CN111062567A - Community service scheduling method and system based on deep learning - Google Patents
Community service scheduling method and system based on deep learning Download PDFInfo
- Publication number
- CN111062567A CN111062567A CN201911096420.3A CN201911096420A CN111062567A CN 111062567 A CN111062567 A CN 111062567A CN 201911096420 A CN201911096420 A CN 201911096420A CN 111062567 A CN111062567 A CN 111062567A
- Authority
- CN
- China
- Prior art keywords
- service
- scheduling
- community
- environment data
- dynamic environment
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
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
- G06Q10/06—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
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- 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
- G06Q50/16—Real estate
- G06Q50/163—Property management
Abstract
The invention provides a deep learning-based community service scheduling method, which comprises the following steps: s1, collecting dynamic environment data in the community and uploading the dynamic environment data to a cloud server; s2, collecting service configuration parameters of property personnel, and uploading the service configuration parameters to the cloud server; and S3, generating a scheduling scheme by the cloud server, and issuing a community service scheduling instruction. A corresponding system is provided based on the method, the method is mainly applied to ultra-large communities or community groups, people and material resources engaged in community service can be effectively scheduled, orderly operation in the aspects of community traffic, sanitation and safety is maintained, compared with the traditional property service, the artificial intelligence application reduces the difficulty of artificial scheduling, and the method has more advantages in processing the community environment with severe dynamic time variation.
Description
Technical Field
The invention relates to the field of neural network technology and community service scheduling, in particular to a community service scheduling method and system based on deep learning.
Background
Traditional property services, which face a relatively limited space and population, are implemented with environmental factors that are relatively static and simple, and processes that are linear and singular. For example, in a conventional community traffic dispersion service, it is only necessary to arrange dispersion members or dispersion devices at some points (such as road intersections) of a community road, and sequentially direct the traffic according to the predetermined traffic distribution time in each traffic flow direction. The traditional community health and security service also divides the community space into subareas, cleaning staff or security guards are allocated according to the subareas, and the cleaning staff and the security guards sequentially carry out garbage cleaning or security guard inspection on each site in the subareas.
With the expansion of cities, ultra-large communities or community groups occupying hundreds of hectares and living hundreds of thousands or even hundreds of thousands of people continuously appear; this presents a huge challenge to property services in terms of traffic, environmental hygiene, security, etc. within the community. For example, due to the increase of space, population and vehicles, the number of sites needing traffic dispersion, garbage cleaning or security patrol maintenance and security in the community is increased in progression, the spatial range of site distribution is remarkably expanded, the external environment where the sites are located presents severe dynamic time variation, and the difficulty, the distance and the time cost of scheduling community service resources among the sites are obviously increased.
Therefore, how to effectively schedule people and material resources engaged in community services among sites and maintain orderly operation in the aspects of community traffic, sanitation and safety is a problem to be solved by technical personnel in the field.
Disclosure of Invention
In view of the above, the present invention provides a method and a system for scheduling community services based on deep learning, which acquire and transmit dynamic environment data in a community through a community environment sensing network, and perform information interaction between a cloud server and an auxiliary scheduling terminal on the basis of a learning mechanism of a BP neural network, so as to efficiently schedule people and material resources of the community services and maintain the orderly operation of the community.
In order to achieve the purpose, the invention adopts the following technical scheme:
a community service scheduling method based on deep learning comprises the following steps:
s1, collecting dynamic environment data in the community and uploading the dynamic environment data to a cloud server;
s2, collecting service configuration parameters of property personnel, and uploading the service configuration parameters to the cloud server;
and S3, generating a scheduling scheme by the cloud server, and issuing a community service scheduling instruction.
Preferably, the S1 acquires the dynamic environment data by using a sensing probe, wherein the sensing probe includes, but is not limited to, a traffic flow probe, a human flow probe, and a mobile phone serial number detector; the collected dynamic environment data comprises but is not limited to traffic flow, people flow and mobile phone serial number distribution; the sensing probes are distributed at different sites of a community space, so that the sites needing to execute community service can be conveniently determined according to the positions of the sensing probes in the subsequent steps.
Preferably, the property personnel in S2 inputs the self ID number, the assignable service type, and the configuration tool type into the auxiliary scheduling terminal, and the auxiliary scheduling terminal uploads the self ID number, the assignable service type, and the configuration tool type to the cloud server; the auxiliary scheduling terminal also has a GPS positioning function and can record and upload the position and the moving track of the property personnel to a cloud server in real time; the service configuration parameters of the property personnel are self ID numbers, assignable service types, configuration tool types, position information and movement tracks. Every property personnel who undertakes community service all carries an auxiliary scheduling terminal, and auxiliary scheduling terminal mainly realizes through the smart mobile phone, can carry out two-way mobile communication with high in the clouds server, just auxiliary scheduling terminal is provided with the display screen, can show the community service instruction that high in the clouds server assigned, and the property personnel of being convenient for carry out the instruction and receive.
Preferably, the specific process of generating the community service scheduling instruction is as follows:
determining the sites needing to execute the community service according to the dynamic environment data acquired by the sensing probes at different sites;
integrating the dynamic environment data uploaded by each site into a dynamic environment data set E ═<e1，e2，e3，…em>Configuring the collected service to be involvedNumber integration into service configuration parameter set D ═<d1，d2，d3，…，dn>(ii) a Wherein E is a dynamic environment data set, EiFor the dynamic environment data, i is 1,2,3 … m, m represents the collection number of the dynamic environment data, D represents the service configuration parameter group, DiConfiguring parameters for the service, wherein i is 1,2,3 … n, and n represents the number of auxiliary scheduling terminals with types meeting the requirements;
generating a fuzzy configuration set containing a scheduling scheme according to the dynamic environment data group and the service configuration parameter group, wherein the fuzzy configuration set contains the relationship among the dynamic environment data group, the service configuration parameter group and the scheduling scheme;
inputting a dynamic environment data set and a service configuration parameter set to a cloud server, and selecting a specific scheduling scheme in the fuzzy configuration set based on a BP neural network structure;
and generating a community service scheduling instruction according to the scheduling scheme, and transmitting the community service scheduling instruction to the auxiliary scheduling terminal.
Specifically, each scheduling scheme describes the time length for configuring service resources at each specific site in the community space and the service resource types configured by the sites to configure the service resources at the sites, and on the basis of the current scheduling scheme, the dynamic environment data group E and the service configuration parameter group D at the current stage are input to the cloud server, that is, the scheduling scheme at the next stage is output through a deep learning mechanism of the BP neural network, and the decision of the scheduling scheme is made by using the BP neural network, so that the high-speed computing capability of the computer can be exerted, and an optimal solution can be quickly found.
Preferably, the community service scheduling instruction includes: the property personnel are required to go to the site location where the community service is performed, the community service type, and the time limit requirement. Specifically, the position of a site requiring a property person to go to execute the community service is displayed through an electronic map, the community service types include traffic evacuation, garbage cleaning and security patrol, and the implementation requirement mainly refers to the latest time point of the site requiring the community service and the execution time length of the community service.
Based on the method, the following system is provided:
a deep learning based community service scheduling system comprising: the system comprises a community sensing network, an auxiliary scheduling terminal and a cloud server; wherein the content of the first and second substances,
the community sensing network comprises a plurality of sensing probes and a sensing Internet of things;
the sensing probe is used for acquiring dynamic environment data in a community, and the sensing Internet of things is used for uploading the acquired dynamic environment data in the community to the cloud server;
the auxiliary scheduling terminal is used for acquiring service configuration parameters of property personnel and uploading the service configuration parameters to the cloud server;
the cloud server is used for generating a scheduling scheme and issuing a community service scheduling instruction.
Preferably, the sensing probe includes but is not limited to a traffic flow probe, a people flow probe, a mobile phone serial number detector; the collected dynamic environment data comprises but is not limited to traffic flow, people flow and mobile phone serial number distribution; the sensing probes are distributed at different positions in a community space.
Preferably, the property personnel inputs the self ID number, the assignable service types and the configuration tool types into the auxiliary scheduling terminal, and the auxiliary scheduling terminal uploads the self ID number, the assignable service types and the configuration tool types to the cloud server; the auxiliary scheduling terminal also has a GPS positioning function and can record and upload the position and the moving track of the property personnel to the cloud server in real time; the service configuration parameters of the property personnel are self ID numbers, assignable service types, configuration tool types, position information and movement tracks.
Preferably, the cloud server includes: the system comprises a locus determining module, a data integration module, a scheduling scheme generating module, a scheduling decision module and a scheduling instruction generating module;
the position point determining module is used for determining the position points needing to execute the community service according to the dynamic environment data acquired by the sensing probes at different position points;
data integration dieIntegrating the dynamic environment data uploaded by each locus into a dynamic environment data set E ═<e1，e2，e3，…em>Integrating the collected service configuration parameters into a service configuration parameter set D ═<d1，d2，d3，…，dn>(ii) a Wherein the content of the first and second substances,
e is a dynamic environment data set, EiFor the dynamic environment data, i is 1,2,3 … m, m represents the collection number of the dynamic environment data, D represents the service configuration parameter group, DiConfiguring parameters for the service, wherein i is 1,2,3 … n, and n represents the number of auxiliary scheduling terminals with types meeting the requirements;
the scheduling scheme generation module is used for generating a fuzzy configuration set containing a scheduling scheme according to the dynamic environment data group and the service configuration parameter group, wherein the fuzzy configuration set contains the relationship among the dynamic environment data group, the service configuration parameter group and the scheduling scheme;
the scheduling decision module is used for inputting a dynamic environment data set and a service configuration parameter set, and selecting a specific scheduling scheme in the fuzzy configuration set based on a BP neural network structure;
and the scheduling instruction generating module is used for generating a community service scheduling instruction according to a scheduling scheme and transmitting the community service scheduling instruction to the auxiliary scheduling terminal.
Preferably, the community service scheduling instruction includes: the property personnel are required to go to the site location where the community service is performed, the community service type, and the time limit requirement.
The invention has the following beneficial effects:
based on the technical scheme, the invention provides the community service scheduling method and system based on deep learning, which are mainly applied to the ultra-large community or community group, can effectively schedule people and material resources engaged in the community service, and maintain ordered operation in the aspects of community traffic, sanitation and safety.
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 embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
FIG. 1 is a flowchart of a deep learning-based community service scheduling method according to the present invention;
FIG. 2 is a block diagram of the deep learning-based community service scheduling system according to the present invention;
FIG. 3 is a schematic structural diagram of a cloud server according to the present invention;
FIG. 4 is a diagram illustrating the relationship between the dynamic environment dataset and the service configuration parameter set and scheduling scheme according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, the present invention provides the following method:
a community service scheduling method based on deep learning comprises the following steps:
s1, collecting dynamic environment data in the community and uploading the dynamic environment data to a cloud server;
the community environment sensing network covers a community space, comprises a sensing probe and a sensing Internet of things, wherein the sensing probe can be a traffic flow probe, a people flow probe, a mobile phone serial number detector and the like according to the type of community service, the sensing probe is used for detecting dynamic environment data such as traffic flow, people flow and mobile phone serial number distribution of a position point where the sensing probe is located, and the dynamic environment data of each detected position point are uploaded to a cloud server through the sensing Internet of things.
S2, collecting service configuration parameters of property personnel, and uploading the service configuration parameters to the cloud server;
each property person configures an auxiliary scheduling terminal, the auxiliary scheduling terminal can be realized by a smart phone and performs bidirectional mobile communication with a cloud server, and the property person inputs and uploads a self ID number, a distributable service type and a configuration tool type, such as a dredging tool, a cleaning tool, a security tool or a vehicle capable of taking, to the cloud server by using the auxiliary scheduling terminal; the auxiliary scheduling terminal is provided with a display, and when the auxiliary scheduling terminal receives a community service scheduling instruction sent by a cloud server, the display of the auxiliary scheduling terminal can display information contained in the community service scheduling instruction, specifically, the information comprises a position point where property personnel are required to go to execute community service, for example, the position point is displayed by using an electronic map; community service types, such as traffic grooming, garbage cleaning, security rounds; a time limit requirement, such as a latest point of time to go to a site where the community service is executed, an execution time length of the community service. In addition, the auxiliary scheduling terminal also has a GPS positioning function, and can record and upload the position and the movement track of the property personnel to the cloud server in real time.
And S3, generating a scheduling scheme by the cloud server, and issuing a community service scheduling instruction.
Specifically, the method comprises the following specific steps:
determining the sites needing to execute the community service according to the dynamic environment data acquired by the sensing probes at different sites; for example, according to the traffic flow, an intersection with a large traffic flow is selected as a site for executing traffic dispersion in the roads of the community, and according to the pedestrian flow and the serial number of the mobile phone, a site with a large pedestrian flow or dense personnel is selected in the community space range as a site for executing security patrol and health service.
Integrating the dynamic environment data uploaded by each site into a dynamic environment data set E ═<e1，e2，e3，…em>Clothes to be collectedIntegrating the service configuration parameters into a service configuration parameter set D ═<d1，d2，d3，…，dn>(ii) a Wherein E is a dynamic environment data set, EiFor the dynamic environment data, i is 1,2,3 … m, m represents the collection number of the dynamic environment data, D represents the service configuration parameter group, DiConfiguring parameters for the service, wherein i is 1,2,3 … n, and n represents the number of auxiliary scheduling terminals with types meeting the requirements;
generating a fuzzy configuration set containing scheduling schemes according to the dynamic environment data group and the service configuration parameter group, wherein the fuzzy configuration set contains the relation among the dynamic environment data group, the service configuration parameter group and the scheduling schemes, and each scheduling scheme uses SiDenotes, i ═ 1,2,3 … …, scheduling scheme SiThe method comprises the steps that service resources are configured at sites of a community space, the service resource types configured at the sites and the time length of the service resources configured at the sites are described; when the current scheduling scheme is stThen, by analyzing the dynamic environment data group E and the service configuration parameter group D, the scheduling scheme S of the next stage can be obtainedt+1If the scheduling scheme status of the current stage is S1, as shown in fig. 4, the dynamic environment data set of the current stage is EaThe service configuration parameter group is DaThen the scheduling scheme of the next stage may be obtained as S2; assuming that the scheduling scheme status of the current stage is S1, if the dynamic environment data set of the current stage is EbThe service configuration parameter group is DbThen the scheduling scheme of the next stage may be obtained as S4; assuming that the scheduling scheme status of the current stage is S2, if the dynamic environment data set of the current stage is EcThe service configuration parameter group is DcThen the scheduling scheme of the next stage may be obtained as S3; assuming that the scheduling scheme status of the current stage is S2, if the dynamic environment data set of the current stage is EdThe service configuration parameter group is DdThen the scheduling scheme of the next stage may be obtained as S5; assuming that the scheduling scheme status of the current stage is S3, if the dynamic environment data set of the current stage is EeThe service configuration parameter group is DeThen the scheduling scheme of the next stage may be obtained as S4; assume the scheduling scenario of the current phaseThe state is S4, if the dynamic environment data set of the current stage is EfThe service configuration parameter group is DfThen the scheduling scheme of the next stage can be obtained as S5.
And inputting the dynamic environment data set and the service configuration parameter set to a cloud server, and based on a BP neural network structure, selecting a specific scheduling scheme in the fuzzy configuration set.
Specifically, the learning process of the BP neural network consists of two processes of information forward propagation and error backward propagation, the input layer neurons receive input dynamic environment data group samples and service configuration parameter group samples, the intermediate layer performs internal information processing, the internal information processing is transmitted to each neuron of the output layer through the last hidden layer, and the output layer outputs information processing results, namely a scheduling scheme; comparing the output scheduling scheme with the expected scheduling scheme, if the output does not accord with the expected scheduling scheme, entering a back propagation stage of errors, correcting the weight of each layer by the errors through an output layer in a mode of error gradient reduction, reversing the weights layer by layer to an intermediate layer and an input layer, training by a large number of samples until the output scheduling scheme is consistent with the expected scheduling scheme, and finishing the training process of the BP neural network. According to the fuzzy configuration set, according to the current scheduling scheme, the dynamic environment data group E and the service configuration parameters D are input into the trained BP neural network, and then the specific scheduling scheme of the next stage can be output. That is, assuming that the scheduling scheme of the current stage is S1, a dynamic environment data set and a service configuration set (E) are inputa，Da) Then, the BP neural network outputs the scheduling scheme S2 of the corresponding next stage.
And generating a community service scheduling instruction according to the scheduling scheme, and transmitting the community service scheduling instruction to the auxiliary scheduling terminal.
As shown in figures 2 and 3 of the drawings,
a deep learning based community service scheduling system comprising: the system comprises a community sensing network 1, an auxiliary scheduling terminal 2 and a cloud server 3; wherein the content of the first and second substances,
the community sensing network 1 comprises a plurality of sensing probes 11 and a sensing Internet of things 12;
the sensing probe 11 is used for acquiring dynamic environment data in a community, and the sensing internet of things 12 is used for uploading the acquired dynamic environment data in the community to the cloud server 3;
the auxiliary scheduling terminal 2 is used for acquiring service configuration parameters of property personnel and uploading the service configuration parameters to the cloud server 3;
the cloud server 3 is used for generating a scheduling scheme and issuing a community service scheduling instruction.
In order to further optimize the above technical solution, the sensing probe 11 includes but is not limited to a traffic flow probe, a people flow probe, a mobile phone serial number detector; the collected dynamic environment data comprises but is not limited to traffic flow, people flow and mobile phone serial number distribution; the sensing probes 11 are distributed at different points in the community space.
In order to further optimize the technical scheme, the property personnel input the ID number, the assignable service types and the configuration tool types into the auxiliary scheduling terminal 2, and the auxiliary scheduling terminal 2 uploads the ID number, the assignable service types and the configuration tool types to the cloud server 3; the auxiliary scheduling terminal 2 also has a GPS positioning function, and can record and upload the position and the moving track of the property personnel to the cloud server 3 in real time; the service configuration parameters of the property personnel are self ID numbers, assignable service types, configuration tool types, position information and movement tracks.
In order to further optimize the above technical solution, the cloud server 3 includes: the system comprises a locus determining module 31, a data integration module 32, a scheduling scheme generating module 33, a scheduling decision module 34 and a scheduling instruction generating module 35;
the site determining module 31 is configured to determine a site that needs to execute the community service according to dynamic environment data acquired by the sensing probes at different sites;
the data integration module 32 integrates the dynamic environment data uploaded by each site into a dynamic environment data set E ═<e1，e2，e3，…em>Integrating the collected service configuration parameters into a service configuration parameter set D ═<d1，d2，d3，…，dn>(ii) a Wherein E isDynamic environment data set, eiFor the dynamic environment data, i is 1,2,3 … m, m represents the collection number of the dynamic environment data, D represents the service configuration parameter group, DiConfiguring parameters for the service, wherein i is 1,2,3 … n, and n represents the number of auxiliary scheduling terminals with types meeting the requirements;
the scheduling scheme generating module 33 is configured to generate a fuzzy configuration set including a scheduling scheme according to the dynamic environment data group and the service configuration parameter group, where the fuzzy configuration set includes a relationship between the dynamic environment data group, the service configuration parameter group, and the scheduling scheme;
the scheduling decision module 34 is configured to input a dynamic environment data set and a service configuration parameter set, and select a specific scheduling scheme in the fuzzy configuration set based on a BP neural network structure;
the scheduling instruction generating module 35 is configured to generate a community service scheduling instruction according to the scheduling scheme, and transmit the community service scheduling instruction to the auxiliary scheduling terminal 2.
In order to further optimize the above technical solution, the community service scheduling instruction includes: the property personnel are required to go to the site location where the community service is performed, the community service type, and the time limit requirement.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A community service scheduling method based on deep learning is characterized by comprising the following steps:
s1, collecting dynamic environment data in the community and uploading the dynamic environment data to a cloud server;
s2, collecting service configuration parameters of property personnel, and uploading the service configuration parameters to the cloud server;
and S3, generating a scheduling scheme by the cloud server, and issuing a community service scheduling instruction.
2. The deep learning-based community service scheduling method of claim 1, wherein the S1 utilizes sensing probes to collect dynamic environment data, the sensing probes include but are not limited to traffic flow probes, people flow probes, mobile phone serial number detectors; the collected dynamic environment data comprises but is not limited to traffic flow, people flow and mobile phone serial number distribution; the sensing probes are distributed at different positions in a community space.
3. The deep learning-based community service scheduling method of claim 1, wherein the property personnel in S2 inputs their ID numbers, assignable service types, and configuration tool types into the auxiliary scheduling terminal, and the auxiliary scheduling terminal uploads their ID numbers, assignable service types, and configuration tool types to the cloud server; the auxiliary scheduling terminal also has a GPS positioning function and can record and upload the position and the moving track of the property personnel to a cloud server in real time; the service configuration parameters of the property personnel are self ID numbers, assignable service types, configuration tool types, position information and movement tracks.
4. The deep learning-based community service scheduling method according to claim 1, wherein the specific process of generating the community service scheduling command is as follows:
determining the sites needing to execute the community service according to the dynamic environment data acquired by the sensing probes at different sites;
integrating the dynamic environment data uploaded by each site into a dynamic environment data set E ═<e1，e2，e3，…em>Integrating the collected service configuration parameters into a service configuration parameter set D ═<d1，d2，d3，…，dn>(ii) a Wherein E is a dynamic environment data set, EiFor the dynamic environment data, i is 1,2,3 … m, m represents the collection number of the dynamic environment data, D represents the service configuration parameter group, DiConfiguring parameters for the service, wherein i is 1,2,3 … n, and n represents the number of auxiliary scheduling terminals with types meeting the requirements;
generating a fuzzy configuration set containing a scheduling scheme according to the dynamic environment data group and the service configuration parameter group, wherein the fuzzy configuration set contains the relationship among the dynamic environment data group, the service configuration parameter group and the scheduling scheme;
inputting a dynamic environment data set and a service configuration parameter set to a cloud server, and selecting a specific scheduling scheme in the fuzzy configuration set based on a BP neural network structure;
and generating a community service scheduling instruction according to the scheduling scheme, generating the community service scheduling instruction, and transmitting the community service scheduling instruction to the auxiliary scheduling terminal.
5. The deep learning-based community service scheduling method according to claim 1, wherein the community service scheduling instruction comprises: the property personnel are required to go to the site location where the community service is performed, the community service type, and the time limit requirement.
6. A deep learning based community service scheduling system, comprising: the system comprises a community sensing network (1), an auxiliary scheduling terminal (2) and a cloud server (3); wherein the content of the first and second substances,
the community sensing network (1) comprises a plurality of sensing probes (11) and a sensing Internet of things (12);
the sensing probe (11) is used for acquiring dynamic environment data in a community, and the sensing internet of things (12) is used for uploading the acquired dynamic environment data in the community to the cloud server (3);
the auxiliary scheduling terminal (2) is used for acquiring service configuration parameters of property personnel and uploading the service configuration parameters to the cloud server (3);
the cloud server (3) is used for generating a scheduling scheme and issuing a community service scheduling instruction.
7. The deep learning based community service scheduling system of claim 6, wherein the sensing probe (11) comprises but is not limited to a traffic flow probe, a people flow probe, a mobile phone serial number detector; the collected dynamic environment data comprises but is not limited to traffic flow, people flow and mobile phone serial number distribution; the sensing probes (11) are distributed at different positions in a community space.
8. The deep learning-based community service scheduling system of claim 6, wherein the property personnel inputs the self ID number, the assignable service type and the configuration tool type into the auxiliary scheduling terminal (2), and the auxiliary scheduling terminal (2) uploads the self ID number, the assignable service type and the configuration tool type to the cloud server (3); the auxiliary scheduling terminal (2) also has a GPS positioning function, and can record and upload the position and the moving track of the property personnel to the cloud server (3) in real time; the service configuration parameters of the property personnel are self ID numbers, assignable service types, configuration tool types, position information and movement tracks.
9. The deep learning based community service scheduling system of claim 6, wherein the cloud server (3) comprises: the system comprises a locus determining module (31), a data integration module (32), a scheduling scheme generating module (33), a scheduling decision module (34) and a scheduling instruction generating module (35);
the position determining module (31) is used for determining positions needing to execute community service according to dynamic environment data acquired by the sensing probes at different positions;
the data integration module (32) integrates the dynamic environment data uploaded by each site into a dynamic environment data set E ═<e1，e2，e3，…em>Integrating the collected service configuration parameters into a service configuration parameter set D ═<d1，d2，d3，…，dn>(ii) a Wherein E is a dynamic environment data set, EiFor the dynamic environment data, i is 1,2,3 … m, m represents the collection number of the dynamic environment data, D represents the service configuration parameter group, DiConfiguring parameters for the service, wherein i is 1,2,3 … n, and n represents the number of auxiliary scheduling terminals with types meeting the requirements;
the scheduling scheme generation module (33) is configured to generate a fuzzy configuration set including a scheduling scheme according to the dynamic environment data group and the service configuration parameter group, where the fuzzy configuration set includes a relationship between the dynamic environment data group, the service configuration parameter group, and the scheduling scheme;
the scheduling decision module (34) is used for inputting a dynamic environment data set and a service configuration parameter set, and selecting a specific scheduling scheme in the fuzzy configuration set based on a BP neural network structure;
the scheduling instruction generating module (35) is used for generating a community service scheduling instruction according to a scheduling scheme and transmitting the community service scheduling instruction to the auxiliary scheduling terminal (2).
10. The deep learning based community service scheduling system of claim 6, wherein the community service scheduling instructions comprise: the property personnel are required to go to the site location where the community service is performed, the community service type, and the time limit requirement.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911096420.3A CN111062567B (en) | 2019-11-11 | 2019-11-11 | Community service scheduling method and system based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911096420.3A CN111062567B (en) | 2019-11-11 | 2019-11-11 | Community service scheduling method and system based on deep learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111062567A true CN111062567A (en) | 2020-04-24 |
| CN111062567B CN111062567B (en) | 2021-06-04 |
Family
ID=70297743
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911096420.3A Active CN111062567B (en) | 2019-11-11 | 2019-11-11 | Community service scheduling method and system based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111062567B (en) |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103136634A (en) * | 2013-02-22 | 2013-06-05 | 成都锦瑞投资有限公司 | Region certified property intelligent task management system |
| CN103179212A (en) * | 2013-03-27 | 2013-06-26 | 无锡祥程科技有限公司 | Intelligent community management service method and network architecture |
| CN103810602A (en) * | 2012-11-09 | 2014-05-21 | 丁力平 | Community business service system and terminal service providing method |
| CN104346695A (en) * | 2014-10-27 | 2015-02-11 | 中国水利水电科学研究院 | Emergency dispatching circumstance generation method for water pollution emergency |
| CN105678666A (en) * | 2016-03-14 | 2016-06-15 | 福建农林大学 | Experimental building security and emergency contingency plan issuing system based on Internet of Things |
| CN106530181A (en) * | 2016-11-03 | 2017-03-22 | 山东瀚岳智能科技股份有限公司 | Prison emergency plan scheduling method and system based on positioning data |
| US9832315B1 (en) * | 2014-04-21 | 2017-11-28 | United Services Automobile Association | Database allocation and analytics for service call centers |
| CN108037993A (en) * | 2017-11-07 | 2018-05-15 | 大国创新智能科技(东莞)有限公司 | Cloud computing dispatching method and system based on big data and deep learning neutral net |
| CN108108926A (en) * | 2018-02-24 | 2018-06-01 | 成都杠上花信息技术有限公司 | A kind of shared bicycle scheduling system and dispatching method based on big data |
| CN109284986A (en) * | 2018-12-05 | 2019-01-29 | 广州市同庆物业管理有限公司 | A kind of Property Management System based on big data |
| CN109872129A (en) * | 2019-01-31 | 2019-06-11 | 广东美的物业管理股份有限公司 | A kind of line reports the closed-loop management method, device and terminal device of thing declaration form |
| CN109886474A (en) * | 2019-01-24 | 2019-06-14 | 同济大学 | A kind of closed test field planing method towards automatic driving vehicle test |
| CN110264380A (en) * | 2019-05-08 | 2019-09-20 | 特斯联（北京）科技有限公司 | A kind of property management method and system based on artificial intelligence |
-
2019
- 2019-11-11 CN CN201911096420.3A patent/CN111062567B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103810602A (en) * | 2012-11-09 | 2014-05-21 | 丁力平 | Community business service system and terminal service providing method |
| CN103136634A (en) * | 2013-02-22 | 2013-06-05 | 成都锦瑞投资有限公司 | Region certified property intelligent task management system |
| CN103179212A (en) * | 2013-03-27 | 2013-06-26 | 无锡祥程科技有限公司 | Intelligent community management service method and network architecture |
| US9832315B1 (en) * | 2014-04-21 | 2017-11-28 | United Services Automobile Association | Database allocation and analytics for service call centers |
| CN104346695A (en) * | 2014-10-27 | 2015-02-11 | 中国水利水电科学研究院 | Emergency dispatching circumstance generation method for water pollution emergency |
| CN105678666A (en) * | 2016-03-14 | 2016-06-15 | 福建农林大学 | Experimental building security and emergency contingency plan issuing system based on Internet of Things |
| CN106530181A (en) * | 2016-11-03 | 2017-03-22 | 山东瀚岳智能科技股份有限公司 | Prison emergency plan scheduling method and system based on positioning data |
| CN108037993A (en) * | 2017-11-07 | 2018-05-15 | 大国创新智能科技(东莞)有限公司 | Cloud computing dispatching method and system based on big data and deep learning neutral net |
| CN108108926A (en) * | 2018-02-24 | 2018-06-01 | 成都杠上花信息技术有限公司 | A kind of shared bicycle scheduling system and dispatching method based on big data |
| CN109284986A (en) * | 2018-12-05 | 2019-01-29 | 广州市同庆物业管理有限公司 | A kind of Property Management System based on big data |
| CN109886474A (en) * | 2019-01-24 | 2019-06-14 | 同济大学 | A kind of closed test field planing method towards automatic driving vehicle test |
| CN109872129A (en) * | 2019-01-31 | 2019-06-11 | 广东美的物业管理股份有限公司 | A kind of line reports the closed-loop management method, device and terminal device of thing declaration form |
| CN110264380A (en) * | 2019-05-08 | 2019-09-20 | 特斯联（北京）科技有限公司 | A kind of property management method and system based on artificial intelligence |
Non-Patent Citations (2)
| Title |
|---|
| 任彬: "基于模糊多属性决策的复杂产品配置方法", 《机械工程学报》 * |
| 轩辕思思: "产品配置的模糊求解及优化算法研究", 《武汉理工大学学报》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111062567B (en) | 2021-06-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Kieu et al. | A modified density-based scanning algorithm with noise for spatial travel pattern analysis from smart card AFC data | |
| CN106845371B (en) | A kind of city road network automotive emission remote sensing monitoring system | |
| Cortés et al. | Commercial bus speed diagnosis based on GPS-monitored data | |
| CN110570651A (en) | Road network traffic situation prediction method and system based on deep learning | |
| Stipancic et al. | Surrogate safety and network screening: Modelling crash frequency using GPS travel data and latent Gaussian Spatial Models | |
| CN104424812B (en) | A kind of public transport arrival time forecasting system and method | |
| CN108039197A (en) | Medical technologies auxiliary examination project scheduling bootstrap technique and system | |
| Ram et al. | SMARTBUS: A web application for smart urban mobility and transportation | |
| CN109376906B (en) | Travel time prediction method and system based on multi-dimensional trajectory and electronic equipment | |
| Pang et al. | Development of people mass movement simulation framework based on reinforcement learning | |
| CN113487863A (en) | Multi-factor traffic risk real-time quantitative evaluation system and method | |
| Bamaqa et al. | SIMCD: SIMulated crowd data for anomaly detection and prediction | |
| Jabamony et al. | IoT Based Bus Arrival Time Prediction Using Artificial Neural Network (ANN) for Smart Public Transport System (SPTS). | |
| Ma et al. | Public transportation big data mining and analysis | |
| Long Cheu et al. | Mobile sensor and sample-based algorithm for freeway incident detection | |
| CN113159371B (en) | Unknown target feature modeling and demand prediction method based on cross-modal data fusion | |
| CN111062567B (en) | Community service scheduling method and system based on deep learning | |
| Liu et al. | Domain-specific data mining for residents' transit pattern retrieval from incomplete information | |
| Wang et al. | Metroeye: A weather-aware system for real-time metro passenger flow prediction | |
| Pramanik et al. | Modeling traffic congestion in developing countries using google maps data | |
| AT&T | ||
| CN110704789B (en) | Population dynamic measurement and calculation method and system based on 'urban superconcephalon' computing platform | |
| CN110474803B (en) | Processing method of Internet of vehicles system and related equipment | |
| Yu et al. | The Application of Multisensor Information Fusion Technology in Environmental Restoration | |
| Grabis et al. | A Smart Winter Road Maintenance Platform to Balance Monitoring Accuracy and Cost |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |