CN116226527B - Digital community treatment method for realizing behavior prediction through resident big data - Google Patents
Digital community treatment method for realizing behavior prediction through resident big data Download PDFInfo
- Publication number
- CN116226527B CN116226527B CN202310197344.5A CN202310197344A CN116226527B CN 116226527 B CN116226527 B CN 116226527B CN 202310197344 A CN202310197344 A CN 202310197344A CN 116226527 B CN116226527 B CN 116226527B
- Authority
- CN
- China
- Prior art keywords
- digital
- behavior
- community
- behaviors
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims description 46
- 230000006399 behavior Effects 0.000 claims abstract description 259
- 230000005477 standard model Effects 0.000 claims abstract description 73
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 37
- 238000010276 construction Methods 0.000 claims abstract description 10
- 238000005457 optimization Methods 0.000 claims abstract description 9
- 230000009471 action Effects 0.000 claims description 33
- 238000012549 training Methods 0.000 claims description 32
- 238000004458 analytical method Methods 0.000 claims description 11
- 230000015654 memory Effects 0.000 claims description 11
- 238000007405 data analysis Methods 0.000 claims description 6
- 238000013135 deep learning Methods 0.000 claims description 6
- 238000011161 development Methods 0.000 claims description 6
- 230000000694 effects Effects 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 4
- 238000005067 remediation Methods 0.000 claims description 3
- 230000003542 behavioural effect Effects 0.000 claims 2
- 238000007726 management method Methods 0.000 abstract description 8
- 230000006870 function Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 3
- 238000004590 computer program Methods 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 238000010009 beating Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 210000001364 upper extremity Anatomy 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—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
- 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
- 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—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Tourism & Hospitality (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Psychiatry (AREA)
- Software Systems (AREA)
- Human Computer Interaction (AREA)
- Medical Informatics (AREA)
- Economics (AREA)
- Social Psychology (AREA)
- Development Economics (AREA)
- Human Resources & Organizations (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Educational Administration (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to a digital community management method for realizing behavior prediction through resident big data, which is characterized in that the digital standard judgment is carried out on community resident behaviors in the digital community resident big data through a preset digital standard model to obtain a digital standard judgment result of the behaviors; classifying and collecting digital standard judgment results aiming at different types of behaviors, and generating behavior characteristics of each behavior; and carrying out feedback adjustment on the digital standard model by utilizing the behavior characteristics, optimizing the algorithm structure of the digital standard model, and continuously keeping refreshing. The digital standard model of each behavior stored on the background cloud server is adopted, so that multidimensional behavior identification can be realized; the community resident behaviors are digital standard, are intelligent models for behavior recognition, and can also utilize recognition results of different types of behaviors to feed back and adjust the models, optimize model algorithms and realize digital optimization construction.
Description
Technical Field
The disclosure relates to the technical field, in particular to a digital community treatment method, a digital community treatment model, a device and a control system for realizing behavior prediction through resident big data.
Background
The digital reform is a novel life trend of the current social development, and under the promotion of science and technology, the acceleration of the digital construction of communities is the current development focus.
The existing community construction is mainly focused on the digital management of communities, how to realize the digital management of all aspects of communities, and the main key points are digital standardization of all resident behaviors of communities. In the prior art, a mode of predicting behaviors is widely adopted for collecting big data of community residents, but the method is mainly focused on the identification of certain behaviors of the community residents and the recommendation of targeted contents, and recommended community activities/contents or other activities are provided for the residents through the identification of the behaviors, so that hobby services of the residents are accurately obtained, and the living of the residents is conveniently guided. For example, publication number CN106202534a provides a content recommendation method and system based on community user behavior, and sends behavior information to a server; collecting and analyzing the community user behavior information in the server; preprocessing the collected behavior information, uploading the behavior information of the specifications in the server, and storing the behavior information by adopting hadoop; classifying the behavior information of the specification; establishing different community user models, and classifying community users; generating a community user portrait through a community user model; and obtaining recommended content for community users. According to the invention, personalized recommendation can be performed on the mobile client home page and the computer home page, and personalized recommendation is uniformly performed according to the interest and hobbies of community users, so that thousands of people and thousands of faces are accurately served.
The technical scheme has the following problems:
The behavior information of resident users is processed more singly, and multidimensional behavior identification cannot be realized;
Although the design user model is also established, the model is only a function of classifying users, not an intelligent model for identifying behaviors, and further has no function of identifying behaviors and feeding back and adjusting the model by utilizing identification results, and the model lacks of digital standard construction.
Disclosure of Invention
In order to solve the problems, the application provides a digital community management method, a digital community management model, a digital community management device and a control system for realizing behavior prediction through resident big data.
On the one hand, the application provides a digital community treatment method for realizing behavior prediction through resident big data, which comprises the following steps:
acquiring digital community resident big data;
Carrying out digital standard judgment on community resident behaviors in the digital community resident big data through a preset digital standard model to obtain digital standard judgment results of the behaviors;
Classifying and collecting digital standard judgment results aiming at different types of behaviors, and generating behavior characteristics of each behavior;
And carrying out feedback adjustment on the digital standard model by utilizing the behavior characteristics, optimizing the algorithm structure of the digital standard model, and continuously keeping refreshing.
As an optional embodiment of the present application, optionally, after digitizing the community-resident-data, further comprising:
Presetting a data analysis rule;
analyzing the big data of the digital community residents according to the data analysis rule to obtain analysis data;
According to the community digital classification standard, the analysis data are divided into different types of data formats, and a sequence table is adopted for output and storage respectively.
As an optional implementation manner of the application, optionally, the community digital classification standard is a digital standard model established for different community activity contents; the digital standard model is deployed and stored on a background cloud server of the community;
the digitized canonical model includes at least one of the following canonical models:
A text behavior digital canonical model;
A language behavior digital canonical model;
The gesture action behavior digitizes the canonical model.
As an optional embodiment of the present application, optionally, the method for establishing a digital specification model includes:
collecting and preprocessing behavior data of each type;
Taking the preprocessed behavior data as an initial training data set;
adding behavior specification data to the initial training data set, and constructing an enhanced training data set aiming at the behavior;
and (3) adopting a deep learning method, taking the enhanced training data set as a model training sample, training and generating digital standard models aiming at different behaviors, and publishing and storing the digital standard models on a background cloud server.
As an optional implementation manner of the present application, optionally, according to a community digitalized classification standard, the parsing data is divided into different types of data formats, and is output and stored by adopting a sequence table, including:
Constructing a sequence table aiming at different types of behaviors;
from the analysis data, the behavior data of different types are obtained in a dividing way, and the behavior data are output according to the data format corresponding to the type;
And inputting the behavior data of each type one by one according to the time sequence and storing the behavior data in a corresponding sequence table.
As an optional implementation manner of the present application, optionally, performing digital standard judgment on the community resident behaviors in the digital community resident big data through a preset digital standard model to obtain a digital standard judgment result of the behaviors, where the digital standard judgment result includes:
the community residents log in a background cloud server to obtain the digital standard model to which the respective behaviors belong;
Judging the behaviors of community residents through a preset behavior prediction algorithm, wherein the method comprises the following steps of:
extracting behavior characteristics and calculating to obtain characteristic values;
Comparing the characteristic value with a preset characteristic value:
If the characteristic value is more than or equal to (0.75-0.85) a preset characteristic value, indicating that the behaviors of community residents accord with the digital standard model;
And otherwise, sending the behavior specification and the nonstandard information aiming at the behavior, which are stored in the digital specification model corresponding to the behavior, to the community residents through the background cloud server.
In another aspect of the application, a digital community governance model is provided, comprising a digital canonical model for different behaviors;
the digital standard model is built by adopting the method for building the digital standard model and is used for:
And carrying out digital standard judgment on the community resident behaviors in the digital community resident big data to obtain a digital standard judgment result of the behaviors.
As an alternative embodiment of the present application, optionally, at least one of the following canonical models is included:
A text behavior digital canonical model;
A language behavior digital canonical model;
The gesture action behavior digitizes the canonical model.
In another aspect of the present application, a device for implementing the digital community governance method for implementing behavior prediction by resident big data is also provided, including:
the community resident big data acquisition module is used for acquiring digital community resident big data;
the behavior specification judging module is used for carrying out digital specification judgment on community resident behaviors in the digital community resident big data through a preset digital specification model to obtain a digital specification judging result of the behaviors;
the behavior feature extraction module is used for classifying and collecting digital standard judgment results aiming at different types of behaviors and generating behavior features of the behaviors;
And the model optimization module is used for carrying out feedback adjustment on the digital standard model by utilizing the behavior characteristics, optimizing the algorithm structure of the digital standard model and continuously keeping refreshing.
In another aspect of the present application, a control system is also provided, including:
A processor;
a memory for storing processor-executable instructions;
The processor is configured to implement the digital community governance method for implementing behavior prediction through resident big data when executing the executable instructions.
The invention has the technical effects that:
According to the application, through a preset digital standard model, digital standard judgment is carried out on community resident behaviors in the digital community resident big data, and a digital standard judgment result of the behaviors is obtained; classifying and collecting digital standard judgment results aiming at different types of behaviors, and generating behavior characteristics of each behavior; and carrying out feedback adjustment on the digital standard model by utilizing the behavior characteristics, optimizing the algorithm structure of the digital standard model, and continuously keeping refreshing. The digital standard model of each behavior stored on the background cloud server is adopted, so that multidimensional behavior identification can be realized; the community resident behaviors are digital standard, are intelligent models for behavior recognition, and can also utilize recognition results of different types of behaviors to feed back and adjust the models, optimize model algorithms and realize digital optimization construction.
Other features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments, which proceeds with reference to the accompanying drawings.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate exemplary embodiments, features and aspects of the present disclosure and together with the description, serve to explain the principles of the disclosure.
FIG. 1 is a schematic diagram of the implementation flow of a digital community governance method for implementing behavior prediction through resident big data according to the invention;
FIG. 2 illustrates an application deployment diagram for the digitized canonical model of the invention;
FIG. 3 is a schematic diagram showing the implementation of the method for establishing the digital canonical model of the invention.
Detailed Description
Various exemplary embodiments, features and aspects of the disclosure will be described in detail below with reference to the drawings. In the drawings, like reference numbers indicate identical or functionally similar elements. Although various aspects of the embodiments are illustrated in the accompanying drawings, the drawings are not necessarily drawn to scale unless specifically indicated.
The word "exemplary" is used herein to mean "serving as an example, embodiment, or illustration. Any embodiment described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments.
In addition, numerous specific details are set forth in the following detailed description in order to provide a better understanding of the present disclosure. It will be understood by those skilled in the art that the present disclosure may be practiced without some of these specific details. In some instances, methods, means, elements, and circuits well known to those skilled in the art have not been described in detail in order not to obscure the present disclosure.
According to the application, the digital standard model capable of identifying each behavior type is deployed on the background cloud server of the community, behaviors in different dimensionalities of resident users are identified and predicted, and the prediction result is used for feeding back, regulating and optimizing the algorithm structure of the digital standard model, so that the healthy development of community digitization is realized.
Through the continuously optimized digital standard model, the prediction, recognition and judgment of the behaviors of community resident users can be gradually improved, the accuracy of behavior recognition is improved, and the accuracy of community digital construction is improved.
In this embodiment, the background cloud server used in the community and the method for the user to log in to the background cloud server may be logged in through APP, applet, or the like, and the present embodiment is not limited to the method for logging in to the background cloud server.
Example 1
As shown in fig. 1, in one aspect of the present application, a digital community governance method for implementing behavior prediction by resident big data is provided, including the following steps:
s1, acquiring digital community resident big data;
The large community resident data are digitalized, and the community resident information of all aspects, such as behavior information, language information, gesture action information, text information and the like of the residents, can be collected through classification.
For example, the gesture action behavior information of the residents can be obtained by acquiring the gesture action behavior information of the users through an internet of things camera system (cloud camera and the like) established by the community, acquiring images of the gesture action information of the residents such as walking, running, falling, frame beating and the like, and identifying and calculating the gesture actions of the residents.
The server monitors the gesture actions of each resident (exposed to monitoring) in real time, calculates gesture action information (such as vector diagrams of upper limbs), and sends and stores the data in the cloud. And comparing the gesture action information by using a pre-established digital standard model aiming at gesture action recognition, so as to judge whether the action of residents accords with the action information specified by the model.
S2, performing digital standard judgment on community resident behaviors in the digital community resident big data through a preset digital standard model to obtain digital standard judgment results of the behaviors;
The digital canonical model is a behavior recognition model which is generated in advance aiming at different resident behavior information. For example, language behavior, gesture action behavior, learning behavior, interaction behavior, text behavior and other types of behavior information are collected, a large amount of behavior data of each type is collected in a deep learning mode, each type of behavior data is used as a model training set, each type of behavior recognition model is obtained through training, namely, each digital standard model is issued to a background cloud server of a community and used as an action standard recognition model in digital construction, and each behavior is specifically recognized.
The training and generating the corresponding model by the deep learning technology such as convolutional neural network is the prior art, and the embodiment is not described in detail.
And the digital standard model is used as an initial model, and is also trained and generated by adopting a deep learning technology. And identifying the digitalized standard model of each type of action, and correspondingly selecting the training data of the corresponding type.
As shown in fig. 3, as an alternative embodiment of the present application, optionally, the method for establishing a digital specification model includes:
S11, collecting behavior data of each type and preprocessing; the behavior data preprocessing mode can be to delete and adjust discrete data in the behavior data, or sort the discrete data according to the acquisition time of the behavior data, sort and sort the discrete data according to a gradient mode, and facilitate training work according to stages and gradients;
s22, taking the preprocessed behavior data as an initial training data set;
S33, adding behavior specification data to the initial training data set, and constructing an enhanced training data set aiming at the behavior; the initial training data set is a set of behavior data specifically generated for each resident behavior, and the resident behavior has uncertainty, discreteness and the like in daily life, so that the recognition accuracy of the model is affected. Therefore, the model generated by training the initial training data set is a digital standard model in an initial state, and as an initial model, the recognition accuracy is not high enough; the method of the embodiment is as follows: and adding a part of behavior specification data for residents in the initial training data set so as to improve the recognition accuracy of the generated model.
S44, adopting a deep learning method, taking the enhanced training data set as a model training sample, training and generating digital standard models aiming at different behaviors, and publishing and storing the digital standard models on a background cloud server.
For example, the behavior specification data of the gesture action can be obtained by collecting data of standard and specification actions, so as to obtain the behavior specification data of the gesture action, taking the behavior specification data as enhancement data, adding the enhancement data into an initial training data set, taking an enhancement training data set as a model training sample, and training again, so as to generate an enhancement model.
The enhancement model is a digital standard model after enhancement, and is released and stored on a background cloud server. Which can improve the accuracy of recognition of the behavior.
In this embodiment, the same training generation manner as described above may be adopted for the digitized canonical models of different types of actions, which is not described in detail in this embodiment.
The standard and standard actions of different types of actions can refer to the criteria of the action or can be constructed in a standardized way, and the embodiment is not limited.
In this embodiment, recognition and judgment of different types of actions are performed by using respective corresponding digital standard models, and respective recognition results are stored.
Therefore, a storage space is opened up by adopting a distributed storage mode, a certain type of digital standard model and the identified digital standard judgment result are independently stored, so that a user can select the corresponding storage space to check the identification result according to the action attribute when logging in the background cloud server, and community classification, search and other works are facilitated.
As an optional implementation manner of the present application, optionally, performing digital standard judgment on the community resident behaviors in the digital community resident big data through a preset digital standard model to obtain a digital standard judgment result of the behaviors, where the digital standard judgment result includes:
the community residents log in a background cloud server to obtain the digital standard model to which the respective behaviors belong;
Judging the behaviors of community residents through a preset behavior prediction algorithm, wherein the method comprises the following steps of:
extracting behavior characteristics and calculating to obtain characteristic values;
Comparing the characteristic value with a preset characteristic value:
If the characteristic value is more than or equal to (0.75-0.85) a preset characteristic value, indicating that the behaviors of community residents accord with the digital standard model;
And otherwise, sending the behavior specification and the nonstandard information aiming at the behavior, which are stored in the digital specification model corresponding to the behavior, to the community residents through the background cloud server.
In the scheme, after the background cloud server obtains the behavior data of the resident user, the behavior type is judged firstly, for example, if the current user behavior is judged to belong to gesture action behavior, a corresponding gesture action behavior digital standard model is called, and recognition judgment is carried out on the behavior data.
Inside each digital standard model, a corresponding behavior prediction algorithm is prestored and is used for judging behaviors.
The behavior prediction algorithm is a behavior recognition algorithm, and the present embodiment is not limited. For example, the identification can be performed by using an HMM algorithm, a DNN algorithm or the like.
The method for extracting the behavior characteristics and calculating the characteristic values is a function of the algorithm, and the embodiment is not described in detail.
When the characteristic value is more than or equal to 0.85 preset characteristic value, the behavior of community residents is indicated to accord with the behavior specification specified in the digital specification model, and the behavior accords with the requirement of the community.
When the characteristic value is less than 0.85 preset characteristic value, the behavior of community residents is not in accordance with the behavior specification specified in the digital specification model, and the behavior is not in accordance with the requirement of the community. At this time, the residential user needs to be reminded and the behavior needs to be noted through the background cloud server.
At the moment, specific behavior specification information for the behavior and nonstandard information for the behavior are sent to the APP of the user, and the user is reminded to check and pay attention to the behavior.
The application also utilizes the behavior characteristics generated by the recognition and judgment results of each type of behavior to feed back and optimize the algorithm structure of the digital standard model, thereby further improving the recognition accuracy of the digital standard model.
Because the algorithm structure of the digital standard model is a general algorithm processing mode and has a unified processing flow aiming at the universal data through the algorithm structure. In this embodiment, the recognition feature is extracted by using the digital specification judgment result of each type of behavior to feed back the adjustment algorithm structure, so that the recognition capability of the digital specification model is optimized by targeted adjustment.
S3, classifying and collecting digital standard judgment results aiming at different types of behaviors, and generating behavior characteristics of each behavior;
the method comprises the steps of respectively collecting data from the digital standard judgment results of different types of behaviors, classifying and collecting the digital standard judgment results of a certain type of behaviors to obtain a large number of digital standard judgment results of the type of behaviors, uniformly collecting the identification calculation data of the type of behaviors as a secondary data set, extracting identification features (referred to herein as behavior features) from the data set (the feature extraction can be performed by adopting a convolutional neural network), and obtaining the identification features of the model on the behaviors.
And S4, carrying out feedback adjustment on the digital standard model by utilizing the behavior characteristics, optimizing the algorithm structure of the digital standard model, and continuously keeping refreshing.
The identification features are utilized to adjust the algorithm structure of the algorithm in the digital standard model, so that the algorithm is more optimized, and the behavior data can be identified more accurately.
The method for identifying characteristic feedback and optimizing and adjusting the algorithm structure in the model can be manually realized by a user, and the defects of the algorithm are found through comparison discovery of the algorithm structure, and the insufficient structural codes are optimized.
After each optimization adjustment of the model, the model optimization upgrade can be performed again at intervals. The continuous maintenance refreshing time of the model optimization upgrading can be set on a background cloud server. For example, the algorithm is updated once every two weeks, the digital development of the model is kept, the optimization is continuously deepened, and the algorithm is suitable for the pace of digital construction of communities.
As an optional embodiment of the present application, optionally, after digitizing the community-resident-data, further comprising:
Presetting a data analysis rule;
analyzing the big data of the digital community residents according to the data analysis rule to obtain analysis data;
According to the community digital classification standard, the analysis data are divided into different types of data formats, and a sequence table is adopted for output and storage respectively.
The digital community resident big data contains various types of behavior information, so that the digital community resident big data needs to be analyzed firstly to be analyzed into the behavior information of various types. The parsing rules are not limited.
And classifying the analysis information according to community digital classification standards, which are actually standards for standardizing each behavior.
And storing the classified behavior data of each type by adopting a corresponding data format such as mkv and MP4 formats adopted by audio and video.
In order to facilitate the input of massive behavior data in each type, the behavior data of each behavior is stored in a sequence table manner, so that orderly storage and data reading and writing of a cloud server are facilitated.
The format of the sequence table is not limited in this embodiment, and can be established by a user using an Excel or other tool.
As shown in fig. 2, as an alternative embodiment of the present application, optionally, the community digital classification standard is a digital specification model established for different community activity contents; the digital standard model is deployed and stored on a background cloud server of the community;
the digitized canonical model includes at least one of the following canonical models:
A text behavior digital canonical model;
A language behavior digital canonical model;
The gesture action behavior digitizes the canonical model.
In the above digital standard model, three models are selected in this embodiment, and are deployed on a background cloud server of a community, so as to implement behavior recognition in three dimensions.
The model building and application are specifically referred to above description and will not be repeated.
As an optional implementation manner of the present application, optionally, according to a community digitalized classification standard, the parsing data is divided into different types of data formats, and is output and stored by adopting a sequence table, including:
Constructing a sequence table aiming at different types of behaviors;
from the analysis data, the behavior data of different types are obtained in a dividing way, and the behavior data are output according to the data format corresponding to the type;
And inputting the behavior data of each type one by one according to the time sequence and storing the behavior data in a corresponding sequence table.
The sequence list is built independently for different behaviors because the behaviors have differences in expression forms, such as voice and gesture actions, and the sequence list is built according to the respective behavior types.
The sequence tables of different types are respectively and independently stored on the background cloud server.
After analyzing the data, distributing the data one by one according to the behavior attribute (type) and writing the data into each sequence table. The sequence is preferably ordered according to the time sequence for reading and writing the sequence table.
Based on the above embodiment, in another aspect of the present application, a digital community governance model is provided, including a digital specification model for different behaviors;
the digital standard model is built by adopting the method for building the digital standard model and is used for:
And carrying out digital standard judgment on the community resident behaviors in the digital community resident big data to obtain a digital standard judgment result of the behaviors.
As an alternative embodiment of the present application, optionally, at least one of the following canonical models is included:
A text behavior digital canonical model;
A language behavior digital canonical model;
The gesture action behavior digitizes the canonical model.
The specific application composition and application principle of the digital community management model are described in the method for establishing the digital standard model and the description of the digital community management method for realizing behavior prediction through resident big data, and are not repeated here.
Therefore, the digital standard model capable of identifying each behavior type is deployed on the background cloud server of the community, behaviors in different dimensions of resident users are identified and predicted, and the prediction result is used for feeding back, adjusting and optimizing the algorithm structure of the digital standard model, so that the healthy development of community digitization is realized. Through the continuously optimized digital standard model, the prediction, recognition and judgment of the behaviors of community resident users can be gradually improved, the accuracy of behavior recognition is improved, and the accuracy of community digital construction is improved.
It should be noted that, although the above behavior recognition/prediction is described by taking the algorithms of HMM, DNN, etc. as examples, those skilled in the art will understand that the present disclosure should not be limited thereto. In fact, the user can flexibly set the behavior recognition/prediction algorithm according to the actual application scene, so long as the technical function of the application can be realized according to the technical method.
It should be apparent to those skilled in the art that the implementation of all or part of the above-described embodiments of the method may be implemented by a computer program for instructing relevant hardware, and the program may be stored in a computer readable storage medium, and the program may include the steps of the embodiments of the control methods described above when executed.
It will be appreciated by those skilled in the art that implementing all or part of the above-described embodiment methods may be implemented by a computer program for instructing relevant hardware, and the program may be stored in a computer readable storage medium, and the program may include the embodiment flow of each control method as described above when executed. The storage medium may be a magnetic disk, an optical disk, a Read-only memory (ROM), a random access memory (RandomAccessMemory, RAM), a flash memory (flash memory), a hard disk (HARDDISKDRIVE, abbreviated as HDD), a Solid state disk (Solid-state STATEDRIVE, SSD), or the like; the storage medium may also comprise a combination of memories of the kind described above.
Example 2
Based on the implementation principle of embodiment 1, in another aspect, the application further provides a device for implementing the digital community governance method for implementing behavior prediction through resident big data, which comprises:
the community resident big data acquisition module is used for acquiring digital community resident big data;
the behavior specification judging module is used for carrying out digital specification judgment on community resident behaviors in the digital community resident big data through a preset digital specification model to obtain a digital specification judging result of the behaviors;
the behavior feature extraction module is used for classifying and collecting digital standard judgment results aiming at different types of behaviors and generating behavior features of the behaviors;
And the model optimization module is used for carrying out feedback adjustment on the digital standard model by utilizing the behavior characteristics, optimizing the algorithm structure of the digital standard model and continuously keeping refreshing.
For specific application functions of each module, please refer to description of embodiment 1, and this embodiment is not repeated.
The modules or steps of the invention described above may be implemented in a general-purpose computing device, they may be centralized in a single computing device, or distributed across a network of computing devices, or they may alternatively be implemented in program code executable by a computing device, such that they may be stored in a memory device and executed by a computing device, or they may be separately fabricated into individual integrated circuit modules, or multiple modules or steps within them may be fabricated into a single integrated circuit module. Thus, the present invention is not limited to any specific combination of hardware and software.
Example 3
Still further, another aspect of the present application provides a control system, including:
A processor;
a memory for storing processor-executable instructions;
The processor is configured to implement the digital community governance method for implementing behavior prediction through resident big data when executing the executable instructions.
Embodiments of the present disclosure control a system that includes a processor and a memory for storing processor-executable instructions. The processor is configured to execute the executable instructions to implement any of the foregoing digital community remediation methods for behavior prediction through resident big data.
Here, it should be noted that the number of processors may be one or more. Meanwhile, in the control system of the embodiment of the present disclosure, an input device and an output device may be further included. The processor, the memory, the input device, and the output device may be connected by a bus, or may be connected by other means, which is not specifically limited herein.
The memory is a computer-readable storage medium that can be used to store software programs, computer-executable programs, and various modules, such as: a program or a module corresponding to a digital community governance method for realizing behavior prediction through resident big data in an embodiment of the disclosure. The processor executes various functional applications and data processing of the control system by running software programs or modules stored in the memory.
The input device may be used to receive an input number or signal. Wherein the signal may be a key signal generated in connection with user settings of the device/terminal/server and function control. The output means may comprise a display device such as a display screen.
The foregoing description of the embodiments of the present disclosure has been presented for purposes of illustration and description, and is not intended to be exhaustive or limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the various embodiments described. The terminology used herein was chosen in order to best explain the principles of the embodiments, the practical application, or the technical improvement of the technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.
Claims (5)
1. The digital community treatment method for realizing behavior prediction through resident big data is characterized by comprising the following steps:
acquiring digital community resident big data;
Presetting a data analysis rule; analyzing the big data of the digital community residents according to the data analysis rule to obtain analysis data; dividing the analysis data into different types of data formats according to community digital classification standards, and respectively outputting and storing the analysis data by adopting a sequence table, wherein the method comprises the following steps: constructing a sequence table aiming at different types of behaviors; from the analysis data, the behavior data of different types are obtained in a dividing way, and the behavior data are output according to the data format corresponding to the type; the behavior data of each type are input one by one according to the time sequence and stored in the corresponding sequence table;
Carrying out digital standard judgment on community resident behaviors in the digital community resident big data through a preset digital standard model to obtain digital standard judgment results of the behaviors; the method for establishing the digital standard model comprises the following steps: collecting and preprocessing behavior data of each type; taking the preprocessed behavior data as an initial training data set; adding behavior specification data to the initial training data set, and constructing an enhanced training data set aiming at the behavior; adopting a deep learning method, taking an enhanced training data set as a model training sample, training and generating digital standard models aiming at different behaviors, and publishing and storing the digital standard models on a background cloud server; identifying and judging different types of actions, identifying by adopting respective corresponding digital standard models, respectively storing respective identification results, opening up a storage space by adopting a distributed storage mode, and independently storing a certain type of digital standard model and the identified digital standard judgment results, thereby facilitating the user to select the corresponding storage space to check the identification results according to action attributes when logging in a background cloud server, and facilitating community classification and retrieval;
Classifying and collecting digital standard judgment results aiming at different types of behaviors, and generating behavior characteristics of each behavior;
performing feedback adjustment on the digital standard model by utilizing the behavior characteristics, optimizing the algorithm structure of the digital standard model, and continuously keeping refreshing;
Identifying and predicting behaviors of residential users in different dimensions, and feeding back, adjusting and optimizing the algorithm structure of the digital standard model by using the prediction result so as to realize the healthy development of community digitization; through the continuously optimized digital standard model, the prediction, recognition and judgment of the behaviors of community resident users can be gradually improved, the accuracy of behavior recognition is improved, and the accuracy of community digital construction is improved.
2. The digital community governance method for realizing behavior prediction through resident big data according to claim 1, wherein the community digital classification standard is a digital standard model established for different community activity contents; the digital standard model is deployed and stored on a background cloud server of the community;
the digitized canonical model includes at least one of the following canonical models:
A text behavior digital canonical model;
A language behavior digital canonical model;
The gesture action behavior digitizes the canonical model.
3. The digital community governance method for realizing behavior prediction through big resident data according to claim 1, wherein the digital specification judgment is performed on community resident behaviors in the digital community big resident data through a preset digital specification model to obtain a digital specification judgment result of the behaviors, and the method comprises the following steps:
the community residents log in a background cloud server to obtain the digital standard model to which the respective behaviors belong;
Judging the behaviors of community residents through a preset behavior prediction algorithm, wherein the method comprises the following steps of:
extracting behavior characteristics and calculating to obtain characteristic values;
Comparing the characteristic value with a preset characteristic value:
if the characteristic value is more than or equal to a preset characteristic value, indicating that the behavior of community residents accords with the digital standard model, wherein the range of the preset characteristic value is 0.75-0.85;
And otherwise, sending the behavior specification and the nonstandard information aiming at the behavior, which are stored in the digital specification model corresponding to the behavior, to the community residents through the background cloud server.
4. An apparatus for implementing a digital community remediation method for implementing behavioral prediction by resident big data in accordance with any one of claims 1 to 3, comprising:
the community resident big data acquisition module is used for acquiring digital community resident big data;
the behavior specification judging module is used for carrying out digital specification judgment on community resident behaviors in the digital community resident big data through a preset digital specification model to obtain a digital specification judging result of the behaviors;
the behavior feature extraction module is used for classifying and collecting digital standard judgment results aiming at different types of behaviors and generating behavior features of the behaviors;
And the model optimization module is used for carrying out feedback adjustment on the digital standard model by utilizing the behavior characteristics, optimizing the algorithm structure of the digital standard model and continuously keeping refreshing.
5. A control system, comprising:
A processor;
a memory for storing processor-executable instructions;
Wherein the processor is configured to implement the digitized community remediation method of any one of claims 1 to 3 with resident big data to implement behavioral prediction when executing the executable instructions.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310197344.5A CN116226527B (en) | 2023-03-03 | 2023-03-03 | Digital community treatment method for realizing behavior prediction through resident big data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310197344.5A CN116226527B (en) | 2023-03-03 | 2023-03-03 | Digital community treatment method for realizing behavior prediction through resident big data |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116226527A CN116226527A (en) | 2023-06-06 |
CN116226527B true CN116226527B (en) | 2024-06-07 |
Family
ID=86580228
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310197344.5A Active CN116226527B (en) | 2023-03-03 | 2023-03-03 | Digital community treatment method for realizing behavior prediction through resident big data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116226527B (en) |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107818344A (en) * | 2017-10-31 | 2018-03-20 | 上海壹账通金融科技有限公司 | The method and system that user behavior is classified and predicted |
CN109166624A (en) * | 2018-09-21 | 2019-01-08 | 广州杰赛科技股份有限公司 | A kind of behavior analysis method, device, server, system and storage medium |
CN109783805A (en) * | 2018-12-17 | 2019-05-21 | 北京邮电大学 | A kind of network community user recognition methods and device |
CN109886699A (en) * | 2019-02-18 | 2019-06-14 | 北京三快在线科技有限公司 | Activity recognition method and device, electronic equipment, storage medium |
CN110232524A (en) * | 2019-06-14 | 2019-09-13 | 哈尔滨哈银消费金融有限责任公司 | Social networks cheats the construction method of model, antifraud method and apparatus |
WO2020169053A1 (en) * | 2019-02-21 | 2020-08-27 | Beijing Didi Infinity Technology And Development Co., Ltd. | Systems and methods for identifying abnormalities |
CN112820071A (en) * | 2021-02-25 | 2021-05-18 | 泰康保险集团股份有限公司 | Behavior identification method and device |
CN113901456A (en) * | 2021-11-10 | 2022-01-07 | 北京安天网络安全技术有限公司 | User behavior security prediction method, device, equipment and medium |
CN114140275A (en) * | 2021-11-10 | 2022-03-04 | 嘉兴海视嘉安智城科技有限公司 | Smart community cloud platform system with health care function |
CN114331786A (en) * | 2021-12-29 | 2022-04-12 | 福建工程学院 | Community management method and system based on Internet of things |
CN114511022A (en) * | 2022-01-24 | 2022-05-17 | 百度在线网络技术(北京)有限公司 | Feature screening, behavior recognition model training and abnormal behavior recognition method and device |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP5536518B2 (en) * | 2009-04-23 | 2014-07-02 | インターナショナル・ビジネス・マシーンズ・コーポレーション | Method, apparatus and computer for automatically extracting a system modeling metamodel language model for the system from the natural language specification of the system |
-
2023
- 2023-03-03 CN CN202310197344.5A patent/CN116226527B/en active Active
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107818344A (en) * | 2017-10-31 | 2018-03-20 | 上海壹账通金融科技有限公司 | The method and system that user behavior is classified and predicted |
CN109166624A (en) * | 2018-09-21 | 2019-01-08 | 广州杰赛科技股份有限公司 | A kind of behavior analysis method, device, server, system and storage medium |
CN109783805A (en) * | 2018-12-17 | 2019-05-21 | 北京邮电大学 | A kind of network community user recognition methods and device |
CN109886699A (en) * | 2019-02-18 | 2019-06-14 | 北京三快在线科技有限公司 | Activity recognition method and device, electronic equipment, storage medium |
WO2020169053A1 (en) * | 2019-02-21 | 2020-08-27 | Beijing Didi Infinity Technology And Development Co., Ltd. | Systems and methods for identifying abnormalities |
CN110232524A (en) * | 2019-06-14 | 2019-09-13 | 哈尔滨哈银消费金融有限责任公司 | Social networks cheats the construction method of model, antifraud method and apparatus |
CN112820071A (en) * | 2021-02-25 | 2021-05-18 | 泰康保险集团股份有限公司 | Behavior identification method and device |
CN113901456A (en) * | 2021-11-10 | 2022-01-07 | 北京安天网络安全技术有限公司 | User behavior security prediction method, device, equipment and medium |
CN114140275A (en) * | 2021-11-10 | 2022-03-04 | 嘉兴海视嘉安智城科技有限公司 | Smart community cloud platform system with health care function |
CN114331786A (en) * | 2021-12-29 | 2022-04-12 | 福建工程学院 | Community management method and system based on Internet of things |
CN114511022A (en) * | 2022-01-24 | 2022-05-17 | 百度在线网络技术(北京)有限公司 | Feature screening, behavior recognition model training and abnormal behavior recognition method and device |
Also Published As
Publication number | Publication date |
---|---|
CN116226527A (en) | 2023-06-06 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107871166B (en) | Feature processing method and feature processing system for machine learning | |
US20190311114A1 (en) | Man-machine identification method and device for captcha | |
CN109471944B (en) | Training method and device of text classification model and readable storage medium | |
CN109993102B (en) | Similar face retrieval method, device and storage medium | |
CN112395500B (en) | Content data recommendation method, device, computer equipment and storage medium | |
CN109598307B (en) | Data screening method and device, server and storage medium | |
CN110008821B (en) | Method and equipment for predicting updating of portrait base map | |
CN110888911A (en) | Sample data processing method and device, computer equipment and storage medium | |
CN113011889B (en) | Account anomaly identification method, system, device, equipment and medium | |
CN112202849A (en) | Content distribution method, content distribution device, electronic equipment and computer-readable storage medium | |
CN113962199B (en) | Text recognition method, text recognition device, text recognition equipment, storage medium and program product | |
CN111488501A (en) | E-commerce statistical system based on cloud platform | |
CN116383521B (en) | Subject word mining method and device, computer equipment and storage medium | |
CN116226527B (en) | Digital community treatment method for realizing behavior prediction through resident big data | |
CN112069803A (en) | Text backup method, device and equipment and computer readable storage medium | |
CN111310451B (en) | Sensitive word dictionary generating method and device, storage medium and electronic equipment | |
CN114491093B (en) | Multimedia resource recommendation and object representation network generation method and device | |
CN114385876B (en) | Model search space generation method, device and system | |
CN112862073B (en) | Compressed data analysis method and device, storage medium and terminal | |
CN111797765B (en) | Image processing method, device, server and storage medium | |
CN114969544A (en) | Hot data-based recommended content generation method, device, equipment and medium | |
CN114328995A (en) | Content recommendation method, device, equipment and storage medium | |
CN116842936A (en) | Keyword recognition method, keyword recognition device, electronic equipment and computer readable storage medium | |
CN114398484A (en) | Public opinion analysis method, device, equipment and storage medium | |
CN113822295A (en) | Image recognition method and device, electronic equipment and computer-readable storage medium |
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 |