CN109543003A - A kind of system object similarity determines method and device - Google Patents
A kind of system object similarity determines method and device Download PDFInfo
- Publication number
- CN109543003A CN109543003A CN201811390480.1A CN201811390480A CN109543003A CN 109543003 A CN109543003 A CN 109543003A CN 201811390480 A CN201811390480 A CN 201811390480A CN 109543003 A CN109543003 A CN 109543003A
- Authority
- CN
- China
- Prior art keywords
- system object
- matching degree
- feature words
- similarity
- word
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Abstract
The present invention provides a kind of system object similarity and determines method and device, and the system object is the system object in cloud computing management system, this method comprises: obtaining the relevant information of the first system object and second system object respectively；The Feature Words of the first system object and second system object are obtained respectively；Based on default semantic word dictionary, the semantic word of the Feature Words correspondence mappings of the first system object and second system object is obtained respectively；Determine the second matching degree of the first matching degree of the Feature Words of the first system object and second system object and the semantic word of the first system object and second system object；The similarity of the first system object and second system object is determined according to the first matching degree and the second matching degree.The present invention improves the accuracy rate and efficiency for judging system object instead of the operation for manually going to judge the similarity between system object.
Description
Technical field
The present invention relates to cloud computing administrative skill fields more particularly to a kind of system object similarity to determine method and dress
It sets.
Background technique
With the development of cloud computing technology, often there are many system objects in cloud computing management system.These systems pair
As being often made of contents of object, object functionality description, object oriented, object link etc..When system object mistake in a system
When more, user goes to select these system objects often very difficult manually.System generally requires to recommend these users automatically
The system object of preference goes to manually select instead of user to the system object of these user preferences of user or auto-associating.
System recommendation and affiliated partner just need a kind of method for studying relationship between system object, provide a kind of high efficiency
System object recommended method.
Summary of the invention
The present invention provides a kind of method and device of determining system object similarity, can substitute and manually go judgement system pair
The operation of similarity as between has improved the accuracy rate and efficiency for judging system object.
In a first aspect, the present invention, which provides a kind of system object similarity, determines method, the system object is cloud computing pipe
System object in reason system, this method comprises:
The relevant information of the first system object and second system object is obtained respectively；
The Feature Words of the first system object and second system object are obtained respectively；
Based on default semantic word dictionary, the Feature Words correspondence mappings of the first system object and second system object are obtained respectively
Semantic word；
Determine the first matching degree and the first system object and of the Feature Words of the first system object and second system object
Second matching degree of the semantic word of two system object；
The similarity of the first system object and second system object is determined according to the first matching degree and the second matching degree.
Optionally, the Feature Words of the first system object and second system object are obtained respectively, comprising:
Sentence division is carried out from the relevant information in the first system object/second system object；
Based on the sentence that sentence divides, removes redundancy vocabulary in the sentence and obtain Feature Words.
Optionally, the default semantic word dictionary is Feature Words and the semantic field of corresponding semanteme word for including default scene
Scape word dictionary.
Optionally it is determined that the first matching degree of the Feature Words of the first system object and second system object, comprising:
According in the Feature Words of the Feature Words of the first system object and second system object, the identical number of Feature Words
Determine the first matching degree.
Optionally it is determined that the second matching degree of the semantic word of the first system object and second system object, comprising:
According in the semantic word of the Feature Words of the first system object and second system object, the identical number of semantic word
Determine the second matching degree.
Optionally, the first system object and second system object are determined according to the first matching degree and the second matching degree
Similarity, comprising:
It sums after being multiplied respectively with corresponding weighting coefficient to the first matching degree and the second matching degree, is finally matched
Degree；
The similarity of the first system object and second system object is determined according to the final matching degree.
Optionally, this method further include:
When a system object in the first system object and second system object is browsed, according to described first
The similarity of system object and second system object, it is determined whether link the second system object.
Optionally, the relevant information of the first system object/second system object includes following any or multiple letters
Breath:
System object content, the description of system object function, system object name, system object link, system object icon.
Second aspect, the present invention provides a kind of system object similarity determining device, including memory and processor, described
Memory is stored with program code, when said program code is executed by the processor, so that processor execution is above-mentioned
The step of determining system object similarity based method.
The third aspect, the present invention provide a kind of computer storage medium, and the computer storage medium is stored with program generation
Code, when the step of said program code is performed, and executes the method for above-mentioned determining system object similarity.
Determine method and device using system object similarity provided in an embodiment of the present invention, it is specific following the utility model has the advantages that
1) by combining two kinds of matching results of character feature and semantic feature, the degree of association of system object is sentenced
It is disconnected, the similarity between system object is obtained, the precision of system object similarity is improved；
2) instead of the operation for manually going the similarity in judgement system between system object, judgement system object is improved
Accuracy rate and efficiency.
Detailed description of the invention
Fig. 1 is that system object similarity provided in an embodiment of the present invention determines method flow diagram；
Fig. 2 is system object similarity determining device structure chart provided in an embodiment of the present invention.
Specific embodiment
To make the objectives, technical solutions, and advantages of the present invention clearer, below in conjunction with attached drawing to the present invention make into
It is described in detail to one step, it is clear that the described embodiments are only some of the embodiments of the present invention, rather than whole implementation
Example.Based on the embodiments of the present invention, obtained by those of ordinary skill in the art without making creative efforts
All other embodiment, shall fall within the protection scope of the present invention.
Embodiment 1
The present invention provides a kind of system object similarity and determines method, which, which is in cloud computing management system, is
System object, as shown in Figure 1, this method comprises:
Step 101, the relevant information of the first system object and second system object is obtained respectively；
Above-mentioned the first system object and second system object are any two system object in cloud computing management system, in reality
Shi Zhong, multiple system objects in available cloud computing management system take out two systems object, according to the present embodiment every time
Method determine the similarity between two systems object, may thereby determine that in multiple system objects every two not homologous ray pair
Similarity as between.
The first system object/second system object relevant information includes following any or appoints multiple information:
System object content, the description of system object function, system object name, system object link, system object icon.
Step 102, the Feature Words of the first system object and second system object are obtained respectively；
May include in relevant information in the first system object/second system object multistage words and/or multiple sentences and/or
Multiple words can according to need the Feature Words extraction method for determining use, from the first system object/second system pair in an implementation
As extracting corresponding Feature Words in middle relevant information.
Feature Words in the present embodiment can be understood as the relevant word of characterization system object feature.
Step 103, based on default semantic word dictionary, the Feature Words of the first system object and second system object are obtained respectively
The semantic word of correspondence mappings；
In an implementation, the semantic word dictionary including multiple semantic words is pre-established, can according to need and determine whether to establish
Feature word lexicon, and establish in semantic word dictionary the mapping relations in semantic word and feature word lexicon between Feature Words.It is obtaining
When Feature Words, based on the mapping relations between Feature Words in word semantic in semantic word dictionary and feature word lexicon, determines and obtain spy
Levy word mapped semanteme word.
As another optional embodiment, feature word lexicon can not also be established, certain rule can be set,
When obtaining Feature Words, is determined according to preset rules and obtain Feature Words mapped semanteme word.
Semantic word mentioned in the present embodiment can be the relevant semanteme word with scene.
For example, there are a series of semantic words in a semantic word dictionary such as: refrigerator, air-conditioning, washing machine, electromagnetic oven, electric wind
Fan, mobile phone, water heater, TV.And the Feature Words of certain system object include: refrigeration, food, clothes cleans, fresh-keeping etc..According to
The mapping relations of Feature Words and semantic word, food and fresh-keeping will be mapped to semantic word refrigerator；Refrigeration can be mapped to air-conditioning
This semantic word；Clothes, cleaning can be mapped to washing machine semanteme word.In conclusion the Feature Words of this system object are reflected
The semantic word penetrated includes refrigerator, air-conditioning, washing machine.
Step 104, the first matching degree and the first system of the Feature Words of the first system object and second system object are determined
Second matching degree of the semantic word of object and second system object；
In an implementation, the first system object and second system object can be determined using corresponding matching degree algorithm
First matching degree of Feature Words；
In an implementation, the semanteme of the first system object and second system object can be determined using corresponding matching degree algorithm
Second matching degree of word.
Step 105, the first system object and second system object are determined according to the first matching degree and the second matching degree
Similarity.
Cloud computing management system has a certain number of system objects, these system objects are by system object content, system
The information such as object functionality description, system object name, system object link, system object icon are constituted.These system objects
For information there is similar relationship, the high object of similarity can be used to recommend by system user or auto-associating one
It rises, it is user-friendly.
As previously mentioned, system recommendation and affiliated partner just need a kind of method for studying relationship between system object.This hair
It is bright that a kind of method of system object similarity in determining cloud computing management system is provided, it can by the similarity between system object
To determine the correlation degree between system object.
It is right due to by combining two kinds of matching results of character feature and semantic feature after taking method of the invention
The degree of association of system object is judged, the similarity between object is obtained, and improves the precision of system object similarity；It replaces
For the operation for manually going the similarity in judgement system between object, the accuracy rate and efficiency for judging system object are improved.
The relevant information of system object is often user oriented in cloud computing management system, can include more without practical meaning
Justice cannot characterize the conjunction in the redundancy of system object feature, such as some descriptive sentences.In an implementation, it obtains respectively
Take the Feature Words of the first system object and second system object, comprising:
Sentence division is carried out from the relevant information in the first system object/second system object；
Based on the sentence that sentence divides, removes redundancy vocabulary in the sentence and obtain Feature Words.
For example, the relevant information of a system object is usually one section of word, this section of words are divided into several semantemes first
Independent sentence.Then the subject and other related terms in sentence are found out, is split.Then around these subjects and
Other related terms extract adjective and the verb containing Special Significance, split.Finally, these are split
Word forms feature set of words.
Optionally, above-mentioned default semantic word dictionary is Feature Words and the semantic field of corresponding semanteme word for including default scene
Scape word dictionary.
Optionally it is determined that the first matching degree of the Feature Words of the first system object and second system object, comprising:
According in the Feature Words of the Feature Words of the first system object and second system object, the identical number of Feature Words is determined
First matching degree.
In an implementation, by the feature phrase of the Feature Words composition characteristic set of words of the first system object and second system object
At feature set of words carry out string matching, according to successful match character string number calculate score value, obtain the first matching degree
Numerical value.
Optionally it is determined that the second matching degree of the semantic word of the first system object and second system object, comprising:
According in the semantic word of the semantic word of the first system object and second system object, the identical number of semantic word
Determine the second matching degree.
In an implementation, the semantic word of the first system object is formed to the semantic phrase of semantic set of words and second system object
At semantic set of words carry out string matching, according to successful match character string number calculate score value, obtain the second matching degree
Numerical value.
Optionally, the first system object and second system object are determined according to the first matching degree and the second matching degree
Similarity, comprising:
It sums after being multiplied respectively with corresponding weighting coefficient to the first matching degree and the second matching degree, is finally matched
Degree；
The similarity of the first system object and second system object is determined according to the final matching degree.
In an implementation, the weighting coefficient and the second matching degree of the first matching degree can be set according to the characteristics of system object
Weighting coefficient.
The weighting coefficient of first matching degree and the weighting coefficient of the second matching degree can be the same or different.
As an alternative embodiment, the weighting coefficient of the second matching degree is greater than the weighting coefficient of the first matching degree.
Optionally, this method a further include: system object in the first system object and second system object
When being browsed, according to the similarity of the first system object and second system object, it is determined whether link the second system
Object.
In an implementation, multiple systems in cloud computing management system have been determined according to the above method provided in an embodiment of the present invention
Similarity between object between any two system objects a, when system object is browsed wherein, according to the system object
Recommend the higher system of similarity according to the sequence of similarity from high to low with the similarity between other each system objects
The efficiency of system object recommendation can be improved in object.
Embodiment 2
The embodiment of the present invention provides a kind of system object similarity determining device, including memory and processor, described to deposit
Reservoir is stored with program code, when said program code is executed by the processor, so that the processor executes following step
It is rapid:
The relevant information of the first system object and second system object is obtained respectively；
The Feature Words of the first system object and second system object are obtained respectively；
Based on default semantic word dictionary, the Feature Words correspondence mappings of the first system object and second system object are obtained respectively
Semantic word；
Determine the first matching degree and the first system object and of the Feature Words of the first system object and second system object
Second matching degree of the semantic word of two system object；
The similarity of the first system object and second system object is determined according to the first matching degree and the second matching degree.
Optionally, above-mentioned processor obtains the Feature Words of the first system object and second system object respectively, comprising:
Sentence division is carried out from the relevant information in the first system object/second system object；
Based on the sentence that sentence divides, removes redundancy vocabulary in the sentence and obtain Feature Words.
Optionally, the default semantic word dictionary is Feature Words and the semantic field of corresponding semanteme word for including default scene
Scape word dictionary.
Optionally, above-mentioned processor determines the first matching degree of the Feature Words of the first system object and second system object,
Include:
According in the Feature Words of the Feature Words of the first system object and second system object, the identical number of Feature Words
Determine the first matching degree.
Optionally, above-mentioned processor determines the second matching degree of the semantic word of the first system object and second system object,
Include:
According in the semantic word of the semantic word of the first system object and second system object, the identical number of semantic word
Determine the second matching degree.
Optionally, above-mentioned processor determines the first system object and according to the first matching degree and the second matching degree
The similarity of two system object, comprising:
It sums after being multiplied respectively with corresponding weighting coefficient to the first matching degree and the second matching degree, is finally matched
Degree；
The similarity of the first system object and second system object is determined according to the final matching degree.
Optionally, above-mentioned processor is also used to:
When a system object in the first system object and second system object is browsed, according to described first
The similarity of system object and second system object, it is determined whether link the second system object.
Optionally, the relevant information of the first system object/second system object includes following any or multiple letters
Breath:
System object content, the description of system object function, system object name, system object link, system object icon.
As shown in Fig. 2, the embodiment of the present invention provides second of system object similarity determining device, the system object is
System object in cloud computing management system, which is characterized in that the device includes:
Relevant information acquiring unit 201, for obtaining the relevant information of the first system object and second system object respectively；
Feature Words acquiring unit 202, for obtaining the Feature Words of the first system object and second system object respectively；
Semantic determination unit 203, for obtaining the first system object and second system respectively based on default semantic word dictionary
The semantic word of the Feature Words correspondence mappings of object；
Matching degree determination unit 204, first of the Feature Words for determining the first system object and second system object
Second matching degree of the semantic word with degree and the first system object and second system object；
Similarity determining unit 205, for determining the first system object according to the first matching degree and the second matching degree
With the similarity of second system object.
Optionally, Feature Words acquiring unit 202 obtains the Feature Words of the first system object and second system object respectively, packet
It includes:
Sentence division is carried out from the relevant information in the first system object/second system object；
Based on the sentence that sentence divides, removes redundancy vocabulary in the sentence and obtain Feature Words.
Optionally, the default semantic word dictionary is Feature Words and the semantic field of corresponding semanteme word for including default scene
Scape word dictionary.
Optionally, matching degree determination unit 204, for determining the Feature Words of the first system object and second system object
First matching degree, comprising:
According in the Feature Words of the Feature Words of the first system object and second system object, the identical number of Feature Words
Determine the first matching degree.
Optionally, matching degree determination unit 204, for determining the semantic word of the first system object and second system object
Second matching degree, comprising:
According in the semantic word of the semantic word of the first system object and second system object, the identical number of semantic word
Determine the second matching degree.
Optionally, similarity determining unit 205, for determining first system according to the first matching degree and the second matching degree
The similarity of system object and second system object, comprising:
It sums after being multiplied respectively with corresponding weighting coefficient to the first matching degree and the second matching degree, is finally matched
Degree；
The similarity of the first system object and second system object is determined according to the final matching degree.
Similarity determining unit 205 is also used to a system in the first system object and second system object
When object is browsed, according to the similarity of the first system object and second system object, it is determined whether link described second
System object.
Optionally, the relevant information of the first system object/second system object includes following any or multiple letters
Breath:
System object content, the description of system object function, system object name, system object link, system object icon.
The embodiment of the present invention also provides a kind of computer storage medium, and the computer storage medium is stored with program generation
Code, when the step of said program code is performed, and execution the provided system object similarity of above-described embodiment 1 determines method.
It should be understood by those skilled in the art that, the embodiment of the present invention can provide as method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the present invention
Apply the form of example.Moreover, it wherein includes the computer of computer usable program code that the present invention, which can be used in one or more,
The shape for the computer program product implemented in usable storage medium (including but not limited to magnetic disk storage and optical memory etc.)
Formula.
The present invention be referring to according to the method for the embodiment of the present invention, the process of equipment (system) and computer program product
Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions
The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs
Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real
The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
Obviously, various changes and modifications can be made to the invention without departing from essence of the invention by those skilled in the art
Mind and range.In this way, if these modifications and changes of the present invention belongs to the range of the claims in the present invention and its equivalent technologies
Within, then the present invention is also intended to include these modifications and variations.
Claims (10)
1. a kind of system object similarity determines method, the system object is the system object in cloud computing management system,
It is characterized in that, this method comprises:
The relevant information of the first system object and second system object is obtained respectively；
The Feature Words of the first system object and second system object are obtained respectively；
Based on default semantic word dictionary, the language of the Feature Words correspondence mappings of the first system object and second system object is obtained respectively
Adopted word；
Determine the first matching degree and the first system object and the second system of the Feature Words of the first system object and second system object
Second matching degree of the semantic word of system object；
The similarity of the first system object and second system object is determined according to the first matching degree and the second matching degree.
2. the method according to claim 1, wherein obtaining the first system object and second system object respectively
Feature Words, comprising:
Sentence division is carried out from the relevant information in the first system object/second system object；
Based on the sentence that sentence divides, removes redundancy vocabulary in the sentence and obtain Feature Words.
3. the method according to claim 1, wherein the default semantic word dictionary is the spy for including default scene
Levy the semantic scene word dictionary of word with corresponding semantic word.
4. the method according to claim 1, wherein determining the feature of the first system object and second system object
First matching degree of word, comprising:
According in the Feature Words of the Feature Words of the first system object and second system object, the identical number of Feature Words is determined
First matching degree.
5. the method according to claim 1, wherein determining the semanteme of the first system object and second system object
Second matching degree of word, comprising:
According in the semantic word of the Feature Words of the first system object and second system object, the identical number of semantic word is determined
Second matching degree.
6. the method according to claim 1, wherein determining described according to the first matching degree and the second matching degree
The similarity of one system object and second system object, comprising:
It sums after being multiplied respectively with corresponding weighting coefficient to the first matching degree and the second matching degree, obtains final matching degree；
The similarity of the first system object and second system object is determined according to the final matching degree.
7. the method according to claim 1, which is characterized in that further include:
When a system object in the first system object and second system object is browsed, according to the first system
The similarity of object and second system object, it is determined whether link the second system object.
8. the method according to claim 1, wherein the first system object/second system object correlation
Information includes following any or appoints multiple information:
System object content, the description of system object function, system object name, system object link, system object icon.
9. a kind of system object similarity determining device, which is characterized in that including memory and processor, the memory storage
There is program code, when said program code is executed by the processor, so that the processor perform claim requires 1~8
The step of one the method.
10. a kind of computer storage medium, which is characterized in that the computer storage medium is stored with program code, when described
The step of program code is performed, and perform claim requires 1~8 any the method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811390480.1A CN109543003A (en) | 2018-11-21 | 2018-11-21 | A kind of system object similarity determines method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811390480.1A CN109543003A (en) | 2018-11-21 | 2018-11-21 | A kind of system object similarity determines method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109543003A true CN109543003A (en) | 2019-03-29 |
Family
ID=65849086
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811390480.1A Pending CN109543003A (en) | 2018-11-21 | 2018-11-21 | A kind of system object similarity determines method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109543003A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113283821A (en) * | 2021-07-22 | 2021-08-20 | 腾讯科技（深圳）有限公司 | Virtual scene processing method and device, electronic equipment and computer storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103258045A (en) * | 2013-05-24 | 2013-08-21 | 百度在线网络技术（北京）有限公司 | System and method for confirming recommended content |
| CN103617157A (en) * | 2013-12-10 | 2014-03-05 | 东北师范大学 | Text similarity calculation method based on semantics |
| CN103631858A (en) * | 2013-10-24 | 2014-03-12 | 杭州电子科技大学 | Science and technology project similarity calculation method |
| CN105760544A (en) * | 2016-03-16 | 2016-07-13 | 合网络技术（北京）有限公司 | Video recommendation method and device |
| CN107273913A (en) * | 2017-05-11 | 2017-10-20 | 武汉理工大学 | A kind of short text similarity calculating method based on multi-feature fusion |
| CN108763566A (en) * | 2018-06-05 | 2018-11-06 | 北京玄科技有限公司 | Text similarity computing method and device, intelligent robot |
-
2018
- 2018-11-21 CN CN201811390480.1A patent/CN109543003A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103258045A (en) * | 2013-05-24 | 2013-08-21 | 百度在线网络技术（北京）有限公司 | System and method for confirming recommended content |
| CN103631858A (en) * | 2013-10-24 | 2014-03-12 | 杭州电子科技大学 | Science and technology project similarity calculation method |
| CN103617157A (en) * | 2013-12-10 | 2014-03-05 | 东北师范大学 | Text similarity calculation method based on semantics |
| CN105760544A (en) * | 2016-03-16 | 2016-07-13 | 合网络技术（北京）有限公司 | Video recommendation method and device |
| CN107273913A (en) * | 2017-05-11 | 2017-10-20 | 武汉理工大学 | A kind of short text similarity calculating method based on multi-feature fusion |
| CN108763566A (en) * | 2018-06-05 | 2018-11-06 | 北京玄科技有限公司 | Text similarity computing method and device, intelligent robot |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113283821A (en) * | 2021-07-22 | 2021-08-20 | 腾讯科技（深圳）有限公司 | Virtual scene processing method and device, electronic equipment and computer storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| TWI664540B (en) | Search word error correction method and device, and weighted edit distance calculation method and device | |
| US10777192B2 (en) | Method and apparatus of recognizing field of semantic parsing information, device and readable medium | |
| CN112533051B (en) | Barrage information display method, barrage information display device, computer equipment and storage medium | |
| US20200110882A1 (en) | Bipartite graph-based topic categorization system | |
| CN106484777B (en) | Multimedia data processing method and device | |
| CN110162753B (en) | Method, apparatus, device and computer readable medium for generating text template | |
| CN109410913B (en) | Voice synthesis method, device, equipment and storage medium | |
| CN112487173B (en) | Man-machine conversation method, device and storage medium | |
| CN109657054A (en) | Abstraction generating method, device, server and storage medium | |
| CN107526846B (en) | Method, device, server and medium for generating and sorting channel sorting model | |
| CN111883122B (en) | Speech recognition method and device, storage medium and electronic equipment | |
| CN110472043B (en) | Clustering method and device for comment text | |
| JP6884947B2 (en) | Dialogue system and computer programs for it | |
| CN111382260A (en) | Method, device and storage medium for correcting retrieved text | |
| CN109918513A (en) | Image processing method, device, server and storage medium | |
| CN110162780A (en) | The recognition methods and device that user is intended to | |
| CN110287405B (en) | Emotion analysis method, emotion analysis device and storage medium | |
| CN109961041A (en) | A kind of video frequency identifying method, device and storage medium | |
| CN110633464A (en) | Semantic recognition method, device, medium and electronic equipment | |
| CN109857873A (en) | The method and apparatus of recommended entity, electronic equipment, computer-readable medium | |
| CN110362601A (en) | Mapping method, device, equipment and the storage medium of metadata standard | |
| CN112818227B (en) | Content recommendation method and device, electronic equipment and storage medium | |
| CN110019832B (en) | Method and device for acquiring language model | |
| CN109543003A (en) | A kind of system object similarity determines method and device | |
| CN110727853A (en) | Presenting controlled heterogeneous digital content to a user |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190329 |