CN112989034A - Social service work quantitative tracking evaluation method based on open source information - Google Patents

Social service work quantitative tracking evaluation method based on open source information Download PDF

Info

Publication number
CN112989034A
CN112989034A CN202011483170.1A CN202011483170A CN112989034A CN 112989034 A CN112989034 A CN 112989034A CN 202011483170 A CN202011483170 A CN 202011483170A CN 112989034 A CN112989034 A CN 112989034A
Authority
CN
China
Prior art keywords
data
index
social service
service work
dynamic
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202011483170.1A
Other languages
Chinese (zh)
Inventor
张鑫
欧文孝
王寅森
樊静
黑梦哲
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.)
National University of Defense Technology
Original Assignee
National University of Defense Technology
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 National University of Defense Technology filed Critical National University of Defense Technology
Priority to CN202011483170.1A priority Critical patent/CN112989034A/en
Publication of CN112989034A publication Critical patent/CN112989034A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/35—Clustering; Classification
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/38—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/387—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using geographical or spatial information, e.g. location
    • 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
    • G06F16/951—Indexing; Web crawling techniques
    • 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
    • G06F16/9536—Search customisation based on social or collaborative filtering
    • 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
    • G06F16/958—Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
    • 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
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2216/00—Indexing scheme relating to additional aspects of information retrieval not explicitly covered by G06F16/00 and subgroups
    • G06F2216/03—Data mining

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • Educational Administration (AREA)
  • Development Economics (AREA)
  • Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Strategic Management (AREA)
  • Game Theory and Decision Science (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Library & Information Science (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The invention discloses a social service work quantitative tracking and evaluating method based on open source information, which comprises the following steps: (1) collecting data related to social service work to be evaluated from the Internet and storing the data in a metadata base; (2) carrying out duplicate removal and filtration on the data to obtain a dynamic information database; (3) marking the geographic attributes of the data to obtain a dynamic information database with geographic labels; (4) clustering news data by using a text clustering technology; (5) classifying the file data from the content level by using a text classification technology, and attaching a topic label to the clustering result and attaching a category label to the classified result to obtain a dynamic tracking database; (6) and establishing an evaluation model, and carrying out quantitative evaluation on social service work of each region. By adopting the method, the social service work intensity of the interested area can be quantitatively evaluated at any time point and any time period in the past, and the method has the advantages of short time consumption and low cost.

