CN112905717A - Public safety data distribution method and device - Google Patents
Public safety data distribution method and device Download PDFInfo
- Publication number
- CN112905717A CN112905717A CN202110215354.8A CN202110215354A CN112905717A CN 112905717 A CN112905717 A CN 112905717A CN 202110215354 A CN202110215354 A CN 202110215354A CN 112905717 A CN112905717 A CN 112905717A
- Authority
- CN
- China
- Prior art keywords
- public safety
- data
- safety data
- public
- hierarchical clustering
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 231100000279 safety data Toxicity 0.000 title claims abstract description 164
- 238000000034 method Methods 0.000 title claims abstract description 49
- 238000009826 distribution Methods 0.000 title claims abstract description 26
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 65
- 238000000605 extraction Methods 0.000 claims abstract description 18
- 238000010801 machine learning Methods 0.000 claims abstract description 17
- 238000012549 training Methods 0.000 claims abstract description 17
- 238000003860 storage Methods 0.000 claims description 13
- 238000005354 coacervation Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 10
- 238000005054 agglomeration Methods 0.000 claims description 6
- 230000002776 aggregation Effects 0.000 claims description 6
- 238000013500 data storage Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 5
- 210000002569 neuron Anatomy 0.000 description 13
- 238000004891 communication Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 7
- 239000011159 matrix material Substances 0.000 description 7
- 238000003064 k means clustering Methods 0.000 description 6
- 239000013598 vector Substances 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000004913 activation Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000002349 favourable effect Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000005065 mining Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002457 bidirectional effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 239000000470 constituent Substances 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000002354 daily effect Effects 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 230000002996 emotional effect Effects 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 230000007717 exclusion Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement 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
- 238000007781 pre-processing Methods 0.000 description 1
- 230000002028 premature Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 229960005486 vaccine Drugs 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
- G06F16/285—Clustering or classification
-
- 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
- G06N3/045—Combinations of 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention provides a public safety data distribution method and a device, comprising the following steps: acquiring public security data based on a public security data source; inputting the public safety data into a deep trust network model for feature extraction to obtain features corresponding to the public safety data; the deep trust network model is obtained by training based on a machine learning algorithm by using public safety sample data as input data and using sample characteristics corresponding to the public safety sample data as output data; and carrying out public safety data distribution by adopting a hierarchical clustering algorithm based on the public safety data and the characteristics corresponding to the public safety data. In the embodiment, the public safety data is subjected to feature extraction by means of the deep trust network, and the public safety data is shunted by adopting a hierarchical clustering algorithm, so that the problems of poor clustering effect and high clustering time consumption are solved, and the shunting of the public data is optimized.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a public safety data distribution method and device.
Background
With the development of mobile interconnection, various social network platforms with the same quality and different quality emerge continuously, and information creation, communication and sharing based on social relations are deepened continuously. The internet social networks and public websites generate a great amount of data which are closely related to public safety every day, such as public event reports, various kinds of true and false news which are enriched on the internet, attention of people to the public safety events, emotional opinions and the like. The data has high mining and utilization values. These daily generated public security data are a sequence of data that arrives in large, rapid, continuous amounts based on the order of the streaming data, and can be generally viewed as a dynamic data set that grows indefinitely over time, with potentially infinite and high-dimensional characteristics. Based on the above features, the distribution and storage of these public security data becomes a difficult problem. The existing public safety data shunting and storing technology is based on a physical hardware platform, such as a switch with a coupling coil connected to a cloud computing platform, to realize data shunting and storage, or to perform hardware shunting on data streams through an ULV processor, and is based on computer program software, such as a clustering algorithm of data.
Therefore, on one hand, the existing public security data classification and storage technology depends on more hardware, and the problems of missing division, wrong division and storage write-in failure can occur. On the other hand, the traditional clustering algorithm is used for processing the problem of static data offline clustering, and the K-means clustering algorithm needs to appoint the number of clustered clusters in advance, is very sensitive to the selection of an initial clustering center, and can cause different clustering results by randomly selecting different initial values, even can not obtain meaningful clustering results. Public safety data exists in high latitude, non-linear volume points. The traditional K-means clustering has the problems of poor clustering effect and high clustering time consumption in high-dimensional nonlinear data.
Disclosure of Invention
Aiming at the problems in the prior art, the embodiment of the invention provides a public safety data shunting method and device.
In a first aspect, an embodiment of the present invention provides a public safety data offloading method, including:
acquiring public security data based on a public security data source;
inputting the public safety data into a deep trust network model for feature extraction to obtain features corresponding to the public safety data; the deep trust network model is obtained by training based on a machine learning algorithm by using public safety sample data as input data and using sample characteristics corresponding to the public safety sample data as output data;
and carrying out public safety data distribution by adopting a hierarchical clustering algorithm based on the public safety data and the characteristics corresponding to the public safety data.
Further, the performing public safety data distribution by using a hierarchical clustering algorithm based on the public safety data and the characteristics corresponding to the public safety data includes:
and carrying out public safety data distribution by adopting a coacervation hierarchical clustering algorithm based on the public safety data and the characteristics corresponding to the public safety data.
Further, the performing public safety data distribution by using a hierarchical clustering algorithm based on the public safety data and the characteristics corresponding to the public safety data specifically includes:
inputting the public safety data and the characteristics corresponding to the public safety data into a hierarchical clustering model or an agglomeration hierarchical clustering model to obtain a public safety data shunting result; the hierarchical clustering model or the coacervation hierarchical clustering model is obtained by training based on a machine learning algorithm by adopting public safety sample data and sample characteristics corresponding to the public safety sample data as input data and public safety sample data shunting results as output data.
Further, still include:
and carrying out public safety data storage based on the public safety data shunting result.
In a second aspect, an embodiment of the present invention provides a public safety data offloading device, including:
the acquisition module is used for acquiring the public safety data based on the public safety data source;
the deep trust network module is used for inputting the public security data into a deep trust network model for feature extraction to obtain features corresponding to the public security data; the deep trust network model is obtained by training based on a machine learning algorithm by using public safety sample data as input data and using sample characteristics corresponding to the public safety sample data as output data;
and the shunting module is used for shunting the public safety data by adopting a hierarchical clustering algorithm based on the public safety data and the characteristics corresponding to the public safety data.
Further, the shunting module is configured to:
and carrying out public safety data distribution by adopting a coacervation hierarchical clustering algorithm based on the public safety data and the characteristics corresponding to the public safety data.
Further, the shunting module is specifically configured to:
inputting the public safety data and the characteristics corresponding to the public safety data into a hierarchical clustering model or an agglomeration hierarchical clustering model to obtain a public safety data shunting result; the hierarchical clustering model or the coacervation hierarchical clustering model is obtained by training based on a machine learning algorithm by adopting public safety sample data and sample characteristics corresponding to the public safety sample data as input data and public safety sample data shunting results as output data.
Further, still include:
and the storage module is used for storing the public safety data based on the public safety data shunting result. In a third aspect, an embodiment of the present invention further provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the steps of the public safety data offloading method according to the first aspect when executing the program.
In a fourth aspect, the present invention further provides a non-transitory computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the common security data offloading method according to the first aspect.
According to the technical scheme, the public safety data shunting method and device provided by the embodiment of the invention acquire the public safety data based on the public safety data source; inputting the public safety data into a deep trust network model for feature extraction to obtain features corresponding to the public safety data; the deep trust network model is obtained by training based on a machine learning algorithm by using public safety sample data as input data and using sample characteristics corresponding to the public safety sample data as output data; and carrying out public safety data distribution by adopting a hierarchical clustering algorithm based on the public safety data and the characteristics corresponding to the public safety data. In the embodiment, the public safety data is subjected to feature extraction by means of the deep trust network, and the public safety data is shunted by adopting a hierarchical clustering algorithm, so that the problems of poor clustering effect and high clustering time consumption are solved, and the shunting of the public data is optimized.
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 introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a schematic flowchart of a public safety data offloading method according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a constrained Boltzmann machine according to an embodiment of the present invention;
FIG. 3 is a diagram illustrating a deep trust network DBN according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of an algorithm flow according to an embodiment of the present invention;
FIG. 5 is a block diagram of a public safety data offload algorithm provided in an embodiment of the present invention;
FIG. 6 is a schematic structural diagram of a public safety data offloading device according to an embodiment of the present invention;
fig. 7 is a schematic physical structure diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some embodiments, but not all embodiments, of the present invention. 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. The public safety data offloading method provided by the present invention will be explained and explained in detail by specific embodiments.
Fig. 1 is a schematic flowchart of a public safety data offloading method according to an embodiment of the present invention; as shown in fig. 1, the method includes:
step 101: public security data is obtained based on a public security data source.
In this step, it can be understood that the public security data source is, for example, online data captured by a social network platform such as a social network site, a forum, a microblog, or offline data acquired by a public security direct reporting system. And extracting the public safety data based on the public safety data source, and further preprocessing the obtained public safety data, such as data cleaning, denoising and removing.
Step 102: inputting the public safety data into a deep trust network model for feature extraction to obtain features corresponding to the public safety data; the deep trust network model is obtained by training based on a machine learning algorithm by using public safety sample data as input data and using sample characteristics corresponding to the public safety sample data as output data.
In this step, it should be noted that, a Deep Belief Network (DBN), which can be used for unsupervised learning, is similar to a self-coding machine; and also can be used for supervised learning and used as a classifier. From the aspect of unsupervised learning, the method aims to retain the characteristics of original features as much as possible, reduce the dimensionality of the features and remove noise. From supervised learning, the aim is to make the classification error rate as small as possible. Regardless of supervised Learning or unsupervised Learning, the nature of DBN is the process of Feature Learning, i.e. how to get better Feature expression. In the embodiment, the characteristics of high dimensionality, large quantity and noise are combined with public security data, and the public security data is subjected to feature extraction by means of a deep trust network, so that the problem of data clustering and shunting is solved.
DBNs are composed of multiple layers of neurons, divided into dominant and recessive neurons. Dominant neurons are used to accept input and recessive neurons are used to extract features. The bottom most layer represents data vectors (data vectors), each neuron representing a dimension of the data vector. The constituent elements of the DBN are Restricted Boltzmann Machines (RBMs), as shown in fig. 2.
A Restricted Boltzmann Machine (RBM) is an energy model based on implicit variables. The restricted boltzmann machine has only two layers of neurons: the Visible Layer (Visible Layer) and the Hidden Layer (Hidden Layer) are connected without any connection in the layers, and the layers are connected in a full-connection bidirectional mode. Each visible layer node and hidden layer node has two states: the value of the activated state is 1, the value of the inactivated state is 0, which represents which nodes the model will select for use, the activated nodes are used (1), and the inactivated nodes are not used (0).
The energy of the visible layer node state and the hidden layer node state is defined as:
the probability of cryptomelanic neuron activation is:
apparent layer neurons can also be activated by hidden layer neurons with the probability:
wherein θ ═ Wij，bi，cjAnd (5) obtaining parameters of the RBM, u is an input vector, h is an output vector, and b, c and W are corresponding weights and offset values through learning. Sigma is sigmoid function, and the threshold value is 0-1.
When an input vector x is input into a display layer, the RBM calculates the probability P of opening each hidden layer neuron according to the activation probability of the display layer neurons, a random number u of 0-1 is taken as a threshold, the neurons larger than the threshold are activated, and otherwise the neurons are not activated.
And connecting a plurality of RBMs in series to form a DBN, wherein the hidden layer of the previous RBM is the display layer of the next RBM, and the output of the previous RBM is the input of the next RBM. As shown in fig. 3.
Step 103: and carrying out public safety data distribution by adopting a hierarchical clustering algorithm based on the public safety data and the characteristics corresponding to the public safety data.
In this step, it should be noted that the better result of the conventional K-means clustering should be: the similarity between samples belonging to the same class is as high as possible, while the difference between samples of different classes is as large as possible. The K-means algorithm needs to appoint the number of clusters to be clustered in advance, continuously performs circular distribution data, continuously calculates and updates the centers of the clusters, and enables the calculation amount of the algorithm to be increased; the algorithm is easily interfered by isolated points and noise points of the data set, Euclidean distances are used in the K-means algorithm, the functions of all attributes are considered to be the same, and the actual situation is not considered, so that the clustering effect is not ideal.
The above problems can be overcome using hierarchical clustering. Hierarchical clustering first calculates the distance between samples. Each time merging the closest points to the same class. Then, the distance between the classes is calculated, and the classes with the closest distance are combined into a large class. And continuously merging until a class is synthesized. The hierarchical clustering algorithm is divided into two types according to the order of hierarchical decomposition, namely, from bottom to top and from top to bottom, i.e., an agglomerative hierarchical clustering algorithm and a disruptive hierarchical clustering algorithm (also known as bottom-up) and top-down (top-down). The bottom-up method is that each individual (object) is a class at first, then the same class is searched according to link, and finally a 'class' is formed. The top-down method is the reverse, all individuals are in a "class" at first, then exclusions are excluded according to the link, and finally each individual is in a "class".
For example, the hierarchical clustering algorithm used in the present embodiment is a minimum distance-based agglomerative hierarchical clustering. Assuming that the common security data sample set has N data samples, the steps are as follows:
(1) regarding each data object as a cluster, only one object in each cluster, and calculating the distance d (i, j) between them to obtain an initialization matrix.
(2) The two clusters that are closest together are merged into a new cluster when d (i, j) is the smallest.
(3) And (4) recalculating the distances d (i, j) between the new cluster and all other clusters, namely selecting the value with the minimum distance from the distances between the newly combined cluster and the original cluster as the similarity between the two clusters.
(4) The second and third steps are repeated until all clusters are finally merged into one cluster or a certain termination condition is reached.
The specific steps of the agglomerative hierarchical clustering algorithm based on the minimum distance method are shown below.
Because the cohesive hierarchical clustering algorithm does not have a global objective function similar to a basic K mean value, the problem of falling into local minimum or difficulty in selecting initial points does not exist, and the problem of initializing the number of the initial clusters is also avoided.
According to the technical scheme, the public safety data shunting method provided by the embodiment of the invention obtains the public safety data based on the public safety data source; inputting the public safety data into a deep trust network model for feature extraction to obtain features corresponding to the public safety data; the deep trust network model is obtained by training based on a machine learning algorithm by using public safety sample data as input data and using sample characteristics corresponding to the public safety sample data as output data; and carrying out public safety data distribution by adopting a hierarchical clustering algorithm based on the public safety data and the characteristics corresponding to the public safety data. In the embodiment, the public safety data is subjected to feature extraction by means of the deep trust network, and the public safety data is shunted by adopting a hierarchical clustering algorithm, so that the problems of poor clustering effect and high clustering time consumption are solved, and the shunting of the public data is optimized.
On the basis of the foregoing embodiment, in this embodiment, the performing public security data splitting by using a hierarchical clustering algorithm based on the public security data and features corresponding to the public security data includes:
and carrying out public safety data distribution by adopting a coacervation hierarchical clustering algorithm based on the public safety data and the characteristics corresponding to the public safety data.
On the basis of the foregoing embodiment, in this embodiment, the performing public security data splitting by using a hierarchical clustering algorithm based on the public security data and features corresponding to the public security data specifically includes:
inputting the public safety data and the characteristics corresponding to the public safety data into a hierarchical clustering model or an agglomeration hierarchical clustering model to obtain a public safety data shunting result; the hierarchical clustering model or the coacervation hierarchical clustering model is obtained by training based on a machine learning algorithm by adopting public safety sample data and sample characteristics corresponding to the public safety sample data as input data and public safety sample data shunting results as output data.
In this embodiment, for example, assuming that there are N public secure data objects to be clustered, and the distance matrix size is N × N, the basic process of the minimum distance-based agglomerative hierarchical clustering method is as follows:
let N × N similarity matrix D ═ D (i, j) ]. clustering results are represented by numbers 0, 1, 2 …, (c-1), l (m) represents the hierarchy of the mth cluster, cluster numbers are represented by (m), and the similarity coefficients (values in the distance matrix) of clusters (r) and(s) are represented by D [ (r),(s) ]. The algorithm is described in detail as follows:
Step1：L(0)＝0，m＝0.
step 2: from all the current cluster pairs, the two clusters (r),(s) most similar to each other are found according to d [ (r),(s) ] -mind [ (i), (j) ].
Step 3: the serial number of the cluster is added with 1, that is, m ═ m +1, the clusters (r),(s) are combined, and the level of the cluster l (m) ═ d [ (r),(s) ].
Step 4: the similarity matrix D is updated, the corresponding rows and columns of the cluster (r),(s) are deleted, and the corresponding rows and columns of the newly generated cluster are added to the matrix. The similarity between the newly generated cluster (r, s) in the similarity matrix and the original cluster (k) is defined by the following formula: d [ (k), (r, s) ] -min d [ (k), (r) ], d [ (k),(s) ].
Step 5: steps 2-4 are repeated until all objects are grouped into a cluster.
The algorithm flow is shown in fig. 4 below.
On the basis of the above embodiment, in this embodiment, the method further includes:
and carrying out public safety data storage based on the public safety data shunting result.
In the embodiment, the public safety data is stored through the public safety data shunting result, and compared with the method of directly storing the disordered public safety data, the method is more favorable for risk study and judgment. In the embodiment, public security, particularly internet public sentiment data, is sufficiently analyzed and feature extracted through a deep trust network, and public security data with the same or similar features are hierarchically clustered, for example, the features of public security related data on the internet are sufficiently utilized according to different semantics, different emotions and different contents, so that compared with the method of directly storing disordered public security data, the method is more favorable for risk study and judgment.
In order to better understand the embodiment, the following further describes the content of the embodiment of the present invention, but the present invention is not limited to the following embodiment.
Deep trust network based clustering: deep trust network and clustering are unsupervised learning methods, which are used for mining internal structures and characteristics of data, and simultaneously face the challenges in time cost and accuracy brought by large-scale data. In combination with the common part of the two, the embodiment provides a hierarchical clustering algorithm based on a deep trust network for data distribution. The algorithmic framework is shown in fig. 5:
referring to fig. 5, firstly, inputting cleaned public security data to a deep trust network, performing feature extraction, and outputting features corresponding to the public security data; and then inputting the public safety data and the characteristics corresponding to the public safety data into a hierarchical clustering model to carry out public safety data shunting, thereby obtaining public safety data shunting results (shunting 1, shunting 2, in. Specifically, the method comprises the following steps:
the method comprises the steps of firstly capturing internet public security public opinion data in a certain time period, inputting a text data set to a deep trust network for subject feature extraction in order to classify, store and analyze the captured internet public opinion data according to event subjects, then inputting the network data and subject extracted by the deep trust network to a hierarchical clustering model, carrying out data distribution and storage on all the internet public opinion data according to subjects (such as shin-top vaccine, Dallas jump window events and the like), and finally obtaining an internet public opinion database based on the subject events.
The K-means clustering algorithm needs to indicate the number of clustered clusters in advance, has high sensitivity to initial center selection, is easy to fall into local optimum under the condition of improper initial center selection, and has premature convergence. The hierarchical clustering algorithm using the clustering does not have a global objective function similar to the basic K mean value, so that the problem that the local minimum problem is involved or the initial point is difficult to select does not exist. Compared with the traditional K-means clustering algorithm, the characteristic makes the invention more suitable for public safety data clustering. From the aspect of unsupervised learning, a Deep Belief Network (DBN) can keep the characteristics of original features as much as possible, meanwhile, the dimensionality of the features is reduced, noise is removed, and the essence of the DBN is how to obtain better feature expression. The invention performs feature extraction on the public security data by means of the deep trust network, thereby optimizing the solution of data distribution storage.
The embodiment of the invention is suitable for the shunting clustering of data, such as data obtained in real time in the fields of network monitoring, sensor networks, aerospace, meteorological measurement and control, financial service and the like, and accords with the relevant conditions of the streaming data shunting clustering; the embodiment of the invention can replace the traditional shunting method based on physical hardware and the traditional K-means clustering algorithm based on software.
Fig. 6 is a schematic structural diagram of a public safety data offloading device according to an embodiment of the present invention, and as shown in fig. 6, the device includes: an acquisition module 201, a deep trust network module 202, and a offloading module 203, wherein:
the acquiring module 201 is configured to acquire the public security data based on a public security data source;
the deep trust network module 202 is configured to input the public security data to a deep trust network model for feature extraction, so as to obtain features corresponding to the public security data; the deep trust network model is obtained by training based on a machine learning algorithm by using public safety sample data as input data and using sample characteristics corresponding to the public safety sample data as output data;
and the shunting module 203 is used for shunting the public safety data by adopting a hierarchical clustering algorithm based on the public safety data and the characteristics corresponding to the public safety data.
On the basis of the foregoing embodiment, in this embodiment, the shunting module is configured to:
and carrying out public safety data distribution by adopting a coacervation hierarchical clustering algorithm based on the public safety data and the characteristics corresponding to the public safety data.
On the basis of the foregoing embodiment, in this embodiment, the shunting module is specifically configured to:
inputting the public safety data and the characteristics corresponding to the public safety data into a hierarchical clustering model or an agglomeration hierarchical clustering model to obtain a public safety data shunting result; the hierarchical clustering model or the coacervation hierarchical clustering model is obtained by training based on a machine learning algorithm by adopting public safety sample data and sample characteristics corresponding to the public safety sample data as input data and public safety sample data shunting results as output data.
On the basis of the above embodiment, in this embodiment, the method further includes: and the storage module is used for storing the public safety data based on the public safety data shunting result.
The public safety data offloading device provided in the embodiment of the present invention may be specifically configured to execute the public safety data offloading method in the foregoing embodiment, and the technical principle and the beneficial effect thereof are similar, and reference may be specifically made to the foregoing embodiment, which is not described herein again.
Based on the same inventive concept, an embodiment of the present invention provides an electronic device, which specifically includes the following components, with reference to fig. 7: a processor 301, a communication interface 303, a memory 302, and a communication bus 304;
the processor 301, the communication interface 303 and the memory 302 complete mutual communication through the communication bus 304; the communication interface 303 is used for realizing information transmission between related devices such as modeling software, an intelligent manufacturing equipment module library and the like; the processor 301 is used for calling the computer program in the memory 302, and the processor executes the computer program to implement the method provided by the above method embodiments, for example, the processor executes the computer program to implement the following steps: acquiring public security data based on a public security data source; inputting the public safety data into a deep trust network model for feature extraction to obtain features corresponding to the public safety data; the deep trust network model is obtained by training based on a machine learning algorithm by using public safety sample data as input data and using sample characteristics corresponding to the public safety sample data as output data; and carrying out public safety data distribution by adopting a hierarchical clustering algorithm based on the public safety data and the characteristics corresponding to the public safety data.
Based on the same inventive concept, yet another embodiment of the present invention further provides a non-transitory computer-readable storage medium, having stored thereon a computer program, which when executed by a processor is implemented to perform the methods provided by the above method embodiments, for example, acquiring common security data based on a common security data source; inputting the public safety data into a deep trust network model for feature extraction to obtain features corresponding to the public safety data; the deep trust network model is obtained by training based on a machine learning algorithm by using public safety sample data as input data and using sample characteristics corresponding to the public safety sample data as output data; and carrying out public safety data distribution by adopting a hierarchical clustering algorithm based on the public safety data and the characteristics corresponding to the public safety data.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods of the various embodiments or some parts of the embodiments.
In addition, in the present invention, terms such as "first" and "second" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "a plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
Moreover, in the present invention, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
Furthermore, in the description herein, reference to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A public safety data distribution method is characterized by comprising the following steps:
acquiring public security data based on a public security data source;
inputting the public safety data into a deep trust network model for feature extraction to obtain features corresponding to the public safety data; the deep trust network model is obtained by training based on a machine learning algorithm by using public safety sample data as input data and using sample characteristics corresponding to the public safety sample data as output data;
and carrying out public safety data distribution by adopting a hierarchical clustering algorithm based on the public safety data and the characteristics corresponding to the public safety data.
2. The method for splitting public safety data according to claim 1, wherein the splitting public safety data by using a hierarchical clustering algorithm based on the public safety data and features corresponding to the public safety data comprises:
and carrying out public safety data distribution by adopting a coacervation hierarchical clustering algorithm based on the public safety data and the characteristics corresponding to the public safety data.
3. The public safety data splitting method according to any one of claims 1 or 2, wherein the splitting of the public safety data is performed by using a hierarchical clustering algorithm based on the public safety data and features corresponding to the public safety data, and specifically comprises:
inputting the public safety data and the characteristics corresponding to the public safety data into a hierarchical clustering model or an agglomeration hierarchical clustering model to obtain a public safety data shunting result; the hierarchical clustering model or the coacervation hierarchical clustering model is obtained by training based on a machine learning algorithm by adopting public safety sample data and sample characteristics corresponding to the public safety sample data as input data and public safety sample data shunting results as output data.
4. The public safety data splitting method according to claim 1, further comprising:
and carrying out public safety data storage based on the public safety data shunting result.
5. A public safety data offload device, comprising:
the acquisition module is used for acquiring the public safety data based on the public safety data source;
the deep trust network module is used for inputting the public security data into a deep trust network model for feature extraction to obtain features corresponding to the public security data; the deep trust network model is obtained by training based on a machine learning algorithm by using public safety sample data as input data and using sample characteristics corresponding to the public safety sample data as output data;
and the shunting module is used for shunting the public safety data by adopting a hierarchical clustering algorithm based on the public safety data and the characteristics corresponding to the public safety data.
6. The public safety data offloading device of claim 5, wherein the offloading module is configured to:
and carrying out public safety data distribution by adopting a coacervation hierarchical clustering algorithm based on the public safety data and the characteristics corresponding to the public safety data.
7. The public safety data offloading device of any of claims 5 or 6, wherein the offloading module is specifically configured to:
inputting the public safety data and the characteristics corresponding to the public safety data into a hierarchical clustering model or an agglomeration hierarchical clustering model to obtain a public safety data shunting result; the hierarchical clustering model or the coacervation hierarchical clustering model is obtained by training based on a machine learning algorithm by adopting public safety sample data and sample characteristics corresponding to the public safety sample data as input data and public safety sample data shunting results as output data.
8. The public safety data splitting device of claim 5, further comprising:
and the storage module is used for storing the public safety data based on the public safety data shunting result.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the public safety data offload method of any of claims 1 to 4 when executing the program.
10. A non-transitory computer readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the public safety data offload method of any of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110215354.8A CN112905717A (en) | 2021-02-25 | 2021-02-25 | Public safety data distribution method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110215354.8A CN112905717A (en) | 2021-02-25 | 2021-02-25 | Public safety data distribution method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112905717A true CN112905717A (en) | 2021-06-04 |
Family
ID=76108414
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110215354.8A Pending CN112905717A (en) | 2021-02-25 | 2021-02-25 | Public safety data distribution method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112905717A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106226816A (en) * | 2016-09-12 | 2016-12-14 | 电子科技大学 | A kind of pre-stack seismic signal waveform sorting technique |
| CN107124410A (en) * | 2017-04-25 | 2017-09-01 | 厦门卓讯信息技术有限公司 | Network safety situation feature clustering method based on machine deep learning |
| US20200106788A1 (en) * | 2018-01-23 | 2020-04-02 | Hangzhou Dianzi University | Method for detecting malicious attacks based on deep learning in traffic cyber physical system |
| CN112132331A (en) * | 2020-09-15 | 2020-12-25 | 宝信软件(武汉)有限公司 | Steelmaking system early warning method and system based on deep learning |
-
2021
- 2021-02-25 CN CN202110215354.8A patent/CN112905717A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106226816A (en) * | 2016-09-12 | 2016-12-14 | 电子科技大学 | A kind of pre-stack seismic signal waveform sorting technique |
| CN107124410A (en) * | 2017-04-25 | 2017-09-01 | 厦门卓讯信息技术有限公司 | Network safety situation feature clustering method based on machine deep learning |
| US20200106788A1 (en) * | 2018-01-23 | 2020-04-02 | Hangzhou Dianzi University | Method for detecting malicious attacks based on deep learning in traffic cyber physical system |
| CN112132331A (en) * | 2020-09-15 | 2020-12-25 | 宝信软件(武汉)有限公司 | Steelmaking system early warning method and system based on deep learning |
Non-Patent Citations (1)
| Title |
|---|
| 杨慧婷等: "基于深度信念网络的K-means聚类算法研究", 《现代电子技术》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11106995B2 (en) | Automatic segmentation of a collection of user profiles | |
| Sharma et al. | Classification in pattern recognition: A review | |
| Fan et al. | Robust deep auto-encoding Gaussian process regression for unsupervised anomaly detection | |
| Liu et al. | Fuzzy mutual information-based multilabel feature selection with label dependency and streaming labels | |
| CN112529638B (en) | Service demand dynamic prediction method and system based on user classification and deep learning | |
| Ramalingaiah et al. | Twitter bot detection using supervised machine learning | |
| CN111641608A (en) | Abnormal user identification method and device, electronic equipment and storage medium | |
| CN115688024A (en) | Network abnormal user prediction method based on user content characteristics and behavior characteristics | |
| CN115588193A (en) | Visual question-answering method and device based on graph attention neural network and visual relation | |
| Papakyriakou et al. | Data mining methods: a review | |
| Fei et al. | Real-time detection of COVID-19 events from Twitter: A spatial-temporally Bursty-Aware method | |
| CN114842247B (en) | Characteristic accumulation-based graph convolution network semi-supervised node classification method | |
| CN112905717A (en) | Public safety data distribution method and device | |
| Umamaheswari et al. | Opinion mining using hybrid methods | |
| Straton et al. | Big social data analytics for public health: Comparative methods study and performance indicators of health care content on Facebook | |
| KR20220105792A (en) | AI-based Decision Making Support System utilizing Dynamic Text Sources | |
| CN116091133A (en) | Target object attribute identification method, device and storage medium | |
| Wang et al. | Towards fake news refuter identification: Mixture of Chi-Merge grounded CNN approach | |
| Ho et al. | Discovering community interests approach to topic model with time factor and clustering methods | |
| Kim et al. | Uncovering diffusion in academic publications using model-driven and model-free approaches | |
| CN112463964A (en) | Text classification and model training method, device, equipment and storage medium | |
| Singh et al. | Implication of Mathematics in Data Science Technology Disciplines | |
| Kaushik et al. | Sentiment analysis based on movie reviews using various classification techniques: a review | |
| Bohra et al. | Popularity Prediction of Social Media Post Using Tensor Factorization. | |
| Mohanty et al. | Fraud detection using outlier analysis: a survey |
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 |