CN114842545A - Station degradation face recognition library distribution method based on roulette - Google Patents

Station degradation face recognition library distribution method based on roulette Download PDF

Info

Publication number
CN114842545A
CN114842545A CN202210787069.8A CN202210787069A CN114842545A CN 114842545 A CN114842545 A CN 114842545A CN 202210787069 A CN202210787069 A CN 202210787069A CN 114842545 A CN114842545 A CN 114842545A
Authority
CN
China
Prior art keywords
station
face
roulette
passengers
matrix
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
Application number
CN202210787069.8A
Other languages
Chinese (zh)
Inventor
焦科杰
陆斌
刘光杰
张鹏
高申
吴娟
熊伟
顾伟
王松松
胡天澍
潘辉
桂大发
徐亮
李熙源
张建
闫震
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Nanjing Panda Electronics Co Ltd
Nanjing Panda Information Industry Co Ltd
Original Assignee
Nanjing Panda Electronics Co Ltd
Nanjing Panda Information Industry Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Nanjing Panda Electronics Co Ltd, Nanjing Panda Information Industry Co Ltd filed Critical Nanjing Panda Electronics Co Ltd
Priority to CN202210787069.8A priority Critical patent/CN114842545A/en
Publication of CN114842545A publication Critical patent/CN114842545A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/51—Indexing; Data structures therefor; Storage structures
    • 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
    • G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/50—Maintenance of biometric data or enrolment thereof
    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
    • G07C9/00—Individual registration on entry or exit
    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
    • G07C9/00—Individual registration on entry or exit
    • G07C9/30—Individual registration on entry or exit not involving the use of a pass
    • G07C9/32—Individual registration on entry or exit not involving the use of a pass in combination with an identity check
    • G07C9/37—Individual registration on entry or exit not involving the use of a pass in combination with an identity check using biometric data, e.g. fingerprints, iris scans or voice recognition

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Multimedia (AREA)
  • Software Systems (AREA)
  • Databases & Information Systems (AREA)
  • Human Computer Interaction (AREA)
  • Pure & Applied Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Computational Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Health & Medical Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Algebra (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Operations Research (AREA)
  • Evolutionary Biology (AREA)
  • Probability & Statistics with Applications (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Artificial Intelligence (AREA)
  • Computing Systems (AREA)
  • Evolutionary Computation (AREA)
  • Medical Informatics (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention discloses a station degradation face recognition library distribution method based on roulette, which comprises the following steps: carrying out statistical preprocessing based on a big data OD of a passenger brushing face and passing through a gate; calculating the constant rate matrix of all passengers at all stations through multiple linear regression based on the statistical matrix on the statistical interval set; normalizing the constant rate matrix; and selecting a given number of degraded face libraries from all passengers on the matrix after the normalization processing based on a roulette method and distributing the degraded face libraries to each station. The degraded face library distributed to each station has the advantages of small scale and high coverage rate, can dynamically roll according to the travel rule of passengers, and can effectively support the stations to autonomously realize face recognition calculation under the condition that a network platform is available.

Description

Station degradation face recognition library distribution method based on roulette
Technical Field
The invention relates to urban rail transit, in particular to a station degradation face recognition library distribution method based on roulette.
Background
The development of urban rails is continuous, more and more urban people select subways as daily commuting tools, meanwhile, the development of machine vision technology is continuous, biological feature recognition technology represented by face recognition is advanced to our daily life, a typical face recognition framework comprises terminal service and cloud service, wherein a terminal can collect face images and extract features of the face images, and a cloud platform is responsible for storing a face library and comparing the face features, namely, the face recognition service is provided for terminal equipment. The rail transit is used for brushing the face and passing a floodgate face recognition system, and the payment level can be achieved by configuring a face recognition cloud platform with high concurrency, high real-time performance and high reliability on a line and a line network. The face brushing terminal equipment collects face information and sends the face information to the cloud platform to achieve rapid comparison in the large-scale face database.
In practical application, the terminal device and the cloud platform of the general network realize face recognition by network communication, but when the network communication fails or the cloud platform of the face recognition fails, the face-brushing gate-passing service loses availability. In order to guarantee the availability of the system, a face recognition server supporting degraded use is generally required to be deployed in a station configuration. Considering the economy of investment construction and the specific requirements of station-level downgrade usage, the server cannot support fast comparison of passengers of the whole network, requiring the distribution of a dedicated downgrade face library. In order to match the passenger with a higher probability in the station-level degraded face database and ensure that the face recognition service in the degraded mode has a certain availability, an effective method for distributing the face database is needed.
Disclosure of Invention
The purpose of the invention is as follows: the invention aims to provide a station degradation face recognition library distribution method based on roulette, so that a degradation face library distributed to each station has the advantages of small scale and high coverage rate, and can dynamically roll according to the travel rule of passengers.
The technical scheme is as follows: the invention relates to a station degradation face recognition library distribution method based on roulette, which comprises the following steps of:
(1) carrying out statistical preprocessing based on a big data OD of a passenger brushing face and passing through a gate;
is provided withnThe number of the passengers is increased, and the passengers,mindividual station, in statistical intervaltThe number of times that the passenger swipes in and out of the station can be determined by the matrixCRepresents:
Figure 108315DEST_PATH_IMAGE001
in a continuous set of statistical intervals
Figure 751786DEST_PATH_IMAGE002
In each statistical section
Figure 306527DEST_PATH_IMAGE003
The matrix elements of which are
Figure 35448DEST_PATH_IMAGE004
。
Whereinc ij Is shown in statistical intervalstThe number of times of face brushing of the inner passenger i at the station j. For different statistical intervalstDifferent statistical results can be obtainedC(t). For statistical interval set
Figure 317525DEST_PATH_IMAGE005
Obtaining statistical intervalsC(t k ) The matrix elements of which are
Figure 815503DEST_PATH_IMAGE006
. Since the OD data is long-term continuous, we can establish continuous observation on long-term continuous OD data by sliding the observation window K.
(2) Calculating the frequent rate matrix of all passengers at all stations based on the statistical matrix on the statistical interval setnA passenger is atmThe constant rate matrix R at each station:
Figure 790412DEST_PATH_IMAGE007
Figure 741050DEST_PATH_IMAGE008
the calculation method of (2) is as follows:
Figure 341665DEST_PATH_IMAGE009
regression parameters
Figure 694149DEST_PATH_IMAGE010
Obtained by the least squares method of the following regression problem, i.e. in a sliding implementation window, the following regression problem is constructed:
Figure 839959DEST_PATH_IMAGE011
wherein the content of the first and second substances,
Figure 277894DEST_PATH_IMAGE012
to define the number of swipes by passengers at stations i and j as described above, V is the number of sequential samples taken to perform the parametric regression estimation.
(3) Normalizing the constant rate matrix to obtain a matrix
Figure 167352DEST_PATH_IMAGE013
；
Figure 639922DEST_PATH_IMAGE014
Figure 707366DEST_PATH_IMAGE015
Wherein the content of the first and second substances,
Figure 632597DEST_PATH_IMAGE016
the elements of the constant rate matrix for the aforementioned locations characterize how often passengers swipe in and out at stations i and j.
(4) And selecting a given number of degraded face libraries from all passengers on the matrix after the normalization processing based on a roulette method and distributing the degraded face libraries to each station.
The matrix after normalization in the step (4)
Figure 325747DEST_PATH_IMAGE017
First, the column integration is performed to obtain
Figure 387243DEST_PATH_IMAGE018
And then, based on the roulette method, selecting a given number of degraded face libraries from all passengers and distributing the degraded face libraries to each station, wherein the step of selecting the given number of degraded face libraries from all passengers in the column score based on the roulette method specifically comprises the following steps:
(4.1) generating random numbers r which accord with [0,1] uniform distribution;
(4.2) find the number i so that the following equation is satisfied:
Figure 874857DEST_PATH_IMAGE019
(4.3) placing the passenger ID and the face feature library corresponding to the serial number i into a degraded face library of the station j, and skipping if the ID of the i exists in the library;
(4.4) whether the number of IDs in the library reaches the set number N, if not, returning to the step (4.1); if yes, jumping to the step (4.5);
and (4.5) outputting a face database distributed by the station j.
A computer storage medium having stored thereon a computer program which, when executed by a processor, implements a method of station demotion face recognition library distribution based on roulette.
A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing a method for allocating a station depopulation face recognition library based on roulette as described above when executing the computer program.
Has the advantages that: compared with the prior art, the invention has the following advantages:
1. by carrying out multivariate linear regression analysis on the big data of the passengers on the trips of brushing the face, a prediction result which is closer to the actual trip rule of the passengers at each station can be obtained;
2. a degraded face database with small scale and high frequent rate is selected from all passengers through a roulette mode, so that the method not only adapts to the limiting conditions of station-level computing resources, but also can meet the frequent face brushing travel requirements of more frequent passengers as much as possible;
3. the allocation method of the degraded face database can dynamically roll according to the travel rule of passengers, and always keeps the allocated degraded face database to have better practical adaptability.
Drawings
FIG. 1 is a flow chart of a station demotion face recognition library distribution method based on roulette;
figure 2 is a method of demotion database generation based on roulette.
Detailed Description
The technical scheme of the invention is further explained by combining the attached drawings.
As shown in fig. 1, a method for allocating a station demotion face recognition library based on roulette comprises the following steps:
s1, carrying out statistical preprocessing based on the big data OD of the passenger on the face brushing and brake passing trip;
is provided withnThe number of the passengers is increased, and the passengers,mindividual station, in statistical intervaltThe number of times that the passenger swipes in and out of the station can be determined by the matrixCRepresents:
Figure 287383DEST_PATH_IMAGE020
in a continuous set of statistical intervals
Figure 33491DEST_PATH_IMAGE021
In each statistical sectionC(t k ) The matrix elements of which are
Figure 215074DEST_PATH_IMAGE022
。
Whereinc ij Is shown in statistical intervalstThe number of times of face brushing of the inner passenger i at the station j. For different statistical intervalstDifferent statistical results can be obtainedC(t). For statistical interval set
Figure 608009DEST_PATH_IMAGE023
Obtaining statistical intervalsC(t k ) The matrix elements of which are
Figure 507832DEST_PATH_IMAGE024
. Since the OD data is long-term continuous, we can establish continuous observation on long-term continuous OD data by sliding the observation window K.
S2, calculating the constant rate matrix of all passengers at all stations based on the statistical matrix on the statistical interval setnA passenger is atmThe constant rate matrix R at each station:
Figure 277205DEST_PATH_IMAGE025
Figure 578873DEST_PATH_IMAGE026
the calculation method of (2) is as follows:
Figure 159021DEST_PATH_IMAGE027
regression parameters
Figure 546140DEST_PATH_IMAGE028
Obtained by the least squares method of the following regression problem, i.e. in a sliding implementation window, the following regression problem is constructed:
Figure 119204DEST_PATH_IMAGE029
wherein the content of the first and second substances,
Figure 9800DEST_PATH_IMAGE030
to define the number of swipes by passengers at stations i and j as described above, V is the number of sequential samples taken to perform the parametric regression estimation.
S3, normalizing the constant rate matrix to obtain a matrix
Figure 275696DEST_PATH_IMAGE031
；
Figure 884532DEST_PATH_IMAGE032
Wherein the content of the first and second substances,
Figure 510554DEST_PATH_IMAGE033
the elements of the constant rate matrix for the aforementioned locations characterize how often passengers swipe in and out at stations i and j.
S4, as shown in FIG. 2, matrix after normalization
Figure 521236DEST_PATH_IMAGE034
The method is based on a roulette method, a given number of degraded face libraries are selected from all passengers of a station j =1, 2.
S4.1, matrix pair
Figure 958033DEST_PATH_IMAGE034
Perform column integration, taking column j as an example;
Figure 54165DEST_PATH_IMAGE035
by integrating point by point one can get:
Figure 969032DEST_PATH_IMAGE036
wherein:
Figure 834219DEST_PATH_IMAGE037
according to
Figure 973077DEST_PATH_IMAGE038
Is obviously defined by
Figure 504640DEST_PATH_IMAGE039
。
The matrix can be obtained finally:
Figure 754356DEST_PATH_IMAGE040
s4.2, matrix pair
Figure 208471DEST_PATH_IMAGE041
Column j (i.e., j stations), each station assigned N passengers, and the selection of passenger IDs is performed according to the roulette flow, as follows:
s4.2.1, generating random numbers r which accord with [0,1] even distribution;
s4.2.2, find sequence number i so as to satisfy the following formula:
Figure 518230DEST_PATH_IMAGE042
s4.2.3, placing the passenger ID and the face feature library corresponding to the serial number i into a degraded face library of the station j, and skipping if the ID of the i exists in the library;
s4.2.4, whether the ID number in the library reaches the set number N, if not, returning to step S4.2.1; if so, go to step S4.2.5;
s4.2.5, outputting a face database distributed by the station j.
The distribution process of the degraded face library is based on an observation window
Figure 792216DEST_PATH_IMAGE043
The distribution process of each station can be updated and distributed according to a fixed updating period.

Claims (7)

1. A station degraded face recognition library distribution method based on roulette is characterized by comprising the following steps:
(1) carrying out statistical preprocessing based on a big data OD of a passenger brushing face and passing through a gate;
(2) calculating the frequent rate matrix of all passengers at all stations based on the statistical matrix on the statistical interval set;
(3) normalizing the constant rate matrix;
(4) and selecting a given number of degraded face libraries from all passengers on the matrix after the normalization processing based on a roulette method and distributing the degraded face libraries to each station.
2. The station degradation face recognition library distribution method based on roulette according to claim 1, wherein the step (1) is specifically as follows:
is provided withnThe number of the passengers is increased, and the passengers,mindividual station, in statistical intervaltThe number of times that the passenger swipes in and out of the station can be determined by the matrixCRepresents:
Figure 31445DEST_PATH_IMAGE001
in a continuous set of statistical intervals
Figure 417427DEST_PATH_IMAGE002
In each statistical section
Figure 400426DEST_PATH_IMAGE003
The matrix elements of which are
Figure 795635DEST_PATH_IMAGE004
。
3. The station demotion face recognition library distribution method based on roulette as claimed in claim 1, wherein the step of calculating the constant rate matrix of all passengers at all stations in step (2) is specifically:
Figure 328117DEST_PATH_IMAGE005
Figure 150579DEST_PATH_IMAGE006
the calculation method of (2) is as follows:
Figure 620875DEST_PATH_IMAGE007
regression parameters
Figure 288617DEST_PATH_IMAGE008
Obtained by the least squares method of the regression problem as follows:
Figure 957495DEST_PATH_IMAGE009
wherein the content of the first and second substances,
Figure 898995DEST_PATH_IMAGE010
to define the number of swipes by passengers at stations i and j as described above, V is the number of sequential samples taken to perform the parametric regression estimation.
4. The method for allocating station degradation face recognition library based on roulette as claimed in claim 1, wherein the normalization of the matrix R in step (3) is calculated as:
Figure 653324DEST_PATH_IMAGE011
wherein the content of the first and second substances,
Figure 593598DEST_PATH_IMAGE012
the elements of the constant rate matrix for the aforementioned locations characterize how often passengers swipe in and out at stations i and j.
5. The station degradation face recognition library distribution method based on roulette as claimed in claim 1, wherein the matrix after normalization in the step (4)
Figure 116983DEST_PATH_IMAGE013
First, the column integration is performed to obtain
Figure 15669DEST_PATH_IMAGE014
And then, based on the roulette method, selecting a given number of degraded face libraries from all passengers and distributing the degraded face libraries to each station, wherein the step of selecting the given number of degraded face libraries from all passengers in the column score based on the roulette method specifically comprises the following steps:
(4.1) generating random numbers r which accord with [0,1] uniform distribution;
(4.2) find the number i so that the following equation is satisfied:
Figure 257295DEST_PATH_IMAGE015
(4.3) placing the passenger ID and the face feature library corresponding to the serial number i into a degraded face library of the station j, and skipping if the ID of the i exists in the library;
(4.4) whether the number of IDs in the library reaches the set number N, if not, returning to the step (4.1); if yes, jumping to the step (4.5);
and (4.5) outputting a face database distributed by the station j.
6. A computer storage medium on which a computer program is stored, the computer program, when executed by a processor, implementing a roulette-based station demotion face recognition library distribution method according to any of claims 1 to 5.
7. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the computer program implements a roulette-based station downgrade face recognition library distribution method according to any of claims 1-5.
CN202210787069.8A 2022-07-06 2022-07-06 Station degradation face recognition library distribution method based on roulette Pending CN114842545A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210787069.8A CN114842545A (en) 2022-07-06 2022-07-06 Station degradation face recognition library distribution method based on roulette

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210787069.8A CN114842545A (en) 2022-07-06 2022-07-06 Station degradation face recognition library distribution method based on roulette

Publications (1)

Publication Number Publication Date
CN114842545A true CN114842545A (en) 2022-08-02

Family

ID=82575305

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210787069.8A Pending CN114842545A (en) 2022-07-06 2022-07-06 Station degradation face recognition library distribution method based on roulette

Country Status (1)

Country Link
CN (1) CN114842545A (en)

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1670764A (en) * 2004-03-19 2005-09-21 中国科学院计算技术研究所 Genetic algorithm based human face sample generating method
WO2020021319A1 (en) * 2018-07-27 2020-01-30 Yogesh Chunilal Rathod Augmented reality scanning of real world object or enter into geofence to display virtual objects and displaying real world activities in virtual world having corresponding real world geography
CN111461793A (en) * 2020-04-27 2020-07-28 吉林省桥王智能科技有限公司 Integral chain consensus method based on activity probability selection
CN111666681A (en) * 2020-06-03 2020-09-15 重庆大学 PBS buffer area vehicle sequencing scheduling method based on improved genetic algorithm
WO2021082521A1 (en) * 2019-10-31 2021-05-06 江西理工大学 Permanent-magnet magnetic levitation rail transit control system based on 5g communication technology
CN113536906A (en) * 2021-06-04 2021-10-22 新大陆数字技术股份有限公司 Face recognition method and device based on passenger portrait
CN114038028A (en) * 2021-09-29 2022-02-11 南京地铁建设有限责任公司 Station degradation face library generation method based on big data of face brushing trip

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1670764A (en) * 2004-03-19 2005-09-21 中国科学院计算技术研究所 Genetic algorithm based human face sample generating method
WO2020021319A1 (en) * 2018-07-27 2020-01-30 Yogesh Chunilal Rathod Augmented reality scanning of real world object or enter into geofence to display virtual objects and displaying real world activities in virtual world having corresponding real world geography
WO2021082521A1 (en) * 2019-10-31 2021-05-06 江西理工大学 Permanent-magnet magnetic levitation rail transit control system based on 5g communication technology
CN111461793A (en) * 2020-04-27 2020-07-28 吉林省桥王智能科技有限公司 Integral chain consensus method based on activity probability selection
CN111666681A (en) * 2020-06-03 2020-09-15 重庆大学 PBS buffer area vehicle sequencing scheduling method based on improved genetic algorithm
CN113536906A (en) * 2021-06-04 2021-10-22 新大陆数字技术股份有限公司 Face recognition method and device based on passenger portrait
CN114038028A (en) * 2021-09-29 2022-02-11 南京地铁建设有限责任公司 Station degradation face library generation method based on big data of face brushing trip

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
刘辉等: ""基于改进遗传算法的转炉炼钢过程数据特征选择"", 《仪器仪表学报》 *
宋优才: ""基于"白名单"的城市轨道交通快速安检方案构思"", 《隧道与轨道交通》 *
曹才轶等: ""基于遗传算法的船舶破舱稳性扶正措施优化研究"", 《中国造船》 *

Similar Documents

Publication Publication Date Title
CN109872535B (en) Intelligent traffic passage prediction method, device and server
CN107977734B (en) Prediction method based on mobile Markov model under space-time big data
CN109637547B (en) Audio data labeling method and device, electronic equipment and storage medium
CN111507762B (en) Urban taxi demand prediction method based on multitasking co-prediction neural network
CN111931978A (en) Urban rail transit passenger flow state prediction method based on space-time characteristics
CN110991527A (en) Similarity threshold determination method considering voltage curve average fluctuation rate
CN106507406A (en) A kind of equipment of wireless network accesses the Forecasting Methodology of number and equipment
CN110569910A (en) method, device and equipment for processing live broadcast cycle and storage medium
CN112215409A (en) Rail transit station passenger flow prediction method and system
CN111079827B (en) Railway data state evaluation method and system
CN111797926A (en) Inter-city migration behavior recognition method and device, computer equipment and storage medium
Liu et al. Data adaptive functional outlier detection: Analysis of the Paris bike sharing system data
CN115794369A (en) Memory occupation value prediction method and device, storage medium and terminal
CN114842545A (en) Station degradation face recognition library distribution method based on roulette
CN111815956B (en) Expressway traffic flow prediction method
CN116226697B (en) Spatial data clustering method, system, equipment and medium
Wang et al. Development of metro track geometry fault diagnosis convolutional neural network model based on car-body vibration data
CN113159408A (en) Rail transit station passenger flow prediction method and device
CN112669595A (en) Online taxi booking flow prediction method based on deep learning
CN116719787A (en) Method and device for uploading equipment logs in track system, medium and electronic equipment
CN116523002A (en) Method and system for predicting dynamic graph generation countermeasure network track of multi-source heterogeneous data
CN114777794B (en) Method, device and equipment for detecting reverse movement sliding window of spacecraft orbit maneuver
CN112799928B (en) Knowledge graph-based industrial APP association analysis method, device and medium
CN113792945A (en) Dispatching method, device, equipment and readable storage medium of commercial vehicle
CN113536493A (en) Effective path generation method based on clustering reverse thrust and section passenger flow estimation method

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20220802