CN107644012A - Electronic installation, problem identification confirmation method and computer-readable recording medium - Google Patents
Electronic installation, problem identification confirmation method and computer-readable recording medium Download PDFInfo
- Publication number
- CN107644012A CN107644012A CN201710754550.6A CN201710754550A CN107644012A CN 107644012 A CN107644012 A CN 107644012A CN 201710754550 A CN201710754550 A CN 201710754550A CN 107644012 A CN107644012 A CN 107644012A
- Authority
- CN
- China
- Prior art keywords
- feature words
- predetermined
- probability
- text
- answer
- 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
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
-
- 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
- G10L15/26—Speech to text systems
Abstract
The present invention discloses a kind of electronic installation, problem identification confirmation method and computer-readable recording medium, wherein, this method includes:User's the problem of sending voice is received, voice carries out speech recognition the problem of to receiving, and generates question text;The problem of to generation, text was according to predetermined word segmentation regulation progress word segmentation processing, the corresponding participle of acquisition described problem text;If contain predetermined Feature Words in the participle obtained, then according to the probability distribution between Feature Words and problem, the problem of determining maximum probability corresponding to the predetermined Feature Words, and according to the mapping relations between predetermined question and answer, the problem of determining the maximum probability corresponding answer;By the answer feedback of determination to user.Technical solution of the present invention improves intelligent customer service robot, intelligent customer service answering system feed back to user answer accuracy.
Description
Technical field
The present invention relates to intelligent sound technical field, more particularly to a kind of electronic installation, problem identification confirmation method and meter
Calculation machine readable storage medium storing program for executing.
Background technology
At present, in order to effectively reduce the wait situation of customer service, lifting service quality, improve customer service it is convenient
Property, the company (for example, mobile with business, insurance company, financial institution etc.) of many service types employs intelligent customer service machine under line
Device people (for example, entity Administrative Area in set intelligent customer service robot) and/or line on intelligent customer service answering system (for example,
Intelligent voice response system) serviced for client.Intelligent customer service response system in this kind of Xian Xia intelligent customer services robot and/or line
System generally use existing scheme be:It is pre-configured with typical problem and the mapping relations data of model answer;When receiving client
After the typical problem of proposition, according to the mapping relations data for the typical problem and model answer being pre-configured with, determine what is received
Model answer corresponding to typical problem, and the model answer determined is fed back into client.For non-standard the asking of user's proposition
Topic, this existing scheme will be difficult to give answer feedback.
Although a kind of improvement project for solving non-standard issue on the market at present be present:When non-standard issue can not be found
During corresponding answer, non-standard issue and each typical problem are subjected to Similarity Measure, and the standard of maximum similarity is asked
Model answer corresponding to topic is fed back as answer corresponding to non-standard issue.But due in most cases, it is non-standard
Similarity between problem and typical problem be all because some words unrelated with sentence implication (for example, " ", " ") and produce
Raw, therefore, the accuracy of this improvement project is very low, and often error, causes to give an irrelevant answer.
The content of the invention
The main object of the present invention is to provide a kind of problem identification confirmation method, it is intended to lifts intelligent customer service system to nonstandard
The accuracy that quasi- problem identification confirms, so as to the accuracy of feedback answer of the lift pins to non-standard issue.
To achieve the above object, electronic installation proposed by the present invention includes memory, processor, is stored on the memory
There is the problem of can running on the processor recognition and verification system, described problem recognition and verification system is by the computing device
Shi Shixian following steps:
S1, user's the problem of sending voice is received, voice carries out speech recognition the problem of to receiving, and generates question text;
S2, to generation the problem of text according to predetermined word segmentation regulation carry out word segmentation processing, obtain described problem text
Segmented corresponding to this;
If contain predetermined Feature Words in S3, the participle obtained, according to the probability between Feature Words and problem point
Cloth, the problem of determining maximum probability corresponding to the predetermined Feature Words, and according between predetermined question and answer
Mapping relations, the problem of determining the maximum probability corresponding answer;
S4, by the answer feedback of determination to user.
Preferably, the step S3 replaces with following steps:
If containing predetermined Feature Words in the participle obtained, according to the probability distribution between Feature Words and problem,
Determine that the predetermined Feature Words correspond to the probability of each problem;
It is ranked up according to the order from big to small of probability for each problem, determines the preceding predetermined number that sorts
Each candidate's problem of determination is provided or reported and selected to user as candidate's problem by problem;
After user have selected a problem, according to the mapping relations between predetermined question and answer, it is determined that should
Answer corresponding to problem.
Preferably, the predetermined word segmentation regulation is priority of long word word segmentation regulation.
Preferably, the probability distribution between the Feature Words and problem determines in accordance with the following steps:
The implicit theme of predetermined number is added between Feature Words and problem;
The problem of obtaining pending training text, and to obtain the problem of text carry out word segmentation processing respectively, obtain each
Segmented corresponding to question text;
According to the mapping relations of predetermined implicit theme and Feature Words, the spy that each implicit theme contains is determined respectively
The first quantity of word is levied, the second quantity of the implicit theme belonging to each Feature Words is determined respectively, according to corresponding first quantity
First choice probability of each Feature Words to each implicit theme is determined with the second quantity;
According to predetermined implicit theme and the mapping relations of question text, determine what each question text contained respectively
3rd quantity of implicit theme, the 4th quantity of the problem of each implicit theme is affiliated text is determined respectively, according to corresponding the
Three quantity and the 4th quantity determine second select probability of each implicit theme to each question text;
Corresponding first choice probability and the second select probability are substituted into predetermined calculation formula to be calculated, calculated
Go out threeth select probability of each Feature Words to each question text, each Feature Words calculated are respectively to each question text
The 3rd select probability be probability distribution between Feature Words and problem.
Preferably, the predetermined calculation formula is:
P3=P1*P2, wherein, P1 represents first choice probability, and P2 represents the second select probability, and it is general that P3 represents the 3rd selection
Rate.
The present invention also proposes a kind of problem identification confirmation method, it is characterised in that the method comprising the steps of:
S1, user's the problem of sending voice is received, voice carries out speech recognition the problem of to receiving, and generates question text;
S2, to generation the problem of text according to predetermined word segmentation regulation carry out word segmentation processing, obtain described problem text
Segmented corresponding to this;
If contain predetermined Feature Words in S3, the participle obtained, according to the probability between Feature Words and problem point
Cloth, the problem of determining maximum probability corresponding to the predetermined Feature Words, and according between predetermined question and answer
Mapping relations, the problem of determining the maximum probability corresponding answer;
S4, by the answer feedback of determination to user.
Preferably, the step S3 replaces with following steps:
If containing predetermined Feature Words in the participle obtained, according to the probability distribution between Feature Words and problem,
Determine that the predetermined Feature Words correspond to the probability of each problem;
It is ranked up according to the order from big to small of probability for each problem, determines the preceding predetermined number that sorts
Each candidate's problem of determination is provided or reported and selected to user as candidate's problem by problem;
After user have selected a problem, according to the mapping relations between predetermined question and answer, it is determined that should
Answer corresponding to problem.
Preferably, the predetermined word segmentation regulation is priority of long word word segmentation regulation.
Preferably, the probability distribution between the Feature Words and problem determines in accordance with the following steps:
The implicit theme of predetermined number is added between Feature Words and problem;
The problem of obtaining pending training text, and to obtain the problem of text carry out word segmentation processing respectively, obtain each
Segmented corresponding to question text;
According to the mapping relations of predetermined implicit theme and Feature Words, the spy that each implicit theme contains is determined respectively
The first quantity of word is levied, the second quantity of the implicit theme belonging to each Feature Words is determined respectively, according to corresponding first quantity
First choice probability of each Feature Words to each implicit theme is determined with the second quantity;
According to predetermined implicit theme and the mapping relations of question text, determine what each question text contained respectively
3rd quantity of implicit theme, the 4th quantity of the problem of each implicit theme is affiliated text is determined respectively, according to corresponding the
Three quantity and the 4th quantity determine second select probability of each implicit theme to each question text;
Corresponding first choice probability and the second select probability are substituted into predetermined calculation formula to be calculated, calculated
Go out threeth select probability of each Feature Words to each question text, each Feature Words calculated are respectively to each question text
The 3rd select probability be probability distribution between Feature Words and problem.
The present invention also proposes a kind of computer-readable recording medium, the problematic knowledge of computer-readable recording medium storage
System is not confirmed, and described problem recognition and verification system can be by least one computing device, so that at least one processor
Perform recognition and verification method the problem of described in any of the above-described.
Technical solution of the present invention is by by after the problematic text of speech recognition the problem of user, dividing question text
Word, obtains the theme that can reflect customer problem that contains or the Feature Words in semantic direction in word segmentation result, and by Feature Words with
Probability distribution between problem, the problem of so as to find out maximum probability (i.e. most probable problem), then determine maximum probability
Answer corresponding to problem, to feed back to user;Because in the technical program, Feature Words can reflect the theme or language of customer problem
The right way of conduct compared to prior art to by the corresponding answer found corresponding to Feature Words the problem of maximum probability, therefore, taking
Whole problem and typical problem are subjected to similarity-rough set, in a manner of obtaining answer corresponding to most like problem for, this case
The accuracy for feeding back to the answer of user significantly improves.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
There is the required accompanying drawing used in technology description to be briefly described, it should be apparent that, drawings in the following description are only this
Some embodiments of invention, for those of ordinary skill in the art, on the premise of not paying creative work, can be with
Structure according to these accompanying drawings obtains other accompanying drawings.
Fig. 1 is the schematic flow sheet of the embodiment of problem identification confirmation method one of the present invention;
Fig. 2 is the schematic flow sheet of the embodiment of problem identification confirmation method two of the present invention;
Fig. 3 is that the flow that the probability distribution between Feature Words and problem is determined in problem identification confirmation method of the present invention is illustrated
Figure;
Fig. 4 is the running environment schematic diagram that problem identification of the present invention confirms system preferred embodiment;
Fig. 5 is the structural representation that problem identification of the present invention confirms the embodiment of system one;
Fig. 6 is the structural representation that problem identification of the present invention confirms the embodiment of system two;.
The realization, functional characteristics and advantage of the object of the invention will be described further referring to the drawings in conjunction with the embodiments.
Embodiment
The principle and feature of the present invention are described below in conjunction with accompanying drawing, the given examples are served only to explain the present invention, and
It is non-to be used to limit the scope of the present invention.
The present invention proposes a kind of problem identification confirmation method, is mainly used in intelligent customer service answering system or intelligent customer service machine
The intelligent customer service product such as people.
As shown in figure 1, Fig. 1 is the schematic flow sheet of the embodiment of problem identification confirmation method one of the present invention.
In the present embodiment, the problem identification confirmation method includes:
Step S1, user's the problem of sending voice is received, voice carries out speech recognition, generation problem text the problem of to receiving
This;
When user puts question to intelligent customer service voice system or intelligent customer service robot, problem identification confirms that system receives and used
The problem of sending voice when family is putd question to, the problem of identification receives voice and will identification the problem of speech production the problem of correspond to it is literary
This.
Step S2, text carries out word segmentation processing according to predetermined word segmentation regulation the problem of to generation, asks described in acquisition
Inscribe and segmented corresponding to text;
Will receive the problem of after the problematic text of speech recognition conversion, problem identification confirms system according to predefining
Word segmentation regulation word segmentation processing is carried out to the question text, after word segmentation processing, then obtain segmenting corresponding to the question text.
In the present embodiment, the participle includes word and word, such as:Described problem text can be that " safety is proposed the grand people's product of honor
", the result after participle is " safety ", " release ", " ", " the grand life of honor ", " product ", " ".
Step S3, if containing predetermined Feature Words in the participle obtained, according to general between Feature Words and problem
Rate is distributed, the problem of determining maximum probability corresponding to the predetermined Feature Words, and according to predetermined question and answer
Between mapping relations, the problem of determining the maximum probability corresponding answer;
There are Feature Words set in advance (for example, " the grand life of honor ", " safety " etc.), Feature Words, which can reflect, asks in system
The theme for the problem of topic text corresponds to or semantic direction;Also there is the probability between predetermined Feature Words and problem in system
Distribution, i.e., each Feature Words have probable value corresponding with each the problem of prestoring respectively, contain each feature word problem text
This may be the probability of each problem;System is additionally provided with the mapping table between default question and answer.System is obtaining
Obtain after being segmented corresponding to described problem text, analyze in the participle of acquisition whether contain predetermined Feature Words;When analyzing
Predetermined Feature Words are not contained in the participle of acquisition, then prompt user to put question to again or prompt None- identified to be asked a question
Deng processing.When containing predetermined Feature Words in the participle for analyzing acquisition, then according to general between Feature Words and problem
Rate is distributed, it is determined that corresponding to the predetermined Feature Words contained the problem of maximum probability, i.e., it is most possible the problem of, in problem
It is determined that afterwards, then according to the mapping relations between predetermined question and answer, the problem of obtaining the maximum probability, is corresponding
Answer.
Step S4, by the answer feedback of determination to user.
System obtain determine answer after, by the answer of determination by voice broadcast or send shown to display device or
Send to modes such as the default terminals of user and feed back to user.
The present embodiment technical scheme is by by after the problematic text of speech recognition the problem of user, dividing question text
Word, obtains the theme that can reflect customer problem that contains or the Feature Words in semantic direction in word segmentation result, and by Feature Words with
Probability distribution between problem, the problem of so as to find out maximum probability (i.e. most probable problem), then determine maximum probability
Answer corresponding to problem, to feed back to user;Because in the technical program, Feature Words can reflect the theme or language of customer problem
The right way of conduct compared to prior art to by the corresponding answer found corresponding to Feature Words the problem of maximum probability, therefore, taking
Whole problem and typical problem are subjected to similarity-rough set, in a manner of obtaining answer corresponding to most like problem for, this case
The accuracy of the answer of feedback user significantly improves.
Preferably, in the present embodiment, the predetermined word segmentation regulation is priority of long word word segmentation regulation.The priority of long word
Word segmentation regulation refers to:The phrase T1 segmented for a needs, first since first character A, one is found out from the dictionary to prestore
The individual most long word X1 originated by A, X1 is then rejected from T1 and is left T2, then identical cutting principle is used to T2, after cutting
Result for " X1/X2/,,, ";For example, the dictionary to prestore include " safety ", " release ", " ", " the grand life of honor ",
When " product ", " ", the cutting result of phrase " safety is proposed the grand people's product of honor " for " safety "/" release "/" "/
" the grand life of honor "/" product "/" ".
As shown in Fig. 2 Fig. 2 is the schematic flow sheet of the embodiment of problem identification confirmation method two of the present invention, the present embodiment side
Case replaces with following steps on the basis of first embodiment, by the step S3:
Step S301, if containing predetermined Feature Words in the participle obtained, according between Feature Words and problem
Probability distribution, determine that the predetermined Feature Words correspond to the probability of each problem;
After predetermined Feature Words are contained in the participle for analyze acquisition, according to predetermined Feature Words in system
Probability distribution between problem, it is determined that the predetermined Feature Words contained in drawing the participle of the acquisition correspond to respectively it is each
The probability of problem.
Step S302, it is ranked up according to the order from big to small of probability for each problem, determines to sort preceding
Each candidate's problem of determination is provided or reported and selected to user as candidate's problem by the problem of predetermined number;
It is right after the predetermined Feature Words contained in the participle for draw the acquisition correspond to the probability of each problem respectively
Each problem carries out descending sort according to obtained probability, then the preceding present count of sequence the problem of extract after sequence in sequence
Candidate's problem of extraction is fed back to user, so that user is selected by the problem of measuring (such as 3,4) as candidate's problem
Select.Wherein, the mode that candidate's problem feeds back to user can be:1st, voice broadcast;2nd, selection interface is provided, candidate's problem is shown
In selection interface (for example, generation problem selection interface selects for user, the selection interface can include candidate's problem list,
Each candidate's problem in the list it is corresponding one " it is determined that " button, user can click on to be asked corresponding to the button selection
Topic);Deng.
Step S303, after user have selected a problem, closed according to the mapping between predetermined question and answer
System, determines answer corresponding to the problem.
After candidate problem of the user based on system feedback makes a choice, system receives the problem of user selects, then root
According to the mapping relations between predetermined question and answer in system, the problem of determining the user's selection received, is corresponding
Answer.
As shown in figure 3, the probability distribution between the Feature Words and problem determines in accordance with the following steps:
Step S51, the implicit theme of predetermined number is added between Feature Words and problem;
First, the implicit theme of pre- quantitation (for example, 50) is added between this two layers of Feature Words and problem, as in
Interbed, so as to form problem preference pattern;Wherein, the implicit theme is virtual, not real meaning;Each implicit master
Topic generally comprises multiple Feature Words, and each problem generally comprises multiple implicit themes again.
Step S52, the problem of obtaining pending training text, and text carries out word segmentation processing respectively the problem of to obtaining,
Obtain segmenting corresponding to each question text;
After problem preference pattern is formed, the problem of obtaining pending training text (question text is prepares in advance
), word segmentation processing is carried out respectively to each question text of acquisition, so as to obtain word segmentation result corresponding to each question text.
Step S53, according to the mapping relations of predetermined implicit theme and Feature Words, each implicit theme is determined respectively
First quantity of the Feature Words contained, the second quantity of the implicit theme belonging to each Feature Words is determined respectively, according to corresponding
First quantity and the second quantity determine first choice probability of each Feature Words to each implicit theme;
According to the mapping relations of predetermined implicit theme and Feature Words in system, each implicit theme is determined respectively
In the first quantity of Feature Words for containing and the second quantity of the implicit theme belonging to each Feature Words, further according to corresponding first
Quantity respectively obtains first choice probability of each Feature Words to each implicit theme with the second quantity;For example, belonging to Feature Words Y
The second quantity of implicit theme be X2, the first quantity of the Feature Words that an implicit theme contains is X1, then Y pairs of this feature word
Select probability of the implicit theme is:1/(X1*X2).
Step S54, according to predetermined implicit theme and the mapping relations of question text, each problem text is determined respectively
3rd quantity of the implicit theme originally contained, the 4th quantity of the problem of each implicit theme is affiliated text is determined respectively, according to
Corresponding 3rd quantity and the 4th quantity determine second select probability of each implicit theme to each question text;
According to the mapping relations of predetermined implicit theme and question text in system, each question text is determined respectively
In the 3rd quantity of implicit theme that contains and the problem of affiliated each implicit theme text the 4th quantity, further according to corresponding
3rd quantity respectively obtains second select probability of each implicit theme to each question text with the 4th quantity;It is for example, implicit
4th quantity of the problem of theme K is affiliated text is J2, and the 3rd quantity of the implicit theme that a question text contains is J1, then
This implies theme K:1/(J1*J2).In the present embodiment, the step S54 and step S53
Order interchangeable.
Step S55, corresponding first choice probability and the second select probability are substituted into predetermined calculation formula and carried out
Calculate, calculate threeth select probability of each Feature Words to each question text, each Feature Words calculated are respectively to each
3rd select probability of individual question text is the probability distribution between Feature Words and problem.
First choice probability distribution according to Feature Words to implicit theme, and second choosing of the implicit theme to question text
Probability distribution is selected, can further show that Feature Words are distributed to the 3rd select probability of question text.Specifically, by that will correspond to
First choice probability and the second select probability substitute into predetermined calculation formula and calculate, draw each Feature Words respectively to each
The select probability of individual question text, that is, obtain the probability distribution between Feature Words and problem.In the present embodiment, this is predetermined
Calculation formula is:P3=P1*P2, wherein, P1 represents first choice probability, and P2 represents the second select probability, and P3 represents the 3rd choosing
Select probability.For example, Feature Words Y is to the first choice probability for implying theme K:1/ (X1*X2), theme K is implied to question text W
The second select probability be:1/ (J1*J2), then Feature Words Y is then 1/ (X1*X2) * (J1* to question text W select probability
J2)。
The present invention also proposes that a kind of problem identification confirms system.
Referring to Fig. 4, it is the running environment schematic diagram that problem identification of the present invention confirms the preferred embodiment of system 10.
In the present embodiment, problem identification confirms that system 10 is installed and run in electronic installation 1.Electronic installation 1 can be with
It is the computing devices such as desktop PC, notebook, palm PC and server.The electronic installation 1 may include, but not only limit
In memory 11, processor 12 and display 13.Fig. 3 illustrate only the electronic installation 1 with component 11-13, it should be understood that
Be, it is not required that implement all components shown, the more or less component of the implementation that can be substituted.
Memory 11 is a kind of computer-readable storage medium, can be the storage inside of electronic installation 1 in certain embodiments
Unit, such as the hard disk or internal memory of the electronic installation 1.Memory 11 can also be electronic installation 1 in further embodiments
The plug-in type hard disk being equipped with External memory equipment, such as electronic installation 1, intelligent memory card (Smart Media Card,
SMC), secure digital (Secure Digital, SD) blocks, flash card (Flash Card) etc..Further, memory 11 may be used also
With both internal storage units including electronic installation 1 or including External memory equipment.Memory 11 is installed on electronics for storage
The application software and Various types of data of device 1, such as problem identification confirm program code of system 10 etc..Memory 11 can also be used
In temporarily storing the data that have exported or will export.
Processor 12 can be in certain embodiments a central processing unit (Central Processing Unit,
CPU), microprocessor or other data processing chips, for the program code or processing data stored in run memory 11, example
Such as executive problem recognition and verification system 10.
Display 13 can be in certain embodiments light-emitting diode display, liquid crystal display, touch-control liquid crystal display and
OLED (Organic Light-Emitting Diode, Organic Light Emitting Diode) touches device etc..Display 13 is used to be shown in
The information that is handled in electronic installation 1 and for showing visual user interface, such as business customizing interface etc..Electronic installation
1 part 11-13 is in communication with each other by system bus.
Referring to Fig. 5, it is the structural representation that problem identification of the present invention confirms the embodiment of system 10 1.In the present embodiment
In, problem identification confirms that system 10 can be divided into one or more modules, and one or more module is stored in storage
In device 11, and it is performed by one or more processors (the present embodiment is processor 12), to complete the present invention.For example, in Fig. 5
In, problem identification confirms that system 10 can be divided into identification module 101, word-dividing mode 102, determining module 103 and feedback mould
Block 104.Module alleged by the present invention is the series of computation machine programmed instruction section for referring to complete specific function, more suitable than program
Confirm the implementation procedure of system 10 in the electronic apparatus 1 together in description problem identification, wherein:
Identification module 101, for receiving the problem of user sends voice, to receive the problem of voice carry out speech recognition,
Generate question text;
When user puts question to intelligent customer service voice system or intelligent customer service robot, problem identification confirms that system receives and used
The problem of sending voice when family is putd question to, the problem of identification receives voice and will identification the problem of speech production the problem of correspond to it is literary
This.
Word-dividing mode 102, for generation the problem of text according to predetermined word segmentation regulation carry out word segmentation processing, obtain
Obtain and segmented corresponding to described problem text;
Will receive the problem of after the problematic text of speech recognition conversion, problem identification confirms system according to predefining
Word segmentation regulation word segmentation processing is carried out to the question text, after word segmentation processing, then obtain segmenting corresponding to the question text.
In the present embodiment, the participle includes word and word, such as:Described problem text can be that " safety is proposed the grand people's product of honor
", the result after participle is " safety ", " release ", " ", " the grand life of honor ", " product ", " ".
Determining module 103, after containing predetermined Feature Words in the participle of acquisition, according to Feature Words and problem
Between probability distribution, the problem of determining maximum probability corresponding to the predetermined Feature Words, and being asked according to predetermined
Inscribe the mapping relations between answer, the problem of determining the maximum probability corresponding answer;
There are Feature Words set in advance (for example, " the grand life of honor ", " safety " etc.), Feature Words, which can reflect, asks in system
The theme for the problem of topic text corresponds to or semantic direction;Also there is the probability between predetermined Feature Words and problem in system
Distribution, i.e., each Feature Words have probable value corresponding with each the problem of prestoring respectively, contain each feature word problem text
This may be the probability of each problem;System is additionally provided with the mapping table between default question and answer.System is obtaining
Obtain after being segmented corresponding to described problem text, analyze in the participle of acquisition whether contain predetermined Feature Words;When analyzing
When containing predetermined Feature Words in the participle of acquisition, then according to the probability distribution between Feature Words and problem, it is determined that containing
Predetermined Feature Words corresponding to maximum probability the problem of, i.e., it is most possible the problem of, after problem determination, then basis
Mapping relations between predetermined question and answer, the problem of obtaining the maximum probability corresponding answer.In addition, determine
After module 103 does not contain predetermined Feature Words also in the participle for analyze acquisition, user is prompted to put question to or carry again
Show that None- identified such as is asked a question at the processing.
Feedback module 104, for by the answer feedback of determination to user.
System obtain determine answer after, by the answer of determination by voice broadcast or send shown to display device or
Send to modes such as the default terminals of user and feed back to user.
The present embodiment technical scheme is by by after the problematic text of speech recognition the problem of user, dividing question text
Word, obtains the theme that can reflect customer problem that contains or the Feature Words in semantic direction in word segmentation result, and by Feature Words with
Probability distribution between problem, the problem of so as to find out maximum probability (i.e. most probable problem), then determine maximum probability
Answer corresponding to problem, to feed back to user;Because in the technical program, Feature Words can reflect the theme or language of customer problem
The right way of conduct compared to prior art to by the corresponding answer found corresponding to Feature Words the problem of maximum probability, therefore, taking
Whole problem and typical problem are subjected to similarity-rough set, in a manner of obtaining answer corresponding to most like problem for, this case
The accuracy of the answer of feedback user significantly improves.
Preferably, in the present embodiment, the predetermined word segmentation regulation is priority of long word word segmentation regulation.The priority of long word
Word segmentation regulation refers to:The phrase T1 segmented for a needs, first since first character A, one is found out from the dictionary to prestore
The individual most long word X1 originated by A, X1 is then rejected from T1 and is left T2, then identical cutting principle is used to T2, after cutting
Result for " X1/X2/,,, ";For example, the dictionary to prestore include " safety ", " release ", " ", " the grand life of honor ",
When " product ", " ", the cutting result of phrase " safety is proposed the grand people's product of honor " for " safety "/" release "/" "/
" the grand life of honor "/" product "/" ".
As shown in fig. 6, Fig. 6 is the structural representation that problem identification of the present invention confirms the embodiment of system two, the present embodiment side
Case replaces with following module on the basis of first embodiment, by the determining module 103:
First determination sub-module 105, after containing predetermined Feature Words in the participle of acquisition, according to Feature Words
Probability distribution between problem, determine that the predetermined Feature Words correspond to the probability of each problem;
After predetermined Feature Words are contained in the participle for analyze acquisition, according to predetermined Feature Words in system
Probability distribution between problem, it is determined that the predetermined Feature Words contained in drawing the participle of the acquisition correspond to respectively it is each
The probability of problem.
Second determination sub-module 106, it is ranked up for the order from big to small according to probability for each problem, it is determined that
Go out to sort preceding predetermined number the problem of as candidate's problem, and by each candidate's problem of determination provide or report to
Family is selected;
It is right after the predetermined Feature Words contained in the participle for draw the acquisition correspond to the probability of each problem respectively
Each problem carries out descending sort according to obtained probability, then the preceding present count of sequence the problem of extract after sequence in sequence
Candidate's problem of extraction is fed back to user, so that user is selected by the problem of measuring (such as 3,4) as candidate's problem
Select.Wherein, the mode that candidate's problem feeds back to user can be:1st, voice broadcast;2nd, selection interface is provided, candidate's problem is shown
In selection interface (for example, generation problem selection interface selects for user, the selection interface can include candidate's problem list,
Each candidate's problem in the list it is corresponding one " it is determined that " button, user can click on to be asked corresponding to the button selection
Topic);Deng.
3rd determination sub-module 107, for after user have selected a problem, according to predetermined question and answer
Between mapping relations, determine answer corresponding to the problem.
After candidate problem of the user based on system feedback makes a choice, system receives the problem of user selects, then root
According to the mapping relations between predetermined question and answer in system, the problem of determining the user's selection received, is corresponding
Answer.
Preferably, in the present embodiment, the probability distribution between the Feature Words and problem determines in accordance with the following steps:
1st, the implicit theme of predetermined number is added between Feature Words and problem;
First, the implicit theme of pre- quantitation (for example, 50) is added between this two layers of Feature Words and problem, as in
Interbed, so as to form problem preference pattern;Wherein, the implicit theme is virtual, not real meaning;Each implicit master
Topic generally comprises multiple Feature Words, and each problem generally comprises multiple implicit themes again.
2nd, the problem of pending training text is obtained, and text carries out word segmentation processing respectively the problem of to obtaining, and obtains each
Segmented corresponding to individual question text;
After problem preference pattern is formed, the problem of obtaining pending training text (question text is prepares in advance
), word segmentation processing is carried out respectively to each question text of acquisition, so as to obtain word segmentation result corresponding to each question text.
3rd, according to the mapping relations of predetermined implicit theme and Feature Words, determine what each implicit theme contained respectively
First quantity of Feature Words, the second quantity of the implicit theme belonging to each Feature Words is determined respectively, according to the corresponding first number
Amount and the second quantity determine first choice probability of each Feature Words to each implicit theme;
According to the mapping relations of predetermined implicit theme and Feature Words in system, each implicit theme is determined respectively
In the first quantity of Feature Words for containing and the second quantity of the implicit theme belonging to each Feature Words, further according to corresponding first
Quantity respectively obtains first choice probability of each Feature Words to each implicit theme with the second quantity;For example, belonging to Feature Words Y
The second quantity of implicit theme be X2, the first quantity of the Feature Words that an implicit theme contains is X1, then Y pairs of this feature word
Select probability of the implicit theme is:1/(X1*X2).
4th, according to predetermined implicit theme and the mapping relations of question text, determine that each question text contains respectively
Implicit theme the 3rd quantity, the 4th quantity of the problem of each implicit theme is affiliated text is determined respectively, according to corresponding
3rd quantity and the 4th quantity determine second select probability of each implicit theme to each question text;
According to the mapping relations of predetermined implicit theme and question text in system, each question text is determined respectively
In the 3rd quantity of implicit theme that contains and the problem of affiliated each implicit theme text the 4th quantity, further according to corresponding
3rd quantity respectively obtains second select probability of each implicit theme to each question text with the 4th quantity;It is for example, implicit
4th quantity of the problem of theme K is affiliated text is J2, and the 3rd quantity of the implicit theme that a question text contains is J1, then
This implies theme K:1/(J1*J2).
5th, corresponding first choice probability and the second select probability are substituted into predetermined calculation formula to be calculated, counted
Threeth select probability of each Feature Words to each question text is calculated, each Feature Words calculated are respectively to each problem text
This 3rd select probability is the probability distribution between Feature Words and problem.
First choice probability distribution according to Feature Words to implicit theme, and second choosing of the implicit theme to question text
Probability distribution is selected, can further show that Feature Words are distributed to the 3rd select probability of question text.Specifically, by that will correspond to
First choice probability and the second select probability substitute into predetermined calculation formula and calculate, draw each Feature Words respectively to each
The select probability of individual question text, that is, obtain the probability distribution between Feature Words and problem.In the present embodiment, this is predetermined
Calculation formula is:P3=P1*P2, wherein, P1 represents first choice probability, and P2 represents the second select probability, and P3 represents the 3rd choosing
Select probability.For example, Feature Words Y is to the first choice probability for implying theme K:1/ (X1*X2), theme K is implied to question text W
The second select probability be:1/ (J1*J2), then Feature Words Y is then 1/ (X1*X2) * (J1* to question text W select probability
J2)。
The present invention also proposes a kind of computer-readable recording medium, the problematic identification of the computer-readable recording medium storage
Confirmation system, described problem recognition and verification system can be by least one computing devices, so that at least one processor is held
The problem of described in any of the above-described embodiment of row recognition and verification method.
The preferred embodiments of the present invention are the foregoing is only, are not intended to limit the scope of the invention, it is every at this
Under the inventive concept of invention, the equivalent structure transformation made using description of the invention and accompanying drawing content, or directly/use indirectly
It is included in other related technical areas in the scope of patent protection of the present invention.
Claims (10)
1. a kind of electronic installation, it is characterised in that the electronic installation includes memory, processor, is stored on the memory
There is the problem of can running on the processor recognition and verification system, described problem recognition and verification system is by the computing device
Shi Shixian following steps:
S1, user's the problem of sending voice is received, voice carries out speech recognition the problem of to receiving, and generates question text;
S2, to generation the problem of text according to predetermined word segmentation regulation carry out word segmentation processing, obtain described problem text pair
The participle answered;
If contain predetermined Feature Words in S3, the participle obtained, according to the probability distribution between Feature Words and problem, really
Corresponding to the fixed predetermined Feature Words the problem of maximum probability, and according to the mapping between predetermined question and answer
Relation, the problem of determining the maximum probability corresponding answer;
S4, by the answer feedback of determination to user.
2. electronic installation as claimed in claim 1, it is characterised in that the step S3 replaces with following steps:
If containing predetermined Feature Words in the participle obtained, according to the probability distribution between Feature Words and problem, it is determined that
The predetermined Feature Words correspond to the probability of each problem;
Be ranked up according to the order from big to small of probability for each problem, determine to sort preceding predetermined number the problem of
As candidate's problem, and each candidate's problem of determination is provided or reported and is selected to user;
After user have selected a problem, according to the mapping relations between predetermined question and answer, the problem is determined
Corresponding answer.
3. electronic installation as claimed in claim 1, it is characterised in that the predetermined word segmentation regulation is priority of long word point
Word rule.
4. the electronic installation as described in any one in claim 1-3, it is characterised in that between the Feature Words and problem
Probability distribution determines in accordance with the following steps:
The implicit theme of predetermined number is added between Feature Words and problem;
The problem of obtaining pending training text, and to obtain the problem of text carry out word segmentation processing respectively, obtain each problem
Segmented corresponding to text;
According to the mapping relations of predetermined implicit theme and Feature Words, the Feature Words that each implicit theme contains are determined respectively
The first quantity, the second quantity of the implicit theme belonging to each Feature Words is determined respectively, according to corresponding first quantity and
Two quantity determine first choice probability of each Feature Words to each implicit theme;
According to predetermined implicit theme and the mapping relations of question text, determine that each question text contains implicit respectively
3rd quantity of theme, the 4th quantity of the problem of each implicit theme is affiliated text is determined respectively, according to the corresponding 3rd number
Amount and the 4th quantity determine second select probability of each implicit theme to each question text;
Corresponding first choice probability and the second select probability are substituted into predetermined calculation formula to be calculated, calculated every
Individual Feature Words are to the 3rd select probability of each question text, and each Feature Words calculated are respectively to the of each question text
Three select probabilities are the probability distribution between Feature Words and problem.
5. electronic installation as claimed in claim 4, it is characterised in that the predetermined calculation formula is:
P3=P1*P2, wherein, P1 represents first choice probability, and P2 represents the second select probability, and P3 represents the 3rd select probability.
6. a kind of problem identification confirmation method, it is characterised in that the method comprising the steps of:
S1, user's the problem of sending voice is received, voice carries out speech recognition the problem of to receiving, and generates question text;
S2, to generation the problem of text according to predetermined word segmentation regulation carry out word segmentation processing, obtain described problem text pair
The participle answered;
If contain predetermined Feature Words in S3, the participle obtained, according to the probability distribution between Feature Words and problem, really
Corresponding to the fixed predetermined Feature Words the problem of maximum probability, and according to the mapping between predetermined question and answer
Relation, the problem of determining the maximum probability corresponding answer;
S4, by the answer feedback of determination to user.
7. problem identification confirmation method as claimed in claim 6, it is characterised in that the step S3 replaces with following steps:
If containing predetermined Feature Words in the participle obtained, according to the probability distribution between Feature Words and problem, it is determined that
The predetermined Feature Words correspond to the probability of each problem;
Be ranked up according to the order from big to small of probability for each problem, determine to sort preceding predetermined number the problem of
As candidate's problem, and each candidate's problem of determination is provided or reported and is selected to user;
After user have selected a problem, according to the mapping relations between predetermined question and answer, the problem is determined
Corresponding answer.
8. problem identification confirmation method as claimed in claim 6, it is characterised in that the predetermined word segmentation regulation is length
The preferential word segmentation regulation of word.
9. the recognition and verification method of the problem of as described in any one in claim 6-8, it is characterised in that the Feature Words are with asking
Probability distribution between topic determines in accordance with the following steps:
The implicit theme of predetermined number is added between Feature Words and problem;
The problem of obtaining pending training text, and to obtain the problem of text carry out word segmentation processing respectively, obtain each problem
Segmented corresponding to text;
According to the mapping relations of predetermined implicit theme and Feature Words, the Feature Words that each implicit theme contains are determined respectively
The first quantity, the second quantity of the implicit theme belonging to each Feature Words is determined respectively, according to corresponding first quantity and
Two quantity determine first choice probability of each Feature Words to each implicit theme;
According to predetermined implicit theme and the mapping relations of question text, determine that each question text contains implicit respectively
3rd quantity of theme, the 4th quantity of the problem of each implicit theme is affiliated text is determined respectively, according to the corresponding 3rd number
Amount and the 4th quantity determine second select probability of each implicit theme to each question text;
Corresponding first choice probability and the second select probability are substituted into predetermined calculation formula to be calculated, calculated every
Individual Feature Words are to the 3rd select probability of each question text, and each Feature Words calculated are respectively to the of each question text
Three select probabilities are the probability distribution between Feature Words and problem.
A kind of 10. computer-readable recording medium, it is characterised in that the problematic identification of computer-readable recording medium storage
Confirmation system, described problem recognition and verification system can be by least one computing devices, so that at least one processor is held
The problem of row is as described in any one of claim 6-9 recognition and verification methods.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710754550.6A CN107644012B (en) | 2017-08-29 | 2017-08-29 | Electronic device, problem identification confirmation method and computer readable storage medium |
PCT/CN2017/108763 WO2019041517A1 (en) | 2017-08-29 | 2017-10-31 | Electronic device, question recognition and confirmation method, and computer-readable storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710754550.6A CN107644012B (en) | 2017-08-29 | 2017-08-29 | Electronic device, problem identification confirmation method and computer readable storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107644012A true CN107644012A (en) | 2018-01-30 |
CN107644012B CN107644012B (en) | 2019-03-01 |
Family
ID=61110870
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710754550.6A Active CN107644012B (en) | 2017-08-29 | 2017-08-29 | Electronic device, problem identification confirmation method and computer readable storage medium |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN107644012B (en) |
WO (1) | WO2019041517A1 (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108388558A (en) * | 2018-02-07 | 2018-08-10 | 平安普惠企业管理有限公司 | Problem matching process, device, customer service robot and storage medium |
CN108595519A (en) * | 2018-03-26 | 2018-09-28 | 平安科技(深圳)有限公司 | Focus incident sorting technique, device and storage medium |
CN109697228A (en) * | 2018-12-13 | 2019-04-30 | 平安科技(深圳)有限公司 | Intelligent answer method, apparatus, computer equipment and storage medium |
CN109829048A (en) * | 2019-01-23 | 2019-05-31 | 平安科技(深圳)有限公司 | Electronic device, interview householder method and computer readable storage medium |
CN110414006A (en) * | 2019-07-31 | 2019-11-05 | 京东方科技集团股份有限公司 | Theme mask method, device, electronic equipment and the storage medium of text |
CN112399019A (en) * | 2020-09-16 | 2021-02-23 | 中国农业银行股份有限公司河北省分行 | Intelligent outbound call method, terminal equipment and readable storage medium |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110211704A (en) * | 2019-05-05 | 2019-09-06 | 平安科技(深圳)有限公司 | The engine method and server of matter of opening |
CN110968669B (en) * | 2019-11-30 | 2023-07-28 | 南京森林警察学院 | Intelligent video analysis police test question classification and recommendation method |
CN111881694A (en) * | 2020-08-05 | 2020-11-03 | 科大讯飞股份有限公司 | Chapter point detection method, device, equipment and storage medium |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090049502A1 (en) * | 2007-08-17 | 2009-02-19 | Searete Llc, A Limited Liability Corporation Of The State Of Delaware | Facilitating communications among message recipients |
US20090313608A1 (en) * | 2008-06-12 | 2009-12-17 | Oracle International Corporation | Enabling a business entity to validate support for specific activities in a crm system before migration from earlier versions |
CN102622413A (en) * | 2012-02-17 | 2012-08-01 | 清华大学 | Method and device for answering natural language questions |
CN104424290A (en) * | 2013-09-02 | 2015-03-18 | 佳能株式会社 | Voice based question-answering system and method for interactive voice system |
CN104657346A (en) * | 2015-01-15 | 2015-05-27 | 深圳市前海安测信息技术有限公司 | Question matching system and question matching system in intelligent interaction system |
CN105094641A (en) * | 2015-07-15 | 2015-11-25 | 百度在线网络技术(北京)有限公司 | Question-answer interaction method and device based on voice |
US20160063111A1 (en) * | 2014-09-03 | 2016-03-03 | International Business Machines Corporation | Management of content tailoring by services |
CN106445905A (en) * | 2015-08-04 | 2017-02-22 | 阿里巴巴集团控股有限公司 | Question and answer data processing method and apparatus and automatic question and answer method and apparatus |
CN106550156A (en) * | 2017-01-23 | 2017-03-29 | 苏州咖啦魔哆信息技术有限公司 | A kind of artificial intelligence's customer service system and its implementation based on speech recognition |
CN106847279A (en) * | 2017-01-10 | 2017-06-13 | 西安电子科技大学 | Man-machine interaction method based on robot operating system ROS |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR101173561B1 (en) * | 2010-10-25 | 2012-08-13 | 한국전자통신연구원 | Question type and domain identifying apparatus and method |
US9443005B2 (en) * | 2012-12-14 | 2016-09-13 | Instaknow.Com, Inc. | Systems and methods for natural language processing |
CN105955976B (en) * | 2016-04-15 | 2019-05-14 | 中国工商银行股份有限公司 | A kind of automatic answering system and method |
CN106601237B (en) * | 2016-12-29 | 2020-02-07 | 上海智臻智能网络科技股份有限公司 | Interactive voice response system and voice recognition method thereof |
-
2017
- 2017-08-29 CN CN201710754550.6A patent/CN107644012B/en active Active
- 2017-10-31 WO PCT/CN2017/108763 patent/WO2019041517A1/en active Application Filing
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090049502A1 (en) * | 2007-08-17 | 2009-02-19 | Searete Llc, A Limited Liability Corporation Of The State Of Delaware | Facilitating communications among message recipients |
US20090313608A1 (en) * | 2008-06-12 | 2009-12-17 | Oracle International Corporation | Enabling a business entity to validate support for specific activities in a crm system before migration from earlier versions |
CN102622413A (en) * | 2012-02-17 | 2012-08-01 | 清华大学 | Method and device for answering natural language questions |
CN104424290A (en) * | 2013-09-02 | 2015-03-18 | 佳能株式会社 | Voice based question-answering system and method for interactive voice system |
US20160063111A1 (en) * | 2014-09-03 | 2016-03-03 | International Business Machines Corporation | Management of content tailoring by services |
CN104657346A (en) * | 2015-01-15 | 2015-05-27 | 深圳市前海安测信息技术有限公司 | Question matching system and question matching system in intelligent interaction system |
CN105094641A (en) * | 2015-07-15 | 2015-11-25 | 百度在线网络技术(北京)有限公司 | Question-answer interaction method and device based on voice |
CN106445905A (en) * | 2015-08-04 | 2017-02-22 | 阿里巴巴集团控股有限公司 | Question and answer data processing method and apparatus and automatic question and answer method and apparatus |
CN106847279A (en) * | 2017-01-10 | 2017-06-13 | 西安电子科技大学 | Man-machine interaction method based on robot operating system ROS |
CN106550156A (en) * | 2017-01-23 | 2017-03-29 | 苏州咖啦魔哆信息技术有限公司 | A kind of artificial intelligence's customer service system and its implementation based on speech recognition |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108388558A (en) * | 2018-02-07 | 2018-08-10 | 平安普惠企业管理有限公司 | Problem matching process, device, customer service robot and storage medium |
CN108388558B (en) * | 2018-02-07 | 2022-04-19 | 平安普惠企业管理有限公司 | Question matching method and device, customer service robot and storage medium |
CN108595519A (en) * | 2018-03-26 | 2018-09-28 | 平安科技(深圳)有限公司 | Focus incident sorting technique, device and storage medium |
CN109697228A (en) * | 2018-12-13 | 2019-04-30 | 平安科技(深圳)有限公司 | Intelligent answer method, apparatus, computer equipment and storage medium |
CN109829048A (en) * | 2019-01-23 | 2019-05-31 | 平安科技(深圳)有限公司 | Electronic device, interview householder method and computer readable storage medium |
CN109829048B (en) * | 2019-01-23 | 2023-06-23 | 平安科技(深圳)有限公司 | Electronic device, interview assisting method, and computer-readable storage medium |
CN110414006A (en) * | 2019-07-31 | 2019-11-05 | 京东方科技集团股份有限公司 | Theme mask method, device, electronic equipment and the storage medium of text |
CN112399019A (en) * | 2020-09-16 | 2021-02-23 | 中国农业银行股份有限公司河北省分行 | Intelligent outbound call method, terminal equipment and readable storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN107644012B (en) | 2019-03-01 |
WO2019041517A1 (en) | 2019-03-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107644012B (en) | Electronic device, problem identification confirmation method and computer readable storage medium | |
US11386893B2 (en) | Human-computer interaction processing system, method, storage medium, and electronic device | |
EP3432197B1 (en) | Method and device for identifying characters of claim settlement bill, server and storage medium | |
US11030547B2 (en) | System and method for intelligent incident routing | |
CN101246410B (en) | Context or linguistic context input method and system | |
CN108595519A (en) | Focus incident sorting technique, device and storage medium | |
US10789561B2 (en) | Recommending production plans | |
CN107204184A (en) | Audio recognition method and system | |
CN108491433A (en) | Chat answer method, electronic device and storage medium | |
CN109587360A (en) | Electronic device should talk with art recommended method and computer readable storage medium | |
CN107680588B (en) | Intelligent voice navigation method, device and storage medium | |
CN107330471B (en) | Method and device for problem location of feedback content, computer equipment and storage medium | |
CN107704512A (en) | Financial product based on social data recommends method, electronic installation and medium | |
CN1190205A (en) | Incremental ideographic character input method | |
US8359364B2 (en) | System and method for optimizing response handling time and customer satisfaction scores | |
CN107704946A (en) | Electronic installation, Voice Navigation needing forecasting method and storage medium | |
CN110211571A (en) | Wrong sentence detection method, device and computer readable storage medium | |
CN112559687A (en) | Question identification and query method and device, electronic equipment and storage medium | |
CN112836521A (en) | Question-answer matching method and device, computer equipment and storage medium | |
CN108351710A (en) | Continuous keyboard identification | |
CN112951233A (en) | Voice question and answer method and device, electronic equipment and readable storage medium | |
CN112380240A (en) | Data query method, device and equipment based on semantic recognition and storage medium | |
CN111369148A (en) | Object index monitoring method, electronic device and storage medium | |
CN113344125B (en) | Long text matching recognition method and device, electronic equipment and storage medium | |
CN109977995A (en) | Text template recognition methods, device 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 |