CN110377743A - A kind of text marking method and device - Google Patents
A kind of text marking method and device Download PDFInfo
- Publication number
- CN110377743A CN110377743A CN201910679022.8A CN201910679022A CN110377743A CN 110377743 A CN110377743 A CN 110377743A CN 201910679022 A CN201910679022 A CN 201910679022A CN 110377743 A CN110377743 A CN 110377743A
- Authority
- CN
- China
- Prior art keywords
- target
- mark
- attribute
- keyword
- objective
- 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
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
Abstract
The present invention provides a kind of text marking method and devices, wherein this method comprises: obtaining target text to be marked and objective attribute target attribute to be marked;Target object to be marked in the target text is determined according to the objective attribute target attribute, wherein the target object includes at least two target keywords;Mark is associated by identical mark mark to the objective attribute target attribute of the target object, wherein, it is described to be identified as mark corresponding with the objective attribute target attribute, therefore, it how can solve in the related technology to having the problem of certain associated more than two keywords are associated mark in text, realize the association mark between multiple keywords.
Description
Technical field
The present invention relates to information technology fields, in particular to a kind of text marking method and device.
Background technique
Machine understands the language of the mankind, is that all circles scholar makes great efforts to solve the problems, such as all the time.If machine can be complete
Understand human language, and suitable feedback is provided according to different situations, then artificial intelligence will also become a reality.Artificial intelligence
The concept well-known as one make everybody for machine solve the problems, such as it is all kinds of entertain indefinite duration and wait for, however, by most people
Do not know, why intelligence is all derived from artificial information input to machine, is that a large amount of artificial information's input just makes machine
Become intelligence.
Natural language processing is a main problem of artificial intelligence, is exactly to allow machine can for natural language processing is popular
With the meaning of the language of the various forms of expression such as the text, the voice that understand the mankind.Likewise, natural language processing still needs greatly
Basis of the artificial information input of amount as machine learning.
Artificial information input is not that any information is ok, and for text field, artificial information input is necessary
It is the information marked, is only only valuable artificial information input for machine by the data of mark ---
It is exactly the training set that people often say, machine learning must have a certain amount of training set as sources of learning.
The mark of data is exactly that data the operation such as be marked to, classified according to the knowledge of the mankind having had in fact.Phase
When allowing machine to be learnt in doing a learning materials for being specific to machine.
When by artificial labeled data, usually by manually marking the label of each entry in text, in a kind of label mark
It in injecting method, is labeled to the attribute of keyword each in text, for having certain associated more than two keywords,
How to be labeled, does not suggest that solution in the related technology.
For in the related technology how to having certain associated more than two keywords to be associated mark in text
Problem, not yet proposition solution.
Summary of the invention
The embodiment of the invention provides a kind of text marking method and devices, how at least to solve in the related technology to text
There is the problem of certain associated more than two keywords are associated mark in this.
According to one embodiment of present invention, a kind of text marking method is provided, comprising:
Obtain target text to be marked and objective attribute target attribute to be marked;
Target object to be marked in the target text is determined according to the objective attribute target attribute, wherein the target object
Including at least two target keywords;
Mark is associated by identical mark mark to the objective attribute target attribute of the target object, wherein the mark
It is identified as mark corresponding with the objective attribute target attribute.
Optionally, before the objective attribute target attribute to the target object is associated mark by identical mark mark,
The method also includes:
Obtain the mark mark of the target object.
Optionally, being associated mark by identical mark mark to the objective attribute target attribute of the target object includes:
In the case where the target object includes first object keyword and the second target keyword, described first is obtained
First mark mark of target keyword and the one or more second of second target keyword mark mark;
In the case where second target keyword corresponding one second mark mark, in the first object keyword
The first predetermined position show with it is one second mark mark it is associated first mark identify;
In the case where second target keyword corresponds to multiple second mark marks, in the first object keyword
The first predetermined position show respectively with it is the multiple second mark mark it is associated it is multiple first mark identify, wherein one
The the second mark mark of first mark mark association one, the multiple second mark mark is different, described more
A first mark mark is different.
Optionally, determine that target object to be marked in the target text includes: according to the objective attribute target attribute
Extract the target keyword in the file destination;
Determine the objective attribute target attribute of the target keyword;
The mesh with the matched target keyword of the objective attribute target attribute to be marked is obtained from the target keyword
Mark the corresponding target object of attribute, wherein the target object is at least two target keywords.
Optionally it is determined that the objective attribute target attribute of the target keyword includes:
The target keyword is inputted into trained target nerve network model in advance, obtains the target nerve network
The target keyword of model output corresponds to the probability of every attribute, wherein the attribute that the probability is greater than predetermined threshold is true
It is set to the objective attribute target attribute.
Optionally, before multiple target objects to be marked in determining the target text, the method also includes:
Attribute belonging to the keyword of acquisition predetermined quantity and the keyword reality;
Using attribute belonging to the keyword of the predetermined quantity and the keyword reality to original neural network mould
Type is trained, and obtains the target nerve network model, wherein the keyword of the predetermined quantity is the original nerve net
The input of network model, objective attribute target attribute belonging to the target keyword of trained target nerve network model output with
Attribute belonging to the target keyword reality meets predeterminated target function.
Optionally, determine that target object to be marked in the target text includes: according to the objective attribute target attribute
It receives and instruction is chosen according to the objective attribute target attribute selected object;
The corresponding object of instruction is chosen to be determined as the target object by described.
Optionally, after the objective attribute target attribute to the target object is associated mark by identical mark mark,
The method also includes:
It establishes and shows relationship classification logotype in the second predetermined position of display interface, wherein the relationship classification logotype
For be associated mark objective attribute target attribute corresponding relationship mark;
The corresponding mark of relationship classification logotype objective attribute target attribute corresponding with the relationship classification logotype is established into association.
Optionally, by the corresponding mark of relationship classification logotype objective attribute target attribute corresponding with the relationship classification logotype
It establishes after association, the method also includes:
Reception chooses the first of the relationship classification logotype to choose instruction, chooses instruction to highlight institute according to described first
State relationship classification logotype and the corresponding objective attribute target attribute of the relationship classification logotype;Or
Reception chooses the second of the objective attribute target attribute to choose instruction, chooses instruction to highlight the mesh according to described second
Mark attribute and the corresponding relationship classification logotype of the objective attribute target attribute.
According to another embodiment of the invention, a kind of text marking device is additionally provided, comprising:
First obtains module, for obtaining target text to be marked;
Second obtains module, for obtaining objective attribute target attribute to be marked;
Determining module, for determining target object to be marked in the target text according to the objective attribute target attribute, wherein
The target object includes at least two target keywords;
It is associated with labeling module, mark is associated by identical mark mark for the objective attribute target attribute to the target object
Note, wherein described to be identified as mark corresponding with the objective attribute target attribute.
Optionally, described device further include:
Third obtains module, and the mark for obtaining the target object identifies.
Optionally, the association labeling module includes:
First acquisition unit, for obtaining the in the case where the target object is the set of two target keywords
First mark mark of one target keyword, the one or more second of second target keyword mark mark;
First display unit is used in the case where second target keyword corresponding one second mark mark,
First predetermined position of the first object keyword is shown to be identified with associated first mark of one second mark mark;
Second display unit is used in the case where second target keyword corresponds to multiple second marks marks,
First predetermined position of the first object keyword, which is shown, identifies associated multiple first with the multiple second mark respectively
Mark mark, wherein a second mark mark of the first mark mark association one, the multiple second mark mark
Know it is different, it is the multiple first mark mark it is different.
Optionally, the determining module includes:
Extraction unit, for extracting the target keyword in the file destination;
First determination unit, for determining the objective attribute target attribute of the target keyword;
Second acquisition unit, for being obtained and the matched institute of the objective attribute target attribute to be marked from the target keyword
State the corresponding target object of objective attribute target attribute of target keyword, wherein the target object is at least two target keywords.
Optionally first determination unit, is also used to
The target keyword is inputted into trained target nerve network model in advance, obtains the target nerve network
The target keyword of model output corresponds to the probability of every attribute, wherein the attribute that the probability is greater than predetermined threshold is true
It is set to the objective attribute target attribute.
Optionally, described device further include:
4th obtain module, for obtain predetermined quantity keyword and the keyword reality belonging to attribute;
Training module, for use the predetermined quantity keyword and the keyword reality belonging to attribute pair
Original neural network model is trained, and obtains the target nerve network model, wherein the keyword of the predetermined quantity is
The input of the original neural network model, the target keyword institute of the trained target nerve network model output
Attribute belonging to the objective attribute target attribute of category and the target keyword reality meets predeterminated target function.
Optionally, the determining module includes:
Receiving unit chooses instruction according to the objective attribute target attribute selected object for receiving;
Second determination unit, for choosing the corresponding object of instruction to be determined as the target object for described.
Optionally, described device further include:
Module is established, for establishing and showing relationship classification logotype in the second predetermined position of display interface, wherein described
Relationship classification is identified as the mark for being associated the corresponding relationship of objective attribute target attribute of mark;
Relating module is established, is used for relationship classification logotype objective attribute target attribute pair corresponding with the relationship classification logotype
The mark answered establishes association.
Optionally, described device further include:
First receiving module chooses the first of the relationship classification logotype to choose instruction, according to described first for receiving
Instruction is chosen to highlight the relationship classification logotype and the corresponding objective attribute target attribute of the relationship classification logotype;Or
Second receiving module is chosen the second of the objective attribute target attribute to choose instruction, is chosen according to described second for receiving
Instruction highlights the objective attribute target attribute and the corresponding relationship classification logotype of the objective attribute target attribute.
According to still another embodiment of the invention, a kind of storage medium is additionally provided, meter is stored in the storage medium
Calculation machine program, wherein the computer program is arranged to execute the step in any of the above-described embodiment of the method when operation.
According to still another embodiment of the invention, a kind of electronic device, including memory and processor are additionally provided, it is described
Computer program is stored in memory, the processor is arranged to run the computer program to execute any of the above-described
Step in embodiment of the method.
Through the invention, target text to be marked is obtained;Obtain objective attribute target attribute to be marked;According to the objective attribute target attribute
Determine target object to be marked in the target text, wherein the target object includes at least two target keywords;It is right
The objective attribute target attribute of the target object is identified by identical mark and is associated mark, wherein described to be identified as and institute
State the corresponding mark of objective attribute target attribute, therefore, can solve in the related technology how to have in text certain associated two with
The problem of upper keyword is associated mark realizes the association mark between multiple keywords.
Detailed description of the invention
The drawings described herein are used to provide a further understanding of the present invention, constitutes part of this application, this hair
Bright illustrative embodiments and their description are used to explain the present invention, and are not constituted improper limitations of the present invention.In the accompanying drawings:
Fig. 1 is a kind of hardware block diagram of the mobile terminal of text marking method of the embodiment of the present invention;
Fig. 2 is the flow chart of text marking method according to an embodiment of the present invention;
Fig. 3 is the schematic diagram of text multirelation mark according to an embodiment of the present invention;
Fig. 4 is the block diagram of text marking device according to an embodiment of the present invention;
Fig. 5 is the block diagram one of text marking device according to the preferred embodiment of the invention;
Fig. 6 is the block diagram two of text marking device according to the preferred embodiment of the invention.
Specific embodiment
Hereinafter, the present invention will be described in detail with reference to the accompanying drawings and in combination with Examples.It should be noted that not conflicting
In the case of, the features in the embodiments and the embodiments of the present application can be combined with each other.
It should be noted that description and claims of this specification and term " first " in above-mentioned attached drawing, "
Two " etc. be to be used to distinguish similar objects, without being used to describe a particular order or precedence order.
Embodiment 1
Embodiment of the method provided by the embodiment of the present application one can be in mobile terminal, terminal or similar fortune
It calculates and is executed in device.For running on mobile terminals, Fig. 1 is a kind of movement of text marking method of the embodiment of the present invention
The hardware block diagram of terminal, as shown in Figure 1, mobile terminal 10 may include at one or more (only showing one in Fig. 1)
It manages device 102 (processing unit that processor 102 can include but is not limited to Micro-processor MCV or programmable logic device FPGA etc.)
Memory 104 for storing data, optionally, above-mentioned mobile terminal can also include the transmission device for communication function
106 and input-output equipment 108.It will appreciated by the skilled person that structure shown in FIG. 1 is only to illustrate, simultaneously
The structure of above-mentioned mobile terminal is not caused to limit.For example, mobile terminal 10 may also include it is more than shown in Fig. 1 or less
Component, or with the configuration different from shown in Fig. 1.
Memory 104 can be used for storing computer program, for example, the software program and module of application software, such as this hair
The corresponding computer program of message method of reseptance in bright embodiment, processor 102 are stored in memory 104 by operation
Computer program realizes above-mentioned method thereby executing various function application and data processing.Memory 104 may include
High speed random access memory, may also include nonvolatile memory, as one or more magnetic storage device, flash memory or its
His non-volatile solid state memory.In some instances, memory 104 can further comprise remotely setting relative to processor 102
The memory set, these remote memories can pass through network connection to mobile terminal 10.The example of above-mentioned network includes but not
It is limited to internet, intranet, local area network, mobile radio communication and combinations thereof.
Transmitting device 106 is used to that data to be received or sent via a network.Above-mentioned network specific example may include
The wireless network that the communication providers of mobile terminal 10 provide.In an example, transmitting device 106 includes a Network adaptation
Device (Network Interface Controller, referred to as NIC), can be connected by base station with other network equipments to
It can be communicated with internet.In an example, transmitting device 106 can for radio frequency (Radio Frequency, referred to as
RF) module is used to wirelessly be communicated with internet.
Based on above-mentioned mobile terminal, a kind of text marking method is present embodiments provided, Fig. 2 is to implement according to the present invention
The flow chart of the text marking method of example, as shown in Fig. 2, the process includes the following steps:
Step S202 obtains target text to be marked and objective attribute target attribute to be marked;
Step S204 determines target object to be marked in the target text according to the objective attribute target attribute, wherein described
Target object includes at least two target keywords;
Step S206 is associated mark by identical mark mark to the objective attribute target attribute of the target object, wherein
It is described to be identified as mark corresponding with the objective attribute target attribute.
By upper step S202 to S206, target text to be marked is obtained;Obtain objective attribute target attribute to be marked;According to institute
It states objective attribute target attribute and determines target object to be marked in the target text, wherein the target object includes at least two mesh
Mark keyword;Mark is associated by identical mark mark to the objective attribute target attribute of the target object, wherein the mark
It is identified as mark corresponding with the objective attribute target attribute, therefore, can solve and how to be closed in the related technology in text with certain
The problem of more than two keywords of connection are associated mark realizes the association mark between multiple keywords.
Optionally, before the objective attribute target attribute to the target object is associated mark by identical mark mark,
It is identified according to the mark that the corresponding relationship of pre-set keyword and mark mark obtains the target object.
Optionally, above-mentioned steps S206 can specifically include:
In the case where the target object includes first object keyword and the second target keyword, described first is obtained
First mark mark of target keyword and the one or more second of second target keyword mark mark;
In the case where second target keyword corresponding one second mark mark, in the first object keyword
The first predetermined position show with it is one second mark mark it is associated first mark identify;
In the case where second target keyword corresponds to multiple second mark marks, in the first object keyword
The first predetermined position show respectively with it is the multiple second mark mark it is associated it is multiple first mark identify, wherein one
The the second mark mark of first mark mark association one, the multiple second mark mark is different, described more
A first mark mark is different.
It should be noted that in the case where the second mark of one or more mark corresponding for multiple first mark marks, root
One or more the second mark mark association display is identified in by the multiple first respectively according to aforesaid way.
Optionally, above-mentioned steps S204 can specifically include:
S2041 extracts the target keyword in the file destination;
S2042 determines the objective attribute target attribute of the target keyword;
S2043 is obtained and the matched target critical of the objective attribute target attribute to be marked from the target keyword
The corresponding target object of the objective attribute target attribute of word, wherein the target object is at least two target keywords.
Further, above-mentioned steps S2042 can specifically include:
The target keyword is inputted into trained target nerve network model in advance, obtains the target nerve network
The target keyword of model output corresponds to the probability of every attribute, wherein the attribute that the probability is greater than predetermined threshold is true
It is set to the objective attribute target attribute.
The embodiment of the present invention in determining the target text before multiple target objects to be marked, obtains predetermined
Attribute belonging to the keyword of quantity and the keyword reality;Keyword and the pass using the predetermined quantity
Attribute belonging to keyword reality is trained original neural network model, obtains the target nerve network model, wherein institute
The keyword for stating predetermined quantity is the input of the original neural network model, and the trained target nerve network model is defeated
Attribute belonging to objective attribute target attribute belonging to the target keyword out and the target keyword reality meets predeterminated target letter
Number.
In another alternative embodiment, above-mentioned steps S204 can specifically include: receive according to the objective attribute target attribute
Selected object chooses instruction;It chooses the corresponding object of instruction to be determined as the target object for described, that is, can also be user
Target object is chosen by selection instruction.
The embodiment of the present invention can also be highlighted associated mark mark, logical in the objective attribute target attribute to the target object
It crosses identical mark mark to be associated after mark, establishes and show relationship classification mark in the second predetermined position of display interface
Know, wherein the relationship classification is identified as the mark for being associated the corresponding relationship of objective attribute target attribute of mark;By the relation object
Not Biao Shi the corresponding mark of corresponding with relationship classification logotype objective attribute target attribute establish association.
Optionally, by the corresponding mark of relationship classification logotype objective attribute target attribute corresponding with the relationship classification logotype
It establishes after association, reception chooses the first of the relationship classification logotype to choose instruction, chooses instruction to protrude according to described first
Show the relationship classification logotype and the corresponding objective attribute target attribute of the relationship classification logotype;Or it receives and chooses the target category
Property second choose instruction, choose that instruction highlights the objective attribute target attribute and the objective attribute target attribute is corresponding according to described second
Relationship classification logotype.
Multirelation mark is exactly to choose one or more texts in one section of natural language text to be marked in simple terms
Note can repeatedly mark alone or in combination any entity marked in text after clicking ' overlapping mark '.In addition, can also point
It hits mark display relational term and obtains the relation chain in mark text, an entity can optionally have multiple relationships.Such as address this
A entity can subdivided into many grades, state, province, city, area, town etc., therefore name etc. can correspond to so many address, just
It needs to use multirelation and marks this method.
Fig. 3 is the schematic diagram of text multirelation mark according to an embodiment of the present invention, as shown in figure 3, being labelled with ' Soviet Union
Light ' and ' the 1 row Room 20 of the Shijiazhuang Zhengding County positive definite town North Street Heng Zhou 58 ', ' Su Guang ' is a name entity, ' Shijiazhuang positive definite
The 1 row Room 20 of county, the North Street Heng Zhou, positive definite town 58 ' this is an address entity, ' Shijiazhuang ', ' Shijiazhuang Zhengding County ', ' stone simultaneously
Family village Zhengding County positive definite town ' it is similarly address entity.Related entity can be labeled to operation, the displaying of mark is such as
Figure, colored rectangular block presentation-entity, colored spherical labels indicate relationship, the spherical shape of same color represent entity it
Between there are certain relationships.If Chinese label, the first character of Chinese label is shown in spherical labels, if English label, then
Show first two letters;Such as occur ' people ' this word (' people ' represents ' name ') above ' Su Guang ', go out above ' Shijiazhuang '
' ground ' this word has been showed (' ground ' represents ' address ').The color of each address mark top circle is different, but one is a pair of
The color of circle above name is answered, corresponding color is a relational term;Such as ' Shijiazhuang Zhengding County ' this mark
The color of top circle is navy blue, makes a general survey of full text, this navy blue has appeared in this mark top ' Su Guang ', this table simultaneously
Show corresponding ' Shijiazhuang Zhengding County ' this address of ' Su Guang ' this name.Why will appear 4 bands ' people ' above ' Su Guang '
Circle is because this name has corresponded to four addresses (this just needs to mark using multirelation), the number pair of every a line circle
The number of words that should be marked.If occurring more ' Su Guang ' corresponding mark, every row two circles of more multirow will occur above in ' Su Guang '
Circle, that is to say, that the label of relationship spherical shape can accumulate to the right arrangement upwards.
Through the above description of the embodiments, those skilled in the art can be understood that according to above-mentioned implementation
The method of example can be realized by means of software and necessary general hardware platform, naturally it is also possible to by hardware, but it is very much
In the case of the former be more preferably embodiment.Based on this understanding, technical solution of the present invention is substantially in other words to existing
The part that technology contributes can be embodied in the form of software products, which is stored in a storage
In medium (such as ROM/RAM, magnetic disk, CD), including some instructions are used so that a terminal device (can be mobile phone, calculate
Machine, server or network equipment etc.) execute method described in each embodiment of the present invention.
Embodiment 2
The embodiment of the present invention additionally provides a kind of text marking device, and the device is for realizing above-described embodiment and preferably
Embodiment, the descriptions that have already been made will not be repeated.As used below, predetermined function may be implemented in term " module "
The combination of software and/or hardware.Although device described in following embodiment is preferably realized with software, hardware, or
The realization of the combination of person's software and hardware is also that may and be contemplated.
Fig. 4 is the block diagram of text marking device according to an embodiment of the present invention, as shown in Figure 4, comprising:
First obtains module 42, for obtaining target text to be marked and objective attribute target attribute to be marked;
Determining module 44, for determining target object to be marked in the target text according to the objective attribute target attribute,
In, the target object includes at least two target keywords;
It is associated with labeling module 46, is associated for the objective attribute target attribute to the target object by identical mark mark
Mark, wherein described to be identified as mark corresponding with the objective attribute target attribute.
Fig. 5 is the block diagram one of text marking device according to the preferred embodiment of the invention, as shown in figure 5, the association is marked
Injection molding block 46 includes:
First acquisition unit 52, for obtaining in the case where the target object is the set of two target keywords
First mark mark of first object keyword, the one or more second of second target keyword mark mark;
First display unit 54 is used in the case where second target keyword corresponding one second mark mark,
It shows in the first predetermined position of the first object keyword and is marked with associated first mark of one second mark mark
Know;
Second display unit 56 is used in the case where second target keyword corresponds to multiple second marks marks,
The first predetermined position of the first object keyword show respectively with the multiple second mark mark associated multiple the
One mark mark, wherein a second mark mark of the first mark mark association one, the multiple second mark
Identify it is different, it is the multiple first mark mark it is different.
Optionally, the determining module 44 includes:
Extraction unit, for extracting the target keyword in the file destination;
First determination unit, for determining the objective attribute target attribute of the target keyword;
Second acquisition unit, for being obtained and the matched institute of the objective attribute target attribute to be marked from the target keyword
State the corresponding target object of objective attribute target attribute of target keyword, wherein the target object is at least two target keywords.
Optionally, first determination unit, is also used to
The target keyword is inputted into trained target nerve network model in advance, obtains the target nerve network
The target keyword of model output corresponds to the probability of every attribute, wherein the attribute that the probability is greater than predetermined threshold is true
It is set to the objective attribute target attribute.
Optionally, described device further include:
Third obtain module, for obtain predetermined quantity keyword and the keyword reality belonging to attribute;
Training module, for use the predetermined quantity keyword and the keyword reality belonging to attribute pair
Original neural network model is trained, and obtains the target nerve network model, wherein the keyword of the predetermined quantity is
The input of the original neural network model, the target keyword institute of the trained target nerve network model output
Attribute belonging to the objective attribute target attribute of category and the target keyword reality meets predeterminated target function.
Optionally, the determining module 44 includes:
Receiving unit chooses instruction according to the objective attribute target attribute selected object for receiving;
Second determination unit, for choosing the corresponding object of instruction to be determined as the target object for described.
Fig. 6 is the block diagram two of text marking device according to the preferred embodiment of the invention, as shown in fig. 6, described device is also
Include:
Module 62 is established, for establishing and showing relationship classification logotype in the second predetermined position of display interface, wherein institute
The relationship classification of stating is identified as the mark for being associated the corresponding relationship of objective attribute target attribute of mark;
Relating module 64 is established, is used for relationship classification logotype objective attribute target attribute corresponding with the relationship classification logotype
Corresponding mark establishes association.
Optionally, described device further include:
First receiving module chooses the first of the relationship classification logotype to choose instruction, according to described first for receiving
Instruction is chosen to highlight the relationship classification logotype and the corresponding objective attribute target attribute of the relationship classification logotype;Or
Second receiving module is chosen the second of the objective attribute target attribute to choose instruction, is chosen according to described second for receiving
Instruction highlights the objective attribute target attribute and the corresponding relationship classification logotype of the objective attribute target attribute.
It should be noted that above-mentioned modules can be realized by software or hardware, for the latter, Ke Yitong
Following manner realization is crossed, but not limited to this: above-mentioned module is respectively positioned in same processor;Alternatively, above-mentioned modules are with any
Combined form is located in different processors.
Embodiment 3
The embodiments of the present invention also provide a kind of storage medium, computer program is stored in the storage medium, wherein
The computer program is arranged to execute the step in any of the above-described embodiment of the method when operation.
Optionally, in the present embodiment, above-mentioned storage medium can be set to store by executing based on following steps
Calculation machine program:
S11 obtains target text to be marked and objective attribute target attribute to be marked;
S12 determines target object to be marked in the target text according to the objective attribute target attribute;
S13 is associated mark by identical mark mark to the objective attribute target attribute of the target object, wherein described
It is identified as mark corresponding with the objective attribute target attribute.
Optionally, in the present embodiment, above-mentioned storage medium can include but is not limited to: USB flash disk, read-only memory (Read-
Only Memory, referred to as ROM), it is random access memory (Random Access Memory, referred to as RAM), mobile hard
The various media that can store computer program such as disk, magnetic or disk.
Embodiment 4
The embodiments of the present invention also provide a kind of electronic device, including memory and processor, stored in the memory
There is computer program, which is arranged to run computer program to execute the step in any of the above-described embodiment of the method
Suddenly.
Optionally, above-mentioned electronic device can also include transmission device and input-output equipment, wherein the transmission device
It is connected with above-mentioned processor, which connects with above-mentioned processor.
Optionally, in the present embodiment, above-mentioned processor can be set to execute following steps by computer program:
S11 obtains target text to be marked and objective attribute target attribute to be marked;
S12 determines target object to be marked in the target text according to the objective attribute target attribute;
S13 is associated mark by identical mark mark to the objective attribute target attribute of the target object, wherein described
It is identified as mark corresponding with the objective attribute target attribute.
Optionally, the specific example in the present embodiment can be with reference to described in above-described embodiment and optional embodiment
Example, details are not described herein for the present embodiment.
Obviously, those skilled in the art should be understood that each module of the above invention or each step can be with general
Computing device realize that they can be concentrated on a single computing device, or be distributed in multiple computing devices and formed
Network on, optionally, they can be realized with the program code that computing device can perform, it is thus possible to which they are stored
It is performed by computing device in the storage device, and in some cases, it can be to be different from shown in sequence execution herein
Out or description the step of, perhaps they are fabricated to each integrated circuit modules or by them multiple modules or
Step is fabricated to single integrated circuit module to realize.In this way, the present invention is not limited to any specific hardware and softwares to combine.
The foregoing is only a preferred embodiment of the present invention, is not intended to restrict the invention, for the skill of this field
For art personnel, the invention may be variously modified and varied.It is all within principle of the invention, it is made it is any modification, etc.
With replacement, improvement etc., should all be included in the protection scope of the present invention.
Claims (10)
1. a kind of text marking method characterized by comprising
Obtain target text to be marked and objective attribute target attribute to be marked;
Target object to be marked in the target text is determined according to the objective attribute target attribute;
Mark is associated by identical mark mark to the objective attribute target attribute of the target object, wherein the mark mark
For mark corresponding with the objective attribute target attribute.
2. the method according to claim 1, wherein the objective attribute target attribute to the target object passes through identical mark
Note mark is associated mark and includes:
In the case where the target object is the set of two target keywords, the first mark of first object keyword is obtained
The one or more second of mark, second target keyword marks mark;
In the case where corresponding one second mark of second target keyword identifies, the of the first object keyword
One predetermined position is shown to be identified with associated first mark of one second mark mark;
In the case where second target keyword corresponds to multiple second marks marks, the of the first object keyword
One predetermined position shows and identifies respectively with associated multiple first marks of the multiple second mark mark, wherein described in one
First the second mark mark of mark mark association one, the multiple second mark mark is different, and the multiple the
One mark mark is different.
3. the method according to claim 1, wherein according to the objective attribute target attribute determine in the target text to
The target object of mark includes:
Extract the target keyword in the file destination;
Determine the objective attribute target attribute of the target keyword;
The target category with the matched target keyword of the objective attribute target attribute to be marked is obtained from the target keyword
Property corresponding target object, wherein the target object is at least two target keywords.
4. according to the method described in claim 3, it is characterized in that, determining that the objective attribute target attribute of the target keyword includes:
The target keyword is inputted into trained target nerve network model in advance, obtains the target nerve network model
The target keyword of output corresponds to the probability of every attribute, wherein the attribute that the probability is greater than predetermined threshold is determined as
The objective attribute target attribute.
5. the method according to claim 1, wherein according to the objective attribute target attribute determine in the target text to
The target object of mark includes:
It receives and instruction is chosen according to the objective attribute target attribute selected object;
The corresponding object of instruction is chosen to be determined as the target object by described.
6. the method according to any one of claims 1 to 5, which is characterized in that in the target category to the target object
Property by identical mark identify be associated after mark, the method also includes:
Establish simultaneously the second predetermined position of display interface show relationship classification logotype, wherein the relationship classification be identified as into
The mark of the corresponding relationship of the objective attribute target attribute of row association mark;
The corresponding mark of relationship classification logotype objective attribute target attribute corresponding with the relationship classification logotype is established into association.
7. according to the method described in claim 6, it is characterized in that, by the relationship classification logotype and the relationship classification mark
Know the corresponding mark of corresponding objective attribute target attribute to establish after association, the method also includes:
Reception chooses the first of the relationship classification logotype to choose instruction, chooses instruction to highlight the pass according to described first
It is classification logotype and the corresponding objective attribute target attribute of the relationship classification logotype;Or
Reception chooses the second of the objective attribute target attribute to choose instruction, chooses instruction to highlight the target category according to described second
Property and the corresponding relationship classification logotype of the objective attribute target attribute.
8. a kind of text marking device characterized by comprising
First obtains module, for obtaining target text to be marked and objective attribute target attribute to be marked;
Determining module, for determining target object to be marked in the target text according to the objective attribute target attribute, wherein described
Target object includes at least two target keywords;
It is associated with labeling module, mark is associated by identical mark mark for the objective attribute target attribute to the target object,
Wherein, described to be identified as mark corresponding with the objective attribute target attribute.
9. a kind of storage medium, which is characterized in that be stored with computer program in the storage medium, wherein the computer
Program is arranged to execute method described in described any one of claims 1 to 7 when operation.
10. a kind of electronic device, including memory and processor, which is characterized in that be stored with computer journey in the memory
Sequence, the processor are arranged to run the computer program to execute side described in described any one of claims 1 to 7
Method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910679022.8A CN110377743B (en) | 2019-07-25 | 2019-07-25 | Text labeling method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910679022.8A CN110377743B (en) | 2019-07-25 | 2019-07-25 | Text labeling method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110377743A true CN110377743A (en) | 2019-10-25 |
CN110377743B CN110377743B (en) | 2022-07-08 |
Family
ID=68256131
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910679022.8A Active CN110377743B (en) | 2019-07-25 | 2019-07-25 | Text labeling method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110377743B (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111324706A (en) * | 2020-01-21 | 2020-06-23 | 全球能源互联网研究院有限公司 | Labeling method and device and electronic equipment |
CN112560408A (en) * | 2020-12-18 | 2021-03-26 | 广东轩辕网络科技股份有限公司 | Text labeling method, text labeling device, text labeling terminal and storage medium |
CN112784588A (en) * | 2021-01-21 | 2021-05-11 | 北京百度网讯科技有限公司 | Method, device, equipment and storage medium for marking text |
CN113592981A (en) * | 2021-07-01 | 2021-11-02 | 北京百度网讯科技有限公司 | Picture labeling method and device, electronic equipment and storage medium |
CN113822013A (en) * | 2021-03-08 | 2021-12-21 | 京东科技控股股份有限公司 | Labeling method and device for text data, computer equipment and storage medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107729319A (en) * | 2017-10-18 | 2018-02-23 | 百度在线网络技术(北京)有限公司 | Method and apparatus for output information |
US20180113856A1 (en) * | 2016-10-26 | 2018-04-26 | Abbyy Infopoisk Llc | Producing training sets for machine learning methods by performing deep semantic analysis of natural language texts |
CN109325121A (en) * | 2018-09-14 | 2019-02-12 | 北京字节跳动网络技术有限公司 | Method and apparatus for determining the keyword of text |
CN109460541A (en) * | 2018-09-27 | 2019-03-12 | 广州大学 | Lexical relation mask method, device, computer equipment and storage medium |
-
2019
- 2019-07-25 CN CN201910679022.8A patent/CN110377743B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20180113856A1 (en) * | 2016-10-26 | 2018-04-26 | Abbyy Infopoisk Llc | Producing training sets for machine learning methods by performing deep semantic analysis of natural language texts |
CN107729319A (en) * | 2017-10-18 | 2018-02-23 | 百度在线网络技术(北京)有限公司 | Method and apparatus for output information |
CN109325121A (en) * | 2018-09-14 | 2019-02-12 | 北京字节跳动网络技术有限公司 | Method and apparatus for determining the keyword of text |
CN109460541A (en) * | 2018-09-27 | 2019-03-12 | 广州大学 | Lexical relation mask method, device, computer equipment and storage medium |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111324706A (en) * | 2020-01-21 | 2020-06-23 | 全球能源互联网研究院有限公司 | Labeling method and device and electronic equipment |
CN111324706B (en) * | 2020-01-21 | 2023-05-26 | 全球能源互联网研究院有限公司 | Labeling method and device and electronic equipment |
CN112560408A (en) * | 2020-12-18 | 2021-03-26 | 广东轩辕网络科技股份有限公司 | Text labeling method, text labeling device, text labeling terminal and storage medium |
CN112784588A (en) * | 2021-01-21 | 2021-05-11 | 北京百度网讯科技有限公司 | Method, device, equipment and storage medium for marking text |
CN112784588B (en) * | 2021-01-21 | 2023-09-22 | 北京百度网讯科技有限公司 | Method, device, equipment and storage medium for labeling text |
CN113822013A (en) * | 2021-03-08 | 2021-12-21 | 京东科技控股股份有限公司 | Labeling method and device for text data, computer equipment and storage medium |
CN113822013B (en) * | 2021-03-08 | 2024-04-05 | 京东科技控股股份有限公司 | Labeling method and device for text data, computer equipment and storage medium |
CN113592981A (en) * | 2021-07-01 | 2021-11-02 | 北京百度网讯科技有限公司 | Picture labeling method and device, electronic equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN110377743B (en) | 2022-07-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110377743A (en) | A kind of text marking method and device | |
CN108595494B (en) | Method and device for acquiring reply information | |
CN110275935A (en) | Processing method, device and storage medium, the electronic device of policy information | |
CN107251060A (en) | For the pre-training and/or transfer learning of sequence label device | |
CN104951456A (en) | Method, device and equipment used for obtaining answer information | |
CN105117387B (en) | A kind of intelligent robot interactive system | |
CN104933084A (en) | Method, apparatus and device for acquiring answer information | |
CN104076944A (en) | Chat emoticon input method and device | |
CN105446592A (en) | Application icon classification and displaying method and device | |
CN105224775A (en) | Based on the method and apparatus that picture processing is arranged in pairs or groups to clothes | |
CN109522068A (en) | The edit methods of the methods of exhibiting and system of the page, page data | |
CN105989112B (en) | A kind of method and server of application program classification | |
CN109218390A (en) | User's screening technique and device | |
CN109513211A (en) | Processing method, device and the game resource display systems of fine arts resource file | |
CN110263338A (en) | Replace entity name method, apparatus, storage medium and electronic device | |
CN110287313A (en) | A kind of the determination method and server of risk subject | |
CN108319888A (en) | The recognition methods of video type and device, terminal | |
CN111523324A (en) | Training method and device for named entity recognition model | |
CN107330009A (en) | Descriptor disaggregated model creation method, creating device and storage medium | |
CN110717312B (en) | Text labeling method and device | |
CN108140055A (en) | Trigger application message | |
CN110210479A (en) | A kind of text information extraction method on waste items | |
CN109857861A (en) | File classification method, device, server and medium based on convolutional neural networks | |
CN105389333B (en) | A kind of searching system construction method and server architecture | |
CN106844732A (en) | The method that automatic acquisition is carried out for the session context label that cannot directly gather |
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 |