CN116049292B - Environment sensing method, system, device and medium based on conversion linkage - Google Patents
Environment sensing method, system, device and medium based on conversion linkage Download PDFInfo
- Publication number
- CN116049292B CN116049292B CN202310207476.1A CN202310207476A CN116049292B CN 116049292 B CN116049292 B CN 116049292B CN 202310207476 A CN202310207476 A CN 202310207476A CN 116049292 B CN116049292 B CN 116049292B
- Authority
- CN
- China
- Prior art keywords
- data
- sensing
- linkage
- conversion
- unit
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/25—Integrating or interfacing systems involving database management systems
- G06F16/258—Data format conversion from or to a database
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Abstract
The invention provides a conversion linkage-based environment sensing method, a conversion linkage-based environment sensing system, a conversion linkage-based environment sensing device and a conversion linkage-based medium, wherein the method comprises the following steps: s1, setting sampling frequency, and synchronously effecting all perception sources; s2, setting a sensing link and adding a sensing node; s3, selecting conversion linkage of a sensing link, and processing data output by the sensing link; the sensing nodes are configured as follows: s21, selecting a perception source; s22, selecting an algorithm, and analyzing and identifying data of the sensing node; s23, converting linkage of a selection algorithm, and processing analysis and identification results; the conversion linkage configuration is as follows: s31, setting an event strategy, and carrying out first filtering on input data; s32, selecting a data processing plug-in, and converting the data after the first filtering; s33, setting data filtering, and performing secondary filtering on the converted data; and S34, setting a linkage rule, and triggering and executing corresponding tasks according to the judging result, so that environment perception is realized accurately and efficiently through conversion linkage.
Description
Technical Field
The invention relates to an environment sensing method, system, device and medium based on conversion linkage, and belongs to the technical field of environment sensing.
Background
The environment sensing refers to a precise artificial intelligence technology, and can simulate the behavior and space movement of objects in natural environment, so that the actual formulated tasks can be effectively understood and solved. Its underlying principles involve various sensing, machine vision algorithms that process data collected from the sensors, and decision making in complex intelligent environments. In many actual scenes at present, environment sensing has become an application foundation in the fields of intelligent home, industrial management, intelligent cities, automatic driving and the like, and can improve the capabilities of robots, mechanical systems and intelligent systems in the actual scene application, extract useful information from complex and chaotic environments and meet different user demands, so that more convenient experience is brought to daily life of people.
However, the conventional method for realizing environment sensing is to perform analysis processing based on a single data source binding fixed algorithm, and has the following technical defects that the effect of extracting useful information from the environment is poor:
1. the types of data sources typically support only video, and do not support usage scenarios for multiple data sources.
2. The algorithm is relatively single in use, auxiliary analysis is not supported by accessories, and after the algorithm finishes data analysis, a result is usually directly output, and data conversion and filtering are lacked, so that the use is not flexible enough.
3. In general, simple linkage is not provided or only supported, only one execution instruction can be transmitted, and the internal parameters of linked tasks cannot be modified.
4. Slightly complex environment sensing is basically realized by adopting a single development mode, has no reusability and expansibility, and lacks a flexible configuration mode to realize the environment sensing of complex use scenes.
Therefore, the invention needs to propose an environment perception implementation method based on conversion linkage to solve the technical bottleneck encountered at present.
Disclosure of Invention
In order to solve the existing technical problems, the invention aims to realize environment sensing through conversion linkage, and provides an environment sensing method, system, device and medium based on conversion linkage, so as to achieve the technical purposes of identifying a sensing object accurately with low cost and high efficiency, collecting more reliable sensing data and further ensuring the reliability of formed services.
In order to achieve the above purpose, the present invention provides an environment sensing method based on conversion linkage, comprising the following steps:
s1, setting sampling frequency according to comprehensive evaluation results of a use scene and the performance of a host, and synchronously effecting all perception sources;
s2, setting a sensing link, adding sensing nodes, and transmitting and outputting data of all the sensing nodes according to the sensing link;
s3, switching linkage of the sensing link is selected, and data output by the sensing link is processed.
The sensing node in the step S2 adopts the following configuration steps:
s21, selecting a sensing source, and extracting data of a sensing node from the sensing source according to the sampling frequency;
s22, selecting an algorithm, uploading accessories for auxiliary analysis according to the need, and analyzing and identifying the data of the sensing nodes based on the algorithm and the accessories;
s23, converting linkage of a selection algorithm, and processing an analysis and identification result.
The switching linkage in the steps S3 and S23 adopts the following configuration steps:
s31, setting an event strategy, and filtering input data for the first time according to the type of the event strategy;
s32, selecting a data processing plug-in, and converting the data after the first filtering according to the conversion rule of the processing plug-in;
s33, setting data filtering, and performing secondary filtering on the converted data based on AND logic judgment;
s34, setting a linkage rule, judging the data after the second filtering, triggering and executing corresponding tasks according to the judging result, and supporting to transfer parameters to the corresponding tasks.
In the method of the present invention, when there is a parallel and serial relationship among the plurality of sensing nodes in the sensing link in the step S2, the data of the upper sensing node is packed and combined and then transferred to the lower sensing node, and the final data output is completed through the end sensing node.
In the method of the present invention, the type of the sensing source in the step S21 is video, audio, text or radar, and different sensing source types correspond to different algorithm types.
In the method of the present invention, in the step S21, when the sampling frequency is lower than or equal to 1 frame/second, the frame is directly extracted through the interface of the sensing node;
when the sampling frequency is higher than 1 frame/second, hard or soft decoding frame extraction is adopted, and GPU or CPU is adopted to improve frame extraction efficiency;
when the same sensing source exists in the plurality of sensing nodes, only one path of frame extraction is performed;
when multiple environmental awareness configurations are different in sampling frequency, frames are extracted at the highest sampling frequency, and redundant frames are discarded when data is returned to the environmental awareness of other sampling frequencies.
The method of the present invention further includes that the type of the event policy in the step S31 is a result change, duration or repetition number;
when the input data is filtered for the first time according to the result change, reporting the data once if the data is different from the data on the current time, otherwise, filtering the data without reporting;
when the input data is filtered for the first time according to the duration, reporting the data once if the data in the set time is the same, otherwise, filtering the data without reporting;
when the input data is filtered for the first time according to the repetition times, reporting the data once if the data in the specified times are the same, otherwise, filtering the data without reporting.
In the method of the present invention, the processing plug-in step S32 adopts python format, fills in the conversion rule based on the fixed template, and converts the data after the first filtering according to the conversion rule.
The method of the present invention further comprises the step of performing an AND or logic determination in the step S33 by using a lambda expression.
In the method of the present invention, the linkage rule in the step S34 adopts a lambda expression, and can trigger to execute a task; each linkage rule can be provided with a parameter transmission rule, and the parameter transmission rule adopts a lambda expression and can transmit parameters to a task which triggers execution.
The invention also provides an environment sensing realization system based on conversion linkage, which comprises an environment sensing module, a sensing node module and a conversion linkage module.
The environment sensing module comprises a sampling frequency setting unit, a sensing link setting unit and a sensing link switching linkage unit; wherein, the liquid crystal display device comprises a liquid crystal display device,
the sampling frequency setting unit is used for setting the sampling frequency according to the comprehensive evaluation result of the use scene and the host performance and synchronously effecting all the perception sources;
the sensing link unit is used for setting a sensing link, adding sensing nodes and outputting the data of all the sensing nodes after being transmitted according to the sensing link;
and the sensing link switching linkage unit is used for selecting switching linkage of the sensing link and processing data output by the sensing link.
The sensing node module is used for sensing the configuration of the sensing node in the link unit and comprises a selection sensing source unit, a selection algorithm unit and a selection algorithm conversion linkage unit; wherein, the liquid crystal display device comprises a liquid crystal display device,
the sensing source unit is used for selecting a sensing source and extracting data of sensing nodes from the sensing source according to the sampling frequency;
the selection algorithm unit is used for selecting an algorithm, uploading accessories for auxiliary analysis according to the need, and analyzing and identifying the data of the sensing node based on the algorithm and the accessories;
and the selection algorithm conversion linkage unit is used for selecting the conversion linkage of the algorithm and processing the analysis and identification result.
The conversion linkage module is used for selecting configuration of conversion linkage in the perception link conversion linkage unit and the selection algorithm conversion linkage unit and comprises an event strategy setting unit, a data processing plug-in unit, a data filtering unit and a linkage rule setting unit; wherein, the liquid crystal display device comprises a liquid crystal display device,
the event policy setting unit is used for setting event policies and filtering input data for the first time according to the types of the event policies;
the data processing plug-in unit is used for selecting a data processing plug-in unit and converting the data after the first filtering according to the conversion rule of the processing plug-in unit;
the setting data filtering unit is used for setting data filtering, and performing secondary filtering on the converted data based on AND logic judgment;
and the linkage rule unit is used for setting a linkage rule, judging the data after the second filtering, triggering and executing a corresponding task according to a judging result, and supporting the transmission of parameters to the corresponding task.
The invention also provides a context awareness realizing device based on conversion linkage, which comprises a memory, a graphic processor, a processor and a computer program stored on the memory and capable of running on the processor;
the graphic processor assists an algorithm in the environment sensing method based on conversion linkage to analyze and identify;
the processor implements the context awareness method based on conversion linkage when executing the computer program.
The invention further provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program for executing the environment sensing method based on conversion linkage.
In summary, compared with the prior art, the invention can accurately identify the perception object with low cost and high efficiency, collect more reliable perception data from complex and chaotic environments, meet different user requirements, ensure the reliability of the formed service, is flexible and convenient, and has the following technical advantages:
1. the perceived sources support video, audio, text, radar, and use scenarios for multiple data sources.
2. Different perception source types correspond to different algorithm types, the algorithm supports uploading accessories for auxiliary analysis, and after the algorithm finishes data analysis, the data are converted and filtered through conversion linkage and then output, so that the method is more flexible to use.
3. The data processing adopts a plug-in, fills in conversion rules based on a fixed template, and converts input data into new data according to the rules.
4. And triggering and executing different tasks according to different data results by the linkage rule, and supporting the transmission of parameters to the corresponding tasks.
5. The environment awareness of the complex use scene is realized in a flexible configuration mode, and the multiplexing performance and the expansibility are realized.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments described in the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of the method of the present invention;
FIG. 2 is a schematic block diagram of the system of the present invention;
fig. 3 is a schematic block diagram of the apparatus of the present invention.
Detailed Description
In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system configurations, techniques, etc. in order to provide a thorough understanding of the embodiments of the present application. It will be apparent, however, to one skilled in the art that the present application may be practiced in other embodiments that depart from these specific details. It will be further understood that the terms "comprises" and/or "comprising," when used in this application, specify the presence of stated features, integers, steps, operations, modules, and/or units, but do not preclude the presence or addition of one or more other features, integers, steps, operations, modules, units, and/or groups thereof. It will also be understood that the term "and/or" as used in this application refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations.
1. The method embodiment of the invention comprises the following steps:
as shown in fig. 1, the invention provides an environment sensing method based on conversion linkage, which comprises the following steps:
s1, setting sampling frequency, namely how many times per second are acquired according to comprehensive evaluation results of the use scene and the host performance. And, after the sampling frequency setting is completed, the sampling frequency setting is synchronously effective for all the perception sources.
S2, setting a sensing link, adding sensing nodes, and transmitting and outputting data of all the sensing nodes according to the sensing link.
The sensing node adopts the following configuration steps:
s21, selecting a sensing source, and extracting data of a sensing node from the sensing source according to the sampling frequency.
In particular, the source is perceived as supporting video, audio, text, or radar. Different perception source types correspond to different algorithm types, and after the perception source is selected, available algorithms are correspondingly changed.
And when the sampling frequency is lower than or equal to 1 frame/second, the frame is directly extracted through the interface of the sensing node. When the sampling frequency is higher than 1 frame/second, hard or soft decoding is adopted to extract frames, and GPU or CPU is adopted to improve the frame extraction efficiency. When the same sensing source exists in the plurality of sensing nodes, only one path of frame extraction is performed. When multiple environmental awareness configurations are different in sampling frequency, frames are extracted at the highest sampling frequency, and redundant frames are discarded when data is returned to the environmental awareness of other sampling frequencies.
When parallel and serial relations exist among a plurality of sensing nodes in the sensing link, data of the upper sensing node are packed and combined and then transferred to the lower sensing node, and final data output is completed through the tail sensing node. If the personnel temperature measurement is performed, the serial link cooperation can be formed by two sensing nodes; the sensing node 1 is responsible for personnel detection, the sensing source is visible light video, and the recognized face area and name are transmitted to the sensing node 2; the sensing node 2 is responsible for infrared temperature measurement, the sensing source is infrared video, the highest temperature in the face area is firstly identified, then the highest temperature is combined with the name, and finally the body temperature of the person is output.
S22, selecting an algorithm, uploading the accessory for auxiliary analysis according to the requirement, and analyzing and identifying the data of the sensing node based on the algorithm and the accessory.
It should be noted that, part of the algorithms also need to additionally upload accessories for auxiliary analysis, such as face recognition algorithms, and can upload different face libraries to realize recognition of different people. And, different perceptual source types correspond to different algorithm types.
S23, selecting conversion linkage of an algorithm, and processing analysis and identification results according to the selected conversion linkage.
The step S23 of switching linkage adopts the following configuration steps:
s31, setting an event strategy, and carrying out first filtering on the analysis and identification result according to the type of the event strategy.
It should be noted that the type of event policy is a result change, duration, or number of repetitions. When the input data is filtered for the first time according to the result change, reporting the data once if the data is different from the data on the current time, otherwise, filtering and not reporting the data. When the input data is filtered for the first time according to the duration, reporting the data once if the data in the set time is the same, otherwise, filtering the data without reporting. When the input data is filtered for the first time according to the repetition times, reporting the data once if the data in the specified times are the same, otherwise, filtering the data without reporting. And based on the event strategy, repeated reporting and false reporting of similar events can be effectively reduced, for example, fire detection can be carried out, and the event strategy repeated for 5 times can be set, so that frequent false reporting caused by false recognition is avoided.
S32, selecting a data processing plug-in, and converting the data after the first filtering according to the conversion rule of the processing plug-in.
In specific implementation, the processing plug-in adopts a python format, fills in conversion rules based on a fixed template, and performs conversion processing on the data after the first filtering according to the conversion rules.
And S33, setting data filtering, and performing secondary filtering on the converted data based on AND logic judgment. In particular, each AND or logical decision uses lambda expression.
S34, setting a linkage rule, judging the data after the second filtering according to the linkage rule, triggering and executing corresponding tasks according to the judging result, triggering and executing different tasks according to different data results, and supporting the transmission of parameters to the corresponding tasks.
In the concrete implementation, each linkage rule adopts a lambda expression and can trigger and execute a task; each linkage rule can be provided with a parameter transmission rule, and the parameter transmission rule adopts a lambda expression and can transmit parameters to a task which triggers execution.
S3, selecting conversion linkage of the sensing link, and processing data output by the sensing link according to the selected conversion linkage.
The configuration step and specific requirements of the switching linkage in the step S3 are the same as those in the steps S31 to S34, except that the processing is performed on the data output by the sensing link, and the specific steps are as follows:
s31, setting an event strategy, wherein the type of the event strategy is result change, duration or repetition number; and according to the type of the event strategy, the data output by the perception link is filtered for the first time. When the input data is filtered for the first time according to the result change, reporting the data once if the data is different from the data on the current time, otherwise, filtering and not reporting the data. When the input data is filtered for the first time according to the duration, reporting the data once if the data in the set time is the same, otherwise, filtering the data without reporting. When the input data is filtered for the first time according to the repetition times, reporting the data once if the data in the specified times are the same, otherwise, filtering the data without reporting.
s32, selecting a data processing plug-in, wherein the processing plug-in adopts a python format, and filling in a conversion rule based on a fixed template; and converting the data after the first filtering according to the conversion rule of the processing plug-in.
And s33, setting data filtering, and performing second filtering on the converted data based on AND or logic judgment, wherein each AND or logic judgment adopts a lambda expression. For example: and filtering the data with the temperature between 60 and 100 when the lambda x is x 0, the temperature is more than or equal to 60 and the lambda x is x 0, the temperature is less than or equal to 100.
S34, setting linkage rules, wherein each linkage rule adopts a lambda expression and can trigger and execute a task; each linkage rule can set a parameter transmission rule, the parameter transmission rule adopts lambda expression, and parameters can be transmitted to the task triggered to be executed, so that data after the second filtering is judged, the corresponding task is triggered to be executed according to a judging result, and the parameters are supported to be transmitted to the corresponding task. For example: after identifying the personnel, playing welcome language containing the name of the opposite party; linkage rules may be configured as lambda x 0 ("name" ] is not None, indicating that a person has been identified and a name obtained; the parameter transmission rule can be configured as lambda x 0 and name, which represents the parameter of name transmitted to the task; finally triggering and executing the task of broadcasting welcome language, wherein one 'name' placeholder is arranged in the welcome language, and the placeholder can be replaced by a transmitted parameter, so that the welcome language broadcasting with the name is finally realized.
2. The embodiment of the system comprises:
as shown in fig. 2, based on the same concept as the embodiment of the method, the embodiment of the application also provides an environment sensing implementation system based on conversion linkage, which comprises an environment sensing module, a sensing node module and a conversion linkage module.
The environment sensing module comprises a sampling frequency setting unit, a sensing link setting unit and a sensing link switching linkage selecting unit. Wherein: the sampling frequency setting unit is used for setting the sampling frequency according to the comprehensive evaluation result of the use scene and the host performance and synchronously effecting all the perception sources; the sensing link unit is used for setting a sensing link, adding sensing nodes and outputting the data of all the sensing nodes after being transmitted according to the sensing link; and the sensing link switching linkage unit is used for selecting switching linkage of the sensing link and processing data output by the sensing link.
The sensing node module is used for sensing the configuration of the sensing node in the link unit and comprises a selection sensing source unit, a selection algorithm unit and a selection algorithm conversion linkage unit. Wherein: the sensing source unit is used for selecting a sensing source and extracting data of sensing nodes from the sensing source according to the sampling frequency; the selection algorithm unit is used for selecting an algorithm, uploading accessories for auxiliary analysis according to the need, and analyzing and identifying the data of the sensing node based on the algorithm and the accessories; and the selection algorithm conversion linkage unit is used for selecting the conversion linkage of the algorithm and processing the analysis and identification result.
The conversion linkage module is used for selecting configuration of conversion linkage in the perception link conversion linkage unit and the selection algorithm conversion linkage unit and comprises an event strategy setting unit, a data processing plug-in unit, a data filtering unit and a linkage rule setting unit. Wherein: the event policy setting unit is used for setting event policies and filtering input data for the first time according to the types of the event policies; the data processing plug-in unit is used for selecting a data processing plug-in unit and converting the data after the first filtering according to the conversion rule of the processing plug-in unit; the setting data filtering unit is used for setting data filtering, and performing secondary filtering on the converted data based on AND logic judgment; and the linkage rule unit is used for setting a linkage rule, judging the data after the second filtering, triggering and executing a corresponding task according to a judging result, and supporting the transmission of parameters to the corresponding task.
3. The embodiment of the device comprises:
as shown in FIG. 3, the present invention also provides a context aware implementation apparatus based on a transformation linkage, comprising a memory, a Graphics Processor (GPU), a processor, and a computer program stored on the memory and executable on the processor. Wherein: the Graphic Processor (GPU) assists an algorithm in the environment sensing method based on conversion linkage to analyze and identify; the processor implements the context awareness method based on conversion linkage when executing the computer program.
In particular implementations, the processor may be a Central Processing Unit (CPU) or other form of processing unit having data processing and/or instruction execution capabilities, and may control other components in the device to perform the desired functions.
Also, the memory may include one or more computer program products, which 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) and/or cache memory (cache), and the like. The non-volatile memory may include, for example, read Only Memory (ROM), hard disk, flash memory, and the like. One or more computer program instructions may be stored on the computer readable storage medium that can be executed by a processor to implement the functions of the methods of the various embodiments and/or systems thereof described above.
4. Storage medium embodiments of the present invention:
the invention further provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program for executing the environment sensing method based on conversion linkage.
In particular, the computer-readable storage medium may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may include, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium would include the following: an electrical connection having one or more wires, a portable disk, a hard disk, random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
Furthermore, the block diagrams of the systems, apparatuses, and methods according to the present invention are merely illustrative examples, and do not require or imply that the connections, arrangements, and configurations must be made in the manner shown in the block diagrams. These systems, devices may be connected, arranged, configured in any manner, as will be appreciated by those skilled in the art. It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein.
Claims (11)
1. The environment sensing method based on conversion linkage is characterized by comprising the following steps of:
s1, setting sampling frequency according to comprehensive evaluation results of a use scene and the performance of a host, and synchronously effecting all perception sources;
s2, setting a sensing link, adding sensing nodes, and transmitting and outputting data of all the sensing nodes according to the sensing link;
s3, selecting conversion linkage of a sensing link, and processing data output by the sensing link;
the sensing node in the step S2 adopts the following configuration steps:
s21, selecting a sensing source, and extracting data of a sensing node from the sensing source according to the sampling frequency;
s22, selecting an algorithm, uploading accessories for auxiliary analysis according to the need, and analyzing and identifying the data of the sensing nodes based on the algorithm and the accessories;
s23, selecting conversion linkage of an algorithm, and processing analysis and identification results;
the switching linkage in the step S3 and the step S23 adopts the following configuration steps:
s31, setting an event strategy, and filtering input data for the first time according to the type of the event strategy;
s32, selecting a data processing plug-in, and converting the data after the first filtering according to the conversion rule of the processing plug-in;
s33, setting data filtering, and performing secondary filtering on the converted data based on AND logic judgment;
s34, setting a linkage rule, judging the data after the second filtering, triggering and executing corresponding tasks according to the judging result, and supporting to transfer parameters to the corresponding tasks.
2. The context awareness method based on the conversion linkage according to claim 1, wherein when parallel and serial relations exist among a plurality of awareness nodes in the awareness link in the step S2, data of an upper-layer awareness node are packed and combined and then transferred to a lower-layer awareness node, and final data output is completed through an end awareness node.
3. The context awareness method according to claim 1, wherein the type of the awareness source in the step S21 is video, audio, text or radar, and different awareness source types correspond to different algorithm types.
4. A context awareness method according to claim 1 or 3, wherein in step S21, when the sampling frequency is lower than or equal to 1 frame/second, frames are directly extracted through an interface of the awareness node;
when the sampling frequency is higher than 1 frame/second, hard or soft decoding frame extraction is adopted, and GPU or CPU is adopted to improve frame extraction efficiency;
when the same sensing source exists in the plurality of sensing nodes, only one path of frame extraction is performed;
when multiple environmental awareness configurations are different in sampling frequency, frames are extracted at the highest sampling frequency, and redundant frames are discarded when data is returned to the environmental awareness of other sampling frequencies.
5. The context awareness method based on a transition linkage according to claim 1, wherein the type of the event policy in step S31 is a result change, duration or repetition number;
when the input data is filtered for the first time according to the result change, reporting the data once if the data is different from the data on the current time, otherwise, filtering the data without reporting;
when the input data is filtered for the first time according to the duration, reporting the data once if the data in the set time is the same, otherwise, filtering the data without reporting;
when the input data is filtered for the first time according to the repetition times, reporting the data once if the data in the specified times are the same, otherwise, filtering the data without reporting.
6. The context awareness method based on conversion linkage according to claim 1, wherein the processing plug-in step S32 uses a python format, fills in conversion rules based on a fixed template, and converts the first filtered data according to the conversion rules.
7. The context awareness method based on a transition linkage according to claim 1, wherein the and or logic determination in step S33 uses lambda expression.
8. The context awareness method based on conversion linkage according to claim 1, wherein the linkage rule in the step S34 adopts a lambda expression and can trigger execution of a task; each linkage rule can be provided with a parameter transmission rule, and the parameter transmission rule adopts a lambda expression and can transmit parameters to a task which triggers execution.
9. The environment sensing system based on conversion linkage is characterized by comprising an environment sensing module, a sensing node module and a conversion linkage module;
the environment sensing module comprises a sampling frequency setting unit, a sensing link setting unit and a sensing link switching linkage unit; wherein, the liquid crystal display device comprises a liquid crystal display device,
the sampling frequency setting unit is used for setting the sampling frequency according to the comprehensive evaluation result of the use scene and the host performance and synchronously effecting all the perception sources;
the sensing link unit is used for setting a sensing link, adding sensing nodes and outputting the data of all the sensing nodes after being transmitted according to the sensing link;
the sensing link conversion linkage unit is used for selecting the conversion linkage of the sensing link and processing the data output by the sensing link;
the sensing node module is used for sensing the configuration of the sensing node in the link unit and comprises a selection sensing source unit, a selection algorithm unit and a selection algorithm conversion linkage unit; wherein, the liquid crystal display device comprises a liquid crystal display device,
the sensing source unit is used for selecting a sensing source and extracting data of sensing nodes from the sensing source according to the sampling frequency;
the selection algorithm unit is used for selecting an algorithm, uploading accessories for auxiliary analysis according to the need, and analyzing and identifying the data of the sensing node based on the algorithm and the accessories;
the algorithm conversion linkage unit is used for selecting conversion linkage of the algorithm and processing analysis and identification results;
the conversion linkage module is used for selecting configuration of conversion linkage in the perception link conversion linkage unit and the selection algorithm conversion linkage unit and comprises an event strategy setting unit, a data processing plug-in unit, a data filtering unit and a linkage rule setting unit; wherein, the liquid crystal display device comprises a liquid crystal display device,
the event policy setting unit is used for setting event policies and filtering input data for the first time according to the types of the event policies;
the data processing plug-in unit is used for selecting a data processing plug-in unit and converting the data after the first filtering according to the conversion rule of the processing plug-in unit;
the setting data filtering unit is used for setting data filtering, and performing secondary filtering on the converted data based on AND logic judgment;
and the linkage rule unit is used for setting a linkage rule, judging the data after the second filtering, triggering and executing a corresponding task according to a judging result, and supporting the transmission of parameters to the corresponding task.
10. An environment perception realizing device based on conversion linkage is characterized by comprising a memory, a graphic processor, a processor and a computer program which is stored in the memory and can run on the processor;
the graphic processor assists the algorithm in the environment sensing method based on the conversion linkage of any one of claims 1 to 8 to analyze and identify;
the processor, when executing the computer program, implements the context awareness method based on conversion linkage of any one of claims 1 to 8.
11. A computer-readable storage medium, wherein the computer-readable storage medium has stored thereon a computer program for executing the context awareness method based on a transformation linkage of any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310207476.1A CN116049292B (en) | 2023-03-07 | 2023-03-07 | Environment sensing method, system, device and medium based on conversion linkage |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310207476.1A CN116049292B (en) | 2023-03-07 | 2023-03-07 | Environment sensing method, system, device and medium based on conversion linkage |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116049292A CN116049292A (en) | 2023-05-02 |
| CN116049292B true CN116049292B (en) | 2023-05-30 |
Family
ID=86127533
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310207476.1A Active CN116049292B (en) | 2023-03-07 | 2023-03-07 | Environment sensing method, system, device and medium based on conversion linkage |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116049292B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104484836A (en) * | 2014-12-26 | 2015-04-01 | 国家电网公司 | Grid fault decision-making assisting visualization system and method |
| CN106610963A (en) * | 2015-10-21 | 2017-05-03 | 星际空间（天津）科技发展有限公司 | Geographic information-based multi-source information processing system |
| CN109327433A (en) * | 2018-09-03 | 2019-02-12 | 北京智游网安科技有限公司 | Threat cognitive method and system based on Run-time scenario analysis |
| CN110843757A (en) * | 2019-10-16 | 2020-02-28 | 武汉客车制造股份有限公司 | Vehicle control method and device capable of recognizing posture of whole vehicle |
| CN111354465A (en) * | 2020-02-26 | 2020-06-30 | 深圳市凯利博实业有限公司 | Health analysis method and system based on thermometer and block chain |
| CN113630436A (en) * | 2021-06-24 | 2021-11-09 | 上海悟城智能系统集成有限公司 | Sensor-adaptive urban self-learning perception network |
| CN114968187A (en) * | 2021-02-19 | 2022-08-30 | 哲晰公司 | Platform for perception system development of an autopilot system |
| CN115469057A (en) * | 2022-07-27 | 2022-12-13 | 启思半导体(杭州)有限责任公司 | Gas detection and analysis method for product state |
| CN115665207A (en) * | 2022-10-28 | 2023-01-31 | 南京华苏科技有限公司 | Method for improving data transmission speed in software defined internet of things |
-
2023
- 2023-03-07 CN CN202310207476.1A patent/CN116049292B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104484836A (en) * | 2014-12-26 | 2015-04-01 | 国家电网公司 | Grid fault decision-making assisting visualization system and method |
| CN106610963A (en) * | 2015-10-21 | 2017-05-03 | 星际空间（天津）科技发展有限公司 | Geographic information-based multi-source information processing system |
| CN109327433A (en) * | 2018-09-03 | 2019-02-12 | 北京智游网安科技有限公司 | Threat cognitive method and system based on Run-time scenario analysis |
| CN110843757A (en) * | 2019-10-16 | 2020-02-28 | 武汉客车制造股份有限公司 | Vehicle control method and device capable of recognizing posture of whole vehicle |
| CN111354465A (en) * | 2020-02-26 | 2020-06-30 | 深圳市凯利博实业有限公司 | Health analysis method and system based on thermometer and block chain |
| CN114968187A (en) * | 2021-02-19 | 2022-08-30 | 哲晰公司 | Platform for perception system development of an autopilot system |
| CN113630436A (en) * | 2021-06-24 | 2021-11-09 | 上海悟城智能系统集成有限公司 | Sensor-adaptive urban self-learning perception network |
| CN115469057A (en) * | 2022-07-27 | 2022-12-13 | 启思半导体(杭州)有限责任公司 | Gas detection and analysis method for product state |
| CN115665207A (en) * | 2022-10-28 | 2023-01-31 | 南京华苏科技有限公司 | Method for improving data transmission speed in software defined internet of things |
Non-Patent Citations (1)
| Title |
|---|
| 工业控制系统安全态势感知技术研究;周明等;《信息安全学报》;第2022年卷(第02期);101-119 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116049292A (en) | 2023-05-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110012165B (en) | Method and device for presenting session list page and readable medium | |
| CN113159091A (en) | Data processing method and device, electronic equipment and storage medium | |
| CN111918230A (en) | Data acquisition method, data transmission method, gateway, equipment and storage medium | |
| CN107611962A (en) | Network system branch road searching method, system and electronic equipment | |
| CN115883407A (en) | Data acquisition method, system, equipment and storage medium | |
| CN115810298A (en) | Fault trend prediction method and system based on ship electromechanical equipment fault information | |
| CN116049292B (en) | Environment sensing method, system, device and medium based on conversion linkage | |
| CN112181549B (en) | System and method for recognizing dynamic perception of power icon of transformer substation monitoring interface | |
| CN114413409A (en) | Detection method and device for air conditioner fault probability and intelligent air conditioner | |
| JP4859535B2 (en) | Business management system, information system, and business management method | |
| CN115242684B (en) | Full-link pressure measurement method and device, computer equipment and storage medium | |
| CN113114986B (en) | Early warning method based on picture and sound synchronization and related equipment | |
| CN115309802A (en) | User distribution thermodynamic diagram acquisition method and device, electronic equipment and storage medium | |
| CN115406626A (en) | AR (augmented reality) glasses-based fault detection method and device, AR glasses and medium | |
| CN109446356A (en) | A kind of multimedia document retrieval method and device | |
| CN112416276B (en) | Display picture analysis device, system and method | |
| CN114496299A (en) | Epidemic prevention information processing method based on deep learning and epidemic prevention service system | |
| CN107528728A (en) | A kind of method and device for obtaining user experience data | |
| CN108829563B (en) | Alarm method and alarm device | |
| CN113449166A (en) | Data acquisition method, device, equipment and storage medium | |
| CN111427858A (en) | Log processing system and processing method thereof | |
| CN114880260B (en) | VGA port selection method, device, equipment and medium | |
| CN115309375B (en) | Processing method and device of application programming interface, electronic equipment and medium | |
| CN113573080B (en) | Live broadcast recording method and device, electronic equipment and storage medium | |
| CN109656961B (en) | Method and device for searching homonymous tasks based on data analysis, medium and electronic equipment |
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 |