CN110321446A - Related data recommended method, device, computer equipment and storage medium - Google Patents
Related data recommended method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN110321446A CN110321446A CN201910609979.5A CN201910609979A CN110321446A CN 110321446 A CN110321446 A CN 110321446A CN 201910609979 A CN201910609979 A CN 201910609979A CN 110321446 A CN110321446 A CN 110321446A
- Authority
- CN
- China
- Prior art keywords
- chart database
- recommended
- target entity
- related data
- entities
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/51—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
Abstract
The present invention relates to related data recommended method, device, computer equipment and storage medium, this method includes obtaining user query request；Related data is obtained using chart database recommended models according to user query request, to obtain recommendation results；Recommendation results are sent to terminal to show；Wherein, chart database recommended models be carried out by several raw data sets analysis and it is built-up.The present invention is by constructing the chart database recommended models recommended based on chart database, after obtaining user query request, it is requested using the chart database recommended models according to the user query, related data can rapidly be inquired, form recommendation results, and shown, realize the accuracy for improving and recommending efficiency and promoting recommendation results.
Description
Technical field
The present invention relates to information processing methods, more specifically refer to related data recommended method, device, computer equipment
And storage medium.
Background technique
In the case where nowadays big data and artificial intelligence technology flourish, people increasingly have a profound understanding of the valence of data
Value.The value of data is not only only that data itself, locating for the direct or indirect connection and data between data object
Contextual information can be supplied to data processing and digging tool more valuable information.
When user gets a certain data, it may be desirable to obtain relevant data, be represented in order to all analyze the data
Value, still, existing technology generally requires user and voluntarily inputs when recommending information relevant with a certain data are calculated etc.
A large amount of characteristic, and traditional Relational DataBase is used, need the merging of mass data table operation associated, these behaviour
Make to be usually extremely time-consuming, is not suitable for constructing an efficient data recommendation mode.
Therefore, it is necessary to design a kind of new method, the accuracy for improving and recommending efficiency and promoting recommendation results is realized.
Summary of the invention
It is an object of the invention to overcome the deficiencies of existing technologies, related data recommended method, device, computer are provided and set
Standby and storage medium.
To achieve the above object, the invention adopts the following technical scheme: related data recommended method, comprising:
Obtain user query request；
Related data is obtained using chart database recommended models according to user query request, to obtain recommendation results；
Recommendation results are sent to terminal to show；
Wherein, the chart database recommended models be carried out by several raw data sets analysis and it is built-up.
Its further technical solution are as follows: the chart database recommended models be carried out by several raw data sets analysis and
Built-up, comprising:
Obtain raw data set；
Raw data set is analyzed, to obtain analysis result；
Original chart database is constructed based on the analysis results；
Original graph database sharing is indexed, to obtain standard chart database；
Recommended engine is designed to standard chart database, to obtain chart database recommended models.
Its further technical solution are as follows: it is described that raw data set is analyzed, to obtain analysis result, comprising:
Text-processing is carried out to the text information in raw data set, to obtain the first data set；
Rule match and word segmentation processing are carried out to the first data set, to obtain target entity and relation information, form institute
State analysis result.
Its further technical solution are as follows: described to construct original chart database based on the analysis results, comprising:
Traversal retrieves other entities relevant to the target entity, to obtain related entities；
The relationship between related entities and target entity is extracted, to obtain original chart database.
Its further technical solution are as follows: it is described that recommended engine is designed to standard chart database, to obtain chart database recommendation
Model, comprising:
The script attribute of related entities and target entity is extracted, to obtain novel entities；
Potential incidence relation between target entity and related entities is extended according to novel entities；
Using the adjacency vector of the adjacent object building target entity of target entity in standard chart database, to be abutted
Vector；
The similarity of adjacency vector is calculated, with the related data recommended；
Optimize current adjacency vector, according to the related data of recommendation to obtain recommended engine；
The standard chart database and corresponding recommended engine are integrated, to obtain chart database recommended models.
Its further technical solution are as follows: it is described that recommended engine is designed to standard chart database, to obtain chart database recommendation
Model, comprising:
The script attribute of related entities and target entity is extracted, to obtain novel entities；
Potential incidence relation between target entity and related entities is extended according to novel entities；
The rank value of the interdependent node of target entity in standard chart database is calculated using PageRank algorithm；
Filtering rank value is unsatisfactory for desired node, to obtain standard chart database correlator figure；
The adjacency vector of target entity is constructed using the adjacent object of target entity in standard chart database correlator figure, with
Obtain adjacency vector；
The similarity of adjacency vector is calculated, with the related data recommended；
Optimize current adjacency vector, according to the related data of recommendation to obtain recommended engine；
The standard chart database correlator figure and corresponding recommended engine are integrated, recommends mould to obtain chart database
Type.
Its further technical solution are as follows: user query request include the target entity relevant information of required inquiry with
And recommend condition.
The present invention also provides related data recommendation apparatus, comprising:
Request unit, for obtaining user query request；
Recommendation results form unit, for obtaining dependency number using chart database recommended models according to user query request
According to obtain recommendation results；
Recommendation results display unit, for recommendation results to be sent to terminal to show.
The present invention also provides a kind of computer equipment, the computer equipment includes memory and processor, described to deposit
Computer program is stored on reservoir, the processor realizes above-mentioned method when executing the computer program.
The present invention also provides a kind of storage medium, the storage medium is stored with computer program, the computer journey
Sequence can realize above-mentioned method when being executed by processor.
Compared with the prior art, the invention has the advantages that: the present invention is recommended by building based on chart database
Chart database recommended models after obtaining user query request, are requested using the chart database recommended models according to the user query,
Related data can be rapidly inquired, forms recommendation results, and shown, realizes to improve and recommends efficiency and promoted to recommend
As a result accuracy.
The invention will be further described in the following with reference to the drawings and specific embodiments.
Detailed description of the invention
Technical solution in order to illustrate the embodiments of the present invention more clearly, below will be to needed in embodiment description
Attached drawing is briefly described, it should be apparent that, drawings in the following description are some embodiments of the invention, general for this field
For logical technical staff, without creative efforts, it is also possible to obtain other drawings based on these drawings.
Fig. 1 is the application scenarios schematic diagram of related data recommended method provided in an embodiment of the present invention；
Fig. 2 is the flow diagram of related data recommended method provided in an embodiment of the present invention；
Fig. 3 is the sub-process schematic diagram of related data recommended method provided in an embodiment of the present invention；
Fig. 4 is the sub-process schematic diagram of related data recommended method provided in an embodiment of the present invention；
Fig. 5 is the sub-process schematic diagram of related data recommended method provided in an embodiment of the present invention；
Fig. 6 is the sub-process schematic diagram of related data recommended method provided in an embodiment of the present invention；
Fig. 7 be another embodiment of the present invention provides related data recommended method sub-process schematic diagram；
Fig. 8 is the schematic block diagram of related data recommendation apparatus provided in an embodiment of the present invention；
Fig. 9 is the schematic block diagram of computer equipment provided in an embodiment of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are some of the embodiments of the present invention, instead of all the embodiments.Based on this hair
Embodiment in bright, every other implementation obtained by those of ordinary skill in the art without making creative efforts
Example, shall fall within the protection scope of the present invention.
It should be appreciated that ought use in this specification and in the appended claims, term " includes " and "comprising" instruction
Described feature, entirety, step, operation, the presence of element and/or component, but one or more of the other feature, whole is not precluded
Body, step, operation, the presence or addition of element, component and/or its set.
It is also understood that mesh of the term used in this description of the invention merely for the sake of description specific embodiment
And be not intended to limit the present invention.As description of the invention and it is used in the attached claims, unless on
Other situations are hereafter clearly indicated, otherwise " one " of singular, "one" and "the" are intended to include plural form.
It will be further appreciated that the term "and/or" used in description of the invention and the appended claims is
Refer to any combination and all possible combinations of one or more of associated item listed, and including these combinations.
Fig. 1 and Fig. 2 are please referred to, Fig. 1 is that the application scenarios of related data recommended method provided in an embodiment of the present invention are illustrated
Figure.Fig. 2 is the schematic flow chart of related data recommended method provided in an embodiment of the present invention.The related data recommended method is answered
For in server.The server and terminal carry out data interaction, after user is requested by terminal input inquiry, by server
If chart database recommended models inquired after recommend, and recommendation results are shown in terminal.
Fig. 2 is the flow diagram of related data recommended method provided in an embodiment of the present invention.As shown in Fig. 2, this method
Include the following steps S110 to S150.
S110, user query request is obtained.
In the present embodiment, user query request is that user is inputted by terminal, and user query request includes required
The target entity relevant information and recommendation condition of inquiry.The recommendation condition refers between entity and target entity that needs are recommended
The condition that is met of similarity, for example similarity is the recommendation condition of top ten list or the recommendation condition that similarity is 90%
Deng.
S120, related data is obtained using chart database recommended models according to user query request, to obtain recommendation results.
In the present embodiment, recommendation results refer to the similarity of target entity meet recommendation condition related entities and
The list that its corresponding similarity is formed.
Wherein, the chart database recommended models be carried out by several raw data sets analysis and it is built-up.
Chart database recommended models be mainly based upon figure at database, analyze the pass in raw data set between entity
Connection relationship, the graph theory that the abstract ways and correlation theory stock of figure are established in Euler in 18th century, but with information technology
Development and new data processing need, and are thought deeply in a manner of scheming and are modeled, and a kind of relatively new data technique；Chart database
Connection between object (i.e. entity) is stored as the first class object, carry out table conjunction is not needed in query object related information
And wait operation, can directly inquire to obtain, by the mode of figure come to data modeling, can it is more efficient, more intuitively indicate number
Complicated, the dynamic interconnecting relation between is more advantageous to the enterprise schema that data are found from the overall situation, more profound to understand number
According to bringing more inspirations to data processing, chart database is in real-time recommendation, risk detection, geographical pathfinding, social networks and number
Wide application prospect is suffered from directions according to visualization etc..
In one embodiment, referring to Fig. 3, above-mentioned chart database recommended models are carried out by several raw data sets
It analyzes and built-up, it may include step S121~S125.
S121, raw data set is obtained.
In the present embodiment, raw data set refers to crawls resulting mass data from internet, can be according to difference
Industry establish different chart database recommended models, according to the actual situation depending on, can preferably improve the efficiency entirely recommended.
S122, raw data set is analyzed, to obtain analysis result.
In the present embodiment, analysis result refers to the pass of entity and entity and the raw data set in raw data set
System.
In one embodiment, referring to Fig. 4, above-mentioned step S122 may include step S1221~S1222.
S1221, text-processing is carried out to the text information in raw data set, to obtain the first data set；
In the present embodiment, the first data set refers to the spcial character and useless character for removing and influencing subsequent rule match
Text information afterwards, therefore, text-processing include removing some spcial characters and useless character for influencing subsequent rule match
Deng.
S1222, rule match and word segmentation processing are carried out to the first data set, to obtain target entity and relation information,
Form the analysis result.
In the present embodiment, target entity refers to that the object as the central node of figure in chart database, each figure have
One intermediate node, the intermediate node are then target entity.
The extraction of entity object is to identify important entity one by one from the record of relational database.It is related to for example, extracting
Court verdict, law entry, legal person, natural person, address, organization for arriving etc..And the extraction of relation information is remembered from database
The relationship between important entity is identified in record.For example, identifying approving person associated by court verdict, personnel concerning the case, judgement ground
The relationships such as location, judgement law court.
Rule match includes similar law entry, judge, the judgement mechanism etc. identified in court verdict text information, and is taken out
Take related entities.Participle tool refers specifically to the Chinese word segmentation tool of similar jieba-analysis, and binding rule matching uses, energy
Effectively promote the accuracy rate for extracting entity.Certainly, above-mentioned court verdict can also be other legal documents or other industry
File etc..
Source database extracts text information, and filters out redundancy, garbage；From pretreated text information, lead to
Keyword extraction, rule match combination Chinese word segmentation tool are crossed, the extraction of the identification and relationship that carry out entity obtains the main of figure
Information.
S123, original chart database is constructed based on the analysis results.
In the present embodiment, original chart database refers to figure only including target entity.It is provided by chart database
JDBC interface writes program for entity and relationship and imports chart database, constructs original chart database.
In one embodiment, referring to Fig. 5, above-mentioned step S123 may include step S1231~S1232.
S1231, traversal retrieve other entities relevant to the target entity, to obtain related entities.
In the present embodiment, related entities refer to the entity for having certain incidence relation with target entity.
According to practical application scene, such as needs to obtain most like court verdict herein according to a certain court verdict and recommend column
Table, therefore to construct chart database of the court verdict as data starting point, that is, the court verdict as target entity, traversal retrieval
Other entities relevant to court verdict entity.
Relationship between S1232, extraction related entities and target entity, to obtain original chart database.
After traversal retrieves other entities relevant to court verdict entity, the connection between related entities and target entity is extracted
System, in order to extend the physical network level of chart database, it is also necessary to the related entities of other entities of extreme saturation, building have compared with
Profound figure network structure.With court verdict data instance here, needing extraction includes the body release of court verdict, trial
Judge, the law law article of trial, relevant case case are by the entity relationships such as the personnel being related to or other organizations are realized
From point to line again to the extension in face, so that entire chart database has the figure network structure of relatively deep, and then can be improved entire
The accuracy rate of recommendation.
When importing diagram data, need to design suitable original chart database, consider figure connectivity and level knot abundant
Structure, various interconnecting relation, the data silo for avoiding relationship to be isolated as far as possible generate, that is, the target reality of onrelevant relationship occur
The appearance of body or related entities.
S124, original graph database sharing is indexed, to obtain standard chart database.
In the present embodiment, standard chart database refers to both have the database that figure is also equipped with manipulative indexing.
According to the original chart database being pre-designed, the index of design object entity increases entity to optimize retrieval performance
Between connection with the network layer of expander graphs, merge, delete redundancy relationship, improve original chart database；Specifically, to needs
The target entity setting index of retrieval is with Optimizing Queries speed, for example, court verdict entity is settable using court verdict title as rope
Draw.
Each figure has a target entity, therefore, setting index is required, in order to rapidly retrieve related entities
Recommend efficiency with improving.
S125, recommended engine is designed to standard chart database, to obtain chart database recommended models.
The similarity calculation mode and efficient related entities searching algorithm for selecting suitable entity, comprehensively consider effectiveness and
Efficiency provides efficient and useful recommendation results, to form chart database recommended models, the recommendation of the chart database recommended models
The process synthesis way of content-based recommendation and collaborative filtering, by constructing multi-level knowledge graph network, design is based on figure
Recommendation process.
In one embodiment, referring to Fig. 6, above-mentioned step S125 may include step S1251~S1256.
S1251, the script attribute for extracting related entities and target entity, to obtain novel entities.
In the present embodiment, novel entities refer to the entity generated based on the script attribute of related entities and target entity.
S1252, potential incidence relation between target entity and related entities is extended according to novel entities.
Combine the process of content-based recommendation and collaborative filtering.In standard chart database, relationship and entity are unified
As the first class object, therefore the attribute of entity script can be extracted as new entity, and establish new entity connection
System extends potential incidence relation between target entity to enrich the content level of figure.For example, analysis court verdict body property
In personnel, place, the organization etc. that are related to, consideration is extracted, as new entity, and simultaneously by itself and original sentence
Certainly book entity establishes new association.The content substance of extraction is more, more abundant to the expression based on content of recommended, therefore
Content-based recommendation effect is better.
S1253, the adjacency vector that target entity is constructed using the adjacent object of target entity in standard chart database, with
To adjacency vector；
S1254, the similarity for calculating adjacency vector, with the related data recommended；
S1255, optimize current adjacency vector according to the related data of recommendation, to obtain recommended engine；
S1256, the standard chart database and corresponding recommended engine are integrated, to obtain chart database recommended models.
The related data of above-mentioned recommendation is real according to section corresponding correlation for selecting similarity to meet the requirements of initial input
Body.
The way of collaborative filtering is the adjacent object i.e. adjacent node or reality using standard drawing database retrieval target entity
Body, constructs the adjacency vector of target entity, and calculates Jaccard similarity, is calculated with this come the recommendation of the recommended engine constructed
Process.
Figure is the set on side and vertex, and standard chart database expresses entity by node, passes through the company between node
Line carrys out relationship between expression.Interconnecting relation complicated between entity can directly be described by being advantageous in that using figure, be convenient to research people
Member more intuitively observes data.Meanwhile chart database is as a kind of unstructured database, carry out data that can be more convenient
Extension, do not need to establish complicated dependence as structured database.Meanwhile can efficiently be inquired using figure, time
Complicated entity relationship network is gone through, heavy, the inefficient conjunction table association process in relational database is avoided, so that looking into real time
It askes and requires to be achieved.
After the foundation of completion standard chart database, the real-time recommendation engine modules based on figure are designed.Make full use of figure number
According to huge advantage of the library technology in relationship retrieval and nomography, suitable recommending module is designed, to meet high correlation simultaneously
With the requirement of efficient recommendation results, the process of real-time recommendation is completed.
By from traditional structured database to the conversion of non-structured chart database, using chart database technology and
The advantage that correlation figure calculates, devises chart database recommended models.Chart database recommended models have high efficiency, accuracy and can
Scalability.Nomography application can effectively boosting algorithm efficiency, and combine object attribute itself and relationship object the considerations of,
The accuracy of recommendation results can be promoted.Meanwhile the unstructured feature of chart database is with good expansibility.
S130, recommendation results are sent to terminal to show；
Specifically, pass through Web API (application programming interface, Application Programming
Interface it) is obtained with the text data format of JSON (data interchange format, JavaScript Object Notation),
The related entities of recommendation can also be immediately seen by using the visualization interface technology of relevant figure.
In practice, after user query request is input in the chart database recommended models, the chart database mould
Type can be automatically positioned the figure where corresponding target entity, and quickly filter out the recommendation knot met the requirements in conjunction with recommendation condition
Fruit, and export, efficiently and accuracy rate is high.
Above-mentioned related data recommended method recommends mould by constructing the chart database recommended based on chart database
Type after obtaining user query request, is requested according to the user query using the chart database recommended models, can rapidly be inquired
To related data, recommendation results are formed, and are shown, realize the accuracy for improving and recommending efficiency and promoting recommendation results.
Fig. 7 be another embodiment of the present invention provides a kind of related data recommended method flow diagram.Such as Fig. 7 institute
Show, the related data recommended method of the present embodiment includes step S210-S230.Wherein step S210-S230 and above-described embodiment
In step S110-S130 it is similar, details are not described herein.The following detailed description of the step S2251 modified in the present embodiment~
S2258。
S2251, the script attribute for extracting related entities and target entity, to obtain novel entities；
S2252, potential incidence relation between target entity and related entities is extended according to novel entities；
S2253, the rank value that the interdependent node of target entity in standard chart database is calculated using PageRank algorithm；
S2254, filtering rank value are unsatisfactory for desired node, to obtain standard chart database correlator figure；
S2255, the adjoining of the adjacent object building target entity of target entity in standard chart database correlator figure is utilized
Vector, to obtain adjacency vector；
S2256, the similarity for calculating adjacency vector, with the related data recommended；
S2257, optimize current adjacency vector according to the related data of recommendation, to obtain recommended engine；
S2258, the standard chart database correlator figure and corresponding recommended engine are integrated, is pushed away with obtaining chart database
Recommend model.
Wherein, S2251~S2252 is similar with step S1251~S1252 in above-described embodiment, and details are not described herein.
For S2253~S2258, firstly, constructing the neighbour of the adjacent object composition of recommended using perfect figure network
Connect vector.Then according to Jaccard similarity principle, adjacency vector similarity is calculated.Due to general similarity calculation efficiency
Increase, the inefficiency under large data sets as data increase.In view of the characteristic and the requirement that calculates in real time of figure network, lead to
It crosses add-on third party and relies on packet, some chart databases support calling directly for PageRank algorithm.PageRank algorithm is a kind of
Common Network Central Node algorithm, can calculate the global PageRank value of figure network node, to obtain the central node of network.
It can also be by the way that different starting diffusion nodes be arranged, using Personalized PageRank algorithm derived from it, to calculate
PageRank value, that is, rank value of interdependent node in network.Using the mapping function of figure, one of low PageRank value is filtered out
Partial node reduces searched targets space to extract related subgraph to promote the efficiency of recommendation process, so that recommended engine reaches real
When the computational efficiency recommended.The subgraph that related object is generated using the mapping of chart database, to support in terms of Jaccard similarity
It calculates, is mapped using subgraph, can effectively promote the efficiency of recommendation, reach the requirement of real-time.
Fig. 8 is a kind of schematic block diagram of related data recommendation apparatus 300 provided in an embodiment of the present invention.As shown in figure 8,
Corresponding to the above related data recommended method, the present invention also provides a kind of related data recommendation apparatus 300.The related data is recommended
Device 300 includes the unit for executing above-mentioned related data recommended method, which can be configured in server.
Specifically, referring to Fig. 8, the related data recommendation apparatus 300 includes:
Request unit 301, for obtaining user query request；
Recommendation results form unit 302, related for being obtained according to user query request using chart database recommended models
Data, to obtain recommendation results；
Recommendation results display unit 303, for recommendation results to be sent to terminal to show.
In one embodiment, described device further include:
Model construction unit, for being analyzed and being constructed by several raw data sets, to form chart database recommendation
Model.
In one embodiment, institute's model construction unit includes:
Data set obtains subelement, for obtaining raw data set；
Subelement is analyzed, for analyzing raw data set, to obtain analysis result；
Original graph database sharing subelement, for constructing original chart database based on the analysis results；
Index construct subelement, for being indexed to original graph database sharing, to obtain standard chart database；
Engine design subelement, for designing recommended engine to standard chart database, to obtain chart database recommended models.
In one embodiment, the analysis subelement includes:
Text processing module, for carrying out text-processing to the text information in raw data set, to obtain the first data
Collection；
Matching module, for carrying out rule match and word segmentation processing to the first data set, to obtain target entity and pass
It is information, forms the analysis result.
In one embodiment, the original graph database sharing subelement includes:
Related entities form module, other entities relevant to the target entity are retrieved for traversing, to obtain correlation
Entity；
Relation extraction module, for extracting the relationship between related entities and target entity, to obtain original chart database.
In one embodiment, the engine design subelement includes:
First abstraction module, for extracting the script attribute of related entities and target entity, to obtain novel entities；
First relational extensions module is potentially associated between target entity and related entities for being extended according to novel entities
System；
Primary vector constructs module, for constructing target entity using the adjacent object of target entity in standard chart database
Adjacency vector, to obtain adjacency vector；
First similarity calculation module, for calculating the similarity of adjacency vector, with the related data recommended；
First optimization module optimizes current adjacency vector for the related data according to recommendation, to obtain recommended engine；
First integrates module, for integrating the standard chart database and corresponding recommended engine, to obtain diagram data
Library recommended models.
In other embodiments, the engine design subelement includes:
Second abstraction module, for extracting the script attribute of related entities and target entity, to obtain novel entities；
Second relational extensions module is potentially associated between target entity and related entities for being extended according to novel entities
System；
Rank value computing module, for calculating the associated section of target entity in standard chart database using PageRank algorithm
The rank value of point；
Filtering module is unsatisfactory for desired node for filtering rank value, to obtain standard chart database correlator figure；
Secondary vector constructs module, for being constructed using the adjacent object of target entity in standard chart database correlator figure
The adjacency vector of target entity, to obtain adjacency vector；
First similarity calculation module, for calculating the similarity of adjacency vector, with the related data recommended；
First optimization module optimizes current adjacency vector for the related data according to recommendation, to obtain recommended engine；
First integrates module, for integrating the standard chart database correlator figure and corresponding recommended engine, with
To chart database recommended models.
It should be noted that it is apparent to those skilled in the art that, above-mentioned related data recommendation apparatus
300 and each unit specific implementation process, can with reference to the corresponding description in preceding method embodiment, for convenience of description and
Succinctly, details are not described herein.
Above-mentioned related data recommendation apparatus 300 can be implemented as a kind of form of computer program, which can
To be run in computer equipment as shown in Figure 9.
Referring to Fig. 9, Fig. 9 is a kind of schematic block diagram of computer equipment provided by the embodiments of the present application.The computer
Equipment 500 is server.
Refering to Fig. 9, which includes processor 502, memory and the net connected by system bus 501
Network interface 505, wherein memory may include non-volatile memory medium 503 and built-in storage 504.
The non-volatile memory medium 503 can storage program area 5031 and computer program 5032.The computer program
5032 include program instruction, which is performed, and processor 502 may make to execute a kind of related data recommended method.
The processor 502 is for providing calculating and control ability, to support the operation of entire computer equipment 500.
The built-in storage 504 provides environment for the operation of the computer program 5032 in non-volatile memory medium 503, should
When computer program 5032 is executed by processor 502, processor 502 may make to execute a kind of related data recommended method.
The network interface 505 is used to carry out network communication with other equipment.It will be understood by those skilled in the art that in Fig. 9
The structure shown, only the block diagram of part-structure relevant to application scheme, does not constitute and is applied to application scheme
The restriction of computer equipment 500 thereon, specific computer equipment 500 may include more more or fewer than as shown in the figure
Component perhaps combines certain components or with different component layouts.
Wherein, the processor 502 is for running computer program 5032 stored in memory, to realize following step
It is rapid:
Obtain user query request；
Related data is obtained using chart database recommended models according to user query request, to obtain recommendation results；
Recommendation results are sent to terminal to show；
Wherein, the chart database recommended models be carried out by several raw data sets analysis and it is built-up.
The user query request includes the target entity relevant information and recommendation condition of required inquiry.
In one embodiment, processor 502 is realizing that the chart database recommended models are by several raw data sets
When carrying out analysis and built-up step, it is implemented as follows step:
Obtain raw data set；
Raw data set is analyzed, to obtain analysis result；
Original chart database is constructed based on the analysis results；
Original graph database sharing is indexed, to obtain standard chart database；
Recommended engine is designed to standard chart database, to obtain chart database recommended models.
In one embodiment, processor 502 realize it is described raw data set is analyzed, with obtain analysis result step
When rapid, it is implemented as follows step:
Text-processing is carried out to the text information in raw data set, to obtain the first data set；
Rule match and word segmentation processing are carried out to the first data set, to obtain target entity and relation information, form institute
State analysis result.
In one embodiment, processor 502 is when realizing the original graph database steps of building based on the analysis results, tool
Body realizes following steps:
Traversal retrieves other entities relevant to the target entity, to obtain related entities；
The relationship between related entities and target entity is extracted, to obtain original chart database.
In one embodiment, processor 502 is described to standard chart database design recommended engine in realization, to obtain figure number
When according to library recommended models step, it is implemented as follows step:
The script attribute of related entities and target entity is extracted, to obtain novel entities；
Potential incidence relation between target entity and related entities is extended according to novel entities；
Using the adjacency vector of the adjacent object building target entity of target entity in standard chart database, to be abutted
Vector；
The similarity of adjacency vector is calculated, with the related data recommended；
Optimize current adjacency vector, according to the related data of recommendation to obtain recommended engine；
The standard chart database and corresponding recommended engine are integrated, to obtain chart database recommended models.
In one embodiment, processor 502 is described to standard chart database design recommended engine in realization, to obtain figure number
When according to library recommended models step, it is implemented as follows step:
The script attribute of related entities and target entity is extracted, to obtain novel entities；
Potential incidence relation between target entity and related entities is extended according to novel entities；
The rank value of the interdependent node of target entity in standard chart database is calculated using PageRank algorithm；
Filtering rank value is unsatisfactory for desired node, to obtain standard chart database correlator figure；
The adjacency vector of target entity is constructed using the adjacent object of target entity in standard chart database correlator figure, with
Obtain adjacency vector；
The similarity of adjacency vector is calculated, with the related data recommended；
Optimize current adjacency vector, according to the related data of recommendation to obtain recommended engine；
The standard chart database correlator figure and corresponding recommended engine are integrated, recommends mould to obtain chart database
Type.
It should be appreciated that in the embodiment of the present application, processor 502 can be central processing unit (Central
Processing Unit, CPU), which can also be other general processors, digital signal processor (Digital
Signal Processor, DSP), specific integrated circuit (Application Specific Integrated Circuit,
ASIC), ready-made programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic
Device, discrete gate or transistor logic, discrete hardware components etc..Wherein, general processor can be microprocessor or
Person's processor is also possible to any conventional processor etc..
Those of ordinary skill in the art will appreciate that be realize above-described embodiment method in all or part of the process,
It is that relevant hardware can be instructed to complete by computer program.The computer program includes program instruction, computer journey
Sequence can be stored in a storage medium, which is computer readable storage medium.The program instruction is by the department of computer science
At least one processor in system executes, to realize the process step of the embodiment of the above method.
Therefore, the present invention also provides a kind of storage mediums.The storage medium can be computer readable storage medium.This is deposited
Storage media is stored with computer program, and processor is made to execute following steps when wherein the computer program is executed by processor:
Obtain user query request；
Related data is obtained using chart database recommended models according to user query request, to obtain recommendation results；
Recommendation results are sent to terminal to show；
Wherein, the chart database recommended models be carried out by several raw data sets analysis and it is built-up.
The user query request includes the target entity relevant information and recommendation condition of required inquiry.
In one embodiment, the processor realizes the chart database recommended models executing the computer program
It is when carrying out analysis and built-up step by several raw data sets, to be implemented as follows step:
Obtain raw data set；
Raw data set is analyzed, to obtain analysis result；
Original chart database is constructed based on the analysis results；
Original graph database sharing is indexed, to obtain standard chart database；
Recommended engine is designed to standard chart database, to obtain chart database recommended models.
In one embodiment, the processor is realized described to raw data set progress in the execution computer program
Analysis is implemented as follows step when obtaining analysis result step:
Text-processing is carried out to the text information in raw data set, to obtain the first data set；
Rule match and word segmentation processing are carried out to the first data set, to obtain target entity and relation information, form institute
State analysis result.
In one embodiment, the processor is realized and described is constructed based on the analysis results executing the computer program
When original graph database steps, it is implemented as follows step:
Traversal retrieves other entities relevant to the target entity, to obtain related entities；
The relationship between related entities and target entity is extracted, to obtain original chart database.
In one embodiment, the processor is realized and described is set to standard chart database executing the computer program
Meter recommended engine is implemented as follows step when obtaining chart database recommended models step:
The script attribute of related entities and target entity is extracted, to obtain novel entities；
Potential incidence relation between target entity and related entities is extended according to novel entities；
Using the adjacency vector of the adjacent object building target entity of target entity in standard chart database, to be abutted
Vector；
The similarity of adjacency vector is calculated, with the related data recommended；
Optimize current adjacency vector, according to the related data of recommendation to obtain recommended engine；
The standard chart database and corresponding recommended engine are integrated, to obtain chart database recommended models.
In one embodiment, the processor is realized and described is set to standard chart database executing the computer program
Meter recommended engine is implemented as follows step when obtaining chart database recommended models step:
The script attribute of related entities and target entity is extracted, to obtain novel entities；
Potential incidence relation between target entity and related entities is extended according to novel entities；
The rank value of the interdependent node of target entity in standard chart database is calculated using PageRank algorithm；
Filtering rank value is unsatisfactory for desired node, to obtain standard chart database correlator figure；
The adjacency vector of target entity is constructed using the adjacent object of target entity in standard chart database correlator figure, with
Obtain adjacency vector；
The similarity of adjacency vector is calculated, with the related data recommended；
Optimize current adjacency vector, according to the related data of recommendation to obtain recommended engine；
The standard chart database correlator figure and corresponding recommended engine are integrated, recommends mould to obtain chart database
Type.
The storage medium can be USB flash disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), magnetic disk
Or the various computer readable storage mediums that can store program code such as CD.
Those of ordinary skill in the art may be aware that list described in conjunction with the examples disclosed in the embodiments of the present disclosure
Member and algorithm steps, can be realized with electronic hardware, computer software, or a combination of the two, in order to clearly demonstrate hardware
With the interchangeability of software, each exemplary composition and step are generally described according to function in the above description.This
A little functions are implemented in hardware or software actually, the specific application and design constraint depending on technical solution.Specially
Industry technical staff can use different methods to achieve the described function each specific application, but this realization is not
It is considered as beyond the scope of this invention.
In several embodiments provided by the present invention, it should be understood that disclosed device and method can pass through it
Its mode is realized.For example, the apparatus embodiments described above are merely exemplary.For example, the division of each unit, only
Only a kind of logical function partition, there may be another division manner in actual implementation.Such as multiple units or components can be tied
Another system is closed or is desirably integrated into, or some features can be ignored or not executed.
The steps in the embodiment of the present invention can be sequentially adjusted, merged and deleted according to actual needs.This hair
Unit in bright embodiment device can be combined, divided and deleted according to actual needs.In addition, in each implementation of the present invention
Each functional unit in example can integrate in one processing unit, is also possible to each unit and physically exists alone, can also be with
It is that two or more units are integrated in one unit.
If the integrated unit is realized in the form of SFU software functional unit and when sold or used as an independent product,
It can store in one storage medium.Based on this understanding, technical solution of the present invention is substantially in other words to existing skill
The all or part of part or the technical solution that art contributes can be embodied in the form of software products, the meter
Calculation machine software product is stored in a storage medium, including some instructions are used so that a computer equipment (can be a
People's computer, terminal or network equipment etc.) it performs all or part of the steps of the method described in the various embodiments of the present invention.
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any
Those familiar with the art in the technical scope disclosed by the present invention, can readily occur in various equivalent modifications or replace
It changes, these modifications or substitutions should be covered by the protection scope of the present invention.Therefore, protection scope of the present invention should be with right
It is required that protection scope subject to.
Claims (10)
1. related data recommended method characterized by comprising
Obtain user query request；
Related data is obtained using chart database recommended models according to user query request, to obtain recommendation results；
Recommendation results are sent to terminal to show；
Wherein, the chart database recommended models be carried out by several raw data sets analysis and it is built-up.
2. related data recommended method according to claim 1, which is characterized in that the chart database recommended models are logical
Cross several raw data sets carry out analysis and it is built-up, comprising:
Obtain raw data set；
Raw data set is analyzed, to obtain analysis result；
Original chart database is constructed based on the analysis results；
Original graph database sharing is indexed, to obtain standard chart database；
Recommended engine is designed to standard chart database, to obtain chart database recommended models.
3. related data recommended method according to claim 2, which is characterized in that described to divide raw data set
Analysis, to obtain analysis result, comprising:
Text-processing is carried out to the text information in raw data set, to obtain the first data set；
Rule match and word segmentation processing are carried out to the first data set, to obtain target entity and relation information, form described point
Analyse result.
4. related data recommended method according to claim 2, which is characterized in that it is described construct based on the analysis results it is original
Chart database, comprising:
Traversal retrieves other entities relevant to the target entity, to obtain related entities；
The relationship between related entities and target entity is extracted, to obtain original chart database.
5. related data recommended method according to claim 2, which is characterized in that described to be pushed away to the design of standard chart database
It recommends and holds up, to obtain chart database recommended models, comprising:
The script attribute of related entities and target entity is extracted, to obtain novel entities；
Potential incidence relation between target entity and related entities is extended according to novel entities；
Using the adjacency vector of the adjacent object building target entity of target entity in standard chart database, with obtain it is adjacent to
Amount；
The similarity of adjacency vector is calculated, with the related data recommended；
Optimize current adjacency vector, according to the related data of recommendation to obtain recommended engine；
The standard chart database and corresponding recommended engine are integrated, to obtain chart database recommended models.
6. related data recommended method according to claim 2, which is characterized in that described to be pushed away to the design of standard chart database
It recommends and holds up, to obtain chart database recommended models, comprising:
The script attribute of related entities and target entity is extracted, to obtain novel entities；
Potential incidence relation between target entity and related entities is extended according to novel entities；
The rank value of the interdependent node of target entity in standard chart database is calculated using PageRank algorithm；
Filtering rank value is unsatisfactory for desired node, to obtain standard chart database correlator figure；
Using the adjacency vector of the adjacent object building target entity of target entity in standard chart database correlator figure, to obtain
Adjacency vector；
The similarity of adjacency vector is calculated, with the related data recommended；
Optimize current adjacency vector, according to the related data of recommendation to obtain recommended engine；
The standard chart database correlator figure and corresponding recommended engine are integrated, to obtain chart database recommended models.
7. related data recommended method according to any one of claims 1 to 6, which is characterized in that the user query are asked
It seeks the target entity relevant information including required inquiry and recommends condition.
8. related data recommendation apparatus characterized by comprising
Request unit, for obtaining user query request；
Recommendation results form unit, for obtaining related data using chart database recommended models according to user query request, with
Obtain recommendation results；
Recommendation results display unit, for recommendation results to be sent to terminal to show.
9. a kind of computer equipment, which is characterized in that the computer equipment includes memory and processor, on the memory
It is stored with computer program, the processor is realized as described in any one of claims 1 to 7 when executing the computer program
Method.
10. a kind of storage medium, which is characterized in that the storage medium is stored with computer program, the computer program quilt
Processor can realize the method as described in any one of claims 1 to 7 when executing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910609979.5A CN110321446B (en) | 2019-07-08 | 2019-07-08 | Related data recommendation method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910609979.5A CN110321446B (en) | 2019-07-08 | 2019-07-08 | Related data recommendation method and device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110321446A true CN110321446A (en) | 2019-10-11 |
| CN110321446B CN110321446B (en) | 2021-09-14 |
Family
ID=68123072
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910609979.5A Active CN110321446B (en) | 2019-07-08 | 2019-07-08 | Related data recommendation method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110321446B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112069412A (en) * | 2020-09-11 | 2020-12-11 | 腾讯科技（深圳）有限公司 | Information recommendation method and device, computer equipment and storage medium |
| CN112749296A (en) * | 2019-10-31 | 2021-05-04 | 北京达佳互联信息技术有限公司 | Video recommendation method and device, server and storage medium |
| CN115797020A (en) * | 2023-02-06 | 2023-03-14 | 网思科技股份有限公司 | Retail recommendation method, system and medium based on data processing of graph database |
Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050144114A1 (en) * | 2000-09-30 | 2005-06-30 | Ruggieri Thomas P. | System and method for providing global information on risks and related hedging strategies |
| US20130066819A1 (en) * | 2011-09-09 | 2013-03-14 | Microsoft Corporation | Adaptive recommendation system |
| CN103218407A (en) * | 2013-03-22 | 2013-07-24 | 南京信通科技有限责任公司 | Recommendation engine based on interest graph |
| US20130268290A1 (en) * | 2012-04-02 | 2013-10-10 | David Jackson | Systems and methods for disease knowledge modeling |
| CN104462504A (en) * | 2014-12-19 | 2015-03-25 | 北京奇虎科技有限公司 | Method and device for providing reasoning process data in search |
| US20150199226A1 (en) * | 2014-01-16 | 2015-07-16 | International Business Machines Corporation | Recommending a Suspicious Component in Problem Diagnosis for a Cloud Application |
| CN105335374A (en) * | 2014-06-19 | 2016-02-17 | 北大方正集团有限公司 | Knowledge point association method and apparatus as well as server and client containing apparatus |
| CN105589976A (en) * | 2016-03-08 | 2016-05-18 | 重庆文理学院 | Object entity determining method and device based on semantic correlations |
| CN106547887A (en) * | 2016-10-27 | 2017-03-29 | 北京百度网讯科技有限公司 | Method and apparatus is recommended in search based on artificial intelligence |
| CN107239665A (en) * | 2017-06-09 | 2017-10-10 | 京东方科技集团股份有限公司 | medical information inquiry system and method |
| CN108763321A (en) * | 2018-05-02 | 2018-11-06 | 深圳智能思创科技有限公司 | A kind of related entities recommendation method based on extensive related entities network |
| CN108920544A (en) * | 2018-06-13 | 2018-11-30 | 桂林电子科技大学 | A kind of personalized position recommended method of knowledge based map |
| CN108932262A (en) * | 2017-05-26 | 2018-12-04 | 北京小唱科技有限公司 | A kind of song recommendations method and device |
| CN109446362A (en) * | 2018-09-05 | 2019-03-08 | 北京费马科技有限公司 | Chart database structure, diagram data storage method, device based on external memory |
| CN109508419A (en) * | 2018-11-23 | 2019-03-22 | 成都品果科技有限公司 | A kind of recommended method and system of knowledge based study |
| CN109558468A (en) * | 2018-12-13 | 2019-04-02 | 北京百度网讯科技有限公司 | Processing method, device, equipment and the storage medium of resource |
-
2019
- 2019-07-08 CN CN201910609979.5A patent/CN110321446B/en active Active
Patent Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050144114A1 (en) * | 2000-09-30 | 2005-06-30 | Ruggieri Thomas P. | System and method for providing global information on risks and related hedging strategies |
| US20130066819A1 (en) * | 2011-09-09 | 2013-03-14 | Microsoft Corporation | Adaptive recommendation system |
| US20130268290A1 (en) * | 2012-04-02 | 2013-10-10 | David Jackson | Systems and methods for disease knowledge modeling |
| CN103218407A (en) * | 2013-03-22 | 2013-07-24 | 南京信通科技有限责任公司 | Recommendation engine based on interest graph |
| US20150199226A1 (en) * | 2014-01-16 | 2015-07-16 | International Business Machines Corporation | Recommending a Suspicious Component in Problem Diagnosis for a Cloud Application |
| CN105335374A (en) * | 2014-06-19 | 2016-02-17 | 北大方正集团有限公司 | Knowledge point association method and apparatus as well as server and client containing apparatus |
| CN104462504A (en) * | 2014-12-19 | 2015-03-25 | 北京奇虎科技有限公司 | Method and device for providing reasoning process data in search |
| CN105589976A (en) * | 2016-03-08 | 2016-05-18 | 重庆文理学院 | Object entity determining method and device based on semantic correlations |
| CN106547887A (en) * | 2016-10-27 | 2017-03-29 | 北京百度网讯科技有限公司 | Method and apparatus is recommended in search based on artificial intelligence |
| CN108932262A (en) * | 2017-05-26 | 2018-12-04 | 北京小唱科技有限公司 | A kind of song recommendations method and device |
| CN107239665A (en) * | 2017-06-09 | 2017-10-10 | 京东方科技集团股份有限公司 | medical information inquiry system and method |
| CN108763321A (en) * | 2018-05-02 | 2018-11-06 | 深圳智能思创科技有限公司 | A kind of related entities recommendation method based on extensive related entities network |
| CN108920544A (en) * | 2018-06-13 | 2018-11-30 | 桂林电子科技大学 | A kind of personalized position recommended method of knowledge based map |
| CN109446362A (en) * | 2018-09-05 | 2019-03-08 | 北京费马科技有限公司 | Chart database structure, diagram data storage method, device based on external memory |
| CN109508419A (en) * | 2018-11-23 | 2019-03-22 | 成都品果科技有限公司 | A kind of recommended method and system of knowledge based study |
| CN109558468A (en) * | 2018-12-13 | 2019-04-02 | 北京百度网讯科技有限公司 | Processing method, device, equipment and the storage medium of resource |
Non-Patent Citations (1)
| Title |
|---|
| 付江柳: "开放网络中信任关系建模问题研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112749296A (en) * | 2019-10-31 | 2021-05-04 | 北京达佳互联信息技术有限公司 | Video recommendation method and device, server and storage medium |
| CN112749296B (en) * | 2019-10-31 | 2024-01-26 | 北京达佳互联信息技术有限公司 | Video recommendation method, device, server and storage medium |
| CN112069412A (en) * | 2020-09-11 | 2020-12-11 | 腾讯科技（深圳）有限公司 | Information recommendation method and device, computer equipment and storage medium |
| CN112069412B (en) * | 2020-09-11 | 2023-08-04 | 腾讯科技（深圳）有限公司 | Information recommendation method, device, computer equipment and storage medium |
| CN115797020A (en) * | 2023-02-06 | 2023-03-14 | 网思科技股份有限公司 | Retail recommendation method, system and medium based on data processing of graph database |
| CN115797020B (en) * | 2023-02-06 | 2023-05-02 | 网思科技股份有限公司 | Retail recommendation method, system and medium for data processing based on graph database |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110321446B (en) | 2021-09-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104881424B (en) | A kind of acquisition of electric power big data, storage and analysis method based on regular expression | |
| JP6247292B2 (en) | Query expansion | |
| CN105630881B (en) | A kind of date storage method and querying method of RDF | |
| CN103455487B (en) | The extracting method and device of a kind of search term | |
| CN106202207A (en) | A kind of index based on HBase ORM and searching system | |
| CN110321446A (en) | Related data recommended method, device, computer equipment and storage medium | |
| CN102402539A (en) | Design technology for object-level personalized vertical search engine | |
| CN103838785A (en) | Vertical search engine in patent field | |
| US9558240B2 (en) | Extending relational algebra for data management | |
| CN110019616A (en) | A kind of POI trend of the times state acquiring method and its equipment, storage medium, server | |
| JP5535062B2 (en) | Data storage and query method for time series analysis of weblog and system for executing the method | |
| CN113254630B (en) | Domain knowledge map recommendation method for global comprehensive observation results | |
| CN105550375A (en) | Heterogeneous data integrating method and system | |
| CN111611304A (en) | Knowledge-driven joint big data query and analysis platform | |
| WO2017040209A1 (en) | Data preparation for data mining | |
| CN103761286B (en) | A kind of Service Source search method based on user interest | |
| CN104298669A (en) | Person geographic information mining model based on social network | |
| Sriramoju | An Application for Annotating Web Search Results | |
| Chu et al. | Automatic data extraction of websites using data path matching and alignment | |
| CN102915304B (en) | Document retrieving apparatus and method | |
| Babur et al. | Towards statistical comparison and analysis of models | |
| CN104537047B (en) | A kind of clothes basic pattern plate searching system based on Lucene | |
| CN110990423A (en) | SQL statement execution method, device, equipment and storage medium | |
| Trabelsi et al. | A new methodology to bring out typical users interactions in digital libraries | |
| CN103246697A (en) | Method and equipment for determining near-synonymy sequence clusters |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 518000 room 701, building 11, Shenzhen Software Park (phase 2), No.1, kejizhong 2 Road, Gaoxin Central District, Maling community, Yuehai street, Nanshan District, Shenzhen City, Guangdong Province Applicant after: Shenzhen Huayun Zhongsheng Technology Co.,Ltd. Address before: 601, devison building, No. 016, Gaoxin South 7th Road, community, high tech Zone, Yuehai street, Nanshan District, Shenzhen City, Guangdong Province Applicant before: SHENZHEN HUAYUN ZHONGSHENG TECHNOLOGY Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |