelligent sound provided in an embodiment of the present invention and does tax method.
Each embodiment of the invention at least has the advantages that：
1st, in embodiments of the present invention, tax knowledge base is pre-set, when receiving the voice request of user, Ke Yigen
Target tax solution is found from tax knowledge base according to the voice request of user, target tax solution is returned to and done
Tax terminal so that user can handle relevant tax business according to target tax solution, and user is without searching related side
Supplementary information, can more easily realize self-help tax.
2nd, in embodiments of the present invention, using artificial intelligence, speech recognition, semantic understanding, ESA semantic analyses model, language
The technology such as sound synthesis and knowledge base realizes intelligent response, and unified interface service is provided for self-help tax channel, and final is to pay taxes
People in operation exist using when obstacle or operation disruption there is provided timely, intelligent guide service, it is to avoid taxpayer
The worry of business hall consulting or telephone counseling is run again, allows taxpayer to enjoy in the case of unmanned instruct intelligent interaction easily
Self-help tax is serviced.
3rd, in embodiments of the present invention, the self-help tax pattern for doing tax device based on the intelligent sound can be solved effectively
Taxpayer can not clearly understand when running into operating barrier or operating process interruption during business handling progress it is follow-up how
The problem of operation, the ease for use, intelligent of self-aided terminal is effectively improved, improve the convenience and business of self-help tax
Continuity, mitigates the operating pressure that live tax staff teaches.
4th, the embodiment of the present invention ensure that each does the security of the data of tax channel, uniformity, be provided more for taxpayer
Plus easily intelligent response service, the intelligence degree and taxpayer for improving concerning taxes application do tax efficiency and satisfaction.
It should be noted that herein, such as first and second etc relational terms are used merely to an entity
Or operation makes a distinction with another entity or operation, and not necessarily require or imply exist between these entities or operation
Any this actual relation or order.Moreover, term " comprising ", "comprising" or its any other variant be intended to it is non-
It is exclusive to include, so that process, method, article or equipment including a series of key elements not only include those key elements,
But also other key elements including being not expressly set out, or also include solid by this process, method, article or equipment
Some key elements.In the absence of more restrictions, the key element limited by sentence " including one ", is not arranged
Except also there is other identical factor in the process including the key element, method, article or equipment.
One of ordinary skill in the art will appreciate that：Realizing all or part of step of above method embodiment can pass through
Programmed instruction related hardware is completed, and foregoing program can be stored in the storage medium of embodied on computer readable, the program
Upon execution, the step of including above method embodiment is performed；And foregoing storage medium includes：ROM, RAM, magnetic disc or light
Disk etc. is various can be with the medium of store program codes.
It is last it should be noted that：Presently preferred embodiments of the present invention is the foregoing is only, the skill of the present invention is merely to illustrate
Art scheme, is not intended to limit the scope of the present invention.Any modification for being made within the spirit and principles of the invention,
Equivalent substitution, improvement etc., are all contained in protection scope of the present invention.
Claims (10)
1. a kind of intelligent sound does tax method, it is characterised in that
Tax knowledge base is pre-set, the tax knowledge base includes at least one tax solution；
Including：
Receive the voice request for doing the user that tax terminal is sent；
Speech recognition is carried out to the voice request, the corresponding request content of the voice request is obtained；
According to the request content, target tax solution is determined from the tax knowledge base；
By the target tax solution, return to it is described do tax terminal so that the tax terminal of doing is by the target tax
Solution is presented to the user.
2. according to the method described in claim 1, it is characterised in that
The tax knowledge base further comprises：At least one problem is described, and each described problem description and at least one
The corresponding relation of individual tax solution；
It is described that target tax solution is determined from the tax knowledge base according to the request content, including：
Determine the similarity that the request content is described with each described problem；
According to the corresponding relation, determine that similarity highest target problem describes the corresponding target tax solution.
3. method according to claim 2, it is characterised in that
The similarity for determining the request content and the description of each described problem, including：
Request keyword is extracted from the request content；
Description keyword is extracted from the description of each described problem；
The description keyword and the request keyword described according to each described problem, calculates the similarity.
4. according to any described method in claim 1-3, it is characterised in that
It is described by the target tax solution, return to it is described do tax terminal, including：
Message encapsulation is carried out to the target tax solution, the target tax solution after encapsulation is encrypted, will
The ciphertext obtained after encryption does tax terminal described in being sent to.
