CN106776825B - User preference entity classification method and system based on hierarchical mapping - Google Patents
User preference entity classification method and system based on hierarchical mapping Download PDFInfo
- Publication number
- CN106776825B CN106776825B CN201611058789.1A CN201611058789A CN106776825B CN 106776825 B CN106776825 B CN 106776825B CN 201611058789 A CN201611058789 A CN 201611058789A CN 106776825 B CN106776825 B CN 106776825B
- Authority
- CN
- China
- Prior art keywords
- information
- target
- entity
- level
- query
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3343—Query execution using phonetics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Mathematical Physics (AREA)
- Human Computer Interaction (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Health & Medical Sciences (AREA)
- Acoustics & Sound (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention belongs to the technical field of intelligent machines, and provides a user preference entity classification method and system based on hierarchical mapping. The user preference entity classification method and system based on hierarchical mapping can classify and store the user preference entities and improve the accuracy of information query and extraction.
Description
Technical Field
The invention relates to the technical field of intelligent machines, in particular to a user preference entity classification method and system based on hierarchical mapping.
Background
When the robot chats with a user, the words spoken by the user, such as the preference of the user, need to be remembered to embody the characteristics of understanding and being attentive, and the human-computer interaction process is more natural and intelligent. However, the existing robot cannot realize information classification storage, cannot classify the preferences of users, is complicated in information query and extraction processes, is low in accuracy, causes that the users cannot know the content related to personal preferences, even has the phenomenon of dislocation of problems and answers, is not natural and smooth in a chat process, and is poor in user experience.
How to store the preferred entities of the users in a classified manner and facilitate information query and extraction is a problem that needs to be solved urgently by technical personnel in the field.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides the user preference entity classification method and system based on the hierarchical mapping, which can classify and store the preference entities of the user, facilitate information query and extraction and have high accuracy.
In a first aspect, the present invention provides a method for classifying user preference entities based on hierarchical mapping, the method comprising the steps of: acquiring entity information preferred by a user;
and (3) information query step: inquiring a pre-acquired common sense library according to the entity information to obtain target level mapping information;
information association step: and associating and storing the target level mapping information and the entity information.
Further, according to the entity information, querying a pre-acquired common sense library to obtain target level mapping information, specifically comprising: inquiring a pre-acquired common sense library according to the entity information to acquire a target entity matched with the entity information;
acquiring the level mapping information of a target entity according to the common sense library and the target entity;
and setting the hierarchy mapping information of the target entity as target hierarchy mapping information.
Further, after associating and storing the target hierarchical mapping information and the entity information, the method for classifying the user preference entity based on the hierarchical mapping according to the embodiment further includes an information feedback step: acquiring query information of a user;
respectively comparing the query information with the first-level category information and the second-level category information to obtain first-level target category information or second-level target category information matched with the query information;
and setting entity information corresponding to the first-level target category information or the second-level target category information as a feedback result of the query information for feedback, wherein the target level mapping information comprises the first-level category information and the second-level category information.
Further, before the information feedback step, the method further comprises an information extraction step of:
acquiring voice information of a user;
query information is extracted from the voice information.
Based on the above embodiment of the method for classifying the user preference entity based on the hierarchical mapping, further, the number of the target hierarchical mapping information is at least one.
In a second aspect, the invention provides a system for classifying user preference entities based on hierarchical mapping, which comprises an information acquisition subsystem, an information inquiry subsystem and an information association subsystem, wherein the information acquisition subsystem is used for acquiring entity information preferred by users; the information query subsystem is used for querying a pre-acquired common sense library according to the entity information to obtain target level mapping information; and the information association subsystem is used for associating and storing the target level mapping information and the entity information.
Further, the information query subsystem is specifically configured to, when querying a pre-acquired common sense library according to the entity information to obtain the target level mapping information: inquiring a pre-acquired common sense library according to the entity information to acquire a target entity matched with the entity information; acquiring the level mapping information of a target entity according to the common sense library and the target entity; and setting the hierarchy mapping information of the target entity as target hierarchy mapping information.
Based on any of the above embodiments of the system for classifying user preferred entities based on hierarchical mapping, the system further comprises an information feedback subsystem: the system is used for acquiring query information of a user; respectively comparing the query information with the first-level category information and the second-level category information to obtain first-level target category information or second-level target category information matched with the query information; and setting entity information corresponding to the first-level target category information or the second-level target category information as a feedback result of the query information for feedback, wherein the target level mapping information comprises the first-level category information and the second-level category information.
Further, the user preference entity classification system based on hierarchical mapping of the present embodiment further includes an information extraction subsystem: the voice information acquisition module is used for acquiring voice information of a user; query information is extracted from the voice information.
Based on any of the above embodiments of the system for classifying user-preferred entities based on hierarchical mapping, further, the number of target hierarchical mapping information in the information query subsystem is at least one.
According to the technical scheme, the target level mapping information matched with the entity information is acquired by utilizing the pre-acquired common sense library, and the entity information is associated with the target level mapping information.
Therefore, the user preference entity classification method and system based on hierarchical mapping can classify and store the user preference entities and improve the accuracy of information query and extraction.
Drawings
In order to more clearly illustrate the detailed description of the invention or the technical solutions in the prior art, the drawings that are needed in the detailed description of the invention or the prior art will be briefly described below. Throughout the drawings, like elements or portions are generally identified by like reference numerals. In the drawings, elements or portions are not necessarily drawn to scale.
FIG. 1 is a flow chart of a user preference entity classification method based on hierarchical mapping according to the present invention;
FIG. 2 is a schematic diagram illustrating the distribution of common sense library information based on hierarchical mapping according to the present invention;
FIG. 3 is a schematic diagram illustrating information association based on hierarchical mapping according to the present invention;
fig. 4 shows a schematic structural diagram of a user preference entity classification system based on hierarchical mapping provided by the present invention.
Detailed Description
Embodiments of the present invention will be described in detail below with reference to the accompanying drawings. The following examples are only for illustrating the technical solutions of the present invention more clearly, and therefore are only examples, and the protection scope of the present invention is not limited thereby.
It is to be noted that, unless otherwise specified, technical or scientific terms used herein shall have the ordinary meaning as understood by those skilled in the art to which the invention pertains.
In a first aspect, an embodiment of the present invention provides a method for classifying user preference entities based on hierarchical mapping, where in combination with fig. 1, the method includes:
information acquisition step S1: and acquiring entity information preferred by the user, wherein the entity information can be a character name, a food name or a sports operation item.
Information inquiry step S2: inquiring a pre-acquired common sense library according to the entity information to obtain target level mapping information; here, the common sense repository has a plurality of map entities and category entries corresponding to the map entities, and the map entities and the category entries have a hierarchical mapping relationship. With reference to fig. 2, if the map entity is "tattoo", the corresponding second-level category information is "japanese cuisine", the first-level category information is "gourmet", the map entity is "chicken bouillon", the corresponding second-level category information is "chuancai", the first-level category information is "gourmet", and the map entity, the second-level category information and the first-level category information are sequentially associated with each other. In the common sense repository, the first-level category information is generally generalized category information, such as food, restaurants, drinks, games, stars, sports, and the like, and the generalized category information is further classified in detail and is divided into second-level category information, third-level category information, and the like. If the entity information is apple, the obtained target level mapping information is fruit and food, the fruit is second-level category information, the food is first-level category information, and a mapping relation exists between the fruit and the food.
Information association step S3: and associating and storing the target level mapping information and the entity information. Here, entity information "apple" and "fruit" are associated, and the mapping relationship among the apple, the fruit and the gourmet can be obtained only by once information association, and stored in the database. For example, the preferences of the first user and the second user are shown in table 1, the entity information "apple" and "banana" of the first user are queried, the obtained target level mapping information is both "fruit" and "food", and the information association diagram shown in fig. 3 is obtained.
Table 1 user preference information table
According to the technical scheme, the target level mapping information matched with the entity information is acquired by utilizing the pre-acquired common sense library, and the entity information is associated with the target level mapping information, so that the method can be used for classifying and storing the entity information preferred by the user, the flexibility of storing the preferred entity information is enhanced, the efficiency and the accuracy of information query and information extraction are improved, the preference of the user on one aspect can be accurately positioned, and the user experience is improved.
Therefore, the user preference entity classification method based on hierarchical mapping can classify and store the user preference entities, and improve the accuracy of information query and extraction.
Specifically, when querying a pre-obtained common sense library according to entity information to obtain target hierarchical mapping information, the implementation process of the hierarchical mapping-based user preference entity classification method according to the embodiment is as follows: inquiring a pre-acquired common sense library according to the entity information to acquire a target entity matched with the entity information; with reference to fig. 2, if the entity information is "apple", the entity information "apple" is compared with the atlas entity "chicken bouillon" and "tattoo", etc., until the entity information is matched with the atlas entity "apple", at this time, the atlas entity "apple" is the target entity "apple".
Acquiring the level mapping information of a target entity according to the common sense library and the target entity; with reference to fig. 2, the hierarchical mapping information is: the food is the first-level category information, and a mapping relation exists between the fruit and the food.
And setting the hierarchy mapping information of the target entity as target hierarchy mapping information. At this time, the target level mapping information is: the food is the first-level category information, and a mapping relation exists between the fruit and the food. According to the method, the target entity in the map entity is obtained firstly, and then the target level mapping information is determined, so that the error of the information association step is reduced, and the accuracy of information feedback is improved.
Specifically, the user preference entity classification method based on hierarchical mapping according to the embodiment can also provide an information feedback function, and the implementation process is as follows: acquiring query information of a user; if the information sent by the user is ' what the fruit that I like ' is ', the query information is ' fruit '.
Respectively comparing the query information with the first-level category information and the second-level category information to obtain first-level target category information or second-level target category information matched with the query information; here, the query information "fruit" is compared with the information "food", "seafood", "Sichuan dish", and the like, respectively, until the query information "fruit" matches with the second-level category information "fruit", the second target category information "fruit" is obtained.
And setting entity information corresponding to the first-level target category information or the second-level target category information as a feedback result of the query information for feedback, wherein the target level mapping information comprises the first-level category information and the second-level category information. At this time, the entity information of the second-level target category information "fruit" pair is "apple", and "apple" is fed back to the user. The method can provide the query result for the user according to the query information of the user, performs information feedback, has high information query and extraction speed and high accuracy, is beneficial to improving the user experience, and is beneficial to realizing a smooth and natural chatting process. Moreover, the user can inquire in a voice mode, and the method can extract information from the voice information, namely the voice information of the user is obtained before the information feedback step; query information is extracted from the voice information to improve information transmission efficiency and user experience.
Specifically, in the user preference entity classification method based on hierarchical mapping of this embodiment, the number of target hierarchical mapping information is at least one. If the entity information is Zhou Ji Lun, the second class information can be singer, actor, director, etc., and the first class information can be music, film and television, etc., it is beneficial for the user to inquire information from many aspects and improve the user experience.
In a second aspect, an embodiment of the present invention provides a hierarchical mapping-based user preference entity classification system, which, with reference to fig. 4, includes an information acquisition subsystem 1, an information query subsystem 2, and an information association subsystem 3, where the information acquisition subsystem 1 is configured to acquire entity information of user preferences; the information inquiry subsystem 2 is used for inquiring a pre-acquired common sense library according to the entity information to acquire target level mapping information; the information association subsystem 3 is used for associating and storing the target level mapping information and the entity information.
According to the technical scheme, the user preference entity classification system based on hierarchical mapping acquires the target hierarchical mapping information matched with the entity information by utilizing the pre-acquired common sense library, and associates the entity information with the target hierarchical mapping information.
Therefore, the user preference entity classification system based on hierarchical mapping can classify and store the preference entities of the user, and improve the accuracy of information query and extraction.
Specifically, in the aspect of information query, the information query subsystem 2 is specifically configured to, when querying a pre-acquired common sense library according to the entity information to obtain the target level mapping information: inquiring a pre-acquired common sense library according to the entity information to acquire a target entity matched with the entity information; acquiring the level mapping information of a target entity according to the common sense library and the target entity; and setting the hierarchy mapping information of the target entity as target hierarchy mapping information. Here, the information query subsystem 2 first obtains a target entity in the map entity, and then determines target level mapping information, which is helpful for reducing errors in information association steps and improving accuracy of information feedback.
Specifically, the user preference entity classification system based on hierarchical mapping of the present embodiment can also provide an information feedback function, and the system further includes an information feedback subsystem: the system is used for acquiring query information of a user; respectively comparing the query information with the first-level category information and the second-level category information to obtain first-level target category information or second-level target category information matched with the query information; and setting entity information corresponding to the first-level target category information or the second-level target category information as a feedback result of the query information for feedback, wherein the target level mapping information comprises the first-level category information and the second-level category information. The information feedback subsystem can provide a query result for the user according to the query information of the user, performs information feedback, is high in information query and extraction speed and accuracy, contributes to improving user experience, and is favorable for realizing a smooth and natural chatting process. Moreover, the system for classifying user preference entities based on hierarchical mapping in this embodiment further includes an information extraction subsystem: the voice information acquisition module is used for acquiring voice information of a user; query information is extracted from the voice information to improve information transmission efficiency and user experience.
Specifically, the number of the target level mapping information in the information query subsystem 2 is at least one, and as the entity information is "zhou jieren", the second level category information may be "singer", "actor", "director", and the like, the first level category information may be "music", "movie", and the like, and a user can perform information query from multiple aspects by using the information query subsystem 2, which is beneficial to improving user experience.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; such modifications and substitutions do not depart from the spirit and scope of the present invention, and they should be construed as being included in the following claims and description.
Claims (8)
1. A user preference entity classification method based on hierarchical mapping is characterized by comprising the following steps:
an information acquisition step: acquiring entity information preferred by a user;
and (3) information query step: inquiring a pre-acquired common sense library according to the entity information to acquire target level mapping information;
information association step: associating and storing the target level mapping information and the entity information;
and information feedback step: acquiring query information of a user; comparing the query information with first-level category information and second-level category information respectively to obtain first-level target category information or second-level target category information matched with the query information; and setting entity information corresponding to the first-level target category information or the second-level target category information as a feedback result of the query information for feedback, wherein the target level mapping information comprises the first-level category information and the second-level category information.
2. The method as claimed in claim 1, wherein the step of querying a pre-obtained common sense library according to the entity information to obtain target hierarchical mapping information comprises: inquiring a pre-acquired common sense library according to the entity information, and acquiring a target entity matched with the entity information;
acquiring the level mapping information of the target entity according to the common sense library and the target entity;
setting hierarchical mapping information of the target entity as the target hierarchical mapping information.
3. The method of claim 2, wherein before the step of feeding back the information, the method further comprises a step of extracting information:
acquiring voice information of a user;
and extracting the query information from the voice information.
4. The method of claim 1, wherein the target hierarchical mapping information is at least one in number.
5. A system for classifying user-preferred entities based on hierarchical mapping, comprising:
the information acquisition subsystem: the entity information is used for acquiring user preference;
the information inquiry subsystem: the system is used for inquiring a pre-acquired common sense library according to the entity information to obtain target level mapping information;
the information association subsystem: the target level mapping information is associated with the entity information and is stored;
the information feedback subsystem: the system is used for acquiring query information of a user; comparing the query information with first-level category information and second-level category information respectively to obtain first-level target category information or second-level target category information matched with the query information; and setting entity information corresponding to the first-level target category information or the second-level target category information as a feedback result of the query information for feedback, wherein the target level mapping information comprises the first-level category information and the second-level category information.
6. The system of claim 5, wherein the information query subsystem, when querying a pre-obtained common sense repository for target hierarchical mapping information based on the entity information, is specifically configured to: inquiring a pre-acquired common sense library according to the entity information, and acquiring a target entity matched with the entity information; acquiring the level mapping information of the target entity according to the common sense library and the target entity; setting hierarchical mapping information of the target entity as the target hierarchical mapping information.
7. The system of claim 6, further comprising an information extraction subsystem: the voice information acquisition module is used for acquiring voice information of a user; and extracting the query information from the voice information.
8. The system of claim 5, wherein the number of target hierarchical mapping information in the information query subsystem is at least one.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611058789.1A CN106776825B (en) | 2016-11-24 | 2016-11-24 | User preference entity classification method and system based on hierarchical mapping |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611058789.1A CN106776825B (en) | 2016-11-24 | 2016-11-24 | User preference entity classification method and system based on hierarchical mapping |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106776825A CN106776825A (en) | 2017-05-31 |
| CN106776825B true CN106776825B (en) | 2020-06-02 |
Family
ID=58912504
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611058789.1A Active CN106776825B (en) | 2016-11-24 | 2016-11-24 | User preference entity classification method and system based on hierarchical mapping |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106776825B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111883230B (en) * | 2019-12-18 | 2024-05-07 | 深圳数字生命研究院 | Diet data generation method and device, storage medium and electronic device |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102262672A (en) * | 2011-08-09 | 2011-11-30 | 鸿富锦精密工业（深圳）有限公司 | Electronic device and information interacting method thereof |
| CN104537065A (en) * | 2014-12-29 | 2015-04-22 | 北京奇虎科技有限公司 | Search result pushing method and system |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6829527B2 (en) * | 2002-08-26 | 2004-12-07 | Honeywell International Inc. | Relational database for maintenance information for complex systems |
| CN101076061A (en) * | 2007-03-30 | 2007-11-21 | 腾讯科技（深圳）有限公司 | Robot server and automatic chatting method |
| CN102955810B (en) * | 2011-08-26 | 2015-12-02 | 中国移动通信集团公司 | A kind of Web page classification method and equipment |
| CN105159977B (en) * | 2015-08-27 | 2019-01-25 | 百度在线网络技术（北京）有限公司 | Information interactive processing method and device |
| CN106095833B (en) * | 2016-06-01 | 2019-04-16 | 竹间智能科技（上海）有限公司 | Human-computer dialogue content processing method |
-
2016
- 2016-11-24 CN CN201611058789.1A patent/CN106776825B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102262672A (en) * | 2011-08-09 | 2011-11-30 | 鸿富锦精密工业（深圳）有限公司 | Electronic device and information interacting method thereof |
| CN104537065A (en) * | 2014-12-29 | 2015-04-22 | 北京奇虎科技有限公司 | Search result pushing method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106776825A (en) | 2017-05-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11636146B2 (en) | Content analysis to enhance voice search | |
| CN112507068B (en) | Document query method, device, electronic equipment and storage medium | |
| US20200125981A1 (en) | Systems and methods for recognizing ambiguity in metadata | |
| US9846696B2 (en) | Apparatus and methods for indexing multimedia content | |
| US8380697B2 (en) | Search and retrieval methods and systems of short messages utilizing messaging context and keyword frequency | |
| US8285718B1 (en) | Clustering multimedia search | |
| CN111324784B (en) | Character string processing method and device | |
| US10268758B2 (en) | Method and system of acquiring semantic information, keyword expansion and keyword search thereof | |
| US8064641B2 (en) | System and method for identifying objects in video | |
| US20210117478A1 (en) | Method, apparatus, and computer-readable medium for generating categorical and criterion-based search results from a search query | |
| CN103106199B (en) | Text searching method and device | |
| US9286546B2 (en) | Identifying labels for image collections | |
| CN103984740B (en) | Based on the method and system that the retrieved page of combination tag shows | |
| CN105653700A (en) | Video search method and system | |
| WO2012056463A1 (en) | Content recommendation for groups | |
| KR20050120786A (en) | Method and apparatus for grouping content items | |
| US20200272674A1 (en) | Method and apparatus for recommending entity, electronic device and computer readable medium | |
| CN103514236A (en) | Retrieval condition error correction prompt processing method based on Pinyin in retrieval application | |
| CN106205613B (en) | A kind of navigation audio recognition method and system | |
| US20140372412A1 (en) | Dynamic filtering search results using augmented indexes | |
| CN103678560A (en) | Multimedia resource error correction searching method and system and multimedia resource server | |
| US20140019482A1 (en) | Apparatus and method for searching for personalized content based on user's comment | |
| CN111309872B (en) | Search processing method, device and equipment | |
| JP2018511115A5 (en) | ||
| US10394838B2 (en) | App store searching |
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 |