CN114372114A - Travel track restoration method and system based on matrix decomposition model - Google Patents
Travel track restoration method and system based on matrix decomposition model Download PDFInfo
- Publication number
- CN114372114A CN114372114A CN202111366385.XA CN202111366385A CN114372114A CN 114372114 A CN114372114 A CN 114372114A CN 202111366385 A CN202111366385 A CN 202111366385A CN 114372114 A CN114372114 A CN 114372114A
- Authority
- CN
- China
- Prior art keywords
- information
- matrix
- user
- perception
- travel
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/80—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for detecting, monitoring or modelling epidemics or pandemics, e.g. flu
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- Public Health (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Pure & Applied Mathematics (AREA)
- Medical Informatics (AREA)
- Mathematical Optimization (AREA)
- Computing Systems (AREA)
- Pathology (AREA)
- Primary Health Care (AREA)
- Epidemiology (AREA)
- Algebra (AREA)
- Software Systems (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Remote Sensing (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a travel track restoration method and a travel track restoration system based on a matrix decomposition model, wherein the method comprises the following steps: obtaining first perception area information; partitioning the first sensing area information according to first partition information to obtain N grid records; constructing a first perception matrix based on the grid records; constructing a user sparse matrix according to the first user travel information and the first partition information; performing matrix decomposition analysis on the first perception matrix and the user sparse matrix to construct a matrix decomposition model; and recovering the user sparse matrix based on the matrix decomposition model to obtain a user complete matrix. The technical problem that the complete travel track of a confirmed person cannot be determined to cause epidemic situation diffusion in the prior art is solved. The technical effects of intelligently perfecting travel information of confirmed personnel, accurately tracking all closely contacted personnel and controlling continuous diffusion of epidemic situation are achieved.
Description
Technical Field
The invention relates to the field of artificial intelligence, in particular to a travel track restoration method and system based on a matrix decomposition model.
Background
Under the condition of epidemic outbreak, the method is a very important link for quickly isolating the infection source and the close contact person, but various subjective and objective factors still exist in the actual prevention and control process, such as the fact that the close contact person cannot be detected or isolated in time due to the fact that the confirmed diagnosis person hides the whereabouts; uncertainty of the moving track of the confirmed personnel, false alarm and the like all make disease prevention and control in a passive situation. With the rapid spread of mobile networks, mobile devices, represented by smartphones, are seen everywhere in daily life. Through carrying out removal crowd's intelligence perception collection and analysis to the relevant user behavior data of mobile intelligent equipment, can provide help for regional population statistics and personnel contact tracking in epidemic situation prevention and control, therefore need to discuss how to utilize information-based means helping hand epidemic situation prevention and control to normalize urgently.
In the process of implementing the technical scheme of the invention in the embodiment of the present application, the inventor of the present application finds that the above-mentioned technology has at least the following technical problems:
the technical problems that the complete travel track of a confirmed person cannot be determined, part of closely contacted persons cannot be detected, examined and isolated in time, and epidemic situations are further diffused exist in the prior art.
Disclosure of Invention
In view of this, the embodiment of the present application provides a method and a system for restoring a travel trajectory based on a matrix decomposition model, where the method includes: obtaining first perception area information; obtaining first partition information according to the first sensing area information; partitioning the first sensing area information according to the first partition information to obtain N grid records, wherein the N grid records have first time information, and N is a positive integer; constructing a first perception matrix based on the grid records; obtaining first user travel information according to the first sensing area information, wherein the first user travel information comprises a first user part track; constructing a user sparse matrix according to the first user travel information and the first partition information; performing matrix decomposition analysis on the first perception matrix and the user sparse matrix to construct a matrix decomposition model; and recovering the user sparse matrix based on the matrix decomposition model to obtain a user complete matrix, wherein the user complete matrix comprises complete travel information of the first user. The technical problems that in the prior art, the complete travel track of a confirmed person cannot be determined, part of closely contacted persons cannot be detected, checked and isolated in time, and epidemic situation is further diffused are solved. The intelligent perfect diagnosis personnel trip information that has reached, all close contact personnel of accurate pursuit further keep apart the detection to it, control epidemic situation and continuously spread's technical effect.
In view of the foregoing problems, the embodiments of the present application provide a travel trajectory reduction method and system based on a matrix decomposition model.
In a first aspect, the present application provides a travel trajectory reduction method based on a matrix decomposition model, where the method is implemented by a travel trajectory reduction system based on a matrix decomposition model, and the method includes: obtaining first perception area information; obtaining first partition information according to the first sensing area information; partitioning the first sensing area information according to the first partition information to obtain N grid records, wherein the N grid records have first time information, and N is a positive integer; constructing a first perception matrix based on the grid records; obtaining first user travel information according to the first sensing area information, wherein the first user travel information comprises a first user part track; constructing a user sparse matrix according to the first user travel information and the first partition information; performing matrix decomposition analysis on the first perception matrix and the user sparse matrix to construct a matrix decomposition model; and recovering the user sparse matrix based on the matrix decomposition model to obtain a user complete matrix, wherein the user complete matrix comprises complete travel information of the first user.
On the other hand, the present application further provides a travel trajectory reduction system based on a matrix decomposition model, which is used for executing the travel trajectory reduction method based on the matrix decomposition model according to the first aspect, wherein the system includes: a first obtaining unit: the first obtaining unit is used for obtaining first perception area information; a second obtaining unit: the second obtaining unit is used for obtaining first partition information according to the first sensing area information; a third obtaining unit: the third obtaining unit is configured to partition the first sensing area information according to the first partition information to obtain N grid records, where the N grid records have first time information and N is a positive integer; a first building unit: the first construction unit is used for constructing a first perception matrix based on the grid record; a fourth obtaining unit: the fourth obtaining unit is configured to obtain first user travel information according to the first sensing area information, where the first user travel information includes a first user partial trajectory; a second building element: the second construction unit is used for constructing a user sparse matrix according to the first user travel information and the first partition information; a third building element: the third construction unit is used for performing matrix decomposition analysis on the first perception matrix and the user sparse matrix to construct a matrix decomposition model; a fifth obtaining unit: the fifth obtaining unit is configured to recover the user sparse matrix based on the matrix decomposition model to obtain a user complete matrix, where the user complete matrix includes complete travel information of the first user.
In a third aspect, an embodiment of the present application further provides a travel trajectory reduction method and system based on a matrix decomposition model, including 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 method according to the first aspect when executing the program.
One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:
1. obtaining first perception region information; obtaining first partition information according to the first sensing area information; partitioning the first sensing area information according to the first partition information to obtain N grid records, wherein the N grid records have first time information, and N is a positive integer; constructing a first perception matrix based on the grid records; obtaining first user travel information according to the first sensing area information, wherein the first user travel information comprises a first user part track; constructing a user sparse matrix according to the first user travel information and the first partition information; performing matrix decomposition analysis on the first perception matrix and the user sparse matrix to construct a matrix decomposition model; and recovering the user sparse matrix based on the matrix decomposition model to obtain a user complete matrix, wherein the user complete matrix comprises complete travel information of the first user. The intelligent perfect diagnosis personnel trip information that has reached, all close contact personnel of accurate pursuit further keep apart the detection to it, control epidemic situation and continuously spread's technical effect.
The foregoing description is only an overview of the technical solutions of the present application, and the present application can be implemented according to the content of the description in order to make the technical means of the present application more clearly understood, and the following detailed description of the present application is given in order to make the above and other objects, features, and advantages of the present application more clearly understandable.
Drawings
In order to more clearly illustrate the embodiments or technical solutions in the prior art of the present invention, the drawings used in the description of the embodiments or prior art will be briefly described below, it is obvious that the drawings in the following description are only exemplary, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a schematic flow chart of a travel trajectory reduction method based on a matrix decomposition model according to an embodiment of the present application;
fig. 2 is a schematic flowchart of a method for obtaining information of a first sensing area according to an embodiment of the present application;
FIG. 3 is a flowchart illustrating a method for obtaining first partition information according to an embodiment of the present disclosure;
fig. 4 is a schematic flowchart of a method for performing a matrix recovery process by using a collaborative filtering algorithm for matrix analysis according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of a travel trajectory reduction system based on a matrix decomposition model according to an embodiment of the present application;
FIG. 6 is a schematic structural diagram of an exemplary electronic device according to an embodiment of the present application;
description of reference numerals:
a first obtaining unit 11, a second obtaining unit 12, a third obtaining unit 13, a first constructing unit 14, a fourth obtaining unit 15, a second constructing unit 16, a third constructing unit 17, a fifth obtaining unit 18, a bus 300, a receiver 301, a processor 302, a transmitter 303, a memory 304, a bus interface 305.
Detailed Description
The embodiment of the application provides a travel track restoration method and system based on a matrix decomposition model, and solves the technical problems that in the prior art, the complete travel track of a confirmed person cannot be determined, partial closely contacted persons cannot be detected, checked and isolated in time, and epidemic situations are further diffused. The intelligent perfect diagnosis personnel trip information that has reached, all close contact personnel of accurate pursuit further keep apart the detection to it, control epidemic situation and continuously spread's technical effect.
In the following, the technical solutions in the embodiments of the present application will be clearly and completely described with reference to the accompanying drawings, and it is to be understood that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments of the present application, and it should be understood that the present application is not limited by the example embodiments described herein. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present application without making any creative effort, shall fall within the protection scope of the present application. It should be further noted that, for the convenience of description, only some but not all of the elements relevant to the present application are shown in the drawings.
Summary of the application
Under the condition of epidemic outbreak, the method is a very important link for quickly isolating the infection source and the close contact person, but various subjective and objective factors still exist in the actual prevention and control process, such as the fact that the close contact person cannot be detected or isolated in time due to the fact that the confirmed diagnosis person hides the whereabouts; uncertainty of the moving track of the confirmed personnel, false alarm and the like all make disease prevention and control in a passive situation. With the rapid spread of mobile networks, mobile devices, represented by smartphones, are seen everywhere in daily life. Through carrying out removal crowd's intelligence perception collection and analysis to the relevant user behavior data of mobile intelligent equipment, can provide help for regional population statistics and personnel contact tracking in epidemic situation prevention and control, therefore need to discuss how to utilize information-based means helping hand epidemic situation prevention and control to normalize urgently. The technical problems that the complete travel track of a confirmed person cannot be determined, part of closely contacted persons cannot be detected, examined and isolated in time, and epidemic situations are further diffused exist in the prior art.
In view of the above technical problems, the technical solution provided by the present application has the following general idea:
the application provides a travel track restoration method based on a matrix decomposition model, which is applied to a travel track restoration system based on the matrix decomposition model, wherein the method comprises the following steps: obtaining first perception area information; obtaining first partition information according to the first sensing area information; partitioning the first sensing area information according to the first partition information to obtain N grid records, wherein the N grid records have first time information, and N is a positive integer; constructing a first perception matrix based on the grid records; obtaining first user travel information according to the first sensing area information, wherein the first user travel information comprises a first user part track; constructing a user sparse matrix according to the first user travel information and the first partition information; performing matrix decomposition analysis on the first perception matrix and the user sparse matrix to construct a matrix decomposition model; and recovering the user sparse matrix based on the matrix decomposition model to obtain a user complete matrix, wherein the user complete matrix comprises complete travel information of the first user.
Having thus described the general principles of the present application, various non-limiting embodiments thereof will now be described in detail with reference to the accompanying drawings.
Example one
Referring to fig. 1, an embodiment of the present application provides a travel trajectory reduction method based on a matrix decomposition model, where the method specifically includes the following steps:
step S100: obtaining first perception area information;
specifically, the matrix decomposition is the most common and popular model-based collaborative filtering technology, and the collaborative filtering simply refers to recommending information that the users may be interested in by utilizing the preferences of the groups with common interests, and individuals give responses to the information to a considerable extent through a collaborative mechanism and record the responses to achieve the purpose of filtering, so that the users of the same type can be helped to screen information, and the method is widely used in the fields of electronic commerce, resource sharing and the like. The first perception area refers to the maximum area range of the travel activities of the specific infectious disease diagnostician. The first perception region information comprises the area and the shape of the first perception region and all information of regions with the characteristics of crowd gathering, large pedestrian volume and the like, such as a market of a market, a school, a hospital, a station, a fruit and vegetable market and the like in the region.
Step S200: obtaining first partition information according to the first sensing area information;
specifically, the crowd sensing is to use the mobile device of a common user as a basic sensing unit to form a crowd sensing network through network communication, so as to realize sensing task distribution and sensing data collection and complete large-scale and complex social sensing tasks. The first partition refers to a dividing mode of dividing the first sensing region into a plurality of small regions based on the first sensing region information, and the first partition information includes the basis of dividing the first sensing region, the area and the number of each divided small region, and the content of main flowing crowd characteristics, people flow information and the like in the small region. The establishment of the first partition information provides an analysis basis for the subsequent improvement of the first user trip information.
Step S300: partitioning the first sensing area information according to the first partition information to obtain N grid records, wherein the N grid records have first time information, and N is a positive integer;
specifically, the first sensing region is divided into regions according to the division basis in the first partition information, and the N divided regions are the N meshes. The first time refers to the same specific time period, and generally refers to the time period after the confirmed infectious disease diagnosis personnel are infected with the virus and before the confirmed diagnosis is isolated. The N grid records are used for recording information such as crowd flow speed, crowd flow rules, crowd main flow direction and total flow quantity in a certain specific time within the N grid ranges. Wherein N is a positive integer.
Step S400: constructing a first perception matrix based on the grid records;
specifically, the grid recording refers to information recording of all small areas formed by partitioning the information of the first sensing area, and a first sensing matrix can be constructed based on a main flow direction of people in the grid recording, where the first sensing matrix is a matrix formed by the first sensing area.
Step S500: obtaining first user travel information according to the first sensing area information, wherein the first user travel information comprises a first user part track;
specifically, the first user refers to a person who obtains complete travel track information by using a travel track restoration system based on a matrix decomposition model, and generally refers to a diagnostician of an infectious disease. The trip information of the first user can be obtained according to the information of the first sensing area, the trip information of the first user generally refers to all self-activities and trip information in a time period after the diagnosed person is infected with the virus but before the confirmed person is diagnosed and isolated, and each complete trip information should include all information such as trip time, an activity area, a contacted person, whether the contacted person wears a protective tool or not in the trip or whether the contacted person is immune. The first user part track refers to all main travel activity information in the time period after the confirmed person is infected with the virus and before the confirmed person is confirmed and isolated, and the main travel activity information forms a part track of the confirmed person, namely the first user part track. The partial information of the first user trip provides basic data for the establishment of a subsequent sparse matrix.
Step S600: constructing a user sparse matrix according to the first user travel information and the first partition information;
specifically, a user sparse matrix is constructed according to the first user travel information and the first partition information. Based on the partial track of the first user included in the first user travel information, all major travel activity information, i.e., major activity areas, of the first user in the time period after being infected with the virus and before being diagnosed and isolated can be obtained. The first partition information refers to N small areas formed by dividing the first sensing area, namely the N grids. Combining the main activity area of the first user, a small area where the main activity of the first user is located in a time period after the first user is infected with the virus and before the first user is undiagnosed and quarantined, namely the grid, can be obtained. Based on the activity duration of the first user in each grid, a sparse matrix of the activity condition of the first user can be constructed. In the matrix, if the number of elements with a value of 0 is much greater than the number of elements other than 0, and the distribution of the elements other than 0 is irregular, the matrix is called a sparse matrix. In the sparse matrix in the embodiment of the present application, the number of the grids reached by the activity of the first user is far smaller than the total number of the grids after the first sensing area is divided, and because the activity of the first user has subjectivity, the distribution of the grids which are not reached by the activity of the first user does not have a strict rule.
Step S700: performing matrix decomposition analysis on the first perception matrix and the user sparse matrix to construct a matrix decomposition model;
step S800: and recovering the user sparse matrix based on the matrix decomposition model to obtain a user complete matrix, wherein the user complete matrix comprises complete travel information of the first user.
In particular, the matrix decomposition is a common method in matrix recovery, which has the advantage of finding potential structures in the data. The Matrix decomposition method used in the embodiment of the present application is non-negative Matrix decomposition (NMF), which makes all components after decomposition non-negative and simultaneously realizes reduction of nonlinear dimension. Briefly, for a data set in a high-dimensional space, matrix decomposition can perform a compressed representation of the data set in the original high-dimensional space by finding a set of bases and a representation of each data point under the base vector. Through matrix decomposition, the information in the first sensing matrix is compressed, and the efficiency and the accuracy of the system for processing data are improved.
The individual user sensor data usually exhibits a slow variation over a finite period of time, and this gradual phenomenon over a certain period of time is referred to as the stability of the time series. For infectious disease confirmed personnel with concealed travel tracks, on the premise that partial travel information of the infectious disease confirmed personnel is collected based on a mobile crowd sensing technology, a matrix decomposition model suitable for recovering complete travel information of the confirmed personnel is established. The whole matrix is restored based on matrix decomposition, so that a complete activity track of the confirmed diagnostician is obtained, further, early notification and early diagnosis can be carried out on the person who is in close contact with the confirmed diagnostician, and once the confirmed diagnostician is diagnosed, treatment can be isolated as early as possible, so that epidemic situation is controlled.
Further, as shown in fig. 2, step S100 in the embodiment of the present application further includes:
step S110: acquiring a first perception information set through perception mobile equipment worn by a second user group, wherein the perception information set comprises perception time and perception place;
step S120: obtaining a connection node of the first sensing information set;
step S130: obtaining a third user group according to the connection node;
step S140: obtaining a second perception information set through perception mobile equipment worn by the third user group;
step S150: repeating the steps to obtain an Mth perception information set, wherein M is a positive integer;
step S160: and obtaining the first perception region information according to the first perception information set, the second perception information set, the mth perception information set and the corresponding connection node.
Specifically, the second group of users may be people who have similar travel activities to the first user or people who live in the same area as the first user. The sensing technology is also called as information collection technology, has the main functions of identifying objects and collecting physical quantity information of required nodes, is positioned in a sensing layer in a mobile sensing system structure, and is a basis for realizing mobile sensing application and a source for acquiring mass data. The perception mobile device refers to a modern intelligent terminal device or a network device and is used for providing ubiquitous and comprehensive perception service for the human society and realizing close contact between people and objects. The second user group can obtain a first perception information set by wearing perception mobile equipment to perform mobile perception record on the first area. The first perception information set comprises the time and the perception place of the user in the second user group.
The connection node of the first perception information set is the time and the place of each user in the second user group for the first perception, and further obtains the next activity situation which is possibly performed by each user after the perception is performed by each user in combination with the time and place information, wherein the next activity is selected to be dining or entertainment based on the time characteristic, and the next activity is selected to be shopping in an adjacent market based on the place information. According to the connection node, a third user group can be obtained. To take a meal as the next activity, e.g., based on time, then all restaurant workers in the 1km vicinity may be designated as the third user group; if the next activity is shopping in a nearby mall based on the connection node of the location, all mall staff in the nearby 1km area can be defined as the third user group.
Further, the third group of users wearing the perception mobile device may obtain a second perception information set. A fourth user group is obtained based on the connecting nodes of the second set of awareness information. A fourth group of users wearing the cognitive mobile device may obtain the second set of cognitive information … … until an mth set of cognitive information is obtained, where M is a positive integer. And finally, the obtained first perception information set, the second perception information set, the Mth perception information set and the corresponding connection nodes are sorted and analyzed, and the first perception region information can be obtained.
The trip track restoration system performs perception recording on a target perception region through a logic meticulous method principle, then further performs second perception analysis on the situation related to the perception based on intelligent analysis on the perception result, and finally forms a logic perception information network in the first region to further construct the first perception region information. Achieving the technical effects of meticulous and exquisite processing and complete and effective processing result.
Further, as shown in fig. 3, step S200 in the embodiment of the present application further includes:
step S210: performing clustering analysis on the first sensing area information to obtain a clustering result set;
step S220: obtaining a clustering range information set according to the clustering result set;
step S230: acquiring a sensing range according to the first sensing area information;
step S240: and obtaining the first partition information according to the clustering range information set and the sensing range.
In particular, the cluster analysis refers to an analysis process that groups a set of physical or abstract objects into classes composed of similar objects. By performing cluster analysis on the first sensing region information, a cluster result set can be obtained. The cluster analysis in the embodiment of the application takes the degree of crowd aggregation at different positions in the first sensing area as a basis, the crowd aggregation degree is divided into 3 levels, the first level of crowd aggregation degree is the highest, the second level of crowd aggregation degree is moderate, and the third level of crowd aggregation degree is lower. For example, a first level may include stations, schools, etc., a second level may include residential areas, and a third level may be areas where highways are located, etc. And the system uniformly and completely divides all the positions in the first sensing area according to a clustering standard, and the division result is the clustering result set.
According to the clustering result set, a clustering range information set can be obtained, namely, after the first perception area is divided into 3 levels according to the people clustering degree, the area sum of the areas of all levels is obtained. Furthermore, the total area of the 3 levels is the area of the first sensing region. According to the first sensing region information, a sensing range, namely the area of the first sensing region, can be obtained. According to the clustering range information set and the sensing range, the first sensing area can be subjected to area division, and the first division information can be obtained.
The crowd gathering level of each position is obtained by analyzing the crowd gathering degree of different positions, and the first sensing area is divided based on the obtained level, so that the dividing result is reasonable and ordered.
Further, step S400 in the embodiment of the present application further includes:
step S410: the grid record is in an N x T format, T is a time period, and N is data in the time period T;
step S420: and extracting the N x T data in the grid record to form the first perception matrix, wherein the first perception matrix is an N x T matrix, each row is time point data of a sampling place, and each column is data of all sampling places at one time point.
Specifically, the grid record is in an N × T format, where T refers to a time period, specifically to a time period; n is the sensed data during a particular time period T. Extracting the N × T data in the grid record to form a first sensing matrix. The first sensing matrix is an N x T matrix, each row is time point data of a sampling place, and each column is data of all sampling places at one time point. The sensing matrix established based on time and place facilitates subsequent travel information recording of the first user, and the travel information of the first user is more visual in the form of the matrix, so that sorting and analysis are facilitated.
Further, step S700 in the embodiment of the present application further includes:
step S710: and performing matrix decomposition analysis on the first perception matrix and the user sparse matrix to perform matrix recovery by using a collaborative filtering algorithm of matrix analysis.
Specifically, the user sparse matrix is restored through a matrix decomposition model, so that a complete matrix of the user can be obtained, wherein the complete matrix of the user comprises complete travel information of the first user. The collaborative filtering is to simply recommend information interested by a user according to the preferences of a group with a certain interest and common experience, and individuals give a considerable response (such as scoring) to the information through a collaborative mechanism and record the response so as to filter the information and help others to filter the information. For the embodiment of the application, based on the same living area as the confirmed person, the daily activities of other users in the area have similar points with the confirmed person, and based on the mobile crowd sensing technology, a matrix decomposition model suitable for recovering the complete travel information of the confirmed person can be established. And further recovering the whole matrix based on a collaborative filtering algorithm of matrix decomposition. Through the recovered matrix, the system can analyze and generate the motion track of the first user, namely the diagnostician after infection and before diagnosis.
Further, as shown in fig. 4, step S800 in this embodiment of the present application further includes:
step S810: obtaining a co-occurrence matrix according to the user sparse matrix;
step S820: performing similarity analysis according to first user travel information in the user sparse matrix and the first perception matrix to obtain similar travel information;
step S830: obtaining travel supplementary information by using the similar travel information and the first user travel information;
step S840: and supplementing the user sparse matrix according to the travel supplementary information to obtain the user complete matrix.
Specifically, the user co-occurrence matrix is not used to calculate the similarity between each user pair, but is constructed by calculating and populating the number of co-occurrences of each user pair in the user scoring list for certain items. It describes the association between users, the more two users appear at the same time, the more likely they are related or similar. The user co-occurrence matrix functions similarly to a user similarity metric in a user-based non-distributed algorithm. Thus, it is a symmetric square matrix, with the number of rows and columns equal to the number of users in the data model, and the diagonal elements are replaced with 0's without meaning. Each row (and each column) expresses the similarity between a particular user and all other users. And performing similarity analysis according to the first user travel information in the user sparse matrix and the first perception matrix to obtain similar travel information. By multiplying the row vector of the item with the user co-occurrence matrix, a new row vector can be obtained. And obtaining travel supplementary information by using the similar travel information and the first user travel information. Further, the travel supplementary information is used for supplementing the user sparse matrix, and the user complete matrix can be obtained.
Further, step S820 in the embodiment of the present application further includes:
step S821: taking the first user travel information as a basic vector, and utilizing cosine similarity analysis to obtain a matrix information set most similar to the first user travel information;
step S822: and performing weighted calculation by using the similarity of the first user trip information and the similarity of the trip information corresponding to the matrix information set to obtain the similar trip information.
Specifically, the cosine similarity is also called cosine similarity, and the similarity is evaluated by calculating the cosine value of the included angle between two vectors. The cosine value of the 0-degree angle is 1, and the cosine value of any other angle is not more than 1; and its minimum value is-1. The system can obtain the travel information of other persons with higher travel similarity with the first user, namely the infectious disease confirmed person by comparing the travel information of all the users in the user set with the travel information of the first user, and respectively establishes the travel information of the other persons as a matrix, thereby obtaining the matrix information set which is most similar to the travel information of the first user.
And by utilizing the similarity degree data of the first user trip information, namely calculating the cosine values of the included angles of the first user and other user trip vectors similar to the trip information of the first user, further determining corresponding weighting coefficients based on the obtained cosine values, and carrying out weighting calculation by a system to obtain a possible trip scheme with the maximum probability of the first user, namely the similar trip information.
The travel track restoration system obtains travel information with different degrees of similarity with the travel information of the first user by analyzing the travel information similar to the first user, establishes a corresponding matrix for each type of travel information, and arranges all the matrixes to be called a matrix information set; and determining a weighting coefficient of each piece of travel information based on the similarity, so that the travel information with the maximum probability of the first user is obtained. And the calculation of big data enables the obtained possible travel information to be more accurate.
To sum up, the travel track restoration method based on the matrix decomposition model provided by the embodiment of the application has the following technical effects:
1. obtaining first perception region information; obtaining first partition information according to the first sensing area information; partitioning the first sensing area information according to the first partition information to obtain N grid records, wherein the N grid records have first time information, and N is a positive integer; constructing a first perception matrix based on the grid records; obtaining first user travel information according to the first sensing area information, wherein the first user travel information comprises a first user part track; constructing a user sparse matrix according to the first user travel information and the first partition information; performing matrix decomposition analysis on the first perception matrix and the user sparse matrix to construct a matrix decomposition model; and recovering the user sparse matrix based on the matrix decomposition model to obtain a user complete matrix, wherein the user complete matrix comprises complete travel information of the first user. The intelligent perfect diagnosis personnel trip information that has reached, all close contact personnel of accurate pursuit further keep apart the detection to it, control epidemic situation and continuously spread's technical effect.
Example two
Based on the same inventive concept as the travel track restoration method based on the matrix decomposition model in the foregoing embodiment, the present invention further provides a travel track restoration system based on the matrix decomposition model, please refer to fig. 5, where the system includes:
the first obtaining unit 11: the first obtaining unit 11 is configured to obtain first sensing region information;
the second obtaining unit 12: the second obtaining unit 12 is configured to obtain first partition information according to the first sensing area information;
the third obtaining unit 13: the third obtaining unit 13 is configured to partition the first sensing area information according to the first partition information to obtain N grid records, where the N grid records have first time information, and N is a positive integer;
the first building element 14: the first construction unit 14 is configured to construct a first perceptual matrix based on the mesh records;
the fourth obtaining unit 15: the fourth obtaining unit 15 is configured to obtain first user travel information according to the first sensing area information, where the first user travel information includes a first user partial trajectory;
second building element 16: the second constructing unit 16 is configured to construct a user sparse matrix according to the first user travel information and the first partition information;
the third building element 17: the third constructing unit 17 is configured to perform matrix decomposition analysis on the first sensing matrix and the user sparse matrix to construct a matrix decomposition model;
the fifth obtaining unit 18: the fifth obtaining unit 18 is configured to recover the user sparse matrix based on the matrix decomposition model, and obtain a user complete matrix, where the user complete matrix includes complete travel information of the first user.
Further, the system further comprises:
a sixth obtaining unit, configured to obtain, through a sensing mobile device worn by a second user group, a first sensing information set, where the sensing information set includes a sensing time and a sensing location;
a seventh obtaining unit, configured to obtain a connection node of the first set of perceptual information;
an eighth obtaining unit, configured to obtain a third user group according to the connection node;
a ninth obtaining unit, configured to obtain a second sensing information set through a sensing mobile device worn by the third user group;
a tenth obtaining unit, configured to repeat the above steps to obtain an mth sensing information set, where M is a positive integer;
an eleventh obtaining unit, configured to obtain the first sensing region information according to the first sensing information set, the second sensing information set, up to an mth sensing information set, and a corresponding connection node.
Further, the system further comprises:
a twelfth obtaining unit, configured to perform cluster analysis on the first sensing region information to obtain a cluster result set;
a thirteenth obtaining unit, configured to obtain a clustering range information set according to the clustering result set;
a fourteenth obtaining unit, configured to obtain a sensing range according to the first sensing region information;
a fifteenth obtaining unit, configured to obtain the first partition information according to the clustering range information set and the sensing range.
Further, the system further comprises:
a first recording unit, configured to record the mesh in an N × T format, where T is a time period and N is data in the time period T;
the first extraction unit is used for extracting N x T data in the grid records to form a first perception matrix, wherein the first perception matrix is an N x T matrix, each row is time point data of a sampling place, and each column is data of all sampling places at one time point.
Further, the system further comprises:
and the first analysis unit is used for carrying out matrix decomposition analysis on the first perception matrix and the user sparse matrix to carry out matrix recovery by utilizing a collaborative filtering algorithm of matrix analysis.
Further, the system further comprises:
a sixteenth obtaining unit, configured to obtain a co-occurrence matrix according to the user sparse matrix;
a seventeenth obtaining unit, configured to perform similarity analysis according to the first user travel information in the user sparse matrix and the first sensing matrix to obtain similar travel information;
an eighteenth obtaining unit, configured to obtain travel supplementary information by using the similar travel information and the first user travel information;
a nineteenth obtaining unit, configured to supplement the user sparse matrix according to the travel supplementary information, and obtain the user complete matrix.
Further, the system further comprises:
a twentieth obtaining unit, configured to obtain, by using the first user travel information as a basis vector, a matrix information set most similar to the first user travel information by using cosine similarity analysis;
a twenty-first obtaining unit, configured to perform weighted calculation by using the similarity of the first user trip information and the similarity of trip information corresponding to the matrix information set, so as to obtain similar trip information.
In the present description, each embodiment is described in a progressive manner, and each embodiment focuses on a difference from other embodiments, and the travel trajectory reduction method based on the matrix decomposition model in the first embodiment of fig. 1 and the specific example are also applicable to a travel trajectory reduction system based on the matrix decomposition model in the present embodiment. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Exemplary electronic device
The electronic apparatus of the embodiment of the present application is described below with reference to fig. 6.
Fig. 6 illustrates a schematic structural diagram of an electronic device according to an embodiment of the present application.
Based on the inventive concept of the travel trajectory restoration method based on the matrix decomposition model in the foregoing embodiment, the present invention further provides a travel trajectory restoration system based on the matrix decomposition model, wherein a computer program is stored thereon, and when the computer program is executed by a processor, the steps of any one of the foregoing emergency plan methods for blood purification center care are implemented.
Where in fig. 6 a bus architecture (represented by bus 300), bus 300 may include any number of interconnected buses and bridges, bus 300 linking together various circuits including one or more processors, represented by processor 302, and memory, represented by memory 304. The bus 300 may also link together various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art, and therefore, will not be described any further herein. A bus interface 305 provides an interface between the bus 300 and the receiver 301 and transmitter 303. The receiver 301 and the transmitter 303 may be the same element, i.e., a transceiver, providing a means for communicating with various other apparatus over a transmission medium.
The processor 302 is responsible for managing the bus 300 and general processing, and the memory 304 may be used for storing data used by the processor 302 in performing operations.
The application provides a travel track restoration method based on a matrix decomposition model, which is applied to a travel track restoration system based on the matrix decomposition model, wherein the method comprises the following steps: obtaining first perception area information; obtaining first partition information according to the first sensing area information; partitioning the first sensing area information according to the first partition information to obtain N grid records, wherein the N grid records have first time information, and N is a positive integer; constructing a first perception matrix based on the grid records; obtaining first user travel information according to the first sensing area information, wherein the first user travel information comprises a first user part track; constructing a user sparse matrix according to the first user travel information and the first partition information; performing matrix decomposition analysis on the first perception matrix and the user sparse matrix to construct a matrix decomposition model; and recovering the user sparse matrix based on the matrix decomposition model to obtain a user complete matrix, wherein the user complete matrix comprises complete travel information of the first user. The technical problems that in the prior art, the complete travel track of a confirmed person cannot be determined, part of closely contacted persons cannot be detected, checked and isolated in time, and epidemic situation is further diffused are solved. The intelligent perfect diagnosis personnel trip information that has reached, all close contact personnel of accurate pursuit further keep apart the detection to it, control epidemic situation and continuously spread's technical effect.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, apparatus, or computer program product. Accordingly, the present application may take the form of an entirely software embodiment, an entirely hardware embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application is in the form of a computer program product that may be embodied on one or more computer-usable storage media having computer-usable program code embodied therewith. And such computer-usable storage media include, but are not limited to: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk Memory, a Compact Disc Read-Only Memory (CD-ROM), and an optical Memory.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a system for implementing the functions specified in the flowchart 1 flow or flows and/or block 1 block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction system which implement the function specified in the flowchart flow or flows of FIG. 1 and/or block diagram block or blocks of FIG. 1.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart 1 flow or flows and/or block 1 block or blocks. While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (9)
1. A travel track restoration method and system based on a matrix decomposition model are disclosed, wherein the method comprises the following steps:
obtaining first perception area information;
obtaining first partition information according to the first sensing area information;
partitioning the first sensing area information according to the first partition information to obtain N grid records, wherein the N grid records have first time information, and N is a positive integer;
constructing a first perception matrix based on the grid records;
obtaining first user travel information according to the first sensing area information, wherein the first user travel information comprises a first user part track;
constructing a user sparse matrix according to the first user travel information and the first partition information;
performing matrix decomposition analysis on the first perception matrix and the user sparse matrix to construct a matrix decomposition model;
and recovering the user sparse matrix based on the matrix decomposition model to obtain a user complete matrix, wherein the user complete matrix comprises complete travel information of the first user.
2. The method of claim 1, wherein the obtaining first perception area information comprises:
acquiring a first perception information set through perception mobile equipment worn by a second user group, wherein the perception information set comprises perception time and perception place;
obtaining a connection node of the first sensing information set;
obtaining a third user group according to the connection node;
obtaining a second perception information set through perception mobile equipment worn by the third user group;
repeating the steps to obtain an Mth perception information set, wherein M is a positive integer;
and obtaining the first perception region information according to the first perception information set, the second perception information set, the mth perception information set and the corresponding connection node.
3. The method of claim 1, wherein the obtaining first partition information according to the first perception area information comprises:
performing clustering analysis on the first sensing area information to obtain a clustering result set;
obtaining a clustering range information set according to the clustering result set;
acquiring a sensing range according to the first sensing area information;
and obtaining the first partition information according to the clustering range information set and the sensing range.
4. The method of claim 1, wherein said constructing a first perceptual matrix based on said grid records comprises:
the grid record is in an N x T format, T is a time period, and N is data in the time period T;
and extracting the N x T data in the grid record to form the first perception matrix, wherein the first perception matrix is an N x T matrix, each row is time point data of a sampling place, and each column is data of all sampling places at one time point.
5. The method of claim 1, wherein the matrix decomposition analysis of the first perception matrix and the user sparse matrix is matrix recovery using a collaborative filtering algorithm of matrix analysis.
6. The method of claim 5, wherein the matrix recovery using a collaborative filtering algorithm of matrix analysis comprises:
obtaining a co-occurrence matrix according to the user sparse matrix;
performing similarity analysis according to first user travel information in the user sparse matrix and the first perception matrix to obtain similar travel information;
obtaining travel supplementary information by using the similar travel information and the first user travel information;
and supplementing the user sparse matrix according to the travel supplementary information to obtain the user complete matrix.
7. The method of claim 6, wherein the obtaining similar travel information by performing similarity analysis according to the first user travel information in the user sparse matrix and the first perception matrix comprises:
taking the first user travel information as a basic vector, and utilizing cosine similarity analysis to obtain a matrix information set most similar to the first user travel information;
and performing weighted calculation by using the similarity of the first user trip information and the similarity of the trip information corresponding to the matrix information set to obtain the similar trip information.
8. A travel track restoration system based on a matrix decomposition model, wherein the system comprises:
a first obtaining unit: the first obtaining unit is used for obtaining first perception area information;
a second obtaining unit: the second obtaining unit is used for obtaining first partition information according to the first sensing area information;
a third obtaining unit: the third obtaining unit is configured to partition the first sensing area information according to the first partition information to obtain N grid records, where the N grid records have first time information and N is a positive integer;
a first building unit: the first construction unit is used for constructing a first perception matrix based on the grid record;
a fourth obtaining unit: the fourth obtaining unit is configured to obtain first user travel information according to the first sensing area information, where the first user travel information includes a first user partial trajectory;
a second building element: the second construction unit is used for constructing a user sparse matrix according to the first user travel information and the first partition information;
a third building element: the third construction unit is used for performing matrix decomposition analysis on the first perception matrix and the user sparse matrix to construct a matrix decomposition model;
a fifth obtaining unit: the fifth obtaining unit is configured to recover the user sparse matrix based on the matrix decomposition model to obtain a user complete matrix, where the user complete matrix includes complete travel information of the first user.
9. A travel trajectory restoration system based on a matrix decomposition model, comprising a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor implements the steps of the method according to any one of claims 1 to 7 when executing the program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111366385.XA CN114372114B (en) | 2021-11-18 | 2021-11-18 | Travel track restoration method and system based on matrix decomposition model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111366385.XA CN114372114B (en) | 2021-11-18 | 2021-11-18 | Travel track restoration method and system based on matrix decomposition model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114372114A true CN114372114A (en) | 2022-04-19 |
| CN114372114B CN114372114B (en) | 2022-11-15 |
Family
ID=81138169
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111366385.XA Active CN114372114B (en) | 2021-11-18 | 2021-11-18 | Travel track restoration method and system based on matrix decomposition model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114372114B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104820905A (en) * | 2015-05-19 | 2015-08-05 | 威海北洋电气集团股份有限公司 | Space trajectory big data analysis-based person management and control method and system |
| CN106506705A (en) * | 2016-12-29 | 2017-03-15 | 平安科技（深圳）有限公司 | Listener clustering method and device based on location-based service |
| CN106649657A (en) * | 2016-12-13 | 2017-05-10 | 重庆邮电大学 | Recommended system and method with facing social network for context awareness based on tensor decomposition |
| CN110399919A (en) * | 2019-07-24 | 2019-11-01 | 中国科学院地理科学与资源研究所 | A kind of sparse track data interpolation reconstruction method of mankind's trip |
| CN111354472A (en) * | 2020-02-20 | 2020-06-30 | 戴建荣 | Infectious disease transmission monitoring and early warning system and method |
| CN112712903A (en) * | 2021-01-15 | 2021-04-27 | 杭州中科先进技术研究院有限公司 | Infectious disease monitoring method based on human-computer three-dimensional cooperative sensing |
| CN113220680A (en) * | 2021-04-29 | 2021-08-06 | 北京理工大学珠海学院 | Method, system, device and storage medium for determining epidemic situation close contact person track |
| CN113365211A (en) * | 2021-04-19 | 2021-09-07 | 中科劲点（北京）科技有限公司 | Epidemic situation forecasting method based on activity track, device, medium and electronic equipment thereof |
-
2021
- 2021-11-18 CN CN202111366385.XA patent/CN114372114B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104820905A (en) * | 2015-05-19 | 2015-08-05 | 威海北洋电气集团股份有限公司 | Space trajectory big data analysis-based person management and control method and system |
| CN106649657A (en) * | 2016-12-13 | 2017-05-10 | 重庆邮电大学 | Recommended system and method with facing social network for context awareness based on tensor decomposition |
| CN106506705A (en) * | 2016-12-29 | 2017-03-15 | 平安科技（深圳）有限公司 | Listener clustering method and device based on location-based service |
| CN110399919A (en) * | 2019-07-24 | 2019-11-01 | 中国科学院地理科学与资源研究所 | A kind of sparse track data interpolation reconstruction method of mankind's trip |
| CN111354472A (en) * | 2020-02-20 | 2020-06-30 | 戴建荣 | Infectious disease transmission monitoring and early warning system and method |
| CN112712903A (en) * | 2021-01-15 | 2021-04-27 | 杭州中科先进技术研究院有限公司 | Infectious disease monitoring method based on human-computer three-dimensional cooperative sensing |
| CN113365211A (en) * | 2021-04-19 | 2021-09-07 | 中科劲点（北京）科技有限公司 | Epidemic situation forecasting method based on activity track, device, medium and electronic equipment thereof |
| CN113220680A (en) * | 2021-04-29 | 2021-08-06 | 北京理工大学珠海学院 | Method, system, device and storage medium for determining epidemic situation close contact person track |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114372114B (en) | 2022-11-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ramchandani et al. | Deepcovidnet: An interpretable deep learning model for predictive surveillance of covid-19 using heterogeneous features and their interactions | |
| Xu et al. | Human mobility and socioeconomic status: Analysis of Singapore and Boston | |
| CN106682212B (en) | Social relation classification method and device based on user mobile behaviors | |
| Sareen et al. | IoT-based cloud framework to control Ebola virus outbreak | |
| Jankowska et al. | A framework for using GPS data in physical activity and sedentary behavior studies | |
| Xu et al. | Understanding aggregate human mobility patterns using passive mobile phone location data: A home-based approach | |
| Bakillah et al. | Geo-located community detection in Twitter with enhanced fast-greedy optimization of modularity: the case study of typhoon Haiyan | |
| Del Valle et al. | Mixing patterns between age groups in social networks | |
| CN112365171A (en) | Risk prediction method, device and equipment based on knowledge graph and storage medium | |
| CN111145917B (en) | Epidemic prevention and control-oriented large-scale population contact network modeling method | |
| Chen et al. | Large-scale mobile fitness app usage analysis for smart health | |
| Svoray et al. | Demonstrating the effect of exposure to nature on happy facial expressions via Flickr data: Advantages of non-intrusive social network data analyses and geoinformatics methodologies | |
| CN111506823A (en) | Information recommendation method and device and computer equipment | |
| Jin et al. | Predicting emergency medical service demand with bipartite graph convolutional networks | |
| CN115394455B (en) | Space-time spread prediction method and device for infectious diseases based on spatial clustering discrete grid | |
| Giacopelli | A full-scale agent-based model to hypothetically explore the impact of lockdown, social distancing, and vaccination during the COVID-19 pandemic in Lombardy, Italy: Model development | |
| Rahardja | Application of the c4. 5 algorithm for identifying regional zone status using a decision tree in the covid-19 series | |
| An et al. | VFP290k: A large-scale benchmark dataset for vision-based fallen person detection | |
| Fränti et al. | Averaging GPS segments competition 2019 | |
| CN114372114B (en) | Travel track restoration method and system based on matrix decomposition model | |
| Yoneki et al. | Distinct types of hubs in human dynamic networks | |
| Mahmoud et al. | A regulative norms mining algorithm for complex adaptive system | |
| Zhou et al. | Identifying golden routes in tourist areas based on AMP collectors | |
| CN104484329B (en) | Consumption hot spot method for tracing and device based on comment centre word timing variations analysis | |
| Fister Jr et al. | Discovering dependencies among mined association rules with population-based metaheuristics |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |