CN112132727B - Government service pushing method of situation big data based on city big data - Google Patents

Government service pushing method of situation big data based on city big data Download PDF

Info

Publication number
CN112132727B
CN112132727B CN202011006238.7A CN202011006238A CN112132727B CN 112132727 B CN112132727 B CN 112132727B CN 202011006238 A CN202011006238 A CN 202011006238A CN 112132727 B CN112132727 B CN 112132727B
Authority
CN
China
Prior art keywords
situation
government
natural
data
person
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
Application number
CN202011006238.7A
Other languages
Chinese (zh)
Other versions
CN112132727A (en
Inventor
陈恩红
陈钢
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Yangtze River Delta Information Intelligence Innovation Research Institute
Original Assignee
Yangtze River Delta Information Intelligence Innovation Research Institute
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Yangtze River Delta Information Intelligence Innovation Research Institute filed Critical Yangtze River Delta Information Intelligence Innovation Research Institute
Priority to CN202011006238.7A priority Critical patent/CN112132727B/en
Publication of CN112132727A publication Critical patent/CN112132727A/en
Application granted granted Critical
Publication of CN112132727B publication Critical patent/CN112132727B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/26—Government or public services
    • 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
    • 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
    • G06F16/9535—Search customisation based on user profiles and personalisation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G06F18/232—Non-hierarchical techniques
    • G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
    • G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A30/00—Adapting or protecting infrastructure or their operation
    • Y02A30/60—Planning or developing urban green infrastructure

Abstract

The invention discloses a government affair service pushing method of situation big data based on city big data, comprising the following steps: step a, constructing a natural person situation data model, and describing the social activity rule, individual business characteristics, social interaction states and the like of a single natural person in an omnibearing manner; step b, pushing situation cluster government affair service; wherein, step a includes: step a1, constructing a basic attribute situation of a natural person; step a2, constructing a natural human life event situation; step a3, constructing a social relationship situation of natural people; step b comprises: step b1, calculating a situation vector; step b2, clustering the situation; and b3, pushing government service. The method not only can innovate government population data application modes, but also is helpful for promoting the transformation from government forms to service forms, so that government departments can provide accurate personalized, refined and mobile services for the public.

Description

Government service pushing method of situation big data based on city big data
Technical Field
The invention relates to a government affair service pushing method based on situation big data of city big data.
Background
With the deep progress of government affair disclosure, the work such as 'internet+' government affair service, the contradiction between the rapid increase of website information content of each level government and the personalized demands of users is increasingly prominent. The traditional electronic commerce recommendation system only considers the relation between the user and the project, and does not consider the situation information of the user. However, in the field of government service, the accuracy of the recommendation algorithm is greatly affected by the context information.
Therefore, a new method is urgently needed to solve the above technical problems.
Disclosure of Invention
The invention aims to provide a government service pushing method for situation big data based on city big data, which not only can innovate government population data application modes, but also is helpful for pushing government forms to change into service forms, so that government departments can provide accurate personalized, refined and mobile services for the public.
In order to achieve the above purpose, the present invention provides a government service pushing method of situation big data based on city big data, comprising:
step a, constructing a natural person situation data model, and describing the social activity rule, individual business characteristics, social interaction states and the like of a single natural person in an omnibearing manner;
step b, pushing situation cluster government affair service; wherein, the liquid crystal display device comprises a liquid crystal display device,
step a comprises:
step a1, constructing a basic attribute situation of a natural person;
step a2, constructing a natural human life event situation;
step a3, constructing a social relationship situation of natural people;
step b comprises:
step b1, calculating a situation vector;
step b2, clustering the situation;
and b3, pushing government service.
Preferably, the basic attribute context in step a1 includes effective identity proof reflecting birth and social attribution of a natural person, index reflecting natural humanization quality, index reflecting employment situation of the natural person and index reflecting knowledge and skill level of the natural person in a professional activity.
Preferably, step a1 comprises:
firstly, extracting relevant data catalogs of government departments such as public security bureau, personal social bureau, civil government bureau and the like, and forming natural person basic information, passport information, driving license information, taiwan pass information, kong and Australian pass information, social security card information, cultural degree information, work unit information, practitioner qualification information, practice qualification information, professional technical job qualification information, professional skill information and religious staff information after multi-table association;
secondly, regarding the multi-source data item in the related information of the natural person, taking the person with the highest weighted score of accuracy and updating time as an adoption object; then connecting to a local MySQL database through a pymysql technology, and storing the regulated data into the local database;
finally, predicting the basic attribute which cannot be obtained through the step a1 by adopting an attribute reasoning method; after acquiring known attribute data affecting unknown attributes, constructing a graph according to a certain algorithm, and then reasoning based on prior probability; calculating influence values among attribute values when constructing an attribute graph, and determining the sequence of attribute influence on the influence sequence among the attributes; wherein, the liquid crystal display device comprises a liquid crystal display device,
the steps required for unknown attribute reasoning include: calculating an influence value between attribute values of the attributes, calculating an influence value between the attributes, and calculating a condition value between the attributes.
Preferably, the personal event context in step a2 comprises various kinds of business events or activities that natural persons participate in during the life cycle.
Preferably, step a2 comprises:
firstly, constructing a life event data model dictionary (key: event type, value: [ business event 1, business event 2, … …, business event n ]), wherein each business event is composed of a plurality of data items (D1, the..once again, DN);
secondly, extracting and regulating data related to natural human life events of various government departments, connecting the data to a local MySQL database through a pymysql technology, and storing the regulated data into the local database;
then, calculating text similarity for the data stored in the substep a2 by using word vectors, generating word vectors by using Glove model, word2vec model and Bert model training, calculating similarity of business item word vectors, setting a specified threshold value, and fusing similar business items of a plurality of departments to form a corresponding life item data set T;
and finally, organizing the data in the data set T by using a life event data model dictionary so as to realize the fusion and standardization of the natural life event multi-source data.
Preferably, the social relationship context in step a3 includes reflecting various person-person relationships established by natural persons during social activities, reflecting person-ground relationships that natural persons belong to and establish with certain types of places (places) for reasons of living, working, learning, etc., and reflecting person-object relationships that natural persons possess tangible or intangible assets during full life cycle history.
Preferably, step a3 comprises:
firstly, defining a plurality of entity objects of natural people, places, motor vehicles, houses, lands and intellectual property rights; each natural person node can establish a plurality of relations with a plurality of nodes (natural persons, places, articles and the like); adding attributes for each entity object, wherein the natural person attributes are basic attributes constructed in the step a1, the place attributes comprise place names, place types and roles of persons in places, and the object attributes comprise object names, object types and possession times; wherein a single node may contain multiple attribute descriptions that characterize its physical characteristics;
secondly, defining a relation and an event, and adding the relation or the event between entity objects; wherein, the comprehensive relationship of relatives, neighbors or colleagues is added between individuals, the belonging relationship is added between individuals and organizations, and the possession relationship is added between individuals and certificates; each relationship comprises a start node and a stop node; the attributes of the relationship include relationship type, relationship establishment time and relationship release time;
then, after the definition of the entity, the attribute, the relation and the event is finished, extracting the existing various data through a data extraction tool, and finally constructing and forming a set of complete natural human social relation knowledge graph through entity alignment and attribute filling of the extracted knowledge;
and finally, establishing an index by adopting common fields of the identification card number, the property right number, the land use right number and the motor vehicle number plate number, and optimizing the inquiry performance of the social relation diagram database.
Preferably, the government service object (i.e. natural person) in step b1 has a basic attribute context (R 1 ) Life event context (R) 2 ) And social relationship context (R) 3 ) Context vector R mi ＝{R 1 mi ,R 2 mi ,R 3 mi ,...,R l mi ' representing a service object U m For the situation index R i Is the selection of vector R nj ＝{R 1 nj ,R 2 nj ,R 3 nj ,...,R l nj U is represented by } n Contextual index data R of (2) j The distance between the two context vectors is calculated as follows:
and obtaining natural people context vectors after context calculation, wherein each natural person corresponds to one context vector, and then generating a user-project-context three-dimensional matrix model according to an original user-project scoring matrix, wherein the matrix model comprises 3 types of vectors, namely a user vector, a government service project vector and a context vector.
Preferably, in the step b2, modeling the natural human situation by adopting a clustering algorithm based on K-means; the clustering algorithm based on K-means needs to define the number of to-be-formed clustering sets, namely the value of K in advance, randomly selects K objects as the centroids of the clusters, distributes the samples to the clustering set closest to the centroids by calculating the similarity between each sample and the centroids for the rest situation vectors, and then updates the centroid value for the clustering set distributed with new samples. Distributing all samples to finish natural person clustering to obtain K similar user clusters; the context clustering execution step comprises the following steps:
1. setting the number K of classifications;
2. selecting K different objects from the dataset S as initial centroids { b } 1 ,b 2 ,...,b k }；
3. Calculating a context distance d between the context vector i and the centroid b for any non-accessed context vector i in the dataset S;
4. classifying the context vector i into a cluster set C closest to the context vector i;
5. re-calculating the average value of all the objects in the K clustering sets as a new centroid value;
6. updating the centroid value b in the changed set C;
7. repeating steps 3 to 6 until all centroids { b } 1 ,b 2 ,...,b k No longer changes;
8. output context cluster set { C 1 ,C 2 ,...,C k } and corresponding centroid value { b } 1 ,b 2 ,...,b k }。
Preferably, in step b3, K similar clusters are obtained according to a K-means clustering algorithm, in order to reduce the computational complexity and obtain better pushing accuracy, in an original user-item matrix, corresponding sub-user-item matrices are obtained by searching according to information of the K clusters, and then a UserCF recommendation algorithm is directly applied to the sub-matrices to perform Top-N pushing; setting a scoring threshold P, wherein the score of the natural person is higher than the scoring threshold P, and the natural person possibly needs the government service project, or else the natural person possibly does not need the government service project; the execution steps are as follows:
1. defining push list length N, scoring threshold P, similarity number M and context cluster set { C } 1 ,C 2 ,...,C k -an original user-project matrix R;
2. selecting a context cluster { C } 1 ,C 2 ,...,C k Any unvisited set C in } i Searching the corresponding user-project subset R in the original user-project matrix R i ；
3. Repeating 2 until all situation cluster clusters { C 1 ,C 2 ,...,C k Corresponding user-item subset { R } 1 ,R 2 ,...,R k }；
4. For user-item subset R i Applying a collaborative filtering recommendation algorithm and predicting a deletion score;
first, for the cluster C i User U in (B) j Find its corresponding government service item set I j ；
Second, in item set I j The government affair service items with the scores Ratings more than or equal to P are screened to obtain government affair service items possibly needed by the government affair service items;
then, calculating the similarity sim between the users, and selecting M similarity neighbors { u }, wherein M is the same as M 1 ,u 2 ,...,u M }；
Next, the current user U is interested in similar neighbors j Government service item p with no score is calculated U j Pearson similarity to p, and in aggregate RI j The steps are sorted according to decreasing similarity;
finally, the top N of the scoring list is taken as the current user U j Generating a government service push list L with the length of N;
5. repeat 4 until the natural people in each cluster get pushed.
According to the technical scheme, the government service object (natural person) situation big data model is built, the potentially required government service is mined according to the situation of the natural person, and the government department is helped to accurately lock the service object. Not only can the government demographic data application model be innovated, but also the transformation of government forms into service forms can be facilitated. And converging government population data based on the natural person situation big data model, and promoting government population data application to expand from a small data primary application mode which can only meet single-system application to a big data deep application mode which can meet multi-system comprehensive application. The situation clustering and government service pushing method is constructed based on the big natural person situation data, and government departments can provide accurate personalized, refined and mobile services for the public and technical support for pushing government forms to change from production forms to service forms.
Additional features and advantages of the invention will be set forth in the detailed description which follows.
Drawings
The accompanying drawings are included to provide a further understanding of the invention, and are incorporated in and constitute a part of this specification, illustrate the invention and together with the description serve to explain, without limitation, the invention. In the drawings:
fig. 1 is a flowchart of a government service pushing method based on situation big data of city big data.
Detailed Description
The following describes specific embodiments of the present invention in detail with reference to the drawings. It should be understood that the detailed description and specific examples, while indicating and illustrating the invention, are not intended to limit the invention.
In the present invention, unless otherwise indicated, directional terms contained in the terms merely represent the orientation of the terms in a conventional use state or are commonly understood by those skilled in the art, and should not be construed as limitations on the terms.
Referring to fig. 1, the invention provides a government service pushing method of situation big data based on city big data, comprising the following steps:
step a, constructing a natural person situation data model, and carrying out omnibearing description and depiction aiming at the social activity rule, individual business characteristics, social interaction state and the like of a single natural person, wherein the omnibearing description and depiction comprises a basic attribute situation, a life event situation and a social relation situation;
step b, pushing situation cluster government affair service; wherein, the liquid crystal display device comprises a liquid crystal display device,
step a comprises:
step a1, constructing a basic attribute situation of a natural person;
step a2, constructing a natural human life event situation;
step a3, constructing a social relationship situation of natural people;
step b comprises:
step b1, calculating a situation vector;
step b2, clustering the situation;
and b3, pushing government service.
The basic attribute context in the step a1 comprises effective identity identification (such as resident identification card, passport, pass and the like) reflecting the birth and social attribution of the natural person, index (cultural degree) reflecting the humanization quality of the natural person, index reflecting the employment situation (current work unit) of the natural person and index reflecting the knowledge and skill level of the natural person in a certain professional activity (such as practitioner qualification, practice qualification, professional skill and the like).
Specifically, step a1 includes:
firstly, extracting relevant data catalogs of government departments such as public security bureau, personal social bureau, civil government bureau and the like, and forming natural person basic information, passport information, driving license information, taiwan pass information, kong and Australian pass information, social security card information, cultural degree information, work unit information, practitioner qualification information, practice qualification information, professional technical job qualification information, professional skill information and religious staff information after multi-table association;
secondly, regarding the multi-source data item in the related information of the natural person, taking the person with the highest weighted score of accuracy and updating time as an adoption object; then connecting to a local MySQL database through a pymysql technology, and storing the regulated data into the local database;
finally, predicting the basic attribute which cannot be obtained through the step a1 by adopting an attribute reasoning method; after acquiring known attribute data affecting unknown attributes, constructing a graph according to a certain algorithm, and then reasoning based on prior probability; calculating influence values among attribute values when constructing an attribute graph, and determining the sequence of attribute influence on the influence sequence among the attributes; wherein, the liquid crystal display device comprises a liquid crystal display device,
the steps required for unknown attribute reasoning include: calculating an influence value between attribute values of the attributes, calculating an influence value between the attributes, and calculating a condition value between the attributes.
The personal event situation in the step a2 comprises various business events or activities participated by natural persons in the life cycle process, such as educational experience, employment experience, lost business registration, social security participation, marital registration, tax payment and the like.
Specifically, step a2 includes:
firstly, constructing a life event data model dictionary (key: event type, value: [ business event 1, business event 2, … …, business event n ]), wherein each business event is composed of a plurality of data items (D1, the..once again, DN);
secondly, extracting and regulating data related to natural human life events of various government departments, connecting the data to a local MySQL database through a pymysql technology, and storing the regulated data into the local database;
then, calculating text similarity for the data stored in the substep a2 by using word vectors, generating word vectors by using Glove model, word2vec model and Bert model training, calculating similarity of business item word vectors, setting a specified threshold value, and fusing similar business items of a plurality of departments to form a corresponding life item data set T;
and finally, organizing the data in the data set T by using a life event data model dictionary so as to realize the fusion and standardization of the natural life event multi-source data.
The social relationship context in the step a3 includes reflecting various person-person relationships (such as family relationships, colleague relationships, etc.) established by natural persons during social activities, reflecting person-ground relationships (such as residential places, employment places, schools, etc.) which the natural persons belong to and establish with for reasons of living, working, learning, etc., and reflecting tangible or intangible assets owned by the natural persons during full life cycle histories and person-object relationships (such as houses, lands, automobiles, intellectual property, etc.) which the natural persons establish with.
Specifically, step a3 includes:
firstly, defining a plurality of entity objects of natural people, places, motor vehicles, houses, lands and intellectual property rights; each natural person node can establish a plurality of relations with a plurality of nodes (natural persons, places, articles and the like); adding attributes for each entity object, wherein the natural person attributes are basic attributes constructed in the step a1, the place attributes comprise place names, place types and roles of persons in places, and the object attributes comprise object names, object types and possession times; wherein a single node may contain multiple attribute descriptions that characterize its physical characteristics;
secondly, defining a relation and an event, and adding the relation or the event between entity objects; wherein, the comprehensive relationship of relatives, neighbors or colleagues is added between individuals, the belonging relationship is added between individuals and organizations, and the possession relationship is added between individuals and certificates; each relationship comprises a start node and a stop node; the attributes of the relationship include relationship type, relationship establishment time and relationship release time;
then, after the definition of the entity, the attribute, the relation and the event is finished, extracting the existing various data through a data extraction tool, and finally constructing and forming a set of complete natural human social relation knowledge graph through entity alignment and attribute filling of the extracted knowledge;
and finally, establishing an index by adopting common fields of the identification card number, the property right number, the land use right number and the motor vehicle number plate number, and optimizing the inquiry performance of the social relation diagram database.
In step b1, the government service object (i.e. natural person) has basic attribute context (R 1 ) Life event context (R) 2 ) And social relationship context (R) 3 ) Context vector R mi ＝{R 1 mi ,R 2 mi ,R 3 mi ,...,R l mi ' representing a service object U m For the situation index R i Is the selection of vector R nj ＝{R 1 nj ,R 2 nj ,R 3 nj ,...,R l nj U is represented by } n Contextual index data R of (2) j The distance between the two context vectors is calculated as follows:
and obtaining natural people context vectors after context calculation, wherein each natural person corresponds to one context vector, and then generating a user-project-context three-dimensional matrix model according to an original user-project scoring matrix, wherein the matrix model comprises 3 types of vectors, namely a user vector, a government service project vector and a context vector.
In the step b2, modeling is carried out on the situation of the natural person by adopting a clustering algorithm based on K-means; the clustering algorithm based on K-means needs to define the number of to-be-formed clustering sets, namely the value of K in advance, randomly selects K objects as the centroids of the clusters, distributes the samples to the clustering set closest to the centroids by calculating the similarity between each sample and the centroids for the rest situation vectors, and then updates the centroid value for the clustering set distributed with new samples. Distributing all samples to finish natural person clustering to obtain K similar user clusters; the context clustering execution step comprises the following steps:
1. setting the number K of classifications;
2. selecting K different objects from the dataset S as initial centroids { b } 1 ,b 2 ,...,b k }；
3. Calculating a context distance d between the context vector i and the centroid b for any non-accessed context vector i in the dataset S;
4. classifying the context vector i into a cluster set C closest to the context vector i;
5. re-calculating the average value of all the objects in the K clustering sets as a new centroid value;
6. updating the centroid value b in the changed set C;
7. repeating steps 3 to 6 until all centroids { b } 1 ,b 2 ,...,b k No longer changes;
8. output context cluster set { C 1 ,C 2 ,...,C k } and corresponding centroid value { b } 1 ,b 2 ,...,b k }。
In the step b3, K similar clusters are obtained according to a K-means clustering algorithm, in order to reduce the computational complexity and obtain better pushing accuracy, in an original user-project matrix, corresponding sub-user-project matrixes are obtained by searching according to the information of the K clusters, and then a UserCF recommendation algorithm is directly applied to the sub-matrixes to push Top-N; setting a scoring threshold P, wherein the score of the natural person is higher than the scoring threshold P, and the natural person possibly needs the government service project, or else the natural person possibly does not need the government service project; the execution steps are as follows:
1. defining push list length N, scoring threshold P, similarity number M and context cluster set { C } 1 ,C 2 ,...,C k -an original user-project matrix R;
2. selecting a context cluster { C } 1 ,C 2 ,...,C k Any unvisited set C in } i Searching the corresponding user-project subset R in the original user-project matrix R i ；
3. Repeating 2 until all situation cluster clusters { C 1 ,C 2 ,...,C k Corresponding user-item subset { R } 1 ,R 2 ,...,R k }；
4. For user-item subset R i Applying a collaborative filtering recommendation algorithm and predicting a deletion score;
first, for the cluster C i User U in (B) j Find its corresponding government service item set I j ；
Second, in item set I j The government affair service items with the scores Ratings more than or equal to P are screened to obtain government affair service items possibly needed by the government affair service items;
then, calculating the similarity sim between the users, and selecting M similarity neighbors { u }, wherein M is the same as M 1 ,u 2 ,...,u M }；
Next, the current user U is interested in similar neighbors j Government service item p with no score is calculated U j Pearson similarity to p, and in aggregate RI j The steps are sorted according to decreasing similarity;
finally, the top N of the scoring list is taken as the current user U j Generating a government service push list L with the length of N;
5. repeat 4 until the natural people in each cluster get pushed.
Through the technical scheme, the government service object (natural person) situation big data model is built, the potentially required government service is mined according to the situation of the natural person, and the government department is helped to accurately lock the service object. Not only can the government demographic data application model be innovated, but also the transformation of government forms into service forms can be facilitated. And converging government population data based on the natural person situation big data model, and promoting government population data application to expand from a small data primary application mode which can only meet single-system application to a big data deep application mode which can meet multi-system comprehensive application. The situation clustering and government service pushing method is constructed based on the big natural person situation data, and government departments can provide accurate personalized, refined and mobile services for the public and technical support for pushing government forms to change from production forms to service forms.
The preferred embodiments of the present invention have been described in detail above with reference to the accompanying drawings, but the present invention is not limited to the specific details of the above embodiments, and various simple modifications can be made to the technical solution of the present invention within the scope of the technical concept of the present invention, and all the simple modifications belong to the protection scope of the present invention.
In addition, the specific features described in the above embodiments may be combined in any suitable manner, and in order to avoid unnecessary repetition, various possible combinations are not described further.
Moreover, any combination of the various embodiments of the invention can be made without departing from the spirit of the invention, which should also be considered as disclosed herein.

Claims (7)

1. The utility model provides a government affair service pushing method of situation big data based on city big data, which is characterized by comprising the following steps:
step a, constructing a natural person situation data model, and describing the social activity rule, individual business characteristics and the social interaction state of a single natural person in an omnibearing way;
step b, pushing situation cluster government affair service; wherein, the liquid crystal display device comprises a liquid crystal display device,
step a comprises:
step a1, constructing a basic attribute situation of a natural person;
step a2, constructing a natural human life event situation;
step a3, constructing a social relationship situation of natural people;
step b comprises:
step b1, calculating a situation vector;
step b2, clustering the situation;
step b3, pushing government service; wherein, the liquid crystal display device comprises a liquid crystal display device,
in step b1, the government service object has basic attribute context (R 1 ) Life event context (R) 2 ) And social relationship context (R) 3 ) Context vector R mi ＝{R 1 mi ,R 2 mi ,R 3 mi ,...,R l mi ' representing a service object U m For the situation index R i Is the selection of vector R nj ＝{R 1 nj ,R 2 nj ,R 3 nj ,...,R l nj U is represented by } n Contextual index data R of (2) j The distance between the two context vectors is calculated as follows:
obtaining natural people situation vectors after situation calculation, wherein each natural person corresponds to one situation vector, and then generating a user-project-situation three-dimensional matrix model according to an original user-project scoring matrix, wherein the matrix model comprises 3 types of vectors which are respectively a user vector, a government service project vector and a situation vector;
in the step b2, modeling is carried out on the situation of the natural person by adopting a clustering algorithm based on K-means; the clustering algorithm based on K-means needs to define the number of clustering sets to be formed, namely the value of K in advance, K objects are randomly selected to serve as the centroids of the clusters, the similarity between each sample and the centroids is calculated for the rest situation vectors, the samples are distributed to the clustering sets closest to the centroids, and then the centroids are updated for the clustering sets distributed with new samples; distributing all samples to finish natural person clustering to obtain K similar user clusters; the context clustering execution step comprises the following steps:
(1) Setting the number K of classifications;
(2) Selecting K different objects from the dataset S as initial centroids { b } 1 ,b 2 ,...,b k }；
(3) Calculating a context distance d between the context vector i and the centroid b for any non-accessed context vector i in the dataset S;
(4) Classifying the context vector i into a cluster set C closest to the context vector i;
(5) Re-calculating the average value of all the objects in the K clustering sets as a new centroid value;
(6) Updating the centroid value b in the changed set C;
(7) Repeating steps 3 to 6 until all centroids { b } 1 ,b 2 ,...,b k No longer changes;
(8) Output context cluster set { C 1 ,C 2 ,...,C k } and corresponding centroid value { b } 1 ,b 2 ,...,b k }；
In the step b3, K similar clusters are obtained according to a K-means clustering algorithm, in order to reduce the computational complexity and obtain better pushing accuracy, in an original user-project matrix, corresponding sub-user-project matrixes are obtained by searching according to the information of the K clusters, and then a UserCF recommendation algorithm is directly applied to the sub-matrixes to push Top-N; setting a scoring threshold P, wherein the score of the natural person is higher than the scoring threshold P, and the natural person possibly needs the government service project, or else the natural person possibly does not need the government service project; the execution steps are as follows:
(1) Defining push list length N, scoring threshold P and similarity numberQuantity M, context cluster set { C 1 ,C 2 ,...,C k -an original user-project matrix R;
(2) Selecting a context cluster { C } 1 ,C 2 ,...,C k Any unvisited set C in } i Searching the corresponding user-project subset R in the original user-project matrix R i ；
(3) Repeating 2 until all situation cluster clusters { C 1 ,C 2 ,...,C k Corresponding user-item subset { R } 1 ,R 2 ,...,R k }；
(4) For user-item subset R i Applying a collaborative filtering recommendation algorithm and predicting a deletion score;
first, for the cluster C i User U in (B) j Find its corresponding government service item set I j ；
Second, in item set I j The government affair service items with the scores Ratings more than or equal to P are screened to obtain government affair service items possibly needed by the government affair service items;
then, calculating the similarity sim between the users, and selecting M similarity neighbors { u }, wherein M is the same as M 1 ,u 2 ,...,u M }；
Next, the current user U is interested in similar neighbors j Government service item p with no score is calculated U j Pearson similarity to p, and in aggregate RI j The steps are sorted according to decreasing similarity;
finally, the top N of the scoring list is taken as the current user U j Generating a government service push list L with the length of N;
(5) Repeating (4) until the natural people in each cluster are pushed.
2. The government affair service pushing method based on the situation big data of the city big data according to claim 1, wherein the basic attribute situation in the step a1 comprises effective identification reflecting the birth and the social attribution of the natural person, an index reflecting the natural humanization quality, an index reflecting the employment situation of the natural person and an index reflecting the knowledge and skill level of the natural person in a certain professional activity.
3. The government service pushing method of contextual big data based on urban big data according to claim 2, wherein step a1 comprises:
firstly, extracting relevant data catalogs of public security bureaus, personal social bureaus and government departments of civil government bureaus, and forming natural person basic information, passport information, driving license information, taiwan pass information, kong and Australian pass information, social security card information, cultural degree information, work unit information, practitioner qualification information, practice qualification information, professional technical job qualification information, professional skill information and religious staff information after multi-table association;
secondly, regarding the multi-source data item in the related information of the natural person, taking the person with the highest weighted score of accuracy and updating time as an adoption object; then connecting to a local MySQL database through a pymysql technology, and storing the regulated data into the local database;
finally, predicting the basic attribute which cannot be obtained through the step a1 by adopting an attribute reasoning method; after acquiring known attribute data affecting unknown attributes, constructing a graph according to a certain algorithm, and then reasoning based on prior probability; calculating influence values among attribute values when constructing an attribute graph, and determining the sequence of attribute influence on the influence sequence among the attributes; wherein, the liquid crystal display device comprises a liquid crystal display device,
the steps required for unknown attribute reasoning include: calculating an influence value between attribute values of the attributes, calculating an influence value between the attributes, and calculating a condition value between the attributes.
4. The government affair service pushing method based on situation big data of city big data according to claim 1, wherein the situation of the personal event in step a2 includes various business events or activities that the natural person participates in during the life cycle.
5. The government service pushing method of contextual big data based on urban big data according to claim 4, wherein step a2 comprises:
firstly, constructing a life event data model dictionary (key: event type, value: [ business event 1, business event 2, … …, business event n ]), wherein each business event is composed of a plurality of data items (D1, the..once again, DN);
secondly, extracting and regulating data related to natural human life events of various government departments, connecting the data to a local MySQL database through a pymysql technology, and storing the regulated data into the local database;
then, calculating text similarity for the data stored in the substep a2 by using word vectors, generating word vectors by using Glove model, word2vec model and Bert model training, calculating similarity of business item word vectors, setting a specified threshold value, and fusing similar business items of a plurality of departments to form a corresponding life item data set T;
and finally, organizing the data in the data set T by using a life event data model dictionary so as to realize the fusion and standardization of the natural life event multi-source data.
6. The government service pushing method according to claim 1, wherein the social relationship context in step a3 includes a person-person relationship reflecting various person-person relationships established by natural persons during social activities, a person-ground relationship reflecting and established by natural person due to living, working, learning reasons belonging to certain places, and a person-object relationship reflecting and established by physical or intangible assets possessed by natural persons during the whole life cycle.
7. The government service pushing method of contextual big data based on urban big data according to claim 6, wherein step a3 comprises:
firstly, defining a plurality of entity objects of natural people, places, motor vehicles, houses, lands and intellectual property rights; each natural person node may establish a plurality of relationships with a plurality of nodes, wherein the plurality of nodes includes natural persons, places, and items; adding attributes for each entity object, wherein the natural person attributes are basic attributes constructed in the step a1, the place attributes comprise place names, place types and roles of persons in places, and the object attributes comprise object names, object types and possession times; wherein a single node may contain multiple attribute descriptions that characterize its physical characteristics;
secondly, defining a relation and an event, and adding the relation or the event between entity objects; wherein, the comprehensive relationship of relatives, neighbors or colleagues is added between individuals, the belonging relationship is added between individuals and organizations, and the possession relationship is added between individuals and certificates; each relationship comprises a start node and a stop node; the attributes of the relationship include relationship type, relationship establishment time and relationship release time;
then, after the definition of the entity, the attribute, the relation and the event is finished, extracting the existing various data through a data extraction tool, and finally constructing and forming a set of complete natural human social relation knowledge graph through entity alignment and attribute filling of the extracted knowledge;
and finally, establishing an index by adopting common fields of the identification card number, the property right number, the land use right number and the motor vehicle number plate number, and optimizing the inquiry performance of the social relation diagram database.
CN202011006238.7A 2020-09-23 2020-09-23 Government service pushing method of situation big data based on city big data Active CN112132727B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011006238.7A CN112132727B (en) 2020-09-23 2020-09-23 Government service pushing method of situation big data based on city big data

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011006238.7A CN112132727B (en) 2020-09-23 2020-09-23 Government service pushing method of situation big data based on city big data

Publications (2)

Publication Number Publication Date
CN112132727A CN112132727A (en) 2020-12-25
CN112132727B true CN112132727B (en) 2023-08-18

Family

ID=73842543

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011006238.7A Active CN112132727B (en) 2020-09-23 2020-09-23 Government service pushing method of situation big data based on city big data

Country Status (1)

Country Link
CN (1) CN112132727B (en)

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2010128927A (en) * 2008-11-28 2010-06-10 Ntt Docomo Inc Apparatus and method for generating recommendation information
CN102982101A (en) * 2012-11-05 2013-03-20 西安工程大学 Method of network community user push-service based on user situation body
CN104361023A (en) * 2014-10-22 2015-02-18 浙江中烟工业有限责任公司 Context-awareness mobile terminal tobacco information push method
EP3070661A1 (en) * 2015-03-20 2016-09-21 Tata Consultancy Services Limited System and method for providing context driven hyper-personalized recommendation
CN107169059A (en) * 2017-04-28 2017-09-15 北京理工大学 A kind of knowledge based on similar variable precision rough set model pushes Rules extraction method
CN108109043A (en) * 2017-12-22 2018-06-01 重庆邮电大学 A kind of commending system reduces the method for repeating to recommend
CN109255586A (en) * 2018-08-24 2019-01-22 安徽讯飞智能科技有限公司 A kind of online personalized recommendation method that E-Governance Oriented is handled affairs
CN110766208A (en) * 2019-10-09 2020-02-07 中电科新型智慧城市研究院有限公司 Government affair service demand prediction method based on social group behaviors

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11017038B2 (en) * 2017-09-29 2021-05-25 International Business Machines Corporation Identification and evaluation white space target entity for transaction operations
JP6965206B2 (en) * 2018-05-09 2021-11-10 株式会社東芝 Clustering device, clustering method and program

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2010128927A (en) * 2008-11-28 2010-06-10 Ntt Docomo Inc Apparatus and method for generating recommendation information
CN102982101A (en) * 2012-11-05 2013-03-20 西安工程大学 Method of network community user push-service based on user situation body
CN104361023A (en) * 2014-10-22 2015-02-18 浙江中烟工业有限责任公司 Context-awareness mobile terminal tobacco information push method
EP3070661A1 (en) * 2015-03-20 2016-09-21 Tata Consultancy Services Limited System and method for providing context driven hyper-personalized recommendation
CN107169059A (en) * 2017-04-28 2017-09-15 北京理工大学 A kind of knowledge based on similar variable precision rough set model pushes Rules extraction method
CN108109043A (en) * 2017-12-22 2018-06-01 重庆邮电大学 A kind of commending system reduces the method for repeating to recommend
CN109255586A (en) * 2018-08-24 2019-01-22 安徽讯飞智能科技有限公司 A kind of online personalized recommendation method that E-Governance Oriented is handled affairs
CN110766208A (en) * 2019-10-09 2020-02-07 中电科新型智慧城市研究院有限公司 Government affair service demand prediction method based on social group behaviors

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
融合SOM功能聚类与DeepFM质量预测的API服务推荐方法;曹步清;肖巧翔;张祥平;刘建勋;;计算机学报(第06期);209-225 *

Also Published As

Publication number Publication date
CN112132727A (en) 2020-12-25

Similar Documents

Publication Publication Date Title
US8990198B2 (en) Method and system for computerized management of related data records
CN109255586B (en) Online personalized recommendation method for e-government affairs handling
KR101009830B1 (en) Compatibility scoring of users in a social network
US8856229B2 (en) System and method for social networking
US8874616B1 (en) Method and apparatus for fusion of multi-modal interaction data
US20100082356A1 (en) System and method for recommending personalized career paths
CN108647800B (en) Online social network user missing attribute prediction method based on node embedding
CN110765117A (en) Fraud identification method and device, electronic equipment and computer-readable storage medium
EP2504779A2 (en) Automated generation of ontologies
CN113722611A (en) Method, device and equipment for recommending government affair service and computer readable storage medium
US20180260446A1 (en) System and method for building statistical predictive models using automated insights
CN106326438A (en) Personnel information correlating method
CN105493082A (en) Person search utilizing entity expansion
JP2017199355A (en) Recommendation generation
CN113190593A (en) Search recommendation method based on digital human knowledge graph
Chang et al. Classification and visualization of the social science network by the minimum span clustering method
Garha et al. Indian diaspora population and space: national register, UN Global Migration Database and Big Data
CN110008411A (en) It is a kind of to be registered the deep learning point of interest recommended method of sparse matrix based on user
CN112182243B (en) Method, terminal and storage medium for constructing knowledge graph based on entity recognition model
CN112132727B (en) Government service pushing method of situation big data based on city big data
CN110795640B (en) Self-adaptive group recommendation method for compensating group member difference
CN109885797B (en) Relational network construction method based on multi-identity space mapping
CN110543601B (en) Method and system for recommending context-aware interest points based on intelligent set
CN114491296B (en) Proposal affiliate recommendation method, system, computer device and readable storage medium
Tossavainen et al. Implementing a system enabling open innovation by sharing public goals based on linked open data

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

Address after: Building 5, Wuhu Science and Technology Industrial Park, Wuhu City, Anhui Province, 241000

Applicant after: Yangtze River delta information intelligence Innovation Research Institute

Address before: 241000 Wuhu Intelligent Collaborative Innovation Center

Applicant before: Institute of smart city University of science and technology of China (Wuhu)

CB02 Change of applicant information
GR01 Patent grant
GR01 Patent grant