CN113032578A - Information pushing method and device based on hotspot event and computer equipment - Google Patents
Information pushing method and device based on hotspot event and computer equipment Download PDFInfo
- Publication number
- CN113032578A CN113032578A CN202110308396.6A CN202110308396A CN113032578A CN 113032578 A CN113032578 A CN 113032578A CN 202110308396 A CN202110308396 A CN 202110308396A CN 113032578 A CN113032578 A CN 113032578A
- Authority
- CN
- China
- Prior art keywords
- data
- event
- entity name
- target
- recommended
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
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
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- 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
-
- 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
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/237—Lexical tools
- G06F40/247—Thesauruses; Synonyms
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses an information pushing method and device based on a hot event, computer equipment and a storage medium, and relates to big data and a knowledge graph.
Description
Technical Field
The invention relates to the field of knowledge graphs of big data, in particular to an information pushing method and device based on hot events, computer equipment and a storage medium.
Background
At present, a common method for a user to pay attention to hot spot information is on a web portal (e.g., green microblog, known name, etc.), and after the user views a certain hot spot information, the user needs to view knowledge related to the hot spot (e.g., a certain person name or a certain term appears in the hot spot information), and then needs to log in a search engine to query the related knowledge, which causes the knowledge to be scattered in each system, i.e., the data is unevenly distributed, the number of returns is large, and the summary search is difficult in the conventional storage method.
Disclosure of Invention
The embodiment of the invention provides an information pushing method, an information pushing device, computer equipment and a storage medium based on a hotspot event, and aims to solve the problems that after a user checks certain hotspot information, the user needs to check hotspot related knowledge and needs to log in a search engine to inquire the related knowledge, so that data distribution is uneven, multiple entrances are made, and summary searching is difficult.
In a first aspect, an embodiment of the present invention provides an information pushing method based on a hotspot event, including:
if the difference between the current data acquisition time and the previous data acquisition time is equal to a preset data acquisition period, acquiring web page data from web pages respectively corresponding to a preset data acquisition website set to obtain a web page data set, and acquiring a sub-web page data set corresponding to each data acquisition website in the web page data set; each subnet page data set comprises a plurality of event data;
extracting through keywords to obtain an entity name set corresponding to each event data;
if an entity name set corresponding to event data is a non-empty set, acquiring corresponding target event data and a target entity name set corresponding to the target event data;
if the target entity name set comprises a first type entity name, acquiring an approximate entity name set corresponding to the first type entity name from a pre-constructed knowledge map library;
generating a target event knowledge graph corresponding to the target event data according to a pre-constructed body and knowledge representation of the target event data to serve as first type data to be recommended;
acquiring a first target knowledge graph corresponding to the first type entity name, acquiring an approximate entity target knowledge graph corresponding to each approximate entity name in the approximate entity name set, and forming second type data to be recommended by the first target knowledge graph and the approximate entity target knowledge graph corresponding to each approximate entity name;
acquiring a current target entity name and a current target sub-knowledge graph corresponding to the first type entity name serving as the condition keyword in the first target knowledge graph to serve as third type data to be recommended; and
and filling the first type of data to be recommended, the second type of data to be recommended and the third type of data to be recommended into a data container to obtain information data to be recommended corresponding to the event data.
In a second aspect, an embodiment of the present invention provides an information pushing apparatus based on a hotspot event, including:
the webpage data acquisition unit is used for acquiring webpage data from webpages respectively corresponding to a preset data acquisition website set to obtain a webpage data set and acquiring a sub-webpage data set corresponding to each data acquisition website in the webpage data set if the difference between the current data acquisition time and the previous data acquisition time is equal to a preset data acquisition period; each subnet page data set comprises a plurality of event data;
the entity extraction unit is used for extracting the keywords to obtain an entity name set corresponding to each event data;
the target event data acquisition unit is used for acquiring corresponding target event data and a target entity name set corresponding to the target event data if the entity name set corresponding to the event data is a non-empty set;
an approximate entity obtaining unit, configured to obtain, if the target entity name set includes a first type entity name, an approximate entity name set corresponding to the first type entity name from a pre-constructed knowledge map library;
the first recommendation data generation unit is used for generating a target event knowledge graph corresponding to the target event data according to a pre-constructed body and knowledge representation of the target event data to serve as first type data to be recommended;
the second recommendation data generation unit is used for acquiring a first target knowledge map corresponding to the first type entity name, acquiring an approximate entity target knowledge map corresponding to each approximate entity name in the approximate entity name set, and forming second type data to be recommended by the first target knowledge map and the approximate entity target knowledge maps corresponding to the approximate entity names;
a third recommendation data generation unit, configured to acquire a current target entity name and a current target sub-knowledge graph corresponding to the first type entity name as the condition keyword in the first target knowledge graph, and use the current target entity name and the current target sub-knowledge graph as third type data to be recommended; and
and the information data to be recommended generating unit is used for filling the first type of data to be recommended, the second type of data to be recommended and the third type of data to be recommended into a data container so as to obtain information data to be recommended corresponding to the event data.
The embodiment of the invention provides an information pushing method, an information pushing device, computer equipment and a storage medium based on a hot event, wherein first type data to be recommended, second type data to be recommended and third type data to be recommended are obtained under the condition that a data acquisition condition is met, the first type data to be recommended, the second type data to be recommended and the third type data to be recommended are filled into a data container to obtain information data to be recommended corresponding to the event data, namely the information data to be recommended are quickly obtained based on the hot event and are sent to a user side in an information card mode.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic view of an application scenario of an information pushing method based on a hotspot event according to an embodiment of the present invention;
fig. 2 is a schematic flowchart of an information pushing method based on a hotspot event according to an embodiment of the present invention;
fig. 3 is a schematic block diagram of an information pushing apparatus based on a hot spot event according to an embodiment of the present invention;
FIG. 4 is a schematic block diagram of a computer device provided by an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It will be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It is also to be understood that the terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the specification of the present invention and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should be further understood that the term "and/or" as used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.
Referring to fig. 1 and fig. 2, fig. 1 is a schematic view of an application scenario of an information pushing method based on a hot spot event according to an embodiment of the present invention; fig. 2 is a schematic flowchart of an information pushing method based on a hotspot event according to an embodiment of the present invention, where the information pushing method based on a hotspot event is applied to a server, and the method is executed by application software installed in the server.
As shown in fig. 2, the method includes steps S101 to S109.
S101, constructing a knowledge graph library according to the acquired data source; the knowledge graph library comprises a plurality of sub knowledge graphs, each sub knowledge graph comprises a plurality of entities with association relations, and the sub knowledge graphs are associated through the association relations among the entities.
In this embodiment, for a clearer understanding of the technical solution, the following describes the terminal related to the present application in detail. The technical scheme is described in the angle of the server.
The knowledge graph library comprises a plurality of sub knowledge graphs, each sub knowledge graph comprises a plurality of entities with association relations, and the sub knowledge graphs are associated through the association relations among the entities. Moreover, the sub-knowledge-graphs in the knowledge-graph library are updated periodically (e.g., a 23:00 update per day of the week is set), which ensures that the content in the knowledge-graph library is current and up-to-date. The server can also acquire webpage contents in the appointed website at regular time to judge whether the concerned entity name exists, if the concerned entity name exists in the webpage contents, a plurality of similar entity names which are most similar to the concerned entity name are obtained in the knowledge map library to form a similar entity name set, and the sub-knowledge maps corresponding to the similar entity names in the similar entity name set and the knowledge maps corresponding to the concerned entity names form thematic contents which are pushed to a user side for viewing.
And secondly, the client can receive the thematic content sent by the server, view the thematic content, share the thematic content and send the thematic content to other clients, and can also query and acquire the corresponding sub-knowledge graph in the knowledge graph library of the server through the input entity name.
Taking the knowledge graph of the insurance field as an example, the data source can be set to be in a plurality of source modes as follows:
A1) generating a sub-knowledge graph of the insurance field based on a plurality of kinds of original data related to the insurance industry based on a pre-constructed ontology and knowledge representation, and storing the sub-knowledge graph into a knowledge graph library;
A2) acquiring a document (the document can be TXT, DOC, EXCEL, PPT, PDF, XML and the like) uploaded to a server, identifying a text of the document in a picture form by an OCR technology, or directly extracting the text of the document in a non-picture form, and then identifying and extracting key knowledge (subject, object, time, place, amount, clause and the like), thereby realizing the construction of the knowledge graph.
When each sub-knowledge graph is specifically constructed, an ontology in an entity-attribute-constraint-value format is adopted, so that the knowledge can be more accurately described compared with the commonly used ontology in two formats of an entity-attribute value and an entity-relation. For example: the question "a 65-year old person died after getting mild symptoms, and what security fund can be drawn when you invest the product a before? ", the following entity attribute relationships are represented: product a-liability for assurance-insurance-underwriting-underdeveloped disease & age 65-value. Namely, product a is an entity and the guarantee liability is an attribute, provided that the elderly are too mild and are 65 years old, and the insurance fund is an attribute.
S102, if the difference between the current data acquisition time and the previous data acquisition time is equal to a preset data acquisition period, acquiring webpage data from webpages respectively corresponding to a preset data acquisition website set to obtain a webpage data set, and acquiring a sub-webpage data set corresponding to each data acquisition website in the webpage data set; wherein each subnet page data set comprises a plurality of event data.
In this embodiment, the server acquires web page data from the web pages corresponding to the preset data acquisition website sets at regular intervals. For example, the preset data acquisition website may be a hot search page of a microblog or an equative portal website, and a hot event in the current time period can be accurately obtained in the hot search page. More specifically, the technical scheme of the application is described by taking a hot search page of a microblog as one of data acquisition websites of a data acquisition website set as an example.
For example, the hot search events corresponding to the microblog at the current data acquisition time include the following 3 events: 1. XXX1 was frayed on the thighs in a game of participating in YY 1; 2. XXX2 is held a wedding today with YY2 in the markov; 3. XXX3 was successful in developing YY 3; and forming a sub-web page data set corresponding to the data acquisition website of the microblog by the texts corresponding to the 3 hot search events. And collecting webpage data from the webpages respectively corresponding to the plurality of data collection website sets to form a webpage data set.
And S103, extracting the keywords to obtain an entity name set corresponding to each event data.
In this embodiment, after acquiring the sub-web data set corresponding to each data acquisition website, each sub-web data set includes a plurality of event data, for example, the data acquisition website corresponding to the microblog in the above example, the 3 texts corresponding to the hot search events form the sub-web data set, where the text corresponding to each hot search event corresponds to one event data.
The general event data exists in the form of short titles and web page hyperlinks, that is, the short title of the click event data is directly jumped to the news information corresponding to the short title, so the process of extracting the entity name set for each event data is as follows:
acquiring an event title and an event news information text corresponding to event data to form an event text corresponding to the event data;
obtaining a keyword set corresponding to the event text by sequentially performing word segmentation and keyword acquisition on the event text;
and deleting the keywords which do not exist in the entity name set of the knowledge map library in the keyword set to obtain the entity name set corresponding to the event data.
In this embodiment, when the server needs to obtain the news information text of a certain event data, a click action is generated to trigger skipping of the news information corresponding to the short title. For example, if the server simulates that the thigh strain occurs during the game of YY1 after clicking the hot search event 1-XXX 1, the server jumps to the news information corresponding to the hot search event 1, and the event text is composed of the event title and the event news information text.
When the keywords are extracted from the event text, performing word segmentation on the event text through a probability statistics based word segmentation model to obtain a word segmentation result corresponding to the event text; and extracting the keywords of which the word segmentation results do not exceed a preset ranking threshold value after descending sorting according to the frequency-inverse text frequency indexes through a word frequency-inverse text frequency index model to form a keyword set.
The keywords in the keyword set extracted by the hot search event 1 may be the entity names of the sub-knowledge maps in the knowledge map library, or may not be the entity names of the sub-knowledge maps in the knowledge map library, and the keywords in the keyword set are compared with the entity names in the knowledge map library one by one, so that the keywords which do not exist in the entity name set in the knowledge map library can be judged, and the keywords which do not exist in the entity name set in the knowledge map library in the keyword set are deleted, so that the entity name set corresponding to the event data is obtained.
After the above-mentioned keyword screening process, the following two situations may occur: firstly, all keywords in the keyword set do not exist in the entity name set of the knowledge map library, and the entity name set corresponding to the event data is obtained as an empty set; and secondly, only part of the keywords in the keyword set do not exist in the entity name set of the knowledge map library, and the entity name set corresponding to the event data is obtained as a non-empty set at the moment.
S104, if the entity name set corresponding to the event data is a non-empty set, acquiring corresponding target event data and a target entity name set corresponding to the target event data.
In this embodiment, if an entity name set corresponding to event data is a non-empty set, which indicates that the content corresponding to the event data is the content concerned by the server, then to further analyze the event data, a target entity name set corresponding to the event data needs to be obtained.
S105, if the target entity name set comprises the first type entity name, obtaining an approximate entity name set corresponding to the first type entity name from a pre-constructed knowledge map library.
In this embodiment, if the target entity name set includes a first type entity name (for example, one of the corresponding entity names in the above-mentioned thermal search event 1 is a thigh pull, and the thigh pull belongs to the first type entity name), then the first type entity name is used to obtain an approximate entity name set corresponding to the first type entity name from a plurality of entity names corresponding to the knowledge map library.
When obtaining the approximate words of the words, the following method can be used:
acquiring an entity name library and a synonym dictionary corresponding to a knowledge map library, and acquiring a word forest corresponding to the synonym dictionary;
and acquiring approximate entity names corresponding to the first type entity names in the entity name library according to the word forest to form an approximate entity name set.
In the present embodiment, a synonym dictionary for determining the similarity between words is stored in the server. All words included in the synonym are organized in one or more tree structures (the tree or a plurality of books are marked as a word forest), nodes corresponding to two words of which the word similarity needs to be judged are found in the word forest, and the path lengths of the two nodes can be used as the semantic distance (also can be understood as the word similarity) between the two words. In order to limit that only a few approximate entity names appear in the approximate entity name set, entity names which need to be corresponding to the first type entity names and whose word similarity exceeds a preset word similarity threshold value can be limited, and thus a final obtained approximate entity name set can be formed. For example, the physical names similar to the strain injury of the thigh are flexor tendon injury and hand tendon injury, and the flexor tendon injury and the hand tendon injury form an approximate physical name set corresponding to the strain injury of the thigh.
And S106, generating a target event knowledge graph corresponding to the target event data according to the pre-constructed body and knowledge representation of the target event data to serve as first type data to be recommended.
In this embodiment, in order to more simply display the target event data, but not simply display the target event data only through an event title, a target event knowledge graph corresponding to the target event data may be extracted at this time, so as to simply display an event.
Specifically, when the target event knowledge graph corresponding to the target event data is generated, the pre-constructed ontology and the ontology in the format of 'entity-attribute-constraint-value' are extracted from the knowledge representation, so that the first type of data to be recommended is obtained.
S107, acquiring a first target knowledge graph corresponding to the first type entity name, acquiring an approximate entity target knowledge graph corresponding to each approximate entity name in the approximate entity name set, and forming second type data to be recommended by the first target knowledge graph and the approximate entity target knowledge graph corresponding to each approximate entity name.
In this embodiment, in addition to simply showing the target event data by using the target event knowledge graph, a plurality of similar entity names most similar to the concerned first type entity name may be obtained from the knowledge graph library to form a similar entity name set, and the topic content formed by the sub-knowledge graphs corresponding to the similar entity names in the similar entity name set and the knowledge graphs corresponding to the concerned entity names is pushed to the user side for viewing. For example, the entity name similar to the strain injury of the thigh includes a flexor tendon injury and a hand tendon injury, a sub-knowledge map corresponding to the entity name of the flexor tendon injury and a sub-knowledge map corresponding to the entity name of the hand tendon injury are obtained, and therefore the second type of data to be recommended are formed by the first target knowledge map, and therefore a special content can be formed and pushed to a user side for viewing.
And S108, acquiring a current target entity name and a current target sub-knowledge graph corresponding to the first type entity name as the condition key word in the first target knowledge graph to be used as third type data to be recommended.
In this embodiment, since the ontology in the format of "entity-attribute-constraint-value" is used in the knowledge graph library, the first type entity name can be used as a condition keyword for a certain product entity in addition to the entity name, as described in the above example, "product a-insurance responsibility-insurance-mild disease &65 years old-age-value". At this time, the current target entity name and the current target sub-knowledge map corresponding to the first type entity name as the condition keyword in the first target knowledge map can be obtained to be used as the third type data to be recommended, so that targeted recommendation of insurance products based on a certain pain type is realized, data matching is more accurate, and the matching process is more efficient due to automatic realization.
S109, filling the first type of data to be recommended, the second type of data to be recommended and the third type of data to be recommended into a data container to obtain information data to be recommended corresponding to the event data.
In this embodiment, since the first type of data to be recommended, the second type of data to be recommended, and the third type of data to be recommended are obtained before, these pieces of information may be regarded as recommendation sub-information sets, and if the pieces of information are pushed to the user side in scattered content, it is inconvenient for the user to view these recommendation sub-information sets. In order to further integrate the concentrated recommendation sub-information sets into a concentrated area, the recommendation sub-information sets may be filled into a called data container, and the recommendation sub-information sets are loaded by using the data container as a carrier. Therefore, when the data container loaded with the content data is sent to the user side, the user can open the data container to view the data pushed by the server in a centralized mode. The created data container can be a card container, and the card container is a component on a UI interface provided by the server, and can be used as a container to conveniently display contents composed of different data elements (such as pictures and texts). When creating the data container, it is only necessary to call from the component library. The data container may be understood as a content aggregation component, which may be divided into different sub-containers to accommodate different types of data.
In one embodiment, step S109 includes:
a blank card container with empty data is created in advance;
acquiring the total number of recommendation sub-information included in the first type of data to be recommended, the second type of data to be recommended and the third type of data to be recommended;
creating sub-card areas with the same number as the total number in the blank card container;
and filling one recommendation sub-information in each sub-chip area to obtain information data to be recommended.
In this embodiment, for better aggregating the content data, the card container may be selected as a carrier to load the recommendation sub-information set. A card may be understood as a component on a UI interface provided by a server, which may be used as a container to conveniently display contents composed of different data elements (such as text). Creating a blank card container, then counting the total number of recommendation sub-information included in the first type of data to be recommended, the second type of data to be recommended and the third type of data to be recommended, wherein the total number determines how many sub-card areas the blank card container is divided into, and finally filling each sub-card area with one recommendation sub-information to obtain the current card. Through the current card, the user can view the information data to be recommended in a centralized manner without acquiring knowledge through a search engine.
In an embodiment, the step of filling one recommendation sub-information in each sub-chip region to obtain information data to be recommended further includes:
and correspondingly increasing buried points in each sub-chip area.
In this embodiment, the buried points are correspondingly added in each sub-chip region, so that user behavior data of a user for the content in each sub-chip region, such as the opening times, the reading duration and the like, can be effectively collected, and the user behavior data can be used as a basis for recommending other information data to the user again in the following.
According to the method, the information data to be recommended are quickly acquired based on the hot event and are sent to the user side in the information card mode, the screened content is more accurate, the content can be viewed in a centralized and visual mode after being loaded through the card container, and a search engine is not needed to retrieve relevant knowledge.
The embodiment of the invention also provides an information pushing device based on the hotspot event, which is used for executing any embodiment of the information pushing method based on the hotspot event. Specifically, referring to fig. 3, fig. 3 is a schematic block diagram of an information pushing apparatus based on a hot spot event according to an embodiment of the present invention. The information pushing apparatus 100 based on the hot spot event can be configured in a server.
As shown in fig. 3, the information pushing apparatus 100 based on the hotspot event includes: the recommendation system comprises a knowledge graph library establishing unit 101, a webpage data collecting unit 102, an entity extracting unit 103, a target event data acquiring unit 104, an approximate entity acquiring unit 105, a first recommendation data generating unit 106, a second recommendation data generating unit 107, a third recommendation data generating unit 108 and an information data generating unit 109 to be recommended.
A knowledge graph library establishing unit 101, configured to establish a knowledge graph library according to the acquired data source; the knowledge graph library comprises a plurality of sub knowledge graphs, each sub knowledge graph comprises a plurality of entities with association relations, and the sub knowledge graphs are associated through the association relations among the entities.
In this embodiment, taking the knowledge graph of the insurance domain as an example, the data source can be set to be a plurality of sources, as follows:
A1) generating a sub-knowledge graph of the insurance field based on a plurality of kinds of original data related to the insurance industry based on a pre-constructed ontology and knowledge representation, and storing the sub-knowledge graph into a knowledge graph library;
A2) acquiring a document (the document can be TXT, DOC, EXCEL, PPT, PDF, XML and the like) uploaded to a server, identifying a text of the document in a picture form by an OCR technology, or directly extracting the text of the document in a non-picture form, and then identifying and extracting key knowledge (subject, object, time, place, amount, clause and the like), thereby realizing the construction of the knowledge graph.
When each sub-knowledge graph is specifically constructed, an ontology in an entity-attribute-constraint-value format is adopted, so that the knowledge can be more accurately described compared with the commonly used ontology in two formats of an entity-attribute value and an entity-relation. For example: the question "a 65-year old person died after getting mild symptoms, and what security fund can be drawn when you invest the product a before? ", the following entity attribute relationships are represented: product a-liability for assurance-insurance-underwriting-underdeveloped disease & age 65-value. Namely, product a is an entity and the guarantee liability is an attribute, provided that the elderly are too mild and are 65 years old, and the insurance fund is an attribute.
The web page data acquisition unit 102 is configured to acquire web page data from web pages respectively corresponding to a preset data acquisition website set to obtain a web page data set and acquire a sub-web page data set corresponding to each data acquisition website in the web page data set if a difference between current data acquisition time and previous data acquisition time is equal to a preset data acquisition period; wherein each subnet page data set comprises a plurality of event data.
In this embodiment, the server acquires web page data from the web pages corresponding to the preset data acquisition website sets at regular intervals. For example, the preset data acquisition website may be a hot search page of a microblog or an equative portal website, and a hot event in the current time period can be accurately obtained in the hot search page. More specifically, the technical scheme of the application is described by taking a hot search page of a microblog as one of data acquisition websites of a data acquisition website set as an example.
For example, the hot search events corresponding to the microblog at the current data acquisition time include the following 3 events: 1. XXX1 was frayed on the thighs in a game of participating in YY 1; 2. XXX2 is held a wedding today with YY2 in the markov; 3. XXX3 was successful in developing YY 3; and forming a sub-web page data set corresponding to the data acquisition website of the microblog by the texts corresponding to the 3 hot search events. And collecting webpage data from the webpages respectively corresponding to the plurality of data collection website sets to form a webpage data set.
And the entity extraction unit 103 is used for extracting through keywords to obtain an entity name set corresponding to each event data.
In this embodiment, after acquiring the sub-web data set corresponding to each data acquisition website, each sub-web data set includes a plurality of event data, for example, the data acquisition website corresponding to the microblog in the above example, the 3 texts corresponding to the hot search events form the sub-web data set, where the text corresponding to each hot search event corresponds to one event data.
The event data is usually in the form of short titles and web page hyperlinks, i.e. the short title of the click event data is directly jumped to the news information corresponding to the short title.
In one embodiment, the entity extraction unit 103 includes:
a news information obtaining unit for obtaining an event title and an event news information text corresponding to event data to form an event text corresponding to the event data;
the keyword extraction unit is used for obtaining a keyword set corresponding to the event text by sequentially performing word segmentation and keyword acquisition on the event text;
and the entity name set acquisition unit is used for deleting the keywords which do not exist in the entity name set of the knowledge map library in the keyword set to obtain the entity name set corresponding to the event data.
In this embodiment, when the server needs to obtain the news information text of a certain event data, a click action is generated to trigger skipping of the news information corresponding to the short title. For example, if the server simulates that the thigh strain occurs during the game of YY1 after clicking the hot search event 1-XXX 1, the server jumps to the news information corresponding to the hot search event 1, and the event text is composed of the event title and the event news information text.
When the keywords are extracted from the event text, performing word segmentation on the event text through a probability statistics based word segmentation model to obtain a word segmentation result corresponding to the event text; and extracting the keywords of which the word segmentation results do not exceed a preset ranking threshold value after descending sorting according to the frequency-inverse text frequency indexes through a word frequency-inverse text frequency index model to form a keyword set.
The keywords in the keyword set extracted by the hot search event 1 may be the entity names of the sub-knowledge maps in the knowledge map library, or may not be the entity names of the sub-knowledge maps in the knowledge map library, and the keywords in the keyword set are compared with the entity names in the knowledge map library one by one, so that the keywords which do not exist in the entity name set in the knowledge map library can be judged, and the keywords which do not exist in the entity name set in the knowledge map library in the keyword set are deleted, so that the entity name set corresponding to the event data is obtained.
After the above-mentioned keyword screening process, the following two situations may occur: firstly, all keywords in the keyword set do not exist in the entity name set of the knowledge map library, and the entity name set corresponding to the event data is obtained as an empty set; and secondly, only part of the keywords in the keyword set do not exist in the entity name set of the knowledge map library, and the entity name set corresponding to the event data is obtained as a non-empty set at the moment.
The target event data obtaining unit 104 is configured to, if an entity name set corresponding to event data is a non-empty set, obtain corresponding target event data and a target entity name set corresponding to the target event data.
In this embodiment, if an entity name set corresponding to event data is a non-empty set, which indicates that the content corresponding to the event data is the content concerned by the server, then to further analyze the event data, a target entity name set corresponding to the event data needs to be obtained.
An approximate entity obtaining unit 105, configured to, if the target entity name set includes a first type entity name, obtain, in a pre-constructed knowledge graph library, an approximate entity name set corresponding to the first type entity name.
In this embodiment, if the target entity name set includes a first type entity name (for example, one of the corresponding entity names in the above-mentioned thermal search event 1 is a thigh pull, and the thigh pull belongs to the first type entity name), then the first type entity name is used to obtain an approximate entity name set corresponding to the first type entity name from a plurality of entity names corresponding to the knowledge map library.
In one embodiment, the approximate entity obtaining unit 105 includes:
the dictionary word forest acquisition unit is used for acquiring an entity name library and a synonym dictionary corresponding to the knowledge map library and acquiring a word forest corresponding to the synonym dictionary;
and the approximate entity name set acquisition unit is used for acquiring the approximate entity names corresponding to the first type entity names in the entity name library according to the word forest so as to form an approximate entity name set.
In the present embodiment, a synonym dictionary for determining the similarity between words is stored in the server. All words included in the synonym are organized in one or more tree structures (the tree or a plurality of books are marked as a word forest), nodes corresponding to two words of which the word similarity needs to be judged are found in the word forest, and the path lengths of the two nodes can be used as the semantic distance (also can be understood as the word similarity) between the two words. In order to limit that only a few approximate entity names appear in the approximate entity name set, entity names which need to be corresponding to the first type entity names and whose word similarity exceeds a preset word similarity threshold value can be limited, and thus a final obtained approximate entity name set can be formed. For example, the physical names similar to the strain injury of the thigh are flexor tendon injury and hand tendon injury, and the flexor tendon injury and the hand tendon injury form an approximate physical name set corresponding to the strain injury of the thigh.
The first recommendation data generating unit 106 is configured to generate a target event knowledge graph corresponding to the target event data according to a pre-constructed ontology and knowledge representation of the target event data, so as to serve as the first type of data to be recommended.
In this embodiment, in order to more simply display the target event data, but not simply display the target event data only through an event title, a target event knowledge graph corresponding to the target event data may be extracted at this time, so as to simply display an event.
In an embodiment, the first recommendation data generating unit 106 is further configured to:
and extracting an entity-attribute-constraint-value format ontology from the target event data according to the ontology and the knowledge representation to obtain first-type data to be recommended.
Specifically, when the target event knowledge graph corresponding to the target event data is generated, the pre-constructed ontology and the ontology in the format of 'entity-attribute-constraint-value' are extracted from the knowledge representation, so that the first type of data to be recommended is obtained.
The second recommendation data generating unit 107 is configured to acquire the first target knowledge graph corresponding to the first type entity name, acquire the approximate entity target knowledge graph corresponding to each approximate entity name in the approximate entity name set, and form second type data to be recommended by using the first target knowledge graph and the approximate entity target knowledge graph corresponding to each approximate entity name.
In this embodiment, in addition to simply showing the target event data by using the target event knowledge graph, a plurality of similar entity names most similar to the concerned first type entity name may be obtained from the knowledge graph library to form a similar entity name set, and the topic content formed by the sub-knowledge graphs corresponding to the similar entity names in the similar entity name set and the knowledge graphs corresponding to the concerned entity names is pushed to the user side for viewing. For example, the entity name similar to the strain injury of the thigh includes a flexor tendon injury and a hand tendon injury, a sub-knowledge map corresponding to the entity name of the flexor tendon injury and a sub-knowledge map corresponding to the entity name of the hand tendon injury are obtained, and therefore the second type of data to be recommended are formed by the first target knowledge map, and therefore a special content can be formed and pushed to a user side for viewing.
A third recommended data generating unit 108, configured to acquire a current target entity name and a current target sub-knowledge graph corresponding to the first type entity name as the condition keyword in the first target knowledge graph, so as to serve as third type data to be recommended.
In this embodiment, since the ontology in the format of "entity-attribute-constraint-value" is used in the knowledge graph library, the first type entity name can be used as a condition keyword for a certain product entity in addition to the entity name, as described in the above example, "product a-insurance responsibility-insurance-mild disease &65 years old-age-value". At this time, the current target entity name and the current target sub-knowledge map corresponding to the first type entity name as the condition keyword in the first target knowledge map can be obtained to be used as the third type data to be recommended, so that targeted recommendation of insurance products based on a certain pain type is realized, data matching is more accurate, and the matching process is more efficient due to automatic realization.
And the information data to be recommended generating unit 109 is configured to fill the first type of data to be recommended, the second type of data to be recommended, and the third type of data to be recommended into a data container, so as to obtain information data to be recommended corresponding to the event data.
In this embodiment, since the first type of data to be recommended, the second type of data to be recommended, and the third type of data to be recommended are obtained before, these pieces of information may be regarded as recommendation sub-information sets, and if the pieces of information are pushed to the user side in scattered content, it is inconvenient for the user to view these recommendation sub-information sets. In order to further integrate the concentrated recommendation sub-information sets into a concentrated area, the recommendation sub-information sets may be filled into a called data container, and the recommendation sub-information sets are loaded by using the data container as a carrier. Therefore, when the data container loaded with the content data is sent to the user side, the user can open the data container to view the data pushed by the server in a centralized mode.
In an embodiment, the information data to be recommended generating unit 109 includes:
the card container creating unit is used for creating a blank card container with empty data in advance;
the number counting unit is used for acquiring the total number of recommendation sub-information included in the first type of data to be recommended, the second type of data to be recommended and the third type of data to be recommended;
the card area dividing unit is used for creating sub card areas with the same number as the total number in the blank card container;
and the data filling unit is used for filling one piece of recommendation sub-information in each sub-chip area to obtain information data to be recommended.
In this embodiment, for better aggregating the content data, the card container may be selected as a carrier to load the recommendation sub-information set. A card may be understood as a component on a UI interface provided by a server, which may be used as a container to conveniently display contents composed of different data elements (such as text). Creating a blank card container, then counting the total number of recommendation sub-information included in the first type of data to be recommended, the second type of data to be recommended and the third type of data to be recommended, wherein the total number determines how many sub-card areas the blank card container is divided into, and finally filling each sub-card area with one recommendation sub-information to obtain the current card. Through the current card, the user can view the information data to be recommended in a centralized manner without acquiring knowledge through a search engine.
In an embodiment, the information data to be recommended generating unit 109 further includes:
and the buried point setting unit is used for correspondingly increasing buried points in each sub-chip area.
In this embodiment, the buried points are correspondingly added in each sub-chip region, so that user behavior data of a user for the content in each sub-chip region, such as the opening times, the reading duration and the like, can be effectively collected, and the user behavior data can be used as a basis for recommending other information data to the user again in the following.
The device realizes that the information data to be recommended is quickly acquired based on the hot event and is sent to the user side in the information card mode, the screened content is more accurate, the content can be intensively and visually checked after being loaded through the card container, and a search engine is not needed to retrieve related knowledge.
The information pushing apparatus based on the hot spot event may be implemented in the form of a computer program, and the computer program may be run on a computer device as shown in fig. 4.
Referring to fig. 4, fig. 4 is a schematic block diagram of a computer device according to an embodiment of the present invention. The computer device 500 is a server, and the server may be an independent server or a server cluster composed of a plurality of servers.
Referring to fig. 4, the computer device 500 includes a processor 502, memory, and a network interface 505 connected by a system bus 501, where the memory may include a non-volatile storage medium 503 and an internal memory 504.
The non-volatile storage medium 503 may store an operating system 5031 and a computer program 5032. The computer program 5032, when executed, may cause the processor 502 to perform a hotspot event based information push method.
The processor 502 is used to provide computing and control capabilities that support the operation of the overall computer device 500.
The internal memory 504 provides an environment for the operation of the computer program 5032 in the non-volatile storage medium 503, and when the computer program 5032 is executed by the processor 502, the processor 502 may be enabled to execute the information push method based on the hot event.
The network interface 505 is used for network communication, such as providing transmission of data information. Those skilled in the art will appreciate that the configuration shown in fig. 4 is a block diagram of only a portion of the configuration associated with aspects of the present invention and is not intended to limit the computing device 500 to which aspects of the present invention may be applied, and that a particular computing device 500 may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
The processor 502 is configured to run the computer program 5032 stored in the memory to implement the information push method based on the hot spot event disclosed in the embodiment of the present invention.
Those skilled in the art will appreciate that the embodiment of a computer device illustrated in fig. 4 does not constitute a limitation on the specific construction of the computer device, and that in other embodiments a computer device may include more or fewer components than those illustrated, or some components may be combined, or a different arrangement of components. For example, in some embodiments, the computer device may only include a memory and a processor, and in such embodiments, the structures and functions of the memory and the processor are consistent with those of the embodiment shown in fig. 4, and are not described herein again.
It should be understood that, in the embodiment of the present invention, the Processor 502 may be a Central Processing Unit (CPU), and the Processor 502 may also be other general purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Wherein a general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
In another embodiment of the invention, a computer-readable storage medium is provided. The computer readable storage medium may be a non-volatile computer readable storage medium. The computer readable storage medium stores a computer program, wherein the computer program, when executed by a processor, implements the information push method based on the hotspot event disclosed by the embodiment of the invention.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described apparatuses, devices and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again. Those of ordinary skill in the art will appreciate that the elements and algorithm steps of the examples described in connection with the embodiments disclosed herein may be embodied in electronic hardware, computer software, or combinations of both, and that the components and steps of the examples have been described in a functional general in the foregoing description for the purpose of illustrating clearly the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the embodiments provided by the present invention, it should be understood that the disclosed apparatus, device and method can be implemented in other ways. For example, the above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only a logical division, and there may be other divisions when the actual implementation is performed, or units having the same function may be grouped into one unit, for example, a plurality of units or components may be combined or may be integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may also be an electric, mechanical or other form of connection.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment of the present invention.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a storage medium. Based on such understanding, the technical solution of the present invention essentially or partially contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a magnetic disk, or an optical disk.
While the invention has been described with reference to specific embodiments, the invention is not limited thereto, and various equivalent modifications and substitutions can be easily made by those skilled in the art within the technical scope of the invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. An information pushing method based on a hotspot event is characterized by comprising the following steps:
if the difference between the current data acquisition time and the previous data acquisition time is equal to a preset data acquisition period, acquiring web page data from web pages respectively corresponding to a preset data acquisition website set to obtain a web page data set, and acquiring a sub-web page data set corresponding to each data acquisition website in the web page data set; each subnet page data set comprises a plurality of event data;
extracting through keywords to obtain an entity name set corresponding to each event data;
if an entity name set corresponding to event data is a non-empty set, acquiring corresponding target event data and a target entity name set corresponding to the target event data;
if the target entity name set comprises a first type entity name, acquiring an approximate entity name set corresponding to the first type entity name from a pre-constructed knowledge map library;
generating a target event knowledge graph corresponding to the target event data according to a pre-constructed body and knowledge representation of the target event data to serve as first type data to be recommended;
acquiring a first target knowledge graph corresponding to the first type entity name, acquiring an approximate entity target knowledge graph corresponding to each approximate entity name in the approximate entity name set, and forming second type data to be recommended by the first target knowledge graph and the approximate entity target knowledge graph corresponding to each approximate entity name;
acquiring a current target entity name and a current target sub-knowledge graph corresponding to the first type entity name serving as the condition keyword in the first target knowledge graph to serve as third type data to be recommended; and
and filling the first type of data to be recommended, the second type of data to be recommended and the third type of data to be recommended into a data container to obtain information data to be recommended corresponding to the event data.
2. The information pushing method based on the hotspot event according to claim 1, further comprising:
constructing a knowledge map library according to the acquired data source; the knowledge graph library comprises a plurality of sub knowledge graphs, each sub knowledge graph comprises a plurality of entities with association relations, and the sub knowledge graphs are associated through the association relations among the entities.
3. The method according to claim 1, wherein the extracting by keyword to obtain the entity name set corresponding to each event data includes:
acquiring an event title and an event news information text corresponding to event data to form an event text corresponding to the event data;
obtaining a keyword set corresponding to the event text by sequentially performing word segmentation and keyword acquisition on the event text;
and deleting the keywords which do not exist in the entity name set of the knowledge map library in the keyword set to obtain the entity name set corresponding to the event data.
4. The information pushing method based on the hotspot event according to claim 1, wherein the obtaining of the approximate entity name set corresponding to the first type entity name from the pre-constructed knowledge map library comprises:
acquiring an entity name library and a synonym dictionary corresponding to a knowledge map library, and acquiring a word forest corresponding to the synonym dictionary;
and acquiring approximate entity names corresponding to the first type entity names in the entity name library according to the word forest to form an approximate entity name set.
5. The information pushing method based on the hotspot event according to claim 1, wherein the generating a target event knowledge graph corresponding to the target event data according to a pre-constructed ontology and knowledge representation to serve as first type data to be recommended includes:
and extracting an entity-attribute-constraint-value format ontology from the target event data according to the ontology and the knowledge representation to obtain first-type data to be recommended.
6. The information pushing method based on the hotspot event according to claim 1, wherein the filling the first type of data to be recommended, the second type of data to be recommended, and the third type of data to be recommended into a data container to obtain information data to be recommended corresponding to the event data includes:
a blank card container with empty data is created in advance;
acquiring the total number of recommendation sub-information included in the first type of data to be recommended, the second type of data to be recommended and the third type of data to be recommended;
creating sub-card areas with the same number as the total number in the blank card container;
and filling one recommendation sub-information in each sub-chip area to obtain information data to be recommended.
7. The information pushing method based on the hotspot event according to claim 6, wherein before the step of filling one piece of recommendation sub-information in each sub-chip area to obtain the information data to be recommended, the method further comprises:
and correspondingly increasing buried points in each sub-chip area.
8. An information pushing device based on a hotspot event is characterized by comprising:
the webpage data acquisition unit is used for acquiring webpage data from webpages respectively corresponding to a preset data acquisition website set to obtain a webpage data set and acquiring a sub-webpage data set corresponding to each data acquisition website in the webpage data set if the difference between the current data acquisition time and the previous data acquisition time is equal to a preset data acquisition period; each subnet page data set comprises a plurality of event data;
the entity extraction unit is used for extracting the keywords to obtain an entity name set corresponding to each event data;
the target event data acquisition unit is used for acquiring corresponding target event data and a target entity name set corresponding to the target event data if the entity name set corresponding to the event data is a non-empty set;
an approximate entity obtaining unit, configured to obtain, if the target entity name set includes a first type entity name, an approximate entity name set corresponding to the first type entity name from a pre-constructed knowledge map library;
the first recommendation data generation unit is used for generating a target event knowledge graph corresponding to the target event data according to a pre-constructed body and knowledge representation of the target event data to serve as first type data to be recommended;
the second recommendation data generation unit is used for acquiring a first target knowledge map corresponding to the first type entity name, acquiring an approximate entity target knowledge map corresponding to each approximate entity name in the approximate entity name set, and forming second type data to be recommended by the first target knowledge map and the approximate entity target knowledge maps corresponding to the approximate entity names;
a third recommendation data generation unit, configured to acquire a current target entity name and a current target sub-knowledge graph corresponding to the first type entity name as the condition keyword in the first target knowledge graph, and use the current target entity name and the current target sub-knowledge graph as third type data to be recommended; and
and the information data to be recommended generating unit is used for filling the first type of data to be recommended, the second type of data to be recommended and the third type of data to be recommended into a data container so as to obtain information data to be recommended corresponding to the event data.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the information push method based on the hotspot event according to any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program, which when executed by a processor causes the processor to execute the information push method based on a hotspot event according to any one of claims 1 to 7.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110308396.6A CN113032578B (en) | 2021-03-23 | 2021-03-23 | Information pushing method and device based on hotspot event and computer equipment |
| PCT/CN2021/091504 WO2022198756A1 (en) | 2021-03-23 | 2021-04-30 | Information pushing method and apparatus based on hot event, computer device, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110308396.6A CN113032578B (en) | 2021-03-23 | 2021-03-23 | Information pushing method and device based on hotspot event and computer equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113032578A true CN113032578A (en) | 2021-06-25 |
| CN113032578B CN113032578B (en) | 2022-12-06 |
Family
ID=76472850
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110308396.6A Active CN113032578B (en) | 2021-03-23 | 2021-03-23 | Information pushing method and device based on hotspot event and computer equipment |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN113032578B (en) |
| WO (1) | WO2022198756A1 (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117494811B (en) * | 2023-11-20 | 2024-05-28 | 南京大经中医药信息技术有限公司 | Knowledge graph construction method and system for Chinese medicine books |
| CN117743564B (en) * | 2024-01-30 | 2024-05-10 | 广东省华南技术转移中心有限公司 | Automatic extraction and recommendation method and system for technological policy information |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103440286A (en) * | 2013-08-14 | 2013-12-11 | 北京百度网讯科技有限公司 | Method and system for providing recommended information on the basis of search results |
| CN105430455A (en) * | 2015-01-23 | 2016-03-23 | Tcl集团股份有限公司 | Information presentation method and system |
| CN105868377A (en) * | 2016-03-31 | 2016-08-17 | 北京奇艺世纪科技有限公司 | Method and device for pushing information |
| CN106570144A (en) * | 2016-02-05 | 2017-04-19 | 中科鼎富（北京）科技发展有限公司 | Method and apparatus for recommending information |
| US20170220607A1 (en) * | 2010-06-22 | 2017-08-03 | Primal Fusion Inc. | Methods and devices for customizing knowledge representation systems |
| CN109325132A (en) * | 2018-12-11 | 2019-02-12 | 平安科技（深圳）有限公司 | Expertise recommended method, device, computer equipment and storage medium |
| CN109508381A (en) * | 2018-09-29 | 2019-03-22 | 北京国双科技有限公司 | The processing method and processing device of knowledge mapping |
| CN110196947A (en) * | 2019-05-31 | 2019-09-03 | 三角兽（北京）科技有限公司 | Method, apparatus, electronic equipment and the storage medium that recommendation information determines |
| CN110321482A (en) * | 2019-06-11 | 2019-10-11 | 阿里巴巴集团控股有限公司 | A kind of recommended method of information, device and equipment |
| CN112084383A (en) * | 2020-09-07 | 2020-12-15 | 中国平安财产保险股份有限公司 | Information recommendation method, device and equipment based on knowledge graph and storage medium |
| CN112199478A (en) * | 2020-09-11 | 2021-01-08 | 北京三快在线科技有限公司 | Automatic question answering method, device, electronic equipment and computer readable storage medium |
| CN112307339A (en) * | 2020-10-30 | 2021-02-02 | 中国平安人寿保险股份有限公司 | User portrait based recommendation information generation method and device and computer equipment |
| CN112328813A (en) * | 2020-10-30 | 2021-02-05 | 中国平安人寿保险股份有限公司 | Recommendation information generation method and device based on AI and computer equipment |
| CN112463980A (en) * | 2020-11-25 | 2021-03-09 | 南京摄星智能科技有限公司 | Intelligent plan recommendation method based on knowledge graph |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103955465A (en) * | 2014-03-28 | 2014-07-30 | 百度在线网络技术（北京）有限公司 | Method and device for generating recommended page |
| CN111930949B (en) * | 2020-09-11 | 2021-01-15 | 腾讯科技（深圳）有限公司 | Search string processing method and device, computer readable medium and electronic equipment |
-
2021
- 2021-03-23 CN CN202110308396.6A patent/CN113032578B/en active Active
- 2021-04-30 WO PCT/CN2021/091504 patent/WO2022198756A1/en active Application Filing
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170220607A1 (en) * | 2010-06-22 | 2017-08-03 | Primal Fusion Inc. | Methods and devices for customizing knowledge representation systems |
| CN103440286A (en) * | 2013-08-14 | 2013-12-11 | 北京百度网讯科技有限公司 | Method and system for providing recommended information on the basis of search results |
| CN105430455A (en) * | 2015-01-23 | 2016-03-23 | Tcl集团股份有限公司 | Information presentation method and system |
| CN106570144A (en) * | 2016-02-05 | 2017-04-19 | 中科鼎富（北京）科技发展有限公司 | Method and apparatus for recommending information |
| CN105868377A (en) * | 2016-03-31 | 2016-08-17 | 北京奇艺世纪科技有限公司 | Method and device for pushing information |
| CN109508381A (en) * | 2018-09-29 | 2019-03-22 | 北京国双科技有限公司 | The processing method and processing device of knowledge mapping |
| CN109325132A (en) * | 2018-12-11 | 2019-02-12 | 平安科技（深圳）有限公司 | Expertise recommended method, device, computer equipment and storage medium |
| CN110196947A (en) * | 2019-05-31 | 2019-09-03 | 三角兽（北京）科技有限公司 | Method, apparatus, electronic equipment and the storage medium that recommendation information determines |
| CN110321482A (en) * | 2019-06-11 | 2019-10-11 | 阿里巴巴集团控股有限公司 | A kind of recommended method of information, device and equipment |
| CN112084383A (en) * | 2020-09-07 | 2020-12-15 | 中国平安财产保险股份有限公司 | Information recommendation method, device and equipment based on knowledge graph and storage medium |
| CN112199478A (en) * | 2020-09-11 | 2021-01-08 | 北京三快在线科技有限公司 | Automatic question answering method, device, electronic equipment and computer readable storage medium |
| CN112307339A (en) * | 2020-10-30 | 2021-02-02 | 中国平安人寿保险股份有限公司 | User portrait based recommendation information generation method and device and computer equipment |
| CN112328813A (en) * | 2020-10-30 | 2021-02-05 | 中国平安人寿保险股份有限公司 | Recommendation information generation method and device based on AI and computer equipment |
| CN112463980A (en) * | 2020-11-25 | 2021-03-09 | 南京摄星智能科技有限公司 | Intelligent plan recommendation method based on knowledge graph |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2022198756A1 (en) | 2022-09-29 |
| CN113032578B (en) | 2022-12-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11567979B2 (en) | Automatically assessing structured data for decision making | |
| US20190370243A1 (en) | Ram daemons | |
| US7676507B2 (en) | Methods and systems for searching and associating information resources such as web pages | |
| CN102831214B (en) | time series search engine | |
| KR101775883B1 (en) | Method and system for processing information of a stream of information | |
| US20080228695A1 (en) | Techniques for analyzing and presenting information in an event-based data aggregation system | |
| US20110087647A1 (en) | System and method for providing web search results to a particular computer user based on the popularity of the search results with other computer users | |
| US20140081928A1 (en) | Skill extraction system | |
| US10430448B2 (en) | Computer-implemented method of and system for searching an inverted index having a plurality of posting lists | |
| US20120041937A1 (en) | Nlp-based sentiment analysis | |
| CN113032578B (en) | Information pushing method and device based on hotspot event and computer equipment | |
| US9442986B2 (en) | Ranking of heterogeneous information objects | |
| US20190332972A1 (en) | Dynamic query response with metadata | |
| US20180046628A1 (en) | Ranking social media content | |
| Albrecht et al. | Blueprints for text analytics using Python | |
| Wolfram | Search characteristics in different types of Web-based IR environments: Are they the same? | |
| CN111447575B (en) | Short message pushing method, device, equipment and storage medium | |
| CN112328857B (en) | Product knowledge aggregation method and device, computer equipment and storage medium | |
| JP2010044462A (en) | Content evaluation server, content evaluation method and content evaluation program | |
| Kosa et al. | Cross-evaluation of automated term extraction tools | |
| CN115203565A (en) | Cold start method and device of recommendation system, electronic equipment and storage medium | |
| Dolma et al. | Improving bounce rate prediction for rare queries by leveraging landing page signals | |
| JP2006277061A (en) | Knowledge retrieval system, method and program | |
| Li et al. | Discovering associations between news and contents in social network sites with the D-Miner service framework | |
| Donig et al. | Web archive analytics: Blind spots and silences in distant readings of the archived web |
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 |