CN108509555A - Search term determines method, apparatus, equipment and storage medium - Google Patents
Search term determines method, apparatus, equipment and storage medium Download PDFInfo
- Publication number
- CN108509555A CN108509555A CN201810239645.9A CN201810239645A CN108509555A CN 108509555 A CN108509555 A CN 108509555A CN 201810239645 A CN201810239645 A CN 201810239645A CN 108509555 A CN108509555 A CN 108509555A
- Authority
- CN
- China
- Prior art keywords
- mark
- character set
- words
- word
- search term
- 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
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention discloses search terms to determine that method, apparatus, equipment and storage medium, this method include:Obtain the mark of character set;The stop words in the character set is segmented and removed to the character set, obtains target set of words;Seek the association relationship of the mark and each target word in the target set of words;Using the corresponding target word of the association relationship for meeting preset threshold condition as the search term of the mark.It solves determined by the prior art, is used for the relatively low technical problem of the accuracy of the search term of searching character set or character set mark, has reached the character set accurately and rapidly searched using target word as search term corresponding to mark or mark.
Description
Technical field
The present embodiments relate to technical field of data processing more particularly to a kind of search term to determine method, apparatus, equipment
And storage medium.
Background technology
In searching for scene, in order to improve search efficiency and accuracy rate, it may search for except through the mark of character set
To outside character set, user also wants to correctly search for required character set by certain relevant search terms.For example, right
In live streaming platform, direct broadcasting room has the mark and main broadcaster ID (mark for being equivalent to character set) of itself, and in addition main broadcaster also has
It some nicknames or exhales and (is equivalent to search term), the fans of main broadcaster can be by the identification search direct broadcasting room of direct broadcasting room, but powder
Silk be more likely to the nickname by main broadcaster or exhale search direct broadcasting room.Since the nickname and address of main broadcaster may be many and usual
Be not unalterable, need to use the mode of artificial screening to set relevant search word for main broadcaster at present, but in this way accuracy compared with
It is low, and there is hysteresis quality.
Invention content
Search term provided in an embodiment of the present invention determines method, apparatus, equipment and storage medium, for solving the prior art
It is identified, it is used for the relatively low technical problem of the accuracy of the search term of searching character set or character set mark.
In a first aspect, an embodiment of the present invention provides a kind of search terms to determine method, including:
Obtain the mark of character set;
The stop words in the character set is segmented and removed to the character set, obtains target set of words;
Seek the association relationship of the mark and each target word in the target set of words;
Using the corresponding target word of the association relationship for meeting preset threshold condition as the search term of the mark.
Further, before the title for obtaining character set, including;
Determine character set is identified as direct broadcasting room mark.
Further, the title for obtaining character set, including;
Using the set of multiple session contents of direct broadcasting room as character set;
The direct broadcasting room is identified into the mark as the character set.
Further, the set using multiple session contents of direct broadcasting room includes as character set:
Using every section of session content of direct broadcasting room as a document;
The character for being included using the document for meeting default document condition is as character set.
Further, described that the stop words in the character set is segmented and removed to the character set, obtain mesh
Set of words is marked, including:
The character set is pre-processed to update the character set, the pretreatment includes during Traditional Chinese turns
Text is simplified and/or goes additional character;
The stop words in the updated character set is removed, target set of words is obtained.
Further, the association relationship for seeking the mark and each target word in the target set of words, including:
Using occurrence number in target set of words or the frequency of occurrences higher than preset times or the target word of predeterminated frequency as pair
As target word;
Obtain occurrence number or the frequency of occurrences of the mark in the target set of words;
Obtain the mark and each co-occurrence number or co-occurrence frequency of the subject object word in the character set;
According to the occurrence number or the frequency of occurrences of the subject object word, the occurrence number of the mark or the frequency of occurrences with
And the co-occurrence number or co-occurrence frequency of the mark and the subject object word, seek the mark and the subject object word
Association relationship;
Wherein, the frequency is the ratio of occurrence number or co-occurrence number and the number of documents.
Further, described using the corresponding target word of the association relationship for meeting preset threshold condition as the search of the mark
Word, including:
The association relationship is ranked up, and will meet the corresponding target word of association relationship of default ranking condition as
Candidate search word;
It is more than the candidate search word of default value as the search term of the mark using occurrence number or the frequency of occurrences.