Description

Social service work quantitative tracking evaluation method based on open source information
Technical Field
The invention relates to the field of social network data mining, in particular to a social service work quantitative tracking and evaluating method based on open source information.
Background
With the rapid development of the internet and the accelerated promotion of informatization construction in China, government departments at all levels also develop portal websites and establish public numbers in WeChat. The policy information about the most realistic interests of social groups and the corresponding implementation promotion dynamic are reported on line in time. Moreover, with the follow-up and promotion of news media and netizens, such information can often be spread and disseminated at a rate far superior to that of yearbors. Not only does this provide convenience for the social public to obtain such information, but also makes it possible to utilize online information mining to evaluate social service performance in different regions.
However, these policy information is often distributed to government websites in various regions, and the implementation thereof is found in news portals and forum spaces in various regions. This makes it difficult to obtain the desired information about individuals and groups. Moreover, the modern society has a large mobility of population, people often stay in different places due to tourism, business trips and the like, and the information of the required social service work is more difficult to obtain due to the fact that the people do not know local related websites. Furthermore, the relevant government functions cannot use this information in a well-summarized manner, not to mention the ability to track and evaluate the respective social service efforts in various areas.
Therefore, the method for quantitatively tracking and evaluating the social service work based on the open source information is designed, and has important significance for the development of the related social service work, the related information service and the like.
Disclosure of Invention
The invention aims to provide a social service work quantitative tracking and evaluating method based on open source information, which utilizes the Internet text mining technology to automatically collect and gather related open source information on the Internet, and continuously analyzes and associates the information with dimensions of time, space and content in comprehensive consideration, thereby realizing the collection of related information of social service work in interested areas and the tracking and evaluating of social service work strength.
The technical scheme adopted by the invention is as follows: the social service work quantitative tracking evaluation method based on open source information comprises the following steps:
(1) collecting data related to social service work to be evaluated from the Internet, and storing the collected data in a metadata base;
(2) carrying out duplicate removal and filtration on the data, and storing the processed information in a database to obtain a dynamic information database;
(3) marking the geographic attribute of the data, and dividing the geographic attribution of the data to obtain a dynamic information database with geographic labels;
(4) clustering news data by using a text clustering technology, and clustering texts on the same topic into one type;
(5) classifying the file data from the content level by using a text classification technology, and attaching a topic label to the clustering result and attaching a category label to the classified result to obtain a dynamic tracking database;
(6) after the data are labeled, an evaluation model is established, the development condition of the social service work of each region is quantified, the social service work strength of each region is quantitatively evaluated in multiple dimensions, and continuous evaluation is carried out on different time periods of a certain region to realize dynamic tracking evaluation.
Further, the scope of data collection in step (1) includes government portals, travel sites and wechat applets.
Further, in the step (2), data deduplication and filtering are performed, firstly, a corresponding filtering rule is formulated through a method based on keyword matching, data irrelevant to the social service work are filtered, and secondly, data which are transferred on a network are identified and merged through a text clustering algorithm, so that deduplication of the data is achieved.
Further, the step (3) of determining the geographical location tag of the text data comprises: firstly, determining the geographic position of the mobile terminal through a data acquisition source; secondly, the geographic information database of province, city and district (county) is established through a text matching method, and then text data with geographic information of province, city and district (county) is input for matching, so that the geographic position attribute of the text data is extracted.
Furthermore, during data acquisition, data acquired on a government portal website are divided into news dynamic classes and normative file classes according to different blocks, and for the news dynamic class data, topics in news dynamic can be gathered by using a text clustering technology; for normative file data, dividing the field type of the data by using a text classification technology; and dividing data collected by the WeChat small program and the tourist website according to the preferential types of scenic spots, folk offers and channel priority, attaching corresponding topic labels and category labels to the data, and storing the topic labels and the category labels in a database to obtain a main province and city dynamic tracking database with well-divided categories.
Further, the evaluation model construction includes:
(1) dividing the evaluation content into three dimensions of a normative file, a preferential discount and news dynamics according to the characterization factors reflecting the social service working strength;
(2) selecting quantitative measurable evaluation indexes and a statistical method for determining the indexes in each dimension, wherein normative files collected on a government portal network are subjected to text classification processing to obtain five types of education, housing, medical treatment, employment and other types, and the number of the five types of files is selected as an index; data collected by a tourist website and a WeChat small program are classified into three types of scenic spot preference, folk preference and channel priority, and the number of the data under the three types is selected as an index; the news dynamic dimension takes the quantity of news dynamic data which are collected on the government portal network and are related to the social service work as an index;
(3) setting proper weight for each index;
(4) establishing a scoring system according to the division of dimensionality, the selection of indexes and the determination of weight, wherein the full score of each index is F, setting a basic score of Z score for each index, and quantitatively calculating the score value of each index to obtain:
the normative file with timeliness and news dynamic index are defined as dynamic index, each index under priority preferential category is defined as static index, and the dynamic index uses Ni,j(t, h) represents the statistical quantity of i area indexes j in the time h before the time t, and the statistical quantity of the static indexes is the sum of all data quantities before the evaluation time t;
wherein, all indexes and news dynamics under the standardization file dimension and the folk preferential indexes under the preferential dimension are influenced by the region condition, and are normalized according to the population:
Figure RE-GDA0003051823540000031
in the formula
Figure RE-GDA0003051823540000032
Denotes the normalization of j index by population in the i region (t, h) time period, miThe number of population in the area i is expressed in units of ten million;
the score value is calculated by the following formula:
Figure RE-GDA0003051823540000033
in the formula Vi,j(t, h) is the score of the j index of the i area in the (t, h) time period,
Figure RE-GDA0003051823540000034
is the maximum value V of j indexes normalized in each region in the (t, h) time periodjmaxThe score obtained by subtracting the base score from the full score of the j index, ZjFor the basic score of the j index, h is infinite when the folk preference index is calculated, namely (t, h) at the moment represents a time period before the t moment;
the scores of the preferential and preferential passage indexes of the scenic spot are calculated by the following formula:
Figure RE-GDA0003051823540000035
where h is infinite, and Q is the priority channel indexi,j(t, h) represents the total number of all sites counted by the i-region j index at the time t, Ni,j(t, h) represents the total number of sites set in the i area j index when the i area j index is counted at the time t; for scenic spot preference indicators, Qi,j(t, h) represents the total number of scenic spots of all scenic spots when the index of i area j is counted at the time t, Ni,jAnd (t, h) represents the total number of scenic spots of the i area j index with preferential policies when the i area j index is counted at the time t.
The expression of the comprehensive social service work force score value in a specified time period in a certain region is as follows:
Yi(t,h)＝∑Vi,j(t,h)×Wj，
in the formula Yi(t, h) is the value of the integrated social service effort score in the i region (t, h) time period, WjIs the weight of the j index.
The invention has the beneficial effects that: the social service work quantitative tracking evaluation method based on open source information constructs a social service work force evaluation model, and carries out multi-directional quantitative evaluation on the corresponding social service work force of a specified area by utilizing the open source information on the Internet, and has the advantages that: the method is more professional, belongs to a first quantitative evaluation model in the field of social service work evaluation, and fills the blank; secondly, the system is more flexible, can evaluate at any time and any place, can quantitatively evaluate interested areas at any time point aiming at any past time period, and can track the working dynamics of the areas through continuous evaluation; thirdly, the time consumption is short, and the cost is low; fourthly, the practical implementation situation shows that the evaluation result has higher conformity with the subjective understanding of the related groups.
Drawings
FIG. 1 is a flow chart of the operation of the present invention.
Detailed Description
In order to facilitate an understanding of the invention, the invention will be described more fully and in detail below with reference to the accompanying drawings and preferred embodiments, but the scope of the invention is not limited to the specific embodiments below.
The social service work quantitative tracking and evaluating method based on the open source information comprises the following steps:
(1) data acquisition: and collecting data related to the social service work to be evaluated from the Internet, and storing the collected data in a metadata base. The related information on the internet is scattered, and various local government portal websites, government WeChat public numbers, tourist websites and the like have related information and are partially repeated. Therefore, to collect data related to social service work to be evaluated on the internet, firstly, a data collection range, a target website and a platform which are clearly collected are determined, and secondly, different websites need to be collected by different collection methods and means due to different web page structures and data protection measures of the different websites. In the embodiment, the method mainly considers obtaining relevant information from government websites, tourism websites and WeChat applets with relatively most concentrated relevant information. The method comprises the steps of collecting government portal websites and tourism websites by using internet data collection software, and compiling targeted crawler codes for the WeChat small programs through a web crawler technology to collect.
(2) Data preprocessing: and carrying out duplication removal and filtration on the data, and storing the processed information in a database to obtain a dynamic information database. The text data collected on the internet is doped with a lot of irrelevant data, and particularly when the data collection software is used for collecting data, the data collection software collects the content of a specified webpage plate according to the rule set by a user, so that the collected data are mostly data irrelevant to the social service work to be evaluated, and the data are filtered to obtain data relevant to the social service work to be evaluated. In the embodiment, a word segmentation tool is used for segmenting the Chinese text, then, a corresponding filtering rule is formulated through a method based on keyword matching, data irrelevant to social service work to be evaluated are filtered, and finally, a single-pass clustering algorithm is used for identifying and merging data which are subjected to load transfer on a network through setting a harsher cluster merging threshold value, so that data deduplication is realized, and repeated data subjected to load transfer are filtered.
The method comprises the steps of marking the geographic position of data, dividing the data according to regions, clustering and classifying the data on the basis of the divided regions, wherein the clustering aims at finding the topics of news data, and the classifying aims at classifying normative file data into expected categories (corresponding to different civilian fields). Appropriate fields are set for the data which are labeled, clustered and classified in the geographic position and are stored in a database for later quantitative assessment of social service working strength and relevant information service provision.
(3) Marking the geographic position: and marking the geographic attributes of the data, and dividing the geographic attribution of the data according to provincial and urban areas (counties) to obtain a dynamic information database with geographic labels. In this embodiment, two methods are adopted to obtain the text geographical position information: one is to determine the geographic location of the data based on the source of the acquisition, based primarily on the observation that information published by local government websites typically only relates to local data; and the other method is that by utilizing an information extraction technology, geographic position information contained in the text is extracted by constructing a geographic information base and by means of a text matching method, and then the complete geographic position information of the text is obtained according to the constructed geographic information base.
(4) News dynamic topic clustering: and clustering the news data by using a text clustering technology, and clustering texts on the same topic into one type. The invention refers to a series of news reports which are close in time and related in content as a topic. In this embodiment, a single-pass clustering algorithm is used to cluster topics of news dynamic data.
(5) Data classification: and classifying the file data from the content level by using a text classification technology, and attaching a topic label to the clustering result and attaching a category label to the classified result to obtain a main province and city dynamic tracking database. For normative document class data, a text classification technology is utilized to divide the field class of the data, collected documents related to social service work to be evaluated relate to a plurality of fields, and the fields mainly concerned by the people are education, employment, housing and medical treatment, so that the documents are divided into four classes, and the documents which do not belong to the four classes are classified into one class called as 'other'. And the data collected by the WeChat small program and the tourist website are divided according to the preferential categories of scenic spot, folk preferential and channel priority. The embodiment classifies the normative file data by using a Text classification model Text-CNN based on a convolutional neural network.
(6) And (3) constructing an evaluation model: after the data are labeled, an evaluation model is established, the development condition of the corresponding social service work of each region is quantified, and the social service work of each region is quantitatively evaluated in multiple dimensions.
The social service work intensity can be reflected from multiple aspects, so that comprehensive evaluation can be realized by adopting a multi-level index and multi-factor analysis method. How much the government-related normative documentation covers the breadth of the field and the number of documentation; the number of news trends associated with the social service work to be evaluated over a period of time; the number of the priority channels of public places such as airports, stations and the like in a certain area and the coverage rate of the priority channels; how much and the coverage rate of the preferential policy of the tourist attractions; whether the relevant hospitality is set up or not and the set up quantity and the like in a certain area can be used for quantitatively evaluating the relevant social service work intensity in the certain area.
According to the method, evaluation contents are divided into three dimensions of normative files, preferential benefits and news dynamics according to the representation factors reflecting the social service working strength to be evaluated; selecting quantitative measurable evaluation indexes and a statistical method for determining the indexes in each dimension, wherein normative files collected on a government portal network are subjected to text classification processing to obtain five types of education, housing, medical treatment, employment and other types, and the number of the five types of files is selected as an index; data collected by a tourist website and a WeChat small program are classified into three types of scenic spot preference, folk preference and channel priority, and the number of the data under the three types is selected as an index; the news dynamic dimension takes the quantity of news dynamic data which are collected on the government portal network and are related to the social service work as an index; then determining the weight of each index through an Analytic Hierarchy Process (AHP), constructing a scoring system according to the division of dimensionality, the selection of the indexes and the determination of the weight, setting the full score F of each index to be 100 scores, setting the basic score Z to be 60 scores, and finally calculating the corresponding social service work force quantitative score of each region through a model.
The normative file and news dynamics have timeliness, the statistical number in different time periods can be different, and the indexes are defined as dynamic indexes. The indexes under the priority preferential offer category are rarely changed within a long period of time (one or more years) after being issued, even most preferential information is not changed, and the indexes are in an effective state from the issuing to the cancelling, and are specified as static indexes.
(t, h) represents a time window of duration h from time t onwards (including time t), the minimum scale of t is month, h represents the width of the time window in the unit of month, and the dynamic index is represented by Ni,jAnd (t, h) represents the statistical number of i area indexes j in the time h before the time t, the statistics of the static indexes are not influenced by a time window, and the statistical number of the static indexes is the sum of all data quantity before the evaluation time t.
Wherein, all indexes and news dynamics under the standardization file dimension and the folk preferential indexes under the preferential dimension are influenced by the region condition, and are normalized according to the population:
Figure RE-GDA0003051823540000061
in the formula
Figure RE-GDA0003051823540000062
Denotes the normalization of j index by population in the i region (t, h) time period, miThe number of population in the i area is expressed in units of ten million.
The score value is calculated by the following formula:
Figure RE-GDA0003051823540000063
in the formula Vi,j(t, h) is the score of the j index of the i area in the (t, h) time period,
Figure RE-GDA0003051823540000064
is the maximum value V of j indexes normalized in each region in the (t, h) time periodjmaxThe score obtained by subtracting the base score from the full score of the j index, ZjAnd h is infinite when the folk preference index is calculated for the basic score of the j index, namely (t, h) at the moment represents a time period before the t moment.
The scores of the preferential and preferential passage indexes of the scenic spot are calculated by the following formula:
Figure RE-GDA0003051823540000065
where h is infinite, and Q is the priority channel indexi,j(t, h) represents the total number of all sites counted by the i-region j index at the time t, Ni,j(t, h) represents the total number of sites set in the i area j index when the i area j index is counted at the time t; for scenic spot preference indicators, Qi,j(t, h) represents the total number of scenic spots of all scenic spots when the index of i area j is counted at the time t, Ni,jAnd (t, h) represents the total number of scenic spots of the i area j index with preferential policies when the i area j index is counted at the time t.
The expression of the comprehensive social service work force score value in a specified time period in a certain region is as follows:
Yi(t,h)＝∑Vi,j(t,h)×Wj，
in the formula Yi(t, h) is the value of the integrated social service effort score in the i region (t, h) time period, WjIs the weight of the j index.
The working flow chart of the social service work quantitative tracking and evaluating method based on open source information of the embodiment is shown in fig. 1.

Claims (6)

1. The social service work quantitative tracking and evaluating method based on open source information is characterized by comprising the following steps:
(1) collecting data related to social service work to be evaluated from the Internet, and storing the collected data in a metadata base;
(2) carrying out duplicate removal and filtration on the data, and storing the processed information in a database to obtain a dynamic information database;
(3) marking the geographic attribute of the data, and dividing the geographic attribution of the data to obtain a dynamic information database with geographic labels;
(4) clustering news data by using a text clustering technology, and clustering texts on the same topic into one type;
(5) classifying the file data from the content level by using a text classification technology, and attaching a topic label to the clustering result and attaching a category label to the classified result to obtain a dynamic tracking database;
(6) after the data are labeled, an evaluation model is established, the development condition of the social service work of each place is quantified, the social service work of each place is quantitatively evaluated in multiple dimensions, and continuous evaluation is carried out on different time periods of a certain area to realize dynamic tracking evaluation.
2. The quantitative tracking and evaluation method for social service work based on open source information as claimed in claim 1, wherein the data collection scope in step (1) comprises government portal web site, tourism web site and wechat applet.
3. The social service work quantitative tracking and evaluation method based on open source information as claimed in claim 1, wherein in the step (2), data deduplication and filtering are performed, wherein corresponding filtering rules are firstly formulated through a method based on keyword matching, data irrelevant to the social service work are filtered, and then data which are transferred on a network are identified and merged through a text clustering algorithm, so that data deduplication is realized.
4. The quantitative tracking and evaluation method for social service work based on open source information as claimed in claim 1, wherein the step (3) of determining the geographic location tag of the text data comprises: firstly, determining the geographic position of the mobile terminal through a data acquisition source; secondly, the geographic information database of province, city and district (county) is established through a text matching method, and then text data with geographic information of province, city and district (county) is input for matching, so that the geographic position attribute of the text data is extracted.
5. The social service work quantitative tracking and evaluating method based on open source information as claimed in claim 2, characterized in that, during data collection, the data obtained from the government portal is divided into news dynamic class and normative file class according to different blocks, and for the news dynamic class data, the topics in the news dynamic can be gathered by using text clustering technology; for normative file data, dividing the field type of the data by using a text classification technology; and dividing data collected by the WeChat small program and the tourist website according to the preferential types of scenic spots, folk offers and channel priority, attaching corresponding topic labels and category labels to the data, and storing the topic labels and the category labels in a database to obtain a main province and city dynamic tracking database with well-divided categories.
6. The social service work quantitative tracking and evaluation method based on open source information as claimed in claim 5, wherein the evaluation model construction comprises:
(1) dividing the evaluation content into three dimensions of a normative file, a preferential discount and news dynamics according to the characterization factors reflecting the social service working strength;
(2) selecting quantitative measurable evaluation indexes and a statistical method for determining the indexes in each dimension, wherein normative files collected on a government portal network are subjected to text classification processing to obtain five types of education, housing, medical treatment, employment and other types, and the number of the five types of files is selected as an index; data collected by a tourist website and a WeChat small program are classified into three types of scenic spot preference, folk preference and channel priority, and the number of the data under the three types is selected as an index; the news dynamic dimension takes the quantity of news dynamic data which are collected on the government portal network and are related to the social service work as an index;
(3) setting proper weight for each index;
(4) establishing a scoring system according to the division of dimensionality, the selection of indexes and the determination of weight, wherein the full score of each index is F, setting a basic score of Z score for each index, and quantitatively calculating the score value of each index to obtain:
the normative file with timeliness and news dynamic index are defined as dynamic index, each index under priority preferential category is defined as static index, and the dynamic index uses Ni,j(t, h) represents the statistical quantity of i area indexes j in the time h before the time t, and the statistical quantity of the static indexes is the sum of all data quantities before the evaluation time t;
wherein, all indexes and news dynamics under the standardization file dimension and the folk preferential indexes under the preferential dimension are influenced by the region condition, and are normalized according to the population:
Figure RE-FDA0003051823530000021
in the formula
Figure RE-FDA0003051823530000022
Denotes the normalization of j index by population in the i region (t, h) time period, miThe number of population in the area i is expressed in units of ten million;
the score value is calculated by the following formula:
Figure RE-FDA0003051823530000023
in the formula Vi,j(t, h) is the score of the j index of the i area in the (t, h) time period,
Figure RE-FDA0003051823530000024
is the maximum value V of j indexes normalized in each region in the (t, h) time periodjmaxThe score obtained by subtracting the base score from the full score of the j index, ZjFor the basic score of the j index, h is infinite when the folk preference index is calculated, namely (t, h) at the moment represents a time period before the t moment;
the scores of the preferential and preferential passage indexes of the scenic spot are calculated by the following formula:
Figure RE-FDA0003051823530000025
where h is infinite, and Q is the priority channel indexi,j(t, h) represents the total number of all sites counted by the i-region j index at the time t, Ni,j(t, h) represents the total number of sites set in the i area j index when the i area j index is counted at the time t; for scenic spot preference indicators, Qi,j(t, h) represents the total number of scenic spots of all scenic spots when the index of i area j is counted at the time t, Ni,j(t, h) represents the total number of scenic spots of the i area j index with preferential policies when the i area j index is counted at the time t;
the expression of the comprehensive social service work force score value in a specified time period in a certain region is as follows:
Yi(t,h)＝∑Vi,j(t,h)×Wj，
in the formula Yi(t, h) is the value of the integrated social service effort score in the i region (t, h) time period, WjIs the weight of the j index.
CN202011483170.1A 2020-12-16 2020-12-16 Social service work quantitative tracking evaluation method based on open source information Pending CN112989034A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011483170.1A CN112989034A (en) 2020-12-16 2020-12-16 Social service work quantitative tracking evaluation method based on open source information

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011483170.1A CN112989034A (en) 2020-12-16 2020-12-16 Social service work quantitative tracking evaluation method based on open source information

Publications (1)

Publication Number Publication Date
CN112989034A true CN112989034A (en) 2021-06-18

Family

ID=76344992

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011483170.1A Pending CN112989034A (en) 2020-12-16 2020-12-16 Social service work quantitative tracking evaluation method based on open source information

Country Status (1)

Country Link
CN (1) CN112989034A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115098671A (en) * 2022-08-25 2022-09-23 深圳市城市交通规划设计研究中心股份有限公司 Government affair data processing method based on artificial intelligence, electronic equipment and storage medium
CN116432092A (en) * 2023-06-15 2023-07-14 北京冠新医卫软件科技有限公司 Index system and method for fusing model data

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104933093A (en) * 2015-05-19 2015-09-23 武汉泰迪智慧科技有限公司 Regional public opinion monitoring and decision-making auxiliary system and method based on big data
CN105631612A (en) * 2016-03-08 2016-06-01 贵州省邮电规划设计院有限公司 System and method of evaluating individual performance and capability of public servant based on big data
CN109101597A (en) * 2018-07-31 2018-12-28 中电传媒股份有限公司 A kind of electric power news data acquisition system

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104933093A (en) * 2015-05-19 2015-09-23 武汉泰迪智慧科技有限公司 Regional public opinion monitoring and decision-making auxiliary system and method based on big data
CN105631612A (en) * 2016-03-08 2016-06-01 贵州省邮电规划设计院有限公司 System and method of evaluating individual performance and capability of public servant based on big data
CN109101597A (en) * 2018-07-31 2018-12-28 中电传媒股份有限公司 A kind of electric power news data acquisition system

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115098671A (en) * 2022-08-25 2022-09-23 深圳市城市交通规划设计研究中心股份有限公司 Government affair data processing method based on artificial intelligence, electronic equipment and storage medium
CN115098671B (en) * 2022-08-25 2023-02-03 深圳市城市交通规划设计研究中心股份有限公司 Government affair data processing method based on artificial intelligence, electronic equipment and storage medium
CN116432092A (en) * 2023-06-15 2023-07-14 北京冠新医卫软件科技有限公司 Index system and method for fusing model data

Similar Documents

Publication Publication Date Title
CN110245981B (en) Crowd type identification method based on mobile phone signaling data
CN104820629B (en) A kind of intelligent public sentiment accident emergent treatment system and method
CN103246670B (en) Microblogging sequence, search, methods of exhibiting and system
Fu et al. Identifying spatiotemporal urban activities through linguistic signatures
CN103235824A (en) Method and system for determining web page texts users interested in according to browsed web pages
CN103235823A (en) Method and system for determining current interest of users according to related web pages and current behaviors
Kurashima et al. Blog map of experiences: Extracting and geographically mapping visitor experiences from urban blogs
CN103914478A (en) Webpage training method and system and webpage prediction method and system
CN103246725A (en) Wireless network based data traffic pushing system and method
CN109800350A (en) A kind of Personalize News recommended method and system, storage medium
CN110533212A (en) Urban waterlogging public sentiment monitoring and pre-alarming method based on big data
CN104346425A (en) Method and system of hierarchical internet public sentiment indication system
KR20090000284A (en) Infomedics prevention system
CN112989034A (en) Social service work quantitative tracking evaluation method based on open source information
CN103577462A (en) Document classification method and document classification device
Pereira et al. Transportation in social media: an automatic classifier for travel-related tweets
CN113010578B (en) Community data analysis method and device, community intelligent interaction platform and storage medium
CN108681977B (en) Lawyer information processing method and system
CN112836109A (en) Heritage tourist site recommendation method and system
CN111143689A (en) Method for constructing recommendation engine according to user requirements and user portrait
CN115408618A (en) Interest point recommendation method based on social relationship fusion position dynamic popularity and geographic features
CN109526027B (en) Cell capacity optimization method, device, equipment and computer storage medium
CN109564646A (en) The existing scoring in internet
Meißner et al. Strategic planning support for road safety measures based on accident data mining
CHATURVEDI et al. Twitter to transport: geo-spatial sentiment analysis of traffic tweets to discover People’s feelings for urban transportation issues

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