CN110533896B - Processing method and device of early warning information and electronic equipment - Google Patents

Processing method and device of early warning information and electronic equipment Download PDF

Info

Publication number
CN110533896B
CN110533896B CN201910834337.5A CN201910834337A CN110533896B CN 110533896 B CN110533896 B CN 110533896B CN 201910834337 A CN201910834337 A CN 201910834337A CN 110533896 B CN110533896 B CN 110533896B
Authority
CN
China
Prior art keywords
early warning
warning information
filtering
intermediate processing
processing data
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201910834337.5A
Other languages
Chinese (zh)
Other versions
CN110533896A (en
Inventor
曹家清
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.)
Beijing Kuangshi Technology Co Ltd
Original Assignee
Beijing Kuangshi Technology 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 Beijing Kuangshi Technology Co Ltd filed Critical Beijing Kuangshi Technology Co Ltd
Priority to CN201910834337.5A priority Critical patent/CN110533896B/en
Publication of CN110533896A publication Critical patent/CN110533896A/en
Application granted granted Critical
Publication of CN110533896B publication Critical patent/CN110533896B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G08SIGNALLING
    • G08BSIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B31/00Predictive alarm systems characterised by extrapolation or other computation using updated historic data

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Computing Systems (AREA)
  • Emergency Management (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Telephone Function (AREA)
  • Image Processing (AREA)

Abstract

The invention provides a processing method and a processing device of early warning information and electronic equipment, wherein the method comprises the following steps: acquiring initial early warning information to be processed; if the initial early warning information is associated with intermediate processing data, filtering the initial early warning information at least once based on the intermediate processing data and a pre-configured filtering condition to obtain final early warning information; the initial early warning information is obtained based on intermediate processing data, and the intermediate processing data is obtained based on the acquired original data; the raw data includes image data. The invention can effectively improve the reliability of the early warning information.

Description

Processing method and device of early warning information and electronic equipment
Technical Field
The present invention relates to the field of data processing technologies, and in particular, to a method and an apparatus for processing early warning information, and an electronic device.
Background
In order to improve social public safety, image acquisition equipment such as a camera is usually installed in a public area to monitor the flow of people in the public area and acquire image data of the public area in real time, and the acquired image data is processed on the basis to obtain early warning information such as single night-day and night-night emergence early warning or group area gathering early warning and the like so as to remind related people to take measures in time. The method for determining the early warning information mainly comprises a real-time stage and an off-line stage, namely, image data are collected and subjected to preliminary statistical analysis in the real-time stage, data obtained in the real-time stage are further analyzed in the off-line stage, and the early warning information is finally generated. However, the inventor has found that the method is separated by a certain time interval between the real-time phase and the offline phase, and the warning influencing factors (such as the change of the area to which the image acquisition device belongs, the change of the archival relationship, and the like) may change in the time interval, so that the reliability of the warning information generated based on the data in the real-time phase in the offline phase is low.
Disclosure of Invention
In view of the above, the present invention provides a method and an apparatus for processing warning information, and an electronic device, which can effectively improve the reliability of the warning information.
In order to achieve the above purpose, the embodiment of the present invention adopts the following technical solutions:
in a first aspect, an embodiment of the present invention provides a method for processing early warning information, including: acquiring initial early warning information to be processed; if the initial early warning information is associated with intermediate processing data, filtering the initial early warning information at least once based on the intermediate processing data and a pre-configured filtering condition to obtain final early warning information; wherein the initial early warning information is obtained based on the intermediate processing data, and the intermediate processing data is obtained based on the collected original data; the raw data includes image data.
Further, the step of performing at least one filtering process on the initial early warning information based on the intermediate processing data and a pre-configured filtering condition to obtain final early warning information includes: filtering the initial early warning information based on the intermediate processing data and a first preset filtering condition to obtain first early warning information; judging whether the acquisition equipment of the original data is updated or not; if yes, updating the intermediate processing data based on the updated original data acquired by the acquisition equipment, and determining a second filtering condition according to the updated intermediate processing data; and filtering the first early warning information based on the second filtering condition to obtain final early warning information.
Further, the step of filtering the initial early warning information based on the intermediate processing data and a first filtering condition configured in advance to obtain first early warning information includes: filtering the intermediate processing data based on a first preset filtering condition to obtain filtered intermediate processing data; adjusting the first filtering condition based on the filtered intermediate processing data to obtain an adjusted first filtering condition; and filtering the initial early warning information by using the adjusted first filtering condition to obtain first early warning information.
Further, the method further comprises: if the initial early warning information is not associated with intermediate processing data, judging whether the acquisition equipment of the original data is updated; if yes, generating intermediate processing data based on the updated original data acquired by the acquisition equipment; and filtering the initial early warning information according to the generated intermediate processing data to obtain final early warning information.
Further, the step of filtering the initial early warning information according to the generated intermediate processing data to obtain final early warning information includes: determining a third filtering condition according to the generated intermediate processing data; and filtering the initial early warning information based on the third filtering condition to obtain final early warning information.
Further, the step of obtaining the initial early warning information to be processed includes: acquiring image data through image acquisition equipment; performing portrait analysis on the image data according to a preset time window to obtain intermediate processing data; generating initial early warning information based on the intermediate processing data; the initial early warning information comprises single early warning information and/or group early warning information.
Further, the filtering condition includes one or more of a threshold condition, a time condition, a region condition, and an archive condition.
Further, the method further comprises: and pushing the final early warning information to a related terminal.
In a second aspect, an embodiment of the present invention provides an apparatus for processing early warning information, including: the information acquisition module is used for acquiring initial early warning information to be processed; the filtering module is used for carrying out at least one filtering treatment on the initial early warning information based on intermediate processing data and a pre-configured filtering condition to obtain final early warning information if the initial early warning information is associated with the intermediate processing data; wherein the initial early warning information is obtained based on the intermediate processing data, and the intermediate processing data is obtained based on the collected original data; the raw data includes image data.
In a third aspect, an embodiment of the present invention provides an electronic device, including a processor and a storage device; the storage device has stored thereon a computer program which, when executed by the processor, performs the method of any one of the aspects as provided in the first aspect.
In a fourth aspect, the present invention provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, performs the steps of the method according to any one of the above-mentioned first aspect.
The method, the device and the electronic equipment for processing the early warning information provided by the embodiment of the invention are used for acquiring initial early warning information to be processed (obtained based on intermediate processing data), and when the initial early warning information is associated with the intermediate processing data (obtained based on acquired original data), filtering the initial early warning information at least once based on the intermediate processing data and pre-configured filtering conditions to obtain final early warning information, wherein the original data comprises image data. The embodiment of the invention processes the initial early warning information on the basis of the initial early warning information, and when the initial early warning information is associated with intermediate processing data, the initial early warning information is filtered at least once according to the intermediate processing data and preset filtering conditions, so that final early warning information with higher reliability is screened out from the initial early warning information, and the reliability of the early warning information is effectively improved.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a schematic structural diagram of an electronic device according to an embodiment of the present invention;
fig. 2 is a schematic flowchart of a method for processing warning information according to an embodiment of the present invention;
fig. 3 is a schematic flowchart of another method for processing warning information according to an embodiment of the present invention;
fig. 4 is a schematic flowchart of another method for processing warning information according to an embodiment of the present invention;
fig. 5 is a schematic flowchart of another method for processing warning information according to an embodiment of the present invention;
fig. 6 is a schematic flowchart of another method for processing warning information according to an embodiment of the present invention;
fig. 7 is a schematic structural diagram of an apparatus for processing warning information according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the embodiments, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Currently, the prior art obtains early warning information by processing raw data such as image data in real time and offline. The real-time processing may be real-time processing of image data acquired by the image acquisition device by using a continuously executed process, and in practical application, a real-time processing result may be stored in an HDFS (Hadoop Distributed File System), for example, real-time daily snapshot statistics, hourly snapshot statistics of each image acquisition device, or per minute image data is stored in the HDFS; the offline processing may be a process that is periodically started to periodically process a real-time processing result stored in the HDFS, for example, the offline processing required by the warning of the daytime and nighttime of an individual needs to further analyze daily real-time snapshot statistics for many consecutive days. However, since there is a certain time difference between the time of offline processing and the time generated by the real-time processing result based on the time of offline processing, factors affecting the accuracy of the warning information may be changed within the time difference, so that the warning information obtained by offline processing is not accurate. In view of the problem that the early warning information obtained by the method has low reliability, embodiments of the present invention provide a method, an apparatus, and an electronic device for processing early warning information, which can be applied to various occasions where early warning information needs to be generated, and the following describes embodiments of the present invention in detail.
The first embodiment is as follows:
first, an example electronic device 100 for implementing the method and apparatus for processing warning information according to the embodiment of the present invention is described with reference to fig. 1.
As shown in fig. 1, an electronic device 100 includes one or more processors 102, one or more memory devices 104, an input device 106, an output device 108, and an image capture device 110, which are interconnected via a bus system 112 and/or other type of connection mechanism (not shown). It should be noted that the components and structure of the electronic device 100 shown in fig. 1 are exemplary only, and not limiting, and the electronic device may have other components and structures as desired.
The processor 102 may be implemented in at least one hardware form of a Digital Signal Processor (DSP), a Field Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), the processor 102 may be one or a combination of several of a Central Processing Unit (CPU) or other forms of processing units with data processing capability and/or instruction execution capability, and may control other components in the electronic device 100 to perform desired functions.
