CN112100506B - Information pushing method, system, equipment and storage medium - Google Patents
Information pushing method, system, equipment and storage medium Download PDFInfo
- Publication number
- CN112100506B CN112100506B CN202011242725.3A CN202011242725A CN112100506B CN 112100506 B CN112100506 B CN 112100506B CN 202011242725 A CN202011242725 A CN 202011242725A CN 112100506 B CN112100506 B CN 112100506B
- Authority
- CN
- China
- Prior art keywords
- equipment
- information
- search
- data
- pushing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—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
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
- G06F16/288—Entity relationship models
-
- 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
- G06F16/9532—Query formulation
-
- 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
- G06F16/9538—Presentation of query results
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/55—Push-based network services
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention belongs to the field of information processing, and discloses an information pushing method, an information pushing system, information pushing equipment and a storage medium, wherein the information pushing method comprises the following steps: acquiring search information; obtaining search equipment according to the search information and preset equipment figures of each equipment; and acquiring and pushing the equipment information of the search equipment. The mode of portrait for every equipment is based on the equipment, fully excavate the attribute of equipment itself, and then adopt the mode of equipment portrait to search for and recommend, accurate understanding user's intention, satisfy many specialty multiusers more high-efficient, more nimble, more accurate information acquisition demand, solve present dispatch control system's the quick expansion of service scale, the regulation and control business in data kind numerous, the information overload problem that the storage dispersion leads to, the realization uses the equipment as the accurate information propelling movement of the multi-dimensional data of main part.
Description
Technical Field
The invention belongs to the field of information processing, and relates to an information pushing method, an information pushing system, information pushing equipment and a storage medium.
Background
The informatization of the power industry is from the automation of power production in the 60 th of the 20 th century, to the management informatization construction in the 80 th of the century and to the comprehensive construction of an intelligent power grid in recent years, the data of a power system is rapidly increased, and various data sources, platforms, types, cross-industry data and the like form various and scattered power big data. With the deep popularization of the construction of the intelligent power grid dispatching control system and the wide construction of the intelligent transformer substation, data in a power grid system is in an explosive growth trend, the power regulation and control field is in the big data era, the problem of information overload is also avoided, and how to enable a user to obtain information wanted by the user in the presence of massive data is not only the embodiment of information intelligence, but also the service quality of the industry can be improved, so that related services continuously and healthily conform to the development of the era. Search and recommendation techniques are two main technical means to solve the above problems. However, the current search engine can only meet a part of requirements of people, and can not meet the query requests of different people, different times and the same query term and different query intentions.
At present, generally, personalized retrieval services are provided for different users by combining a personalized recommendation technology and a search technology, for example, patent CN108038237A discloses an information recommendation method and system, which obtains inherent attributes and behavior attributes of users; carrying out statistical analysis processing on the inherent attribute and the behavior attribute, and mining user interest; analyzing and mining the behavior attributes, and mining the reading habits and consumption concepts of the users; mining a user portrait and behavior habits of a user according to the inherent attribute, the behavior attribute, the user interest, the reading habits and the consumption concept; and calling a preset information recommendation model to acquire recommendation information according to the behavior habit of the user portrait, and pushing the recommendation to the user. The personalized recommendation technology mainly builds user portrait, wherein the user portrait refers to the situation that labels of users on different attributes, such as age, sex, occupation, income, interest and the like, are mined and extracted from various data generated by the users, and complete and accurate attribute labels can effectively reveal the essential characteristics of the users, so that accurate personalized recommendation is greatly promoted. The general flow of the mainstream user portrait recommendation method is data source end data collection, data preprocessing, behavior modeling, user portrait construction and relevancy scoring based on user portrait modification search results.
Although, the current user portrayal method has achieved good results and is widely applied to the actual search recommendation system. However, in the professional field, the behavior data tags of the users have similar dimensions, and the user intentions cannot be accurately understood through the user tags, so that effective searching and recommending cannot be performed.
Disclosure of Invention
The invention aims to overcome the defects that in the prior art, the behavior data labels of users have similar dimensions and the intention of the users cannot be accurately understood through the user labels, so that effective searching and recommending cannot be performed, and provides an information pushing method, an information pushing system, an information pushing device and a readable storage medium.
In order to achieve the purpose, the invention adopts the following technical scheme to realize the purpose:
in a first aspect of the present invention, an information push method includes the following steps:
acquiring search information; obtaining search equipment according to the search information and preset equipment figures of each equipment; and acquiring and pushing the equipment information of the search equipment.
The information pushing method of the invention is further improved in that:
the specific method for obtaining the search equipment according to the search information and the preset equipment portrait of each equipment comprises the following steps:
acquiring a keyword in the search information, and comparing the keyword in the search information with preset equipment portrait of each equipment to obtain the similarity between the search information and the equipment portrait of each equipment; and selecting the equipment corresponding to the equipment image with the maximum similarity as searching equipment.
The specific method for obtaining the search equipment according to the search information and the preset equipment portrait of each equipment comprises the following steps:
acquiring a keyword in the search information, and comparing the keyword in the search information with preset equipment portrait of each equipment to obtain the similarity between the search information and the equipment portrait of each equipment; arranging equipment corresponding to a plurality of large equipment images before the similarity according to the size of the similarity; and acquiring selection information, and selecting search equipment from the equipment corresponding to the large equipment images with the similarity according to the selection information.
The device representation is constructed by:
acquiring equipment information of equipment; extracting the equipment characteristics of the equipment based on the equipment information, and obtaining the label of the equipment according to the equipment characteristics; and integrating the labels of the equipment to obtain the equipment picture.
The specific method for obtaining the label of the equipment according to the equipment characteristics comprises the following steps:
presetting a plurality of label rules and labels corresponding to the label rules; traversing a plurality of label rules, and when the equipment characteristics meet the label rules, the equipment contains the labels corresponding to the current label rules.
The specific method for obtaining the label of the equipment according to the equipment characteristics comprises the following steps:
presetting a plurality of label rules and labels corresponding to the label rules; selecting sample equipment, traversing a plurality of label rules according to the equipment characteristics of the sample equipment, and when the equipment characteristics of the sample equipment meet the label rules, enabling the sample equipment to contain a label corresponding to the current label rules; and establishing a corresponding relation between the equipment characteristics and the label according to the equipment characteristics of the sample equipment and the label of the sample equipment, and obtaining the label of the equipment according to the equipment characteristics based on the corresponding relation.
The device representation includes at least one of an individual representation, a classified group representation, a corporate representation, and a custom community representation.
Further comprising: and acquiring and pushing the device portrait and/or the associated information of the search device.
The specific method for acquiring and pushing the equipment information of the search equipment and acquiring and pushing the equipment portrait and/or the associated information of the search equipment comprises the following steps:
based on the search equipment, obtaining equipment information and associated information of the search equipment through a preset data relation network, and pushing the equipment information of the search equipment and the equipment portrait and/or the associated information; the data relation network takes the equipment and the equipment portrait as main bodies, and the equipment information and the associated information of the equipment are constructed in an attached mode.
The data relation network is constructed in the following way:
according to the equipment information and the associated information of the equipment in the pushing range, constructing a plurality of ontology classes and determining the relationship among the ontology classes to obtain an ontology library; and mapping each device and the device portrait of each device into an ontology library one by one through ontology mapping, and using the device information and the associated information as the attachment of the devices to obtain a data relation network.
The specific method of ontology mapping comprises: one or more of mapping by a preset rule, mapping by similarity calculation and mapping by naive Bayes classification.
The data relation network is constructed in a data relation graph mode, equipment and an equipment portrait are taken as main nodes in the data relation graph, and equipment information and associated information of the equipment are taken as dependent nodes; and the data relation network is stored in a mode of a graph database.
The specific method for pushing the equipment information of the search equipment and the equipment portrait and/or the associated information of the search equipment comprises the following steps:
and pushing the equipment information and the associated information of the search equipment according to the arrangement sequence of the equipment information in front and the equipment portrait and/or the associated information in back, wherein all information in the associated information is pushed according to the arrangement sequence of preset weights from large to small.
Further comprising: and acquiring and pushing micro application information corresponding to the information contained in the equipment information of the search equipment according to the micro application information of each piece of information in the preset equipment information.
Further comprising: acquiring nearest neighbor equipment of the search equipment, and pushing equipment information and associated information of the nearest neighbor equipment; wherein, the nearest neighbor device is a plurality of big devices before the similarity with the searching device.
In a second aspect of the present invention, an information push system includes:
the information acquisition module is used for acquiring search information; the searching module is used for obtaining searching equipment according to the searching information and preset equipment figures of each equipment; and the pushing module is used for acquiring and pushing the equipment information of the search equipment.
The information pushing system of the invention is further improved in that:
the pushing module is further used for acquiring and pushing the device portrait and/or the associated information of the searching device.
Further comprising: and the micro-application pushing module is used for acquiring and pushing micro-application information corresponding to the information contained in the equipment information of the search equipment according to the micro-application information of each piece of information in the preset equipment information.
Further comprising: the nearest neighbor pushing module is used for acquiring the nearest neighbor of the searching device and pushing the device information and the associated information of the nearest neighbor; wherein, the nearest neighbor device is a plurality of big devices before the similarity with the searching device.
In a third aspect of the present invention, a terminal device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the information pushing method when executing the computer program.
In a fourth aspect of the present invention, a computer-readable storage medium stores a computer program, and the computer program realizes the steps of the information pushing method when executed by a processor.
Compared with the prior art, the invention has the following beneficial effects:
according to the information pushing method, the searching equipment corresponding to the searching information is obtained by obtaining the searching information and combining the preset equipment images of all the equipment, and the equipment information and the searching equipment information are further pushed. Compared with the existing searching and recommending mode based on user portrait, due to the fact that the behavior data labels of the users are close in dimensionality, the intention of the users cannot be accurately understood through the user labels, effective searching and recommending cannot be conducted, portrait is conducted on each device through the mode of user portrait borrowing for reference, the attributes of the devices are fully mined, searching and recommending are conducted in the mode of device portrait, the intention of the users can be accurately understood, the requirements of multiple professions and multiple users on more efficient, more flexible and more accurate information acquisition are met, and the method is quite suitable for searching and recommending in the professional field.
Furthermore, effective information is mined from the equipment information of the equipment portrait to form a semantic label, a search engine does not need to analyze and store operation data, internal space is released, and search efficiency is improved.
Furthermore, the equipment portrait and/or the associated information of the search equipment are obtained and pushed, and the equipment information, the equipment portrait and the associated information are stored in the same database through a data relation network, so that cross-database query is not needed for data, and query efficiency is improved.
Furthermore, the data relation network is constructed in a data relation graph mode, the data relation network is stored in a graph database mode, data are visually stored in a graph mode, and compared with a traditional relational data storage mode, the speed and accuracy of searching and recommending functional data query in a search engine are improved.
Drawings
Fig. 1 is a schematic diagram illustrating an implementation principle of an information push method according to an embodiment of the present invention;
fig. 2 is a flow chart of an information pushing method according to an embodiment of the present invention;
FIG. 3 is a flow diagram of an apparatus representation implementation in accordance with an embodiment of the present invention;
FIG. 4 is a block diagram of an apparatus representation construction method according to an embodiment of the present invention;
FIG. 5 is a block diagram of a data relationship network construction method according to an embodiment of the present invention;
FIG. 6 is a diagram illustrating an example of ontology mapping according to an embodiment of the present invention;
FIG. 7 is a data relationship diagram of an embodiment of the present invention;
FIG. 8 is a block diagram illustrating an exemplary method for pushing information according to an embodiment of the present invention;
fig. 9 is a block diagram of an information push system according to an embodiment of the invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, 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 only a part of the embodiments of the present invention, and not all of the embodiments. 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 should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
The invention is described in further detail below with reference to the accompanying drawings:
referring to fig. 1, an implementation principle of each embodiment of the present invention is shown, and specifically, the implementation principle of an information push method mainly includes three parts, namely, data collection analysis, data preprocessing, and search recommendation; the data collection analysis can adopt the existing data collection analysis method, data preprocessing is supported by means of a data collection technology, an equipment portrait is constructed by extracting equipment characteristics, a data relation network with equipment as a main body is established, and the equipment portrait and the equipment are stored in the data relation network in a one-to-one correspondence mode; and optimizing a searching and recommending method by using a data relation network and a relation evaluation system to form equipment information searching and associated information recommending, and finally realizing accurate information pushing of multi-dimensional data with equipment as a main body.
Next, the implementation principle described above is applied to the technical field of power automation, and specifically, the implementation in a power system is taken as an example for explanation.
Referring to fig. 2, an information pushing method provided in an embodiment of the present invention is shown, where the information pushing method is implemented based on the principle described in fig. 1, and in this embodiment, an electric power device is taken as an example for description, but not limited thereto, and specifically, the information pushing method includes the following steps:
s1: and acquiring search information.
In this embodiment, after the search information is obtained, the search information is preprocessed, for example, long search information is divided into a plurality of search keywords according to a word segmentation algorithm, and the search is performed by using the search keywords as a search reference, so as to obtain the search device. Such as: the search information is 'thermal power equipment in the power grid of the Shijiazhuang', and the keywords are obtained by word segmentation: "Shijiazhuang", "power grid", and "thermal power plant", and further search and recommendation are performed with these keywords.
S2: and obtaining the searching equipment according to the searching information and preset equipment figures of each equipment.
Specifically, in this embodiment, the keyword in the search information is obtained, the keyword in the search information is compared with the preset device portrait of each device, the similarity between the search information and the device portrait of each device is obtained, and the device corresponding to the device portrait with the largest similarity is selected as the search device.
Wherein the device representation is a representation of the device in a manner that references the user representation and characterizes the device with the device representation. Specifically, the construction of the device portrait is realized by gradually determining the device attribute, the device characteristic and the device label, and the overall process is divided into three blocks: obtaining and researching equipment information, establishing an equipment label and developing an equipment picture. The device information corresponds to the device attributes in the three elements, and the process of converting the device information into the device label is actually the flow of device feature extraction.
In this embodiment, referring to fig. 3, a flow framework for implementing an equipment portrait is provided, referring to fig. 4, the following equipment portrait construction method is implemented based on the framework, and includes the following steps:
s201: device information of a device is acquired.
Specifically, in the field of regulation and control of business, data can be summarized into static data and dynamic data. The static data comprises equipment data, scheduling rules, power failure diagnosis, decision and the like; the dynamic data is the business data such as electricity quantity, measurement, events and the like generated in the production process, namely the operation data, and the static data is freely filled by a user and can be lost or even forged, so that the use of the information is not considered temporarily.
In this embodiment, taking the power device as an example for description, the data types of the device information participating in the portrait of the power device are mainly classified into eight types, that is, basic information, measurement data, electric quantity data, alarm data, environment data, event data, plan data, prediction data, and other information, where the other information mainly refers to data combined with other platforms or external data. The basic information describes basic characteristics of the equipment, including ID, name, operation state, region of the equipment, and the like, and these attributes can reflect the basic characteristics and categories of the equipment. Data information such as measurement data, electric quantity data alarm data, environment data, event data, plan data and forecast data is used as operation data, and mainly refers to operation records of equipment in an operation period, including use time, use times, use duration and the like.
S202: and extracting the equipment characteristics of the equipment based on the equipment information, and obtaining the label of the equipment according to the equipment characteristics. Specifically, a plurality of label rules and labels corresponding to the label rules are preset, then the label rules are traversed, and when the equipment characteristics meet the label rules, the equipment comprises the labels corresponding to the current label rules.
Based on this, in this embodiment, a tag definition system is constructed, and the device tag is determined by the tag definition system. Specifically, the label definition system comprises a complete cycle management support function of the label and a label library for storing the label. The period management support function comprises primary definition, analysis verification and optimization updating, and the full life period management of label definition, generation and maintenance is realized. The label library consists of a label rule library and a label definition library, wherein the label rule library stores label rules for generating labels, and for example, an active or reactive meter of a generator indicates that a rated value is exceeded, the generator is provided with an overload label; the label definition library stores generated labels, for example, the object class of the 'power grid' includes the class of the 'innovation high' label, and the entity object of the 'Beijing power grid' has the 'innovation high' label of power generation and power reception.
In the embodiment, an automatic label labeling mode is further provided, a sample device is selected, a plurality of label rules are traversed according to the device characteristics of the sample device, and when the device characteristics of the sample device meet the label rules, the sample device contains a label corresponding to the current label rules; and establishing a corresponding relation between the equipment characteristics and the label according to the equipment characteristics of the sample equipment and the label of the sample equipment, and obtaining the label of the equipment according to the equipment characteristics based on the corresponding relation.
Specifically, the process of determining the tags included in the device through the tag definition system is as follows: firstly, selecting some or one device as a sample device according to expert experience or business requirements, analyzing basic information and operation data of the sample device, such as data information of a device model, device operation, analysis prediction and the like, mining and extracting data labels, establishing a label rule base of label objects of a power grid regulation object, a platform service, a regulation business file, base table attributes and the like, wherein the label rule base defines rules for generating labels, including taking data from which table of which database, calculating by using what formula or algorithm, for how long a calculation period is (day dimension, year dimension, static label and the like), then performing rapid classification identification and accurate abstract feature extraction of mass operation data through data analysis methods such as visual facts, statistical processing, model mining and combination definition and the like, such as a K-means clustering algorithm, a support vector machine classification algorithm, an FP-growth correlation analysis algorithm and the like, the method and the device realize the establishment and management of the data category information labels of the power equipment and determine the labels contained in the sample equipment. Then, on the basis of the existing label, combining with the expert experience of regulation and control service and the service characteristics, extracting the operating data characteristic and the label characteristic, establishing the corresponding relation between the equipment characteristic and the label by utilizing the clustering and classification mining technology, constructing a data classifier, training the data classifier to update the parameters of the data classifier, and finally realizing the association between the equipment characteristic and the label based on the data classifier, and further automatically determining the label contained in each equipment after obtaining the equipment characteristic based on the basis.
S203: and integrating the equipment label of the equipment to obtain the equipment picture.
In this embodiment, all tags of the device are combined to obtain a device representation of the device, where the representation is an abstracted tagged model of the device. For example, the device image of a certain device can be described by a Beijing grid, a thermal power plant, a thermal power device and a thermal power generator.
The device portrait comprises at least one of an individual portrait, a classified group portrait, an overall portrait and a self-defined group portrait, the portrait can be understood as a set of labels, different types of device portraits can be obtained when the environments for feature extraction are different, for example, on the basis of a label definition system of the device portrait at the initial stage, one or more labels are selected as input of portrait calculation according to expert experience and business requirements, a target label is obtained by combination, the label weight is marked by considering factors such as a business scene, and the like, and the device with similar labels is aggregated through a TF-IDF, a correlation coefficient matrix and other weight classification algorithms, machine learning clustering and classification algorithms, so that the target label represents the group portrait of the device of the category. For example, the labels of 'overload', 'high temperature' and 'high humidity' of the generator are counted, and a 'summer high-risk' equipment group figure can be obtained. Based on the selection of the device objects and tags, an individual representation, a categorized group representation, an ensemble representation, and a custom group representation categorization are ultimately formed.
It should be noted that the individual portraits, the categorized group portraits, the ensemble portraits and the custom group portraits are used to categorize the device portraits for ease of management and the same process of forming the device portraits.
Based on the equipment portrait construction method, the equipment portrait of each equipment is constructed by acquiring the equipment information of each equipment in the push range.
Preferably, in this embodiment, when obtaining the search device according to the search information and the preset device images of each device, there may also be a relevant recommendation, for example, obtaining a keyword in the search information, comparing the keyword in the search information with the preset device images of each device to obtain a similarity between the search information and the device images of each device, at this time, sequentially arranging devices corresponding to a plurality of previous device images according to the size of the similarity, then obtaining selection information, and selecting from the devices corresponding to a plurality of previous device images according to the selection information to obtain the search device, where the selection information may be determined and input by an operator according to a sorting result, and thus, the accuracy of subsequent pushing is further ensured.
S3: and acquiring and pushing the sum equipment information of the search equipment. Preferably, the device portrait and/or the associated information of the search device can be acquired and pushed, and in practical application, the device information and the associated information of each device can be stored together with the device portrait, so that the device information and the associated information of the search device can be directly acquired after the search device is obtained, and then pushing is realized.
Specifically, in this embodiment, a data relationship network is provided for storing device information and associated information of each device, where the data relationship network uses the device as a main component, and the device information and the associated information of the device are constructed in an attached manner. Based on the data relationship network, the specific method for acquiring and pushing the device information and the associated information of the search device comprises the following steps: and based on the search equipment, obtaining the equipment information and the associated information of the search equipment through a preset data relation network, and pushing the equipment information and the associated information of the search equipment. Referring to fig. 5, a data relationship network construction method is provided, which includes the following steps:
s301: and according to the equipment information and the associated information of the equipment in the pushing range, constructing a plurality of ontology classes and determining the relationship among the ontology classes to obtain an ontology library.
Specifically, in this embodiment, according to the basic information of each device in the push range, and relevant linguistic data such as data information, scheduling rules, and papers of the basic information are analyzed, a plurality of ontology classes including a device class, a station class, a power grid class, a scheduling mechanism class, and the like are abstracted, and a relationship between the ontology classes is determined, where the ontology classes can be understood as a formal expression of a certain set of concepts in a specific field and a relationship between the concepts in the specific field, and then an ontology library is formed according to the established ontology classes and the relationship between the ontology classes by using an ontology construction tool.
S302: and mapping the devices into the ontology library one by one through ontology mapping, and using the device information and the associated information as the attachment of the devices to obtain the data relation network.
Specifically, in this embodiment, based on the device representation of each device, the device information of the device and the associated information, such as the area, station, line, and mechanism, related to the device are used as entities, and the entities are mapped into the ontology library one by one through ontology mapping to obtain the data relationship network. The specific method for ontology mapping comprises the following steps: one or more of mapping through a preset rule, mapping through similarity calculation and mapping through naive Bayes classification, specifically, different ontology mapping methods can be selected according to different data sources, for example, when an entity and a relation come from a structured database, mapping can be performed through the preset rule; when the entity comes from the equipment portrait or a new label is added in the equipment portrait, the label with similar content can be calculated and merged through the similarity on the basis of a preset rule, and the label is classified through a naive Bayes classification algorithm.
