CN112669978B - Epidemic infection risk assessment method - Google Patents
Epidemic infection risk assessment method Download PDFInfo
- Publication number
- CN112669978B CN112669978B CN202011317829.6A CN202011317829A CN112669978B CN 112669978 B CN112669978 B CN 112669978B CN 202011317829 A CN202011317829 A CN 202011317829A CN 112669978 B CN112669978 B CN 112669978B
- Authority
- CN
- China
- Prior art keywords
- base station
- time
- patient
- track
- risk
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 208000015181 infectious disease Diseases 0.000 title claims abstract description 45
- 238000000034 method Methods 0.000 title claims abstract description 27
- 238000012502 risk assessment Methods 0.000 title claims abstract description 22
- 230000011218 segmentation Effects 0.000 claims description 11
- 230000036541 health Effects 0.000 claims description 4
- 238000012216 screening Methods 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 description 5
- 238000012163 sequencing technique Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000001502 supplementing effect Effects 0.000 description 2
- 230000007704 transition Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Landscapes
- Medical Treatment And Welfare Office Work (AREA)
Abstract
本发明公开了一种疫情感染风险评估方法，包括：获取患者的移动终端号或身份证号，并根据移动终端号或身份证号从运营商轨迹接口中获取患者对应的轨迹信息；从患者的轨迹信息中提取基站轨迹，并通过通行方式判断算法得到患者通过基站时的通行方式；根据基站轨迹获取患者进出基站时间，并将患者进出基站时间按照预设时间片进行时间片切分；统计预设时间内进出基站相同通行方式相同时间片内的人数，将相同通行方式的人数乘以对应的权重，得到每个通行方式的风险值，再将基站所有通行方式的风险值相加，得到基站的疫情感染风险度，实现地区的疫情感染风险评估。本发明实现了地区和个人的疫情感染风险自动评估，且评估依据多，评估结果准确。
The invention discloses an epidemic infection risk assessment method. The base station trajectory is extracted from the trajectory information, and the patient's traffic mode when passing through the base station is obtained through the traffic mode judgment algorithm; the patient's entry and exit time from the base station is obtained according to the base station trajectory, and the patient's entry and exit time is divided into time slices according to preset time slices; statistical prediction Set the number of people entering and leaving the base station in the same time slice in the same way, multiply the number of people in the same way by the corresponding weight, get the risk value of each way, and then add the risk values of all the ways of the base station to get the base station The risk degree of epidemic infection can be achieved to achieve regional epidemic infection risk assessment. The invention realizes the automatic assessment of the epidemic infection risk of regions and individuals, and has many assessment bases and accurate assessment results.
Description
Technical Field
The invention relates to the technical field of base station big data processing, in particular to an epidemic infection risk assessment method.
Background
In order to effectively control the spread of epidemic situations in the society, the infection risks of individuals and regions need to be accurately evaluated, so that corresponding measures, such as forbidding people from entering high-risk regions, isolating high-risk individuals and the like, can be implemented by using the data. It follows that the entire epidemic prevention work needs to be spread around the infection risk data of individuals and regions. Therefore, how to accurately evaluate the infection risk of individuals and regions is very important in preventing the spread of epidemic situations.
The existing risk assessment method requires a user to report health information and trip information consciously so as to obtain the infection risk of the user. The number of patients is a main factor for evaluating the infection risk in each region. The existing risk assessment method has three main disadvantages: 1. the health information and the trip information are too complicated to be filled every day, and the user experience is influenced. 2. The data filled by the user can be misreported or concealed, and the infection risk generated according to the data is not high in authenticity. 3. The basis for evaluating the infection risk of one region is too single, and the accuracy of the regional risk degree is influenced.
Therefore, there is a need in the industry to develop a method and system for automatic assessment of infection risk in areas and individuals with a large number of assessment bases.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides a method for evaluating the epidemic infection risk of regions and individuals.
The purpose of the invention is realized by the following technical scheme:
an epidemic infection risk assessment method, comprising:
s11, acquiring the mobile terminal number or the identity card number of the patient according to epidemic situation data provided by Weijian committee, and acquiring the track information corresponding to the patient from the operator track interface according to the mobile terminal number or the identity card number;
s12, extracting the base station track from the track information of the patient, and obtaining the passing mode of the patient when the patient passes through the base station through a passing mode judgment algorithm;
s13, acquiring the time of the patient getting in and out of the base station according to the base station track, and carrying out time slice segmentation on the time of the patient getting in and out of the base station according to preset time slices;
s14, counting the number of people who pass in and out of the same time slice of the same passing mode of the base station within the preset time, multiplying the number of people in the same passing mode by the corresponding weight to obtain the risk value of each passing mode, and adding the risk values of all the passing modes of the base station to obtain the epidemic infection risk degree of the base station, thereby realizing the epidemic infection risk assessment of the region.
Preferably, the passing modes in the step 12 comprise home, office, residence, walking and riding; the passing mode of the patient when passing through the base station is obtained through the passing mode judgment algorithm and is as follows: if delta t > is alpha, the track is judged as the home; if alpha >. DELTA.t > beta and the time range is at night, the track is judged as being at home; if alpha >. DELTA.t > beta and the time range is in the daytime, the track is judged as office work; if beta > delta t > is x, the track is judged to be resident; if x > delta t > is delta, the track is judged to be walking; if the situations are not met, judging the track as a bus; wherein, Δ t is the time difference in and out of the base station calculated according to the track of the base station, and is counted in seconds; α represents a threshold value of the residence time at home, [ β, α ] represents a range of residence time at home or at work, [ χ, β) is a threshold value of the residence time at residence, and [ δ, χ) is a threshold value of the walking residence time.
Preferably, step S13 includes:
s131, dividing the time of 24 hours a day into different time periods according to time segmentation granularity, wherein the segmentation granularity is counted in seconds from 0 to 86400;
s132, converting the time stamp of the time when the patient enters and exits the base station into a character string format of 'year, month, day, minute and second', and segmenting the character string of 'year, month, day, minute and second' according to the formats of 'year, month, day' and 'hour, minute and second';
s133, supplementing the segmented 'year, month and day' part into 'xxxx: xx: xx00:00: 00', converting the segmented 'year, month and day' part into a timestamp format, converting the 'hour, minute and second' part, namely 'xx: xx: xx: xx' into corresponding seconds, and adding the corresponding timestamps of 'xxxx: xx: xx00: 00';
s134, comparing the seconds of minutes and seconds corresponding to the time of the patient entering and exiting the base station with the time period segmented in the step S131, finding the time period interval to which the entering and exiting time belongs, replacing the entering time with the starting time of the time period interval to which the entering time belongs, and replacing the leaving time with the ending time of the time period interval to which the leaving time belongs;
s135, adding the replaced start time and end time with the converted time stamps of the corresponding 'xxxx: xx: xx00:00: 00' respectively to obtain the time stamp finally corresponding to the time when the patient enters and exits the base station;
and S136, segmenting the time of the patient entering and exiting the base station according to the segmentation granularity by the corresponding timestamp finally.
Preferably, the steps S13 and S14 further include: the number of the patients in different time slices and different passing modes of the same base station is updated, and the method specifically comprises the following steps: traversing a new base station track time slice passing mode list of the patient, sequentially comparing the number of the passing modes with the number of the patient base station time slices in the database, if the number of the base stations, the time slices and the passing modes are the same, adding 1 to the corresponding number of the people, and if the number of the passing modes is not the same, adding the base station record.
Preferably, step 14 is specifically: traversing the updated base station time slice passing mode person number list, taking out the base station number and the time slice, traversing all base station time slice passing mode person number lists in the database, taking out all records with the same updated base station number and the time slice, calculating the risk value recorded by each base station time slice passing mode according to the passing mode and the number of the persons, calculating the home risk value as the patient number alpha, the office risk value as the patient number beta, the resident risk value as the patient number chi, the walking risk value as the patient number delta, the riding risk value as the patient number epsilon, and adding the risk values of different passing modes corresponding to the base station and the time slice to obtain the risk degree of the base station time slice.
Preferably, step S14 is followed by: the epidemic situation infection risk assessment method for the individual to be assessed specifically comprises the following steps:
s15, determining whether the person to be evaluated is a patient, if not, executing the step S16;
s16, matching the base station track of the individual to be evaluated, and sequencing the base stations entering and exiting according to the base station track and the entering time;
s17, taking out the track of the personal base station to be evaluated, wherein the traffic mode is the track of the bus; judging whether the riding track of the patient is overlapped with the riding track of the patient or not; if yes, giving a risk value to the base station weighted risk degree of the individual to be evaluated, and executing step S19; if not, go to step S18;
s18, acquiring a single base station track of the person to be evaluated from the base station tracks, matching the risk degree of each time period in the base station through the time of the person to be evaluated entering and leaving the base station, and accumulating to obtain the risk degree of the person to be evaluated passing the base station;
and S19, if the risk value obtained in the step S17 or the risk degree obtained in the step S18 is larger than a preset threshold value, determining that the personal epidemic infection risk blacklist is to be evaluated.
Preferably, the step of determining whether the riding track of the patient coincides with the riding track of the patient in the step S18 includes:
s181, screening out base stations through which each patient passes, grouping the base station tracks according to the patients, and sequencing the base station tracks of each patient according to the entry time;
s182, obtaining the base station track information of the patient;
s183, taking out the base station track information in the preset window of the patient;
s184, judging whether the base station track information in the window of the patient is continuous; if not, the initial base station moves one backward, and step S183 is executed; if yes, go to step S185;
s185, matching the track of the personal base station to be evaluated with the continuous track of the base station in the patient window, and checking whether the continuous track of the personal base station to be evaluated is matched with the track of the personal base station to be evaluated in the window; if not, the initial base station moves one backward, and step S183 is executed; if yes, judging that the person to be evaluated has an accompanying relationship with the patient.
Preferably, the base station track information of the patient is [ S1, S2, S3,.., Sn,.., Sm ], where Sn represents information contained in the nth base station that the patient passes through, and the information is the base station number of the base station and the time when the patient passes in and out of the base station.
Preferably, the mobile terminal number is a mobile phone number.
Compared with the prior art, the invention has the following advantages:
according to the invention, patient information is obtained from Wei-Jian-Wei in each region, the track information of the patient is obtained by using the mobile phone number of the patient, time slice division and pass mode judgment are carried out according to the track information of the patient, the number of people in the same pass mode in the time slices of the base station is counted, the infection risk values of each base station in each time slice are calculated, and the risk values are dynamically updated along with the track change of the patient. According to the invention, the user track information is obtained through the mobile phone number of the common user and is matched with the patient track information, so that the infection risk value of the common user is obtained, the risk value is changed along with the change of the user track and the patient track, the automatic evaluation of the epidemic infection risk of the region and the individual is finally realized, the evaluation basis is more, and the evaluation result is accurate.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate embodiments of the invention and, together with the description, serve to explain the invention and not to limit the invention. In the drawings:
FIG. 1 is an overall flowchart of the epidemic infection risk assessment method of the present invention.
Fig. 2 is a flowchart of a method for evaluating a base station epidemic infection risk according to the present invention.
FIG. 3 is a flow chart of the method for evaluating the risk of infection of a personal epidemic situation according to the present invention.
Detailed Description
The invention is further illustrated by the following figures and examples.
Referring to fig. 1-3, a method for assessing epidemic infection risk, comprising:
s11, acquiring the mobile terminal number or the identity card number of the patient according to epidemic situation data provided by Weijian committee, and acquiring the track information corresponding to the patient from the operator track interface according to the mobile terminal number or the identity card number; in this embodiment, the mobile terminal number is a mobile phone number.
S12, extracting the base station track from the track information of the patient, and obtaining the passing mode of the patient when the patient passes through the base station through a passing mode judgment algorithm; the passing mode comprises home, office, residence, walking and riding; the passing mode of the patient when passing through the base station is obtained through the passing mode judgment algorithm and is as follows: if delta t > is alpha, the track is judged as the home; if alpha >. DELTA.t > beta and the time range is at night, the track is judged as being at home; if alpha >. DELTA.t > beta and the time range is in the daytime, the track is judged as office work; if beta > delta t > is x, the track is judged to be resident; if x > delta t > is delta, the track is judged to be walking; if the situations are not met, judging the track as a bus;
wherein, Δ t is the time difference in and out of the base station calculated according to the track of the base station, and is counted in seconds; α represents a threshold value of the residence time at home, such as 12h, [ β, α ] represents a range of residence times at home or at work, such as [8h,12h ], [ χ, β) is a threshold value of residence time at residence, and [ δ, χ) is a threshold value of walking residence time.
S13, acquiring the time of the patient getting in and out of the base station according to the base station track, and carrying out time slice segmentation on the time of the patient getting in and out of the base station according to preset time slices; specifically, step S13 includes:
s131, dividing the time of 24 hours a day into different time periods according to time segmentation granularity, wherein the segmentation granularity is counted in seconds from 0 to 86400;
s132, converting the time stamp of the time when the patient enters and exits the base station into a character string format of 'year, month, day, minute and second', and segmenting the character string of 'year, month, day, minute and second' according to the formats of 'year, month, day' and 'hour, minute and second';
s133, supplementing the segmented 'year, month and day' part into 'xxxx: xx: xx00:00: 00', converting the segmented 'year, month and day' part into a timestamp format, converting the 'hour, minute and second' part, namely 'xx: xx: xx: xx' into corresponding seconds, and adding the corresponding timestamps of 'xxxx: xx: xx00: 00';
s134, comparing the seconds of minutes and seconds corresponding to the time of the patient entering and exiting the base station with the time period segmented in the step S131, finding the time period interval to which the entering and exiting time belongs, replacing the entering time with the starting time of the time period interval to which the entering time belongs, and replacing the leaving time with the ending time of the time period interval to which the leaving time belongs;
s135, adding the replaced start time and end time with the converted time stamps of the corresponding 'xxxx: xx: xx00:00: 00' to obtain the time stamp finally corresponding to the time when the patient enters and exits the base station;
and S136, segmenting the time of the patient entering and exiting the base station according to the segmentation granularity by the corresponding timestamp finally.
Such as: the time slices are divided starting from 00:00:00 for 1 day, assuming a particle size of 10min, so that 24 hours for 1 day can be divided into time slices [0,600], [600,1200], … [85800,86400 ].
The timestamp 1580533390 entering the base station is converted into a "year-month-day-hour: minutes: seconds" format of 2020-02-0113: 03:10, which divides 2020-02-0113: 03:10 into two parts 2020-02-0100: 00:00 and 13:03:10 in sum.
2020-02-0100: 00:00 is converted into a time stamp 1580486400 according to the difference with 1970-01-0108: 00:00, 13:03:10 is converted into 46990 according to the difference with 00:00:00, 46990 is converted into a time slice interval of [46800,47400], and the time stamp of 2020-02-0100: 00:00 is added to be converted into [1580533200,1580533800 ].
The timestamp 1580551390 leaving the base station is converted to a "year-month-day hour: minutes: seconds" format of 2020-02-0118: 03:10, which splits 2020-02-0118: 03:10 into a sum of two parts 2020-02-0100: 00:00 and 18:03: 10.
2020-02-0100: 00:00 is converted into a time stamp 1580486400 according to the difference value with 1970-01-0108: 00:00, 18:03:10 is converted into 64990 according to the difference value with 00:00:00, 64990 is converted into a time slice interval of [64800,65400], the time stamp of 2020-02-0100: 00:00 is added into the time slice interval, and the time slice interval is converted into [1580551200,1580551800]
Therefore, the time interval for entering and exiting the base station can be divided into time slices of [1580533200,1580533800], [1580533800,1580534400], … [1580551200,1580551800], since the time stamp of the beginning of the time transition of entering the base station is 1580533200, the time stamp of the end of the time transition of leaving the base station is 1580551800, and the granularity of the time interval division is 10 min.
Further, the steps between S13 and S14 further include: the number of the patients in different time slices and different passing modes of the same base station is updated, and the method specifically comprises the following steps: traversing a new base station track time slice passing mode list of the patient, sequentially comparing the number of the passing modes with the number of the patient base station time slices in the database, if the number of the base stations, the time slices and the passing modes are the same, adding 1 to the corresponding number of the people, and if the number of the passing modes is not the same, adding the base station record.
S14, counting the number of people who pass in and out of the same time slice of the same passing mode of the base station within the preset time, multiplying the number of people in the same passing mode by the corresponding weight to obtain the risk value of each passing mode, and adding the risk values of all the passing modes of the base station to obtain the epidemic infection risk degree of the base station, thereby realizing the epidemic infection risk assessment of the region. Specifically, step S14 specifically includes:
traversing the updated base station time slice passing mode person number list, taking out the base station number and the time slice, traversing all base station time slice passing mode person number lists in the database, taking out all records with the same updated base station number and the time slice, calculating the risk value recorded by each base station time slice passing mode according to the passing mode and the number of the persons, calculating the home risk value as the patient number alpha, the office risk value as the patient number beta, the resident risk value as the patient number chi, the walking risk value as the patient number delta, the riding risk value as the patient number epsilon, and adding the risk values of different passing modes corresponding to the base station and the time slice to obtain the risk degree of the base station time slice.
In this embodiment, step S14 is followed by: the epidemic situation infection risk assessment method for the individual to be assessed specifically comprises the following steps:
s15, determining whether the person to be evaluated is a patient, if not, executing the step S16; if yes, directly returning to the blacklist. The person (user) to be evaluated can directly input the user information, and then whether the person to be evaluated is a patient can be determined.
S16, matching the base station track of the individual to be evaluated, and sequencing the base stations entering and exiting according to the base station track and the entering time;
s17, taking out the track of the personal base station to be evaluated, wherein the traffic mode is the track of the bus; judging whether the riding track of the patient is overlapped with the riding track of the patient or not; if yes, giving a risk value to the base station weighted risk degree of the individual to be evaluated, and executing step S19; if not, go to step S18;
s18, acquiring a single base station track of the person to be evaluated from the base station tracks, matching the risk degree of each time period in the base station through the time of the person to be evaluated entering and leaving the base station, and accumulating to obtain the risk degree of the person to be evaluated passing the base station; specifically, in the step S18, if it is determined that the riding track of the patient coincides with the riding track of the patient, the riding track of the patient is matched with the riding track of the inquirer, and the specific matching process includes:
s181, screening out base stations through which each patient passes by the bus, grouping the base station tracks according to the patients (mobile phone numbers), and sequencing the base station tracks of each patient according to the entry time;
s182, obtaining the base station track information of the patient; if the information of the patient is not traversed, the individual to be evaluated has no accompanying relationship with all the patients.
S183, taking out the base station track information in the preset window of the patient; if the number of base stations in the window is not enough, the process returns to step S182. The information of the base station track of the patient is [ S1, S2, S3, wherein Sn denotes information contained in the nth base station through which the patient passes, and the information is the base station number of the base station and the time for the patient to get in and out of the base station. If the window size is 3, the base station trajectory information in the patient window is [ S1, S2, S3 ].
S184, judging whether the base station track information in the window of the patient is continuous; if not, the initial base station moves one backward, and step S183 is executed; if yes, go to step S185; for example, if the information of the base station trajectory in the window of the patient is [ S1, S2, S3], it is necessary to determine whether the time when the patient leaves the base station S1 is consistent with the time when the patient enters the base station S2, if so, the base stations S1 and S2 are consecutive, and similarly, it is determined whether the base stations S2 and S3 are consecutive. If one of the two is not continuous, the judgment is continued by taking [ S2, S3, S4], and the like.
S185, matching the track of the personal base station to be evaluated with the continuous track of the base station in the patient window, and checking whether the continuous track of the personal base station to be evaluated is matched with the track of the personal base station to be evaluated in the window; if not, the initial base station moves one backward, and step S183 is executed; if yes, judging that the person to be evaluated has an accompanying relationship with the patient. For example, the continuous patient trajectories screened in the step 4 are [ S1, S2, S3], the patient trajectories are matched with the user trajectories, and if 3 trajectories which are consistent with the base station numbers of [ S1, S2, S3] and have continuous in-out time appear in the user trajectories, the accompanying relationship is judged.
And S19, if the risk value obtained in the step S17 or the risk degree obtained in the step S18 is larger than a preset threshold value, determining that the personal epidemic infection risk blacklist is to be evaluated. And if the risk value obtained in the step S17 or the risk degree obtained in the step S18 is smaller than a preset threshold value, determining that the individual to be evaluated is infected with the epidemic situation risk white list. After step S19, the determination result is returned to generate the two-dimensional code, and the user acquires the determination result from the two-dimensional code.
In summary, the present invention includes information acquisition, base station risk level generation, and risk level query (individual risk level assessment). In the information acquisition part, patient information is mainly obtained from health and fitness committees in various regions, and a user base station track is obtained from a mobile phone operator. And in the base station risk degree generating part, the base station time slice risk degree is obtained through the patient information generated in the last part and the user base station track. And in the risk degree inquiry part, acquiring the base station track of the user by using the mobile phone number input by the user, and respectively matching the base station track with the patient information, the base station time slice risk degree and the patient base station passing mode, thereby evaluating the infection risk of the inquirer. The invention has multiple evaluation bases, and the automatic evaluation of infection risks can be realized in areas and individuals.
The above-mentioned embodiments are preferred embodiments of the present invention, and the present invention is not limited thereto, and any other modifications or equivalent substitutions that do not depart from the technical spirit of the present invention are included in the scope of the present invention.
Claims (7)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011317829.6A CN112669978B (en) | 2020-11-23 | 2020-11-23 | Epidemic infection risk assessment method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011317829.6A CN112669978B (en) | 2020-11-23 | 2020-11-23 | Epidemic infection risk assessment method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112669978A CN112669978A (en) | 2021-04-16 |
| CN112669978B true CN112669978B (en) | 2022-03-04 |
Family
ID=75403510
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011317829.6A Active CN112669978B (en) | 2020-11-23 | 2020-11-23 | Epidemic infection risk assessment method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112669978B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114297448B (en) * | 2022-03-09 | 2022-07-05 | 广州卓腾科技有限公司 | License applying method, system and medium based on intelligent epidemic prevention big data identification |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111863270A (en) * | 2020-05-20 | 2020-10-30 | 京东城市(北京)数字科技有限公司 | Disease infection probability determination method, device, system and storage medium |
| CN111933299A (en) * | 2020-08-14 | 2020-11-13 | 工银科技有限公司 | Infectious disease infection risk assessment method and apparatus, electronic device, and storage medium |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111311018A (en) * | 2020-03-04 | 2020-06-19 | 苏州远征魂车船技术有限公司 | Accurate management and control system of epidemic situation |
| CN111489831A (en) * | 2020-04-10 | 2020-08-04 | 智慧足迹数据科技有限公司 | Public health incident risk assessment method and device |
| CN111508609A (en) * | 2020-04-17 | 2020-08-07 | 腾讯科技（深圳）有限公司 | Health condition risk prediction method and device, computer equipment and storage medium |
| CN111739653B (en) * | 2020-06-19 | 2022-11-15 | 南方科技大学 | Evaluation method, device, computer equipment and storage medium for infectious disease transmission |
| CN111885502B (en) * | 2020-06-28 | 2021-07-27 | 华东师范大学 | An early warning and traceability system and method for epidemic prevention and control that protects privacy |
-
2020
- 2020-11-23 CN CN202011317829.6A patent/CN112669978B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111863270A (en) * | 2020-05-20 | 2020-10-30 | 京东城市(北京)数字科技有限公司 | Disease infection probability determination method, device, system and storage medium |
| CN111933299A (en) * | 2020-08-14 | 2020-11-13 | 工银科技有限公司 | Infectious disease infection risk assessment method and apparatus, electronic device, and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112669978A (en) | 2021-04-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110245981B (en) | Crowd type identification method based on mobile phone signaling data | |
| CN107133318B (en) | A population identification method based on mobile phone signaling data | |
| CN108596409B (en) | Method for improving accident risk prediction precision of traffic hazard personnel | |
| CN107798876B (en) | Road traffic abnormal jam judging method based on event | |
| WO2016177066A1 (en) | Employee potential relationship analysis method and device | |
| CN109711890B (en) | User data processing method and system | |
| CN112669978B (en) | Epidemic infection risk assessment method | |
| KR102473697B1 (en) | Method for collecting data reflecting traveler's behavioral characteristics using facial recognition | |
| CN109684373A (en) | Emphasis party based on trip and call bill data analysis has found method | |
| CN109670540B (en) | A short-term prediction method for the change trend of the number of residents in the passenger hub area based on the kNN algorithm | |
| Chen et al. | Extracting bus transit boarding stop information using smart card transaction data | |
| CN111291216A (en) | Method and system for analyzing foothold based on face structured data | |
| CN106528850A (en) | Door access data abnormal detection method based on machine learning clustering algorithm | |
| CN111105849A (en) | Channel collaborative satisfaction investigation method and system based on big data | |
| Scowcroft | Suicide statistics report 2017 | |
| CN108681741B (en) | Subway commuting crowd information fusion method based on IC card and resident survey data | |
| CN109241320A (en) | The division methods of teenage crime area cluster based on Time Series Clustering | |
| Chen et al. | Extracting bus transit boarding and alighting information using smart card transaction data | |
| JP5658593B2 (en) | Vehicle congestion rate prediction apparatus and method | |
| CN112699955B (en) | A user classification method, device, equipment and storage medium | |
| CN110148041A (en) | A kind of healthy diet analysis recommender system design method | |
| Yang et al. | A K-shape clustering based transformer-decoder model for predicting multi-step potentials of urban mobility field | |
| CN113935560A (en) | Airport passenger digital portrait evaluation system and method | |
| CN114358375B (en) | Crowd density prediction method and system based on big data | |
| Wang et al. | A destination prediction model for individual passengers in urban rail transit |
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 | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20220704 Address after: 510006 No. 230 West Ring Road, University of Guangdong, Guangzhou Patentee after: Guangzhou University Patentee after: National University of Defense Technology Address before: 510006 No. 230 West Ring Road, Panyu District University, Guangdong, Guangzhou Patentee before: Guangzhou University |
|
| TR01 | Transfer of patent right |