5. a kind of intelligent sound does tax device, it is characterised in that including：
Tax knowledge base, for preserving at least one tax solution；
Receiving unit, the voice request for the user that tax terminal is sent is done for receiving；
Recognition unit, for carrying out speech recognition to the voice request, obtains the corresponding request content of the voice request；
Determining unit, for according to the request content, target tax solution to be determined from the tax knowledge base；
Returning unit, for by the target tax solution, return to it is described do tax terminal so that the tax terminal of doing will
The target tax solution is presented to the user.
6. device according to claim 5, it is characterised in that
The tax knowledge base further comprises：At least one problem is described, and each described problem description and at least one
The corresponding relation of individual tax solution；
The determining unit, for determining the similarity that the request content is described with each described problem, according to the correspondence
Relation, determines that similarity highest target problem describes the corresponding target tax solution.
7. device according to claim 6, it is characterised in that
The determining unit, for extracting request keyword from the request content, is carried from the description of each described problem
Description keyword is taken out, the description keyword and the request keyword described according to each described problem calculates institute
State similarity.
8. according to any described device in claim 5-7, it is characterised in that
The returning unit, for carrying out message encapsulation to the target tax solution, by the target tax after encapsulation
Solution of being engaged in encryption, the ciphertext obtained after encryption is sent to and described does tax terminal.
9. a kind of intelligent sound does tax system, it is characterised in that including：
Any described intelligent sound does tax device in claim 5-8 and at least one does tax terminal；
It is described to do tax terminal, the target tax solution that tax device is sent is done for receiving the intelligent sound, by the mesh
Mark tax solution is presented to user.
10. system according to claim 9, it is characterised in that
The intelligent sound does the returning unit of tax device, for carrying out message encapsulation to the target tax solution, will
Target tax solution encryption after encapsulation, the ciphertext obtained after encryption is sent to and described does tax terminal；
It is described to do tax terminal, for receiving the ciphertext, the ciphertext is decrypted, the message that decryption is obtained is unsealed
Dress, obtains the target tax solution；
And/or,
It is described to do tax terminal, for the target tax solution to be presented into the use in the form of text and/or voice
Family.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710281594.1A CN107123042A (en) | 2017-04-26 | 2017-04-26 | A kind of intelligent sound does tax method, apparatus and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710281594.1A CN107123042A (en) | 2017-04-26 | 2017-04-26 | A kind of intelligent sound does tax method, apparatus and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107123042A true CN107123042A (en) | 2017-09-01 |
Family
ID=59725431
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710281594.1A Pending CN107123042A (en) | 2017-04-26 | 2017-04-26 | A kind of intelligent sound does tax method, apparatus and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107123042A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109034986A (en) * | 2018-07-06 | 2018-12-18 | 山东浪潮商用系统有限公司 | A kind of intelligent sound self-help tax administration apparatus and method based on speech recognition |
| CN109102809A (en) * | 2018-06-22 | 2018-12-28 | 北京光年无限科技有限公司 | A kind of dialogue method and system for intelligent robot |
| CN109343705A (en) * | 2018-09-14 | 2019-02-15 | 广州越维信息科技有限公司 | AR auxiliary does tax method and system |
| CN109949813A (en) * | 2017-12-20 | 2019-06-28 | 北京君林科技股份有限公司 | A kind of method, apparatus and system converting speech into text |
| CN111081224A (en) * | 2019-12-31 | 2020-04-28 | 中国石油集团安全环保技术研究院有限公司 | Data acquisition method and device for petroleum safety event |
| CN111192584A (en) * | 2019-12-11 | 2020-05-22 | 秒针信息技术有限公司 | Document verification and cancellation method and system |
| CN111508494A (en) * | 2020-04-20 | 2020-08-07 | 广东工业大学 | Intelligent tax payment voice consultation method and system |
| CN111626452A (en) * | 2019-02-28 | 2020-09-04 | 百度在线网络技术（北京）有限公司 | Intelligent government affair processing method, device, terminal and medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105046550A (en) * | 2015-06-18 | 2015-11-11 | 浪潮软件集团有限公司 | Income tax declaration method, self-service tax handling terminal and system |
| CN105894370A (en) * | 2016-03-29 | 2016-08-24 | 浪潮软件集团有限公司 | Solution for realizing interconnection and intercommunication of self-service tax handling terminal and tax core system |
| CN105930452A (en) * | 2016-04-21 | 2016-09-07 | 北京紫平方信息技术股份有限公司 | Smart answering method capable of identifying natural language |
| CN106447484A (en) * | 2016-09-29 | 2017-02-22 | 山东浪潮商用系统有限公司 | Self-help tax payment system and self-help tax payment method |
-
2017
- 2017-04-26 CN CN201710281594.1A patent/CN107123042A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105046550A (en) * | 2015-06-18 | 2015-11-11 | 浪潮软件集团有限公司 | Income tax declaration method, self-service tax handling terminal and system |
| CN105894370A (en) * | 2016-03-29 | 2016-08-24 | 浪潮软件集团有限公司 | Solution for realizing interconnection and intercommunication of self-service tax handling terminal and tax core system |
| CN105930452A (en) * | 2016-04-21 | 2016-09-07 | 北京紫平方信息技术股份有限公司 | Smart answering method capable of identifying natural language |
| CN106447484A (en) * | 2016-09-29 | 2017-02-22 | 山东浪潮商用系统有限公司 | Self-help tax payment system and self-help tax payment method |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109949813A (en) * | 2017-12-20 | 2019-06-28 | 北京君林科技股份有限公司 | A kind of method, apparatus and system converting speech into text |
| CN109102809A (en) * | 2018-06-22 | 2018-12-28 | 北京光年无限科技有限公司 | A kind of dialogue method and system for intelligent robot |
| CN109034986A (en) * | 2018-07-06 | 2018-12-18 | 山东浪潮商用系统有限公司 | A kind of intelligent sound self-help tax administration apparatus and method based on speech recognition |
| CN109343705A (en) * | 2018-09-14 | 2019-02-15 | 广州越维信息科技有限公司 | AR auxiliary does tax method and system |
| CN111626452A (en) * | 2019-02-28 | 2020-09-04 | 百度在线网络技术（北京）有限公司 | Intelligent government affair processing method, device, terminal and medium |
| CN111626452B (en) * | 2019-02-28 | 2023-08-04 | 百度在线网络技术（北京）有限公司 | Intelligent government affair processing method, device, terminal and medium |
| CN111192584A (en) * | 2019-12-11 | 2020-05-22 | 秒针信息技术有限公司 | Document verification and cancellation method and system |
| CN111081224A (en) * | 2019-12-31 | 2020-04-28 | 中国石油集团安全环保技术研究院有限公司 | Data acquisition method and device for petroleum safety event |
| CN111508494A (en) * | 2020-04-20 | 2020-08-07 | 广东工业大学 | Intelligent tax payment voice consultation method and system |
| CN111508494B (en) * | 2020-04-20 | 2023-03-07 | 广东工业大学 | Intelligent tax payment voice consultation method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107123042A (en) | A kind of intelligent sound does tax method, apparatus and system | |
| KR102268989B1 (en) | Data structure pooling of voice activated data packets | |
| US20210342547A1 (en) | System for focused conversation context management in a reasoning agent/behavior engine of an agent automation system | |
| CN109691036A (en) | The natural language interaction formula message transfer service of internet cloud trustship with the communication based on entity | |
| CN109791592A (en) | The sensitive data in application program is handled using external treatment | |
| CN110377712A (en) | A kind of intelligence conversation switching method, device, equipment and storage medium | |
| US20220353801A1 (en) | Distributed multi-access edge service delivery | |
| CN110096584A (en) | A kind of answer method and device | |
| CN112015402B (en) | Method and device for quickly establishing service scene and electronic equipment | |
| CN111382252B (en) | Method, device, equipment and medium for determining problem category based on user request | |
| CN108073587A (en) | A kind of automatic question-answering method, device and electronic equipment | |
| WO2024198355A1 (en) | Human-ai interaction method and system based on llm model | |
| CN107528912A (en) | A kind of automatic method, system and relevant apparatus for realizing distributing real time system | |
| CN114202203A (en) | Complaint work order processing method and device, storage medium and electronic equipment | |
| CN113140219A (en) | Regulation and control instruction generation method and device, electronic equipment and storage medium | |
| CN112016327A (en) | Intelligent structured text extraction method and device based on multiple rounds of conversations and electronic equipment | |
| EP3609157A1 (en) | Methods and systems for managing communication sessions | |
| CN107085584A (en) | A kind of cloud document management method, system and service end based on content | |
| CN110033291A (en) | Information object method for pushing, device and system | |
| CN102546595A (en) | Light weight transformation for media | |
| CN110400094A (en) | Operation row number method, apparatus, system, electronic equipment and storage medium | |
| CN110110099A (en) | A kind of multimedia document retrieval method and device | |
| CN110096514A (en) | Data query method and apparatus | |
| CN109120509A (en) | A kind of method and device that information is collected | |
| US11526542B2 (en) | Server and method for classifying entities of a query |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170901 |
|
| RJ01 | Rejection of invention patent application after publication |