CN110060674A - Form management method, apparatus, terminal and storage medium - Google Patents
Form management method, apparatus, terminal and storage medium Download PDFInfo
- Publication number
- CN110060674A CN110060674A CN201910201238.3A CN201910201238A CN110060674A CN 110060674 A CN110060674 A CN 110060674A CN 201910201238 A CN201910201238 A CN 201910201238A CN 110060674 A CN110060674 A CN 110060674A
- Authority
- CN
- China
- Prior art keywords
- voice signal
- terminal
- user
- operation information
- instruction
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/16—Sound input; Sound output
- G06F3/167—Audio in a user interface, e.g. using voice commands for navigating, audio feedback
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/08—Speech classification or search
- G10L15/16—Speech classification or search using artificial neural networks
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/08—Speech classification or search
- G10L15/18—Speech classification or search using natural language modelling
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; 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 OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/223—Execution procedure of a spoken command
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Acoustics & Sound (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The embodiment of the invention discloses a kind of form management method, apparatus, terminal and storage mediums, wherein, method includes, user is received for the voice signal instruction of table input, voice signal instruction is parsed, it obtains voice signal and instructs corresponding operation information, voice signal is obtained in the historical operation record using operation information from user for table and instructs corresponding key message, table is operated according to operation information and key message.By implementing the above method, the phonetic order of user can accurately be identified in conjunction with historical operation record, promote intelligence degree when carrying out voice management to table.
Description
Technical field
The present invention relates to field of computer technology more particularly to a kind of form management method, apparatus, terminal and storage to be situated between
Matter.
Background technique
As voice technology is more and more mature, user, which can be used voice and carry out office software, to be operated, if user is defeated
After entering voice messaging, the voice messaging received is parsed in terminal (mobile phone, computer, tablet computer etc.), then according to
Corresponding control instruction is searched according to parsing result, and control instruction is acted in software to the operation realized to software.
But existing terminal can only could execute corresponding behaviour when receiving the very voice messaging of standard now
Make, when user input voice messaging and received pronunciation information do not match that when, then terminal can not to user input voice into
Row identification, causes operation that can not execute, and intelligence is poor.
Summary of the invention
The embodiment of the invention provides a kind of form management method, apparatus, terminal and storage mediums, can grasp in conjunction with history
It notes down and the phonetic order of user is accurately identified, promote intelligence degree when carrying out voice management to table.
In a first aspect, the embodiment of the invention provides a kind of form management methods, which comprises
User is received for the voice signal instruction of table input；
Voice signal instruction is parsed, the voice signal is obtained and instructs corresponding operation information；
The voice is obtained in historical operation record using the operation information from the user for the table to believe
Number corresponding key message of instruction；
The table is operated according to the operation information and the key message.
Second aspect, the embodiment of the invention provides a kind of form management device, described device includes:
Receiving module, for receiving user for the voice signal instruction of table input；
Parsing module obtains the voice signal and instructs corresponding behaviour for parsing to voice signal instruction
Make information；
Module is obtained, for obtaining in the historical operation record using the operation information from the user for the table
The voice signal is taken to instruct corresponding key message；
Operation module, for being operated according to the operation information and the key message to the table.
The third aspect the embodiment of the invention provides a kind of terminal, including processor, input equipment, output equipment and is deposited
Reservoir, the processor, input equipment, output equipment and memory are connected with each other, wherein the memory is calculated for storing
Machine program, the computer program include program instruction, and the processor is configured for calling described program instruction, execute the
Method described in one side.
Fourth aspect, the embodiment of the invention provides a kind of computer readable storage mediums, which is characterized in that the calculating
Machine readable storage medium storing program for executing is stored with computer program, and the computer program includes program instruction, and described program instruction, which is worked as, to be located
Reason device makes the processor execute method described in first aspect when executing.
In the embodiment of the present invention, terminal receives user for the voice signal instruction of table input, instructs to voice signal
It is parsed, obtains voice signal and instruct corresponding operation information, terminal is directed to the history of table using operation information from user
Voice signal is obtained in operation note and instructs corresponding key message, and table is grasped according to operation information and key message
Make.By implementing the above method, voice can be identified in conjunction with historical operation record, promote the intelligence of terminal.
Detailed description of the invention
Technical solution in order to illustrate the embodiments of the present invention more clearly, below will be to needed in embodiment description
Attached drawing is briefly described, it should be apparent that, drawings in the following description are some embodiments of the invention, general for this field
For logical technical staff, without creative efforts, it is also possible to obtain other drawings based on these drawings.
Fig. 1 is a kind of flow diagram of form management method provided in an embodiment of the present invention；
Fig. 2 is the flow diagram that a kind of object run type provided in an embodiment of the present invention determines method；
Fig. 3 is the flow diagram that a kind of target operation object provided in an embodiment of the present invention determines method；
Fig. 4 is the flow diagram that a kind of operating result storage destination provided in an embodiment of the present invention determines method；
Fig. 5 is the flow diagram of another form management method provided in an embodiment of the present invention；
Fig. 6 is a kind of structural schematic diagram of form management device provided in an embodiment of the present invention；
Fig. 7 is a kind of structural schematic diagram of terminal provided in an embodiment of the present invention.
Specific embodiment
Currently, voice technology is more and more mature, voice-based service is more and more, and user can not only use intelligent sound box
The internet of things equipment of family is controlled, can be made a phone call with the voice assistant of using terminal application, use software etc..User
After input voice information, the voice messaging that software can input user is parsed, and then searches control instruction, realizes phase
Answer function.However, existing voice assistant can only be operated with the control language of very standard now, when the voice of user's input
When mismatching with received pronunciation, terminal can not then wish user that the operation executed identifies, intelligence is poor.
Based on foregoing description, the embodiment of the present invention provides a kind of form management method, specifically includes the following steps: 1. terminal
User is received for the voice signal instruction of table input.Specifically, user can open voice after opening spreadsheet
Input pattern, and corresponding voice signal instruction is inputted, terminal receives the voice signal instruction that user inputs.2. terminal
The voice signal instruction received is parsed, voice signal is obtained and instructs corresponding operation information.Wherein, operation information packet
Include one of object run type, target operation object and operating result storage destination or a variety of.Terminal parses operation
After information, it can be determined that whether directly corresponding operation can be executed according to operation information, if so, terminal obtains user's
Operating right, if the operating right of user reaches the corresponding operating right of operation information, it is corresponding that terminal executes operation information
Operation, and terminate this process.If it is not, then being obtained in historical operation record of the terminal execution using operation information from user for table
The step of taking voice signal to instruct corresponding key message.3. terminal is directed to the historical operation of table using operation information from user
Voice signal is obtained in record instructs corresponding key message.Wherein, key message includes object run type, object run pair
As with operating result storage one of destination or a variety of.Specifically, terminal determination can not be executed directly according to operation information
After corresponding operating, the essential elements lacked in key message, and necessity member that will lack will be searched in historical operation record
Element is used as key message, for example, including target operation object in operation information, then the essential elements lacked in operation information is mesh
Action type is marked, alternatively, including object run type in operation information, then the essential elements lacked in operation information is target behaviour
Make object.4. terminal operates table according to operation information and key message, in the specific implementation, the available use of terminal
The corresponding operating right of operating right and operation information and key message at family, if the operating right of user reaches operation letter
Corresponding operating right is ceased, then terminal executes operation information and the corresponding operation of key message.5. terminal, which updates user, is directed to table
The historical operation record of lattice, and traced to the source using historical operation record after update table progress reduction treatment and problem.
It should be noted that form management method provided by the invention can be applied in terminal, terminal includes that hand is mechanical, electrical
Brain, tablet computer etc., in a kind of implement scene, user can open table class application software (such as EXCEL) in mobile phone, so
Afterwards input speech signal instruct, terminal receive voice signal instruction after instructed according to voice signal in content-control table
Lattice class application software executes corresponding operation.For example, input " draws histogram according to the third line data after user opens EXCEL
The voice signal instruction of figure ", then control EXCEL is drawn the corresponding histogram of the third line data after receiving the instruction by terminal
Figure, and shown in EXCEL, further, user can also continue to input " data of fourth line are also ", then terminal will
It controls EXCEL and draws the corresponding histogram of fourth line data.By the above-mentioned means, greatly simplifying user on mobile phone to table
The operating process of lattice.
In summary, form management method provided in an embodiment of the present invention at least has following advantages:
(1) user is recorded for the operation of table, in order to trace to the source table progress reduction treatment and problem.
(2) it combines historical operation record to parse the voice signal instruction that user provides, promotes the intelligence of terminal.(3) it is directed to
Table provides voice operating mode, reduces the operation difficulty of user.
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
It referring to Figure 1, is a kind of flow diagram of form management method provided in an embodiment of the present invention, in the present embodiment
Form management method may include:
S101, terminal receive user for the voice signal instruction of table input.
In the embodiment of the present invention, user can input corresponding voice signal and refer to after opening table (such as EXECL) software
Enable, the voice signal instruction that terminal input user receives, wherein voice signal instruct in include content specifically can be with
For " calculate tertial mean value and be stored in E3 ", " being switched to table 2 ", " opening table two " etc..
S102, terminal parse voice signal instruction, obtain voice signal and instruct corresponding operation information.
It, will be to the voice received after terminal receives the voice signal instruction of user's input in the embodiment of the present invention
Signal instruction is parsed, and is obtained voice signal and is instructed corresponding operation information, wherein operation information includes object run class
One of type, target operation object and operating result storage destination are a variety of.Object run type is specifically as follows mean value
It calculates type, switching type, addition type, delete type etc., target operation object is specifically as follows to be needed to operate in table
Data, operating result storage destination are specifically as follows operation and execute the corresponding storage position of operating result for completing to obtain later
It sets, such as E3, F4.
The voice signal instruction that end-on receives is parsed after obtaining corresponding operation information, and will judge whether can
Directly to execute corresponding operation according to operation information, if so, terminal obtains the operating right of user, if the operating rights of user
Limit reaches the corresponding operating right of operation information, then terminal executes the corresponding operation of operation information, it should be noted that if terminal
Corresponding operation directly can be executed according to operation information, then include at least object run type in the operation information and target is grasped
Make object, for example, the voice signal instruction that terminal receives is " deleting the data in E3 ", then terminal instructs the voice signal
Object run type is obtained after being parsed to delete type, target operation object is the data in E3, and terminal obtains above-mentioned behaviour
After making information, by the corresponding operation of target operation object performance objective action type in table, that is, the data in E3 are deleted.
It optionally, include that object run type, target operation object and operating result store destination in operation information, for example, terminal
The voice signal instruction received is " mean value for calculating the data in the third line is stored in E3 ", then terminal refers to the voice signal
Order obtains object run type after being parsed be mean value computation type, and target operation object is the data in the third line, operation
As a result storage destination is E3, after terminal obtains aforesaid operations information, will be grasped to the target operation object performance objective in table
Make the corresponding operation of type, and operating result is stored into operating result storage destination, i.e., terminal calculates in the third line
The mean value being calculated simultaneously is stored in E3 by the mean value of data.After terminal executes corresponding operating, this process will be terminated.
In one implementation, after the voice signal instruction that end-on receives is parsed, terminal can not be direct
Corresponding operation is executed according to the operation information that parsing obtains, for example, the voice signal instruction of user's input is " in fourth line
Data are also ", then it is the number in fourth line that terminal, which can only obtain target operation object, after parsing to voice signal instruction
According to lacking object run type, then terminal can not be directly according to above-mentioned voice signal instruction execution corresponding operation, and terminal will be held
Row step S103.
S103, terminal obtain voice signal instruction pair in the historical operation record using operation information from user for table
The key message answered.
In the embodiment of the present invention, key message includes object run type, target operation object and operating result storage mesh
One of ground or a variety of, be specifically as follows the essential elements lacked in operation information.Optionally, if including in operation information
Target operation object, the then essential elements lacked in operation information are object run type.If including that target is grasped in operation information
Make type, then the essential elements lacked in operation information is target operation object.
In the specific implementation, obtaining voice signal in historical operation record of the terminal using operation information from user for table
Instructing corresponding key message concrete mode can be that terminal gets the essential elements lacked from operation information, and inquires
The user is directed to the historical operation record of table input, gets object run type or target from historical operation record
Operation object.Wherein, historical operation record is specifically as follows the record of the preceding once-through operation of this operation, and terminal is by historical operation
The essential elements recorded in record instructs corresponding key message as the voice signal.It should be noted that user is directed to table
The historical operation record of lattice can be voice operating record, be also possible to non-voice operation note.
For example, the voice signal instruction of user's input is " data of fourth line are also ", then terminal believes the voice
Number instruction parsed after can only obtain target operation object be fourth line in data, the essential elements lacked be target grasp
Make type, terminal is to obtain historical operation record.Assuming that historical operation record record is in the data for mark the third line
Maximum value marks maximum value this operation in the data of the third line specifically to can be user and passes through input speech trigger,
It can be user and pass through conventional input mode (such as mouse click, keyboard input etc.) triggering, corresponding historical operation class
Type is to mark maximum Value Types, and historical operation object is the data in the third line, then terminal will mark maximum Value Types to be determined as
Key message.
S104, terminal operate table according to operation information and key message.
It, will be according to operation information and crucial letter after terminal obtains operation information and key message in the embodiment of the present invention
Breath operates table.Optionally, operation information is object run type, and key message is target operation object, then terminal
To the corresponding operation of target operation object performance objective action type in table.Optionally, operation information is object run pair
As key message is object run type, then terminal is corresponding to the target operation object performance objective action type in table
Operation.It optionally, can also include that operating result stores destination in operation information, then terminal is to the object run pair in table
As the corresponding operation of performance objective action type, and the operating result obtained after operation is stored to operating result and stores destination
In.Further, terminal stores the operating result obtained after operation to before operating result storage destination, it is also necessary to judge
Whether storage condition is met, if satisfied, then terminal stores operating result to operating result storage destination, if not satisfied, then
Terminal issues the user with prompt information.Include in the prompt information determine storage option and abandon storage option, terminal according to
The selection result of user determines whether to store operating result into operating result storage destination.For example, operation information and pass
The corresponding operation of key information is " calculate tertial mean value and be stored in E3 ", if table E3 is sky, terminal directly deposits it
It puts, if data with existing in table E3, terminal issue the user with prompt information, asks the user whether to determine storage, specifically may be used
To be voice prompting, it is also possible to show in the form of pop-up, finally result executes corresponding operation to terminal according to the user's choice.
Further, after terminal has executed corresponding operation, the operation of execution will be recorded.
In the embodiment of the present invention, terminal receives user for the voice signal instruction of table input, instructs to voice signal
It is parsed, obtains voice signal and instruct corresponding operation information, be directed to the historical operation of table from user using operation information
Voice signal is obtained in record and instructs corresponding key message, and table is operated according to operation information and key message.
By implementing the above method, the phonetic order of user can accurately be identified in conjunction with historical operation record, be promoted to table
Lattice carry out intelligence degree when voice management, even if the phonetic order of the criteria of right and wrong of user's input, can also anticipate to user
Figure is accurately identified, voice operating threshold when form management is reduced.
Fig. 2 is referred to, the flow diagram of method, this reality are determined for object run type in step S102 shown in FIG. 1
It applies object run type in example and determines that method may include:
S201, terminal parse the keyword determined in voice signal instruction by carrying out to voice signal instruction.
It, will be by voice signal after terminal receives the voice signal instruction of user's input in the embodiment of the present invention
Instruction carries out parsing the keyword determined in voice signal instruction, specifically, voice signal instruction is converted to text by terminal
Information, and word segmentation processing is carried out to text information, obtain the keyword in voice signal instruction.For example, the voice of user's input
Information command is " being switched to table 2 ", then corresponding keyword is " being switched to " and " table 2 ".
S202, terminal determine voice signal instruction corresponding with the corresponding relationship of action type according to preset keyword
One action type.
In the embodiment of the present invention, the corresponding relationship between keyword and action type can be preset by research staff,
And it is stored in database profession, wherein different keywords can correspond to same action type, for example, keyword " mean value meter
Calculation " and the corresponding action type of keyword " calculating average value " are all mean value computation type.Keyword " being switched to table 2 " and key
The corresponding action type of word " opening table 2 " is all switching type.It, can after terminal gets the keyword in voice signal instruction
To search the corresponding action type of the keyword in the database, and the corresponding action type of the keyword found is determined
Corresponding first action type is instructed for voice signal.
S203, terminal determine that voice signal instructs corresponding second action type according to similarity model, and according to point
Class model determines that voice signal instructs corresponding third action type.
In the embodiment of the present invention, similarity model is specifically used for the voice signal instruction and default language that computing terminal receives
Similarity between sound signal instruction, wherein each default voice signal instruction has corresponded to an action type, corresponding relationship
It can be preset by research staff.Terminal calculates between the voice signal instruction received and each default voice signal instruction
Similarity, and instruct corresponding action type to be determined as voice signal instruction the highest default voice signal of similarity and correspond to
The second action type.Wherein, similarity model can be keyword weight computational algorithm (term frequency-inverse
Document frequency, tf-idf) model, latent semantic indexing (Latent Semantic Indexing, LSI)
Model, editing distance model etc., the present invention is it is not limited here.In one implementation, the specific calculation of similarity
Or terminal calculates the quantity of the identical characters between voice signal instruction and the instruction of default voice signal, and will be identical
Ratio in quantity and the voice signal instruction of character between the total quantity of character is determined as voice signal instruction and default voice
Similarity between signal instruction.