The storage 104 may include one or more computer program products that may include various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory. The volatile memory may include, for example, Random Access Memory (RAM), cache memory (cache), and/or the like. The non-volatile memory may include, for example, Read Only Memory (ROM), hard disk, flash memory, etc. On which one or more computer program instructions may be stored that may be executed by processor 102 to implement client-side functionality (implemented by the processor) and/or other desired functionality in embodiments of the invention described below. Various applications and various data, such as various data used and/or generated by the applications, may also be stored in the computer-readable storage medium.
The input device 106 may be a device used by a user to input instructions and may include one or more of a keyboard, a mouse, a microphone, a touch screen, and the like.
The output device 108 may output various information (e.g., images or sounds) to the outside (e.g., a user), and may include one or more of a display, a speaker, and the like.
The image capture device 110 may take images (e.g., photographs, videos, etc.) desired by the user and store the taken images in the storage device 104 for use by other components.
Exemplary electronic devices for implementing the method and apparatus for processing warning information according to the embodiments of the present invention may be implemented on mobile terminals such as smart phones, tablet computers, and the like.
Example two:
referring to a flow diagram of a processing method of early warning information shown in fig. 2, the method mainly includes the following steps S202 to S204:
step S202, initial early warning information to be processed is obtained.
The initial warning information may be understood as information for warning an abnormal activity of an individual or a group, for example, the abnormal activity may include one or more of abnormal behaviors such as sudden increase of the individual activity, sudden decrease of the individual activity, staying of an individual region, frequent emergence of the individual region, frequent emergence of a group region, aggregation of group regions, aggregation of group single points, aggregation of group region foot-drop points, aggregation of group single point foot-drop points, and the like.
In one embodiment, the initial warning information to be processed may be directly pulled from a database or a message queue storing the initial warning information, where the message queue may include Kafka (distributed publish-subscribe messaging system) message middleware; the initial early warning information obtained by the prior art is stored in the database or the message queue. In another embodiment, the image data acquired by the image acquisition device may be acquired, and the initial warning information may be obtained by performing real-time and offline processing on the image data, for example, the image data acquired by the image acquisition device in a first time period may be processed in real time to obtain intermediate processing data, then all the intermediate processing data in a second time period may be processed offline to obtain an offline processing result, and finally the offline processing result may be roughly filtered to obtain the initial warning information.
And step S204, if the initial early warning information is associated with intermediate processing data, filtering the initial early warning information at least once based on the intermediate processing data and pre-configured filtering conditions to obtain final early warning information.
If the initial warning information is associated with intermediate processed data, the initial warning information is obtained based on the intermediate processed data, and the intermediate processed data is obtained based on the acquired raw data, wherein the raw data includes image data, such as a snapshot of an image acquisition device. The filtering conditions may include a filtering condition for filtering the intermediate processing data and a filtering condition for filtering the initial early warning data, and may be configured based on actual conditions in specific applications, for example, the filtering conditions are respectively set for different abnormal activities. The final early warning information is the early warning information with higher credibility screened from the initial early warning information. In practical application, an early warning model can be established based on the filtering condition, initial early warning information is input to the early warning model configured with the filtering condition, and final early warning information output by the early warning model is obtained.
In some embodiments, if the initial warning information is associated with intermediate processing data, the intermediate processing data may be filtered by using a filtering condition, and then the filtering condition is adjusted based on the filtered intermediate processing data, so that the initial warning information is once filtered based on the adjusted filtering condition, and on this basis, it is determined whether the filtered initial warning information still needs to be filtered again, for example, the image acquisition device B arranged in the target area a is deleted, and at this time, the original data acquired by the image acquisition device B is invalid original data. And if invalid original data exists in the original data, determining that the filtered initial early warning information needs to be filtered for the second time until determining that the initial early warning information which is filtered for many times does not need to be filtered again, and taking the initial early warning information obtained by the last filtering as final early warning information.
In the method for processing the early warning information, initial early warning information to be processed (obtained based on intermediate processing data) is obtained, and when the initial early warning information is associated with the intermediate processing data (obtained based on acquired original data), the initial early warning information is filtered at least once based on the intermediate processing data and pre-configured filtering conditions, so that final early warning information is obtained, wherein the original data comprises image data. The embodiment of the invention processes the initial early warning information on the basis of the initial early warning information, and when the initial early warning information is associated with intermediate processing data, the initial early warning information is filtered at least once according to the intermediate processing data and preset filtering conditions, so that final early warning information with higher reliability is screened out from the initial early warning information, and the reliability of the early warning information is effectively improved.
In order to facilitate understanding of the step S202, an embodiment of the present invention provides a specific implementation manner for acquiring initial warning information to be processed, which may be performed according to the following steps (1) to (3):
(1) and acquiring image data through image acquisition equipment. The image capturing apparatus may include an apparatus having a photographing function, such as a camera, among others. In specific implementation, image acquisition equipment can be arranged at a specified position to acquire or capture image data in a target area in real time.
(2) And carrying out portrait analysis on the image data according to a preset time window to obtain intermediate processing data. The time window, that is, the first duration, may be set based on an actual requirement in an actual application, such as setting the time window to 5 minutes, 1 hour, or one day, and the portrait analysis may be identification analysis of people in the image data by using an image identification technology, and the content of the portrait analysis may include analyzing the number of people in the image data, or performing facial recognition on a portrait in the image data to find identity information corresponding to each portrait based on a facial recognition result, or analyzing a behavior of the portrait in the image data. In some embodiments, the portrait analysis results may be used directly as intermediate processing data; the portrait analysis result may also be further processed, for example, statistically processed, and the processed result is used as intermediate processing data, where the intermediate processing data may include real-time snapshot statistics per hour for individuals, real-time snapshot statistics per day for individuals, snapshot statistics for image acquisition devices, duplicate removal operation performed on snapshot data in a certain period of time at intervals of a preset duration, or image data stored at intervals of a preset duration.
(3) And generating initial early warning information based on the intermediate processing data. The initial early warning information can be a big data portrait early warning result, and various types of initial early warning information meeting public safety requirements are generated by performing real-time and offline streaming processing on the acquired image data, wherein the intermediate processing data is a result obtained by real-time processing. During specific implementation, all intermediate processing data in the second duration needs to be processed offline, and the result of offline processing needs to be filtered to obtain initial early warning information.
In addition, the initial early warning information comprises single early warning information and/or group early warning information, wherein the single early warning information can comprise one or more of a personal night-day and night-night emergence early warning, a personal activity surge early warning, a personal area residence early warning and a personal area frequent emergence early warning, and the group early warning information can comprise one or more of a group area frequent emergence early warning, a group area aggregation early warning, a group single-point aggregation early warning, a group area footfall aggregation early warning and a group single-point footfall aggregation early warning.
Specifically, the individual daytime and nighttime warning can be understood as that a preset multiple threshold value that the number of times of night occurrence is the number of times of daytime occurrence is satisfied for a plurality of consecutive days by a certain person, for example, if the number of times of night occurrence is 5 times of the number of times of daytime occurrence is satisfied for 7 consecutive days by the target object a, the individual daytime and nighttime warning is generated; the personal activity surge warning can be understood as a preset multiple threshold value that the number of times that a person spends or spends on the same day is a plurality of consecutive days before the same day, for example, the number of times that the target object a spends or spends on 10 days in 8 months is 15 times, and the number of times that the target object a spends or spends on 9 days in 8 months is less than 5 times each day between 4 days in 8 months and 9 days in 8 months, namely the number of times that the target object a spends on 10 days in 8 months is 3 times that the number of times that the target object a spends on 10 days in 8 months is 5 consecutive days before 10 days in 8 months, and then the personal activity surge warning is generated; the early warning of sudden reduction of personal activities can be understood as that the number of times of the person is a preset score threshold value of the number of times of the person continuously appearing and disappearing for a plurality of days before the current day; the personal area residence early warning can be understood as that a person appears in the current area and does not appear in other areas within a period of time; the condition that the number of times that a person appears in the current area is higher than a preset number threshold value in a specified period can be understood as that the person frequently gives out early warning.
The embodiment of the invention further exemplarily illustrates the group early warning information, wherein frequent occurrence of early warning in a group area can be understood as that the number of times of capturing the group personnel appearing in the current area in a specified period is higher than a preset number threshold; the group area gathering early warning can be understood as that the number of people in a certain area is higher than a preset number threshold; the group single-point gathering early warning can be understood that the number of people of a group appearing under a certain image acquisition device is higher than a preset number threshold, for example, a drug-taking group gathers under a certain image acquisition device; the early warning of the gathering of the footfall points in the population area can be understood as that the number of people of the population standing in a certain area is higher than a preset threshold, for example, the drug-taking population leaves after a period of time when the footfall of the drug-taking population in the certain area occurs, and the appearance time of the drug-taking population at the footfall points has intersection; the group single-point footfall gathering early warning can be understood as that the number of people of a group standing under a certain image acquisition device is higher than a preset number threshold.
In addition, the filtering condition provided for the embodiment of the present invention may include one or more of a threshold condition, a time condition, a region condition, and an archive condition. The threshold condition may include the preset multiple threshold, the preset score threshold, the preset number threshold, and the like, and may be specifically set based on an actual situation; the time condition may be understood as presetting an effective time period and an ineffective time period, for example, setting a working day as the effective time period and setting a holiday as the ineffective time period, and when determining the final early warning information, the initial early warning information in the ineffective time period may be filtered out; the area condition can be understood as presetting a target area, so that initial early warning information outside the target area is filtered when final early warning information is determined; the profile condition may be understood as a filtering condition of the personal identity information, for example, if the personal profile of the target object a belongs to a white list profile, the target object a may be directly filtered out when determining the final warning information, wherein the white list may be understood as a security personnel, and may be determined based on the daily activities or social status of the target object a. For the above-mentioned archive conditions, in a specific application, each person has a corresponding personal archive, that is, a person-file, which is a personal archive obtained by initially clustering existing portrait data and classifying subsequently acquired portrait data into corresponding personal archive, and an obtained personal archive set (that is, the aforementioned personal archive) of each person in different time and space is obtained.
In order to facilitate understanding of the step S204, an embodiment of the present invention provides a method for performing at least one filtering process on initial early warning information based on intermediate processing data and a pre-configured filtering condition to obtain final early warning information, where the method includes the following steps 1 to 4:
step 1, filtering the initial early warning information based on the intermediate processing data and a first preset filtering condition to obtain first early warning information. The first filtering condition may include a threshold condition and a number of considerations (including the aforementioned temporal condition, and archival condition). In specific implementation, a first filtering condition can be configured in advance for intermediate processing data, the intermediate processing data is subjected to primary filtering processing according to the first filtering condition, required intermediate processing data is screened out, the first filtering condition is adjusted based on the required intermediate processing data, and initial early warning information is filtered by the adjusted first filtering condition. The embodiment of the present invention further provides a specific implementation manner of step 1, which is shown in the following steps (1) to (3):
(1) and filtering the intermediate processing data based on a first preset filtering condition to obtain filtered intermediate processing data. For example, the first filtering condition includes a target area M, an effective time period N, a personal profile, a group to which each personal profile belongs, and the like, and invalid intermediate processing data, which does not belong to the target area M, is not within the effective time period N, is marked with a white list for the personal profile, and does not belong to a dangerous group, in the intermediate processing data is filtered out based on the first filtering condition, so that valid intermediate processing data (that is, the aforementioned filtered intermediate processing data) satisfying the first filtering condition is obtained.
(2) And adjusting the first filtering condition based on the filtered intermediate processing data to obtain an adjusted first filtering condition. Taking the individual daytime and nighttime occurrence warning as an example, the number of nighttime occurrences set in the first filtering condition before adjustment is 1.1 times the number of daytime occurrences, and after the effective intermediate processing data is processed, it is found that the average number of nighttime occurrences of the individual is 1.1 times the number of daytime occurrences, and at this time, the number of nighttime occurrences in the first filtering condition is adjusted to 1.2 times the number of daytime occurrences. When the first filtering condition is adjusted, the influence of different filtering conditions on the first early warning information needs to be considered, and in practical application, when the number of personal files is adjusted up in the first filtering condition, the phenomenon of missing report can be caused; when the number of personal files is adjusted downwards in the first filtering condition, a false alarm phenomenon can be caused; altering the population (e.g., removing target object a from the drug-addicted population) for each person profile in the first filtering condition may result in a false positive.
(3) And filtering the initial early warning information by using the adjusted first filtering condition to obtain first early warning information. The filtering can be called as first-time threshold value calculating filtering, and initial early warning information is primarily screened by using a first filtering condition obtained on the basis of effective intermediate processing data so as to obtain first early warning information with relatively high reliability.
And 2, judging whether the acquisition equipment of the original data is updated or not. If yes, executing step 3; if not, the process is ended. Considering that when the initial early warning information is processed, the current image acquisition equipment in the target area may be changed, and the first early warning information is inevitably inaccurate, the method judges whether the acquisition equipment of the original data is updated, and takes the first early warning information as the final early warning information when the acquisition equipment is determined not to be updated, but if the acquisition equipment is updated, the following steps 3 to 4 are executed to screen out the final early warning information from the first early warning information. For example, the image capturing devices of the hai lake area are classified into the west area, which corresponds to a decrease in the image capturing devices, and an increase in the image capturing devices for the west area. When the final early warning information of the lake region is determined, due to the fact that the number of image acquisition devices is reduced, invalid early warning information exists in first early warning information obtained by screening from the initial early warning information, and a false warning phenomenon may occur; when the final early warning information of the western city is determined, the newly added image acquisition equipment does not acquire the original data acquired by the newly added image acquisition equipment, so that intermediate processing data acquired based on the original data is incomplete, and at the moment, although false alarm is not given, the phenomenon of missing report may exist.
In one embodiment, whether the acquisition device of the original data is updated may be determined by determining whether the number of image acquisition devices in the target area changes, and if the number of image acquisition devices in the target area increases or decreases, determining that the acquisition device of the original data is updated. In another embodiment, the identity information (such as a number) of the image capturing device may be obtained, and when the identity information of the image capturing device changes, it is determined that the capturing device of the original data is updated.
And 3, updating the intermediate processing data based on the updated original data acquired by the acquisition equipment, and determining a second filtering condition according to the updated intermediate processing data. In order to make the intermediate data more accurate, the embodiment of the invention obtains the updated original data acquired by the acquisition device, updates the intermediate processing data based on the updated original data, and determines the second filtering condition by using the updated intermediate processing data, thereby screening the final early warning information with higher reliability from the first early warning information based on the second filtering condition.
And 4, filtering the first early warning information based on the second filtering condition to obtain final early warning information. The filtering can be called as second-time threshold value filtering, and the first early warning information is subjected to second-time screening by using a second filtering condition obtained on the basis of the updated intermediate processing data, so that the final early warning information with higher reliability is obtained.
In view of the fact that the initial early warning information is not associated with intermediate processing data, in order to obtain final early warning information with high reliability from such initial early warning information, the embodiment of the present invention further provides a method for processing the initial early warning information when the initial early warning information is not associated with intermediate processing data, which may specifically refer to steps a to c:
and a, if the initial early warning information is not associated with intermediate processing data, judging whether the acquisition equipment of the original data is updated. If yes, executing step b; if not, the process is ended. Because the initial early warning information is not associated with the intermediate processing data, the initial early warning information is not required to be subjected to threshold value calculation filtering for the first time, and the initial early warning information is directly subjected to threshold value calculation filtering for the second time, wherein the threshold value calculation filtering for the first time can be understood as filtering the initial early warning information based on the intermediate processing data, and the threshold value calculation filtering for the second time can be understood as filtering the first early warning information or the initial early warning information based on the original data. In addition, the method for judging whether the acquisition device of the original data is updated can be referred to the aforementioned step 2.
And b, generating intermediate processing data based on the updated original data acquired by the acquisition equipment. In one embodiment, if an image acquisition device is newly added in the target area, acquiring original data acquired by the newly added image acquisition device, and calculating intermediate processing data by combining the original data acquired by the original image acquisition device and the original data acquired by the newly added image acquisition device; if the image acquisition equipment in the target area is removed (namely, invalid equipment), the original data acquired by the image acquisition equipment which is not removed can be acquired again, the original data acquired by the invalid equipment can be deleted from the acquired original data, and the intermediate processing data is recalculated on the basis of the acquired original data or on the basis of the deleted original data acquired by the invalid equipment.
And c, filtering the initial early warning information according to the generated intermediate processing data to obtain final early warning information. The embodiment of the invention provides a specific implementation method for filtering initial early warning information according to generated intermediate processing data to obtain final early warning information, which comprises the following steps: (1) and determining a third filtering condition according to the generated intermediate processing data. The third filtering condition also includes the aforementioned threshold condition, time condition, area condition or archive condition, and the third filtering condition may also be set based on actual conditions. (2) And filtering the initial early warning information based on the third filtering condition to obtain final early warning information. In a specific implementation, N filtering conditions are configured in the third filtering condition, and zero or one piece of early warning information can be obtained when each filtering condition is used for filtering the initial early warning information, so that at most N pieces of early warning information are obtained when the N filtering conditions are configured in the third filtering condition, that is, the number of the final early warning information obtained by filtering is greater than or equal to 0 and less than or equal to N.
When the final group early warning information is determined, the situation that the personal files are manually merged exists, for example, the personal files are manually removed from dangerous group files or two personal files are manually merged (namely, a subclass is scattered and then clustered), intermediate processing data are inaccurate, wherein false alarm possibly occurs due to the removal of the personal files, so that whether the group files to which the personal files belong are updated or not can be judged, all the personal files in a target group file are obtained again when the group files to which the personal files belong are changed, the intermediate processing data are generated by combining original data acquired by image acquisition equipment, and the initial early warning information is filtered based on the intermediate processing data to obtain the final early warning information.
The embodiment of the invention can obtain the following technical effects by executing at least one filtering process on the initial early warning information to be processed: (1) the accuracy and the timeliness of the final early warning information are improved; (2) the filtering condition can be customized based on actual conditions, such as customizing a white list; (3) the processing flow of the existing early warning information is optimized, and the efficiency of processing the early warning information is improved; (4) the embodiment of the invention can improve the existing big data portrait early warning, and particularly, the early warning effect of the initial early warning information is poor because the filtering condition set when the initial early warning information is generated by the existing big data portrait early warning is wider, and the embodiment of the invention combines intermediate processing data and the pre-configured filtering condition to filter the initial early warning information at least once on the basis of the existing big data portrait early warning to obtain final early warning information with higher accuracy, namely, the early warning information processing method provided by the embodiment of the invention is further used for improving the processing process of the existing big data portrait early warning.
Example three:
for a second method for processing the warning information provided in the embodiment, an application example of the method is provided in the embodiment of the present invention, referring to a flow diagram of another method for processing the warning information shown in fig. 3, the method may include the following steps S302 to S312:
step S302, a QAM (Quasi-Alert Message, Quasi-early warning information), that is, the aforementioned initial early warning information, is pulled from the Kafka Message middleware.
Step S304, carrying out at least one filtering process on QAM based on intermediate processing data (namely, stream intermediate results) to obtain final early warning information. In one embodiment, a first and/or second calculation of threshold filtering may be performed on a QAM.
And step S306, judging whether the final early warning information is empty or not. If yes, ending; if not, step S308 is performed. And finally, if the early warning information is null, the QAM is understood to be filtered completely.
And step S308, performing warehousing processing on the final early warning information. The warehousing process may be understood as storing the final warning information in a PG (PostgreSQL, database management system) library.
In an embodiment, the final warning information may also be pushed to a related terminal to put the final warning information into a specific application scenario, which may be specifically seen in steps S310 to S312 shown below.
And step S310, carrying out real-time situation statistics on the final early warning information, and displaying the final early warning information in real time through a front end (such as a display device) and associating an intermediate processing result with the final early warning information. Visualization of the final early warning information can be achieved by pushing the final early warning information to the front end.
Step S312, the final early warning information and the intermediate processing result associated with the final early warning information are sent to an application module, such as an attention point calculation module, the attention point integral of the corresponding person in the single early warning information is calculated by the attention point integral calculation module, when the attention point integral is higher, the personal file corresponding to the single early warning information is moved to a high-attention group file (for example, a dangerous group file or a virus-absorbing group file), and in addition, the calculated attention point integral can be saved in Kafka message middleware.
Step S314, if abnormal conditions such as power failure or network failure occur in the process of processing the early warning information, the QAM can be backed up into the PG library through QAMB (RAM Backup), so that the QAM can be processed continuously after the abnormal conditions are recovered.
In order to facilitate understanding of the step S302, the embodiment of the present invention provides an implementation manner of the step S302, referring to a flowchart of another method for processing warning information shown in fig. 4, where the method may include the following steps S402 to S410:
step S402, obtaining QAM to be processed.
Step S404, judging whether the QAM is single-person early warning information or not; if yes, go to step S406; if not, step S408 is performed.
And S406, filtering the single early warning information at least once to obtain the single final early warning information.
And step S408, filtering the group early warning information at least once to obtain the final group early warning information.
And step S410, returning APF (alert-Profiles-Faces) based on the single final early warning information or the group final early warning information. Wherein, Alerts is the aforementioned final warning information, Profiles is personal files, and Faces is the original data.
For the step S406, the embodiment of the present invention further provides a specific implementation manner of a method for processing single warning information, referring to a flow diagram of another method for processing single warning information shown in fig. 5, where the method may include the following steps S502 to S522:
and step S502, acquiring single early warning information to be processed.
In step S504, a personal early warning model (i.e., the aforementioned first filtering condition) is obtained. Wherein the personal early warning model includes one or more of a threshold condition, a time condition, and an area condition.
Step S506, judging whether the personal early warning model is empty. If yes, ending; if not, step S508 is performed. That is, whether the personal early warning model is configured or not is judged, and if the personal early warning model is not configured, the personal early warning model is determined to be empty.
In step S508, a personal profile is obtained. In one embodiment, the image data captured by the image capturing device carries a capture ID (identification), and a personal profile corresponding to the person in the image data can be obtained based on the capture ID. In another embodiment, the image data may be subjected to portrait processing to determine identity information corresponding to the portrait in the image data, and then a personal profile corresponding to the portrait may be obtained based on the identity information.
Step S510, determine whether the personal profile is valid. If yes, go to step S512; if not, the process is ended. In order to screen out effective intermediate processing data from the intermediate processing data, the embodiment of the invention judges the validity of the personal profile, for example, judges whether the identity information recorded in the personal profile is expired or not.
Step S512, performing first-time calculation threshold filtering on the single early warning information based on the personal early warning model and the personal archive to obtain a first early warning set, wherein the first early warning set can be understood as a set of the first early warning information. During specific implementation, archive conditions are configured based on the personal archive, so that intermediate processing data are filtered based on the personal early warning model and the archive conditions, effective intermediate processing data are obtained, the personal early warning model and the archive conditions are adjusted based on the effective intermediate processing data, and then threshold value filtering is calculated for the first time on the basis of the personal early warning model and the archive conditions on the single early warning information.
Step S514, determine whether the first warning set is empty. If yes, ending; if not, step S516 is performed. And if the early warning model and the file condition completely filter the single early warning information, the first early warning set is empty.
Step S516, the first early warning set is organized into a personal profile. In some embodiments, the first early warning set may be added to a personal profile, and the raw data and intermediate processed data may also be added to the personal profile to complete the personal profile.
And step S518, performing threshold value filtering on the first early warning set for the second time to obtain a second early warning set, where the second early warning set can be understood as the set of the aforementioned final early warning information. During specific implementation, the updated original data captured by the image acquisition equipment is obtained, the intermediate processing data is determined based on the original data, and the personal early warning model is updated again based on the intermediate processing data, so that the second calculation threshold filtering is performed on the first early warning set based on the updated personal early warning model.
Step S520, determine whether the second early warning set is empty. If yes, ending; if not, step S522 is performed. And if the first early warning information is completely filtered by the second time of threshold value calculation filtering, the second early warning set is empty.
Step S522, saving the second warning set to the PG library. In specific implementation, the second early warning set, the early warning personnel file and the file snapshot portrait are stored in the PG library in an associated mode.
In one embodiment, the processing of the single-person early warning information can be divided into a general person early warning and an attention person early warning, wherein the general person early warning can be understood that the personal profile of the target object does not belong to any group profile, and the attention person early warning can be understood that the personal profile of the target object belongs to a high-attention group profile such as a dangerous group. In practical application, even if abnormal behaviors exist in ordinary personnel, the early warning information may not be generated, and when abnormal behaviors exist in concerned personnel, the early warning information is generated.
For the step S408, the embodiment of the present invention further provides a specific implementation manner of a group warning information processing method, referring to a flow diagram of another warning information processing method shown in fig. 6, where the method may include the following steps S602 to S6:
and step S602, acquiring group early warning information.
In step S604, a group warning model (i.e., the first filtering condition) is obtained. Wherein the population pre-warning model comprises one or more of a threshold condition, a time condition, and a region condition.
Step S606, judging whether the group early warning model is empty. If yes, ending; if not, step S608 is performed.
And step S608, performing first-time calculation threshold filtering on the group early warning information according to the intermediate processing data and the early warning model to obtain a third early warning set. The third warning set can be understood as the set of the first warning information.
Step S610 determines whether the third early warning set is empty. If yes, ending; if not, step S612 is performed.
And step S612, weaving the third early warning set into a group file. In particular implementations, a third early warning set, raw data, and intermediate processed data may be added to the group profile. For example, the group file is divided into a dangerous group file or a drug-taking group file in advance, the group file to which the third early warning set belongs is determined, and the third early warning set, the original data and the intermediate processing data are added to the corresponding group file in an associated manner.
In step S614, it is determined whether the portrait set is empty. If yes, ending; if not, step S616 is performed. The portrait collection can be understood as a collection obtained by processing the portrait of the original data. And if the original data does not contain the portrait, the portrait set corresponding to the original data is empty. Considering that the second threshold filtering is performed based on the original data, further, the second threshold filtering is performed based on the portrait set in the original data, so that whether the portrait set is empty is determined, and the second threshold filtering is performed on the third early warning set based on the portrait set.
Step S616, determining whether to perform the second threshold filtering on the third early warning set. If yes, go to step S618; if not, the process is ended. Specifically, whether the image acquisition device is updated or whether the group archive to which the personal archive belongs changes can be judged, and if the image acquisition device is updated or the group archive to which the personal archive belongs changes, the threshold value of the third early warning set is calculated for the second time and filtered.
And step 618, performing threshold value calculation and filtering on the third early warning set for the second time to obtain a fourth early warning set. During specific implementation, the portrait set is used for calculating intermediate processing data, the group early warning model is updated based on the intermediate processing data, the updated group early warning model is used for carrying out second calculation threshold filtering on the third early warning set, and a fourth early warning set is obtained, wherein the fourth early warning set is also the set of the final early warning information.
Step S620, determine whether the fourth warning set is empty. If yes, ending; if not, step S622 is performed.
And step S622, perfecting the fourth early warning set. In one embodiment, the fourth early warning set may be added to the corresponding group profile and the number of personal profiles in the group profile, the name or number of each personal profile, and the raw data contained in each personal profile may be updated.
And step S624, storing the completed fourth early warning set to the PG library.
The processing method of the early warning information provided by the embodiment of the invention processes the initial early warning information on the basis of the initial early warning information, and when the initial early warning information is associated with intermediate processing data, the initial early warning information is filtered at least once according to the intermediate processing data and preset filtering conditions, so that the final early warning information with higher reliability is screened out from the initial early warning information, the problem of inaccurate early warning information caused by the change of the relationship between the initial data and a personal file, the relationship between the personal file and a group file and the relationship between an image acquisition device and a target area in the prior art is effectively solved, and the reliability of the early warning information is further effectively improved.
Example four:
as to the processing method of the warning information provided in the foregoing embodiment, an embodiment of the present invention provides a processing apparatus of warning information, and referring to a schematic structural diagram of a processing apparatus of warning information shown in fig. 7, the apparatus may include the following components:
an information obtaining module 702, configured to obtain initial early warning information to be processed.
And the filtering module 704 is configured to, if the initial early warning information is associated with intermediate processing data, perform at least one filtering process on the initial early warning information based on the intermediate processing data and a pre-configured filtering condition to obtain final early warning information.
The initial early warning information is obtained based on intermediate processing data, and the intermediate processing data is obtained based on the acquired original data; the raw data includes image data.
The processing device for the early warning information provided by the embodiment of the invention processes the initial early warning information on the basis of the initial early warning information, and when the initial early warning information is associated with intermediate processing data, the initial early warning information is filtered at least once according to the intermediate processing data and preset filtering conditions, so that final early warning information with higher reliability is screened out from the initial early warning information, and the reliability of the early warning information is effectively improved.
In an embodiment, the filtering module 704 further includes a first filtering unit, a first determining unit, a condition updating unit, and a second filtering unit, where the first filtering unit is configured to filter the initial warning information based on the intermediate processing data and a first filtering condition configured in advance, so as to obtain first warning information; the first judgment unit is used for judging whether the acquisition equipment of the original data is updated or not; the condition updating unit is used for updating the intermediate processing data based on the updated original data acquired by the acquisition equipment and determining a second filtering condition according to the updated intermediate processing data when the judgment result of the first judging unit is yes; the second filtering unit is used for filtering the first early warning information based on a second filtering condition to obtain final early warning information.
In one embodiment, the first filter unit is further configured to: filtering the intermediate processing data based on a first preset filtering condition to obtain filtered intermediate processing data; adjusting the first filtering condition based on the filtered intermediate processing data to obtain an adjusted first filtering condition; and filtering the initial early warning information by using the adjusted first filtering condition to obtain first early warning information.
In an embodiment, the processing apparatus for processing the early warning information further includes a second determining unit, a generating unit, and a third filtering unit, where the second determining unit is configured to determine whether the acquisition device of the original data is updated if the initial early warning information is not associated with intermediate processing data; the generating unit is used for generating intermediate processing data based on the updated original data acquired by the acquisition equipment when the judgment result of the second judging unit is yes; and the third filtering unit is used for filtering the initial early warning information according to the generated intermediate processing data to obtain final early warning information.
In one embodiment, the third filter unit is further configured to: determining a third filtering condition according to the generated intermediate processing data; and filtering the initial early warning information based on the third filtering condition to obtain final early warning information.
In an embodiment, the information obtaining module 702 is further configured to: acquiring image data through image acquisition equipment; performing portrait analysis on the image data according to a preset time window to obtain intermediate processing data; generating initial early warning information based on the intermediate processing data; the initial early warning information comprises single-person early warning information and/or group early warning information.
In one embodiment, the filtering condition includes one or more of a threshold condition, a time condition, a region condition, and an archive condition.
In an embodiment, the processing apparatus of the warning information further includes a pushing module, configured to push the final warning information to the associated terminal.
The device provided by the embodiment of the present invention has the same implementation principle and technical effect as the method embodiments, and for the sake of brief description, reference may be made to the corresponding contents in the method embodiments without reference to the device embodiments.
Example five:
the present embodiment also provides a computer-readable storage medium having stored thereon a computer program which, when being executed by a processor, performs the steps of the method provided by the aforementioned method embodiments.
The computer program product of the readable storage medium provided in the embodiment of the present invention includes a computer readable storage medium storing a program code, where instructions included in the program code may be used to execute the method described in the foregoing method embodiment, and specific implementation may refer to the foregoing method embodiment, which is not described herein again.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
Finally, it should be noted that: the above-mentioned embodiments are only specific embodiments of the present invention, which are used for illustrating the technical solutions of the present invention and not for limiting the same, and the protection scope of the present invention is not limited thereto, although the present invention is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: any person skilled in the art can modify or easily conceive the technical solutions described in the foregoing embodiments or equivalent substitutes for some technical features within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the embodiments of the present invention, and they should be construed as being included therein. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims (10)

1. A processing method of early warning information is characterized by comprising the following steps:
acquiring initial early warning information to be processed, wherein the initial early warning information is information for early warning abnormal activities of individuals or groups;
if the initial early warning information is associated with intermediate processing data, filtering the initial early warning information at least once based on the intermediate processing data and filtering conditions to obtain final early warning information; the filtering condition comprises a pre-configured filtering condition, and the reliability of the final early warning information is higher than that of the initial early warning information;
the initial early warning information is obtained by filtering the intermediate processing data, and the intermediate processing data is obtained based on the acquired original data; the intermediate processing data is a portrait analysis result obtained by performing portrait analysis on the image data or a result of further processing the portrait analysis result; the original data comprises image data, and the filtering condition comprises a filtering condition for filtering the intermediate processing data and a filtering condition for filtering the initial early warning information;
if the initial early warning information is not associated with intermediate processing data, judging whether the acquisition equipment of the original data is updated;
if yes, generating intermediate processing data based on the updated original data acquired by the acquisition equipment;
and filtering the initial early warning information according to the generated intermediate processing data to obtain final early warning information.
2. The method of claim 1, wherein the step of filtering the initial early warning information at least once based on the intermediate processing data and pre-configured filtering conditions to obtain final early warning information comprises:
filtering the initial early warning information based on the intermediate processing data and a first preset filtering condition to obtain first early warning information;
judging whether the acquisition equipment of the original data is updated or not;
if yes, updating the intermediate processing data based on the updated original data acquired by the acquisition equipment, and determining a second filtering condition according to the updated intermediate processing data;
and filtering the first early warning information based on the second filtering condition to obtain final early warning information.
3. The method of claim 2, wherein the step of filtering the initial pre-warning information based on the intermediate processing data and a pre-configured first filtering condition to obtain first pre-warning information comprises:
filtering the intermediate processing data based on a first preset filtering condition to obtain filtered intermediate processing data;
adjusting the first filtering condition based on the filtered intermediate processing data to obtain an adjusted first filtering condition;
and filtering the initial early warning information by using the adjusted first filtering condition to obtain first early warning information.
4. The method of claim 1, wherein the step of filtering the initial early warning information according to the generated intermediate processing data to obtain final early warning information comprises:
determining a third filtering condition according to the generated intermediate processing data;
and filtering the initial early warning information based on the third filtering condition to obtain final early warning information.
5. The method of claim 1, wherein the step of obtaining the initial pre-warning information to be processed comprises:
acquiring image data through image acquisition equipment;
performing portrait analysis on the image data according to a preset time window to obtain intermediate processing data;
generating initial early warning information based on the intermediate processing data; the initial early warning information comprises single early warning information and/or group early warning information.
6. The method of claim 1, wherein the filtering condition comprises one or more of a threshold condition, a time condition, a regional condition, and an archival condition.
7. The method of claim 1, further comprising:
and pushing the final early warning information to a related terminal.
8. An apparatus for processing warning information, comprising:
the system comprises an information acquisition module, a processing module and a processing module, wherein the information acquisition module is used for acquiring initial early warning information to be processed, and the initial early warning information is information for early warning abnormal activities of individuals or groups;
the filtering module is used for carrying out at least one filtering treatment on the initial early warning information based on intermediate processing data and filtering conditions to obtain final early warning information if the initial early warning information is associated with the intermediate processing data; the filtering condition comprises a pre-configured filtering condition, and the reliability of the final early warning information is higher than that of the initial early warning information;
the initial early warning information is obtained by filtering the intermediate processing data, and the intermediate processing data is obtained based on the acquired original data; the intermediate processing data is a portrait analysis result obtained by performing portrait analysis on the image data or a result of further processing the portrait analysis result; the original data comprises image data, and the filtering condition comprises a filtering condition for filtering the intermediate processing data and a filtering condition for filtering the initial early warning information;
the apparatus is further configured to: if the initial early warning information is not associated with intermediate processing data, judging whether the acquisition equipment of the original data is updated; if yes, generating intermediate processing data based on the updated original data acquired by the acquisition equipment; and filtering the initial early warning information according to the generated intermediate processing data to obtain final early warning information.
9. An electronic device comprising a processor and a memory device;
the storage device has stored thereon a computer program which, when executed by the processor, performs the method of any one of claims 1 to 7.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method according to any one of the claims 1 to 7.
CN201910834337.5A 2019-09-03 2019-09-03 Processing method and device of early warning information and electronic equipment Active CN110533896B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910834337.5A CN110533896B (en) 2019-09-03 2019-09-03 Processing method and device of early warning information and electronic equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910834337.5A CN110533896B (en) 2019-09-03 2019-09-03 Processing method and device of early warning information and electronic equipment

Publications (2)

Publication Number Publication Date
CN110533896A CN110533896A (en) 2019-12-03
CN110533896B true CN110533896B (en) 2022-05-03

Family

ID=68666992

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910834337.5A Active CN110533896B (en) 2019-09-03 2019-09-03 Processing method and device of early warning information and electronic equipment

Country Status (1)

Country Link
CN (1) CN110533896B (en)

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101127892A (en) * 2006-07-27 2008-02-20 索尼株式会社 Monitoring apparatus, filter calibration method, and filter calibration program
CN101820531A (en) * 2010-03-16 2010-09-01 江苏瀚远科技股份有限公司 Video anti-counterfeiting monitoring device and monitoring method
CN102884557A (en) * 2010-05-13 2013-01-16 国际商业机器公司 Auditing video analytics
CN103440738A (en) * 2013-08-16 2013-12-11 吉林大学 Early warning method of overloading of tourist footbridge in scenic area
CN204270451U (en) * 2014-12-08 2015-04-15 北京声迅电子股份有限公司 Alarming check system
CN104794827A (en) * 2014-01-17 2015-07-22 温科尼克斯多夫国际有限公司 Method and apparatus for prevention of false alarms in monitoring systems
CN107633238A (en) * 2017-10-12 2018-01-26 深圳市信海通科技有限公司 A kind of video analysis method and intellectual analysis server
CN110002303A (en) * 2018-08-09 2019-07-12 浙江新再灵科技股份有限公司 A kind of system and method based on the wrong report of temporal relationship network real time filtering elevator malfunction

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8013738B2 (en) * 2007-10-04 2011-09-06 Kd Secure, Llc Hierarchical storage manager (HSM) for intelligent storage of large volumes of data
CN106127814A (en) * 2016-07-18 2016-11-16 四川君逸数码科技股份有限公司 A kind of wisdom gold eyeball identification gathering of people is fought alarm method and device
CN109743595A (en) * 2018-12-28 2019-05-10 视联动力信息技术股份有限公司 Terminal data synchronous method and device

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101127892A (en) * 2006-07-27 2008-02-20 索尼株式会社 Monitoring apparatus, filter calibration method, and filter calibration program
CN101820531A (en) * 2010-03-16 2010-09-01 江苏瀚远科技股份有限公司 Video anti-counterfeiting monitoring device and monitoring method
CN102884557A (en) * 2010-05-13 2013-01-16 国际商业机器公司 Auditing video analytics
CN103440738A (en) * 2013-08-16 2013-12-11 吉林大学 Early warning method of overloading of tourist footbridge in scenic area
CN104794827A (en) * 2014-01-17 2015-07-22 温科尼克斯多夫国际有限公司 Method and apparatus for prevention of false alarms in monitoring systems
CN204270451U (en) * 2014-12-08 2015-04-15 北京声迅电子股份有限公司 Alarming check system
CN107633238A (en) * 2017-10-12 2018-01-26 深圳市信海通科技有限公司 A kind of video analysis method and intellectual analysis server
CN110002303A (en) * 2018-08-09 2019-07-12 浙江新再灵科技股份有限公司 A kind of system and method based on the wrong report of temporal relationship network real time filtering elevator malfunction

Also Published As

Publication number Publication date
CN110533896A (en) 2019-12-03

Similar Documents

Publication Publication Date Title
CN108965826B (en) Monitoring method, monitoring device, processing equipment and storage medium
CN111901573A (en) Fine granularity real-time supervision system based on edge calculation
CN110750670B (en) Stranger monitoring method, device and system and storage medium
CN112188531A (en) Abnormality detection method, abnormality detection device, electronic apparatus, and computer storage medium
JP6217888B1 (en) Analysis device, analysis method, and program
WO2018112722A1 (en) Video inspection method and system thereof
CN109800664B (en) Method and device for determining passersby track
US10936876B2 (en) Content recognition method, system and storage medium thereof
CN112948614A (en) Image processing method, image processing device, electronic equipment and storage medium
CN114943936A (en) Target behavior identification method and device, electronic equipment and storage medium
CN106781167B (en) Method and device for monitoring motion state of object
CN114418388A (en) Personnel management method and device based on image recognition and storage medium
CN110533896B (en) Processing method and device of early warning information and electronic equipment
CN110796014A (en) Garbage throwing habit analysis method, system and device and storage medium
CN110505438B (en) Queuing data acquisition method and camera
CN114139016A (en) Data processing method and system for intelligent cell
CN112035534A (en) Real-time big data processing method and device and electronic equipment
CN106067963B (en) Distributed automatic report method for remote large monitor abnormity
CN116245865A (en) Image quality detection method and device, electronic equipment and storage medium
CN115223076A (en) Behavior warning method, behavior warning device, behavior warning equipment and storage medium
CN110046606B (en) Early warning method and device
CN114549884A (en) Abnormal image detection method, device, equipment and medium
CN114143571B (en) User processing method, device, equipment and storage medium
CN110309878B (en) Information processing method and device and storage medium
CN117274916A (en) Security analysis method and device for monitoring video and readable storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant