CN104462326A - Person relation analyzing method as well as method and device for providing person information - Google Patents
Person relation analyzing method as well as method and device for providing person information Download PDFInfo
- Publication number
- CN104462326A CN104462326A CN201410721415.8A CN201410721415A CN104462326A CN 104462326 A CN104462326 A CN 104462326A CN 201410721415 A CN201410721415 A CN 201410721415A CN 104462326 A CN104462326 A CN 104462326A
- Authority
- CN
- China
- Prior art keywords
- name
- character
- character relation
- relation information
- personage
- 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
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/951—Indexing; Web crawling techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/221—Parsing markup language streams
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Machine Translation (AREA)
Abstract
The invention provides a person relation analyzing method as well as a method and a device for providing person information. The method comprises the following steps: abstracting a plurality of sentences in content data related to a person; conducting interdependency analysis on the sentences respectively to generate a plurality of interdependency analysis trees; conducting semantic character tagging on the sentences respectively according to the interdependency analysis trees to generate a plurality of semantic character tagging results; generating a person time and space relation chart according to the semantic character tagging results; generating a person relation knowledge base of the interest person according to the person time and space relation chart. The person relation knowledge base related to the person is acquired accurately by conducting interdependency analysis and semantic character tagging on the person content data; abundant and accurate person relation information is provided for a user.
Description
Technical field
The present invention relates to natural language processing technique field, particularly relate to a kind of by computer implemented character relation analytical approach, the method providing people information and device.
Background technology
Take personage as the search of core be one of important need of searching products.Demand mainly comprises: the information such as the concrete name of input, the biography searching this personage and nearest activity.When user inputs concrete name, when searching the information relevant to name, search engine not only can show normal result for retrieval, but also can provide a relevant search list.In relevant search list, the result with the name of user search with certain degree of association can be shown.
Fig. 1 is that existing personage is correlated with the schematic diagram of search listing.As shown in Figure 1, when inputting retrieve statement " Zhang Yaqin ", in relevant search list, occurred " Zhang Xinyu " this name, and " Zhang Xinyu " is the daughter of " Zhang Yaqin ", is not well-known female star.
In above-mentioned search procedure, Search Results result in the synonym of name.In addition, the content shown in relevant search list is more at random, has very large randomness, makes user cannot obtain information needed for oneself.
Summary of the invention
Embodiments of the invention provide a kind of by computer implemented character relation analytical approach, the method providing people information and device, by carrying out natural language analysis to content-data, automatically to obtain the higher character relation knowledge base of accuracy, and provide abundant to user, the information of character relation accurately.
According to an aspect of the present invention, provide a kind of by computer implemented character relation analytical approach.Described method comprises: extract multiple statement from the content-data relevant to personage; Respectively dependency analysis is carried out to described multiple statement, generate multiple dependency analysis tree; Respectively semantic character labeling is carried out to described multiple statement according to described multiple dependency analysis tree, generate multiple semantic character labeling result; Personage's time-space relationship table is generated according to described multiple semantic character labeling result; The character relation knowledge base paying close attention to personage is generated according to described personage's time-space relationship table.
According to a further aspect in the invention, provide a kind of method providing people information, described method comprises: receive the search word comprising the first name; Obtain the character relation information relevant to described the first name according to described first name from the character relation knowledge base prestored, described character relation information comprises at least one second name and the relation data with described first name thereof; Send described character relation information.
According to a further aspect in the invention, provide a kind of method providing people information, described method comprises: obtain the search word comprising the first name; Described search word is sent to server; Receive the character relation information relevant to described the first name from described server, described character relation information comprises at least one second name and the relation data with described first name thereof; Show described character relation information.According to a further aspect in the invention, a kind of character relation analytical equipment is provided.Described device comprises: statement extracting unit, for extracting multiple statement from the content-data relevant to personage; Dependency analysis unit, for carrying out dependency analysis to described multiple statement respectively, generates multiple dependency analysis tree; Semantic character labeling unit, for carrying out semantic character labeling to described multiple statement respectively according to described multiple dependency analysis tree, generates multiple semantic character labeling result; Personage's time-space relationship table generation unit, for generating personage's time-space relationship table according to described multiple semantic character labeling result; Character relation knowledge base generation unit, for generating the character relation knowledge base paying close attention to personage according to described personage's time-space relationship table.
According to a further aspect in the invention, a kind of device that people information is provided is provided.Described device comprises: search word receiving element, for receiving the search word comprising the first name; Character relation information acquisition unit, for obtaining the character relation information relevant to described the first name according to described first name from the character relation knowledge base prestored, described character relation information comprises at least one second name and the relation data with described first name thereof; Character relation information transmitting unit, for sending described character relation information.
According to a further aspect in the invention, provide a kind of device providing people information, described device comprises: search word acquiring unit, for obtaining the search word comprising the first name; Search word transmitting element, for sending to server by described search word; Character relation information receiving unit, for receiving the character relation information relevant to described the first name from described server, described character relation information comprises at least one second name and the relation data with described first name thereof; Character relation information display unit, for showing described character relation information.
The embodiment of the present invention provide by computer implemented character relation analytical approach, people information method and device are provided, by carrying out dependency analysis and semantic character labeling to personage's content-data, thus obtain the character relation knowledge base relevant to personage exactly, and provide abundant to user, the information of character relation accurately.
Accompanying drawing explanation
Fig. 1 is that existing personage is correlated with the schematic diagram of search listing;
Fig. 2 is the process flow diagram of the character relation analytical approach that the embodiment of the present invention provides;
Fig. 3 is the process flow diagram providing the method for people information that the embodiment of the present invention provides;
Fig. 4 is the process flow diagram providing the method for people information that another embodiment of the present invention provides;
Fig. 5 is the logic diagram of the character relation analytical equipment that the embodiment of the present invention provides;
Fig. 6 is the logic diagram providing the device of people information that the embodiment of the present invention provides;
Fig. 7 is the logic diagram providing the device of people information that another embodiment of the present invention provides;
Fig. 8 is the schematic diagram of the semantic character labeling result that the embodiment of the present invention provides;
Fig. 9 is the schematic diagram of the relation between the dependency analysis that provides of the embodiment of the present invention and semantic character labeling;
Figure 10 is the example of the personage's time-space relationship entry generated based on the semantic character labeling result of multiple statement according to the embodiment of the present invention;
Figure 11 is the schematic diagram of the character relation information that the embodiment of the present invention provides;
Figure 12 is the schematic diagram of another character relation information that the embodiment of the present invention provides.
Embodiment
Present general inventive concept of the present invention is, statement is extracted from the content-data relating to personage, described statement is comprised to the natural language analysis of dependency analysis and semantic character labeling, thus obtain the character relation knowledge base relevant to personage exactly, and provide the character relation information relevant to predetermined name according to described character relation knowledge base to user.
Below in conjunction with accompanying drawing to the embodiment of the present invention provide by computer implemented character relation analysis, provide people information method and device to be described in detail.
Fig. 2 is the process flow diagram of the character relation analytical approach that the embodiment of the present invention provides.
With reference to Fig. 2, in step S201, extract multiple statement from the content-data relevant to personage.
Step S202, carries out dependency analysis to described multiple statement respectively, generates multiple dependency analysis tree.
Here, described content-data can be about the encyclopaedia webpage of personage, the news web page relating to personage or information webpage.
Particularly, according to exemplary embodiment of the present invention, in step S201, from described content-data identification name, and extract multiple statement according to described name from described content-data.In step S202, respectively dependency analysis being carried out to described multiple statement according to shifting near reduction algorithm, generating multiple dependency analysis tree.
For " I likes China " the words, the dependency tree obtained after dependency analysis can be expressed as:
| Sequence number | Word | Father node | Relation |
| 1 | I | 2 | Subject-predicate |
| 2 | Like | 0 | |
| 3 | China | 2 | Meaning guest |
Namely 2 dependence arcs are obtained: " I ← sbv love " and " China ← vob likes ".Wherein that sbv representative is subject-verb, i.e. " subject-predicate " relation; That vob represents is verb-object, i.e. " meaning guest relation ".Dependency tree portrays the structural information of sentence from grammer angle, interdependent dependence between each word that just can be obtained a statement by this dependency tree, namely " I " modifies " love ", is " subject-predicate " relation, is " calling guest " relation between " love " and " China " between them.
After this, in step S203, respectively semantic character labeling is carried out to described multiple statement according to described multiple dependency analysis tree, generate multiple semantic character labeling result.
According to exemplary embodiment of the present invention, in the process of step S203, for arbitrary described statement, identify predicate wherein and argument thereof, and determine the semantic role (such as: the role such as agent, word denoting the receiver of an action, time, place) of its each argument and character labeling is carried out to described argument.
Here, semantic character labeling portrays emphatically the structural information of statement from semantic angle.Semanteme typically refers to the predicate in statement, first identifies the predicate in statement and the argument relevant to predicate, then determines the semantic role composition of each argument, finally carry out character labeling to argument.Such as, statement " Christina beat Scott with baseball yesterday ", by carrying out character labeling to this statement, thus obtains the schematic diagram of the semantic character labeling result that the embodiment of the present invention as shown in Figure 8 provides.As shown in Figure 8, according to semantic character labeling result, can put question to as follows: " who has beaten Scott with baseball? ", " who has been beaten by Christina baseball? ", " Scott what Christina beaten with? " and " Scott when Christina is beaten with baseball? " Deng.
By step S202 and step S203 to the dependency analysis of statement and semantic character labeling, dependency analysis that the embodiment of the present invention as shown in Figure 9 provides and semantic character labeling relation schematic diagram can be obtained.As shown in Figure 9, after carrying out dependency analysis and semantic character labeling to statement " the child Lucas of Xie Tingfeng and Zhang Baizhi has been born ", the semantic character labeling result obtained is " entity-Xie thunderbolt cutting edge of a knife or a sword; Attribute-child; Value-Lucas ".
In step S204, generate personage's time-space relationship table according to described multiple semantic character labeling result.Each entry in described personage's time-space relationship table can comprise following key element: personage 1, personage 2, relation, when and where.
By step S203, semantic character labeling is carried out to multiple statement, identify the ornamental equivalents such as " predicate " and " time ", " place " and " argument " relevant to " predicate " of each statement, other three key elements such as " time ", " place " and " personage " can be determined further by the process of step S204, wherein, described " predicate " is the relational factors in entry.
Figure 10 is the example of the personage's time-space relationship entry generated based on the semantic character labeling result of multiple statement according to the embodiment of the present invention.As shown in Figure 10, the place (Seattle) and time (2009) that within 2009, can hold is extracted from sentence " Microsoft can hold in Microsoft Headquarters Seattle for 2009 ", from the argument " Bill Gates " of sentence " Bill Gates has at the meeting carried out cordial and friendly talk with Zhang Yaqin and its wife " extraction " talk ", " Zhang Yaqin ", " at the meeting " (place), in conjunction with the semantic character labeling result of aforementioned two sentences, < Bill Gates can be generated, Zhang Yaqin, talks, 2009, personage's time-space relationship entry of Seattle >.
As can be seen from aforesaid example, in order to the semantic character labeling result of multiple statement is integrated, need to carry out normalized process to the data related to, comprise named entity recognition, the semantic disambiguation of demonstrative pronoun, the normalization of abbreviation and the normalization of time representation and automatically calculate.
Named entity recognition (Named Entity Recognition, NER) mainly carries out Automatic Extraction and integration to information such as name, place name and times.
The elimination of ambiguity is mainly carried out in the semantic disambiguation of demonstrative pronoun to the infull name information occurred in content-data and pronoun information, make infull name information and pronoun information unification.Such as " Julius happy spreads ", " Caesar ", " he ", " Julius Caesar " etc. are all the same persons " Julius happy spreads " referred to, and in order to disambiguation, need its infull name information and pronoun to be unified into a name.
The normalization of abbreviation is that full name and abbreviation are carried out normalizing.Such as " U.S. " and " United States of America " all refer to the U.S..
The normalization of time representation is mainly normalized the time relevant to personage with automatically calculating and automatically calculates.Such as Zhang Yaqin is born in 1966,12 year old that year, he was admitted to " classes for exceptionally gifted children in colleges and universities of China Science & Technology University ", here " 12 years old " can be calculated by " 1966+12=1978 ", in order to be normalized, can be rewritten as " within 1978, Zhang Yaqin has been admitted to classes for exceptionally gifted children in colleges and universities of China Science & Technology University ".
In step S205, generate the character relation knowledge base paying close attention to personage according to described personage's time-space relationship table.
In the entry comprised in described personage's time-space relationship table, the personage 1 related to and personage 2 are parallel, that is, if one section of article comprises the content about Zhang Yaqin, Li Yanhong, Li Kaifu, grand using Li Yan in the Li Kaifu entry as personage 1 and personage 2 in the personage's time-space relationship table so generated, also may be comprised.In step S205, using Zhang Yaqin as concern personage, carry out the tissue of relation, event around Zhang Yaqin, generate character relation knowledge base.
What the embodiment of the present invention provided realizes character relation analytical approach by computing machine, by carrying out dependency analysis and semantic character labeling to multiple statement, thus obtains the character relation knowledge relevant to personage exactly.Fig. 3 is the process flow diagram providing the method for people information that the embodiment of the present invention provides, and with reference to Fig. 3, the method comprises the following steps:
Step S301, receives the search word comprising the first name.
Step S302, obtain the character relation information relevant to described the first name according to described first name from the character relation knowledge base prestored, described character relation information comprises at least one second name and the relation data with described first name thereof.
Step S303, sends described character relation information.
According to a preferred embodiment of the invention, described method also comprises: the described character relation information obtained in step S302 classified according to family relationship and social relationships.
Figure 11 and Figure 12 is the schematic diagram of the character relation information that the embodiment of the present invention provides respectively.
Wherein, " intension+stranger " part comprises the information of the family relationship according to aforementioned preferred embodiments classification gained, comprises wife Zhang Yaqin, daughter Zhang Yaqin etc.; " extension+stranger " part comprises the information of social relationships, as peaceful platinum (University of Science and Technology classes for exceptionally gifted children in colleges and universities classmate), Li Kaifu (msra colleague), Tang Jun (ms colleague), Li Yanhong (present boss) etc.
According to another preferred embodiment of the invention, described method also comprises: the described character relation information of time order and function order to classification occurred according to the relation of described first name and the second name sorts.Such as, with forming Peer Relationships with Zhang Yaqin, Li Kaifu works together compared with Li Yan grand early knowing each other with Zhang Yaqin, therefore in " colleague " relation, Lee can be opened multiple bank before Li Yanhong.
According to another preferred embodiment of the invention, described method also comprises: sort according to the height of its user's clicking rate to the second name of identical social relationships.
Figure 12 is another character relation information schematic diagram that the embodiment of the present invention provides.
The method of what the embodiment of the present invention provided provide people information, by the character relation knowledge base of aforementioned generation, can provide abundant, character relation information accurately.
Fig. 4 is that the another kind that the embodiment of the present invention provides provides people information method flow diagram.As shown in Figure 4, the method comprises the following steps:
Step S401, receives the search word comprising the first name.
Step S402, sends to server by described search word.
Step S403, receive the character relation information relevant to described the first name from described server, described character relation information comprises at least one second name and the relation data with described first name thereof.
Step S404, shows described character relation information.
According to a preferred embodiment of the invention, described character relation information is the data be classified according to family relationship and social relationships, in step S403, and the described character relation information of classification display.
According to another preferred embodiment of the invention, the described character relation information of described classification is the data that the time order and function order occurred according to the relation of described first name and the second name is sorted.The another kind that the embodiment of the present invention provides provides people information method, the character relation information relevant to the first name sent by reception server, thus shows character relation information intuitively.
Fig. 5 is the character relation analytical equipment schematic diagram that the embodiment of the present invention provides.
With reference to Fig. 5, described character relation analytical equipment comprises statement extracting unit 501, dependency analysis unit 502, semantic character labeling unit 503, personage's time-space relationship table generation unit 504 and character relation knowledge base generation unit 505.
Statement extracting unit 501 is for extracting multiple statement from the content-data relevant to personage.
Dependency analysis unit 502, for carrying out dependency analysis to described multiple statement respectively, generates multiple dependency analysis tree.Such as, dependency analysis unit 502 can carry out dependency analysis to described multiple statement respectively according to shifting near reduction algorithm, generates multiple dependency analysis tree.
Semantic character labeling unit 503, for carrying out semantic character labeling to described multiple statement respectively according to described multiple dependency analysis tree, generates multiple semantic character labeling result.
According to exemplary embodiment of the present invention, described semantic character labeling unit 503, for arbitrary described statement, identifies predicate wherein and argument thereof, and determines the semantic role of its each argument and carry out character labeling to described argument.
Personage's time-space relationship table generation unit 504 is for generating personage's time-space relationship table according to described multiple semantic character labeling result.
Character relation knowledge base generation unit 505 is for generating the character relation knowledge base paying close attention to personage according to described personage's time-space relationship table.According to exemplary embodiment of the present invention, described content-data is about the encyclopaedia webpage of personage, the news web page relating to personage or information webpage.
The character relation analytical equipment that the embodiment of the present invention provides, by carrying out dependency analysis and semantic character labeling to multiple statement, thus obtains the character relation knowledge base relevant to personage exactly.
Fig. 6 is the logic diagram providing the device of people information that the embodiment of the present invention provides.
With reference to Fig. 6, described in provide the device of people information to comprise search word receiving element 601, character relation information acquisition unit 602 and character relation information transmitting unit 603.
Search word receiving element 601 comprises the search word of the first name for receiving.
Character relation information acquisition unit 602 is for obtaining the character relation information relevant to described the first name according to described first name from the character relation knowledge base prestored, and described character relation information comprises at least one second name and the relation data with described first name thereof.
Character relation information transmitting unit 603 is for sending described character relation information.
According to exemplary embodiment of the present invention, described device also comprises: taxon (not shown) is used for the described character relation information obtained to classify according to family relationship and social relationships.
According to exemplary embodiment of the present invention, described device also comprises: the first sequencing unit (not shown) sorts for the described character relation information of time order and function order to classification occurred according to the relation of described first name and the second name.
According to exemplary embodiment of the present invention, described device also comprises: the second sequencing unit (not shown) is used for sorting according to the height of its user's clicking rate to the second name of identical social relationships.
The one that the embodiment of the present invention provides provides people information device, by the character relation knowledge base prestored, thus provide abundant, character relation information accurately.
Fig. 7 is the logic diagram providing the device of people information that another embodiment of the present invention provides.
With reference to Fig. 7, described in provide the device of people information to comprise search word acquiring unit 701, search word transmitting element 702, character relation information receiving unit 703 and character relation information display unit 704.
Search word acquiring unit 701 comprises the search word of the first name for obtaining.
Search word transmitting element 702 is for sending to server by described search word.
Character relation information receiving unit 703 is for receiving the character relation information relevant to described the first name from described server, and described character relation information comprises at least one second name and the relation data with described first name thereof.
Character relation information display unit 704 is for showing described character relation information.
According to exemplary embodiment of the present invention, described device also comprises: taxon (not shown) is used for the described character relation information received to classify according to family relationship and social relationships.
According to exemplary embodiment of the present invention, described device also comprises: the first sequencing unit (not shown) sorts for the described character relation information of time order and function order to classification occurred according to the relation of described first name and the second name.
According to exemplary embodiment of the present invention, it is characterized in that, described device also comprises: the second sequencing unit (not shown) is used for sorting according to the height of its user's clicking rate to the second name of identical social relationships.
What the embodiment of the present invention provided realizes character relation analysis by computing machine, provides people information method and device, by carrying out dependency analysis and semantic character labeling to personage's content-data, thus obtain the character relation knowledge base relevant to personage exactly, and provide abundant to user, the information of character relation accurately.
Above-mentioned can at hardware according to method of the present invention, realize in firmware, or be implemented as and can be stored in recording medium (such as CD ROM, RAM, floppy disk, hard disk or magneto-optic disk) in software or computer code, or be implemented and will be stored in the computer code in local recording medium by the original storage of web download in remote logging medium or nonvolatile machine readable media, thus method described here can be stored in use multi-purpose computer, such software process on the recording medium of application specific processor or able to programme or specialized hardware (such as ASIC or FPGA).Be appreciated that, computing machine, processor, microprocessor controller or programmable hardware comprise and can store or receive the memory module of software or computer code (such as, RAM, ROM, flash memory etc.), when described software or computer code by computing machine, processor or hardware access and perform time, realize disposal route described here.In addition, when the code for realizing the process shown in this accessed by multi-purpose computer, multi-purpose computer is converted to the special purpose computer for performing the process shown in this by the execution of code.
The above; be only the specific embodiment of the present invention, but protection scope of the present invention is not limited thereto, is anyly familiar with those skilled in the art in the technical scope that the present invention discloses; change can be expected easily or replace, all should be encompassed within protection scope of the present invention.Therefore, protection scope of the present invention should be as the criterion with the protection domain of described claim.
Claims (20)
1. by a computer implemented character relation analytical approach, it is characterized in that, described method comprises:
Multiple statement is extracted from the content-data relevant to personage;
Respectively dependency analysis is carried out to described multiple statement, generate multiple dependency analysis tree;
Respectively semantic character labeling is carried out to described multiple statement according to described multiple dependency analysis tree, generate multiple semantic character labeling result;
Personage's time-space relationship table is generated according to described multiple semantic character labeling result;
The character relation knowledge base paying close attention to personage is generated according to described personage's time-space relationship table.
2. method according to claim 1, is characterized in that, carries out semantic character labeling respectively, generate in the process of multiple semantic character labeling result described according to described multiple dependency analysis tree to described multiple statement,
For arbitrary described statement, identify predicate wherein and argument thereof, and determine the semantic role of its each argument and character labeling is carried out to described argument.
3. method according to claim 1 and 2, is characterized in that, described content-data is about the encyclopaedia webpage of personage, the news web page relating to personage or information webpage.
4. method according to claim 3, it is characterized in that, describedly carry out dependency analysis to described multiple statement, the process generating multiple dependency analysis tree comprises: carry out dependency analysis to described multiple statement respectively according to shifting near reduction algorithm, generates multiple dependency analysis tree.
5. provide a method for people information, it is characterized in that, described method comprises:
Receive the search word comprising the first name;
Obtain the character relation information relevant to described the first name according to described first name from the character relation knowledge base prestored, described character relation information comprises at least one second name and the relation data with described first name thereof;
Send described character relation information.
6. method according to claim 5, is characterized in that, described method also comprises: the described character relation information obtained classified according to family relationship and social relationships.
7. method according to claim 6, is characterized in that, described method also comprises: the described character relation information of time order and function order to classification occurred according to the relation of described first name and the second name sorts.
8. method according to claim 7, is characterized in that, described method also comprises: sort according to the height of its user's clicking rate to the second name of identical social relationships.
9. provide a method for people information, it is characterized in that, described method comprises:
Obtain the search word comprising the first name;
Described search word is sent to server;
Receive the character relation information relevant to described the first name from described server, described character relation information comprises at least one second name and the relation data with described first name thereof;
Show described character relation information.
10. method according to claim 9, is characterized in that, described character relation information is the data be classified according to family relationship and social relationships, and the process of described display described character relation information comprises: the described character relation information of classification display.
11. methods according to claim 10, is characterized in that, the described character relation information of classification is the data that the time order and function order occurred according to the relation of described first name and the second name is sorted.
12. 1 kinds of character relation analytical equipments, is characterized in that, described device comprises:
Statement extracting unit, for extracting multiple statement from the content-data relevant to personage;
Dependency analysis unit, for carrying out dependency analysis to described multiple statement respectively, generates multiple dependency analysis tree;
Semantic character labeling unit, for carrying out semantic character labeling to described multiple statement respectively according to described multiple dependency analysis tree, generates multiple semantic character labeling result;
Personage's time-space relationship table generation unit, for generating personage's time-space relationship table according to described multiple semantic character labeling result;
Character relation knowledge base generation unit, for generating the character relation knowledge base paying close attention to personage according to described personage's time-space relationship table.
13. devices according to claim 12, is characterized in that, described mark unit, for arbitrary described statement, identifies predicate wherein and argument thereof, and determines the semantic role of its each argument and carry out character labeling to described argument.
14. devices according to claim 12 or 13, it is characterized in that, described content-data is about the encyclopaedia webpage of personage, the news web page relating to personage or information webpage.
15. 1 kinds of devices that people information is provided, it is characterized in that, described device comprises:
Search word receiving element, for receiving the search word comprising the first name;
Character relation information acquisition unit, for obtaining the character relation information relevant to described the first name according to described first name from the character relation knowledge base prestored, described character relation information comprises at least one second name and the relation data with described first name thereof;
Character relation information transmitting unit, for sending described character relation information.
16. devices according to claim 15, is characterized in that, described device also comprises: taxon, for the described character relation information obtained being classified according to family relationship and social relationships.
17. devices according to claim 16, is characterized in that, described device also comprises: the first sequencing unit, sort for the described character relation information of time order and function order to classification occurred according to the relation of described first name and the second name.
18. devices according to claim 17, is characterized in that, described device also comprises: the second sequencing unit, for sorting according to the height of its user's clicking rate to the second name of identical social relationships.
19. 1 kinds of devices that people information is provided, it is characterized in that, described device comprises:
Search word acquiring unit, for obtaining the search word comprising the first name;
Search word transmitting element, for sending to server by described search word;
Character relation information receiving unit, for receiving the character relation information relevant to described the first name from described server, described character relation information comprises at least one second name and the relation data with described first name thereof;
Character relation information display unit, for showing described character relation information.
20. devices according to claim 19, is characterized in that, described character relation information is the data be classified according to family relationship and social relationships, the described character relation information of described display unit classification display.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410721415.8A CN104462326A (en) | 2014-12-02 | 2014-12-02 | Person relation analyzing method as well as method and device for providing person information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410721415.8A CN104462326A (en) | 2014-12-02 | 2014-12-02 | Person relation analyzing method as well as method and device for providing person information |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104462326A true CN104462326A (en) | 2015-03-25 |
Family
ID=52908361
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410721415.8A Pending CN104462326A (en) | 2014-12-02 | 2014-12-02 | Person relation analyzing method as well as method and device for providing person information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104462326A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109271525A (en) * | 2018-08-08 | 2019-01-25 | 北京百度网讯科技有限公司 | For generating the method, apparatus, equipment and computer readable storage medium of knowledge mapping |
| CN109815296A (en) * | 2018-12-29 | 2019-05-28 | 北京中科闻歌科技股份有限公司 | The personage's construction of knowledge base method, apparatus and storage medium of notarization document |
| CN110717014A (en) * | 2019-09-12 | 2020-01-21 | 北京四海心通科技有限公司 | Ontology knowledge base dynamic construction method |
| CN110717034A (en) * | 2018-06-26 | 2020-01-21 | 杭州海康威视数字技术股份有限公司 | Ontology construction method and device |
| CN110851560A (en) * | 2018-07-27 | 2020-02-28 | 杭州海康威视数字技术股份有限公司 | Information retrieval method, device and equipment |
| CN111953577A (en) * | 2019-05-16 | 2020-11-17 | 武汉Tcl集团工业研究院有限公司 | Method, system and readable storage medium for preventing message from being mistakenly sent |
| CN113361280A (en) * | 2021-06-30 | 2021-09-07 | 北京百度网讯科技有限公司 | Method for training model, prediction method, prediction device, electronic device and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2011008635A (en) * | 2009-06-26 | 2011-01-13 | Hitachi Ltd | Time-space data display device, time-space data analysis method, and program |
| CN102117283A (en) * | 2009-12-30 | 2011-07-06 | 安世亚太科技（北京）有限公司 | Semantic indexing-based data retrieval method |
| CN103678281A (en) * | 2013-12-31 | 2014-03-26 | 北京百度网讯科技有限公司 | Method and device for automatically labeling text |
| CN104133916A (en) * | 2014-08-14 | 2014-11-05 | 百度在线网络技术（北京）有限公司 | Search result information organizational method and device |
-
2014
- 2014-12-02 CN CN201410721415.8A patent/CN104462326A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2011008635A (en) * | 2009-06-26 | 2011-01-13 | Hitachi Ltd | Time-space data display device, time-space data analysis method, and program |
| CN102117283A (en) * | 2009-12-30 | 2011-07-06 | 安世亚太科技（北京）有限公司 | Semantic indexing-based data retrieval method |
| CN103678281A (en) * | 2013-12-31 | 2014-03-26 | 北京百度网讯科技有限公司 | Method and device for automatically labeling text |
| CN104133916A (en) * | 2014-08-14 | 2014-11-05 | 百度在线网络技术（北京）有限公司 | Search result information organizational method and device |
Non-Patent Citations (1)
| Title |
|---|
| 袁晓虹: "基于依存关系的中文语义角色标注研究", 《中国优秀硕士学位论文全文数据库 信息科技辑（月刊）》 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110717034A (en) * | 2018-06-26 | 2020-01-21 | 杭州海康威视数字技术股份有限公司 | Ontology construction method and device |
| CN110851560A (en) * | 2018-07-27 | 2020-02-28 | 杭州海康威视数字技术股份有限公司 | Information retrieval method, device and equipment |
| CN110851560B (en) * | 2018-07-27 | 2023-03-10 | 杭州海康威视数字技术股份有限公司 | Information retrieval method, device and equipment |
| CN109271525A (en) * | 2018-08-08 | 2019-01-25 | 北京百度网讯科技有限公司 | For generating the method, apparatus, equipment and computer readable storage medium of knowledge mapping |
| CN109815296A (en) * | 2018-12-29 | 2019-05-28 | 北京中科闻歌科技股份有限公司 | The personage's construction of knowledge base method, apparatus and storage medium of notarization document |
| CN109815296B (en) * | 2018-12-29 | 2020-12-22 | 北京中科闻歌科技股份有限公司 | Figure knowledge base construction method and device for notarization document and storage medium |
| CN111953577A (en) * | 2019-05-16 | 2020-11-17 | 武汉Tcl集团工业研究院有限公司 | Method, system and readable storage medium for preventing message from being mistakenly sent |
| CN110717014A (en) * | 2019-09-12 | 2020-01-21 | 北京四海心通科技有限公司 | Ontology knowledge base dynamic construction method |
| CN110717014B (en) * | 2019-09-12 | 2020-09-04 | 北京四海心通科技有限公司 | Ontology knowledge base dynamic construction method |
| CN113361280A (en) * | 2021-06-30 | 2021-09-07 | 北京百度网讯科技有限公司 | Method for training model, prediction method, prediction device, electronic device and storage medium |
| CN113361280B (en) * | 2021-06-30 | 2023-10-31 | 北京百度网讯科技有限公司 | Model training method, prediction method, apparatus, electronic device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109189942B (en) | Construction method and device of patent data knowledge graph | |
| CN104462326A (en) | Person relation analyzing method as well as method and device for providing person information | |
| US8583420B2 (en) | Method for the extraction of relation patterns from articles | |
| US20200301987A1 (en) | Taste extraction curation and tagging | |
| JP2017508214A (en) | Provide search recommendations | |
| WO2014031458A1 (en) | Translating natural language utterances to keyword search queries | |
| CN104978332B (en) | User-generated content label data generation method, device and correlation technique and device | |
| Alami et al. | Cybercrime profiling: Text mining techniques to detect and predict criminal activities in microblog posts | |
| US11157540B2 (en) | Search space reduction for knowledge graph querying and interactions | |
| Psomakelis et al. | Comparing methods for twitter sentiment analysis | |
| US10949418B2 (en) | Method and system for retrieval of data | |
| Oramas et al. | ELMD: An automatically generated entity linking gold standard dataset in the music domain | |
| CN103313248A (en) | Method and device for identifying junk information | |
| Ahlgren | Research on sentiment analysis: the first decade | |
| CN104298683A (en) | Theme digging method and equipment and query expansion method and equipment | |
| AU2021105938A4 (en) | Automatic and dynamic contextual analysis of sentiment of social content and feedback reviews based on machine learning model | |
| Tandel et al. | Multi-document text summarization-a survey | |
| CN104281565A (en) | Semantic dictionary constructing method and device | |
| Qundus et al. | AI supported topic modeling using KNIME-workflows | |
| Weichselbraun et al. | Name variants for improving entity discovery and linking | |
| Jeon et al. | Making a graph database from unstructured text | |
| CN109992651A (en) | A kind of problem target signature automatic identification and abstracting method | |
| Babur et al. | Model analytics for feature models: case studies for SPLOT repository | |
| Chawla et al. | Performance evaluation of vsm and lsi models to determine bug reports similarity | |
| JP2010198278A (en) | Apparatus, method, and program for classification of reputation information |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20150325 |
|
| RJ01 | Rejection of invention patent application after publication |