Further, terminal will also determine that voice signal instructs corresponding third action type according to disaggregated model, wherein
The method used in disaggregated model be specifically as follows based on convolutional neural networks (Convolutional Neural Networks,
CNN method) is based on two-way long short-term memory Recognition with Recurrent Neural Network (bi-directional long-short-term-
Memory recurrent-neural-network, Bi-LSTM-RNN) method, based on circulation physical network (Recurrent
Entity Network, EntNet) method, be based on stratification attention mechanism network (Hierarchical Attention
Networks, HAN) method, based on dynamic memory network (Dynamic Memory Networks, DMN) method, be based on
The method of Fast Text Classification device (FastText), or the combination of above a variety of methods.Terminal is docked by using disaggregated model
The voice signal instruction received is handled, and voice signal can be obtained and instruct corresponding third action type.
S204, terminal are based on the first default decision rule and operate class from the first action type, the second action type and third
Object run type is determined in type, and instructs corresponding operation information for object run type as voice signal.
In the embodiment of the present invention, terminal obtain in different ways voice signal instruct corresponding first action type,
After second action type and third action type, it will be operated based on the first default decision rule from the first action type, second
Object run type is determined in type and third action type.Specifically, terminal detects the first action type, the second operation class
Identical action type whether is contained at least two in type and third action type；If comprising identical action type is true
It is set to object run type.For example, the first action type is mean value computation type, the second action type is mean value computation type,
Third action type is that maximizing type, then the first action type and the second action type are two identical action types,
Mean value computation type is determined as object run type by terminal.Optionally, if the first action type, the second action type and third
It is all different in action type, then terminal determines that being unable to get voice signal instructs corresponding object run type.Specific implementation
In, if terminal has obtained voice signal and instructed corresponding object run type, terminal determines obtained object run type
Corresponding operation information is instructed for voice signal.
Traditional scheme is according only to Keywords matching, if can not be matched from database effectively according to user voice signal
Keyword can not then determine object run type, and in the embodiment of the present invention, and terminal is according to pair of keyword and action type
It should be related to that determining voice signal instructs corresponding first action type, determine that voice signal instruction is corresponding according to similarity model
Second action type, and determine that voice signal instructs corresponding third action type according to disaggregated model, and pre- based on first
If decision rule determines object run type from the first action type, the second action type and third action type, pass through
Aforesaid way, can be more accurate determine object run type, improve the intelligence of terminal.
Fig. 3 is referred to, is the flow diagram of the determination method of target operation object in step S102 shown in FIG. 1, this
The determination method of target operation object may include: in embodiment
S301, terminal parse the keyword determined in voice signal instruction by carrying out to voice signal instruction.
It, will be by voice signal after terminal receives the voice signal instruction of user's input in the embodiment of the present invention
Instruction carries out parsing the keyword determined in voice signal instruction, specifically, voice signal instruction is converted to text by terminal
Information, and word segmentation processing is carried out to text information, obtain the keyword in voice signal instruction.
S302, terminal determine voice signal instruction corresponding with the corresponding relationship of operation object according to preset keyword
One operation object.
In the embodiment of the present invention, the corresponding relationship between keyword and operation object can be preset by research staff,
And it is stored in database profession, wherein different keywords can correspond to same operation object, for example, keyword is " in the third line
Data " and the corresponding operation object of keyword " the third line value " be all the data in the third line.Terminal gets voice signal
After keyword in instruction, the corresponding operation object of the keyword can be searched, and by the corresponding behaviour of the keyword found
It is determined as the voice signal as object and instructs corresponding first operation object.
S303, terminal determine that voice signal instructs corresponding second operand according to semantic dependency analysis method, and
Determine that voice signal instructs corresponding third operation object according to interdependent syntactic analysis method.
In the embodiment of the present invention, in the embodiment of the present invention, terminal can carry out semantic dependency point by deep learning library
Analysis obtains the semantic dependent tree of sentence in the voice signal instruction of user's input, then obtains the second operation pair by grammer logic
As.
Further, terminal can also carry out interdependent syntactic analysis by deep learning library, obtain the voice of user's input
The syntax dependency tree of sentence in signal instruction, then third operation object is obtained by syntax logic.For example, voice signal instruction is
" seeking tertial maximum value " " is asked " in the instruction and the relationship of " value " is guest's relationship, " column " and " value " be surely in relationship,
" third " and " column " is also relationship in fixed, by the structure of these syntax trees, can analyze to obtain third operation object to be " third
Column ".
S304, terminal are based on the second default decision rule from the operation pair of the first operation object, second operand and third
Target operation object is determined as in, and instructs corresponding operation information for target operation object as voice signal.
In the embodiment of the present invention, terminal obtain in different ways voice signal instruct corresponding first operation object,
After second operand and third operation object, it will be operated based on the second default decision rule from the first operation object, second
Target operation object is determined in object and third operation object.Specifically, terminal detects the first operation object, the second operation pair
As with whether contain at least two identical operation object in third operation object, if comprising identical operation object is true
It is set to target operation object.For example, the first operation object is " table 2 ", second operand is " table 2 ", and third operation object is
" table 3 ", then the first operation object and second operand are two identical operation objects, and " table 2 " is determined as target by terminal
Operation object.Optionally, if the first operation object, second operand and third operation object are all different, terminal is determined
It is unable to get voice signal and instructs corresponding target operation object.In the specific implementation, if terminal has obtained voice signal instruction pair
The target operation object answered, then obtained target operation object is determined as the corresponding operation information of voice signal instruction by terminal.
In the embodiment of the present invention, terminal determines that voice signal instruction is corresponding with the corresponding relationship of operation object according to keyword
The first operation object, determine that voice signal instructs corresponding second operand, Yi Jigen according to semantic dependency analysis method
Determine that voice signal instructs corresponding third operation object according to interdependent syntactic analysis method, and based on the second default decision rule from
Target operation object is determined in first operation object, second operand and third operation object, by the above-mentioned means, can be with
More accurate determines object run type, improves the intelligence of terminal.
Fig. 4 is referred to, is the flow chart for the determination method that operating result stores destination in step S102 shown in FIG. 1,
The determination method of operating result storage destination may include: in the present embodiment
S401, terminal parse the keyword determined in voice signal instruction by carrying out to voice signal instruction.
S402, terminal determine that voice signal instruction is corresponding with the corresponding relationship of storage destination according to preset keyword
First storage destination.
S403, terminal determine voice signal instruction corresponding second storage destination according to semantic dependency analysis method, with
And determine that voice signal instructs corresponding third to store destination according to interdependent syntactic analysis method.
S404, terminal are based on the default decision rule of third and deposit from the first storage destination, the second storage destination and third
It puts and determines that operating result stores destination in destination, and operating result storage destination is instructed as voice signal and is corresponded to
Operation information.
In the embodiment of the present invention, the first storage of terminal detection destination, the second storage destination and third store destination
In whether contain at least two identical storage destination, if comprising identical storage destination is determined as operating result
Store destination.
In the embodiment of the present invention, terminal determines voice signal instruction pair according to the corresponding relationship of keyword and storage destination
The the first storage destination answered determines voice signal instruction corresponding second storage destination according to semantic dependency analysis method,
And determine that voice signal instructs corresponding third to store destination according to interdependent syntactic analysis method, and preset certainly based on second
Plan rule determines that operating result stores purpose from the first storage destination, the second storage destination and third storage destination
Ground, by the above-mentioned means, can be more accurate determine operating result store destination, improve the intelligence of terminal.
Fig. 5 is referred to, is a kind of flow diagram of form management method provided in an embodiment of the present invention, in the present embodiment
Form management method may include:
S501, terminal receive user for the voice signal instruction of table input.
S502, terminal parse voice signal instruction, obtain voice signal and instruct corresponding operation information.
S503, terminal obtain voice signal instruction pair in the historical operation record using operation information from user for table
The key message answered.
S504, terminal obtain needed for the first operating right and operation information and the corresponding operation of key message of user
The second operating right.
In the embodiment of the present invention, the first operating right or the second operating right are specifically as follows read-only authority, access limit
Deng in the specific implementation, the method for determination of the first operating right is specifically as follows, user pre-enters when opening spreadsheet and tests
Information is demonstrate,proved, terminal determines the user's according to the corresponding relationship of the verification information and verification information and operating right that receive
First operating right, wherein verification information can be account, password, fingerprint, vocal print etc..The method of determination of second operating right
It is specifically as follows, terminal determines the operation information and the corresponding object run of key message that parsing obtains, and according to object run
The second operating right is determined with the corresponding relationship of operating right.
If S505, the first operating right reach the second operating right, terminal is according to operation information and key message to table
Lattice are operated.
In the embodiment of the present invention, terminal gets the first operating right and operation information and key message pair of user
After second operating right needed for the operation answered, it will test whether the first operating right reaches the second operating right, if reaching,
Then terminal operates table according to operation information and key message.If not up to, terminal can export operation failure
Dialog box.In the specific implementation, the first operating right necessarily reaches if the first operating right is the access limit for entire table
To the second operating right, if the first operating right is the access limit of partial content in table, when the second operating right is also
For when the access limit of the contents of the section, the first operating right reaches the second operating right in table.If the first operating right
Read-only authority, then when the second operating right read-only authority, the first operating right reaches the second operating right.
It should be noted that during terminal operates table according to operation information and key message, if eventually
End detects that object run type is specified type, such as draws or calculate type, terminal may further be to object run pair
As the data for being included are analyzed, data type is obtained, during terminal executes corresponding operating, combined data type is carried out
Operation, obtains corresponding operation result.Such as: terminal needs the data creating chart to a certain column, if the column data type
It is percentage, then after terminal executes operation information and the corresponding operation of key message, obtained operating result is exactly to obtain pie
Figure.
S506, terminal update the historical operation record that user is directed to table, and using updated user for table
Historical operation record carries out reduction treatment to table and/or problem is traced to the source.
It, will be based on this after terminal operates table according to operation information and key message in the embodiment of the present invention
Secondary operation updates the historical operation record that user is directed to table, when needing to carry out table subsequent audit or to check each user's
When operation history, terminal can use updated user for table historical operation record to table carry out reduction treatment and
Problem is traced to the source.Wherein, reduction treatment is some step that content in table is restored in user operation process by terminal, problem
It traces to the source i.e. when the data in table are distorted, terminal determines the body for distorting the user of the table according to historical operation record
Part.It should be noted that user can also operate table using non-voice mode, terminal also can operation to user into
Row record.
In the embodiment of the present invention, user operates table by voice, reduces the operation difficulty of user, also,
Terminal provides the function traced to the source table progress reduction treatment and problem by recording user for the operation of table
Can, further, terminal combination historical operation record parses the voice signal instruction that user provides, and improves voice knowledge
Other accuracy, so that terminal is more intelligent.
It describes in detail below in conjunction with attached drawing 6 to form management device provided in an embodiment of the present invention.It needs to illustrate
, attached form management device shown in fig. 6, the method for executing Fig. 1-embodiment illustrated in fig. 5 of the present invention, for the ease of saying
Bright, only parts related to embodiments of the present invention are shown, disclosed by specific technical details, through referring to Fig. 1-5 institute of the present invention
The embodiment shown.
Fig. 6 is referred to, is a kind of structural schematic diagram of form management device provided by the invention, the form management device 60
Can include: receiving module 601, obtains module 603, operation module 604 at parsing module 602.
Receiving module 601, for receiving user for the voice signal instruction of table input；
It is corresponding to obtain the voice signal instruction for parsing to voice signal instruction for parsing module 602
Operation information；
Module 603 is obtained, for being directed to the historical operation record of the table from the user using the operation information
It is middle to obtain the corresponding key message of the voice signal instruction；
Operation module 604, for being operated according to the operation information and the key message to the table.
In one implementation, the operation information includes object run type, target operation object and operating result
Store one of destination or a variety of；
The key message includes one of object run type, target operation object and operating result storage destination
Or it is a variety of.
In one implementation, the operation module 604, is specifically used for:
The corresponding operation of the object run type is executed to the target operation object in the table.
In one implementation, the parsing module 602, is specifically used for:
By carrying out parsing the keyword determined in the voice signal instruction to voice signal instruction；
Determine that the voice signal instruction corresponding first is grasped with the corresponding relationship of action type according to preset keyword
Make type；
Determine that the voice signal instructs corresponding second action type according to similarity model, and according to disaggregated model
Determine that the voice signal instructs corresponding third action type；
It is operated based on the first default decision rule from first action type, second action type and the third
The object run type is determined in type, and instructs corresponding behaviour for the object run type as the voice signal
Make information.
In one implementation, the parsing module 602, is also used to:
By carrying out parsing the keyword determined in the voice signal instruction to voice signal instruction；
Determine that the voice signal instruction corresponding first is grasped with the corresponding relationship of operation object according to preset keyword
Make object；
Determine that the voice signal instructs corresponding second operand according to semantic dependency analysis method, and according to according to
It deposits syntactic analysis method and determines that the voice signal instructs corresponding third operation object；
It is operated based on the second default decision rule from first operation object, the second operand and the third
The target operation object is determined in object, and instructs corresponding behaviour for the target operation object as the voice signal
Make information.
In one implementation, the acquisition module 603, is specifically used for:
Obtain the first operating right and the operation information and the corresponding operation institute of the key message of the user
The second operating right needed；
Detect whether first operating right reaches second operating right；
If so, executing the step operated according to the operation information and the key message to the table
Suddenly.
In one implementation, the operation module 604, is also used to:
Update the historical operation record that the user is directed to the table；
Reduction treatment is carried out to the table for the historical operation record of the table using the updated user
And/or problem is traced to the source.
In the embodiment of the present invention, receiving module 601 receives user for the voice signal instruction of table input, parsing module
602 pairs of voice signal instructions parse, and obtain voice signal and instruct corresponding operation information, obtain module 603 using operation
Information obtains the voice signal and instructs corresponding key message, operation module in the historical operation record from user for table
604 operate table according to operation information and key message.By implementing the above method, historical operation record can be combined
The phonetic order of user is accurately identified, intelligence degree when carrying out voice management to table is promoted.
Fig. 7 is referred to, is a kind of structural schematic diagram of terminal provided in an embodiment of the present invention.As shown in fig. 7, the terminal packet
It includes: at least one processor 701, input equipment 703, output equipment 704, memory 705, at least one communication bus 702.Its
In, communication bus 702 is for realizing the connection communication between these components.Wherein, input equipment 703 can be control panel or
Person's microphone etc., output equipment 704 can be display screen etc..Wherein, memory 705 can be high speed RAM memory, can also be with
It is non-labile memory (non-volatile memory), for example, at least a magnetic disk storage.Memory 705 is optional
Can also be that at least one is located remotely from the storage device of aforementioned processor 701.Wherein processor 701 can combine Fig. 6 institute
The device of description, batch processing code, and processor 701, input equipment 703 are stored in memory 705, and output equipment 704 is adjusted
With the program code stored in memory 705, for performing the following operations:
Input equipment 703, for receiving user for the voice signal instruction of table input；
Processor 701 obtains the voice signal and instructs corresponding behaviour for parsing to voice signal instruction
Make information；
Processor 701, in the historical operation record using the operation information from the user for the table
It obtains the voice signal and instructs corresponding key message；
Processor 701, for being operated according to the operation information and the key message to the table
In one implementation, the operation information includes object run type, target operation object and operating result
Store one of destination or a variety of；
The key message includes one of object run type, target operation object and operating result storage destination
Or it is a variety of.
In one implementation, processor 701 are also used to execute institute to the target operation object in the table
State the corresponding operation of object run type.
In one implementation, processor 701 are specifically used for:
By carrying out parsing the keyword determined in the voice signal instruction to voice signal instruction；
Determine that the voice signal instruction corresponding first is grasped with the corresponding relationship of action type according to preset keyword
Make type；
Determine that the voice signal instructs corresponding second action type according to similarity model, and according to disaggregated model
Determine that the voice signal instructs corresponding third action type；
It is operated based on the first default decision rule from first action type, second action type and the third
The object run type is determined in type, and instructs corresponding behaviour for the object run type as the voice signal
Make information.
In one implementation, processor 701 are specifically used for:
By carrying out parsing the keyword determined in the voice signal instruction to voice signal instruction；
Determine that the voice signal instruction corresponding first is grasped with the corresponding relationship of operation object according to preset keyword
Make object；
Determine that the voice signal instructs corresponding second operand according to semantic dependency analysis method, and according to according to
It deposits syntactic analysis method and determines that the voice signal instructs corresponding third operation object；
It is operated based on the second default decision rule from first operation object, the second operand and the third
The target operation object is determined in object, and instructs corresponding behaviour for the target operation object as the voice signal
Make information.
In one implementation, processor 701 are specifically used for:
Obtain the first operating right and the operation information and the corresponding operation institute of the key message of the user
The second operating right needed；
Detect whether first operating right reaches second operating right；
If so, executing the step operated according to the operation information and the key message to the table
Suddenly.
In one implementation, processor 701 are specifically used for:
Update the historical operation record that the user is directed to the table；
Reduction treatment is carried out to the table for the historical operation record of the table using the updated user
And/or problem is traced to the source.
In the embodiment of the present invention, input equipment 703 receives user for the voice signal instruction of table input, processor
701 pairs of voice signal instructions parse, and obtain voice signal and instruct corresponding operation information, processor 701 utilizes operation letter
It ceases and obtains the corresponding key message of voice signal instruction in the historical operation record from user for table, and according to operation information
Table is operated with key message.By implementing the above method, the voice of user can be referred in conjunction with historical operation record
Order is accurately identified, intelligence degree when carrying out voice management to table is promoted.
Module described in the embodiment of the present invention can pass through universal integrated circuit, such as CPU (Central
Processing Unit, central processing unit), or pass through ASIC (Application Specific Integrated
Circuit, specific integrated circuit) Lai Shixian.
It should be appreciated that in embodiments of the present invention, alleged processor 701 can be central processing module (Central
Processing Unit, CPU), which can also be other general processors, digital signal processor (Digital
Signal Processor, DSP), specific integrated circuit (Application Specific Integrated Circuit,
ASIC), ready-made programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic
Device, discrete gate or transistor logic, discrete hardware components etc..General processor can be microprocessor or this at
Reason device is also possible to any conventional processor etc..
It is total that bus 702 can be industry standard architecture (Industry Standard Architecture, ISA)
Line, Peripheral Component Interconnect (Peripheral Component, PCI) bus or extended industry-standard architecture (Extended
Industry Standard Architecture, EISA) bus etc., it is total which can be divided into address bus, data
Line, control bus etc., for convenient for indicating, Fig. 7 is only indicated with a thick line, it is not intended that an only bus or a seed type
Bus.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the program can be stored in computer readable storage medium,
The program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein, the computer readable storage medium
It can be magnetic disk, CD, read-only memory (Read-Only Memory, ROM) or random access memory (Random
Access Memory, RAM) etc..
The above disclosure is only the preferred embodiments of the present invention, cannot limit the right model of the present invention with this certainly
It encloses, therefore equivalent changes made in accordance with the claims of the present invention, is still within the scope of the present invention.
Claims (10)
1. a kind of form management method, which is characterized in that the described method includes:
User is received for the voice signal instruction of table input；
Voice signal instruction is parsed, the voice signal is obtained and instructs corresponding operation information；
The voice signal is obtained in historical operation record using the operation information from the user for the table to refer to
Enable corresponding key message；
The table is operated according to the operation information and the key message.
2. the method according to claim 1, wherein the operation information includes object run type, target behaviour
Make one of object and operating result storage destination or a variety of；
The key message includes one of object run type, target operation object and operating result storage destination or more
Kind.
3. according to the method described in claim 2, it is characterized in that, described according to the operation information and the key message pair
The table is operated, comprising:
The corresponding operation of the object run type is executed to the target operation object in the table.
4. according to the method described in claim 2, it is characterized in that, it is described to the voice signal instruction parse, obtain
The voice signal instructs corresponding operation information, comprising:
By carrying out parsing the keyword determined in the voice signal instruction to voice signal instruction；
Determine that the voice signal instruction corresponding first operates class with the corresponding relationship of action type according to preset keyword
Type；
It determines that the voice signal instructs corresponding second action type according to similarity model, and is determined according to disaggregated model
The voice signal instructs corresponding third action type；
Based on the first default decision rule from first action type, second action type and the third action type
In determine the object run type, and instruct corresponding operation letter for the object run type as the voice signal
Breath.
5. according to the method described in claim 2, it is characterized in that, it is described to the voice signal instruction parse, obtain
The voice signal instructs corresponding operation information, comprising:
By carrying out parsing the keyword determined in the voice signal instruction to voice signal instruction；
Corresponding first operation pair of the voice signal instruction is determined according to preset keyword and the corresponding relationship of operation object
As；
Determine that the voice signal instructs corresponding second operand according to semantic dependency analysis method, and according to interdependent sentence
Method analysis method determines that the voice signal instructs corresponding third operation object；
Based on the second default decision rule from first operation object, the second operand and the third operation object
In determine the target operation object, and instruct corresponding operation letter for the target operation object as the voice signal
Breath.
6. the method according to claim 1, wherein described according to the operation information and the key message pair
Before the table is operated, the method also includes:
It obtains needed for the first operating right and the operation information and the corresponding operation of the key message of the user
Second operating right；
Detect whether first operating right reaches second operating right；
If so, executing described the step of operating according to the operation information and the key message to the table.
7. the method according to claim 1, wherein described according to the operation information and the key message pair
After the table is operated, the method also includes:
Update the historical operation record that the user is directed to the table；
Using the updated user for the table historical operation record to the table carry out reduction treatment and/or
Problem is traced to the source.
8. a kind of form management device, which is characterized in that described device includes:
Receiving module, for receiving user for the voice signal instruction of table input；
Parsing module obtains the voice signal and instructs corresponding operation letter for parsing to voice signal instruction
Breath；
Module is obtained, for obtaining institute in the historical operation record using the operation information from the user for the table
Predicate sound signal instructs corresponding key message；
Operation module, for being operated according to the operation information and the key message to the table.
9. a kind of terminal, which is characterized in that the processor, defeated including processor, input equipment, output equipment and memory
Enter equipment, output equipment and memory to be connected with each other, wherein the memory is for storing computer program, the computer
Program includes program instruction, and the processor is configured for calling described program instruction, is executed such as any one of claim 1-7
The method.
10. a kind of computer readable storage medium, which is characterized in that the computer-readable recording medium storage has computer journey
Sequence, the computer program include program instruction, and described program instruction executes the processor such as
The described in any item methods of claim 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910201238.3A CN110060674B (en) | 2019-03-15 | 2019-03-15 | Table management method, device, terminal and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910201238.3A CN110060674B (en) | 2019-03-15 | 2019-03-15 | Table management method, device, terminal and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110060674A true CN110060674A (en) | 2019-07-26 |
| CN110060674B CN110060674B (en) | 2022-02-01 |
Family
ID=67317068
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910201238.3A Active CN110060674B (en) | 2019-03-15 | 2019-03-15 | Table management method, device, terminal and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110060674B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111897511A (en) * | 2020-07-31 | 2020-11-06 | 科大讯飞股份有限公司 | Voice drawing method, device, equipment and storage medium |
| CN111930776A (en) * | 2020-09-10 | 2020-11-13 | 北京维数统计事务所有限公司 | Form processing method and device, electronic equipment and readable storage medium |
| CN112435667A (en) * | 2020-11-04 | 2021-03-02 | 杭州讯酷科技有限公司 | Method for intelligently constructing system through voice |
| CN112540758A (en) * | 2020-12-08 | 2021-03-23 | 杭州讯酷科技有限公司 | UI intelligent construction method based on voice recognition |
| CN112562651A (en) * | 2020-11-26 | 2021-03-26 | 杭州讯酷科技有限公司 | Method for generating page based on intelligent recognition of keywords of natural language |
| CN113254698A (en) * | 2021-06-23 | 2021-08-13 | 江苏盖睿健康科技有限公司 | Form design method and system with auxiliary filling function |
| CN116049294A (en) * | 2023-03-27 | 2023-05-02 | 北京大学深圳研究生院 | Excel operation method, device, equipment and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006003321A (en) * | 2004-06-21 | 2006-01-05 | Nissan Motor Co Ltd | Information providing system for vehicle |
| CN1766820A (en) * | 2004-08-05 | 2006-05-03 | 安捷伦科技有限公司 | Method of selecting portion of graph, and network analyzing apparatus using the same |
| CN101807399A (en) * | 2010-02-02 | 2010-08-18 | 华为终端有限公司 | Voice recognition method and device |
| CN104571916A (en) * | 2014-12-31 | 2015-04-29 | 广东欧珀移动通信有限公司 | Method and device for executing terminal operating information |
| CN105408890A (en) * | 2013-07-15 | 2016-03-16 | 微软技术许可有限责任公司 | Performing an operation relative to tabular data based upon voice input |
| CN108108094A (en) * | 2017-12-12 | 2018-06-01 | 深圳和而泰数据资源与云技术有限公司 | A kind of information processing method, terminal and computer-readable medium |
| CN108287815A (en) * | 2017-12-29 | 2018-07-17 | 重庆小雨点小额贷款有限公司 | Information input method, device, terminal and computer readable storage medium |
| CN108984510A (en) * | 2018-09-12 | 2018-12-11 | 山西中电科新能源技术有限公司 | By voice by the system of data input table |
-
2019
- 2019-03-15 CN CN201910201238.3A patent/CN110060674B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006003321A (en) * | 2004-06-21 | 2006-01-05 | Nissan Motor Co Ltd | Information providing system for vehicle |
| CN1766820A (en) * | 2004-08-05 | 2006-05-03 | 安捷伦科技有限公司 | Method of selecting portion of graph, and network analyzing apparatus using the same |
| CN101807399A (en) * | 2010-02-02 | 2010-08-18 | 华为终端有限公司 | Voice recognition method and device |
| CN105408890A (en) * | 2013-07-15 | 2016-03-16 | 微软技术许可有限责任公司 | Performing an operation relative to tabular data based upon voice input |
| CN104571916A (en) * | 2014-12-31 | 2015-04-29 | 广东欧珀移动通信有限公司 | Method and device for executing terminal operating information |
| CN108108094A (en) * | 2017-12-12 | 2018-06-01 | 深圳和而泰数据资源与云技术有限公司 | A kind of information processing method, terminal and computer-readable medium |
| CN108287815A (en) * | 2017-12-29 | 2018-07-17 | 重庆小雨点小额贷款有限公司 | Information input method, device, terminal and computer readable storage medium |
| CN108984510A (en) * | 2018-09-12 | 2018-12-11 | 山西中电科新能源技术有限公司 | By voice by the system of data input table |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111897511A (en) * | 2020-07-31 | 2020-11-06 | 科大讯飞股份有限公司 | Voice drawing method, device, equipment and storage medium |
| CN111930776A (en) * | 2020-09-10 | 2020-11-13 | 北京维数统计事务所有限公司 | Form processing method and device, electronic equipment and readable storage medium |
| CN111930776B (en) * | 2020-09-10 | 2021-01-05 | 北京维数统计事务所有限公司 | Form processing method and device, electronic equipment and readable storage medium |
| CN112435667A (en) * | 2020-11-04 | 2021-03-02 | 杭州讯酷科技有限公司 | Method for intelligently constructing system through voice |
| CN112562651A (en) * | 2020-11-26 | 2021-03-26 | 杭州讯酷科技有限公司 | Method for generating page based on intelligent recognition of keywords of natural language |
| CN112540758A (en) * | 2020-12-08 | 2021-03-23 | 杭州讯酷科技有限公司 | UI intelligent construction method based on voice recognition |
| CN113254698A (en) * | 2021-06-23 | 2021-08-13 | 江苏盖睿健康科技有限公司 | Form design method and system with auxiliary filling function |
| CN116049294A (en) * | 2023-03-27 | 2023-05-02 | 北京大学深圳研究生院 | Excel operation method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110060674B (en) | 2022-02-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10540965B2 (en) | Semantic re-ranking of NLU results in conversational dialogue applications | |
| CN110060674A (en) | Form management method, apparatus, terminal and storage medium | |
| US9269354B2 (en) | Semantic re-ranking of NLU results in conversational dialogue applications | |
| US9171542B2 (en) | Anaphora resolution using linguisitic cues, dialogue context, and general knowledge | |
| US9607102B2 (en) | Task switching in dialogue processing | |
| US9361884B2 (en) | Communicating context across different components of multi-modal dialog applications | |
| CN111062217B (en) | Language information processing method and device, storage medium and electronic equipment | |
| CN107330011A (en) | The recognition methods of the name entity of many strategy fusions and device | |
| US10783877B2 (en) | Word clustering and categorization | |
| WO2020038251A1 (en) | Process customizing system and method, and computer readable storage medium | |
| Zhang et al. | Memory-augmented dialogue management for task-oriented dialogue systems | |
| Zamanirad et al. | Programming bots by synthesizing natural language expressions into API invocations | |
| CN111563144A (en) | Statement context prediction-based user intention identification method and device | |
| CN111046667A (en) | Sentence recognition method, sentence recognition device and intelligent equipment | |
| CN109918494A (en) | Context relation based on figure replys generation method, computer and medium | |
| CN116802629A (en) | Multi-factor modeling for natural language processing | |
| CN116583837A (en) | Distance-based LOGIT values for natural language processing | |
| CN116615727A (en) | Keyword data augmentation tool for natural language processing | |
| CN116635862A (en) | Outside domain data augmentation for natural language processing | |
| CN110489730A (en) | Text handling method, device, terminal and storage medium | |
| Stoyanchev et al. | Action state update approach to dialogue management | |
| CN113515616A (en) | Task driving system based on natural language | |
| JP2022076439A (en) | Dialogue management | |
| CN110020429A (en) | Method for recognizing semantics and equipment | |
| CN110287487A (en) | The recognition methods of subject-predicate language, device, equipment and computer readable storage medium |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |