CN113010578A

CN113010578A - Community data analysis method and device, community intelligent interaction platform and storage medium

Info

Publication number: CN113010578A
Application number: CN202110303133.6A
Authority: CN
Inventors: 莫海彤; 刘玉亭
Original assignee: South China University of Technology SCUT
Current assignee: South China University of Technology SCUT
Priority date: 2021-03-22
Filing date: 2021-03-22
Publication date: 2021-06-22
Anticipated expiration: 2041-03-22
Also published as: CN113010578B

Abstract

The invention discloses a community data analysis method, a device, a community intelligent interaction platform and a storage medium, wherein the method comprises the following steps: acquiring space-time trajectory data and personal information data of community residents, binding the space-time trajectory data and the personal information data with basic geographic block data, and identifying each activity of the community residents into different types; recording the daily activities of each resident in the community through a sequence consisting of different activity types; carrying out sequence analysis on the activities of residents in each community to obtain basic behavior patterns of residents in different communities; and mining social and economic attributes of residents related to various behavior modes according to the personal information data of the residents. The invention is beneficial to improving the quality and efficiency of primary community treatment, and the intelligent method and the cooperative mechanism of community treatment are clear, thereby promoting the construction and the perfection of a community co-construction and co-treatment sharing system.

Description

Community data analysis method and device, community intelligent interaction platform and storage medium

Technical Field

The invention relates to a community data analysis method and device, a community intelligent interaction platform and a storage medium, and belongs to the field of digital management and community development planning.

Background

The community is a foundation stone for social governance, and promotion of community improvement is top-level design guidance for community planning in a new era. The construction of the complete community is also classified into the working key points of the national housing and urban and rural construction department in 2020, and the emphasis is placed on the community construction on the basis of complementing public service resource short boards, so that the governing attribute of the community is further enhanced, and the ever-increasing beautiful living needs of community residents are better adapted.

Aiming at the construction and popularization of a complete community and community co-construction co-treatment shared treatment system, urban and rural communities in various regions of China have successively developed good environment and happy life co-association activities, and go deep into the primary community to develop specific activities such as public interview, questionnaire survey, communication and discussion, and experts and scholars also provide a lot of beneficial guidance for how the co-association activities should be developed and implemented. However, due to the shortage of financial, material and human resources, the covered community is still very limited, and it is still difficult to form a long-term operation mechanism. The primary community still faces outstanding management difficulty, and needs to complement community facilities, resources and treatment capacity short boards to intelligently, efficiently and systematically improve the treatment level of the primary community.

Information communication technology has deeply penetrated into various fields of national governance, and a digital governance mode based on the information communication technology has become a basic characteristic of a national governance system and modernization of governance capability, but at the community level, methods and mechanisms for governing digitization, refinement and intellectualization still need to be further mined.

Disclosure of Invention

In order to solve the defects of the prior art, the invention provides a community data analysis method, a device, a community intelligent interaction platform and a storage medium, wherein a big data technology platform is used for realizing specialized collection, analysis and processing of mass community data resources, obtaining basic behavior patterns of residents in different communities, mining social and economic attributes of residents associated with various behavior patterns, calculating the accessibility of community life circle facilities, analyzing the action of each main body in a community management network, and further providing the community intelligent interaction platform for information exchange and decision interaction jointly participated by multiple main bodies such as governments, enterprises, expert scholars, community residents, social organizations and the like. The method is beneficial to improving the quality and efficiency of domestic basic community treatment, the intelligent method and the cooperative mechanism of community treatment are clear, and the construction and the perfection of a complete community and co-construction co-treatment sharing system are deeply promoted.

The first purpose of the invention is to provide a community data analysis method.

A second object of the present invention is to provide a community data analysis device.

The third purpose of the invention is to provide a community intelligent interaction platform.

It is a fourth object of the present invention to provide a storage medium.

The first purpose of the invention can be achieved by adopting the following technical scheme:

a method of community data analysis, the method comprising:

acquiring space-time trajectory data and personal information data of community residents, binding the space-time trajectory data and the personal information data with basic geographic block data, and identifying each activity of the community residents into different types;

recording the daily activities of each resident in the community through a sequence consisting of different activity types;

carrying out sequence analysis on the activities of residents in each community to obtain basic behavior patterns of residents in different communities;

and mining social and economic attributes of residents related to various behavior modes according to the personal information data of the residents.

Further, the performing sequence analysis on the activities of residents in each community to obtain the basic behavior patterns of residents in different communities specifically includes:

comparing the sequences of residents in the community;

classifying according to sequence similarity, wherein each sequence classification represents a behavior mode;

and comparing the sequences of the residents in the communities to obtain the basic behavior patterns of the residents in different communities.

Further, the comparing the sequences of the residents in the community specifically comprises:

constructing an assignment function: if the characters corresponding to the two sequences are matched, assigning a score of 1, and if the characters are mismatched, assigning a score of 0; gap appears in any sequence chain, and is marked as gap penalty d;

and (3) aligning the two sequences: when two sequences are aligned, a Needleman-Wunsch algorithm is used for global alignment, a Smith-Waterman algorithm is used for local alignment, the two algorithms are used for alignment each time, and one algorithm with the optimal matching result is selected to complete sequence alignment.

Further, the classifying according to the sequence similarity, each sequence classification representing a behavior pattern, specifically includes:

in the global alignment, H_ijThe calculation formula of (2) is as follows:

in the local alignment, H_ijThe calculation formula of (2) is as follows:

the similarity score of the two sequences is marked as S, and the calculation formula is as follows:

S＝H_ijmax

according to the S value, sequences with the highest pairwise comparison score are classified into the same class, and each sequence class represents a resident behavior pattern; wherein H_ijDenotes the similarity of the matrix cells in the ith row and the jth column, W_ijRepresenting the similarity weight at row i and column j, with d representing a gap penalty.

Further, the obtaining of the basic behavior patterns of the residents in different communities according to the comparison result of the sequences of the residents in the communities specifically includes:

and performing multi-sequence comparison analysis on the plurality of sequences, constructing an evolutionary tree by using a maximum likelihood method on the comparison result, extracting typical sequences of each branch in the evolutionary tree, and analyzing to obtain basic behavior patterns of residents in different communities.

Further, the mining of social and economic attributes of residents associated with various behavior patterns according to the personal information data of the residents specifically includes:

and acquiring social and economic attributes of residents from the personal information data of the residents, coding the social and economic attributes of the residents, mining frequent items of the social and economic attributes of the residents in each sequence classification, and acquiring high-frequency social and economic attributes associated with various behavior patterns.

Further, the method further comprises:

and (4) according to the resident behavior mode of each community, the service facility types commonly used by residents of each community are deduced, and the accessibility of the community life circle facility is calculated.

Further, the method further comprises:

obtaining attention information and comment information of a multi-element main body in a community communication forum of an interactive platform, and analyzing the effect of each main body in a community management network by constructing a relationship network of the multi-element main body in community management; the method comprises the following steps of constructing a relationship network of a plurality of main bodies in community governance, analyzing the effect of each main body in the community governance network, and specifically comprising the following steps:

and establishing a relation network of the main bodies in community management, calculating the degree centrality, the approach centrality and the intermediary centrality of each node in the network, and analyzing the effect of the multi-element main bodies in the community management network.

The second purpose of the invention can be achieved by adopting the following technical scheme:

a community data analysis device is applied to a cloud server, and comprises:

the system comprises an acquisition unit, a storage unit and a processing unit, wherein the acquisition unit is used for acquiring space-time trajectory data and personal information data of community residents, binding the space-time trajectory data and the personal information data with basic geographic block data, and identifying each activity of the community residents into different types;

the sequence unit is used for recording the daily activities of each resident in the community through a sequence consisting of different activity types;

the analysis unit is used for carrying out sequence analysis on the activities of residents in various communities to obtain basic behavior patterns of residents in different communities;

and the association unit is used for mining the social and economic attributes of the residents associated with various behavior modes according to the personal information data of the residents.

The third purpose of the invention can be achieved by adopting the following technical scheme:

the utility model provides an interactive platform of community's intelligence, the platform includes user side, staff end and cloud ware, user side, staff end and cloud ware are two liang of connections respectively, user side, staff end and cloud ware specifically include:

the user side is used for inputting information and sending the input information to the staff side;

the staff side is used for auditing, registering and filing the information sent by the user side, returning the audited information to the user side and sending the audited information to the cloud server;

the cloud server is used for executing the community data analysis method.

The fourth purpose of the invention can be achieved by adopting the following technical scheme:

a storage medium stores a program that, when executed by a processor, implements the community data analysis method described above.

Compared with the prior art, the invention has the following beneficial effects:

the method comprises the steps of obtaining time-space trajectory data and personal information data of community residents, and performing sequence analysis to obtain basic behavior patterns and social economic attributes of different community residents, wherein the method can be used for assisting planning practitioners to perform planning decisions of community public service facilities and providing decision references for layout and positioning of commercial service facilities for related enterprises; the service facility types commonly used by residents of all communities are deduced backwards through the resident behavior patterns of all communities, and the accessibility of the community life circle facilities is calculated by using an accumulative chance method and can be used for evaluating and designing the overall accessibility of the facilities of all communities; by constructing a relationship network of the multivariate main bodies in the community treatment, the network relationship of benefit stakeholders such as governments, enterprises, social organizations, experts and scholars, residents, enterprises and the like in the community treatment can be observed, and the role of the multivariate main bodies in the treatment network can be quantitatively measured through calculation; the community intelligent platform collects news, comments and complaint information of each network platform about each community in real time, extracts useful information and is used for guiding improvement and promotion of community living environment quality.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the structures shown in the drawings without creative efforts.

Fig. 1 is a structural block diagram of a community intelligent interaction platform according to embodiment 1 of the present invention.

Fig. 2 is a flowchart of a community data analysis method according to embodiment 1 of the present invention.

FIG. 3 is a graph showing the alignment results of two sequences in the global alignment algorithm with better global alignment results in example 1 of the present invention.

FIG. 4 is a diagram showing the alignment results of two sequences in the local alignment algorithm with better global alignment results in example 1 of the present invention.

FIG. 5 is a diagram showing the alignment results of two sequences in the global alignment algorithm of example 1.

FIG. 6 is a diagram showing the alignment results of two sequences in the global alignment algorithm of example 1.

FIG. 7 shows S in example 1 of the present invention_kFP-tree diagram of (a).

FIG. 8 is a diagram of a final FP tree as a whole in accordance with embodiment 1 of the present invention.

FIG. 9 is a diagram of the FP subtree of c3 in embodiment 1.

FIG. 10 is a diagram of the FP subtree of b2 in embodiment 1 of the present invention.

Fig. 11 is a block diagram showing a configuration of a community data analysis apparatus according to embodiment 2 of the present invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer and more complete, the technical solutions in the embodiments of the present invention will be described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some embodiments of the present invention, but not all embodiments, and all other embodiments obtained by a person of ordinary skill in the art without creative efforts based on the embodiments of the present invention belong to the protection scope of the present invention.

Example 1:

this embodiment provides an intelligent interactive platform of community, as shown in fig. 1, this platform is built based on little letter applet APP/website, cloud server and multisource heterogeneous data, and it includes user side, staff end and cloud server, and the user side is connected with the staff end, the cloud server is connected with user side, staff end respectively, and the user side includes information registration module, community service module and supervision module, and the staff end includes authentication module, and the cloud server includes community service module, data service module and supervision module, and the concrete description of each module is as follows:

information registration module

The user login/registration interface is an interface for registering information of residents, enterprises and social organizations, etc., the residents need to fill in personal information such as identity information, education level, income level, marriage and childbirth conditions, and the enterprises (such as property management companies) and the social organizations (such as endowment service stations, staff's homes, and compulsory organizations, etc.) need to register various information and project libraries, business data, etc. of the companies/organizations.

Authentication module

The staff examines the registered resident information on the background, and performs qualification examination, information registration and filing on enterprises, social organizations and employees thereof; the staff mainly refers to persons who have a job in related government departments, street offices, living committees and the like.

Third, community service module

Clicking 'community service' in the platform can jump to the page, mainly comprising five parts of community information display, project application and management, activity registration/service application, community communication forum and community management, and other plates can be continuously built in the platform.

Community information display: the system comprises information such as relevant policies and planning files of communities, enterprise/social organization data, community public service facilities, public open spaces and the like, and comprises spatial positions, use and maintenance conditions and the like of the community.

(II) project application and management: the government shows policy standards, rules and budgets of purchasing social services and supplementing with prizes by the government on the page, and opens a way for submitting related community projects by streets, enterprises, community organizations, residents and the like. The results of project declaration and information of project operation condition, financial income, social benefit and the like are displayed/disclosed in the interface.

(III) activity registration/service application: the page shows the content introduction of various community activities and services and the holding time and other information, and opens the entrance for residents to apply for activities/services or to act as volunteers. The community types include community micro-improvement, community farms, artistic activities, exchange discussions, and the like, and the community service types include career care, early education halls, and the like.

(IV) community communication forum: the user can access the page after logging in. The realization of the communication function adopts a mode of network forum (Bulletin Board System, BBS) and group chat, specifically comprises discussion groups in community enterprises and residents, and all parties can post or reply posts on the forum; the built-in page surveys the satisfaction degree of governments, enterprises, social organizations and residents on various works of the community, and can perform opinion collection activities such as community affair voting and the like; this page also opens the interface for complaints and reports.

(V) community management: the method comprises two parts of security protection and property management. The security board comprises a closed circuit monitoring system networking management, a parking space management, a fire control management, an entrance guard attendant information display and the like. The property management plate comprises property, water, electricity, gas and other expenses payment, maintenance declaration, consultation complaint, neighborhood mediation and the like.

In addition, other plates can be arranged in the community service module, such as community resident cognitive map investigation, community facility and public space management, or exclusive plates can be arranged for important community activities such as community micro-transformation and co-construction.

Fourth, data service module

Clicking 'data service' in the platform can skip to the page, and the data service module mainly comprises three parts of data acquisition and processing, data sharing and model analysis.

Data acquisition and processing

1. The data source mainly comprises:

(1) official base database:

accessing basic databases of all levels of governments, street offices, living parties, places of delivery, planning and designing houses and the like in the past years, wherein the basic databases comprise a geographic information base, a legal person base, a project base, a population base, a community planning file, registration information of a rental house, monitoring and stationing information, crime records, hospitalizing records, registration information of a student status, a statistical yearbook, statistical communique data, community house attributes and the like;

(2) network start database:

community material space attributes: and accessing network map data. The POI and AOI information under each category such as 'business housing' in the original network map (such as an API of a Baidu map and a Gade map) is crawled by using requests, pandas, json libraries and related codes of python, and data of a Point of Interest (POI) and a vector boundary (AOI) thereof, roads, greenbelts, water systems and the like of urban and rural communities and various facilities are extracted.

The resident space-time trajectory: and (3) extracting the track data of the residents by using the mobile phone signaling data (such as Baidu map comet data and Unicom intelligent footprints).

Social sentiment and folk meaning: collecting news, comments/complaints information of each network platform (such as a people network, a Xinhua community, black cat complaints, a Homing, a Baidu post bar and the like) about each community in real time;

(3) interactive platform data:

the social and economic attributes of residents are as follows: the information registration module can collect personal information such as identity information, education level, income level, marriage and childbirth conditions and the like of residents.

Basic information, project libraries, business data and the like of enterprises (such as property and various living service industries) and social organizations (such as endowment service stations, staff families, and labor organizations) are also collected through the information registration module.

Satisfaction of each party: and the satisfaction degree of governments, residents, enterprises and social organizations on the development of various community works is obtained through the interactive platform.

Because the acquired data structures are different, especially the information of a plurality of original data is numerous and complicated, various data and information need to be cleaned, processed and processed to fully mine the data value.

2. The data processing mainly comprises the following steps:

(1) spatial attributes of community materials

After the POI and AOI data crawled by the network map are subjected to duplicate removal and invalid information elimination, the names, vector boundaries, longitude and latitude, and vector boundaries of roads, water systems and green lands of various communities and facilities (such as categories of catering, shopping, company enterprises, transportation facility services and the like) are extracted.

(2) Resident identity information and trajectory data

The basic geographic block information is integrated for standby, then the original mobile phone signaling data is processed, and the real resident and trip information of the user is restored based on the noise reduction calibration technology. And selecting a Spark cluster data processing platform, storing the cleaned mobile phone signaling data and basic map information in the Spark cluster data processing platform, matching the topological relation between the base station cell and the geographic area AOI, and projecting the user track data to a geographic entity. In addition, the mobile phone signaling data is bound with the identity card information of the residents, and can be associated with the personal information of the residents collected in the information grade module according to the names, so that the personal economic attribute data such as the sex, the age, the education level and the income level of the residents and the travel track data are obtained.

(3) Community related enterprise and social organization information

And (3) registering enterprises and social organizations of each community and related workers in a classified manner, and performing classified filing on projects related to the construction and management of each enterprise/social organization and the community.

(4) News reports, comments, complaints, etc

Because of the lack of an official community communication platform, community owners/tenants have comments and complaint information of residents on communities in WeChat groups, black cat complaints, Homing, Baidu posts, Xinlang microblogs and the like, and various network media such as people's network and Xinhua community also have related information of various communities. Relevant information of the community is collected from the website through a web crawler means, the text is detected through python programming, junk texts such as yellow-related texts and advertisements are removed, and the remaining texts are reserved for later use.

(5) Data information relating to personal privacy information and business secrets

The platform needs to process classified data information related to personal privacy information and business confidentiality, for example, sensitive information such as names, identification numbers, home addresses, income and the like needs to be protected in a targeted manner, so that the safety protection capability of the data information is improved.

(II) data sharing

Different data are opened and shared in the face of different users, and partial data content allows the users to modify, increase and decrease. The user types comprise governments, technical supporters (such as scientific research institutions, planning and design institutions and the like), social organizations, enterprises, community residents and the like, wherein desensitization processing is required for data information which relates to personal and commercial confidentiality. Besides, it also provides various forms, specification file downloads, and various working manuals and example displays of community activities.

(III) analysis of the model

And basic data are stored in the cloud server for background analysts to perform model operation analysis.

As shown in fig. 2, the present embodiment provides a community data analysis method, which includes a resident activity sequence analysis, a community life circle facility reachability analysis, and a community governance network analysis, and specifically includes the following steps:

s201, acquiring space-time trajectory data and personal information data of community residents, binding the space-time trajectory data and the personal information data with basic geographic block data, and identifying each activity of the community residents into different types.

Further, the step S201 specifically includes:

and S2011, integrating the basic geographic zone information.

After the POI and AOI data crawled by the network map are subjected to duplicate removal and invalid information elimination, the names, vector boundaries, longitude and latitude, and vector boundaries of roads, water systems and greenbelts of various communities and facilities such as catering, shopping, company enterprises, transportation facility services and the like are extracted and integrated.

S2012, processing the original mobile phone signaling data, and restoring the real resident and trip information of the user based on the noise reduction calibration technology.

S2013, selecting a Spark cluster data processing platform, storing the cleaned mobile phone signaling data and basic map block information in the Spark cluster data processing platform, matching the topological relation between the base station cell and the geographic block AOI, and projecting the user track data to a geographic entity. The mobile phone signaling data is bound with the identity card information of residents, and can be correlated according to the personal information of the residents collected in the information level module, so that the personal economic attribute data of the residents, such as gender, age, education level, income level and the like, and the travel track data are obtained.

S2014, based on the space-time trajectory data of residents and the collected personal information data, the data are bound with basic geographic block data, and accordingly, all activities of the residents can be identified as nine types including home (A), work (B), study (C), medical treatment (D), shopping (E), leisure exercise (F), sightseeing and tourism (G), outgoing and office (bank, post office, library and the like) (H) and other types (I). The identification rules of the residence and the work/school place need to be added with the following two rules:

(1) recording the longest retention time in 9:00 to 17:00 as a working place/school place, and recording the longest retention time in 21:00 to the next day of 8:00 as a residence place;

(2) and the condition that the number of working days exceeds 10 days in one month is satisfied.

S202, recording the daily activities of each resident in the community through a sequence consisting of different activity types.

And respectively recording the activity types of residents in the community as A-I, and recording the daily activity of each resident by using a sequence formed by English characters. Such as: a (at home) -B (at work) -H (out at work) -A (at home) -F (leisure exercise).

S203, carrying out sequence analysis on the activities of residents in each community to obtain basic behavior patterns of residents in different communities.

Further, step S203 specifically includes:

s2031, comparing the sequences of the residents in the community.

Comparing the sequences of all residents by using a sequence comparison algorithm through python programming, wherein the sequence comparison algorithm specifically comprises the following steps:

(1) constructing valuation functions

If the characters corresponding to the two sequences are matched, assigning a score of 1; assigning a score of 0 if the number of the codes is mismatched; gap appears in either sequence chain and is marked as gap penalty d, where a score of-1 is taken. The actual values of the above matches, mismatches and gap penalties can all be adjusted as required. Let the similarity weight of ith row and jth column be W_ijThe formula is as follows:

(2) alignment of two sequences

H_ijRepresenting the similarity of the matrix cells in row i and column j, and d represents a gap penalty. Wherein, the global comparison uses a Needleman-Wunsch (NW) algorithm to emphasize the identification of the matching of the activities of residents all day long; local comparison uses a Smith-Waterman (SW) algorithm to emphasize the identification of activity matching of resident local time periods; since different two sequences may have different effects using the two methods, the two algorithms are used for comparison each time, and the matching result is selectedThe most preferred one accomplishes the sequence alignment.

In the global alignment, H_ijThe calculation formula of (2) is as follows:

in the local alignment, H_ijThe calculation formula of (2) is as follows:

A. a scenario with better global comparison results:

assuming two sequences, ADAF and ABHAF respectively, GAP- ｃA-D- ｃA-F on the horizontal axis and GAP- ｃA-B-H- ｃA-F on the vertical axis, the values of each bin in the first row and first column are 0 minus ｃA GAP penalty (1 in this example), the values of each other bin can be derived from three directions, top, left, oblique top left. If the two letters of the grid can correspond to each other, taking a value +1 at the upper left oblique side, and if the two letters of the grid do not correspond to each other, taking a value +0 at the upper left oblique side; the upper value is taken from above minus a gap penalty (-1 in this example) and the left value-1 is also taken from the left. The value of the grid is taken to be the largest of the values in the three directions. When a local comparison method is used, if the maximum value is a negative value, 0 is taken; when the global comparison method is used, the original value is adopted no matter whether the maximum value is a negative value or not, and 0 is not required to be adopted.

In the comparison of the two sequences, the maximum value of the last column is found, the reverse deduction is carried out, the maximum values are taken along the path, and then the optimal comparison path is found.

If the global alignment NW algorithm is used, the alignment of the two sequences is shown in fig. 3, and there are three sets of values that can be corresponded.

If the local alignment SW algorithm is used, the alignment result of the two sequences is shown in FIG. 4, only two sets of values can correspond to each other, and the two sets of sequences are more suitable to use the global matching method.

B. Scene with better local comparison result:

assuming that the two sequences are AFAC and GHAEA, respectively, if a global alignment NW algorithm is used, the alignment results of the two sequences are shown in fig. 5, and a set of values can correspond to each other; if the local alignment SW algorithm is used, the alignment of the two sequences is shown in FIG. 6, and there are two sets of values that can be mapped.

The two groups of sequences are preferably aligned locally, which is more beneficial to capture the portions of the two sequences that are more closely matched.

S2032, classifying according to sequence similarity, wherein each sequence classification represents a behavior mode.

Classifying according to the sequence similarity, and forming a group by the sequences with the maximum similarity; each sequence class represents a pattern of behavior;

S＝H_ijmax

and according to the S value, two sequences are aligned, the sequences with the highest scores are classified into the same class, and each sequence class represents a resident behavior pattern. Such as "inhabitation-work-going out to do work-shopping-inhabitation", "inhabitation-leisure exercise-hospitalization-shopping-inhabitation", etc.

S2033, comparing the sequences of the residents in the communities to obtain the basic behavior patterns of the residents in different communities.

And (3) introducing the multiple sequences into MEGA software, performing multi-sequence alignment analysis, using the Clustalw aligned sequences, and exporting the analysis result into a MEGA format. Loading the MEGA file into MEGA software again, constructing an evolutionary tree by using a maximum likelihood method, extracting typical sequences of all branches in the evolutionary tree for analysis, and summarizing main behavior mode types of residents; further, the basic behavior patterns of different community residents can be known by using the method.

And S204, mining social and economic attributes of residents related to various behavior modes according to the personal information data of the residents.

According to the personal information data of residents, acquiring and coding the socioeconomic attribute data of the residents, and mining the frequent socioeconomic attribute items in each sequence classification by using an FP-Growth algorithm through python programming.

The socioeconomic attributes of residents are divided into two levels of codes, wherein the first level comprises gender (a), age (b), occupation (c), income (d), expenditure level (e), health condition (f) and the like, and the second level is the classification options of the first level, such as gender classification into male (1) and female (2). According to this rule, men are denoted as "a 1" and women as "a 2". And according to the classification of the previous step, the social and economic attributes of residents in various resident behavior modes are respectively mined.

First, the attribute sequence of each resident is denoted as S₁＝{a1,b2,c2,d1,e2,f2}，S₂Traversing data sets of all socio-economic attribute single items in all sequences, and calculating the support degree of each item, namely the occurrence times of the items; secondly, sorting all socioeconomic attribute values in descending order based on the descending order of the support degree, such as' c3:54 times; a1:49 times; a2:46 times; b2, 40 times; d2:38 times; e5:32 times; f1:30 times … … "; thirdly, removing the infrequent items of the social and economic attributes of the residents, namely, the numerical value of which the occurrence times is less than a certain number of times, wherein in the example, the boundary support degree is set to be 10% of the total sample amount (the number of the residents); fourth, each sequence is read piece by piece (S)₁、S₂Etc.), sequentially inserting each character in each sequence into the FP tree; the top ranked characters are marked as ancestor nodes, and the bottom ranked characters are marked as descendant nodes. Such as the sequence S_kAs { a1, b2, c3, d2, e5, f1}, the FP-tree structure is as shown in fig. 7. By analogy, other sequences are read and inserted into the FP tree, if there is a common ancestor, the number of corresponding common ancestor nodes is added by 1, and finally the whole FP tree is formed, as shown in fig. 8, the lower diagram is only a schematic diagram; and fifthly, constructing a conditional FP tree, sequentially searching a conditional mode base corresponding to the item head table from the node character at the bottommost layer upwards, recursively mining to obtain a frequent item set, and returning the applicable frequent item set. For example, the subtree of c3 is shown in FIG. 9, and the frequent item set is (c3: 54). And the subtree of b2 is: the frequent item set itself contains (b2:24), is hollowed out (a1:17), (a2:7), (c3:24), and is prefixed with b2 (b2 a1:17), (b2 a2:7), (b2 c3:24), and this result is combined with other subtrees to get the final form, as shown in fig. 10.

The extraction of the above frequent items can be obtained by python programming. Therefore, the social and economic attributes and the combination of the high-frequency resident socioeconomic attributes associated with various behavior patterns can be obtained, and the' time and space behavior patterns of the resident can be solved. Similarly, by applying the method in each community and combining the above steps, the main behavior pattern of residents in each community and the main socioeconomic attributes of the residents can be obtained, and the method can be used for assisting planning practitioners to carry out planning decisions of community public service facilities and providing decision references for the layout and positioning of business service facilities for related enterprises.

S205, according to the resident behavior mode of each community, the service facility types commonly used by residents of each community are reversely deduced, and the accessibility of the community life circle facilities is calculated.

By adopting the resident activity sequence analysis method, the resident behavior patterns of all communities are obtained, accordingly, the service facility types commonly used by residents of all communities can be deduced and recorded as a facility set F, and all facilities in the set are recorded as F_j,j＝1,2,……,n,F＝{F₁，F₂，......，F_n}。

The accumulated chance method can calculate the reachable facility number within a certain time and space distance, and is used for measuring the accessibility of community facilities. According to the national urban residential area planning and design standard GB50180-2018, the urban residential area can be divided into three levels of life circles which can be reached in five, ten and fifteen minutes respectively, and the walking distances correspond to 300, 500 and 1000 meters respectively, and the accessibility of various facilities in the three levels of life circles can be measured by adopting an accumulative chance method.

The calculation formula of the accumulative chance method is as follows:

A_j＝P_jf(d)

wherein A is_jRepresenting cumulative opportunity reachability, P, of facility j in a community_jAnd f (d) is a binary variable, when the distance cost d from the community to the facility j is less than a set threshold value, f (d) takes a value of 1, otherwise, the value is 0. Combining POI data, successively calculating a facility set F of each community_jCumulative opportunity reachability over different community life circle ranges (300, 500, 1000 meters),if the accessibility of the accumulated opportunities of the facilities in the range of the three living quarters is 0, corresponding facility complementation is carried out on the provision of the facilities of each living quarter according to the planning and designing standard of urban living quarters. In the aspect of specific facility construction, the facility design can be carried out according to the high-frequency social and economic attributes associated with the resident activity patterns of the facility with reference to the result of the resident activity sequence analysis and the social and economic attributes of the residents with pertinence.

In addition, the accumulative chance method can also carry out comprehensive measurement on the accessibility of various facilities in the community, and evaluate the overall accessibility of the facilities in each community, wherein the calculation formula is as follows:

s206, obtaining the attention and comment information of the multi-element main bodies in the community communication forum of the interaction platform, and analyzing the effect of each main body in the community governance network by constructing the relationship network of the multi-element main bodies in the community governance network.

Wherein the multivariate body comprises governments, corporations, social organizations, industry committees, expert scholars, and residents.

And constructing a relation network of the main body in community governance through a network X library of python, and calculating the degree centrality, the approach centrality and the intermediary centrality of each node in the network.

Further, the method specifically comprises the following steps:

s2061, constructing a relationship network of the multi-element subjects in community treatment.

Dividing the relationship between the main bodies into a symmetrical relationship and a unidirectional relationship, wherein the symmetrical relationship refers to mutual attention, mutual comments and the like in a community communication forum of an interactive platform; while a one-way relationship refers to a one-way focus, commenting on a post, and so forth. Based on the formed social network, the network relationship of the vital stakeholders such as governments, enterprises, social organizations, experts, scholars, residents, industry and committees in community treatment can be observed.

S2062, the effect of the measure multi-element main body in the governing network can be quantified through calculating the degree centrality, the approach centrality and the intermediate centrality of each node in the network.

(1) Degree of Centrality (Degree Centrality)

The degree centrality of the node represents the sum of connecting lines between the node and other nodes in the network, and can represent the cohesion strength of the node main body in the community management network. Since the connections are directional, the degree-centric degree can be further divided into In-degree (In-degree) and Out-degree (Out-degree). The degree of income represents the attention degree of the node main body in the community management network, and if the value is larger, the node main body has higher reputation and is more likely to guide the action and the communication of the community management network; the out degree represents the degree of the node main body concerning other main bodies in the network, and a larger value indicates that the node main body has stronger communication and enthusiasm in the network. In practice, subjects with higher in-degree values may be identified as leading persons, leader persons, and subjects with higher out-degree values may be identified as active participants.

If there are N nodes in a network, the degree of centrality C of the node i_DiThe calculation formula of (2) is as follows:

wherein the content of the first and second substances,

for calculating the number of contacts of the node i with other N-1 nodes. In order to eliminate the influence of the network scale on the degree-centrality value of the node, the degree-centrality value is normalized, and the formula is as follows:

C_D(i)′＝C_Di/(N-1)

(2) proximity Centrality (Closense Central)

The near-center degree represents the proximity of the node to other nodes within the network. Because the connection of each node of the social network has directionality, the nodes can be divided into an In-close centricity (In-close centricity) and an Out-close centricity (Out-close centricity). In fact, community management activities such as co-construction and the like have strong relevance with entity space, and most community management activities are developed on line at the present stage, and off-line professional social organizations and related practitioners also need to be cultivated. Therefore, the approach centrality index can identify the community governance main body with higher approach centrality in the geographic space and the community where the community governance main body is located, and more important offline community governance and planning activities (such as community micro-transformation and co-construction workshops) can be arranged in the community, so that the influence and the radiation power of the demonstration community are expanded.

Specifically, the residence of each subject in the social network is extracted as the node position of the subject. The approximate centrality formula for node i relative to other nodes j is:

(3) medium Centrality (Betwenness Centrality)

The individuals with the highest degree of centrality in a social network are not necessarily the most active individuals. The degree of mediation may measure the effect of connecting different group networks across the group nodes. In practice, if a resident is a member of a community social organization or an industry committee, participates in different community activities, replies to or posts, the resident exists in a plurality of community governance networks formed by different subjects. This identifies the role of some key abatement principal (e.g., social organization, cadres of industry committees, members, etc.) in different abatement networks, as well as the role that the principal plays in the affiliation of members within each network.

The formula for calculating the intermediary centrality of the node β is:

wherein σ_ij(β) is the number of shortest paths from node i to node j through node β, σ_ijIs the number of shortest paths from node i to node j, c_b(β) The importance of node β in connecting node i and node j is measured.

In practical cases, the path of nodes i and j through node β can be interpreted as that member i makes a friend with member j through the recommendation of member β (similar to the business card recommendation function), or members i and j comment each other under the post issued by member β, or join the group established by member β at the same time, etc.

It should be noted that while the method operations of the above-described embodiments are described in a particular order, this does not require or imply that these operations must be performed in that particular order, or that all of the illustrated operations must be performed, to achieve desirable results. Rather, the depicted steps may change the order of execution. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step execution, and/or one step broken down into multiple step executions.

In addition, the method can also identify the material space environmental characteristics of the community based on the data such as community pictures and the like, construct corresponding evaluation indexes to grade and monitor the environmental quality of the community, and the evaluation analysis result can be used for guiding the development of planning practices such as community micro-modification, old community modification and the like.

In addition, other analysis functions can be built in the model analysis module. If the lightweight and rapid MobileNet convolutional neural network model is applied, the material space environment characteristics of the community are identified based on the data such as community pictures and the like, corresponding evaluation indexes are constructed to grade and monitor the environment quality of the community, and the evaluation analysis result can be used for guiding the development of planning practices such as community micro-modification, old community modification and the like.

Fifth, supervision module

The supervision indexes aiming at government work comprise transaction efficiency, financial income and expense, times of organizing and negotiating meetings and related activities, satisfaction degree of residents and the like; the supervision indexes aiming at the enterprise/social organization comprise project progress, financial income and expenditure, social benefit, government satisfaction, resident satisfaction and the like; the supervision indexes aiming at the participation degree of residents mainly comprise the proportion of the number of the residents who have to do in the living and committee, party organization, cooperative management and third party community organization, the suggested acceptance rate of the residents, the complaint handling rate, the number of times of attending an interview and the like. Specifically, a satisfaction survey page, a complaint page and a report page are built in the interactive platform, the satisfaction and the complaint of the work of the government, residents and enterprises/social organizations on community public services and facilities, social organizations, property management companies and the like are surveyed, the satisfaction is measured by using a Likter five-component meter, and the performance and the score of each community work are published in the platform regularly according to the supervision indexes.

In addition, the community intelligent system can collect news, comments/complaints information of various network platforms (such as a national 12315 platform, a people network, a Xinhua community, black cat complaints, a Hope, a Baidu post and the like) about various communities in real time. After the junk text is removed, emotional color analysis is carried out on text contents such as news reports, comments and posts by using python programming, comments with positive (positive) or negative (negative) emotions are identified, and the comments are audited and processed by a specially-assigned person, so that useful information is extracted and used for guiding improvement and promotion of community living environment quality.

In the embodiment, the intelligent interaction platform is formed on the basis of the user side, the staff side and the cloud server, the user side is used for acquiring information input by the user, the staff side performs auditing, information registration and filing on the information sent by the user side and returns information data to the user side, the cloud server is a platform for background acquisition, processing, storage and analysis of multi-source heterogeneous data, and the cloud server is not particularly specified, for example, a Tencent cloud server can be rented.

In order to acquire information data input by a user, a user side can adopt a mode of WeChat applet, APP, a webpage and the like, wherein the WeChat applet/APP/website is an entrance accessed by the user and a page for information display. The information data of the user are sent to a cloud server through interfaces such as WeChat small programs, APPs and web pages, the cloud server carries out sequence analysis on the activities of residents in various communities through data acquisition and processing, and basic behavior patterns and social and economic attributes of the residents in different communities are obtained; according to the resident behavior mode of each community, the service facility types commonly used by residents of each community are back-deduced, and the accessibility of the community life circle facility is calculated; by obtaining the attention and comment information of the multi-element main bodies in the community communication forum of the interactive platform and constructing the relationship network of the multi-element main bodies in community management, the effects of the main bodies in the community management network are further analyzed and obtained.

Example 2:

as shown in fig. 11, the present embodiment provides a community data analysis apparatus, which is applied to a cloud server, and includes an acquisition unit 1101, a sequence unit 1102, an analysis unit 1103, and an association unit 1104, where specific functions of each unit are as follows:

an obtaining unit 1101, configured to obtain spatio-temporal trajectory data and personal information data of community residents, bind the spatio-temporal trajectory data and the personal information data with basic geographic block data, and identify each activity of the community residents as a different type;

a sequence unit 1102, configured to record daily activities of each community resident through a sequence composed of different activity types;

the analysis unit 1103 is configured to perform sequence analysis on activities of residents in each community to obtain basic behavior patterns of residents in different communities;

and the association unit 1104 is used for mining the social and economic attributes of the residents associated with various behavior patterns according to the personal information data of the residents.

Further, the apparatus further comprises:

the calculating unit 1105 is configured to back-derive the types of service facilities commonly used by the residents of each community according to the behavior patterns of the residents of each community, and calculate the reachability of the facilities in the community life circle.

Further, the apparatus further comprises:

and the second analysis unit 1106 is configured to acquire the attention information and the comment information of the multi-element subject in the community communication forum of the interaction platform, and analyze the role of each subject in the community governance network by constructing a relationship network of the multi-element subject in the community governance.

For specific implementation of each unit in this embodiment, reference may be made to embodiment 1 above, and details are not described here. It should be noted that the apparatus provided in this embodiment is only exemplified by the division of the above functional units, and in practical applications, the above function distribution may be completed by different functional units according to needs, that is, the internal structure is divided into different functional units to complete all or part of the above described functions.

It is to be understood that the terms "first", "second", and the like, as used in the apparatus of the present embodiment, may be used to describe various units, but the units are not limited by these terms. These terms are only used to distinguish one element from another. For example, a first cue unit may be referred to as a second cue unit, and similarly, a second cue unit may be referred to as a first cue unit, both the first and second cue units being cue units, but not the same cue unit, without departing from the scope of the present invention.

Example 3:

the present embodiment provides a storage medium, which is a computer-readable storage medium, and stores a computer program, and when the computer program is executed by a processor, the method for analyzing community data of embodiment 1 is implemented as follows:

recording the daily activities of each resident in the community by a sequence consisting of different activity types;

Further, the method further comprises: and (4) according to the resident behavior mode of each community, the service facility types commonly used by residents of each community are deduced, and the accessibility of the community life circle facility is calculated.

Further, the method further comprises: the method comprises the steps of obtaining attention information and comment information of a multi-element main body in a community communication forum of an interactive platform, and analyzing the effect of each main body in a community governance network by constructing a relation network of the multi-element main body in community governance.

The storage medium in this embodiment may be a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a Random Access Memory (RAM), a usb disk, a removable hard disk, or other media.

In conclusion, the invention obtains the time-space trajectory data and the user information data of the community residents, performs sequence analysis on the activities of the residents in each community to obtain the basic behavior patterns of the residents in different communities, and excavates the social and economic attributes of the residents associated with various behavior patterns, so that the invention can be used for assisting planning practitioners to perform planning decisions of community public service facilities and providing decision references for the layout and positioning of business service facilities for related enterprises; the service facility types commonly used by residents of all communities are deduced backwards through the resident behavior patterns of all communities, and the accessibility of the community life circle facilities is calculated by using an accumulative chance method and can be used for evaluating and designing the overall accessibility of the facilities of all communities; by constructing a relationship network of the multivariate main bodies in the community treatment, the network relationship of benefit stakeholders such as governments, enterprises, social organizations, experts and scholars, residents, enterprises and the like in the community treatment can be observed, and the role of the multivariate main bodies in the treatment network can be quantitatively measured through calculation.

The above description is only for the preferred embodiments of the present invention, but the protection scope of the present invention is not limited thereto, and any person skilled in the art can substitute or change the technical solution of the present invention and the inventive concept within the scope of the present invention, which is disclosed by the present invention, and the equivalent or change thereof belongs to the protection scope of the present invention.

Claims

1. A community data analysis method is applied to a cloud server and is characterized by comprising the following steps:

2. The community data analysis method according to claim 1, wherein the performing sequence analysis on activities of residents in each community to obtain basic behavior patterns of residents in different communities specifically comprises:

comparing the sequences of residents in the community;

3. The method of claim 2, wherein the comparing the sequences of the residents in the community specifically comprises:

4. The community data analysis method of claim 2, wherein the classification is performed according to sequence similarity, each sequence classification represents a behavior pattern, and specifically comprises:

in the global alignment, H_ijThe calculation formula of (2) is as follows:

in the local alignment, H_ijThe calculation formula of (2) is as follows:

S＝H_ijmax

5. The community data analysis method according to claim 2, wherein the obtaining of the basic behavior patterns of the residents in different communities according to the comparison result of the community resident sequences specifically comprises:

6. The community data analysis method according to claim 1, wherein the mining of socioeconomic attributes of residents associated with various behavioral patterns according to the personal information data of the residents specifically comprises:

7. The community data analysis method of claim 1, wherein the method further comprises:

8. The community data analysis method of claim 1, wherein the method further comprises:

9. A community data analysis device is applied to a cloud server, and is characterized by comprising:

10. The intelligent community interaction platform is characterized by comprising a user side, a worker side and a cloud server, wherein the user side is connected with the worker side, and the cloud server is respectively connected with the user side and the worker side;

the cloud server is used for executing the community data analysis method of any one of claims 1 to 8.