CN111125372A - Text information publishing method and device, readable storage medium and electronic equipment - Google Patents
Text information publishing method and device, readable storage medium and electronic equipment Download PDFInfo
- Publication number
- CN111125372A CN111125372A CN201911289019.1A CN201911289019A CN111125372A CN 111125372 A CN111125372 A CN 111125372A CN 201911289019 A CN201911289019 A CN 201911289019A CN 111125372 A CN111125372 A CN 111125372A
- Authority
- CN
- China
- Prior art keywords
- information
- node
- data
- determining
- attribute data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
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
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/338—Presentation of query results
-
- 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
- G06F16/38—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Library & Information Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention discloses a text information publishing method, a text information publishing device, a readable storage medium and electronic equipment.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a text information publishing method, a text information publishing device, a readable storage medium and electronic equipment.
Background
With the rapid development of the internet, more and more channels are available for people to acquire information, the amount of the acquired information is larger and larger, and the information acquisition speed is higher and higher. Therefore, in the internet environment with great variety of information, it is a problem for newscasts in various fields to acquire field information in which readers are interested in a short time and produce corresponding news according to the field information. At present, the conventional method is to manually screen, sort and edit the current information to generate corresponding news. The method needs to consume a large amount of labor cost for generating the news, the timeliness is often not met, and meanwhile, the quantity of the information acquired manually is limited, so that the richness of the news content is not enough.
Disclosure of Invention
In view of this, the embodiment of the present invention discloses a text information publishing method, device, readable storage medium and electronic device, which aim to automatically generate text information corresponding to each node quickly and timely, and simultaneously ensure real-time performance and richness of text information content.
In a first aspect, an embodiment of the present invention discloses a text information publishing method, where the method includes:
determining a knowledge graph, wherein the knowledge graph comprises a plurality of nodes for representing concept information;
acquiring at least one current attribute data corresponding to each node from a preset data source;
acquiring historical attribute data corresponding to each node;
determining the data characteristics of each node according to the historical attribute data and the current attribute data corresponding to each node;
acquiring at least one piece of related information from a preset information source, wherein each piece of related information comprises at least one piece of entity information corresponding to the concept information;
identifying entity information in each piece of relevant information to determine the corresponding relation between each piece of relevant information and each node;
automatically generating a text to be issued according to the relevant information and the data characteristics corresponding to each node in the knowledge graph;
and publishing the text to be published.
Further, the determining the knowledge-graph comprises:
determining a plurality of nodes for characterizing conceptual information;
determining the corresponding relation among the concept information;
and connecting every two nodes corresponding to the concept information with the corresponding relationship.
Further, the acquiring at least one current attribute data corresponding to each node from a preset data source includes:
acquiring data information corresponding to each node from a preset data source;
and extracting current attribute data from the data information.
Further, the determining the data characteristics of each node according to the historical attribute data and the current attribute data corresponding to each node includes:
determining a characteristic value for characterizing a difference between the historical attribute data and the current attribute data;
and determining the data characteristics corresponding to the nodes according to the characteristic values and preset rules.
Further, the acquiring at least one related information from a predetermined information source includes:
acquiring a plurality of information from a preset information source;
and screening the information to obtain related information.
Further, the identifying the entity information in the related information to determine the corresponding relationship between the related information and the nodes includes:
identifying entity information included in the related information:
and determining the nodes corresponding to the related information according to the concept information corresponding to each entity information.
Further, the generating of the text to be published according to the transaction information and the data characteristics corresponding to each node in the knowledge graph specifically includes:
and inputting the transaction information and the data characteristics corresponding to each node into a preset template to obtain a corresponding text to be issued.
In a second aspect, an embodiment of the present invention discloses a text information publishing device, where the device includes:
the knowledge graph determining module is used for determining a knowledge graph, and the knowledge graph comprises a plurality of nodes for representing concept information;
the current data determining module is used for acquiring at least one current attribute data corresponding to each node from a preset data source;
the historical data determining module is used for acquiring historical attribute data corresponding to each node;
the characteristic determining module is used for determining the data characteristics of each node according to the historical attribute data and the current attribute data corresponding to each node;
the information acquisition module is used for acquiring at least one piece of related information from a preset information source, wherein each piece of related information comprises at least one piece of entity information corresponding to the concept information;
the entity identification module is used for identifying entity information in the related information to determine the corresponding relation between the related information and each node;
the text generation module is used for automatically generating a text to be issued according to the relevant information and the data characteristics corresponding to each node in the knowledge graph;
and the text publishing module is used for publishing the text to be published.
In a third aspect, an embodiment of the present invention discloses a computer-readable storage medium for storing computer program instructions, which when executed by a processor implement the method according to any one of the first aspect.
In a fourth aspect, an embodiment of the present invention discloses an electronic device, including a memory and a processor, the memory being configured to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement the method according to any one of the first aspect.
According to the embodiment of the invention, the data characteristics and the related information corresponding to each node in the knowledge map are obtained by determining the knowledge map, and finally the corresponding text information to be published is generated and published based on the data characteristics and the related information corresponding to each node, so that the text information corresponding to each node can be automatically generated quickly and timely, and the real-time property and the richness of the text information content can be ensured.
Drawings
The above and other objects, features and advantages of the present invention will become more apparent from the following description of the embodiments of the present invention with reference to the accompanying drawings, in which:
fig. 1 is a flowchart of a text message publishing method according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of knowledge-graph generation according to an embodiment of the present invention;
fig. 3 is a schematic diagram of a text message publishing method according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a text message publishing device according to an embodiment of the present invention;
fig. 5 is a schematic diagram of an electronic device according to an embodiment of the invention.
Detailed Description
The present invention will be described below based on examples, but the present invention is not limited to only these examples. In the following detailed description of the present invention, certain specific details are set forth. It will be apparent to one skilled in the art that the present invention may be practiced without these specific details. Well-known methods, procedures, components and circuits have not been described in detail so as not to obscure the present invention.
Further, those of ordinary skill in the art will appreciate that the drawings provided herein are for illustrative purposes and are not necessarily drawn to scale.
Unless the context clearly requires otherwise, throughout the description, the words "comprise", "comprising", and the like are to be construed in an inclusive sense as opposed to an exclusive or exhaustive sense; that is, what is meant is "including, but not limited to".
In the description of the present invention, it is to be understood that the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. In addition, in the description of the present invention, "a plurality" means two or more unless otherwise specified.
Fig. 1 is a flowchart of a text information publishing method according to an embodiment of the present invention, and as shown in fig. 1, the text information publishing method includes:
and step S100, determining a knowledge graph.
Specifically, the knowledge graph comprises a plurality of nodes for representing concept information. The knowledge graph is preset in the server, or the knowledge graph is generated through a knowledge graph generating instruction sent by the client side through the server, and the knowledge graph generating instruction comprises at least one concept information.
Therefore, the process of determining the knowledge graph through the method for automatically generating the knowledge graph by the server may include:
and step S110, determining a plurality of nodes for representing the concept information.
Specifically, the server receives a knowledge graph generation instruction sent by a client, analyzes the content of the knowledge graph generation instruction to obtain at least one piece of concept information, and determines each piece of concept information as a node in the knowledge graph. Wherein the concept information is used for characterizing basic concepts of a certain field. For example, in the financial field, the conceptual information may be foreign exchange, trust, fund, stock, benchmark interest rate, loan rate, and the like.
And step S120, determining the corresponding relation among the concept information.
Specifically, the correspondence between the concept information may include a causal relationship, an inference relationship, and the like. The corresponding relationship may also be sent by the client, that is, the knowledge graph generation instruction sent by the client further includes the corresponding relationship of each concept information. And the server determines the corresponding relation among the concept information in the process of analyzing the knowledge graph generation instruction. The correspondence between the conceptual information may be determined by the server by setting a correspondence rule in advance. Still in the financial field, for example, adjustment of the baseline interest rate may affect fluctuations in the loan rate. Therefore, an inference relationship between the reference interest rate and the borrowing rate may be set in the server in advance, and when the concept information determined through step S110 includes the reference interest rate and the borrowing rate, a correspondence relationship between the reference interest rate and the borrowing rate is determined.
Further, the corresponding relationship of each concept information may also be determined by inputting every two concept information determined in step S110 into the trained relevance model. For example, every two pieces of concept information are used as the input of the relevance model, a relevance value between 0 and 1 is used as the output of the relevance model, when the output relevance value is greater than a preset relevance threshold value, it is determined that there is a correspondence between the two pieces of input concept information, and when the output relevance value is less than the preset relevance threshold value, it is determined that there is no correspondence between the two pieces of input concept information.
And S130, connecting every two nodes corresponding to the concept information with the corresponding relationship.
Specifically, after the corresponding relationship of each concept information is determined through step S120, the corresponding knowledge graph is finally determined through the connection relationship between each node and each node by connecting the nodes corresponding to each two characterized concept information together. Optionally, one node in the knowledge-graph may be connected to one or more nodes, and may also be unconnected to other nodes. Further, the knowledge graph can be further edited by expanding, modifying, deleting and the like after being generated.
Fig. 2 is a schematic diagram of a knowledge graph generation process according to an embodiment of the present invention, and as shown in fig. 2, the process of generating the knowledge graph needs to determine a plurality of nodes 20, then determine a correspondence between the nodes, and finally connect every two nodes corresponding to the represented concept information together to obtain a knowledge graph 21. The knowledge graph 21 can be sent to a client for display through a server after being generated, and the server can also perform operations such as adding, deleting, modifying and the like on nodes in the knowledge graph according to a modification instruction sent by the client.
Step S200, at least one current attribute data corresponding to each node is obtained from a preset data source.
Specifically, the preset data source may be preset as required, and includes official data release related to the industry, a statistical website, and the like. For example, in the financial field, the predetermined data source may be a chinese foreign exchange trading center, a chinese futures market monitoring center, or the like.
In this embodiment, the acquiring current attribute data corresponding to each node includes:
step S210, obtaining data information corresponding to each node from a preset data source.
Specifically, the preset data source includes a plurality of data information corresponding to each node. The preset data source is taken as an example of a Chinese foreign exchange trading center for explanation, and the obtained data information comprises various data information such as Renminbi exchange rate intermediate price, loan market quotation interest rate, Renminbi exchange rate index, USD borrowing weighted interest rate, Renminbi foreign exchange remote quotation and the like. Wherein, the data information includes data information corresponding to at least one of the nodes, for example, the dollar is decomposed into weighted interest rate and node: the borrowing rate corresponds to; the loan market quote interest rate and node: quoted rate corresponds, etc. Meanwhile, the acquired data information may further include content that has no correspondence with each node.
And step S220, extracting the current attribute data from the data information.
Specifically, the process of acquiring the current attribute data may be periodic acquisition or real-time acquisition. In the process of acquiring the current attribute data, since the data information data sources corresponding to the nodes acquired in step S210 are different, and the formats of the data information are different, the formats of the data information need to be processed to convert the data information into recognizable information. For example, when the obtained data information is presented in the form of an HTML table, the HTML table is subjected to structure analysis to determine the information contained in the table. When the acquired data information is presented in the form of a picture, OCR recognition may be performed on the picture to determine information included in the picture.
Further, each piece of data information further includes at least one piece of attribute data and generation time of each piece of attribute data, and by comparing the generation time of each piece of attribute data with the current time, the server may determine the current attribute data, for example, may determine the attribute data closest to the current time as the current attribute data. For example, when the data information corresponding to the node a includes the generation time of the attribute data 1 of 3 pm on 11 th month in 2019, and the generation time of the attribute data 2 of 3 pm on 12 th month in 11 th month in 2019. And the server determines that the current time is 4 pm on 11/12/2019, and then determines the attribute data 2 as the current attribute data.
And step S300, acquiring historical attribute data corresponding to each node.
Specifically, as an optional implementation manner of this embodiment, the method for acquiring historical attribute data corresponding to each node may be that when the current attribute data is determined in step S220, historical attribute data is simultaneously determined in data information corresponding to each node, for example, attribute data whose generation time is before the generation time of the current attribute data is determined as historical attribute data. For example, when the data information corresponding to the node a includes the generation time of the attribute data 1 of 3 pm on 11 th month in 2019, and the generation time of the attribute data 2 of 3 pm on 12 th month in 11 th month in 2019. The server determines that the current time is 4 pm on 11/12/2019, and then determines the attribute data 1 as the history attribute data.
As another optional implementation manner of this embodiment, the current attribute data acquired at the historical time of each node may also be used as the current historical attribute data. For example, when determining attribute data in a cycle of days, the server determines that the current attribute data determined by node a at 3 pm on 11 th month 11 in 2019 is attribute data 1, and the current attribute data determined at 3 pm on 12 th month 11 in 2019 is attribute data 2, and then determines that the attribute data 1 is history attribute data at 3 pm on 12 th month 11 in 2019. Optionally, the historical attribute data is current attribute data of a previous cycle, or all current attribute data determined in a period of time before the current time.
And S400, determining the data characteristics of each node according to the historical attribute data and the current attribute data corresponding to each node.
In particular, the data characteristics may be used to characterize data fluctuation of the nodes currently or over a period of time.
In this embodiment, the determining the data characteristics of each node includes:
and step S500, determining a characteristic value for representing the difference between the historical attribute data and the current attribute data.
Specifically, after the current attribute data and the historical attribute data corresponding to each node are determined through steps S200 and S300, the current attribute data and the historical attribute data are structurally stored, and the difference between the current attribute data and the historical attribute data is determined by calculating a feature value. The characteristic value can be, for example, a same-ratio growth rate, a ring-ratio growth rate, or the like, which is used for characterizing the current data fluctuation situation. Optionally, the feature value may also be obtained by inputting the current attribute data and the historical attribute data into a trained feature model, and outputting a corresponding feature value.
And step S510, determining the data characteristics corresponding to the nodes according to the characteristic values and preset rules.
Specifically, the server sets a preset rule in advance to determine the corresponding relationship between the characteristic value and a data characteristic, where the data characteristic may be, for example, a word used for characterizing the fluctuation condition and degree of data, such as slow, sharp, abrupt drop, and sharp increase. When the characteristic value is a numerical value, data characteristics corresponding to numerical values in different ranges can be set. For example, when the characteristic value is 0 to 1, 0 to 0.33 may be set to correspond to a slow speed, 0.33 to 0.67 to correspond to a sharp speed, and 0.67 to 1 to correspond to a sharp speed. When the characteristic value is-1-1, 0-0.33 and-0.33-0 are set to correspond to slow, 0.33-0.67 and-0.33- (-0.67) to correspond to rapid, 0.67- (-1) to correspond to abrupt decrease, and 0.67-1 to correspond to rapid increase. Therefore, after the feature value corresponding to each node is determined according to step S500, the data feature corresponding to each node can be obtained.
Step S500, at least one related information is obtained from a predetermined information source.
Specifically, the preset information source may be an official information publishing platform, an industry media forum, an industry expert blog and the like in the corresponding field of the knowledge graph.
In this embodiment, the process of acquiring the related information may include:
step S510, obtaining a plurality of information from a predetermined information source.
Specifically, the server acquires a plurality of information messages from an information source according to a preset period, wherein the information messages comprise all or part of information generated from the last acquisition period of the information source to the current time. For example, for the financial industry, the obtained information includes duration information, transaction information, policy information, commentator comments, and information such as policy news, social information or blogs published by industry experts about other irrelevant contents in information sources that are irrelevant to the financial industry.
Step S520, the information is filtered to obtain the related information.
Specifically, after information is obtained from a plurality of preset information sources through step S510, the relevant information may be filtered to obtain relevant information related to each node in the knowledge graph. The screening process may be, for example, screening by keywords, that is, constructing a keyword lexicon in advance, determining that the information is related information when the server can retrieve keywords included in the keyword lexicon from the information, and determining that the information is non-related information when the server does not retrieve keywords included in the keyword lexicon from the information. Furthermore, the screening of the information can also output the correlation degree of the information by inputting each information into a trained correlation model. And when the correlation degree is greater than a correlation threshold value, determining the information as the related information.
Step S600, identifying entity information in each relevant information to determine the corresponding relation between each information and each node.
Specifically, each related information message includes at least one entity message corresponding to the concept message.
In this embodiment, the process of determining the corresponding relationship between the information and the node includes:
step S610, identify the entity information included in the related information.
Specifically, the entity information is used to characterize conceptual information of an entity. For example, for the financial industry, the entity information may be exchange rate, closing price, weighted interest rate, etc. Each of the related information messages may include one or more entity messages corresponding to concept messages. Therefore, the server identifies the content of each related information message to obtain one or more entity messages corresponding to the concept message, and the identification method can be, for example, entity message identification through a keyword corresponding to the entity message.
Step S620, determining a node corresponding to the related information according to the concept information corresponding to each entity information.
Specifically, after identifying each piece of related information to obtain corresponding entity information through step S610, it is necessary to further determine the corresponding relationship between each piece of entity information and the concept information. In this embodiment, the corresponding relationship between the related information and the concept information may be preset. The corresponding relation can be that the entity information is the same as and related to the concept information characterized by the node, wherein the related relation comprises reasoning relation and causal relation. Therefore, every time the server identifies entity information corresponding to the concept information, the server establishes a corresponding relation with the nodes representing the concept information. Through the steps, the corresponding relation between each piece of relevant information and at least one node in the knowledge graph can be determined. For example, concept information a may correspond to entity information a, entity information B, and entity information C, concept information B may correspond to entity information d, entity information e, and concept information C may correspond to entity information f. When a piece of related information includes entity information a, entity information b, and entity information f, the server may determine that the related information is related to concept information a and concept information C, and finally determine that a node corresponding to the related information is a node for representing the concept information a and the concept information C.
Step S700, automatically generating a text to be published according to the relevant information and the data characteristics corresponding to each node in the knowledge graph.
Specifically, after the knowledge graph, the data characteristics and the related information corresponding to each node in the knowledge graph are determined through the steps S100 to S600, the server inputs the related information and the data characteristics corresponding to each node into a preset template to automatically generate a corresponding text to be published. For example, for the financial field, when one node in the knowledge graph is the interest rate, the corresponding data characteristic is the surge, and the related information is the interest rate related information, then the trading market news related to the interest rate surge is correspondingly generated.
And S800, releasing the text to be released.
Specifically, after automatically generating the text to be published in step S700, the server automatically publishes the text to be published, or publishes the text to be published after receiving a publishing instruction sent by the client.
The method of the embodiment of the invention obtains the data characteristics and the related information corresponding to each node in the knowledge map by determining the knowledge map, generates and releases the corresponding text information to be released based on the data characteristics and the related information corresponding to each node, can quickly and timely automatically generate the text information corresponding to each node, and can simultaneously ensure the real-time property and the richness of the text information content.
Fig. 3 is a schematic diagram of a text information publishing method according to an embodiment of the present invention, and as shown in fig. 3, the method firstly determines a preset information source 30 and a data source 30 'through a server, and respectively obtains information 31 from the information source according to a preset period, and obtains current attribute data 31' corresponding to a knowledge graph node in the server from the data source in real time. The server then screens the acquired information to obtain related information 32, and determines historical attribute information 32 'corresponding to each node, and processes the related information and the current attribute data respectively to obtain entity information included in each related information, nodes 33 corresponding to each entity information, and current data characteristics 33' of each node. After determining the entity information and the current data characteristics corresponding to each node, judging whether a causal event exists between the data characteristics and the entity information corresponding to each node, wherein the process can be judged through a preset causal event rule. And when the causal event 34' exists between the data characteristic and the entity information, determining related information comprising the entity information, and when the causal event 34 does not exist between the data characteristic and the entity information, determining the same related information as the corresponding node of the data information. After the data characteristics and the related information are determined through the above process, the information 35 corresponding to the data characteristics and the related information, such as tables, pictures, abstracts, comments, and the like, is summarized, the information is input into a preset template to automatically generate a text to be published, and finally, the text to be published is automatically published through a server 36.
The method can automatically generate the text information corresponding to each node quickly and timely, and meanwhile, the content of the generated text information is more accurate by establishing a causal relationship between the data characteristics and the entity information.
Fig. 4 is a schematic diagram of a text information publishing device according to an embodiment of the present invention, and as shown in fig. 4, the device includes a knowledge graph determining module 40, a current data determining module 41, a historical data determining module 42, a feature determining module 43, an information obtaining module 44, an entity identifying module 45, a text generating module 46, and a text publishing module 47.
Specifically, the knowledge graph determining module 40 is configured to determine a knowledge graph, where the knowledge graph includes a plurality of nodes for representing concept information. The current data determining module 41 is configured to obtain at least one current attribute data corresponding to each node from a preset data source. The historical data determining module 42 is configured to obtain historical attribute data corresponding to each node. The characteristic determining module 43 is configured to determine the data characteristics of each node according to the historical attribute data and the current attribute data corresponding to each node. The information obtaining module 44 is configured to obtain at least one piece of related information from a preset information source, where each piece of related information includes at least one piece of entity information having a corresponding relationship with the concept information. The entity identification module 45 is configured to identify entity information in the related information to determine a corresponding relationship between the related information and each node. The text generating module 46 is configured to automatically generate a text to be published according to the relevant information and the data features corresponding to each node in the knowledge graph. The text publishing module 47 is configured to publish the text to be published.
The device of the embodiment of the invention can acquire the data characteristics and the related information corresponding to each node in the knowledge map by determining the knowledge map, generate and release the corresponding text information to be released based on the data characteristics and the related information corresponding to each node, can quickly and timely automatically generate the text information corresponding to each node, and can ensure the real-time property and the richness of the text information content.
Fig. 5 is a schematic view of an electronic device according to an embodiment of the present invention, as shown in fig. 5, in this embodiment, the electronic device may be a server or a terminal, and the terminal may be, for example, an intelligent device such as a mobile phone, a computer, a tablet computer, and the like. As shown, the electronic device includes: at least one processor 51; a memory 50 communicatively coupled to the at least one processor; and a communication component 52 communicatively coupled to the storage medium, the communication component 52 receiving and transmitting data under control of the processor; the memory 50 stores instructions executable by the at least one processor 51, and the instructions are executed by the at least one processor 51 to implement the text message issuing method according to the embodiment of the present invention.
In particular, the memory 50, as a non-volatile computer-readable storage medium, may be used to store non-volatile software programs, non-volatile computer-executable programs, and modules. The processor 51 executes various functional applications and data processing of the device by running nonvolatile software programs, instructions, and modules stored in the memory, that is, implements the above-described text information distribution method.
The memory 50 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store a list of options, etc. Further, the memory 50 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some embodiments, the memory 50 may optionally include memory located remotely from the processor 51, which may be connected to an external device via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
One or more modules are stored in the memory 50 and, when executed by the one or more processors 51, perform the text information distribution method of any of the above-described method embodiments.
The product can execute the method disclosed in the embodiment of the present application, and has corresponding functional modules and beneficial effects of the execution method, and reference may be made to the method disclosed in the embodiment of the present application without detailed technical details in the embodiment.
The present invention also relates to a computer-readable storage medium for storing a computer-readable program for causing a computer to perform some or all of the above-described method embodiments.
That is, as can be understood by those skilled in the art, all or part of the steps in the method for implementing the embodiments described above may be implemented by a program instructing related hardware, where the program is stored in a storage medium and includes several instructions to enable a device (which may be a single chip, a chip, or the like) or a processor (processor) to execute all or part of the steps of the method described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A text message publishing method, the method comprising:
determining a knowledge graph, wherein the knowledge graph comprises a plurality of nodes for representing concept information;
acquiring at least one current attribute data corresponding to each node from a preset data source;
acquiring historical attribute data corresponding to each node;
determining the data characteristics of each node according to the historical attribute data and the current attribute data corresponding to each node;
acquiring at least one piece of related information from a preset information source, wherein each piece of related information comprises at least one piece of entity information corresponding to the concept information;
identifying entity information in each piece of relevant information to determine the corresponding relation between each piece of relevant information and each node;
automatically generating a text to be issued according to the relevant information and the data characteristics corresponding to each node in the knowledge graph;
and publishing the text to be published.
2. The method of claim 1, wherein determining the knowledge-graph comprises:
determining a plurality of nodes for characterizing conceptual information;
determining the corresponding relation among the concept information;
and connecting every two nodes corresponding to the concept information with the corresponding relationship.
3. The method according to claim 1, wherein the obtaining at least one current attribute data corresponding to each node from a preset data source comprises:
acquiring data information corresponding to each node from a preset data source;
and extracting current attribute data from the data information.
4. The method of claim 1, wherein determining the data characteristics of each node according to the historical attribute data and the current attribute data corresponding to each node comprises:
determining a characteristic value for characterizing a difference between the historical attribute data and the current attribute data;
and determining the data characteristics corresponding to the nodes according to the characteristic values and preset rules.
5. The method of claim 1, wherein the obtaining at least one related information from a predetermined information source comprises:
acquiring a plurality of information from a preset information source;
and screening the information to obtain related information.
6. The method of claim 1, wherein the identifying entity information in the related information messages to determine the corresponding relationship between the related information messages and the nodes comprises:
identifying entity information included in the related information:
and determining the nodes corresponding to the related information according to the concept information corresponding to each entity information.
7. The method according to claim 1, wherein the generating of the text to be published according to the transaction information and the data characteristics corresponding to the nodes in the knowledge graph specifically comprises:
and inputting the transaction information and the data characteristics corresponding to each node into a preset template to obtain a corresponding text to be issued.
8. A text information distribution apparatus, characterized in that the apparatus comprises:
the knowledge graph determining module is used for determining a knowledge graph, and the knowledge graph comprises a plurality of nodes for representing concept information;
the current data determining module is used for acquiring at least one current attribute data corresponding to each node from a preset data source;
the historical data determining module is used for acquiring historical attribute data corresponding to each node;
the characteristic determining module is used for determining the data characteristics of each node according to the historical attribute data and the current attribute data corresponding to each node;
the information acquisition module is used for acquiring at least one piece of related information from a preset information source, wherein each piece of related information comprises at least one piece of entity information corresponding to the concept information;
the entity identification module is used for identifying entity information in the related information to determine the corresponding relation between the related information and each node;
the text generation module is used for automatically generating a text to be issued according to the relevant information and the data characteristics corresponding to each node in the knowledge graph;
and the text publishing module is used for publishing the text to be published.
9. A computer readable storage medium storing computer program instructions which, when executed by a processor, implement the method of any one of claims 1-7.
10. An electronic device comprising a memory and a processor, wherein the memory is configured to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement the method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911289019.1A CN111125372A (en) | 2019-12-12 | 2019-12-12 | Text information publishing method and device, readable storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911289019.1A CN111125372A (en) | 2019-12-12 | 2019-12-12 | Text information publishing method and device, readable storage medium and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111125372A true CN111125372A (en) | 2020-05-08 |
Family
ID=70498890
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911289019.1A Pending CN111125372A (en) | 2019-12-12 | 2019-12-12 | Text information publishing method and device, readable storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111125372A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090164387A1 (en) * | 2007-04-17 | 2009-06-25 | Semandex Networks Inc. | Systems and methods for providing semantically enhanced financial 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 |
| CN107895056A (en) * | 2017-12-29 | 2018-04-10 | 百度在线网络技术（北京）有限公司 | A kind of information recommendation method, device, electronic equipment and storage medium |
| CN109284342A (en) * | 2018-11-22 | 2019-01-29 | 北京百度网讯科技有限公司 | Method and apparatus for output information |
| CN110134842A (en) * | 2019-04-03 | 2019-08-16 | 深圳价值在线信息科技股份有限公司 | Information matching method, device, storage medium and server based on Information Atlas |
| CN110222127A (en) * | 2019-06-06 | 2019-09-10 | 中国电子科技集团公司第二十八研究所 | The converging information method, apparatus and equipment of knowledge based map |
| CN110442700A (en) * | 2019-08-12 | 2019-11-12 | 珠海格力电器股份有限公司 | Man-machine multi-turn conversation method and system for man-machine interaction and intelligent equipment |
-
2019
- 2019-12-12 CN CN201911289019.1A patent/CN111125372A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090164387A1 (en) * | 2007-04-17 | 2009-06-25 | Semandex Networks Inc. | Systems and methods for providing semantically enhanced financial 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 |
| CN107895056A (en) * | 2017-12-29 | 2018-04-10 | 百度在线网络技术（北京）有限公司 | A kind of information recommendation method, device, electronic equipment and storage medium |
| CN109284342A (en) * | 2018-11-22 | 2019-01-29 | 北京百度网讯科技有限公司 | Method and apparatus for output information |
| CN110134842A (en) * | 2019-04-03 | 2019-08-16 | 深圳价值在线信息科技股份有限公司 | Information matching method, device, storage medium and server based on Information Atlas |
| CN110222127A (en) * | 2019-06-06 | 2019-09-10 | 中国电子科技集团公司第二十八研究所 | The converging information method, apparatus and equipment of knowledge based map |
| CN110442700A (en) * | 2019-08-12 | 2019-11-12 | 珠海格力电器股份有限公司 | Man-machine multi-turn conversation method and system for man-machine interaction and intelligent equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110352425B (en) | Cognitive regulatory compliance automation for blockchain transactions | |
| CN109344170B (en) | Stream data processing method, system, electronic device and readable storage medium | |
| WO2020037917A1 (en) | User behavior data recommendation method, server and computer readable medium | |
| CN111680165B (en) | Information matching method and device, readable storage medium and electronic equipment | |
| CN112153426B (en) | Content account management method and device, computer equipment and storage medium | |
| CN110458324B (en) | Method and device for calculating risk probability and computer equipment | |
| CN112231533A (en) | Data processing method, device, equipment and storage medium | |
| JP5848199B2 (en) | Impact prediction device, impact prediction method, and program | |
| CN111369344B (en) | Method and device for dynamically generating early warning rules | |
| CN112184302A (en) | Product recommendation method and device, rule engine and storage medium | |
| JP2011227721A (en) | Interest extraction device, interest extraction method, and interest extraction program | |
| CN112148946A (en) | Microblog-based analysis and view display method and system | |
| CN110245684B (en) | Data processing method, electronic device, and medium | |
| CN112818234B (en) | Network public opinion information analysis processing method and system | |
| CN117216393A (en) | Information recommendation method, training method and device of information recommendation model and equipment | |
| CN117291722A (en) | Object management method, related device and computer readable medium | |
| CN111125372A (en) | Text information publishing method and device, readable storage medium and electronic equipment | |
| CN113343133B (en) | Display page generation method, related device and computer program product | |
| JP2018198044A (en) | Apparatus and method for generating multiple-event pattern query | |
| CN114925275A (en) | Product recommendation method and device, computer equipment and storage medium | |
| CN113961811A (en) | Conversational recommendation method, device, equipment and medium based on event map | |
| CN113674023A (en) | Rights upgrading method, device, equipment and storage medium based on member level | |
| EP3956774A1 (en) | Company size estimation system | |
| DE102015008607B4 (en) | Adapting network requirements to client requirements in digital networks | |
| JP2011227720A (en) | Recommendation system, recommendation method and recommendation program |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200508 |