Second aspect, the embodiment of the present invention additionally provide a kind of search term determining device, which includes:
Identifier acquisition module, the mark for obtaining character set;
Target set of words acquisition module stops for the character set to be segmented and removed in the character set
Word obtains target set of words;
Association relationship seeks module, the mutual trust for seeking the mark and each target word in the target set of words
Breath value;
Search term determining module, the corresponding target word of association relationship for that will meet preset threshold condition is as the mark
The search term of knowledge.
The third aspect, the embodiment of the present invention additionally provide a kind of equipment, and the equipment includes:
One or more processors;
Storage device, for storing one or more programs;
When one or more of programs are executed by one or more of processors so that one or more of processing
Device realizes that search term as described in relation to the first aspect determines method.
Fourth aspect, the embodiment of the present invention additionally provide a kind of storage medium including computer executable instructions, special
Sign is that the computer executable instructions by computer processor when being executed for executing search as described in relation to the first aspect
Word determines method.
Search term provided in this embodiment determines the technical solution of method, obtains the mark of character set;To character set
It is segmented and removes the stop words in character set to obtain target set of words;Seek each of mark and target set of words
The association relationship of target word determines each target word and the mark of character set by the association relationship between mark and target word
Strength of association;Using the corresponding target word of the association relationship for meeting preset threshold condition as the search term of mark.By default
Threshold condition is determined can be with since target word and mark have the strong degree of association with target word of the mark with the strong degree of association
The character set corresponding to mark or mark is accurately and rapidly searched using target word as search term.
Description of the drawings
To describe the technical solutions in the embodiments of the present invention more clearly, make required in being described below to embodiment
Attached drawing does one and simply introduces, it should be apparent that, drawings in the following description are some embodiments of the invention, for this
For the those of ordinary skill of field, without creative efforts, others are can also be obtained according to these attached drawings
Attached drawing.
Fig. 1 is the flow chart that the search term that the embodiment of the present invention one provides determines method;
Fig. 2 is the flow chart that search term provided by Embodiment 2 of the present invention determines method;
Fig. 3 is the flow chart of the method for the mark provided by Embodiment 2 of the present invention for obtaining character set;
Fig. 4 is the flow chart that association relationship provided by Embodiment 2 of the present invention determines method;
Fig. 5 is the structure diagram for the search term determining device that the embodiment of the present invention three provides;
Fig. 6 is the structure diagram for the equipment that the embodiment of the present invention four provides.
Specific implementation mode
To make the object, technical solutions and advantages of the present invention clearer, hereinafter with reference to attached in the embodiment of the present invention
Figure, technical scheme of the present invention is clearly and completely described by embodiment, it is clear that described embodiment is the present invention one
Section Example, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art are not doing
Go out the every other embodiment obtained under the premise of creative work, shall fall within the protection scope of the present invention.
Embodiment one
Fig. 1 is the flow chart that the search term that the embodiment of the present invention one provides determines method.The technical solution of the present embodiment is suitable
The case where search term for determining searching character set, the case where being particularly suitable for determining the search term of search direct broadcasting room.It should
Method can be executed by search term determining device provided in an embodiment of the present invention, which may be used software and/or hardware
Mode realize, and configure apply in the processor.As shown in Figure 1, this method specifically comprises the following steps:
S101, the mark for obtaining character set.
The character set of the present embodiment can be the character set of single document, can also be the character set of multiple documents
It closes, certainly, the character in document can come from any scene.The mark of character set can be the title or word of character set
The ID of set is accorded with, also or other character fields that can indicate the character set.
S102, the stop words in character set is segmented and removed to character set, obtain target set of words.
Character set is pre-processed to update character set, pretreatment include Traditional Chinese turn Simplified Chinese and/or
Go additional character;Participle operation is carried out to character set, character set is divided into several words, it then will be in character set
Stop words removes, for example, remove, etc. not no practical significance word, obtain with the practical target word for indicating meaning
Set.The amount of analysis of character data can be reduced by removing stop words, and then improves the speed that search term determines.It needs to illustrate
, stop words can be removed by the general deactivated vocabulary of the prior art, can also by with usage scenario is relevant deactivates
Vocabulary removes.
S103, the association relationship for seeking mark and each target word in target set of words.
The search term for determining the mark for searching character set or character set is needed from several target set of words
In find out word of the mark with larger strength of association with character set or character set.The present embodiment passes through association relationship
Embody the strength of association between character, specially:Seek the association relationship of mark and each target word in target set of words.
S104, using the corresponding target word of the association relationship for meeting preset threshold condition as mark search term.
Preset threshold condition in the present embodiment includes association relationship ranking condition and target word in target set of words or word
Occurrence number or frequency in symbol set.The association relationship sought is ranked up, and the mutual of default ranking condition will be met
The corresponding target word of the value of information ensures that candidate search word has larger strength of association with mark as candidate search word, with this;
It is more than the candidate search word of default value as the search term identified using occurrence number or frequency, it is ensured that the frequency of use of search term
It is higher, it is further ensured that the accuracy of search term.
The search term of the present embodiment determines the technical solution of method, obtains the mark of character set;Character set is carried out
It segments and removes the stop words in character set to obtain target set of words;Seek mark and each target in target set of words
The association relationship of word determines the pass of each target word and the mark of character set by the association relationship between mark and target word
Join intensity;Using the corresponding target word of the association relationship for meeting preset threshold condition as the search term of mark, pass through predetermined threshold value
Condition is determined can be with target since target word and mark have the strong degree of association with target word of the mark with the strong degree of association
Word is that search term accurately and rapidly searches mark or identifies corresponding character set.
Embodiment two
Fig. 2 is the flow chart that search term provided by Embodiment 2 of the present invention determines method.As shown in Fig. 2, the present invention is implemented
Example on the basis of the above embodiments, before the title for obtaining character set, it is straight to increase being identified as determining character set
The step of being identified between broadcasting.Correspondingly, the method for the present embodiment includes:
S200, determine that the direct broadcasting room that is identified as of character set identifies.
When usage scenario is direct broadcasting room, the mark of character set corresponds to direct broadcasting room mark.Direct broadcasting room in the present embodiment
Mark can be title, the direct broadcasting room ID of direct broadcasting room, also or similar to main broadcaster's title etc. can uniquely indicate the mark of direct broadcasting room.
S201, the mark for obtaining character set.
As shown in figure 3, when usage scenario is direct broadcasting room, the method for obtaining the mark of character set includes:
S2011, using the set of multiple session contents of direct broadcasting room as character set.
For direct broadcasting room in live streaming, user would generally send dialogue to reach mutual with main broadcaster or other users by dialog box
Dynamic purpose, such as barrage.The present embodiment, which summarizes user by the character that dialog box is sent, is used as session content.Optionally,
The present embodiment, which summarizes the character that a user is sent by dialog box within a preset period of time, is used as a session content, each
Session content corresponds to a document, using the set of the corresponding document content of multiple session contents as character set.Preset time
The length of section should be set according to actual use situation, such as one month time span.
S2012, direct broadcasting room is identified into the mark as character set.
Using the title of direct broadcasting room or ID or other identifier as the mark of character set.
S202, the stop words in character set is segmented and removed to character set, obtain target set of words.
S203, the association relationship for seeking mark and each target word in target set of words.
When determining the search term for searching for direct broadcasting room, needing to find out from target set of words has with direct broadcasting room mark
The word of larger strength of association.The present embodiment embodies the strength of association between character by association relationship, specially:It seeks straight
The association relationship of mark and each target word in target set of words between broadcasting.
Association relationship can determine that the present embodiment passes through correlation first by the occurrence number or frequency of relevant character
The occurrence number of character illustrates, as shown in figure 4, the determination method of association relationship is as follows:
S2031, the target word using occurrence number in target set of words higher than preset times are as subject object word.
Some phrase will become search term, usually have higher frequency of use, i.e. its appearance in character set
Number is higher.The present embodiment first obtains the number of documents N that character set is distributed, and each target word in target set of words or
Then occurrence number in character set or target set of words is higher than the mesh of preset times by the number f (s) occurred in character set
Word is marked as subject object word, the model of the target set of words to be analyzed is further reduced with the access times by target word
It encloses, under the premise of ensureing the accuracy of search term determination, improves search term constant speed degree really.
S2032, occurrence number of the mark in target set of words is obtained.
It obtains direct broadcasting room and identifies the occurrence number f (k) in target set of words.
S2033, mark and co-occurrence number of each subject object word in target set of words are obtained.
The number that direct broadcasting room mark occurs with each subject object word in target set of words or character set jointly is obtained,
That is the co-occurrence number f (k, s) of the two.
S2034, it is total to subject object word according to the occurrence number of subject object word, the occurrence number of mark and mark
Occurrence number seeks the association relationship of mark and subject object word.
The occurrence number of occurrence number, mark based on the subject object word obtained, mark and subject object word go out
Occurrence number and number of documents N determine the association relationship of mark k and subject object word s by following formula, specially:
In addition, since the co-occurrence frequency p (k, s) between direct broadcasting room mark and subject object word is represented by:
P (k, s)=f (k, s)/N 1.2
Frequency of occurrences p (k) of the direct broadcasting room mark in target set of words or character set is represented by:
P (k)=f (k)/N 1.3
Frequency of occurrences p (s) of the subject object word in target set of words or character set is represented by:
P (s)=f (s)/N 1.4
Thus show that direct broadcasting room mark and the association relationship of subject object word are:
It i.e. also can be by the frequency of occurrences of the direct broadcasting room mark in target set of words or character set, subject object word in mesh
The frequency of occurrences in set of words or character set is marked, and mark and subject object word are in target set of words or character set
Co-occurrence frequency come seek mark subject object word between association relationship.
Illustratively, it is assumed that collected 10000 documents, i.e. N=10000, the wherein name of direct broadcasting room by data
The number that word k occurs is referred to as 100 times, and the number that subject object word s occurs is 40 times, title word k and subject object word s co-occurrences
Number is 20 times, therefore:
That is the association relationship of title word k and subject object word s is 3.912.Seek accordingly title word k respectively with each object
The association relationship of target word.
S204, using the corresponding target word of the association relationship for meeting preset threshold condition as mark search term.
Association relationship is ranked up, and the corresponding target word of association relationship of default ranking condition will be met as search
Word, to ensure that direct broadcasting room mark and selected target word have higher strength of association.For the usage scenario of direct broadcasting room, when
When direct broadcasting room is identified as direct broadcasting room title, search term may be ID marks, main broadcaster's title or main broadcaster's nickname of direct broadcasting room etc..Example
Property, when identified search term is main broadcaster's title or main broadcaster's nickname, user can be by searching for main broadcaster's title or master at this time
Nickname is broadcast to search for direct broadcasting room.
The embodiment of the present invention defines the usage scenario of direct broadcasting room, and the access times by limiting target word reduce target
The quantity of word, and by association relationship sequence the larger target word of strength of association is selected and identified as search term, thus
Reach the technique effect of rapidly and accurately determining search term.
Embodiment three
Fig. 5 is the structure diagram for the search term determining device that the embodiment of the present invention three provides.The device is above-mentioned for executing
The search term that any embodiment is provided determines method, which is chosen as software or hardware realization.As shown in figure 5, the device
Including:
Identifier acquisition module 11, the mark for obtaining character set;
Target set of words acquisition module 12, for being segmented and being removed in the character set to the character set
Stop words obtains target set of words;
Association relationship seeks module 13, mutual with each target word in the target set of words for seeking the mark
The value of information;
Search term determining module 14, described in the corresponding target word of association relationship for that will meet preset threshold condition is used as
The search term of mark.
The technical solution of search term determining device provided in an embodiment of the present invention, obtains the mark of character set;To character
Set is segmented and removes the stop words in character set to obtain target set of words;It seeks in mark and target set of words
The association relationship of each target word determines each target word and character set by the association relationship between mark and target word
The strength of association of mark;Using the corresponding target word of the association relationship for meeting preset threshold condition as the search term of mark, pass through
Preset threshold condition determines the target word for having the strong degree of association with mark, since target word and mark have the strong degree of association,
The character set corresponding to mark or mark can be accurately and rapidly searched using target word as search term.
The search term determining device that the embodiment of the present invention is provided can perform the search that any embodiment of the present invention is provided
Word determines method, has the corresponding function module of execution method and advantageous effect.
Example IV
Fig. 6 is the structural schematic diagram for the equipment that the embodiment of the present invention four provides, as shown in fig. 6, the equipment includes processor
201, memory 202, input unit 203 and output device 204;The quantity of processor 201 can be one or more in equipment
It is a, in Fig. 6 by taking a processor 201 as an example;Processor 201, memory 202, input unit 203 in equipment and output dress
Setting 204 can be connected by bus or other modes, in Fig. 6 for being connected by bus.
Memory 202 is used as a kind of computer readable storage medium, can be used for storing software program, computer can perform journey
Sequence and module, as the search term in the embodiment of the present invention determines the corresponding program instruction/module of method (for example, mark obtains
Module 11, target set of words acquisition module 12, association relationship seek module 13 and search term determining module 14).Processor 201 is logical
Cross operation and be stored in software program, instruction and module in memory 202, to execute equipment various function application and
Data processing realizes that above-mentioned search term determines method.
Memory 202 can include mainly storing program area and storage data field, wherein storing program area can store operation system
Application program needed for system, at least one function;Storage data field can be stored uses created data etc. according to terminal.This
Outside, memory 202 may include high-speed random access memory, can also include nonvolatile memory, for example, at least one
Disk memory, flush memory device or other non-volatile solid state memory parts.In some instances, memory 202 can be into one
Step includes the memory remotely located relative to processor 201, these remote memories can pass through network connection to equipment.On
The example for stating network includes but not limited to internet, intranet, LAN, mobile radio communication and combinations thereof.
Input unit 203 can be used for receiving the number or character information of input, and generate with the user setting of equipment with
And the related key signals input of function control.
Output device 204 may include that display screen etc. shows equipment, for example, the display screen of user terminal.
Embodiment five
The embodiment of the present invention five also provides a kind of storage medium including computer executable instructions, and the computer can be held
Row instruction determines that method, this method include when being executed by computer processor for executing search term:
Obtain the mark of character set;
The stop words in the character set is segmented and removed to the character set, obtains target set of words;
Seek the association relationship of the mark and each target word in the target set of words;
Using the corresponding target word of the association relationship for meeting preset threshold condition as the search term of the mark.
Certainly, a kind of storage medium including computer executable instructions that the embodiment of the present invention is provided, computer
The method operation that executable instruction is not limited to the described above, it is true to can also be performed the search term that any embodiment of the present invention is provided
Determine the relevant operation in method.
By the description above with respect to embodiment, it is apparent to those skilled in the art that, the present invention
It can be realized by software and required common hardware, naturally it is also possible to which by hardware realization, but the former is more in many cases
Good embodiment.Based on this understanding, technical scheme of the present invention substantially in other words contributes to the prior art
Part can be expressed in the form of software products, which can be stored in computer readable storage medium
In, such as the floppy disk of computer, read-only memory (Read-Only Memory, abbreviation ROM), random access memory (Random
Access Memory, abbreviation RAM), flash memory (FLASH), hard disk or CD etc., including some instructions are used so that a calculating
Machine equipment (can be personal computer, server or the network equipment etc.) executes the search described in each embodiment of the present invention
Word determines method.
It is worth noting that, in the embodiment of above-mentioned search term determining device, included each unit and module are
It is divided according to function logic, but is not limited to above-mentioned division, as long as corresponding function can be realized;Separately
Outside, the specific name of each functional unit is also only to facilitate mutually distinguish, the protection domain being not intended to restrict the invention.
Note that above are only presently preferred embodiments of the present invention and institute's application technology principle.It will be appreciated by those skilled in the art that
The present invention is not limited to specific embodiments described here, can carry out for a person skilled in the art it is various it is apparent variation,
It readjusts and substitutes without departing from protection scope of the present invention.Therefore, although being carried out to the present invention by above example
It is described in further detail, but the present invention is not limited only to above example, without departing from the inventive concept, also
May include other more equivalent embodiments, and the scope of the present invention is determined by scope of the appended claims.
Claims (10)
1. a kind of search term determines method, which is characterized in that including:
Obtain the mark of character set;
The stop words in the character set is segmented and removed to the character set, obtains target set of words;
Seek the association relationship of the mark and each target word in the target set of words;
Using the corresponding target word of the association relationship for meeting preset threshold condition as the search term of the mark.
2. according to the method described in claim 1, it is characterized in that, it is described obtain character set title before, including;
Determine character set is identified as direct broadcasting room mark.
3. according to the method described in claim 2, it is characterized in that, it is described obtain character set title, including;
Using the set of multiple session contents of direct broadcasting room as character set;
The direct broadcasting room is identified into the mark as the character set.
4. according to the method described in claim 3, it is characterized in that, it is described using the set of multiple session contents of direct broadcasting room as
Character set includes:
Using every section of session content of direct broadcasting room as a document;
The character for being included using the document for meeting default document condition is as character set.
5. according to the method described in claim 1, it is characterized in that, described segment the character set and removed described
Stop words in character set obtains target set of words, including:
The character set is pre-processed to update the character set, the pretreatment includes that Traditional Chinese turns Chinese letter
Body and/or go additional character;
The stop words in the updated character set is removed, target set of words is obtained.
6. according to the method described in claim 4, it is characterized in that, described seek in the mark and the target set of words
The association relationship of each target word, including:
Using occurrence number in target set of words or frequency higher than the target word of preset times or frequency as subject object word;
Obtain occurrence number or the frequency of occurrences of the mark in the target set of words;
Obtain the mark and each co-occurrence number or co-occurrence frequency of the subject object word in the character set;
According to the occurrence number or the frequency of occurrences, the occurrence number of the mark or the frequency of occurrences and institute of the subject object word
The co-occurrence number or co-occurrence frequency for stating mark and the subject object word seek the mutual trust of the mark and the subject object word
Breath value;
Wherein, the frequency is the ratio of occurrence number or co-occurrence number and the number of documents.
7. according to any methods of claim 1-5, which is characterized in that the mutual information that preset threshold condition will be met
It is worth search term of the corresponding target word as the mark, including:
The association relationship is ranked up, and the corresponding target word of association relationship of default ranking condition will be met as candidate
Search term;
It is more than the candidate search word of default value as the search term of the mark using occurrence number or the frequency of occurrences.
8. a kind of search term determining device, which is characterized in that including:
Identifier acquisition module, the mark for obtaining character set;
Target set of words acquisition module, for deactivating in the character set to be segmented and removed to the character set
Word obtains target set of words;
Association relationship seeks module, the mutual information for seeking the mark and each target word in the target set of words
Value;
Search term determining module, the corresponding target word of association relationship for that will meet preset threshold condition is as the mark
Search term.
9. a kind of equipment, which is characterized in that the equipment includes:
One or more processors;
Storage device, for storing one or more programs;
When one or more of programs are executed by one or more of processors so that one or more of processors are real
Now the search term as described in any in claim 1-7 determines method.
10. a kind of storage medium including computer executable instructions, which is characterized in that the computer executable instructions by
When computer processor executes method is determined for executing the search term as described in any in claim 1-7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810239645.9A CN108509555B (en) | 2018-03-22 | 2018-03-22 | Search term determination method, device, equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810239645.9A CN108509555B (en) | 2018-03-22 | 2018-03-22 | Search term determination method, device, equipment and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108509555A true CN108509555A (en) | 2018-09-07 |
CN108509555B CN108509555B (en) | 2021-07-23 |
Family
ID=63378031
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810239645.9A Active CN108509555B (en) | 2018-03-22 | 2018-03-22 | Search term determination method, device, equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108509555B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110430476A (en) * | 2019-08-05 | 2019-11-08 | 广州华多网络科技有限公司 | Direct broadcasting room searching method, system, computer equipment and storage medium |
CN110674365A (en) * | 2019-09-06 | 2020-01-10 | 腾讯科技(深圳)有限公司 | Searching method, device, equipment and storage medium |
CN112735428A (en) * | 2020-12-27 | 2021-04-30 | 科大讯飞(上海)科技有限公司 | Hot word acquisition method, voice recognition method and related equipment |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH10171807A (en) * | 1996-12-13 | 1998-06-26 | Nec Corp | Device and method for canceling semantic ambiguity |
CN101055588A (en) * | 2007-05-25 | 2007-10-17 | 北京搜狗科技发展有限公司 | Method for catching limit word information, optimizing output and input method system |
CN101609459A (en) * | 2009-07-21 | 2009-12-23 | 北京大学 | A kind of extraction system of affective characteristic words |
CN102929873A (en) * | 2011-08-08 | 2013-02-13 | 腾讯科技(深圳)有限公司 | Method and device for extracting searching value terms based on context search |
CN103020212A (en) * | 2012-12-07 | 2013-04-03 | 合一网络技术(北京)有限公司 | Method and device for finding hot videos based on user query logs in real time |
CN104063387A (en) * | 2013-03-19 | 2014-09-24 | 三星电子(中国)研发中心 | Device and method abstracting keywords in text |
CN107590214A (en) * | 2017-08-30 | 2018-01-16 | 腾讯科技(深圳)有限公司 | The recommendation method, apparatus and electronic equipment of search key |
CN107659559A (en) * | 2017-08-24 | 2018-02-02 | 网易(杭州)网络有限公司 | A kind of games system |
-
2018
- 2018-03-22 CN CN201810239645.9A patent/CN108509555B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH10171807A (en) * | 1996-12-13 | 1998-06-26 | Nec Corp | Device and method for canceling semantic ambiguity |
CN101055588A (en) * | 2007-05-25 | 2007-10-17 | 北京搜狗科技发展有限公司 | Method for catching limit word information, optimizing output and input method system |
CN101609459A (en) * | 2009-07-21 | 2009-12-23 | 北京大学 | A kind of extraction system of affective characteristic words |
CN102929873A (en) * | 2011-08-08 | 2013-02-13 | 腾讯科技(深圳)有限公司 | Method and device for extracting searching value terms based on context search |
CN103020212A (en) * | 2012-12-07 | 2013-04-03 | 合一网络技术(北京)有限公司 | Method and device for finding hot videos based on user query logs in real time |
CN104063387A (en) * | 2013-03-19 | 2014-09-24 | 三星电子(中国)研发中心 | Device and method abstracting keywords in text |
CN107659559A (en) * | 2017-08-24 | 2018-02-02 | 网易(杭州)网络有限公司 | A kind of games system |
CN107590214A (en) * | 2017-08-30 | 2018-01-16 | 腾讯科技(深圳)有限公司 | The recommendation method, apparatus and electronic equipment of search key |
Non-Patent Citations (1)
Title |
---|
张锋 等: "基于互信息的中文术语抽取系统", 《计算机应用研究》 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110430476A (en) * | 2019-08-05 | 2019-11-08 | 广州华多网络科技有限公司 | Direct broadcasting room searching method, system, computer equipment and storage medium |
CN110674365A (en) * | 2019-09-06 | 2020-01-10 | 腾讯科技(深圳)有限公司 | Searching method, device, equipment and storage medium |
CN112735428A (en) * | 2020-12-27 | 2021-04-30 | 科大讯飞(上海)科技有限公司 | Hot word acquisition method, voice recognition method and related equipment |
Also Published As
Publication number | Publication date |
---|---|
CN108509555B (en) | 2021-07-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110543574B (en) | Knowledge graph construction method, device, equipment and medium | |
CN109145099B (en) | Question-answering method and device based on artificial intelligence | |
CN106649818B (en) | Application search intention identification method and device, application search method and server | |
CN104252533B (en) | Searching method and searcher | |
CN105357586B (en) | Video barrage filter method and device | |
JP5894335B2 (en) | A system, apparatus, and method for recommending a thesaurus in an input method. | |
US20190205477A1 (en) | Method for Processing Fusion Data and Information Recommendation System | |
JP6163607B2 (en) | Method and apparatus for constructing event knowledge database | |
CN109710841B (en) | Comment recommendation method and device | |
CN107220098B (en) | Method and device for implementing rule engine | |
CN111061750A (en) | Query processing method and device and computer readable storage medium | |
CN109800414A (en) | Faulty wording corrects recommended method and system | |
CN108509555A (en) | Search term determines method, apparatus, equipment and storage medium | |
CN106528894B (en) | The method and device of label information is set | |
DE102021000736A1 (en) | Model-based semantic text search | |
CN110895656B (en) | Text similarity calculation method and device, electronic equipment and storage medium | |
CN112541095B (en) | Video title generation method and device, electronic equipment and storage medium | |
CN102982125B (en) | A kind of method and apparatus for determining synonym text | |
CN111488453B (en) | Resource grading method, device, equipment and storage medium | |
Moon et al. | Memory graph networks for explainable memory-grounded question answering | |
CN109190116B (en) | Semantic analysis method, system, electronic device and storage medium | |
JP6867963B2 (en) | Summary Evaluation device, method, program, and storage medium | |
CN113886568A (en) | Text abstract generation method and device | |
CN112148844A (en) | Information reply method and device for robot | |
CN104899310A (en) | Information ranking method, and method and device for generating information ranking model |
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 |