CN111125566A - Information acquisition method and device, electronic equipment and storage medium - Google Patents

Information acquisition method and device, electronic equipment and storage medium Download PDF

Info

Publication number
CN111125566A
CN111125566A CN201911266244.3A CN201911266244A CN111125566A CN 111125566 A CN111125566 A CN 111125566A CN 201911266244 A CN201911266244 A CN 201911266244A CN 111125566 A CN111125566 A CN 111125566A
Authority
CN
China
Prior art keywords
label
attribute
information
text
category
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
Application number
CN201911266244.3A
Other languages
Chinese (zh)
Other versions
CN111125566B (en
Inventor
苏文博
孙拔群
王贺青
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Seashell Housing Beijing Technology Co Ltd
Original Assignee
Beike Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beike Technology Co Ltd filed Critical Beike Technology Co Ltd
Priority to CN201911266244.3A priority Critical patent/CN111125566B/en
Publication of CN111125566A publication Critical patent/CN111125566A/en
Application granted granted Critical
Publication of CN111125566B publication Critical patent/CN111125566B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/955—Retrieval from the web using information identifiers, e.g. uniform resource locators [URL]
    • 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
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation

Landscapes

  • Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The embodiment of the disclosure discloses an information acquisition method and device, electronic equipment and a storage medium, wherein the method comprises the following steps: extracting an attribute label of the current object; acquiring at least one other type object matched based on the attribute label of the current object from the label system based on the matching relation between the attribute labels of different types of objects in the label system; the label system comprises attribute labels of various types of objects in various categories and a matching relation between the attribute labels of different types of objects; the different types of objects include: users, items, and text; returning the matched at least one other type object. The method and the device for recommending the objects can accurately match other types of objects matched with one type of object, so that accurate recommendation/search of items, texts and the like is met, recommendation efficiency and search efficiency are improved, and recommendation and search requirements can be met more widely.

Description

Information acquisition method and device, electronic equipment and storage medium
Technical Field
The present disclosure relates to internet technologies, and in particular, to an information obtaining method and apparatus, an electronic device, and a storage medium.
Background
In recent years, with the rapid development of internet technology, people gradually step from the information-deficient era to the information-overloaded era. Due to the explosive growth of information levels, both information producers and information consumers have met with significant challenges. The application of the personalized recommendation system and the search system provides an effective way for solving the challenge. By means of the recommendation system, on one hand, the project (such as commodities, products and the like) and the information producer can realize accurate recommendation of the project by relying on data; on the other hand, by using the search system, the user can also quickly locate own requirements from the information of the full object of the Lin Lang and match the items meeting the own requirements.
However, in the existing recommendation system and retrieval system, since the requirements of the users are relatively generalized and abstract, the requirements of the users cannot be clearly and accurately determined, so that matched items cannot be provided for the users, and the recommendation and search requirements cannot be met.
Disclosure of Invention
The embodiment of the disclosure provides an information acquisition method and device, electronic equipment and a storage medium, so as to realize matching between a user and information.
In one aspect of the embodiments of the present disclosure, an information obtaining method is provided, including:
extracting an attribute label of the current object;
acquiring at least one other type object matched based on the attribute label of the current object from the label system based on the matching relation between the attribute labels of different types of objects in the label system; the label system comprises attribute labels of various types of objects in various categories and a matching relation between the attribute labels of different types of objects; the different types of objects include: users, items, and text;
returning the matched at least one other type object.
Optionally, in any of the above method embodiments of the present disclosure, the method further includes the step of establishing the label system:
extracting the labels of the user information in the first database by using a label extraction model to obtain attribute labels of at least one user under each category; performing label extraction on the item information in the second database by using the label extraction model to obtain attribute labels of at least one item under each category; extracting labels of the text information in the third database by using the label extraction model to obtain attribute labels of at least one text under each category;
and establishing a matching relation among the attribute label of the at least one user under each category, the attribute label of the at least one item under each category and the attribute label of the at least one text under each category based on the extracted attribute labels of the at least one user under each category, the extracted attribute labels of the at least one item under each category and the extracted attribute labels of the at least one text under each category to obtain a label system.
Optionally, in any one of the method embodiments of the present disclosure, the extracting the user information in the first database by using a tag extraction model to obtain an attribute tag of at least one user in each category includes:
extracting the labels of the user information in the first database by using a regular model in the label extraction model to obtain abstract labels of at least one user under each category;
and obtaining the attribute label of the at least one user under each category by using the machine learning model in the label extraction model and the abstract label of the at least one user under each category.
Optionally, in any one of the method embodiments of the present disclosure, the performing, by using the tag extraction model, tag extraction on item information in a second database to obtain an attribute tag of at least one item under each category includes:
performing label extraction on the item information in the second database by using a formula model in the label extraction model to obtain abstract labels of at least one item under each category;
and obtaining the attribute label of the at least one item under each category according to the abstract label of the at least one item under each category by using a machine learning model in the label extraction model.
Optionally, in any one of the method embodiments of the present disclosure, the performing, by using the tag extraction model, tag extraction on text information in a third database to obtain an attribute tag of at least one text under each category includes:
performing label extraction on the text information in the third database by using a regular model in the label extraction model to obtain abstract labels of at least one text under each category;
and obtaining the attribute label of the at least one text under each category according to the abstract label of the at least one text under each category by using a machine learning model in the label extraction model.
Optionally, in any embodiment of the method of the present disclosure, before performing tag extraction on the user information in the first database, the method further includes: carrying out duplicate removal and/or filtration on the user information in the first database; and/or the presence of a gas in the gas,
before the tag extraction of the item information in the second database, the method further includes: removing duplicate and/or filtering project information in the second database; and/or the presence of a gas in the gas,
before extracting the label from the text information in the third database, the method further includes: and carrying out duplicate removal and/or filtering on the text information in the third database.
Optionally, in any of the method embodiments of the present disclosure above, the method further includes:
updating the label system based on the incremental user information in the first database, the incremental item information in the second database, and/or the attribute label of the incremental text information in the third database.
Optionally, in any one of the method embodiments of the present disclosure, the extracting an attribute tag of the current object includes: and extracting the attribute label of the current object by using the label extraction model.
Optionally, in any of the method embodiments of the present disclosure above, the method further includes:
and storing the label system and the link addresses of the users, the items or the texts corresponding to the attribute labels in the label system in a distributed full-text search engine ElasticSearch.
Optionally, in any one of the method embodiments of the present disclosure, the obtaining at least one other type of object based on attribute tag matching of the current object from the tag system includes:
acquiring a link address of at least one other type object matched based on the attribute tag of the current object from the tag system stored in the ElasticSearch;
if the at least one other type object comprises a user, obtaining user information linked with a link address of the user from the first database;
if the at least one other type object comprises an item, acquiring item information linked with a link address of the included item from the second database;
and if the at least one other type of object comprises a text, acquiring text information linked with the link address of the included text from the second database.
Optionally, in any of the above method embodiments of the present disclosure, the current object is a user;
before the extracting the attribute tag of the current object, the method further includes: acquiring user related information of the user;
the extracting of the attribute tag of the current object includes: inputting the user-related information into a label extraction model, and extracting an attribute label of the user-related information through the label extraction model;
the obtaining at least one other type object based on the attribute tag matching of the current object from the tag system includes: acquiring items and/or texts matched with the attribute labels based on the user related information from the label system;
the returning of the matched at least one other type of object includes: sending the matched item and/or text to the user.
Optionally, in any method embodiment of the present disclosure, before the obtaining the user-related information of the user, the method further includes:
and receiving a search request initiated by the user, wherein the search request comprises keywords of the items or the texts.
Optionally, in any of the above method embodiments of the present disclosure, the current object is an item;
the extracting of the attribute tag of the current object includes: inputting the project related information of the project into a tag extraction model, and extracting the attribute tag of the project related information through the tag extraction model;
the obtaining at least one other type object based on the attribute tag matching of the current object from the tag system includes: acquiring a text matched with the attribute tag based on the item related information from the tag system;
after the returning of the matched at least one other type object, the method further includes: taking the matched text as introduction information of the item; or, the matched text or the link address of the matched text is set in the item related information.
Optionally, in any of the above method embodiments of the present disclosure, the current object is a text;
the extracting of the attribute tag of the current object includes: inputting the text into a label extraction model, and extracting attribute labels of the text through the label extraction model;
the obtaining at least one other type object based on the attribute tag matching of the current object from the tag system includes: acquiring items matched with the attribute labels based on the text from the label system;
after the returning of the matched at least one other type object, the method further includes: setting the matched item or the link address of the matched item in the text.
Optionally, in any of the above method embodiments of the present disclosure, the item includes any one of: goods, products, services.
In another aspect of the embodiments of the present disclosure, an information acquiring apparatus is provided, including:
the extracting module is used for extracting the attribute label of the current object;
the first acquisition module is used for acquiring at least one other type object matched based on the attribute label of the current object from the label system based on the matching relation of different types of objects in the label system among the attribute labels; the label system comprises attribute labels of various types of objects in various categories and a matching relation between the attribute labels of different types of objects; the different types of objects include: users, items, and text;
and the feedback module is used for returning the matched at least one other type of object.
Optionally, in any apparatus embodiment of the present disclosure, the extracting module is specifically configured to extract the attribute tag of the current object by using a tag extraction model.
Optionally, in any apparatus embodiment of the present disclosure above, the extracting module is further configured to: extracting the labels of the user information in the first database by using a label extraction model to obtain attribute labels of at least one user under each category; extracting the labels of the item information in the second database to obtain attribute labels of at least one item under each category; extracting labels of the text information in the third database to obtain attribute labels of at least one text under each category;
the device further comprises:
and the establishing module is used for establishing a matching relation among the attribute label of the at least one user under each category, the attribute label of the at least one item under each category and the attribute label of the at least one text under each category based on the extracted attribute labels of the at least one user under each category, the extracted attribute labels of the at least one item under each category and the extracted attribute labels of the at least one text under each category to obtain the label system.
Optionally, in any one of the apparatus embodiments of the present disclosure, the apparatus further includes:
the duplication removal filtering module is used for carrying out duplication removal and/or filtering on the user information in the first database; and/or, performing deduplication and/or filtering on the project information in the second database; and/or, performing deduplication and/or filtering on the text information in the third database.
Optionally, in any apparatus embodiment of the present disclosure above, the extracting module is further configured to: extracting the labels of the enhanced user information in the first database, extracting the labels of the incremental project information in the second database and extracting the labels of the incremental text information in the third database in real time or according to a preset period by using a label extraction model;
the establishing module is further configured to update the tag system based on the incremental user information in the first database, the incremental item information in the second database, and/or the attribute tag of the incremental text information in the third database.
Optionally, in any one of the apparatus embodiments of the present disclosure, the apparatus further includes:
and the storage module is used for storing the tag system and the link addresses of the users, the items or the texts corresponding to the attribute tags in the tag system in the distributed full-text search engine ElasticSearch.
Optionally, in any apparatus embodiment of the present disclosure above, the first obtaining module is specifically configured to:
acquiring a link address of at least one other type object matched based on the attribute tag of the current object from the tag system stored in the ElasticSearch;
if the at least one other type object comprises a user, obtaining user information linked with a link address of the user from the first database;
if the at least one other type object comprises an item, acquiring item information linked with a link address of the included item from the second database;
and if the at least one other type of object comprises a text, acquiring text information linked with the link address of the included text from the second database.
Optionally, in any apparatus embodiment of the present disclosure above, the current object is a user;
the device further comprises:
the second acquisition module is used for acquiring the user related information of the user;
the extracting module is specifically used for inputting the user related information into a label extracting model, and extracting the attribute label of the user related information through the label extracting model;
the first obtaining module is specifically configured to obtain, from the tag system, an item and/or a text that is matched based on the attribute tag of the user-related information;
the feedback module is specifically configured to send the matched item and/or text to the user.
Optionally, in any one of the apparatus embodiments of the present disclosure, the apparatus further includes:
a receiving module, configured to receive a search request initiated by the user, where the search request includes a keyword of an item or a text;
the second obtaining module is specifically configured to obtain the user-related information of the user after the receiving module receives the search request initiated by the user.
Optionally, in any of the apparatus embodiments of the present disclosure above, the current object is an item;
the extracting module is specifically used for inputting the project related information of the project into a tag extracting model, and extracting the attribute tag of the project related information through the tag extracting model;
the first obtaining module is specifically configured to obtain a text based on attribute tag matching of the item-related information from the tag system;
the feedback module is further used for taking the matched text as introduction information of the item; or, the matched text or the link address of the matched text is set in the item related information.
Optionally, in any one of the apparatus embodiments of the present disclosure, the current object is a text;
the extracting module is specifically used for inputting the text into a label extracting model, and extracting the attribute label of the text through the label extracting model;
the first obtaining module is specifically configured to obtain an item based on attribute tag matching of the text from the tag system;
the feedback module is further configured to set the matched item or a link address of the matched item in the text.
Optionally, in any of the above apparatus embodiments of the present disclosure, the item includes any one of: goods, products, services.
In another aspect of the disclosed embodiments, an electronic device is provided, including:
a memory for storing a computer program;
a processor for executing the computer program stored in the memory, and the computer program, when executed, implements the method of any of the above embodiments of the present disclosure.
In yet another aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored, and the computer program, when executed by a processor, implements the method according to any of the above embodiments of the present disclosure.
Based on the information acquisition method and apparatus, the electronic device, and the storage medium provided by the above embodiments of the present disclosure, a tag system is established in advance, including attribute tags of various types of objects in various categories and a matching relationship between the attribute tags of different types of objects, where the different types of objects include: users, items, and text; and after receiving the current object, extracting the attribute tag of the current object, and further acquiring at least one other type object matched with the attribute tag of the current object based on the matching relation in the tag system, so as to obtain at least one other type object matched with the current object. Due to the fact that the attribute tags can describe the attributes of the objects accurately, the matching relationship is established among the objects of various types in advance based on the attribute tags of the objects of various types under various categories, the method and the device for recommending the objects of various types can accurately match other objects matched with one type of object, accurate recommendation/search of items, texts and the like is met, recommendation efficiency and search efficiency are improved, and recommendation and search requirements can be met more widely.
The technical solution of the present disclosure is further described in detail by the accompanying drawings and examples.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the disclosure and together with the description, serve to explain the principles of the disclosure.
The present disclosure may be more clearly understood from the following detailed description, taken with reference to the accompanying drawings, in which:
fig. 1 is a flowchart of an embodiment of an information acquisition method according to the present disclosure.
Fig. 2 is a flowchart of another embodiment of the information acquisition method of the present disclosure.
Fig. 3 is a flowchart of another embodiment of the information acquisition method of the present disclosure.
Fig. 4 is a schematic structural diagram of an embodiment of an information acquisition apparatus according to the present disclosure.
Fig. 5 is a schematic structural diagram of another embodiment of the information acquisition apparatus according to the present disclosure.
Fig. 6 is a schematic structural diagram of an embodiment of an electronic device according to the present disclosure.
Detailed Description
Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. It should be noted that: the relative arrangement of the components and steps, the numerical expressions, and numerical values set forth in these embodiments do not limit the scope of the present disclosure unless specifically stated otherwise.
It will be understood by those of skill in the art that the terms "first," "second," and the like in the embodiments of the present disclosure are used merely to distinguish one element from another, and are not intended to imply any particular technical meaning, nor is the necessary logical order between them.
It is also understood that in embodiments of the present disclosure, "a plurality" may refer to two or more and "at least one" may refer to one, two or more.
It is also to be understood that any reference to any component, data, or structure in the embodiments of the disclosure, may be generally understood as one or more, unless explicitly defined otherwise or stated otherwise.
In addition, the term "and/or" in the present disclosure is only one kind of association relationship describing an associated object, and means that three kinds of relationships may exist, for example, a and/or B may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" in the present disclosure generally indicates that the former and latter associated objects are in an "or" relationship.
It should also be understood that the description of the various embodiments of the present disclosure emphasizes the differences between the various embodiments, and the same or similar parts may be referred to each other, so that the descriptions thereof are omitted for brevity.
Meanwhile, it should be understood that the sizes of the respective portions shown in the drawings are not drawn in an actual proportional relationship for the convenience of description.
The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the disclosure, its application, or uses.
Techniques, methods, and apparatus known to those of ordinary skill in the relevant art may not be discussed in detail but are intended to be part of the specification where appropriate.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, further discussion thereof is not required in subsequent figures.
The disclosed embodiments may be applied to electronic devices such as terminal devices, computer systems, servers, etc., which are operational with numerous other general purpose or special purpose computing system environments or configurations. Examples of well known terminal devices, computing systems, environments, and/or configurations that may be suitable for use with electronic devices, such as terminal devices, computer systems, servers, and the like, include, but are not limited to: personal computer systems, server computer systems, thin clients, thick clients, hand-held or laptop devices, microprocessor-based systems, set-top boxes, programmable consumer electronics, networked personal computers, minicomputer systems, mainframe computer systems, distributed cloud computing environments that include any of the above, and the like.
Electronic devices such as terminal devices, computer systems, servers, etc. may be described in the general context of computer system-executable instructions, such as program modules, being executed by a computer system. Generally, program modules may include routines, programs, objects, components, logic, data structures, etc. that perform particular tasks or implement particular abstract data types. The computer system/server may be practiced in distributed cloud computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed cloud computing environment, program modules may be located in both local and remote computer system storage media including memory storage devices.
Fig. 1 is a flowchart of an embodiment of an information acquisition method according to the present disclosure. As shown in fig. 1, the information acquisition method of the embodiment includes:
and 102, extracting the attribute tag of the current object.
Optionally, in some possible implementations, the attribute tag of the current object may be extracted using a tag extraction model.
And 104, acquiring at least one other type object matched based on the attribute label of the current object from the label system based on the matching relation of the different types of objects in the label system among the attribute labels.
The label system comprises attribute labels of various types of objects in various categories and matching relations among the attribute labels of different types of objects.
Optionally, in some possible implementations, the different types of objects may include, but are not limited to: user, item, and text. The current object may be any of the different types of objects, such as a user, an item, or text.
Optionally, in some possible implementations, the item may include, but is not limited to, any one of the following: goods, products, services, and the like.
106, returning the matched at least one other type object.
Based on the information acquisition method provided by the above embodiment of the present disclosure, a tag system is pre-established, including the attribute tags of each type of object in each category and the matching relationship between the attribute tags of different types of objects, where the different types of objects include: users, items, and text; and after receiving the current object, extracting the attribute tag of the current object, and further acquiring at least one other type object matched with the attribute tag of the current object based on the matching relation in the tag system, so as to obtain at least one other type object matched with the current object. Due to the fact that the attribute tags can describe the attributes of the objects accurately, the matching relationship is established among the objects of various types in advance based on the attribute tags of the objects of various types under various categories, the method and the device for recommending the objects of various types can accurately match other objects matched with one type of object, accurate recommendation/search of items, texts and the like is met, recommendation efficiency and search efficiency are improved, and recommendation and search requirements can be met more widely.
Fig. 2 is a flowchart of another embodiment of the information acquisition method of the present disclosure. As shown in fig. 2, on the basis of the embodiment shown in fig. 1, the embodiment further includes the following steps of establishing a label system:
202, extracting the labels of the user information in the first database by using a label extraction model to obtain attribute labels of at least one user under each category; performing label extraction on the item information in the second database by using a label extraction model to obtain attribute labels of at least one item under each category; and extracting the label of the text information in the third database by using the label extraction model to obtain the attribute label of at least one text under each category.
The first database, the second database and the third database are stored with various data depended on for establishing a label system.
In some possible implementations, the first database stores comprehensive user information, which may include, but is not limited to, any one or more of the following items: communication sessions, search logs, item click logs, user portraits, article browsing history, question and answer browsing history, etc.
Where the user representation includes personalized user information, such as but not limited to: the age, sex, hobbies, social attributes, lifestyle and consumption behaviors of the user, and the personalized user information may be obtained from information provided by the user when the user registers with the device implementing the method of the embodiment of the present disclosure, or from information provided when the user registers in other applications or websites. However, the acquisition of the user information by the embodiments of the present disclosure is not limited thereto.
Wherein, from the communication session of the user, the current situation (such as whether married, whether old people exist, whether children exist, etc.) and the project preference information (such as favorite project characteristics, concerned project characteristics, etc.) of the user can be mined; in addition, the behavior preference of the user can be determined according to the search record, the item click log, the article browsing history, the question and answer browsing history and the like of the user; finally, the attribute labels of the users are sorted by taking the project requirements and the user preferences as the guide.
In some possible implementations, the second database stores comprehensive project information, which may include, but is not limited to, any one or more of the following: project title, core selling point, suitable crowd, broker evaluation, owner evaluation, project inherent attributes, user feedback, and the like. For example, when the item is a house source, the house source information in the second database may be, for example: house source title, core selling points, suitable crowd, surrounding matched landmark information, broker evaluation, owner evaluation, house source inherent attribute, watching feedback and the like.
The text in the disclosed embodiments may include articles, questions, and answers, and the like. In some possible implementations, the third database stores comprehensive text information, which may include, but is not limited to, any one or more of the following items: information of the project, encyclopedia articles, service articles, question answers, related knowledge, etc. For example, when the item is a house source, the text information stored in the third database may be, for example: house property information, encyclopedia articles, decoration articles, house property question and answer, house property knowledge and the like. The topics and the keywords of the extracted text can be analyzed in a text clustering and keyword extraction mode, and therefore various attribute labels of the text can be obtained.
And 204, establishing a matching relation among the attribute label of the at least one user under each category, the attribute label of the at least one item under each category and the attribute label of the at least one text under each category based on the extracted attribute labels of the at least one user under each category, the extracted attribute labels of the at least one item under each category and the extracted attribute labels of the at least one text under each category, so as to obtain a label system.
Based on the embodiment, a tag system of matching relations among the attribute tags of the user, the item and the text under each category can be established based on the extraction of the attribute tags of the data stored in the first database, the second database and the third database, so that the matching, information recommendation and matching of the attribute tags are performed based on the tag system in the following, and the accurate recommendation/search of the item, the text and the like is met.
Optionally, in some possible implementation manners, in operation 202, the regular model in the tag extraction model may be used to perform tag extraction on the user information in the first database to obtain abstract tags of at least one user in each category, and then the machine learning model in the tag extraction model is used to obtain attribute tags of the at least one user in each category from the abstract tags of the at least one user in each category.
Because the user information is the unstructured text, the embodiment of the disclosure can rapidly mine and extract the label information of the unstructured text by using the regular model and based on the pre-established regular library, so as to obtain the abstract label with higher accuracy; because the generalization of the regular model is poor, the abstract label is further processed by using the machine learning model, so that the attribute labels of the user under various categories can be obtained.
Optionally, in some possible implementations, in operation 202, the formula model in the tag extraction model may be used to perform tag extraction on the item information in the second database to obtain abstract tags of at least one item under each category, and then, the machine learning model in the tag extraction model is used to obtain attribute tags of the at least one item under each category from the abstract tags of the at least one item under each category.
The project information is structured data, for example, the project information includes: area of the commodity: 88m2(ii) a Price: 8999 yuan; …, the formula model can be used to directly extract the value of each index and compare with the preset range, so as to obtain the attribute label, for example, assume 80-90m2Attribute tag corresponding to Dabie, 60-80m2Attribute tag corresponding to Dayiju, 100- & lt120 & gt m2Corresponding to the attribute label of big one house, 88m will be2And 80-90m2The comparison may determine that the attribute label for the item is a big population, thereby directly generating the attribute label.
Optionally, in some possible implementations, in operation 202, the regular model in the label extraction model may be used to perform label extraction on the text information in the third database to obtain abstract labels of at least one text under each category, and then, the machine learning model in the label extraction model is used to obtain attribute labels of at least one text under each category from the abstract labels of the at least one text under each category.
Because the text information (articles, questions and answers and the like) is the unstructured text, the embodiment of the disclosure can rapidly mine and extract the label information of the unstructured text by using the regular model and based on the pre-established regular library, so as to obtain the abstract label with higher accuracy; because the generalization of the regular model is poor, the abstract labels are further processed by using the machine learning model, so that the attribute labels of the text under various categories can be obtained.
The machine learning model in the embodiment of the present disclosure may be obtained by training in advance based on a test data set composed of a large number of training samples, and the machine learning model obtained by training may obtain corresponding attribute labels for abstract labels of each user or text, and may obtain attribute labels for each item. The training samples of the test data set may include user information samples, project information samples, and text information samples, and each sample is labeled with a corresponding attribute label.
Based on the embodiment, after the attribute tags of the user, the text and the item are extracted, the coverage rate and the accuracy rate of the extracted attribute tags can be calculated and evaluated. Wherein, the coverage refers to how much proportion of the training sample can be covered by one attribute label. For example, if the attribute label of "old people" can cover 15% of the user information samples, the coverage is 15%, and the label coverage can be calculated based on statistical data after obtaining the attribute label. The accuracy rate refers to the accuracy of an attribute label, and can be obtained by comparing the attribute label extracted by the label extraction model with the attribute label marked on the training sample. Based on the coverage rate of the label, the application universality of an attribute label can be obtained, and based on the accuracy rate of the label, the performance of a label extraction model can be obtained, so that a basis is provided for subsequent accurate recommendation and search.
Optionally, in some possible implementations, in operation 204, when a matching relationship between the attribute tag of the at least one user in each category, the attribute tag of the at least one item in each category, and the attribute tag of the at least one text in each category is established, the matching relationship between the at least one user in each category, the at least one item in each category, and the keyword that is contained in the at least one text in the attribute tag in each category may be directly established, or the three may be mapped to a uniform corresponding field to establish the matching relationship between the three.
For example, when the item is a house source, the attribute label of the user is "old people", the attribute label of the house source is "suitable for old people", the attribute label of the text is "about old people", and although the attribute labels of the three are different, the three contain "old people", and a matching relationship can be established based on "old people"; alternatively, all three may be mapped to corresponding "old _ man _ pos" to establish the matching relationship.
The categories of each item, user, text may be different for different domains. For example, for the real estate domain, the label system may include 10 major categories, such as family status, buying purpose, school, cell preference, price, house property, house type, building location, house type, transaction property, etc., subdivided into 93 minor categories. The properties of the house may include, for example, small categories such as lighting, gas, elevator, yard, garden, furniture, household appliances, central heating, north-south permeability, and the like, and the property labels of the user, the house source, and the text corresponding to each small category are matched, for example, in the small category of lighting, the property labels of the matched user, house source, and text are respectively: regarding lighting, good lighting, regarding lighting; in the small category of the elevator, the attribute labels of the matched user, house source and text are respectively as follows: about elevators, with elevators, about elevators; and so on.
Optionally, in the implementation manner, before performing tag extraction on the user information in the first database, the user information in the first database may be deduplicated and/or filtered, for example, the user information may be deduplicated and/or filtered based on a user Identification (ID), where the user ID is used to uniquely identify one user, where deduplication is to remove duplicate user information of the same user, and filtering is to filter out user information that does not meet a preset requirement (for example, an illegal field), so as to implement cleaning of the user information, avoid subsequent processing of duplicate and invalid user information, and improve the processing efficiency of subsequent user information.
Optionally, in the foregoing implementation manner, before performing tag extraction on the item information in the second database, the item information in the second database may be deduplicated and/or filtered, for example, the item information may be deduplicated and/or filtered based on an item Identification (ID), where the item ID is used to uniquely identify an item, where deduplication removes duplicate item information of the same item, and filtering filters out item information that does not meet a preset requirement (e.g., an illegal field), so as to implement cleaning of the item information, avoid subsequent processing on duplicate and invalid item information, and improve processing efficiency of subsequent item information.
Optionally, in the implementation manner, before performing tag extraction on the text information in the third database, the text information in the third database may be deduplicated and/or filtered, for example, the text information may be deduplicated and/or filtered based on a text Identification (ID), where the text ID is used to uniquely identify one text, where deduplication removes repeated text information of the same text, and filtering filters text information that does not meet preset requirements (e.g., illegal fields), so as to implement cleaning of the text information, avoid subsequent processing of repeated and invalid text information, and improve processing efficiency of subsequent text information.
Further, after the embodiment shown in fig. 2, the tag system may be updated based on the incremental user information in the first database, the incremental item information in the second database, and/or the attribute tag of the incremental text information in the third database. Specifically, the incremental user information in the first database, the incremental item information in the second database, and/or the incremental text information in the third database are acquired according to a preset period or in real time, and then the flow of the embodiment shown in fig. 2 is executed for the acquired incremental user information in the first database, the acquired incremental item information in the second database, and/or the acquired incremental text information in the third database, so as to update the established tag system.
Optionally, after the embodiment shown in fig. 2, a tag system and link addresses of users, items or texts corresponding to attribute tags in the tag system may also be stored in a distributed full-text search engine (elastic search).
Fig. 3 is a flowchart of another embodiment of the information acquisition method of the present disclosure. As shown in fig. 3, the information acquisition method of this embodiment includes:
302, the attribute tags of the current object are extracted.
And 304, acquiring a link address of at least one other type object matched based on the attribute tag of the current object from the tag system stored in the elastic search based on the matching relationship between the attribute tags of the different types of objects in the tag system.
The label system comprises attribute labels of various types of objects in various categories and matching relations among the attribute labels of different types of objects.
Optionally, in some possible implementations, the different types of objects may include, but are not limited to: user, item, and text. The current object may be any of the different types of objects, such as a user, an item, or text.
If the at least one other type of object includes a user, performing operation 306; if the at least one other type of object includes an item, performing operation 308; if at least one other type of object includes text, operation 310 is performed.
And 306, acquiring the user information linked with the link address of the user from the first database.
Operation 312 is then performed.
Item information linked to the link address of the included item is acquired from the second database 308.
Operation 312 is then performed.
And 310, acquiring text information linked by the link address of the included text from the third database.
And 312, returning the acquired user information, item information and text information.
The elastic search may store a tag system and link addresses of users, items or texts corresponding to attribute tags in the tag system in an inverted index manner, in this embodiment, a link address of at least one other type of object matched based on an attribute tag of a current object is obtained from the tag system stored in the elastic search, and then user information, item information or text information linked by the link address is obtained from a corresponding database, so that the obtaining efficiency is improved, and the service response time is reduced.
Further, in the above embodiments, when the current object is a user, before operation 102, user-related information of the user may also be acquired. Accordingly, in operation 102, the user-related information may be input into a tag extraction model, and attribute tags of the user-related information may be extracted via the tag extraction model; in operation 104, items and/or texts matched with the attribute tags based on the user-related information may be obtained from the tag system; in operation 106, the matched items and/or text may be sent to the user.
Based on the embodiment, the items and/or texts matched with the requirements of the user can be recommended to the user based on the user related information of the user, so that the accurate recommendation of the user to the items, the texts and the like is met, the recommendation efficiency is improved, and the recommendation requirements of the user can be met more widely.
In addition, in the above embodiment, before obtaining the user-related information of the user, a search request initiated by the user may be further received, where the search request includes a keyword of an item or a text. The method and the device trigger execution of the acquisition of the user related information of the user based on the search request sent by the user, so that the accurate search of the user for items, texts and the like is met, the search efficiency is improved, and the search requirement of the user can be met more widely.
Alternatively, in each of the above embodiments, when the current object is an item, in operation 102, the item-related information of the item may be input into the tag extraction model, and the attribute tag of the item-related information may be extracted through the tag extraction model. Accordingly, in operation 104, a text matched with the attribute tag based on the related information of the item may be obtained from the tag system; after operation 106, the matched text can also be used as introduction information of the item; alternatively, the matched text or the link address of the matched text is set in the item-related information.
Based on the embodiment, the text accurately matched with the project can be obtained, so that the article and the like related to the project can be recommended, a user can comprehensively know the information and knowledge related to the project, and the project recommendation effect is improved.
Alternatively, in each of the above embodiments, when the current object is a text, in operation 102, the text may be input into a tag extraction model, and the attribute tag of the text may be extracted through the tag extraction model. Accordingly, in operation 104, an item matched based on the attribute tag of the text may be obtained from the tag system; in operation 106, the matched item or the link address of the matched item may be set in the text.
Based on the embodiment, the items accurately matched with the text can be obtained, so that recommendation of the items and the like related to the text is realized, a user can conveniently obtain the related items or detailed information thereof under the condition of interest, recommendation of the items is facilitated, and the item recommendation effect is improved.
When the item in the embodiment of the present disclosure is a house source, the scheme in the embodiment of the present disclosure may be applied to house finding, house source recommendation, and service search scenarios, for example, in a broker gabby helper, a house finding robot, house source retrieval recommendation, content retrieval recommendation, and the like. For example, the house source recommendation and search can be applied to the following scenarios:
scene one: the method comprises the steps that a user puts forward a generalized and abstract house finding demand, for example, "i want to find a house which is convenient for a kindergarten and a primary school", wherein the "transportation convenience" and the "convenient for the kindergarten and the primary school" are relatively generalized and abstract concepts, attribute labels of the user, namely "transportation", "kindergarten" and "primary school", can be extracted based on the embodiment of the disclosure, and then house resources consistent with the attribute labels of "transportation", "kindergarten" and "primary school" are matched and recommended to the user;
scene two: the user does not specify his needs, e.g. "i now is: two old people in a family, married for three years, a baby of 1 year old, and what house is recommended? Based on the embodiment of the disclosure, attribute labels 'old people' and 'children' of a user can be extracted, and then house resources consistent with the attribute labels 'old people' and 'children' are matched and recommended to the user;
scene three: in some articles, question answering and other content texts, the attribute tags of the texts can be extracted, and consistent house sources are matched and embedded in the texts, so that better recommendation experience is provided for users. For example, embedding a house source belonging to the law shooting house in an article explaining the law shooting house;
scene four: and extracting the attribute labels of the house resources aiming at the house resources on the house resource card, matching out consistent texts and adding the texts on the house resource card. For example, an article or question and answer about "the bottom trader" is shown on a house source detail page belonging to "the bottom trader".
In recommendation and search scenarios, attribute tags are widely used, and as a brief representation mode, attributes of users, articles or information can be flexibly and accurately described. In the recommendation system, the attribute tags can be used for depicting the preference of the user and improving the recommendation effect; in a search system, attribute tags can be used as attributes of articles or information to improve recall and ranking efficiency. Based on the embodiment of the disclosure, strong relation can be established among three basic entities of users, items and text contents, the extracted attribute tags also have strong abstraction, and in practice, the recommendation and search requirements of the items can be more widely met.
Any of the information acquisition methods provided by the embodiments of the present disclosure may be performed by any suitable device having data processing capabilities, including but not limited to: terminal equipment, a server and the like. Alternatively, any of the information acquisition methods provided by the embodiments of the present disclosure may be executed by a processor, for example, the processor may execute any of the information acquisition methods mentioned in the embodiments of the present disclosure by calling a corresponding instruction stored in a memory. And will not be described in detail below.
Those of ordinary skill in the art will understand that: all or part of the steps for implementing the method embodiments may be implemented by hardware related to program instructions, and the program may be stored in a computer readable storage medium, and when executed, the program performs the steps including the method embodiments; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.
Fig. 4 is a schematic structural diagram of an embodiment of an information acquisition apparatus according to the present disclosure. The information acquisition apparatus of this embodiment can be used to implement the above-mentioned information acquisition method embodiments of the present disclosure. As shown in fig. 4, the information acquisition apparatus of this embodiment includes: the device comprises an extraction module, a first acquisition module and a feedback module. Wherein:
and the extracting module is used for extracting the attribute label of the current object.
The first obtaining module is used for obtaining at least one other type object matched based on the attribute label of the current object from the label system based on the matching relation of different types of objects in the label system among the attribute labels. The label system comprises attribute labels of various types of objects in various categories and a matching relation between the attribute labels of different types of objects; the different types of objects include: user, item, and text. Optionally, in some possible implementations, the item may include, but is not limited to, any one of the following: goods, products, services, and the like.
And the feedback module is used for returning the matched at least one other type of object.
Based on the information acquisition device provided by the embodiment of the disclosure, other types of objects matched with one type of object can be accurately matched, so that accurate recommendation/search of items, texts and the like is met, recommendation efficiency and search efficiency are improved, and recommendation and search requirements can be met more widely.
Optionally, in some possible implementations, the extracting module is specifically configured to extract the attribute tag of the current object by using a tag extraction model.
Fig. 5 is a schematic structural diagram of another embodiment of the information acquisition apparatus according to the present disclosure. In this embodiment, the extracting module may be further configured to: extracting the labels of the user information in the first database by using a label extraction model to obtain attribute labels of at least one user under each category; extracting the labels of the item information in the second database to obtain attribute labels of at least one item under each category; and extracting labels of the text information in the third database to obtain attribute labels of at least one text under each category.
As shown in fig. 5, compared with the embodiment shown in fig. 4, the embodiment further includes: and the establishing module is used for establishing a matching relation among the attribute label of the at least one user under each category, the attribute label of the at least one item under each category and the attribute label of the at least one text under each category based on the extracted attribute labels of the at least one user under each category, the extracted attribute labels of the at least one item under each category and the extracted attribute labels of the at least one text under each category to obtain the label system.
In addition, referring back to fig. 5, in the information acquisition apparatus of the further embodiment, the information acquisition apparatus may further include: the duplication removal filtering module is used for carrying out duplication removal and/or filtering on the user information in the first database; and/or, performing deduplication and/or filtering on the project information in the second database; and/or, performing deduplication and/or filtering on the text information in the third database.
Optionally, in the above embodiment, the extracting module may be further configured to: and extracting the labels of the enhanced user information in the first database, extracting the labels of the incremental project information in the second database and extracting the labels of the incremental text information in the third database in real time or according to a preset period by using a label extraction model. Correspondingly, the establishing module may be further configured to update the tag system based on the incremental user information in the first database, the incremental item information in the second database, and/or the attribute tag of the incremental text information in the third database.
In addition, referring back to fig. 5, in the information acquisition apparatus of still another embodiment, the information acquisition apparatus may further include: and the storage module is used for storing the tag system and the link addresses of the users, the items or the texts corresponding to the attribute tags in the tag system in the distributed full-text search engine ElasticSearch.
Optionally, in some possible implementation manners, the first obtaining module is specifically configured to: acquiring a link address of at least one other type object matched based on the attribute tag of the current object from the tag system stored in the ElasticSearch; if the at least one other type object comprises a user, obtaining user information linked with a link address of the user from the first database; if the at least one other type object comprises an item, acquiring item information linked with a link address of the included item from the second database; and if the at least one other type object comprises an item, acquiring item information linked with the link address of the included item from the second database.
Optionally, in some possible implementations, the current object is a user. Accordingly, the information acquisition apparatus of the above embodiment may further include: and the second acquisition module is used for acquiring the user related information of the user. Correspondingly, the extracting module is specifically configured to input the user-related information into a tag extraction model, and extract the attribute tag of the user-related information through the tag extraction model; the first obtaining module is specifically configured to obtain, from the tag system, an item and/or a text that is matched based on the attribute tag of the user-related information; the feedback module is specifically configured to send the matched item and/or text to the user.
Optionally, in the embodiment of the information acquiring apparatus, the method may further include: a receiving module, configured to receive a search request initiated by the user, where the search request includes a keyword of an item or a text. Accordingly, in this embodiment, the second obtaining module is specifically configured to obtain the user-related information of the user after the receiving module receives the search request initiated by the user.
In other possible implementations, the current object is an item. Correspondingly, in this embodiment, the extracting module is specifically configured to input the item-related information of the item into a tag extraction model, and extract the attribute tag of the item-related information through the tag extraction model; the first obtaining module is specifically configured to obtain a text based on attribute tag matching of the item-related information from the tag system; the feedback module is further used for taking the matched text as introduction information of the item; or, the matched text or the link address of the matched text is set in the item related information.
Alternatively, in yet other possible implementations, the current object is text. Correspondingly, in this embodiment, the extracting module is specifically configured to input the text into a tag extraction model, and extract the attribute tag of the text through the tag extraction model; the first obtaining module is specifically configured to obtain an item based on attribute tag matching of the text from the tag system; the feedback module is further configured to set the matched item or a link address of the matched item in the text.
In addition, an embodiment of the present disclosure also provides an electronic device, including:
a memory for storing a computer program;
a processor, configured to execute the computer program stored in the memory, and when the computer program is executed, implement the information obtaining method according to any of the above embodiments of the present disclosure.
In addition, an embodiment of the present disclosure further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the information acquisition method according to any one of the above embodiments of the present disclosure is implemented.
Fig. 6 is a schematic structural diagram of an embodiment of an electronic device according to the present disclosure. Next, an electronic apparatus according to an embodiment of the present disclosure is described with reference to fig. 6. The electronic device may be either or both of the first device and the second device, or a stand-alone device separate from them, which stand-alone device may communicate with the first device and the second device to receive the acquired input signals therefrom.
As shown in fig. 6, the electronic device includes one or more processors and memory.
The processor may be a Central Processing Unit (CPU) or other form of processing unit having data processing capabilities and/or instruction execution capabilities, and may control other components in the electronic device to perform desired functions.
The memory may include one or more computer program products that may include various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory. The volatile memory may include, for example, Random Access Memory (RAM), cache memory (cache), and/or the like. The non-volatile memory may include, for example, Read Only Memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium and executed by a processor to implement the information acquisition methods of the various embodiments of the present disclosure described above and/or other desired functions.
In one example, the electronic device may further include: an input device and an output device, which are interconnected by a bus system and/or other form of connection mechanism (not shown).
The input device may also include, for example, a keyboard, a mouse, and the like.
The output device may output various information including the determined distance information, direction information, and the like to the outside. The output devices may include, for example, a display, speakers, a printer, and a communication network and remote output devices connected thereto, among others.
Of course, for simplicity, only some of the components of the electronic device relevant to the present disclosure are shown in fig. 6, omitting components such as buses, input/output interfaces, and the like. In addition, the electronic device may include any other suitable components, depending on the particular application.
In addition to the above methods and apparatus, embodiments of the present disclosure may also be a computer program product comprising computer program instructions that, when executed by a processor, cause the processor to perform the steps in the information acquisition method according to the various embodiments of the present disclosure described in the above section of this specification.
The computer program product may write program code for carrying out operations for embodiments of the present disclosure in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server.
Furthermore, embodiments of the present disclosure may also be a computer-readable storage medium having stored thereon computer program instructions that, when executed by a processor, cause the processor to perform the steps in the information acquisition method according to the various embodiments of the present disclosure described in the above section of the present specification.
The computer-readable storage medium may take any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may include, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
The foregoing describes the general principles of the present disclosure in conjunction with specific embodiments, however, it is noted that the advantages, effects, etc. mentioned in the present disclosure are merely examples and are not limiting, and they should not be considered essential to the various embodiments of the present disclosure. Furthermore, the foregoing disclosure of specific details is for the purpose of illustration and description and is not intended to be limiting, since the disclosure is not intended to be limited to the specific details so described.
In the present specification, the embodiments are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same or similar parts in the embodiments are referred to each other. For the system embodiment, since it basically corresponds to the method embodiment, the description is relatively simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The block diagrams of devices, apparatuses, systems referred to in this disclosure are only given as illustrative examples and are not intended to require or imply that the connections, arrangements, configurations, etc. must be made in the manner shown in the block diagrams. These devices, apparatuses, devices, systems may be connected, arranged, configured in any manner, as will be appreciated by those skilled in the art. Words such as "including," "comprising," "having," and the like are open-ended words that mean "including, but not limited to," and are used interchangeably therewith. The words "or" and "as used herein mean, and are used interchangeably with, the word" and/or, "unless the context clearly dictates otherwise. The word "such as" is used herein to mean, and is used interchangeably with, the phrase "such as but not limited to".
The methods and apparatus of the present disclosure may be implemented in a number of ways. For example, the methods and apparatus of the present disclosure may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above-described order for the steps of the method is for illustration only, and the steps of the method of the present disclosure are not limited to the order specifically described above unless specifically stated otherwise. Further, in some embodiments, the present disclosure may also be embodied as programs recorded in a recording medium, the programs including machine-readable instructions for implementing the methods according to the present disclosure. Thus, the present disclosure also covers a recording medium storing a program for executing the method according to the present disclosure.
It is also noted that in the devices, apparatuses, and methods of the present disclosure, each component or step can be decomposed and/or recombined. These decompositions and/or recombinations are to be considered equivalents of the present disclosure.
The previous description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other aspects without departing from the scope of the disclosure. Thus, the present disclosure is not intended to be limited to the aspects shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
The foregoing description has been presented for purposes of illustration and description. Furthermore, this description is not intended to limit embodiments of the disclosure to the form disclosed herein. While a number of example aspects and embodiments have been discussed above, those of skill in the art will recognize certain variations, modifications, alterations, additions and sub-combinations thereof.

Claims (10)

1. An information acquisition method, comprising:
extracting an attribute label of the current object;
acquiring at least one other type object matched based on the attribute label of the current object from the label system based on the matching relation between the attribute labels of different types of objects in the label system; the label system comprises attribute labels of various types of objects in various categories and a matching relation between the attribute labels of different types of objects; the different types of objects include: users, items, and text;
returning the matched at least one other type object.
2. The method of claim 1, further comprising the step of establishing the label system:
extracting the labels of the user information in the first database by using a label extraction model to obtain attribute labels of at least one user under each category; performing label extraction on the item information in the second database by using the label extraction model to obtain attribute labels of at least one item under each category; extracting labels of the text information in the third database by using the label extraction model to obtain attribute labels of at least one text under each category;
and establishing a matching relation among the attribute label of the at least one user under each category, the attribute label of the at least one item under each category and the attribute label of the at least one text under each category based on the extracted attribute labels of the at least one user under each category, the extracted attribute labels of the at least one item under each category and the extracted attribute labels of the at least one text under each category to obtain a label system.
3. The method of claim 2, wherein extracting the user information in the first database by using a label extraction model to obtain the attribute labels of at least one user under each category comprises:
extracting the labels of the user information in the first database by using a regular model in the label extraction model to obtain abstract labels of at least one user under each category;
and obtaining the attribute label of the at least one user under each category by using the machine learning model in the label extraction model and the abstract label of the at least one user under each category.
4. The method according to claim 2 or 3, wherein the extracting the tags from the item information in the second database by using the tag extraction model to obtain the attribute tags of at least one item under each category comprises:
performing label extraction on the item information in the second database by using a formula model in the label extraction model to obtain abstract labels of at least one item under each category;
and obtaining the attribute label of the at least one item under each category according to the abstract label of the at least one item under each category by using a machine learning model in the label extraction model.
5. The method according to any one of claims 2 to 4, wherein the performing label extraction on the text information in the third database by using the label extraction model to obtain the attribute label of at least one text under each category comprises:
performing label extraction on the text information in the third database by using a regular model in the label extraction model to obtain abstract labels of at least one text under each category;
and obtaining the attribute label of the at least one text under each category according to the abstract label of the at least one text under each category by using a machine learning model in the label extraction model.
6. The method according to any one of claims 2-5, wherein before extracting the tag from the user information in the first database, the method further comprises: carrying out duplicate removal and/or filtration on the user information in the first database; and/or the presence of a gas in the gas,
before the tag extraction of the item information in the second database, the method further includes: removing duplicate and/or filtering project information in the second database; and/or the presence of a gas in the gas,
before extracting the label from the text information in the third database, the method further includes: and carrying out duplicate removal and/or filtering on the text information in the third database.
7. The method of any of claims 2-6, further comprising:
updating the label system based on the incremental user information in the first database, the incremental item information in the second database, and/or the attribute label of the incremental text information in the third database.
8. An information acquisition apparatus characterized by comprising:
the extracting module is used for extracting the attribute label of the current object;
the first acquisition module is used for acquiring at least one other type object matched based on the attribute label of the current object from the label system based on the matching relation of different types of objects in the label system among the attribute labels; the label system comprises attribute labels of various types of objects in various categories and a matching relation between the attribute labels of different types of objects; the different types of objects include: users, items, and text;
and the feedback module is used for returning the matched at least one other type of object.
9. An electronic device, comprising:
a memory for storing a computer program;
a processor for executing a computer program stored in the memory, and when executed, implementing the method of any of the preceding claims 1-7.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the method of any one of the preceding claims 1 to 7.
CN201911266244.3A 2019-12-11 2019-12-11 Information acquisition method and device, electronic equipment and storage medium Active CN111125566B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911266244.3A CN111125566B (en) 2019-12-11 2019-12-11 Information acquisition method and device, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911266244.3A CN111125566B (en) 2019-12-11 2019-12-11 Information acquisition method and device, electronic equipment and storage medium

Publications (2)

Publication Number Publication Date
CN111125566A true CN111125566A (en) 2020-05-08
CN111125566B CN111125566B (en) 2021-08-31

Family

ID=70498511

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911266244.3A Active CN111125566B (en) 2019-12-11 2019-12-11 Information acquisition method and device, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN111125566B (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112131321A (en) * 2020-08-06 2020-12-25 亿存(北京)信息科技有限公司 User portrait label generation method and device, computer equipment and storage medium
CN112487035A (en) * 2020-12-04 2021-03-12 国泰新点软件股份有限公司 Label storage and query method and device based on elastic search
CN113326254A (en) * 2021-06-18 2021-08-31 立信(重庆)数据科技股份有限公司 Research data cleaning method and system
CN113362105A (en) * 2021-06-01 2021-09-07 北京十一贝科技有限公司 User label forming method, device and computer readable storage medium
CN114416669A (en) * 2022-03-30 2022-04-29 天津联想协同科技有限公司 Group process file management method, device, network disk and storage medium

Citations (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1284461A1 (en) * 2001-08-13 2003-02-19 Xerox Corporation Meta-document management system with user definable personalities
CN101283353A (en) * 2005-08-03 2008-10-08 温克科技公司 Systems for and methods of finding relevant documents by analyzing tags
CN101331474A (en) * 2005-12-16 2008-12-24 微软公司 Browsing items related to email
KR20130128525A (en) * 2012-05-17 2013-11-27 삼성탈레스 주식회사 Configuration management system of derivative projects and method thereof
CN105227971A (en) * 2015-07-09 2016-01-06 传成文化传媒（上海）有限公司 The information recommendation method of a kind of hotel TV and system
CN106796609A (en) * 2014-12-19 2017-05-31 三星电子株式会社 The method that content is provided and the electronic installation for performing the method
CN107292097A (en) * 2017-06-14 2017-10-24 华东理工大学 The feature selection approach of feature based group and traditional Chinese medical science primary symptom system of selection
CN107992585A (en) * 2017-12-08 2018-05-04 北京百度网讯科技有限公司 Universal tag method for digging, device, server and medium
CN108280200A (en) * 2018-01-29 2018-07-13 百度在线网络技术（北京）有限公司 Method and apparatus for pushed information
CN108628981A (en) * 2018-04-27 2018-10-09 四川斐讯信息技术有限公司 A kind of article method for pushing and system based on body index
CN108681969A (en) * 2018-04-24 2018-10-19 深圳市众投邦股份有限公司 Terminal, the determination method of investment project and its device and readable storage medium storing program for executing
CN109344249A (en) * 2018-08-14 2019-02-15 阿里巴巴集团控股有限公司 Information processing method, device, electronic equipment and computer readable storage medium
CN109493199A (en) * 2019-01-04 2019-03-19 深圳壹账通智能科技有限公司 Products Show method, apparatus, computer equipment and storage medium
CN110188268A (en) * 2019-05-21 2019-08-30 浙江工商大学 A kind of personalized recommendation method based on label and temporal information
CN110196948A (en) * 2019-06-10 2019-09-03 北京金山安全软件有限公司 Content recommendation method and device, computer equipment and storage medium
CN110222252A (en) * 2019-06-14 2019-09-10 宜春宜联科技有限公司 Information retrieval method, device and equipment
US20190303768A1 (en) * 2016-12-30 2019-10-03 Huawei Technologies Co., Ltd. Community Question Answering-Based Article Recommendation Method, System, and User Device

Patent Citations (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1284461A1 (en) * 2001-08-13 2003-02-19 Xerox Corporation Meta-document management system with user definable personalities
CN101283353A (en) * 2005-08-03 2008-10-08 温克科技公司 Systems for and methods of finding relevant documents by analyzing tags
CN101331474A (en) * 2005-12-16 2008-12-24 微软公司 Browsing items related to email
KR20130128525A (en) * 2012-05-17 2013-11-27 삼성탈레스 주식회사 Configuration management system of derivative projects and method thereof
CN106796609A (en) * 2014-12-19 2017-05-31 三星电子株式会社 The method that content is provided and the electronic installation for performing the method
CN105227971A (en) * 2015-07-09 2016-01-06 传成文化传媒（上海）有限公司 The information recommendation method of a kind of hotel TV and system
US20190303768A1 (en) * 2016-12-30 2019-10-03 Huawei Technologies Co., Ltd. Community Question Answering-Based Article Recommendation Method, System, and User Device
CN107292097A (en) * 2017-06-14 2017-10-24 华东理工大学 The feature selection approach of feature based group and traditional Chinese medical science primary symptom system of selection
CN107992585A (en) * 2017-12-08 2018-05-04 北京百度网讯科技有限公司 Universal tag method for digging, device, server and medium
CN108280200A (en) * 2018-01-29 2018-07-13 百度在线网络技术（北京）有限公司 Method and apparatus for pushed information
CN108681969A (en) * 2018-04-24 2018-10-19 深圳市众投邦股份有限公司 Terminal, the determination method of investment project and its device and readable storage medium storing program for executing
CN108628981A (en) * 2018-04-27 2018-10-09 四川斐讯信息技术有限公司 A kind of article method for pushing and system based on body index
CN109344249A (en) * 2018-08-14 2019-02-15 阿里巴巴集团控股有限公司 Information processing method, device, electronic equipment and computer readable storage medium
CN109493199A (en) * 2019-01-04 2019-03-19 深圳壹账通智能科技有限公司 Products Show method, apparatus, computer equipment and storage medium
CN110188268A (en) * 2019-05-21 2019-08-30 浙江工商大学 A kind of personalized recommendation method based on label and temporal information
CN110196948A (en) * 2019-06-10 2019-09-03 北京金山安全软件有限公司 Content recommendation method and device, computer equipment and storage medium
CN110222252A (en) * 2019-06-14 2019-09-10 宜春宜联科技有限公司 Information retrieval method, device and equipment

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
王树梅: "信息检索相关技术研究", 《中国博士学位论文全文数据库 信息科技辑》 *
范强: "基于社区热度的开源软件排序关键技术研究", 《中国优秀硕士学位论文全文数据库 信息科技辑 》 *

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112131321A (en) * 2020-08-06 2020-12-25 亿存(北京)信息科技有限公司 User portrait label generation method and device, computer equipment and storage medium
CN112487035A (en) * 2020-12-04 2021-03-12 国泰新点软件股份有限公司 Label storage and query method and device based on elastic search
CN113362105A (en) * 2021-06-01 2021-09-07 北京十一贝科技有限公司 User label forming method, device and computer readable storage medium
CN113362105B (en) * 2021-06-01 2024-02-02 北京十一贝科技有限公司 User tag forming method, apparatus and computer readable storage medium
CN113326254A (en) * 2021-06-18 2021-08-31 立信(重庆)数据科技股份有限公司 Research data cleaning method and system
CN114416669A (en) * 2022-03-30 2022-04-29 天津联想协同科技有限公司 Group process file management method, device, network disk and storage medium
CN114416669B (en) * 2022-03-30 2022-07-26 天津联想协同科技有限公司 Group process file management method, device, network disk and storage medium

Also Published As

Publication number Publication date
CN111125566B (en) 2021-08-31

Similar Documents

Publication Publication Date Title
CN111125566B (en) Information acquisition method and device, electronic equipment and storage medium
US20180218015A1 (en) Intelligent internet system with adaptive user interface providing one-step access to knowledge
Zhao et al. Connecting social media to e-commerce: Cold-start product recommendation using microblogging information
US9576075B2 (en) Context aware query selection
US8370358B2 (en) Tagging content with metadata pre-filtered by context
US9361317B2 (en) Method for entity enrichment of digital content to enable advanced search functionality in content management systems
US8688702B1 (en) Techniques for using dynamic data sources with static search mechanisms
US9454781B2 (en) Ranking and recommendation of online content
JP7387432B2 (en) Systems and methods for collecting data related to unauthorized content in a networked environment
US8984414B2 (en) Function extension for browsers or documents
US20090240638A1 (en) Syntactic and/or semantic analysis of uniform resource identifiers
US11514124B2 (en) Personalizing a search query using social media
US9390168B1 (en) Customer keyword-based item recommendations
US11416907B2 (en) Unbiased search and user feedback analytics
US20160092960A1 (en) Product recommendations over multiple stores
CN111949785A (en) Query statement management method and device, readable storage medium and electronic device
WO2014107150A1 (en) Inferring facts from online user activity
Hsu et al. Integrated machine learning with semantic web for open government data recommendation based on cloud computing
US10529002B2 (en) Classification of visitor intent and modification of website features based upon classified intent
KR101853388B1 (en) Social context for offsite advertisements
US11347929B1 (en) Method and system for linking product page on social media
US10423636B2 (en) Relating collections in an item universe
EP3968182A1 (en) Computerized smart inventory search methods and systems using classification and tagging
US20220075835A1 (en) Feature recommendation based on user-generated content
Thaokar et al. Recommendation System: Overview, Current Applications and Future Scope.

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
TA01 Transfer of patent application right
TA01 Transfer of patent application right

Effective date of registration: 20201020

Address after: 100085 Floor 102-1, Building No. 35, West Second Banner Road, Haidian District, Beijing

Applicant after: Seashell Housing (Beijing) Technology Co.,Ltd.

Address before: 300 457 days Unit 5, Room 1, 112, Room 1, Office Building C, Nangang Industrial Zone, Binhai New Area Economic and Technological Development Zone, Tianjin

Applicant before: BEIKE TECHNOLOGY Co.,Ltd.

GR01 Patent grant
GR01 Patent grant