Here, the relationship between the ontology base and the data relational network is similar to the relationship between the database table structure and the concrete data, and is an abstract concept, and does not include concrete devices or tags. The ontology library can establish a power generator class entity, a power plant class entity and a subordinate station relation between the power generator class entity and the power plant class entity. The ontology mapping process is to extract the generator table, the power plant table and the foreign key relationship, create specific multiple generator entities, multiple power plant entities and specific corresponding relationships in the data relationship network, and obtain the result of the ontology mapping as the data relationship network.
Referring to fig. 6, in the present embodiment, a process of ontology mapping is described by way of example, specifically, based on a rule: the generator table (sg _ dev _ generator _ b) and the power plant table (sg _ con _ plant _ b) are associated with an external key (sg _ dev _ generator _ b.plant = sg _ con _ plant _ b.id) to form a affiliated plant-station relation; based on the portrait: the No. 1 generator is provided with a summer high-risk portrait, a label and a portrait name corresponding to equipment are established as entities from an equipment portrait storage table, and a relationship is established to associate the equipment with related entities; the label of ' 2019 operation ' of the No. 1 generator is in ' relationship with ' the No. 1 generator ' entity, and labels related to ' summer high-risk ' portrait, such as ' high temperature ', ' overload ', and the like, are in ' relationship with ' the summer high-risk ' entity on the basis of ' relationship with ' the No. 1 generator ' entity.
Preferably, in this embodiment, referring to fig. 7, in order to improve the storage performance and read-write flexibility of the data relationship network, the data relationship network is constructed in a data relationship graph manner, specifically, the data relationship graph takes the device as a master node, and takes the device portrait, the device information, and the associated information of the device as dependent nodes, and performs data query in a graph traversal manner, and the data relationship network is stored in a graph database manner, so that compared with a conventional relational data storage manner, the speed and accuracy of searching and recommending functional data query in a search engine are improved, and the searching and recommending effects are improved.
By the method for constructing the data relation network, the data relation network containing the equipment image, the equipment information and the associated information of the equipment is obtained, on the basis, the searching equipment is found in the data relation network based on the traversing of the preset data relation network by the searching equipment, and the equipment image, the equipment information and the associated information of the searching equipment are obtained and pushed.
In this embodiment, when pushing the device information and the associated information of the search device, the method that is adopted is as follows: and pushing the equipment information and the associated information of the search equipment according to the arrangement sequence of the equipment information and the equipment portrait in the front and the associated information in the back, wherein all the information in the associated information is pushed according to the arrangement sequence of preset weights from large to small. The push is to visually display the device representation, the device information and the associated information of the search device one by one for the user to view.
Specifically, referring to fig. 8, in this embodiment, the device information and the device portrait are pushed first, and then the pieces of information in the related information are pushed in the order from the largest to the smallest according to the preset weight of the pieces of information in the related information. The preset weight can be determined by the prior knowledge of the service expert and the use habit of the user of the search system. The preset weight is set in a pre-established relation evaluation base, a service expert defines an initial relation weight by using professional knowledge and historical experience, the initial relation weight is added into the relation evaluation base through evaluation, analysis and verification approval of the initial relation, and the relation evaluation base converts an evaluation index into the weight and adds the weight into a database where a data relation network is located by means of a storage structure of the data relation network so as to determine the weight of each information in the associated information of the equipment.
The information pushing method adopts a mode completely different from the existing mode based on user image search, constructs the equipment image of the equipment by using the construction thought of the user image and combining the latest technologies in the fields of cloud computing, natural language processing, artificial intelligence and the like and by determining the equipment attribute, the equipment characteristic and the equipment label, thereby realizing the data integration and the unified management of the equipment; constructing a data relation network taking equipment as a main body based on the equipment portrait, wherein the data relation network comprises basic information of the equipment, associated information of the equipment and the like, so that the carding and integration of the relation between the equipment and related data are realized, and the high-efficiency management and clear classification of the power grid regulation and control data are realized; and then, based on key information search and associated recommendation of a data relation network taking equipment as a main body, active push of the key information and associated information of the equipment is realized in a search system, the requirements of multi-professional and multi-user on more efficient, more flexible and more accurate information acquisition are met, the value of deep awakening of deep sleep data is achieved, and a hidden flash point of the data is found.
In another embodiment of the present invention, compared to the information pushing method shown in fig. 2, the information pushing method further includes, in addition to all the contents of the information pushing method shown in fig. 2, at least: and acquiring and pushing micro application information corresponding to the information contained in the equipment information of the search equipment according to the micro application information of each piece of information in the preset equipment information.
Specifically, the regulation cloud of the power system constructs micro applications such as model data, measurement data, electric quantity data, alarm data, environment data, event data, plan data and prediction data in a micro application mode. When a user searches a certain device, the micro application information related to the device is actively pushed, such as link address information, and the user can directly access the related micro application page from a search system page.
In another embodiment of the present invention, compared to the information pushing method shown in fig. 2, the information pushing method further includes, in addition to all the contents of the information pushing method shown in fig. 2, at least: acquiring nearest neighbor equipment of the search equipment, and pushing equipment information and associated information of the nearest neighbor equipment; wherein, the nearest neighbor device is a plurality of big devices before the similarity with the searching device.
And selecting other stations, lines or devices which are related to the search device and are in the same station, the same voltage level and the same area for pushing by means of a data relation network taking the device as a main body. The pushing mode mainly depends on nearest neighbor, a plurality of devices with the highest similarity are selected as the nearest neighbor, the searching device scores according to the interest degree of the nearest neighbor user to the devices to obtain a traditional scoring prediction result, and the user can access other related devices through known devices to realize quick access of basic information and related information of the devices.
The following are embodiments of the apparatus of the present invention that may be used to perform embodiments of the method of the present invention. For details of non-careless mistakes in the embodiment of the apparatus, please refer to the embodiment of the method of the present invention.
Referring to fig. 9, in a further embodiment of the present invention, an information pushing system is provided, which can be used to implement the information pushing method described above, and the information pushing system includes an information obtaining module, a searching module, and a pushing module. The information acquisition module is used for acquiring search information; the searching module is used for obtaining searching equipment according to the searching information and preset equipment figures of each equipment; the pushing module is used for acquiring and pushing the device information of the searching device.
Preferably, the push module can also be used for acquiring and pushing the device representation and/or the associated information of the search device.
Preferably, the information pushing system further comprises a portrait construction module. The portrait construction module is used for acquiring equipment information of the equipment; extracting the equipment characteristics of the equipment based on the equipment information, and obtaining the label of the equipment according to the equipment characteristics; and integrating the labels of the equipment to obtain the equipment picture.
Preferably, the information push system further comprises a data relationship network construction module. The data relation network building module is used for building a plurality of body classes and determining the relation among the body classes according to the equipment information and the associated information of the equipment in the pushing range to obtain a body library; and mapping each device and the device portrait of each device into an ontology library one by one through ontology mapping, and using the device information and the associated information as the attachment of the devices to obtain a data relation network. Based on the above, the pushing module is used for obtaining the device information and the associated information of the search device through a preset data relation network based on the search device and pushing the device information and the associated information of the search device.
In yet another embodiment of the present invention, a terminal device is provided that includes a processor and a memory, the memory storing a computer program comprising program instructions, the processor executing the program instructions stored by the computer storage medium. The Processor may be a Central Processing Unit (CPU), or may be other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable gate array (FPGA) or other Programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, etc., which is a computing core and a control core of the terminal, and is adapted to implement one or more instructions, and is specifically adapted to load and execute one or more instructions to implement a corresponding method flow or a corresponding function; the processor according to the embodiment of the present invention may be used for the operation of the information push method, and includes: acquiring search information; obtaining search equipment according to the search information and preset equipment figures of each equipment; and acquiring and pushing the device portrait and the device information of the search device.
In still another embodiment, the present invention also provides a computer-readable storage medium (Memory) which is a Memory device in a terminal device and stores programs and data. It is understood that the computer readable storage medium herein may include a built-in storage medium in the terminal device, and may also include an extended storage medium supported by the terminal device. The computer-readable storage medium provides a storage space storing an operating system of the terminal. Also, one or more instructions, which may be one or more computer programs (including program code), are stored in the memory space and are adapted to be loaded and executed by the processor. It should be noted that the computer-readable storage medium may be a high-speed RAM memory, or may be a non-volatile memory (non-volatile memory), such as at least one disk memory.
One or more instructions stored in the computer-readable storage medium can be loaded and executed by the processor to implement the corresponding steps of the related information pushing method in the above embodiments; one or more instructions in the computer-readable storage medium are loaded by the processor and perform the steps of: acquiring search information; obtaining search equipment according to the search information and preset equipment figures of each equipment; and acquiring and pushing the device portrait and the device information of the search device.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting the same, and although the present invention is described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: modifications and equivalents may be made to the embodiments of the invention without departing from the spirit and scope of the invention, which is to be covered by the claims.
Claims (14)
1. An information pushing method is characterized by comprising the following steps:
acquiring search information;
obtaining search equipment according to the search information and preset equipment figures of each equipment;
wherein, the equipment portrait is constructed by the following method:
acquiring equipment information of equipment; extracting the equipment characteristics of the equipment based on the equipment information, and obtaining the label of the equipment according to the equipment characteristics; integrating the labels of the equipment to obtain an equipment image;
the equipment is power equipment, and the data types of the equipment information comprise basic information, measurement data, electric quantity data, alarm data, environment data, event data, plan data, forecast data and data combined with other platforms or the outside;
the specific method for obtaining the label of the equipment according to the equipment characteristics comprises the following steps: presetting a plurality of label rules and labels corresponding to the label rules; selecting sample equipment, traversing a plurality of label rules according to the equipment characteristics of the sample equipment, and when the equipment characteristics of the sample equipment meet the label rules, enabling the sample equipment to contain a label corresponding to the current label rules; establishing a corresponding relation between the equipment characteristics and the label according to the equipment characteristics of the sample equipment and the label of the sample equipment, and obtaining the label of the equipment according to the equipment characteristics based on the corresponding relation;
acquiring and pushing equipment information and/or associated information of search equipment; the specific method comprises the following steps: based on the search equipment, obtaining equipment information and associated information of the search equipment through a preset data relation network, and pushing the equipment information of the search equipment and the equipment portrait and/or the associated information; the data relation network takes equipment and an equipment portrait as a main body, and equipment information and associated information of the equipment are constructed in an attached manner; the specific method comprises the following steps: according to the equipment information and the associated information of the equipment in the pushing range, constructing a plurality of ontology classes and determining the relationship among the ontology classes to obtain an ontology library;
and mapping each device and the device portrait of each device into an ontology library one by one through ontology mapping, and using the device information and the associated information as the attachment of the devices to obtain a data relation network.
2. The information pushing method according to claim 1, wherein the specific method for obtaining the search device according to the search information and the preset device images of the devices is as follows:
acquiring a keyword in the search information, and comparing the keyword in the search information with preset equipment portrait of each equipment to obtain the similarity between the search information and the equipment portrait of each equipment;
and selecting the equipment corresponding to the equipment image with the maximum similarity as searching equipment.
3. The information pushing method according to claim 1, wherein the specific method for obtaining the search device according to the search information and the preset device images of the devices is as follows:
acquiring a keyword in the search information, and comparing the keyword in the search information with preset equipment portrait of each equipment to obtain the similarity between the search information and the equipment portrait of each equipment;
arranging equipment corresponding to a plurality of large equipment images before the similarity according to the size of the similarity;
and acquiring selection information, and selecting search equipment from the equipment corresponding to the large equipment images with the similarity according to the selection information.
4. The information push method of claim 1, wherein the device representation includes at least one of an individual representation, a classified group representation, a corporate representation, and a custom group representation.
5. The information pushing method according to claim 1, wherein the specific method of ontology mapping comprises: one or more of mapping by a preset rule, mapping by similarity calculation and mapping by naive Bayes classification.
6. The information pushing method according to claim 1, wherein the data relationship network is constructed in a data relationship graph, the data relationship graph takes the device and the device portrait as main nodes, and the device information and the associated information of the device as dependent nodes; and the data relation network is stored in a mode of a graph database.
7. The information pushing method according to claim 1, wherein the specific method for pushing the device information of the search device and the device portrait and/or the associated information of the search device is as follows:
and pushing the equipment information and the associated information of the search equipment according to the arrangement sequence of the equipment information in front and the equipment portrait and/or the associated information in back, wherein all information in the associated information is pushed according to the arrangement sequence of preset weights from large to small.
8. The information pushing method according to claim 1, further comprising:
and acquiring and pushing micro application information corresponding to the information contained in the equipment information of the search equipment according to the micro application information of each piece of information in the preset equipment information.
9. The information pushing method according to claim 1, further comprising:
acquiring nearest neighbor equipment of the search equipment, and pushing equipment information and associated information of the nearest neighbor equipment; wherein, the nearest neighbor device is a plurality of big devices before the similarity with the searching device.
10. An information push system, comprising:
the information acquisition module is used for acquiring search information;
the searching module is used for obtaining searching equipment according to the searching information and preset equipment figures of each equipment; wherein, the equipment portrait is constructed by the following method:
acquiring equipment information of equipment; extracting the equipment characteristics of the equipment based on the equipment information, and obtaining the label of the equipment according to the equipment characteristics; integrating the labels of the equipment to obtain an equipment image;
the equipment is power equipment, and the data types of the equipment information comprise basic information, measurement data, electric quantity data, alarm data, environment data, event data, plan data, forecast data and data combined with other platforms or the outside;
the specific method for obtaining the label of the equipment according to the equipment characteristics comprises the following steps: presetting a plurality of label rules and labels corresponding to the label rules; selecting sample equipment, traversing a plurality of label rules according to the equipment characteristics of the sample equipment, and when the equipment characteristics of the sample equipment meet the label rules, enabling the sample equipment to contain a label corresponding to the current label rules; establishing a corresponding relation between the equipment characteristics and the label according to the equipment characteristics of the sample equipment and the label of the sample equipment, and obtaining the label of the equipment according to the equipment characteristics based on the corresponding relation;
the pushing module is used for acquiring and pushing the equipment information and/or the associated information of the search equipment; the specific method comprises the following steps: based on the search equipment, obtaining equipment information and associated information of the search equipment through a preset data relation network, and pushing the equipment information of the search equipment and the equipment portrait and/or the associated information; the data relation network takes equipment and an equipment portrait as a main body, and equipment information and associated information of the equipment are constructed in an attached manner; the specific method comprises the following steps: according to the equipment information and the associated information of the equipment in the pushing range, constructing a plurality of ontology classes and determining the relationship among the ontology classes to obtain an ontology library;
and mapping each device and the device portrait of each device into an ontology library one by one through ontology mapping, and using the device information and the associated information as the attachment of the devices to obtain a data relation network.
11. The information push system according to claim 10, further comprising:
and the micro-application pushing module is used for acquiring and pushing micro-application information corresponding to the information contained in the equipment information of the search equipment according to the micro-application information of each piece of information in the preset equipment information.
12. The information push system according to claim 10, further comprising:
the nearest neighbor pushing module is used for acquiring the nearest neighbor of the searching device and pushing the device information and the associated information of the nearest neighbor; wherein, the nearest neighbor device is a plurality of big devices before the similarity with the searching device.
13. A terminal device, comprising a memory, a processor and a computer program stored in the memory and operable on the processor, wherein the processor implements the steps of the information pushing method according to any one of claims 1 to 9 when executing the computer program.
14. A computer-readable storage medium, in which a computer program is stored, which, when being executed by a processor, carries out the steps of the information push method according to any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011242725.3A CN112100506B (en) | 2020-11-10 | 2020-11-10 | Information pushing method, system, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011242725.3A CN112100506B (en) | 2020-11-10 | 2020-11-10 | Information pushing method, system, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112100506A CN112100506A (en) | 2020-12-18 |
| CN112100506B true CN112100506B (en) | 2021-03-16 |
Family
ID=73785134
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011242725.3A Active CN112100506B (en) | 2020-11-10 | 2020-11-10 | Information pushing method, system, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112100506B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112732787B (en) * | 2021-01-02 | 2024-04-16 | 西北工业大学 | Equipment portrait and personalized operation and maintenance service method for important parts of motor train unit |
| CN115271277A (en) * | 2022-10-08 | 2022-11-01 | 中国电力科学研究院有限公司 | Power equipment portrait construction method and system, computer equipment and storage medium |
| CN116016204A (en) * | 2022-12-05 | 2023-04-25 | 中国联合网络通信集团有限公司 | Method and device for constructing industrial equipment portrait and readable storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101283353B (en) * | 2005-08-03 | 2015-11-25 | 搜索引擎科技有限责任公司 | The system and method for relevant documentation is found by analyzing tags |
| CN107315810A (en) * | 2017-06-27 | 2017-11-03 | 济南浪潮高新科技投资发展有限公司 | A kind of internet of things equipment behavior portrait method |
| CN109086377A (en) * | 2018-07-24 | 2018-12-25 | 江苏通付盾科技有限公司 | Generation method, device and the calculating equipment of equipment portrait |
| CN109635127A (en) * | 2019-02-20 | 2019-04-16 | 云南电网有限责任公司信息中心 | A kind of power equipment portrait knowledge mapping construction method based on big data technology |
| CN110347779A (en) * | 2019-05-30 | 2019-10-18 | 中国电力科学研究院有限公司 | Power equipment three-dimensional is drawn a portrait depicting method in a kind of electric system |
| CN110363379A (en) * | 2019-05-30 | 2019-10-22 | 中国电力科学研究院有限公司 | A kind of search and monitoring method of electric system |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180293314A1 (en) * | 2017-04-11 | 2018-10-11 | Mastercard International Incorporated | Systems and methods for generating location profiles based on verified user input |
| US10762083B2 (en) * | 2017-12-21 | 2020-09-01 | Microsoft Technology Licensing, Llc | Entity- and string-based search using a dynamic knowledge graph |
-
2020
- 2020-11-10 CN CN202011242725.3A patent/CN112100506B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101283353B (en) * | 2005-08-03 | 2015-11-25 | 搜索引擎科技有限责任公司 | The system and method for relevant documentation is found by analyzing tags |
| CN107315810A (en) * | 2017-06-27 | 2017-11-03 | 济南浪潮高新科技投资发展有限公司 | A kind of internet of things equipment behavior portrait method |
| CN109086377A (en) * | 2018-07-24 | 2018-12-25 | 江苏通付盾科技有限公司 | Generation method, device and the calculating equipment of equipment portrait |
| CN109635127A (en) * | 2019-02-20 | 2019-04-16 | 云南电网有限责任公司信息中心 | A kind of power equipment portrait knowledge mapping construction method based on big data technology |
| CN110347779A (en) * | 2019-05-30 | 2019-10-18 | 中国电力科学研究院有限公司 | Power equipment three-dimensional is drawn a portrait depicting method in a kind of electric system |
| CN110363379A (en) * | 2019-05-30 | 2019-10-22 | 中国电力科学研究院有限公司 | A kind of search and monitoring method of electric system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112100506A (en) | 2020-12-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111444236B (en) | Mobile terminal user portrait construction method and system based on big data | |
| CN112100506B (en) | Information pushing method, system, equipment and storage medium | |
| CN114238573B (en) | Text countercheck sample-based information pushing method and device | |
| CN106447346A (en) | Method and system for construction of intelligent electric power customer service system | |
| KR20200007969A (en) | Information processing methods, terminals, and computer storage media | |
| CN112508609B (en) | Crowd expansion prediction method, device, equipment and storage medium | |
| CN111125086B (en) | Method, device, storage medium and processor for acquiring data resources | |
| CN108846097B (en) | User interest tag representation method, article recommendation device and equipment | |
| CN109033277A (en) | Class brain system, method, equipment and storage medium based on machine learning | |
| CN113254711B (en) | Interactive image display method and device, computer equipment and storage medium | |
| CN108874783A (en) | Power information O&M knowledge model construction method | |
| CN107368521A (en) | A kind of Promote knowledge method and system based on big data and deep learning | |
| CN113806560A (en) | Power data knowledge graph generation method and system | |
| CN113064999A (en) | Knowledge graph construction algorithm, system, equipment and medium based on IT equipment operation and maintenance | |
| CN113946686A (en) | Electric power marketing knowledge map construction method and system | |
| CN110795613A (en) | Commodity searching method, device and system and electronic equipment | |
| CN116151235A (en) | Article generating method, article generating model training method and related equipment | |
| Ma et al. | Content Feature Extraction-based Hybrid Recommendation for Mobile Application Services. | |
| Wu et al. | PaintKG: the painting knowledge graph using bilstm-crf | |
| CN114328800A (en) | Text processing method and device, electronic equipment and computer readable storage medium | |
| CN112685452B (en) | Enterprise case retrieval method, device, equipment and storage medium | |
| CN115757735A (en) | Intelligent retrieval method and system for power grid digital construction result resources | |
| CN115048503A (en) | User preference label design method based on content analysis | |
| CN107577690A (en) | The recommendation method and recommendation apparatus of magnanimity information data | |
| CN114528378A (en) | Text classification method and device, electronic equipment and storage medium |
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 | ||
| CB03 | Change of inventor or designer information | ||
| CB03 | Change of inventor or designer information |
Inventor after: Wang Jiaqi Inventor after: Di Fangchun Inventor after: Yang Qingbo Inventor after: Li Zhihong Inventor after: Cui Can Inventor after: Zhang Linpeng Inventor after: Li Dapeng Inventor after: Li Lixin Inventor after: Huang Yunhao Inventor after: Tao Lei Inventor after: Liu Jinbo Inventor after: Xia Wenyue Inventor after: Song Xuri Inventor after: Ye Ruili Inventor before: Wang Jiaqi Inventor before: Yang Qingbo Inventor before: Li Zhihong Inventor before: Cui Can Inventor before: Zhang Linpeng Inventor before: Li Dapeng Inventor before: Li Lixin Inventor before: Huang Yunhao Inventor before: Tao Lei Inventor before: Xia Wenyue Inventor before: Song Xuri Inventor before: Ye Ruili Inventor before: Di Fangchun |