CN113868471A

CN113868471A - Data matching method and system based on monitoring equipment relationship

Info

Publication number: CN113868471A
Application number: CN202111177526.3A
Authority: CN
Inventors: 李红杰; 周琳莹; 周国强; 钟丹
Original assignee: Individual
Current assignee: Individual
Priority date: 2021-10-09
Filing date: 2021-10-09
Publication date: 2021-12-31

Abstract

The invention provides a data matching method and system based on monitoring equipment relationship, and relates to the technical field of monitoring. In the invention, the equipment relation information among a plurality of monitoring terminal equipment is determined based on the first equipment characteristic information and the second equipment characteristic information of each monitoring terminal equipment, wherein the first equipment characteristic information is static characteristic information, and the second equipment characteristic information is dynamic characteristic information; acquiring to-be-processed monitoring data acquired by a plurality of monitoring terminal devices, and classifying the to-be-processed monitoring data based on device relation information among the plurality of monitoring terminal devices to obtain a corresponding data classification set; and aiming at each data classification set in at least one data classification set, carrying out data matching confirmation processing on each piece of monitoring data to be processed included in the data classification set. Based on the method, the problem of poor reliability of data matching confirmation in the prior art can be solved.

Description

Data matching method and system based on monitoring equipment relationship

Technical Field

The invention relates to the technical field of monitoring, in particular to a data matching method and system based on a monitoring device relation.

Background

In some applications of monitoring technology, sometimes a large number of monitoring terminal devices need to be arranged in a monitoring scene for information collection. For convenience of processing information acquired by each monitoring terminal device and for convenience of management and control of each monitoring terminal device, the device relationship among each monitoring terminal device needs to be determined, so that corresponding management and control can be performed on each monitoring terminal device or corresponding processing can be performed on the information acquired by each monitoring terminal device based on the device relationship among each monitoring terminal device. However, the inventor has found that, in the prior art, the device relationship between the monitoring terminal devices is generally customized based on the corresponding administrator, which may result in a problem that the reliability of the determined device relationship information between the monitoring terminal devices is not good. Therefore, when the acquired to-be-processed monitoring data collected by each monitoring terminal device is matched and confirmed based on the device relation information between the monitoring terminals, the problem of poor reliability of data matching and confirmation can occur.

Disclosure of Invention

In view of the above, the present invention provides a data matching method and system based on a monitoring device relationship to solve the problem of poor reliability of data matching confirmation in the prior art.

In order to achieve the above purpose, the embodiment of the invention adopts the following technical scheme:

a data matching method based on monitoring equipment relation is applied to a monitoring background server, the monitoring background server is in communication connection with a plurality of monitoring terminal equipment, and the data matching method based on the monitoring equipment relation comprises the following steps:

after determining that the device relationship among the plurality of monitoring terminal devices needs to be determined, determining device relationship information among the plurality of monitoring terminal devices based on first device feature information and second device feature information of each monitoring terminal device, wherein the first device feature information is used for representing static feature information of the corresponding monitoring terminal device, and the second device feature information is used for representing dynamic feature information of the corresponding monitoring terminal device;

acquiring to-be-processed monitoring data acquired by the monitoring terminal devices to obtain a plurality of pieces of to-be-processed monitoring data, and classifying the plurality of pieces of to-be-processed monitoring data based on device relationship information among the monitoring terminal devices to obtain at least one corresponding data classification set, wherein each data classification set comprises at least one piece of to-be-processed monitoring data;

and aiming at each data classification set in the at least one data classification set, carrying out data matching confirmation processing on each piece of monitoring data to be processed included in the data classification set.

In some preferred embodiments, in the data matching method based on the monitoring device relationship, the step of obtaining to-be-processed monitoring data acquired by the plurality of monitoring terminal devices to obtain a plurality of to-be-processed monitoring data, and classifying the plurality of to-be-processed monitoring data based on the device relationship information between the plurality of monitoring terminal devices to obtain the corresponding at least one data classification set includes:

clustering the monitoring terminal devices based on the device relationship information among the monitoring terminal devices to obtain at least one device cluster set, wherein each device cluster set comprises at least one monitoring terminal device;

respectively constructing a corresponding data classification empty set aiming at each equipment cluster set;

and acquiring to-be-processed monitoring data acquired by the monitoring terminal devices to obtain a plurality of pieces of to-be-processed monitoring data, attributing the to-be-processed monitoring data to the data classification empty set corresponding to the device cluster set of the monitoring terminal device corresponding to the to-be-processed monitoring data aiming at each piece of to-be-processed monitoring data, and forming a corresponding data classification set.

In some preferred embodiments, in the above data matching method based on a monitoring device relationship, the clustering the multiple monitoring terminal devices based on the device relationship information between the multiple monitoring terminal devices to obtain at least one device cluster set includes:

counting the number of the plurality of pieces of monitoring data to be processed to obtain a corresponding first data number, and determining the size relationship between the first data number and a preset first data number threshold;

if the first data quantity is smaller than the first data quantity threshold value, acquiring a preset first clustering quantity, and determining the monitoring terminal equipment with the first clustering quantity as first monitoring terminal equipment from the monitoring terminal equipment, wherein the first clustering quantity is used for representing the quantity of equipment clustering sets to be clustered;

for each monitoring terminal device except the first monitoring terminal device in the plurality of monitoring terminal devices, determining a first monitoring terminal device corresponding to the monitoring terminal device based on the device relation information between the monitoring terminal device and each first monitoring terminal device;

and aiming at each first monitoring terminal device, constructing the first monitoring terminal device and each monitoring terminal device corresponding to the first monitoring terminal device to obtain a corresponding device cluster set so as to obtain the device cluster sets with the first cluster number.

In some preferred embodiments, in the above data matching method based on a monitoring device relationship, the clustering the multiple monitoring terminal devices based on the device relationship information between the multiple monitoring terminal devices to obtain at least one device cluster set further includes:

if the first data quantity is greater than or equal to the first data quantity threshold value, calculating an average value of the device relation closeness degree values corresponding to the device relation information between the monitoring terminal device and each other monitoring terminal device aiming at each monitoring terminal device in the plurality of monitoring terminal devices, and obtaining a device relation closeness degree average value corresponding to the monitoring terminal device;

for each monitoring terminal device in the plurality of monitoring terminal devices, performing dispersion calculation processing based on a device relationship compactness degree value corresponding to the device relationship information between the monitoring terminal device and each other monitoring terminal device and the device relationship compactness mean value corresponding to the monitoring terminal device to obtain a device relationship compactness dispersion value corresponding to the monitoring terminal device;

calculating an average value corresponding to the equipment relationship compactness discrete value corresponding to each monitoring terminal equipment to obtain a corresponding target average value, and determining a second clustering number having a positive correlation with the target average value based on the target average value;

determining a second cluster number of monitoring terminal devices as second monitoring terminal devices in the plurality of monitoring terminal devices, wherein the second cluster number is used for representing the number of device cluster sets to be clustered;

for each monitoring terminal device other than the second monitoring terminal device in the plurality of monitoring terminal devices, determining a second monitoring terminal device corresponding to the monitoring terminal device based on the device relationship information between the monitoring terminal device and each second monitoring terminal device;

and for each second monitoring terminal device, constructing the second monitoring terminal device and each monitoring terminal device corresponding to the second monitoring terminal device to obtain a corresponding device cluster set so as to obtain a second cluster number of device cluster sets.

In some preferred embodiments, in the above data matching method based on a monitoring device relationship, the step of determining, as the second monitoring terminal device, the second aggregation number of monitoring terminal devices from among the plurality of monitoring terminal devices includes:

calculating the data similarity between each piece of to-be-processed monitoring data and each piece of other to-be-processed monitoring data aiming at each piece of to-be-processed monitoring data in the plurality of pieces of to-be-processed monitoring data;

calculating an average value of data similarity between the monitoring data to be processed and each other monitoring data to be processed aiming at each monitoring data to be processed in the plurality of monitoring data to be processed to obtain a data similarity average value corresponding to the monitoring data to be processed;

and determining the second cluster quantity of the to-be-processed monitoring data with the maximum corresponding data similarity mean value from the plurality of to-be-processed monitoring data, and taking the monitoring terminal equipment corresponding to the second cluster quantity of the to-be-processed monitoring data as second monitoring terminal equipment.

In some preferred embodiments, in the above monitoring device relationship-based data matching method, the step of performing, for each data classification set in the at least one data classification set, data matching confirmation processing on each piece of monitoring data to be processed included in the data classification set includes:

counting the number of the monitoring data to be processed included in the data classification set aiming at each data classification set in the at least one data classification set to obtain a first data statistical number corresponding to the data classification set, and determining a relative size relation between the first data statistical number and a predetermined first data statistical number threshold;

and for each data classification set in the at least one data classification set, if the first data statistical quantity corresponding to the data classification set is smaller than the first data statistical quantity threshold, determining each piece of to-be-processed monitoring data included in the data classification set as valid to-be-processed monitoring data respectively.

In some preferred embodiments, in the above monitoring device relationship-based data matching method, the step of performing, for each data classification set in the at least one data classification set, data matching confirmation processing on each piece of monitoring data to be processed included in the data classification set further includes:

for each data classification set in the at least one data classification set, if the first data statistical quantity corresponding to the data classification set is greater than or equal to the first data statistical quantity threshold, determining whether each monitored data to be processed included in the data classification set is valid monitored data to be processed based on the data content represented by each monitored data to be processed included in the data classification set.

The embodiment of the invention also provides a data matching system based on the monitoring device relationship, which is applied to a monitoring background server, wherein the monitoring background server is in communication connection with a plurality of monitoring terminal devices, and the data matching system based on the monitoring device relationship comprises:

the device relationship information determining module is configured to determine device relationship information between the plurality of monitoring terminal devices based on first device feature information and second device feature information of each monitoring terminal device after determining that a device relationship between the plurality of monitoring terminal devices needs to be determined, where the first device feature information is used to represent static feature information of the corresponding monitoring terminal device, and the second device feature information is used to represent dynamic feature information of the corresponding monitoring terminal device;

the monitoring data classification processing module is used for acquiring to-be-processed monitoring data acquired by the monitoring terminal devices to obtain a plurality of pieces of to-be-processed monitoring data, and classifying the plurality of pieces of to-be-processed monitoring data based on device relation information among the monitoring terminal devices to obtain at least one corresponding data classification set, wherein each data classification set comprises at least one piece of to-be-processed monitoring data;

and the data matching confirmation processing module is used for carrying out data matching confirmation processing on each piece of monitoring data to be processed included in the data classification set aiming at each data classification set in the at least one data classification set.

In some preferred embodiments, in the data matching system based on monitoring device relationship, the monitoring data classification processing module is specifically configured to:

In some preferred embodiments, in the data matching system based on the monitoring device relationship, the data matching confirmation processing module is specifically configured to:

In the data matching method and system based on the monitoring device relationship provided by the embodiment of the invention, after the device relationship information among a plurality of monitoring terminal devices is determined based on the first device characteristic information and the second device characteristic information of each monitoring terminal device, the obtained multiple pieces of monitoring data to be processed can be classified based on the device relation information among multiple pieces of monitoring terminal devices to obtain at least one corresponding data classification set, so that the data matching confirmation process can be performed according to different data classification sets, and thus, since the device relationship information between the monitoring terminal devices on which the data classification is performed has high reliability, the reliability of the data matching confirmation processing based on the data classification is better, and the problem of poor reliability of the data matching confirmation in the prior art is solved.

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

Fig. 1 is a schematic diagram of a monitoring backend server according to an embodiment of the present invention.

Fig. 2 is a schematic diagram of a data matching method based on a monitoring device relationship according to an embodiment of the present invention.

Fig. 3 is a schematic diagram of a data matching system based on monitoring device relationships according to an embodiment of the present invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.

Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the 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.

As shown in fig. 1, an embodiment of the present invention provides a monitoring backend server. Wherein the monitoring backend server may include a memory and a processor.

In detail, the memory and the processor are electrically connected directly or indirectly to realize data transmission or interaction. For example, they may be electrically connected to each other via one or more communication buses or signal lines. The memory can have stored therein at least one software function (computer program) which can be present in the form of software or firmware. The processor may be configured to execute the executable computer program stored in the memory, so as to implement the monitoring device relationship-based data matching method provided by the embodiment of the present invention (described later).

Alternatively, in some preferred embodiments, the Memory may be, but is not limited to, Random Access Memory (RAM), Read Only Memory (ROM), Programmable Read-Only Memory (PROM), Erasable Read-Only Memory (EPROM), electrically Erasable Read-Only Memory (EEPROM), and the like.

Alternatively, in some preferred embodiments, the Processor may be a general-purpose Processor including a Central Processing Unit (CPU), a Network Processor (NP), a System on Chip (SoC), and the like; but may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components.

Optionally, in some preferred embodiments, the structure shown in fig. 1 is only an illustration, and the monitoring backend server may further include more or fewer components than those shown in fig. 1, or have a different configuration from that shown in fig. 1, for example, may include a communication unit for information interaction with other devices (such as a monitoring terminal device, etc.).

With reference to fig. 2, an embodiment of the present invention further provides a data matching method based on a monitoring device relationship, which is applicable to the monitoring background server. The method steps defined by the related flow of the data matching method based on the monitoring device relationship can be realized by the monitoring background server, and the monitoring background server is in communication connection with a plurality of monitoring terminal devices.

The specific process shown in FIG. 2 will be described in detail below.

Step 100, determining device relation information among a plurality of monitoring terminal devices based on the first device characteristic information and the second device characteristic information of each monitoring terminal device.

In this embodiment of the present invention, after determining that the device relationship between the multiple monitoring terminal devices needs to be determined, the monitoring backend server may determine device relationship information between the multiple monitoring terminal devices based on first device characteristic information and second device characteristic information of each monitoring terminal device, where the first device characteristic information is used to represent static characteristic information of the corresponding monitoring terminal device, and the second device characteristic information is used to represent dynamic characteristic information of the corresponding monitoring terminal device.

Step 200, acquiring a plurality of pieces of to-be-processed monitoring data acquired by the plurality of monitoring terminal devices, and classifying the plurality of pieces of to-be-processed monitoring data based on the device relationship information among the plurality of monitoring terminal devices to obtain at least one corresponding data classification set.

In the embodiment of the present invention, the monitoring background server may obtain to-be-processed monitoring data acquired by the plurality of monitoring terminal devices after determining the device relationship information among the plurality of monitoring terminal devices, to obtain a plurality of pieces of to-be-processed monitoring data, and perform classification processing on the plurality of pieces of to-be-processed monitoring data based on the device relationship information among the plurality of monitoring terminal devices, to obtain the corresponding at least one data classification set. Wherein each data classification set comprises at least one piece of monitoring data to be processed.

Step 300, for each data classification set in the at least one data classification set, performing data matching confirmation processing on each monitored data to be processed included in the data classification set.

In this embodiment of the present invention, after obtaining the at least one data classification set, the monitoring background server may perform data matching confirmation processing on each piece of monitoring data to be processed included in the data classification set, for each data classification set in the at least one data classification set.

Based on the steps included in the method, after determining the device relationship information between the plurality of monitoring terminal devices based on the first device feature information and the second device feature information of each monitoring terminal device, the obtained plurality of pieces of monitoring data to be processed can be classified based on the device relationship information between the plurality of monitoring terminal devices to obtain at least one corresponding data classification set, so that the data matching confirmation processing can be performed according to different data classification sets.

Optionally, in some preferred embodiments, step 100 in the above embodiments may include the following steps 110, 120 and 130 to determine the device relationship information between the plurality of monitoring terminal devices.

Step 110, determining whether to determine the device relationship among the plurality of monitoring terminal devices.

In the embodiment of the present invention, the monitoring background server may first determine whether the device relationship among the plurality of monitoring terminal devices needs to be determined.

Step 120, obtaining first device characteristic information and second device characteristic information of each of the plurality of monitoring terminal devices.

In this embodiment of the present invention, the monitoring background server may obtain the first device characteristic information and the second device characteristic information of each of the plurality of monitoring terminal devices after determining that the device relationship between the plurality of monitoring terminal devices needs to be determined. The first device characteristic information may be used to represent static characteristic information of the corresponding monitoring terminal device, and the second device characteristic information may be used to represent dynamic characteristic information of the corresponding monitoring terminal device.

Step 130, determining device relationship information between the plurality of monitoring terminal devices based on the first device characteristic information and the second device characteristic information of each monitoring terminal device.

In this embodiment of the present invention, after acquiring the first device characteristic information and the second device characteristic information of each monitoring terminal device, the monitoring background server may determine device relationship information between the plurality of monitoring terminal devices based on the first device characteristic information and the second device characteristic information of each monitoring terminal device.

Based on the steps included in the method, when it is determined that the device relationship between the plurality of monitoring terminal devices needs to be determined, the first device characteristic information and the second device characteristic information of each monitoring terminal device may be obtained first, so that the device relationship information between the plurality of monitoring terminal devices may be determined based on the first device characteristic information and the second device characteristic information of each monitoring terminal device. In this way, because the basis for determining the device relationship information between the monitoring terminal devices is not the experience of the administrator in the prior art, but the first device characteristic information and the second device characteristic information of each monitoring terminal device, the reliability of the basis is ensured, thereby ensuring the reliability of the determined device relationship information, and further improving the problem in the prior art that the reliability of the determined device relationship information between the monitoring terminal devices is poor.

Optionally, in some preferred embodiments, step 110 in the foregoing embodiments may include the following steps to determine whether to determine the device relationship between multiple monitoring terminal devices:

firstly, determining whether a relation determination notification instruction for indicating that the device relation among the plurality of monitoring terminal devices needs to be determined is received;

secondly, if a relation determination notification instruction for indicating that the device relation among the plurality of monitoring terminal devices needs to be determined is determined to be received, counting the number of the plurality of monitoring terminal devices to obtain the corresponding device counting number, and determining the size relation between the device counting number and a preset device counting number threshold;

then, if the device count number is greater than or equal to the device count number threshold, it is determined that the device relationship between the plurality of monitoring terminal devices needs to be determined.

Optionally, in some preferred embodiments, step 110 in the foregoing embodiments may further include the following step to determine whether to determine the device relationship between the multiple monitoring terminal devices:

first, if it is determined that a relationship determination notification instruction indicating that determination of the device relationship between the plurality of monitoring terminal devices is required is not received, it is determined that determination of the device relationship between the plurality of monitoring terminal devices is not required.

firstly, if the device statistics number is smaller than the device statistics number threshold, generating corresponding relationship determination confirmation request information, and sending the relationship determination confirmation request information to a target management terminal device, wherein the relationship determination notification instruction is generated and sent based on the target management terminal device, and the target management terminal device is configured to, after receiving the relationship determination confirmation request information, respond to a selection operation performed by a corresponding management user based on a requirement whether the determination of the device relationship among the plurality of monitoring terminal devices is required, generate corresponding first confirmation feedback information or generate corresponding second confirmation feedback information, and send the first confirmation feedback information or the second confirmation feedback information to the monitoring background server;

secondly, if the first acknowledgement feedback information is received, it is determined that the device relationship among the plurality of monitoring terminal devices does not need to be determined, and if the second acknowledgement feedback information is received, it is determined that the device relationship among the plurality of monitoring terminal devices needs to be determined.

Optionally, in some preferred embodiments, the step 120 in the foregoing embodiments may include the following steps to obtain the first device characteristic information and the second device characteristic information of each of the plurality of monitoring terminal devices:

firstly, if it is determined that the device relationship among the plurality of monitoring terminal devices needs to be determined, generating first acquisition notification information and second acquisition notification information, and sending the first acquisition notification information and the second acquisition notification information to each of the plurality of monitoring terminal devices, wherein each monitoring terminal device is configured to, after receiving the first acquisition notification information and the second acquisition notification information, perform a first information acquisition operation based on the first acquisition notification information to obtain corresponding first device characteristic information, and perform a second information acquisition operation based on the second acquisition notification information to obtain corresponding second device characteristic information;

and secondly, acquiring first device characteristic information and second device characteristic information (namely the first device characteristic information and the second device characteristic information of each monitoring terminal device) acquired and sent by each monitoring terminal device based on the first acquisition notification information and the second acquisition notification information.

Optionally, in some preferred embodiments, if it is determined that the device relationship between the plurality of monitoring terminal devices needs to be determined, the step of generating first acquisition notification information and second acquisition notification information, and sending the first acquisition notification information and the second acquisition notification information to each of the plurality of monitoring terminal devices may include the following steps:

firstly, if the equipment relationship among the plurality of monitoring terminal equipment needs to be determined, generating first acquisition notification information for instructing the monitoring terminal equipment to acquire and send the position information of the monitoring terminal equipment, and generating second acquisition notification information for instructing the monitoring terminal equipment to acquire and send the environment information of the monitoring terminal equipment, wherein the acquired position information is used as the first equipment characteristic information, and the acquired environment information is used as the second equipment characteristic information;

secondly, the first acquisition notification information and the second acquisition notification information are sent to each monitoring terminal device in the plurality of monitoring terminal devices.

Optionally, in some preferred embodiments, the step 130 in the foregoing embodiments may include the following steps to determine whether to determine the device relationship between the multiple monitoring terminal devices:

firstly, calculating the similarity between the first device characteristic information of the monitoring terminal device and the first device characteristic information of each other monitoring terminal device aiming at each monitoring terminal device in the plurality of monitoring terminal devices to obtain corresponding first characteristic similarity information;

secondly, calculating the similarity between the second device characteristic information of the monitoring terminal device and the second device characteristic information of each other monitoring terminal device aiming at each monitoring terminal device in the plurality of monitoring terminal devices to obtain corresponding second characteristic similarity information;

then, the first feature similarity information and the second feature similarity information corresponding to each monitoring terminal device are subjected to fusion processing, and device relationship information among the plurality of monitoring terminal devices is determined based on the obtained feature similarity fusion information.

Optionally, in some preferred embodiments, the step of calculating, for each of the multiple monitoring terminal devices, a similarity between the first device characteristic information of the monitoring terminal device and the first device characteristic information of each of the other monitoring terminal devices to obtain corresponding first characteristic similarity information may include the following steps:

firstly, for each monitoring terminal device in the plurality of monitoring terminal devices, calculating to obtain position distance information between the monitoring terminal device and each other monitoring terminal device based on position information corresponding to first device characteristic information of the monitoring terminal device and position information corresponding to first device characteristic information of each other monitoring terminal device;

secondly, determining position distance information with the maximum value in the position distance information between all two monitoring terminal devices as target position distance information;

then, for each monitoring terminal device in the plurality of monitoring terminal devices, based on the target position distance information and the position distance information between the monitoring terminal device and each other monitoring terminal device, a corresponding distance ratio calculation (the former is divided by the latter, and then, a value that can be normalized is taken as the first feature similarity information) is performed to obtain first feature similarity information between the monitoring terminal device and each other monitoring terminal device.

Optionally, in some preferred embodiments, the step of calculating, for each of the multiple monitoring terminal devices, a similarity between the second device characteristic information of the monitoring terminal device and the second device characteristic information of each of the other monitoring terminal devices to obtain corresponding second characteristic similarity information may include the following steps:

firstly, for each monitoring terminal device in the plurality of monitoring terminal devices, performing segmentation processing on a multi-frame environment monitoring image included in second device characteristic information of the monitoring terminal device to obtain a plurality of monitoring video segments corresponding to the monitoring terminal device, wherein each monitoring video segment includes a plurality of temporally continuous multi-frame environment monitoring images;

secondly, for each monitoring terminal device in the plurality of monitoring terminal devices, sequentially performing target image duplicate removal processing on each monitoring video segment corresponding to the monitoring terminal device, including the environment monitoring image, to obtain each monitoring video duplicate removal segment corresponding to the monitoring terminal device;

then, for each monitoring terminal device in the multiple monitoring terminal devices, sequentially performing deduplication processing on two adjacent surveillance video deduplication segments corresponding to the monitoring terminal device (for example, if the two surveillance video deduplication segments are completely the same or the similarity is higher than a threshold, one of the two surveillance video deduplication segments may be discarded, and if the two surveillance video deduplication segments are completely different or the similarity is not higher than a threshold, the two surveillance video deduplication segments may be retained), obtaining at least one surveillance video target segment corresponding to the monitoring terminal device, and taking each frame of environment monitoring image included in each surveillance video target segment as a target environment monitoring image;

then, for each two monitoring terminal devices in the plurality of monitoring terminal devices, a target image similarity calculation operation is performed on the multi-frame target environment monitoring images corresponding to the two monitoring terminal devices (for example, for each frame of target environment monitoring image corresponding to a first monitoring terminal device in the two monitoring terminal devices, a multi-frame target environment monitoring image with a collection time within a range is determined in the multi-frame target environment monitoring image corresponding to a second monitoring terminal device based on the collection time of the target environment monitoring image, and is used as a comparison target environment monitoring image, then, an image similarity between the target environment monitoring image and each comparison target environment monitoring image is calculated, and the image similarity with the maximum value is used as the image similarity corresponding to the target environment monitoring image, and thus, the average value of the image similarity corresponding to each frame of target environment monitoring image corresponding to the first monitoring terminal device may be calculated and used as the second feature similarity information between the two corresponding monitoring terminal devices), so as to obtain the second feature similarity information between the two monitoring terminal devices.

Optionally, in some preferred embodiments, the performing, for each of the plurality of monitoring terminal devices, target image deduplication processing in the step of sequentially performing, on each of the monitoring video segments corresponding to the monitoring terminal device and including the environment monitoring image, to obtain each of the monitoring video deduplication segments corresponding to the monitoring terminal device may include:

firstly, for each frame of the environment monitoring image in the monitoring video segment, segmenting a plurality of corresponding frames of environment monitoring sub-images (for example, 4 frames of environment monitoring sub-images corresponding to an upper left position, an upper right position, a lower left position and a lower right position, the number of frames of the environment monitoring sub-images can be more, for example, hundreds of frames and the like, based on the precision requirement) from the environment monitoring image to obtain a monitoring sub-image set corresponding to the environment monitoring image, wherein the monitoring sub-image set comprises the plurality of corresponding environment monitoring sub-images, and the plurality of environment monitoring sub-images form the corresponding environment monitoring image according to the corresponding segmented position relationship;

secondly, aiming at each frame of the environment monitoring image in the monitoring video clip, taking the environment monitoring subimage in the monitoring subimage set corresponding to the environment monitoring image as an index key word, taking the environment monitoring image as an index relation object corresponding to the index key word, and forming a corresponding index relation pair by the index key word and the corresponding index relation object to obtain a target index corresponding relation between the environment monitoring image and the environment monitoring subimage in the corresponding monitoring subimage set;

then, aiming at each kind of environment monitoring sub-image (multiple frames of Hanzi rape monitoring sub-images which are completely the same can be used as the same environment monitoring sub-image), determining each frame of environment monitoring image corresponding to the environment monitoring sub-image based on the target index corresponding relation, and obtaining an environment monitoring image set corresponding to the environment monitoring sub-image;

then, aiming at each environment monitoring sub-image, selecting one frame of environment monitoring image from the environment monitoring image set corresponding to the environment monitoring sub-image as an environment monitoring image to be processed, and adding the environment monitoring image to be processed into a pre-constructed image initial set, wherein the image initial set is a null set during construction;

further, traversing each frame of the environment monitoring image in the environment monitoring image set, and determining whether the currently traversed environment monitoring image and the environment monitoring image in the image initial set belong to similar environment monitoring images;

further, if the currently traversed environment monitoring image and the environment monitoring image in the image initial set do not belong to a similar environment monitoring image, adding the currently traversed environment monitoring image to the image initial set, traversing a next frame of the environment monitoring image in the environment monitoring image set, and if the currently traversed environment monitoring image and the environment monitoring image in the image initial set belong to a similar environment monitoring image, traversing a next frame of the environment monitoring image in the environment monitoring image set;

and finally, when all the environment monitoring images in the environment monitoring image set are traversed, taking the image initial set as a monitoring image deduplication set of the corresponding environment monitoring sub-images, and taking a union set of the surveillance image deduplication sets of each environment monitoring sub-image as a surveillance video deduplication segment corresponding to the surveillance video segment.

Optionally, in some preferred embodiments, the step of traversing each frame of the environment monitoring image in the environment monitoring image set and determining whether the currently traversed environment monitoring image and the environment monitoring image in the initial image set belong to similar environment monitoring images may include the following steps:

firstly, traversing each frame of the environment monitoring image in the environment monitoring image set;

secondly, acquiring image similarity information between the currently traversed environment monitoring image and the environment monitoring images in the image initial set;

and then, determining whether the currently traversed environment monitoring image and the environment monitoring image in the initial image set are similar environment monitoring images according to the image similarity information.

Optionally, in some preferred embodiments, the step of obtaining image similarity information between the currently traversed environment monitoring image and the environment monitoring images in the initial set of images may include the following steps:

firstly, respectively carrying out pixel grouping processing on the currently traversed environment monitoring image and the environment monitoring image in the image initial set (for example, sequencing sequentially from top left to bottom right, and then sequentially segmenting at certain intervals to obtain a corresponding pixel group), so as to obtain a first pixel group set corresponding to the currently traversed environment monitoring image and a second pixel group set corresponding to the environment monitoring image in the image initial set;

then, according to the first pixel grouping set and the second pixel grouping set, a monitoring image similarity between the currently traversed environment monitoring image and the environment monitoring image in the image initial set is calculated (for example, the first pixel grouping set and the second pixel grouping set may be an ordered combination, such as ordered according to the positions of the corresponding pixels in the environment monitoring image, so that whether the pixel groupings at the corresponding positions in the two pixel grouping sets are the same or not may be determined, and then, the same number ratio of the pixel groupings at the corresponding positions is calculated as the monitoring image similarity).

Optionally, in some preferred embodiments, the step of performing fusion processing on the first feature similarity information and the second feature similarity information corresponding to each monitoring terminal device, and determining device relationship information between the multiple monitoring terminal devices based on the obtained feature similarity fusion information may include the following steps:

firstly, for each two monitoring terminal devices in the plurality of monitoring terminal devices, performing product processing on the first feature similarity information and the second feature similarity information between the two monitoring terminal devices to obtain feature similarity fusion information between the two monitoring terminal devices;

secondly, for each two monitoring terminal devices of the multiple monitoring terminal devices, determining device relationship information between the two monitoring terminal devices based on the feature similarity fusion information between the two monitoring terminal devices to determine the device relationship information between the multiple monitoring terminal devices (for example, the feature similarity fusion information may be directly used as a corresponding device relationship closeness degree, and if the feature similarity is greater, the corresponding device relationship closeness degree is higher).

Optionally, in some preferred embodiments, the step 200 in the above embodiments may include the following steps to obtain at least one data classification set:

firstly, clustering the monitoring terminal devices based on device relationship information among the monitoring terminal devices to obtain at least one device cluster set, wherein each device cluster set comprises at least one monitoring terminal device;

secondly, respectively constructing a corresponding data classification empty set for each equipment cluster set (namely, the equipment cluster sets and the data classification empty sets are in one-to-one correspondence, and each data classification empty set is an empty set);

and then, acquiring to-be-processed monitoring data acquired by the plurality of monitoring terminal devices to obtain a plurality of to-be-processed monitoring data, attributing the to-be-processed monitoring data to the data classification empty set corresponding to the device cluster set of the monitoring terminal device corresponding to the to-be-processed monitoring data aiming at each piece of the to-be-processed monitoring data, and forming a corresponding data classification set.

Optionally, in some preferred embodiments, the step of clustering the multiple monitoring terminal devices based on the device relationship information between the multiple monitoring terminal devices to obtain at least one device cluster set may include the following steps:

firstly, counting the number of the plurality of pieces of monitoring data to be processed to obtain a corresponding first data number, and determining the size relationship between the first data number and a preset first data number threshold;

secondly, if the first data quantity is smaller than the first data quantity threshold value, acquiring a preset first cluster quantity, and determining the first cluster quantity monitoring terminal equipment as first monitoring terminal equipment from the plurality of monitoring terminal equipment, wherein the first cluster quantity is used for representing the quantity of an equipment cluster set to be clustered;

then, for each monitoring terminal device other than the first monitoring terminal device in the plurality of monitoring terminal devices, determining a first monitoring terminal device corresponding to the monitoring terminal device (if the device relationship between the first monitoring terminal device and the first monitoring terminal device is the most tight) based on the device relationship information between the monitoring terminal device and each first monitoring terminal device;

and finally, aiming at each first monitoring terminal device, constructing the first monitoring terminal device and each monitoring terminal device corresponding to the first monitoring terminal device to obtain a corresponding device cluster set so as to obtain the device cluster sets with the first cluster quantity.

Optionally, in some preferred embodiments, the step of clustering the multiple monitoring terminal devices based on the device relationship information between the multiple monitoring terminal devices to obtain at least one device cluster set may further include the following steps:

firstly, if the first data quantity is greater than or equal to the first data quantity threshold value, calculating an average value of the device relationship compactness degree values corresponding to the device relationship information between the monitoring terminal device and each other monitoring terminal device aiming at each monitoring terminal device in the plurality of monitoring terminal devices, and obtaining a device relationship compactness degree average value corresponding to the monitoring terminal device;

secondly, for each monitoring terminal device in the plurality of monitoring terminal devices, performing dispersion calculation processing (referring to a data dispersion calculation mode in the prior art) based on a device relationship compactness degree value corresponding to the device relationship information between the monitoring terminal device and each other monitoring terminal device and the device relationship compactness mean value corresponding to the monitoring terminal device to obtain a device relationship compactness dispersion value corresponding to the monitoring terminal device;

then, calculating an average value corresponding to the device relationship compactness discrete value corresponding to each monitoring terminal device to obtain a corresponding target average value, and determining a second cluster number having a positive correlation with the target average value based on the target average value (that is, the larger the target average value is, the larger the second cluster number is);

then, determining a second clustering number of monitoring terminal devices as second monitoring terminal devices in the plurality of monitoring terminal devices, wherein the second clustering number is used for representing the number of device clustering sets to be clustered;

further, for each monitoring terminal device other than the second monitoring terminal device in the plurality of monitoring terminal devices, determining a second monitoring terminal device corresponding to the monitoring terminal device (e.g., the device relationship between the second monitoring terminal device and the second monitoring terminal device is the most compact) based on the device relationship information between the monitoring terminal device and each second monitoring terminal device;

and finally, aiming at each second monitoring terminal device, constructing the second monitoring terminal device and each monitoring terminal device corresponding to the second monitoring terminal device to obtain a corresponding device cluster set so as to obtain a second cluster number of device cluster sets.

Optionally, in some preferred embodiments, the step of determining, as the second monitoring terminal device, the second aggregation number of monitoring terminal devices from the plurality of monitoring terminal devices may include the following steps:

first, for each piece of to-be-processed monitoring data in the plurality of pieces of to-be-processed monitoring data, calculating data similarity between the to-be-processed monitoring data and each piece of other to-be-processed monitoring data (for example, calculating image similarity between corresponding monitoring images);

secondly, calculating an average value of data similarity between the monitoring data to be processed and each other monitoring data to be processed aiming at each monitoring data to be processed in the plurality of monitoring data to be processed to obtain a data similarity average value corresponding to the monitoring data to be processed;

and finally, determining the second cluster quantity of the to-be-processed monitoring data with the maximum corresponding data similarity mean value from the plurality of to-be-processed monitoring data, and taking the monitoring terminal equipment corresponding to the second cluster quantity of the to-be-processed monitoring data as second monitoring terminal equipment.

Optionally, in some preferred embodiments, the step 300 in the foregoing embodiments may include the following steps to obtain a data matching confirmation process for each piece of monitoring data to be processed:

firstly, counting the number of the monitoring data to be processed included in the data classification set aiming at each data classification set in at least one data classification set to obtain a first data statistical number corresponding to the data classification set, and determining the relative size relation between the first data statistical number and a predetermined first data statistical number threshold;

secondly, for each data classification set in the at least one data classification set, if the first data statistical quantity corresponding to the data classification set is smaller than the first data statistical quantity threshold (for example, 1), determining each piece of to-be-processed monitoring data included in the data classification set as valid to-be-processed monitoring data respectively.

Optionally, in some preferred embodiments, the step 300 in the foregoing embodiments may further include the following step to obtain data matching confirmation processing for each piece of monitoring data to be processed:

first, for each data classification set in the at least one data classification set, if the first statistical number of data corresponding to the data classification set is greater than or equal to the first statistical number threshold, determining whether each monitored data to be processed included in the data classification set is valid monitored data to be processed based on the data content represented by each monitored data to be processed included in the data classification set (for example, determining whether the data contents represented by two monitored data to be processed are in conflict, if there is a same person or object in the images of two positions acquired at the same time, it is indicated that there is a possibility of an error in at least one of the images, and thus, the monitored data to be processed may be invalid).

With reference to fig. 3, an embodiment of the present invention further provides a data matching system based on a relationship between monitoring devices, which is applicable to the monitoring backend server. The data matching system based on the monitoring equipment relationship can comprise the following modules:

Optionally, in some preferred embodiments, the monitoring data classification processing module is specifically configured to: clustering the monitoring terminal devices based on the device relationship information among the monitoring terminal devices to obtain at least one device cluster set, wherein each device cluster set comprises at least one monitoring terminal device; respectively constructing a corresponding data classification empty set aiming at each equipment cluster set; and acquiring to-be-processed monitoring data acquired by the monitoring terminal devices to obtain a plurality of pieces of to-be-processed monitoring data, attributing the to-be-processed monitoring data to the data classification empty set corresponding to the device cluster set of the monitoring terminal device corresponding to the to-be-processed monitoring data aiming at each piece of to-be-processed monitoring data, and forming a corresponding data classification set.

Optionally, in some preferred embodiments, the data matching confirmation processing module is specifically configured to: counting the number of the monitoring data to be processed included in the data classification set aiming at each data classification set in the at least one data classification set to obtain a first data statistical number corresponding to the data classification set, and determining a relative size relation between the first data statistical number and a predetermined first data statistical number threshold; and for each data classification set in the at least one data classification set, if the first data statistical quantity corresponding to the data classification set is smaller than the first data statistical quantity threshold, determining each piece of to-be-processed monitoring data included in the data classification set as valid to-be-processed monitoring data respectively.

In summary, the present invention provides a data matching method and system based on monitoring device relationship, after determining the device relationship information between the plurality of monitoring terminal devices based on the first device characteristic information and the second device characteristic information of each monitoring terminal device, the obtained multiple pieces of monitoring data to be processed can be classified based on the device relation information among multiple pieces of monitoring terminal devices to obtain at least one corresponding data classification set, so that the data matching confirmation process can be performed according to different data classification sets, and thus, since the device relationship information between the monitoring terminal devices on which the data classification is performed has high reliability, the reliability of the data matching confirmation processing based on the data classification is better, and the problem of poor reliability of the data matching confirmation in the prior art is solved.

The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A data matching method based on monitoring equipment relationship is characterized in that the data matching method is applied to a monitoring background server, the monitoring background server is in communication connection with a plurality of monitoring terminal equipment, and the data matching method based on the monitoring equipment relationship comprises the following steps:

2. The monitoring device relationship-based data matching method according to claim 1, wherein the step of obtaining the to-be-processed monitoring data acquired by the plurality of monitoring terminal devices to obtain a plurality of pieces of to-be-processed monitoring data, and classifying the plurality of pieces of to-be-processed monitoring data based on the device relationship information among the plurality of monitoring terminal devices to obtain the corresponding at least one data classification set comprises:

3. The monitoring device relationship-based data matching method according to claim 2, wherein the step of clustering the plurality of monitoring terminal devices based on the device relationship information between the plurality of monitoring terminal devices to obtain at least one device cluster set comprises:

4. The monitoring device relationship-based data matching method according to claim 3, wherein the step of clustering the plurality of monitoring terminal devices based on the device relationship information among the plurality of monitoring terminal devices to obtain at least one device cluster set further comprises:

5. The monitoring device relationship-based data matching method according to claim 4, wherein the step of determining the second cluster number of monitoring terminal devices as second monitoring terminal devices in the plurality of monitoring terminal devices comprises:

6. The monitoring device relationship-based data matching method according to any one of claims 1 to 5, wherein the step of performing data matching confirmation processing on each piece of monitoring data to be processed included in each data classification set of the at least one data classification set includes:

7. The monitoring device relationship-based data matching method according to claim 6, wherein the step of performing data matching confirmation processing on each piece of monitoring data to be processed included in each data classification set of the at least one data classification set further includes:

8. The utility model provides a data matching system based on supervisory equipment relation which characterized in that is applied to control backend server, control backend server communication connection has a plurality of monitor terminal equipment, data matching system based on supervisory equipment relation includes:

9. The monitoring-device-relationship-based data matching system of claim 8, wherein the monitoring data classification processing module is specifically configured to:

10. The monitoring-device-relationship-based data matching system of claim 8, wherein the data matching validation processing module is specifically configured to: