CN109960807A - A kind of intelligent semantic matching process based on context relation - Google Patents
A kind of intelligent semantic matching process based on context relation Download PDFInfo
- Publication number
- CN109960807A CN109960807A CN201910231582.7A CN201910231582A CN109960807A CN 109960807 A CN109960807 A CN 109960807A CN 201910231582 A CN201910231582 A CN 201910231582A CN 109960807 A CN109960807 A CN 109960807A
- Authority
- CN
- China
- Prior art keywords
- data
- sentence
- lteral data
- lteral
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 70
- 230000008569 process Effects 0.000 title claims abstract description 49
- 239000013589 supplement Substances 0.000 claims abstract description 32
- 239000000284 extract Substances 0.000 claims abstract description 14
- 238000012795 verification Methods 0.000 claims description 27
- 238000012545 processing Methods 0.000 claims description 16
- 230000008859 change Effects 0.000 claims description 3
- 238000003780 insertion Methods 0.000 claims description 2
- 230000037431 insertion Effects 0.000 claims description 2
- 230000006870 function Effects 0.000 description 4
- 238000003058 natural language processing Methods 0.000 description 4
- 241001269238 Data Species 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 235000013399 edible fruits Nutrition 0.000 description 2
- 210000003296 saliva Anatomy 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Abstract
The present invention relates to a kind of intelligent semantic matching process based on context relation, which comprises semantic processes system receives phrase data, obtains current statement lteral data；Extract the fixation language information and extensive object information in current statement lteral data；When the fixation language information in current statement lteral data is empty, the fixation language information in upper sentence lteral data is obtained, and generates new sentence lteral data according to the extensive object information in the fixation language information and current statement lteral data in upper sentence lteral data；When the extensive object information in current statement lteral data is empty, boot statement data are generated；The supplement phrase data that user inputs according to boot statement data is received, and extracts the extensive object information in supplement phrase data；New sentence lteral data is generated according to the fixation language information in the extensive object information and current statement lteral data in supplement phrase data；New sentence lteral data is parsed, semantic matches result data is obtained.
Description
Technical field
The present invention relates to technical field of data processing more particularly to a kind of intelligent semantic match parties based on context relation
Method.
Background technique
Natural language processing (Natural Language Processing, NLP) is the most difficult in artificial intelligence asks
One of topic, and be also full of challenges to the research of natural language processing.In general, the natural language of user's input be user according to
What the logic in oneself brain was formed, due to speech habits, language may conceal some key words when being formed.For example,
User inputs " my Pekinese Xiang Cha weather ", then semantic processes system can export corresponding as a result, and working as and using according to the sentence
Family inputs " that day saliva " again, because lacking corresponding subject and predicate in sentence, semantic processes system can not root
According to the purpose that " that day saliva " determines user, cause semantic processes system that can not export corresponding result according to the sentence.Therefore,
How to determine that the semanteme of an incomplete sentence becomes this field to obtain answer corresponding with user's statement semantics
One of difficult point.
Summary of the invention
The purpose of the present invention is in view of the drawbacks of the prior art, provide a kind of intelligent semantic matching based on context relation
Method, in the case where current statement data lack and parse required element, Cong Shangyi sentence lteral data or next statement text
Information corresponding with the current scarce element of institute is extracted in data, and the language of current statement data is determined by way of associated context
Adopted matching result realizes the semanteme for determining incomplete sentence, to obtain answer corresponding with user's statement semantics.
To achieve the above object, the present invention provides a kind of intelligent semantic matching process based on context relation, it is described
Method includes:
Semantic processes system receives phrase data, carries out speech recognition to the phrase data, obtains current statement text
Data；
The extensive processing of clause is carried out to the current statement lteral data, extracts consolidating in the current statement lteral data
Attribute information and extensive object information；
Determine the fixation language information or extensive in the current statement lteral data in the current statement lteral data
Whether object information is empty；
When the fixation language information in the current statement lteral data is empty, consolidating in upper sentence lteral data is obtained
Attribute information, and according to general in the fixation language information and the current statement lteral data in the upper sentence lteral data
Change object information and generates new sentence lteral data；
When the extensive object information in the current statement lteral data is empty, boot statement data are generated, and export；
The supplement phrase data that user inputs according to the boot statement data is received, and extracts the supplement phrase data
In extensive object information；
According to the fixed language in the extensive object information and current statement lteral data in the supplement phrase data
Information generates new sentence lteral data；
The new sentence lteral data is parsed, semantic matches result data is obtained, and exports the semantic matches result
Data.
Preferably, the phrase data includes sentence voice data and sentence lteral data；The semantic processes system connects
Phrase data is received, speech recognition is carried out to the phrase data, obtains current statement lteral data specifically:
The speech convertor of the semantic processes system receives the phrase data, to the sentence language in the phrase data
Sound data are identified, obtain the sentence lteral data of the sentence voice data, and by the sentence of the sentence voice data
Lteral data is inserted into the end of the input rank of the semantic processes system；
The interrogator of the semantic processes system monitors the data insertion of the input rank, obtains from the input rank
The sentence lteral data for taking the input rank end obtains the current statement lteral data.
It is further preferred that the fixation language information in the acquisition in a sentence lteral data specifically:
Upper sentence lteral data is obtained from the input rank；
The extensive processing of clause is carried out to the upper sentence lteral data, extracts consolidating in the upper sentence lteral data
Attribute information.
Preferably, the fixation language information in the acquisition in a sentence lteral data specifically:
From the fixation language information obtained in the buffer in the semantic processes system in upper sentence lteral data.
Preferably, after the fixation language information in the acquisition in a sentence lteral data, the method also includes:
Fixation language information in the upper sentence lteral data is substituted into current statement lteral data to verify；
If verification passes through, according to the fixation language information and current statement text number in the upper sentence lteral data
Extensive object information in generates the new sentence lteral data.
It is further preferred that if verification does not pass through, the method also includes:
Boot statement data are generated, and are exported, input supplement phrase data according to the boot statement data to user.
Preferably, when the extensive object information is empty, in the generation boot statement data, and before output, institute
State method further include:
The extensive object information in upper sentence lteral data is obtained, and according to general in the upper sentence lteral data
The fixation language information changed in object information and the current statement lteral data obtains new sentence lteral data.
It is further preferred that after extensive object information in the acquisition in a sentence lteral data, the method
Further include:
Extensive object information in the upper sentence lteral data is substituted into current statement lteral data to verify；
If verification passes through, according to the extensive object information and current statement text in the upper sentence lteral data
Fixation language information in data generates the new sentence lteral data；
If verification does not pass through, the boot statement data are generated, and export.
Preferably, after the extensive object information extracted in the supplement phrase data, the method also includes:
Extensive object information in the supplement phrase data is substituted into current statement lteral data to verify；
If verification passes through, according to the extensive object information and current statement lteral data in the supplement phrase data
In fixation language information generate the new sentence lteral data；
If verification does not pass through, the boot statement data are generated, and export.
Intelligent semantic matching process provided in an embodiment of the present invention based on context relation, lacks in current statement data
It is extracted in the case where element needed for parsing, in Cong Shangyi sentence lteral data or next statement lteral data and the current scarce element of institute
Corresponding information determines the semantic matches of current statement data as a result, realizing determining residual by way of associated context
The semanteme for lacking sentence, to obtain answer corresponding with user's statement semantics.
Detailed description of the invention
Fig. 1 is the flow chart of the intelligent semantic matching process provided in an embodiment of the present invention based on context relation.
Specific embodiment
Below by drawings and examples, technical scheme of the present invention will be described in further detail.
A kind of intelligent semantic matching process based on context relation provided in an embodiment of the present invention is used for semantic processes system
System is carried out semanteme to the incomplete sentence received and has been mended by the method for associated context, to be finished fruit output phase according to benefit
The statement matching result answered.Its method flow diagram is as shown in Figure 1, include the following steps:
Step 101, phrase data is received, current statement lteral data is obtained；
Specifically, semantic processes system can be understood as one with input by sentence, the system for handling and exporting function.Language
Adopted processing system includes speech convertor, input rank, interrogator, buffer and processor.When the starting of semantic processes system,
The monitor configured in the system output page is activated, which can load the configuration file for voice service, domain
(domain) output statement of class and the corresponding user profile of domain, semantic processes system specific condition, is opened simultaneously
Dynamic speech convertor, input rank, interrogator, buffer and processor.
Phrase data includes sentence voice data and sentence lteral data.That is, user can pass through voice or text
The mode of word is to system read statement data.Speech convertor receives phrase data, to the sentence voice data in phrase data
It is identified, obtains the sentence lteral data of sentence voice data, and by the sentence lteral data of sentence voice data or directly
The sentence lteral data of user's input is inserted into the end of the input rank of semantic processing system.
Interrogator can monitor always whether input rank has new message, that is, monitor whether have sentence lteral data into
Enqueue, and from input rank obtain input rank end sentence lteral data, to obtain current statement lteral data.
Step 102, the extensive processing of clause is carried out to current statement lteral data, extracts the fixation language in sentence lteral data
Information and extensive object information；
Specifically, interrogator sends current statement lteral data after interrogator gets current statement lteral data
To processor.Processor carries out the extensive processing of clause to phrase data according to syntax rule tree, extracts the fixation in phrase data
Language information and extensive object information.The extensive processing of clause is understood that more to be expanded to according to syntax rule tree by a sentence
The expression-form of kind sentence, and extract the process of key element in sentence.In this process, key element in sentence is extracted
Including fixed language information and extensive object information.For example, " I wants to go to " is fixed in the sentence of one " I wants to go to cinema "
Language information, is a part of clause, and " cinema " is extensive object information；For another example, in the sentence of one " I wants to buy film ticket "
In, " I wants to buy " is fixed language information, and " film ticket " is extensive object information.
In a specific example, user has input the sentence voice data of " I wants to go to cinema ", language by voice
Sound converter carries out voice recognition processing to the sentence voice data, has obtained the sentence lteral data of " I wants to go to cinema ".
Then the processor in semantic processes system first recognizes " going ", then recognizes " wanting to go to " further along and then recognizes
The clause of " I wants to go to ... ", and according to the-clause of " wanting to go to "-" I wants to go to " " is gone " in preset syntax rule tree, extract language
Fixation language information " I wants to go to " in sentence data, and the extensive object information of word " cinema " conduct after " I wants to go to ".
It is understood that a sentence lteral data may correspond to a fixed language information and an extensive object letter
Breath, it is also possible to corresponding multiple fixed language information and multiple extensive object informations, but in a normal sentence lteral data, often
A fixed language information should at least be corresponding with an extensive object information.
In some preferred embodiments, what syntax rule tree was also possible to obtain by model training.It is further specific
, the multiple sentence lteral datas of semantic processes system acquisition are as sample, and multiple sentence lteral datas are trained, and obtain sentence
Formula analytic modell analytical model obtains syntax rule tree according to clause analytic modell analytical model, to realize according to syntax rule tree to sentence text number
According to the progress extensive processing of clause.
Step 103, determine whether the fixation language information in current statement lteral data is empty；
Specifically, when in current statement lteral data fixation language information or extensive object information be empty when, illustrate currently
Sentence representated by sentence lteral data is a semantic incomplete sentence, and semantic processes system can not be directly according to current statement
Lteral data obtains the matching result of sentence.For example, a content is the phrase data of " Tianjin ", fixing language information is
Sky, extensive object information are " Tianjin ", another content is the phrase data of " I will book tickets ", and fixing language information is " to order
Ticket ", extensive object information are sky, and in the two sentences, speech processing system can not be directly according to current statement text number
According to its determining semanteme.
Here, the judgement of step 103 and step 105 is respectively to determine that the fixation language information in current statement lteral data is
It is no to be whether the extensive object information in empty step and determining current statement lteral data is empty step, it is possible to understand that
It is that user can according to need the sequencing of setting steps 103 and step 105.
In this step 103, when the fixation language information extracted from current statement data is empty, following step is executed
104；When the fixation language information extracted from current statement data is not sky, then following step 105 is executed, that is, also need
Determine whether the extensive object information in current statement lteral data is empty.
Step 104, the fixation language information in upper sentence lteral data is obtained；
Specifically, being obtained in upper sentence lteral data when the fixation language information in current statement lteral data is empty
The mode of fixation language information may include following two.
In the first way, processor obtains upper sentence lteral data from input rank, then to a upper sentence
Lteral data carries out the extensive processing of clause, extracts the fixation language information in upper sentence lteral data.In the process, due to defeated
The fixation language information in history phrase data is not saved in enqueue, so if needing to obtain in upper sentence lteral data
Fixed language information, then need after getting upper sentence lteral data, then parse to upper sentence lteral data, extracts
Fixation language information in upper sentence lteral data.
In the second way, the fixation language that processor can obtain upper sentence lteral data by cache module is believed
Breath.That is, if necessary to obtain the fixation language information in upper sentence lteral data, then it can be directly from cache module
The fixation language information in upper sentence lteral data is obtained, without parsing to upper sentence lteral data.With
Family can according to need the above two mode of selection.
After performing step 104, following step 107 is needed to be implemented.
Step 105, determine whether the extensive object information in current statement lteral data is empty；
Specifically, if the processor determine that the fixation language information in current statement lteral data is not empty, it is also necessary to really
Determine whether the extensive object information in current statement lteral data is empty.When the fixation language information in current statement lteral data not
For sky, and when the extensive object information extracted in current statement data is empty, following step 106 is executed；When current statement text
Fixation language information in digital data is not empty, and when the extensive object information extracted in current statement data is also not empty, is said
Bright current statement lteral data is a complete sentence, and the processing of next step can be directly carried out to it, then directly executes step
Rapid 110.
Step 106, the extensive object information in the supplement phrase data of user's input is extracted；
Specifically, when the fixation language information in current statement lteral data is not empty, and extracted in current statement data
Extensive object information when being empty, processor generates and exports boot statement data, to prompt the current language of user's supplement input
It is empty fixation language information or extensive object information in sentence data.Then processor receives user and is inputted according to boot statement data
Supplement phrase data and extract supplement phrase data in extensive object information.At this point, supplement phrase data can be understood as
The next statement lteral data of current statement lteral data.Extracting method is referred to above-mentioned steps 102.
Preferably, boot statement data are processors according to the fixation language information in current statement lteral data, and are combined
Default that clause is putd question to generate, in a specific example, phrase data is " I will book tickets ", and fixing language information is " to order
Ticket ", extensive object information are sky, then semantic processes system according to be sky fixation language information for " ticket booking ", in conjunction with " ' may I ask
Need '+verb+' what '+noun " default enquirement clause, generate " may I ask and what ticket needed to book " boot statement data, and
Output.The way of output may include voice prompting and/or text prompt.
In further embodiments, before processor generates and exports boot statement data, processor first obtains upper one
Extensive object information in upper sentence lteral data is substituted into current statement text by the extensive object information in sentence lteral data
Digital data is verified；If verification passes through, according to the extensive object information and current statement in upper sentence lteral data
Fixation language information in lteral data generates new phrase data.If verification does not pass through, boot statement data are generated, and defeated
Out.Here checking procedure is described in detail in following step 107.
Step 107, new fixation language information or new extensive object information are verified, determines whether verification passes through；
Specifically, here, new fixation language information includes: the fixation in the upper sentence lteral data that processor is got
Fixation language information in the supplement phrase data that language information and processor are got.New extensive object information includes: processing
In the supplement phrase data that the extensive object information and processor that device is got in upper sentence lteral data are got
Extensive object information.
Since new fixation language information or the new extensive object information of extensive object information are not necessarily applied to current language
In sentence lteral data, the scene of current statement might not be with the scene in a upper sentence or the scene in supplement sentence in other words
It is identical, if not carrying out scene verification to new fixation language information or new extensive object information is likely to mistake occur.Therefore,
Processor is needed the fixation language information or extensive object information or the benefit that gets of processor in upper sentence lteral data
The fixation language information or extensive object information filled in phrase data substitute into current statement lteral data and carry out scene verification, if school
It tests by can just execute following step 108, executes following step 109 if not passing through.
Further specifically, in the scene verification for fixed language information, processor needs to obtain upper sentence text
Scene information corresponding to the fixation language information in fixation language information or supplement phrase data in data, by the fixation language information
Current statement lteral data is substituted into the scene information corresponding to it, is carried out with the extensive object information of current statement lteral data
Semantic rules matching, if semantic rules successful match, illustrate scene verification pass through, on the contrary it is then illustrate scene verify it is obstructed
It crosses.
In a specific example, current statement lteral data is " Tianjin ", and fixing language information is sky, extensive right
Image information is " Tianjin ".A upper sentence lteral data is " my Pekinese Xiang Cha weather ", and fixing language information is " Cha Tianqi ",
The corresponding contextual data of fixation language information " Cha Tianqi " is " weather ".By the fixation language information in upper sentence lteral data
" Cha Tianqi " and the scene information " weather " corresponding to it substitute into current statement lteral data in extensive object information " Tianjin ",
Semantic rules determine that " Cha Tianqi " matches with " Tianjin ", it is determined that verification passes through.
In the scene verification for extensive object information, processor needs will be extensive right in upper sentence lteral data
Extensive object information in image information or supplement phrase data substitutes into current statement lteral data, with current statement lteral data
Fixed language information carries out semantic rules matching, if semantic rules successful match, illustrates that scene verification passes through, on the contrary then illustrate
Scene verification does not pass through.
Step 108, new sentence lteral data is obtained；
Specifically, if by extensive right in new fixation language information substitution current statement data, with current statement data
Image information passes through verification after carrying out semantic rules matching, then processor will be general in new fixation language information and current statement data
Change object information to combine, obtains new sentence lteral data.If new extensive object information is substituted into current statement data,
It carries out after semantic rules matching with the fixation language information in current statement data through verification, then processor is by new extensive object
Fixation language information in information and current statement data combines, and obtains new sentence lteral data.
In a specific example, current statement data are " Tianjin ", and fixing language information is sky, extensive object letter
Breath is " Tianjin ", then it is " my Pekinese Xiang Cha day that semantic processes system, which obtains the upper sentence lteral data of the phrase data,
Gas ", fixing language information is " Cha Tianqi ", by extensive object information " Tianjin " He Shangyi sentence text in current statement data
The middle fixed language information " Cha Tianqi " of data combines, and obtains the new sentence lteral data of " Cha Tianjin weather ".
Step 109, boot statement data are generated, and are exported；
Specifically, if new fixation language information is substituted into current statement lteral data, with current statement lteral data
Extensive object information matched after, verification does not pass through, or brings new extensive object information into current statement text number
According to after being matched with the fixation language information in current statement lteral data, verification does not pass through, then processor generates boot statement
Data simultaneously export, to prompt user to supplement input supplement phrase data.
After having executed this step, 101 are returned to step, that is, processor continues to user according to boot statement
The supplement phrase data of data input, to extract the fixation language information or extensive object information in supplement phrase data, in turn
New sentence lteral data is generated according to the fixation language information or extensive object information supplemented in phrase data.At this point, step 101
In phrase data be this step in user input supplement phrase data.
Step 110, sentence lteral data is parsed, obtains semantic matches result data, and export；
Specifically, executing the step 108 namely after processor has obtained informative statement lteral data, or in step
The extensive object information in the fixation language information and current statement lteral data in current statement lteral data has been determined in rapid 105
When being not empty, processor determines the corresponding scene number of phrase data according to the fixation sentence information in sentence lteral data first
According to.Each fixed sentence information can be mapped to a contextual data.Here, each contextual data can be understood as one solely
Vertical user behavior scene.
Meanwhile processor matched in point of interest library it is corresponding with the extensive object information in new sentence lteral data
Interest point data obtains the check value of phrase data according to matching result.Point of interest library can be understood as user setting, current
The database of matching relationship in semantic processes system, for storing point of interest and extensive object.Interest in point of interest library
Point data can be what user was set as needed.If be matched in point of interest library corresponding with extensive object information
When interest point data, processor obtains the check value of phrase data according to the interest point data.If matched in point of interest library
When less than interest point data corresponding with currently extensive object information, then processor connects external data according to external interface
Library, and the check value in external database matching interest point data corresponding with extensive object information, as phrase data.
In some preferred embodiments, interest point data corresponding with extensive object information is matched in point of interest library
When, matching condition includes locality condition.That is, matching the corresponding interest point data of extensive object information in processor
When, need to obtain the current location information of user, and using current location information as matching condition, screening and matching condition phase
The interest point data of symbol.
Finally, processor brings the check value of phrase data in the data set of contextual data into, semantic matches result is obtained.
Semantic matches result can be the matching result in semantic processes system itself, be also possible to semantic processes system and open other to answer
With the matching result shown after program.For example, semantic matches result can be in semantic processes system itself, " navigating to position is
The output of the cinema C " of z is as a result, for another example, semantic matches result is also possible to the output knot of " open certain and purchase by group application program "
Fruit.
And when exporting semantic matches result data, semantic matches result data is encapsulated into output queue by processor.?
In preset time, if including semantic matches result data in output queue, the semantic matches result data is exported.Default
In time, if in output queue not including semantic matches result data, default feedback sentence is exported.For example, at 1 minute
It is interior, due to being not matched to any semantic matches result data, so that not including semantic matches result data in output queue, then
Processor exports the default feedback sentence of " I needs more information ".
Intelligent semantic matching process provided in an embodiment of the present invention based on context relation, lacks in current statement data
It is extracted in the case where element needed for parsing, in Cong Shangyi sentence lteral data or next statement lteral data and the current scarce element of institute
Corresponding information determines the semantic matches of current statement data as a result, realizing determining residual by way of associated context
The semanteme for lacking sentence, to obtain answer corresponding with user's statement semantics.
Professional should further appreciate that, described in conjunction with the examples disclosed in the embodiments of the present disclosure
Unit and algorithm steps, can be realized with electronic hardware, computer software, or a combination of the two, hard in order to clearly demonstrate
The interchangeability of part and software generally describes each exemplary composition and step according to function in the above description.
These functions are implemented in hardware or software actually, the specific application and design constraint depending on technical solution.
Professional technician can use different methods to achieve the described function each specific application, but this realization
It should not be considered as beyond the scope of the present invention.
The step of method described in conjunction with the examples disclosed in this document or algorithm, can be executed with hardware, user terminal
Software module or the combination of the two implement.Software module can be placed in random access memory (RAM), memory, read-only storage
Device (ROM), electrically programmable ROM, electrically erasable ROM, register, hard disk, moveable magnetic disc, CD-ROM or technology neck
In any other form of storage medium well known in domain.
Above-described specific embodiment has carried out further the purpose of the present invention, technical scheme and beneficial effects
It is described in detail, it should be understood that being not intended to limit the present invention the foregoing is merely a specific embodiment of the invention
Protection scope, all within the spirits and principles of the present invention, any modification, equivalent substitution, improvement and etc. done should all include
Within protection scope of the present invention.
Claims (9)
1. a kind of intelligent semantic matching process based on context relation, which is characterized in that the described method includes:
Semantic processes system receives phrase data, carries out speech recognition to the phrase data, obtains current statement lteral data；
The extensive processing of clause is carried out to the current statement lteral data, extracts the fixation language in the current statement lteral data
Information and extensive object information；
Determine the fixation language information in the current statement lteral data or the extensive object in the current statement lteral data
Whether information is empty；
When the fixation language information in the current statement lteral data is empty, the fixation language in upper sentence lteral data is obtained
Information, and according to extensive right in the fixation language information and the current statement lteral data in the upper sentence lteral data
Image information generates new sentence lteral data；
When the extensive object information in the current statement lteral data is empty, boot statement data are generated, and export；
The supplement phrase data that user inputs according to the boot statement data is received, and is extracted in the supplement phrase data
Extensive object information；
According to the fixed language information in the extensive object information and current statement lteral data in the supplement phrase data
Generate new sentence lteral data；
The new sentence lteral data is parsed, semantic matches result data is obtained, and exports the semantic matches result data.
2. the intelligent semantic matching process according to claim 1 based on context relation, which is characterized in that the sentence
Data include sentence voice data and sentence lteral data；The semantic processes system receives phrase data, to the sentence number
According to speech recognition is carried out, current statement lteral data is obtained specifically:
The speech convertor of the semantic processes system receives the phrase data, to the sentence voice number in the phrase data
According to being identified, the sentence lteral data of the sentence voice data is obtained, and by the sentence text of the sentence voice data
Data are inserted into the end of the input rank of the semantic processes system；
The interrogator of the semantic processes system monitors the data insertion of the input rank, and institute is obtained from the input rank
The sentence lteral data for stating input rank end obtains the current statement lteral data.
3. the intelligent semantic matching process according to claim 2 based on context relation, which is characterized in that the acquisition
Fixation language information in upper sentence lteral data specifically:
Upper sentence lteral data is obtained from the input rank；
The extensive processing of clause is carried out to the upper sentence lteral data, extracts the fixation language in the upper sentence lteral data
Information.
4. the intelligent semantic matching process according to claim 1 based on context relation, which is characterized in that the acquisition
Fixation language information in upper sentence lteral data specifically:
From the fixation language information obtained in the buffer in the semantic processes system in upper sentence lteral data.
5. the intelligent semantic matching process according to claim 1 based on context relation, which is characterized in that obtained described
After taking the fixation language information in a sentence lteral data, the method also includes:
Fixation language information in the upper sentence lteral data is substituted into current statement lteral data to verify；
If verification passes through, according in the fixation language information and current statement lteral data in the upper sentence lteral data
Extensive object information, generate the new sentence lteral data.
6. the intelligent semantic matching process according to claim 5 based on context relation, which is characterized in that if verification
Do not pass through, the method also includes:
Boot statement data are generated, and are exported, input supplement phrase data according to the boot statement data to user.
7. the intelligent semantic matching process according to claim 1 based on context relation, which is characterized in that when described general
When change object information is empty, in the generation boot statement data, and before output, the method also includes:
The extensive object information in upper sentence lteral data is obtained, and according to extensive right in the upper sentence lteral data
Fixation language information in image information and the current statement lteral data obtains new sentence lteral data.
8. the intelligent semantic matching process according to claim 7 based on context relation, which is characterized in that obtained described
After taking the extensive object information in a sentence lteral data, the method also includes:
Extensive object information in the upper sentence lteral data is substituted into current statement lteral data to verify；
If verification passes through, according to the extensive object information and current statement lteral data in the upper sentence lteral data
In fixation language information generate the new sentence lteral data；
If verification does not pass through, the boot statement data are generated, and export.
9. the intelligent semantic matching process according to claim 1 based on context relation, which is characterized in that mentioned described
After taking the extensive object information in the supplement phrase data, the method also includes:
Extensive object information in the supplement phrase data is substituted into current statement lteral data to verify；
If verification passes through, according in the extensive object information and current statement lteral data in the supplement phrase data
Fixed language information generates the new sentence lteral data；
If verification does not pass through, the boot statement data are generated, and export.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910231582.7A CN109960807A (en) | 2019-03-26 | 2019-03-26 | A kind of intelligent semantic matching process based on context relation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910231582.7A CN109960807A (en) | 2019-03-26 | 2019-03-26 | A kind of intelligent semantic matching process based on context relation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109960807A true CN109960807A (en) | 2019-07-02 |
Family
ID=67024962
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910231582.7A Pending CN109960807A (en) | 2019-03-26 | 2019-03-26 | A kind of intelligent semantic matching process based on context relation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109960807A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110427625A (en) * | 2019-07-31 | 2019-11-08 | 腾讯科技（深圳）有限公司 | Sentence complementing method, device, medium and dialog process system |
| CN111177338A (en) * | 2019-12-03 | 2020-05-19 | 北京博瑞彤芸科技股份有限公司 | Context-based multi-turn dialogue method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105468583A (en) * | 2015-12-09 | 2016-04-06 | 百度在线网络技术（北京）有限公司 | Entity relationship obtaining method and device |
| CN107305769A (en) * | 2016-04-20 | 2017-10-31 | 斑马网络技术有限公司 | Voice interaction processing method, device, equipment and operating system |
| CN107368572A (en) * | 2017-07-13 | 2017-11-21 | 张勇 | Multifunctional intellectual man-machine interaction method and system |
| CN107728497A (en) * | 2017-09-29 | 2018-02-23 | 深圳狗尾草智能科技有限公司 | Communication means for man-machine interaction |
| CN108806671A (en) * | 2018-05-29 | 2018-11-13 | 杭州认识科技有限公司 | Semantic analysis, device and electronic equipment |
-
2019
- 2019-03-26 CN CN201910231582.7A patent/CN109960807A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105468583A (en) * | 2015-12-09 | 2016-04-06 | 百度在线网络技术（北京）有限公司 | Entity relationship obtaining method and device |
| CN107305769A (en) * | 2016-04-20 | 2017-10-31 | 斑马网络技术有限公司 | Voice interaction processing method, device, equipment and operating system |
| CN107368572A (en) * | 2017-07-13 | 2017-11-21 | 张勇 | Multifunctional intellectual man-machine interaction method and system |
| CN107728497A (en) * | 2017-09-29 | 2018-02-23 | 深圳狗尾草智能科技有限公司 | Communication means for man-machine interaction |
| CN108806671A (en) * | 2018-05-29 | 2018-11-13 | 杭州认识科技有限公司 | Semantic analysis, device and electronic equipment |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110427625A (en) * | 2019-07-31 | 2019-11-08 | 腾讯科技（深圳）有限公司 | Sentence complementing method, device, medium and dialog process system |
| CN111177338A (en) * | 2019-12-03 | 2020-05-19 | 北京博瑞彤芸科技股份有限公司 | Context-based multi-turn dialogue method |
| CN111177338B (en) * | 2019-12-03 | 2023-07-21 | 北京博瑞彤芸科技股份有限公司 | Context-based multi-round dialogue method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109523989B (en) | Speech synthesis method, speech synthesis device, storage medium, and electronic apparatus | |
| US10832657B2 (en) | Use of small unit language model for training large unit language models | |
| CN107423363B (en) | Artificial intelligence based word generation method, device, equipment and storage medium | |
| US20190163691A1 (en) | Intent Based Dynamic Generation of Personalized Content from Dynamic Sources | |
| US20210158795A1 (en) | Generating audio for a plain text document | |
| JP5099953B2 (en) | Generation of unified task-dependent language model by information retrieval method | |
| CN110428820B (en) | Chinese and English mixed speech recognition method and device | |
| US20060069545A1 (en) | Method and apparatus for transducer-based text normalization and inverse text normalization | |
| US6098042A (en) | Homograph filter for speech synthesis system | |
| CN111223498A (en) | Intelligent emotion recognition method and device and computer readable storage medium | |
| JP2001523019A (en) | Automatic recognition of discourse structure in text body | |
| Davel et al. | Pronunciation dictionary development in resource-scarce environments | |
| CN109740053A (en) | Sensitive word screen method and device based on NLP technology | |
| Dethlefs et al. | Conditional random fields for responsive surface realisation using global features | |
| CN110008471A (en) | A kind of intelligent semantic matching process based on phonetic conversion | |
| El Ouahabi et al. | Toward an automatic speech recognition system for amazigh-tarifit language | |
| US20240028893A1 (en) | Generating neural network outputs using insertion commands | |
| CN112463942A (en) | Text processing method and device, electronic equipment and computer readable storage medium | |
| CN109960807A (en) | A kind of intelligent semantic matching process based on context relation | |
| KR20190059185A (en) | Method and system for improving the accuracy of speech recognition technology based on text data analysis for deaf students | |
| Breiner et al. | Userlibri: A dataset for asr personalization using only text | |
| CN111402864A (en) | Voice processing method and electronic equipment | |
| CN109960806A (en) | A kind of natural language processing method | |
| CN109960805A (en) | A kind of intelligent semantic matching process divided based on semantic domain | |
| CN115132182B (en) | Data identification method, device, equipment and 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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190702 |