CN110766208A - Government affair service demand prediction method based on social group behaviors - Google Patents
Government affair service demand prediction method based on social group behaviors Download PDFInfo
- Publication number
- CN110766208A CN110766208A CN201910951979.3A CN201910951979A CN110766208A CN 110766208 A CN110766208 A CN 110766208A CN 201910951979 A CN201910951979 A CN 201910951979A CN 110766208 A CN110766208 A CN 110766208A
- Authority
- CN
- China
- Prior art keywords
- government affair
- government
- service
- social group
- affair service
- 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
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- 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
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06315—Needs-based resource requirements planning or analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Abstract
A government affair service demand forecasting method based on social group behaviors comprises the steps of adopting a clustering algorithm and dividing an object set into a plurality of larger social groups according to personal information of the objects; dividing the historical information of the government affair service of the object to obtain the historical information of the government affair service of the department of the object, and dividing each large social group into a plurality of smaller social groups; in each small social group, performing government affair service demand prediction on a target object by adopting a collaborative filtering algorithm; and summarizing the demand forecasting result. In the invention, the government department can recommend the personalized government affair service of the object by using the demand prediction result and can reasonably allocate the department resources, thereby realizing the demand prediction with human center and improving the capacity of the government affair service according to the demand and the efficiency of blind approval.
Description
Technical Field
The invention relates to the field of electronic government affairs, in particular to a method for predicting government affair service demands based on social group behaviors.
Background
The electronic government affair website is used as a way for people to actively inquire government affair service, can provide government affair service actively needed by the people, but cannot mine the potential government affair service requirement of the people, and along with the rapid development of 'Internet + government affair service' in recent years, the data volume of government affair data is explosively increased, so that the data can be upgraded, and the existing data is used for predicting the possible government affair service requirement of the people, so that the problem which needs to be solved urgently is solved.
In order to solve the problems, the application provides a method for forecasting government affair service demands based on social group behaviors.
Disclosure of Invention
Objects of the invention
In order to solve the technical problems in the background art, the invention provides a method for forecasting the demand of government affairs service based on social group behaviors.
(II) technical scheme
In order to solve the above problems, the present invention provides a method for forecasting government affairs service demand based on social group behaviors, which comprises the following steps:
s1, dividing an object set into a plurality of larger social groups according to personal information of the objects by adopting a clustering algorithm, and sequentially marking as a large social group 1, a large social group 2 and a large social group 3.. the large social group n;
s2, dividing the government affair service historical information of the object according to different government departments to obtain the department government affair service historical information of the object, dividing each large social group into a plurality of smaller social groups according to the department government affair service historical information of the object by adopting a clustering algorithm, and sequentially marking as a small social group 11, a small social group 12 and a small social group 13.
S3, performing government affair service demand prediction on the target object by adopting a collaborative filtering algorithm in each small social group, and sequentially recording results as a prediction result 11, a prediction result 12 and a prediction result 13..... the prediction result nn;
and S4, summarizing a demand forecasting result.
Preferably, in S1 and S2, the number of large social groups and small social groups is determined by the elbow method.
Preferably, in S1, the personal information is derived from a municipal unified government service APP, including sex, age, education level, income, etc.; carrying out numeralization and dimensionless processing on the personal information, and constructing an object-personal information matrix according to the personal information of the object; where the row vector represents the object, the column vector represents personal information attributes such as gender, age, etc., and the matrix value represents the value of the corresponding attribute.
Preferably, in S2, the government affair service history information is derived from a uniform government affair service APP in a certain city, and the government affair service history information is divided according to government departments and includes public security government affair service history information, judicial government affair service history information, social security government affair service history information, and the like; the description is given by taking the household administration service information of the history information of the public security and government affair service as an example, and the household administration service information comprises household registration, birth registration, urban immigration, household entrance to the city, household entrance logout, household registration information change, household entrance to the home, population information inquiry and household entrance recovery; taking time as a parameter, performing 0-1 processing on historical information of the government affair service, marking as 1 if the object handles the government affair service in the determined time, and marking as 0 if the object handles the government affair service in the determined time; and then constructing an object-department government affair service matrix according to the historical information of the object department government affair service, wherein row vectors represent the object, column vectors represent the attributes of the department government affair service, such as the immigration of the household registration, the birth registration and the like, and the matrix values represent whether the object transacts the government affair service within a certain time.
Preferably, in S1 and S2, in order to solve the problem that the selection of the initial point may cause the classification result to fall into the local optimal solution, a dichotomy clustering method is adopted to perform the classification of the social group types.
Preferably, the sum of squared errors E is taken as an objective function of the dichotomous clustering algorithm:
wherein: k represents the number of social groups; ciRepresenting the ith social group; u. ofiIs a social group CiThe mean vector of (a), also called centroid, is expressed as:
preferably, in S3, the collaborative filtering algorithm is based on an object similarity algorithm to perform prediction, so that the algorithm has a better prediction effect; the specific method comprises the following steps: and finding a group of objects most similar to the target object according to the historical information of the department government affair services of the objects through the object similarity, summarizing the department government affair services of the group of objects, finding the government affair services which are not transacted by the target object, obtaining the preference of each government affair service according to the similarity of the similar objects, and sequencing the government affair services based on the preference, thereby predicting the government affair services which may be needed by the target object.
Preferably, the object similarity algorithm uses euclidean distance evaluation, and the similarity calculation formula is as follows:
wherein: x, y represent the subject; n represents the number of government affairs services in the department.
Preferably, the preference of the target object x for the ith government affair service is calculated according to the following formula:
wherein: c represents a set of similar objects; d (x, y) represents the similarity of the objects x, y.
Preferably, in S4, each object in each small social group is sequentially selected as a target object, demand prediction is performed, and the demand prediction results are collected.
The technical scheme of the invention has the following beneficial technical effects:
in the invention, the government department can recommend the personalized government affair service of the object by using the demand prediction result and can reasonably allocate the department resources, thereby realizing the demand prediction with human center and improving the capacity of the government affair service according to the demand and the efficiency of blind approval.
Drawings
Fig. 1 is a specific schematic diagram of a method for forecasting government affairs service demand based on social group behaviors according to the present invention.
Fig. 2 is a simple frame diagram of a method for forecasting government affairs service demand based on social group behaviors according to the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail with reference to the accompanying drawings in conjunction with the following detailed description. It should be understood that the description is intended to be exemplary only, and is not intended to limit the scope of the present invention. Moreover, in the following description, descriptions of well-known structures and techniques are omitted so as to not unnecessarily obscure the concepts of the present invention.
As shown in fig. 1-2, the present invention provides a method for forecasting government affairs service demand based on social group behaviors, which comprises the following steps:
s1, dividing an object set into a plurality of larger social groups according to personal information of the objects by adopting a clustering algorithm, and sequentially marking as a large social group 1, a large social group 2 and a large social group 3.. the large social group n;
s2, dividing the government affair service historical information of the object according to different government departments to obtain the department government affair service historical information of the object, dividing each large social group into a plurality of smaller social groups according to the department government affair service historical information of the object by adopting a clustering algorithm, and sequentially marking as a small social group 11, a small social group 12 and a small social group 13.
S3, performing government affair service demand prediction on the target object by adopting a collaborative filtering algorithm in each small social group, and sequentially recording results as a prediction result 11, a prediction result 12 and a prediction result 13..... the prediction result nn;
and S4, summarizing a demand forecasting result.
In an alternative embodiment, the number of large and small social groups is determined using the elbow method in S1 and S2.
In an alternative embodiment, at S1, the personal information is derived from a municipal unified government service APP, including gender, age, education, income, etc.; carrying out numeralization and dimensionless processing on the personal information, and constructing an object-personal information matrix according to the personal information of the object; where the row vector represents the object, the column vector represents personal information attributes such as gender, age, etc., and the matrix value represents the value of the corresponding attribute.
In an alternative embodiment, in S2, the government affairs service history information is derived from a uniform government affairs service APP in a certain city, and the government affairs service history information is divided according to government departments and comprises public security government affairs service history information, judicial government affairs service history information, social security government affairs service history information and the like; the description is given by taking the household administration service information of the history information of the public security and government affair service as an example, and the household administration service information comprises household registration, birth registration, urban immigration, household entrance to the city, household entrance logout, household registration information change, household entrance to the home, population information inquiry and household entrance recovery; taking time as a parameter, performing 0-1 processing on historical information of the government affair service, marking as 1 if the object handles the government affair service in the determined time, and marking as 0 if the object handles the government affair service in the determined time; and then constructing an object-department government affair service matrix according to the historical information of the object department government affair service, wherein row vectors represent the object, column vectors represent the attributes of the department government affair service, such as the immigration of the household registration, the birth registration and the like, and the matrix values represent whether the object transacts the government affair service within a certain time.
In an alternative embodiment, in S1 and S2, in order to solve the problem that the selection of the initial point may cause the classification result to fall into the locally optimal solution, a dichotomy clustering method is used to perform the classification of the social group types.
In an alternative embodiment, the sum of squared errors E is used as the objective function of the dichotomous clustering algorithm:
wherein: k represents the number of social groups; ciRepresenting the ith social group; u. ofiIs a social group CiThe mean vector of (a), also called centroid, is expressed as:
in an alternative embodiment, in S3, the collaborative filtering algorithm predicts based on the object similarity algorithm, so that the algorithm has a better prediction effect; the specific method comprises the following steps: and finding a group of objects most similar to the target object according to the historical information of the department government affair services of the objects through the object similarity, summarizing the department government affair services of the group of objects, finding the government affair services which are not transacted by the target object, obtaining the preference of each government affair service according to the similarity of the similar objects, and sequencing the government affair services based on the preference, thereby predicting the government affair services which may be needed by the target object.
In an alternative embodiment, the object similarity algorithm uses euclidean distance evaluation, and the similarity calculation formula is as follows:
wherein: x, y represent the subject; n represents the number of government affairs services in the department.
In an alternative embodiment, the preference of the target object x for the ith government service is calculated as follows:
wherein: c represents a set of similar objects; d (x, y) represents the similarity of the objects x, y.
In an alternative embodiment, in S4, each object in each small social group is selected as a target object in turn, demand forecasting is performed, and the demand forecasting results are summarized.
In the invention, the government department can recommend the personalized government affair service of the object by using the demand prediction result and can reasonably allocate the department resources, thereby realizing the demand prediction with human center and improving the capacity of the government affair service according to the demand and the efficiency of blind approval.
It is to be understood that the above-described embodiments of the present invention are merely illustrative of or explaining the principles of the invention and are not to be construed as limiting the invention. Therefore, any modification, equivalent replacement, improvement and the like made without departing from the spirit and scope of the present invention should be included in the protection scope of the present invention. Further, it is intended that the appended claims cover all such variations and modifications as fall within the scope and boundaries of the appended claims or the equivalents of such scope and boundaries.
Claims (10)
1. A method for forecasting government affair service demands based on social group behaviors is characterized by comprising the following steps:
s1, dividing the object set into a plurality of larger social groups by adopting a clustering algorithm according to the personal information of the objects;
s2, dividing the government affair service history information of the object according to different government departments to obtain the department government affair service history information of the object, and dividing each large social group into a plurality of smaller social groups by adopting a clustering algorithm according to the department government affair service history information of the object;
s3, in each small social group, performing government affair service demand prediction on the target object by adopting a collaborative filtering algorithm;
and S4, summarizing a demand forecasting result.
2. The method of claim 1, wherein the numbers of the large social group and the small social group are determined by elbow method at S1 and S2.
3. A method for predicting the demand of government affairs service based on social group behaviors according to claim 1, wherein in S1, the personal information is derived from a uniform government affairs service APP of a certain city, including sex, age, education level, income, etc.; carrying out numeralization and dimensionless processing on the personal information, and constructing an object-personal information matrix according to the personal information of the object; where the row vectors represent objects, the column vectors represent personal information attributes, and the matrix values represent values corresponding to the attributes.
4. A method for predicting the demand of government affairs services based on social group behaviors as claimed in claim 1, wherein in S2, the history information of government affairs services is derived from a uniform government affairs service APP in a certain city, and the history information of government affairs services is divided according to government departments and comprises public security government affairs service history information, judicial government affairs service history information, social security government affairs service history information and the like; the description is given by taking the household administration service information of the history information of the public security and government affair service as an example, and the household administration service information comprises household registration, birth registration, urban immigration, household entrance to the city, household entrance logout, household registration information change, household entrance to the home, population information inquiry and household entrance recovery; taking time as a parameter, performing 0-1 processing on historical information of the government affair service, marking as 1 if the object handles the government affair service in the determined time, and marking as 0 if the object handles the government affair service in the determined time; and then constructing an object-department government affair service matrix according to the historical information of the object department government affair service, wherein the row vector represents the object, the column vector represents the attribute of the department government affair service, and the matrix value represents whether the object transacts the government affair service in a certain time.
5. The method for forecasting government affair service requirements based on social group behaviors as claimed in claim 1, wherein in S1 and S2, in order to solve the problem that the selection of the initial point may cause the classification result to fall into the local optimal solution, the social group types are divided by using a dichotomy clustering method.
6. The method according to claim 5, wherein the sum of squared errors E is used as an objective function of a dichotomous clustering algorithm:
wherein: k represents the number of social groups; ciRepresenting the ith social group; u. ofiIs a social group CiThe mean vector of (a), also called centroid, is expressed as:
7. a method for forecasting government affair service demands based on social group behaviors according to claim 1, wherein in S3, the collaborative filtering algorithm is used for forecasting based on an object similarity algorithm, so that the algorithm has a better forecasting effect; the specific method comprises the following steps: and finding a group of objects most similar to the target object according to the historical information of the department government affair services of the objects through the object similarity, summarizing the department government affair services of the group of objects, finding the government affair services which are not transacted by the target object, obtaining the preference of each government affair service according to the similarity of the similar objects, and sequencing the government affair services based on the preference, thereby predicting the government affair services which may be needed by the target object.
8. The method according to claim 7, wherein the object similarity algorithm uses Euclidean distance evaluation, and the similarity calculation formula is as follows:
wherein: x, y represent the subject; n represents the number of government affairs services in the department.
9. The method according to claim 8, wherein the preference of the target object x for the ith government affairs service is calculated according to the following formula:
wherein: c represents a set of similar objects; d (x, y) represents the similarity of the objects x, y.
10. A method for forecasting government affair service demand based on social group behaviors according to claim 1, wherein in S4, each object in each small social group is sequentially selected as a target object, demand forecasting is performed, and demand forecasting results are collected.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910951979.3A CN110766208A (en) | 2019-10-09 | 2019-10-09 | Government affair service demand prediction method based on social group behaviors |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910951979.3A CN110766208A (en) | 2019-10-09 | 2019-10-09 | Government affair service demand prediction method based on social group behaviors |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110766208A true CN110766208A (en) | 2020-02-07 |
Family
ID=69330926
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910951979.3A Pending CN110766208A (en) | 2019-10-09 | 2019-10-09 | Government affair service demand prediction method based on social group behaviors |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110766208A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112132727A (en) * | 2020-09-23 | 2020-12-25 | 中国科学技术大学智慧城市研究院(芜湖) | Situation big data government affair service pushing method based on city big data |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109255586A (en) * | 2018-08-24 | 2019-01-22 | 安徽讯飞智能科技有限公司 | A kind of online personalized recommendation method that E-Governance Oriented is handled affairs |
| CN109544231A (en) * | 2018-11-21 | 2019-03-29 | 浙江工商大学 | Logistics distribution service personalization recommended method based on Logistics Information Platform |
| CN109583777A (en) * | 2018-12-05 | 2019-04-05 | 广东工业大学 | A kind of financial product recommender system, method, equipment and medium |
| CN109933666A (en) * | 2019-03-18 | 2019-06-25 | 西安电子科技大学 | A kind of good friend's automatic classification method, device, computer equipment and storage medium |
| CN110070048A (en) * | 2019-04-23 | 2019-07-30 | 山东建筑大学 | Device type recognition methods and system based on double secondary K-means clusters |
| CN110086874A (en) * | 2019-04-30 | 2019-08-02 | 清华大学 | A kind of Expressway Service user classification method, system, equipment and medium |
-
2019
- 2019-10-09 CN CN201910951979.3A patent/CN110766208A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109255586A (en) * | 2018-08-24 | 2019-01-22 | 安徽讯飞智能科技有限公司 | A kind of online personalized recommendation method that E-Governance Oriented is handled affairs |
| CN109544231A (en) * | 2018-11-21 | 2019-03-29 | 浙江工商大学 | Logistics distribution service personalization recommended method based on Logistics Information Platform |
| CN109583777A (en) * | 2018-12-05 | 2019-04-05 | 广东工业大学 | A kind of financial product recommender system, method, equipment and medium |
| CN109933666A (en) * | 2019-03-18 | 2019-06-25 | 西安电子科技大学 | A kind of good friend's automatic classification method, device, computer equipment and storage medium |
| CN110070048A (en) * | 2019-04-23 | 2019-07-30 | 山东建筑大学 | Device type recognition methods and system based on double secondary K-means clusters |
| CN110086874A (en) * | 2019-04-30 | 2019-08-02 | 清华大学 | A kind of Expressway Service user classification method, system, equipment and medium |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112132727A (en) * | 2020-09-23 | 2020-12-25 | 中国科学技术大学智慧城市研究院(芜湖) | Situation big data government affair service pushing method based on city big data |
| CN112132727B (en) * | 2020-09-23 | 2023-08-18 | 长三角信息智能创新研究院 | Government service pushing method of situation big data based on city big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Kang et al. | Prediction of crime occurrence from multi-modal data using deep learning | |
| Haixiang et al. | Learning from class-imbalanced data: Review of methods and applications | |
| US20210125732A1 (en) | System and method with federated learning model for geotemporal data associated medical prediction applications | |
| CN109545386B (en) | Influenza spatiotemporal prediction method and device based on deep learning | |
| Al-Molegi et al. | Move, attend and predict: An attention-based neural model for people’s movement prediction | |
| US11663282B2 (en) | Taxonomy-based system for discovering and annotating geofences from geo-referenced data | |
| Wachowicz et al. | Finding spatial outliers in collective mobility patterns coupled with social ties | |
| Wang et al. | Multi-objective path finding in stochastic networks using a biogeography-based optimization method | |
| Azari et al. | Imbalanced learning to predict long stay Emergency Department patients | |
| CN114842553A (en) | Behavior detection method based on residual shrinkage structure and non-local attention | |
| Arai et al. | Comparative perspective of human behavior patterns to uncover ownership bias among mobile phone users | |
| Zhao et al. | Online spatial event forecasting in microblogs | |
| Duan et al. | Prediction of suspect location based on spatiotemporal semantics | |
| CN110766208A (en) | Government affair service demand prediction method based on social group behaviors | |
| Cao et al. | Efficient fine-grained location prediction based on user mobility pattern in lbsns | |
| Chen et al. | The spatiotemporal pattern and driving factors of cyber fraud crime in China | |
| Adje et al. | Smart City Based on Open Data: A Survey | |
| Bi et al. | Collaborative forecasting of tourism demand for multiple tourist attractions with spatial dependence: A combined deep learning model | |
| Shen et al. | Novel model for predicting individuals’ movements in dynamic regions of interest | |
| Vo-Van et al. | An efficient robust automatic clustering algorithm for interval data | |
| CN115730125A (en) | Object identification method and device, computer equipment and storage medium | |
| Sun et al. | Predicting future locations with semantic trajectories | |
| Tang et al. | Anisotropic diffusion for improved crime prediction in urban China | |
| Dixon et al. | Spatially disaggregated car ownership prediction using deep neural networks | |
| CN113010754B (en) | Target behavior recognition system |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200207 |
|
| RJ01 | Rejection of invention patent application after publication |