CN109948937B - Method, system, equipment and medium for detecting potential safety hazard of artificial intelligence self-learning - Google Patents
Method, system, equipment and medium for detecting potential safety hazard of artificial intelligence self-learning Download PDFInfo
- Publication number
- CN109948937B CN109948937B CN201910228163.8A CN201910228163A CN109948937B CN 109948937 B CN109948937 B CN 109948937B CN 201910228163 A CN201910228163 A CN 201910228163A CN 109948937 B CN109948937 B CN 109948937B
- Authority
- CN
- China
- Prior art keywords
- classification model
- model
- new classification
- target parameter
- existing
- 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
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 33
- 238000013145 classification model Methods 0.000 claims abstract description 207
- 238000012544 monitoring process Methods 0.000 claims abstract description 94
- 230000006870 function Effects 0.000 claims description 64
- 230000002159 abnormal effect Effects 0.000 claims description 44
- 238000001514 detection method Methods 0.000 claims description 38
- 238000012545 processing Methods 0.000 claims description 21
- 238000004590 computer program Methods 0.000 claims description 7
- 230000032683 aging Effects 0.000 claims description 5
- 230000000875 corresponding effect Effects 0.000 description 43
- 230000003287 optical effect Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000011835 investigation Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 238000012549 training Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000011534 incubation Methods 0.000 description 2
- 239000013307 optical fiber Substances 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000009413 insulation Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Landscapes
- Alarm Systems (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The embodiment of the invention discloses a method, a system, equipment and a medium for detecting potential safety hazards by artificial intelligence self-learning, wherein the method comprises the following steps: acquiring monitoring data of an electrical system; if the monitoring data meet a first preset condition, determining at least one target parameter based on the monitoring data; judging whether a classification model matched with the at least one target parameter exists in an existing model library according to the parameter type and the numerical range of the at least one target parameter, and if so, acquiring the hidden danger type of the potential safety hazard existing in the electrical system based on the classification model matched with the at least one target parameter; if the existing model library does not have the classification model matched with the at least one target parameter, a new classification model is established based on the at least one target parameter, and the new classification model is added to the existing model library. By adopting the technical scheme, the potential safety hazard of the electrical system is actively detected.
Description
Technical Field
The embodiment of the invention relates to the technical field of electrical safety, in particular to an artificial intelligence self-learning potential safety hazard detection method, system, equipment and medium.
Background
With the development of modern science and technology, electric energy is correspondingly widely developed and utilized. The wide application of the electric energy is beneficial to the human society and brings great potential safety hazard to the human society. An electrical fire is a common electrical disaster, and generally refers to a fire caused by igniting an electrical body or other combustible materials by heat released after an electrical circuit, electrical equipment and power supply and distribution equipment fail. Because of the specificity of the electric fire, the electric fire cannot be seen and touched before the electric fire does not occur, so that the electric fire early warning difficulty is high.
At present, the conventional electric fire early warning method is mainly based on a residual current type electric fire monitoring system to continuously monitor the residual current or temperature of an electric circuit in real time for a long time, and when the residual current or temperature exceeds a set threshold value, the alarm is immediately given, otherwise, the alarm is not given.
Therefore, the electrical fire early warning method cannot actively detect potential safety hazards of the electrical system, so that potential safety hazards of the electrical system, which are not reached to cause fire, cannot be detected in time.
Disclosure of Invention
The embodiment of the invention provides an artificial intelligence self-learning potential safety hazard detection method, system, equipment and medium.
In a first aspect, an embodiment of the present invention provides a method for detecting a potential safety hazard in artificial intelligence self-learning, where the method includes:
acquiring monitoring data of an electrical system;
if the monitoring data meet a first preset condition, determining at least one target parameter based on the monitoring data;
judging whether a classification model matched with the at least one target parameter exists in an existing model library according to the parameter type and the numerical range of the at least one target parameter, and if so, acquiring the hidden danger type of the potential safety hazard existing in the electrical system based on the classification model matched with the at least one target parameter;
if the existing model library does not have the classification model matched with the at least one target parameter, a new classification model is established based on the at least one target parameter, and the new classification model is added to the existing model library.
Further, establishing a new classification model based on the at least one target parameter and adding the new classification model to the existing model library, comprising:
Receiving a new classification model established based on the at least one target parameter;
matching the new classification model with each model in an existing model library to judge whether an existing model with the same function as the new classification model exists or not;
if so, merging the new classification model with the existing model with the same function.
Further, matching the new classification model with each model in the existing model library to determine whether an existing model with the same function as the new classification model exists, including:
matching the processing mode corresponding to the new classification model with the processing modes corresponding to the models in the existing model library, and determining that the existing model with the same function as the new classification model exists if the matching similarity reaches a set threshold value; and/or the number of the groups of groups,
and matching the parameter type and the numerical range of the target parameter corresponding to the new classification model with the parameter type and the numerical range of the target parameter corresponding to each model in the existing model library, and if the matching similarity reaches a set threshold, determining that the existing model with the same function as the new classification model exists.
Further, merging the new classification model with an existing model having the same function includes:
And storing the new classification model in association with the existing model with the same function.
Further, if no existing model with the same function as the new classification model exists, matching the new classification model with each new classification model in a new classification model library to judge whether the new classification model with the same function as the new classification model exists or not;
if the new classification model exists, merging the new classification model with the same function, otherwise, adding the new classification model into a new classification model library.
Further, after merging the new classification model with the same function, the method further includes:
and if the number of the newly added classification models with the same function reaches a set threshold, adding the newly added classification models with the same function into the existing model library.
Further, if the monitoring data does not meet the first preset condition, storing the monitoring data according to a preset rule; the target parameters include: at least one of phase temperature, phase current, reactive power, power factor, or ratio of phase temperature increase to phase current increase;
the hidden trouble category comprises: at least one of poor contact, short circuit, leakage, overload, and circuit aging.
In a second aspect, an embodiment of the present invention provides an artificial intelligence self-learning potential safety hazard detection system, the system including:
the acquisition module is used for acquiring monitoring data of the electrical system;
the determining module is used for determining at least one target parameter based on the monitoring data if the monitoring data meet a first preset condition;
the judging module is used for judging whether a classification model matched with the at least one target parameter exists in the existing model library according to the parameter type and the numerical range of the at least one target parameter;
the detection module is used for acquiring hidden danger categories of potential safety hazards existing in the electrical system based on the classification model matched with the at least one target parameter if the classification model matched with the at least one target parameter exists;
and the building module is used for building a new classification model based on the at least one target parameter if the classification model matched with the at least one target parameter does not exist in the existing model library, and adding the new classification model to the existing model library.
In a third aspect, an embodiment of the present invention provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the method for detecting a safety hazard by artificial intelligence self-learning according to any one of claims 1 to 7 when the processor executes the computer program.
In a fourth aspect, embodiments of the present invention provide a storage medium containing computer executable instructions which, when executed by a computer processor, implement the artificial intelligence self-learning security risk detection method of any one of claims 1 to 7.
According to the safety hidden danger detection method for artificial intelligence self-learning, monitoring data of an electrical system are obtained; if the monitoring data meet a first preset condition, determining at least one target parameter based on the monitoring data; judging whether a classification model matched with the at least one target parameter exists in an existing model library according to the parameter type and the numerical range of the at least one target parameter, and if so, acquiring the hidden danger type of the potential safety hazard existing in the electrical system based on the classification model matched with the at least one target parameter; if the existing model library does not have the classification model matched with the at least one target parameter, a new classification model is established based on the at least one target parameter, and the new classification model is added to the existing model library, so that the problem that potential safety hazards of an electrical system cannot be actively detected by an electrical fire early warning method in the prior art is solved, and the timely detection of potential safety hazards of a fire caused by a plurality of electrical systems is realized.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following description will briefly explain the drawings needed in the description of the embodiments of the present invention, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to the contents of the embodiments of the present invention and these drawings without inventive effort for those skilled in the art.
FIG. 1 is a schematic flow chart of a method for detecting potential safety hazards by artificial intelligence self-learning according to a first embodiment of the invention;
FIG. 2 is a flowchart of an abnormal data processing method according to a first embodiment of the present invention;
FIG. 3 is a schematic flow chart of a method for detecting potential safety hazards by artificial intelligence self-learning according to a second embodiment of the invention;
FIG. 4 is a schematic structural diagram of an artificial intelligence self-learning safety hazard detection system according to a third embodiment of the present invention;
fig. 5 is a schematic structural diagram of an electronic device according to a fourth embodiment of the present invention.
Detailed Description
In order to make the technical problems solved by the present invention, the technical solutions adopted and the technical effects achieved more clear, the technical solutions of the embodiments of the present invention will be described in further detail below with reference to the accompanying drawings, and it is obvious that the described embodiments are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to fall within the scope of the invention.
Example 1
Fig. 1 is a schematic flow chart of a method for detecting potential safety hazards by artificial intelligence self-learning according to a first embodiment of the invention. The method for detecting the potential safety hazards of the fire disaster disclosed by the embodiment is suitable for detecting the potential safety hazards of the electrical system in various scenes, such as a mall, a hospital, a factory, a hotel, a residence, an office building, an entertainment place, a warehouse or a school, and the like. Referring specifically to fig. 1, the method may include the steps of:
110. monitoring data of the electrical system is obtained.
The monitoring data of the electrical system comprises monitoring data when the electrical system operates and monitoring data when the electrical system is stopped due to faults. In the power supply process of the electrical system, a large amount of heat is released due to faults of the electrical circuit, the electric equipment and the power supply and distribution equipment, so that an electrical body or other combustible matters are ignited to cause fire, monitoring data of the electrical system can be actively acquired at intervals to ensure the safety of the electrical system, the safety of the electrical system is analyzed based on the monitoring data, and corresponding measures are timely taken to ensure the safety of the electrical system when the potential safety hazard of the electrical system is determined. The monitoring data includes, but is not limited to, current data, temperature data, power data, etc., and new monitoring data may also appear with the continuous innovation of the electrical system.
Specifically, the monitoring data may be obtained by a sensor disposed at a corresponding position of the electrical system, for example, by a temperature sensor disposed in the electrical line to obtain temperature data of the monitored line, or by a detector disposed in the electrical line to obtain remaining circuit data of the monitored line, or the like.
Illustratively, acquiring monitoring data of an electrical system includes:
acquiring monitoring data of the electrical system in real time according to the set frequency through a monitoring terminal;
the monitoring terminal is equipment which is configured at the front end of the electrical system and used for monitoring various power characteristic data of the electrical system. The monitoring frequency of the monitoring terminal can be set by oneself, the good performance of the monitoring terminal ensures the diversity and the accuracy of monitoring data, the structure and the monitoring mode of the monitoring terminal are not limited in the embodiment, and the monitoring data with various and accurate types can be obtained. After the monitoring terminal acquires the monitoring data, the monitoring data can be further packaged and uploaded to the cloud server, and the cloud server can complete subsequent data discrimination, verification, target parameter calculation and hidden danger category detection; or after the monitoring terminal acquires the monitoring data, the monitoring terminal completes the subsequent operations of data discrimination, verification and target parameter calculation, and uploads the calculation result, namely the target parameter, to the cloud server, and the cloud server detects hidden danger types.
120. And if the monitoring data meets a first preset condition, determining at least one target parameter based on the monitoring data.
The first preset condition may specifically be a numerical range or a numerical interval, and may also be a specific data attribute identifier. For example, when the monitored data is the residual current of the electrical circuit, the first preset condition may specifically be a current value range obtained according to national standard regulations on the residual current of the electrical circuit, for example [300mA-1000mA ], if the monitored residual current falls within the value range, it is determined that the monitored data meets the first preset condition, otherwise, it is determined that the monitored data does not meet the first preset condition.
Further, the monitoring data includes data when the electrical system is running and data when the electrical system is stopped due to a fault, and the data for determining potential safety hazards of the electrical system is data when the electrical system is running, so the first preset condition may specifically be an attribute identifier for identifying that the monitoring data belongs to the data when the electrical system is running, and if the attribute identifier of the monitored data is consistent with the attribute identifier of the data belonging to the data when the electrical system is running, it is determined that the monitoring data meets the first preset condition. When the monitoring terminal uploads the collected monitoring data to the cloud server, an attribute identifier is usually added to the monitoring data to identify whether the current monitoring data is the monitoring data when the electrical system is running or the monitoring data when the electrical system is stopped.
If the monitoring data meets a first preset condition, determining at least one target parameter based on the monitoring data, specifically, the monitoring data refers to original data of the monitored electric system during operation, the target parameter refers to data for analyzing whether potential safety hazards exist in the electric system and potential hazard types corresponding to the potential safety hazards, the target parameter can be the monitoring data, for example, the monitoring data is a temperature value of an electric circuit, and meanwhile, the target parameter is also the temperature value of the electric circuit; the target parameter may also be obtained by performing a certain arithmetic processing on the monitored data.
Illustratively, determining at least one target parameter based on the monitoring data includes:
and calculating the monitoring data according to a preset formula to determine at least one target parameter.
For example, when the monitoring data includes a line current, the target parameter may be a phase current of a certain phase calculated based on the line current according to a conversion formula between the line current and the phase current, or the target parameter may be an average value of the line current; when the monitoring data comprise current and voltage, the target parameter can be power data obtained according to a power calculation formula based on the current and the voltage; when the monitoring data includes: when the phase temperature T and the phase current I are calculated according to a preset formula (k2=t/I), the ratio K2 of the phase temperature T and the phase current I may be calculated, and K2 is the target parameter. Preferably, the target parameters include: at least one of phase temperature, phase current, reactive power, power factor, or a ratio of phase temperature increase to phase current increase.
If the monitoring data does not meet the first preset condition, the monitoring data is considered to be abnormal data, and the abnormal data is stored according to a preset rule. Specifically, referring to a flow chart of a method for processing abnormal data shown in fig. 2, the method includes the following steps:
210. and judging whether the abnormal data is valid, if so, continuing to execute the step 220, otherwise, executing the step 260.
Taking the monitoring data as current data when the electrical system operates as an example, if the current data monitored currently is 2000mA, the current data obviously does not meet a first preset condition ([ 300mA-1000mA ]), so that the current data is abnormal data, and the current data is effective data because the current data belongs to the data when the electrical system operates, at the moment, the current data is stored in an abnormal database, and abnormal information warning is generated to remind related responsible persons of carrying out safety investigation on the electrical system. If the current data belongs to the data when the electrical system is stopped due to faults, determining that the current data is invalid data, and directly eliminating the invalid data.
220. And storing the abnormal data into an abnormal database, and generating an abnormal information warning to remind relevant responsible persons of carrying out safety investigation on the electrical system, and continuing to execute step 230.
230. And judging whether the abnormal data can be combined with the abnormal data existing in the abnormal database, if so, executing the step 240a, otherwise, executing the step 240b.
Judging whether the abnormal data and the existing abnormal data in the abnormal database can be combined or not, specifically judging whether the existing abnormal data which is in the same numerical range with the abnormal data exists in the abnormal database, if so, determining that the matched data which can be combined with the abnormal data exists, and combining the abnormal data with the matched data, wherein the combination essence is as follows: the abnormal data and the matched data are stored in a correlated mode, and the purpose of the abnormal data and the matched data is to identify that the abnormal data and the matched data possibly represent the same potential safety hazard, so that potential hazard investigation is facilitated for engineering personnel, and the matched data refer to the existing abnormal data which are in the same numerical range with the abnormal data.
240a, merging the abnormal data with the matched existing abnormal data, judging the occurrence frequency of the merged abnormal data, if the frequency reaches a set threshold, continuing to execute the step 250a, otherwise, executing the step 250b.
The higher the frequency of the combined abnormal data, the greater the possibility that the hidden danger corresponding to the abnormal data occurs to the electric system.
240b, storing the abnormal data in an abnormal database as new abnormal data.
250a, taking the combined abnormal data as a new hidden danger type parameter, and updating a hidden danger type parameter database. When the engineering personnel determines the hidden danger category corresponding to the hidden danger category parameter, the hidden danger category parameter and the corresponding hidden danger category are stored into the existing model library as a new classification model, so that model types in the existing model library are continuously enriched, and the classification function of the existing model library is improved.
250b, storing the merged abnormal data into an abnormal database.
260. And (5) removing.
130. Judging whether a classification model matched with the at least one target parameter exists in the existing model library according to the parameter type and the numerical range of the at least one target parameter, and if so, executing step 140; if not, step 150 is performed.
The parameter type of the target parameter specifically refers to the meaning of the parameter, and for example, the parameter type can be current, temperature or power. The classification models in the existing model library may be specifically one or more network models obtained by training through a large number of training samples, where the training samples include target parameters and hidden danger types of the electrical system when the target parameters exist, and the network models may be, for example: a deep neural network model or a convolutional neural network model, etc. The classification models in the existing model library may also be predetermined correspondence between the target parameters and the corresponding hidden trouble categories, for example, when the target parameters include: the corresponding relation between the target parameter and the corresponding hidden trouble category can be seen in table 1 when the temperature of the phase a, the current of the phase a, the ratio of the temperature increment of the phase a to the phase current increment, the reactive power and the power factor are as follows:
Table 1: correspondence between target parameters and corresponding hidden trouble categories
Table 1 is merely exemplary, and the present embodiment is not limited thereto.
And judging whether a classification model matched with the at least one target parameter exists in the existing model library or not after the at least one target parameter is acquired, specifically judging whether the matched classification model exists in the existing model library or not based on the parameter type of the at least one target parameter and the corresponding numerical range, and calling the classification model matched with the at least one target parameter if the matched classification model exists, and obtaining the hidden danger type of the potential safety hazard existing in the current electrical system based on the classification model.
140. And obtaining hidden danger categories of potential safety hazards existing in the electrical system based on the classification model matched with the at least one target parameter.
Specifically, the hidden danger category of the potential safety hazard existing in the current electrical system is obtained based on the corresponding relation between the target parameter and the corresponding hidden danger category. Wherein, hidden danger category includes: at least one of poor contact, short circuit, electrical leakage, overload, circuit aging, use of high power electrical appliances, flammable buildup, and insulation damage. It should be noted that, with the increase of application scenarios, many new hidden trouble categories may also appear, and are not limited to the above-mentioned several types.
Furthermore, the classification model can also provide a processing mode corresponding to the hidden danger category, for example, when the hidden danger category is 'circuit aging', the corresponding processing mode is 'timely replacing a line wire', and the like, and the classification model can also provide a hidden danger level corresponding to the hidden danger category, for example, when the electric leakage level is 'serious', an alarm can be further triggered to perform early warning at the moment so as to improve the importance of related personnel.
150. A new classification model is established based on the at least one target parameter and is added to the existing model library.
If the existing model library does not have the classification model matched with the at least one target parameter, the hidden danger category of the current electrical system can be determined through manual investigation or through the self-learning function of the neural network, and the at least one target parameter and the corresponding hidden danger category are used as new classification models to be supplemented into the model library, so that the classification models in the model library are continuously enriched, and the classification function of the classification model in the model library is improved.
Based on the above technical solution, before determining whether a classification model matched with the at least one target parameter exists in the existing model library according to the parameter type and the numerical range of the at least one target parameter, the method may further include:
Judging whether the electrical system has potential safety hazards according to the at least one target parameter, if so, continuing to execute the step of judging whether a classification model matched with the at least one target parameter exists in the existing model library according to the parameter type and the numerical range of the at least one target parameter. Illustratively, determining whether the electrical system has a safety hazard according to the at least one target parameter includes:
determining whether potential safety hazards exist in the electrical system according to the grade of the target parameter, for example, assuming that the target parameter is the temperature of a certain phase and the corresponding temperature value is 50 degrees, obtaining a grade discrimination result of 2 grades through grade discrimination, and reaching the potential safety hazard grade, thereby determining that the potential safety hazards exist in the current electrical system; if the corresponding temperature value is 10 degrees, the grade discrimination result is 0 grade after grade discrimination, and the potential safety hazard level is not reached, so that the current electrical system is determined to have no potential safety hazard.
Or judging whether the set key value in the at least one target parameter exceeds a set threshold value, if so, determining that the electrical system has potential safety hazard. The set key value may be a parameter, such as the temperature value in the above example, or a combination of several parameters, for example, when the temperature reaches 30 degrees and the phase current reaches 100mA, it is determined that the current electrical system has a potential safety hazard. The set key value and the corresponding threshold value can be set according to engineering experience.
If it is determined that the potential safety hazard exists in the current electrical system, further performing potential safety hazard analysis, executing step 130 to determine the potential hazard type, and taking corresponding measures according to the potential hazard type to avoid the occurrence of a safety accident, and if no potential safety hazard exists, returning to executing step 110 to continuously acquire monitoring data of the electrical system, and continuously monitoring the electrical system for the potential safety hazard.
According to the artificial intelligence self-learning potential safety hazard detection method, detection of potential hazards of an electrical system is achieved by combining existing classification models in a model library with monitoring data of the front end of the electrical system, the purpose of timely carrying out fire early warning in an electrical fire incubation period is achieved, the occurrence rate of the electrical fire is reduced, meanwhile, when the classification model matched with the current target parameters does not exist in the model library, a new classification model is built based on the current target parameters and is added to the model library, real-time expansion of the model library is achieved, and the detection function of the model library is improved.
Example two
Fig. 3 is a schematic flow chart of an artificial intelligence self-learning potential safety hazard detection method according to a second embodiment of the present invention, and the technical solution of this embodiment is further optimized based on the foregoing embodiments, specifically, the foregoing step 150 "creates a new classification model based on the at least one target parameter, and adds the new classification model to the existing model library" to perform optimization, which has the advantages of realizing real-time expansion of the model library and improving the detection function of the model library. For a part of this method embodiment that is not described in detail, reference is made to embodiment one. Referring specifically to fig. 3, the method comprises the steps of:
310. And acquiring monitoring data of the electrical system, and determining at least one target parameter based on the monitoring data if the monitoring data meets a first preset condition.
320. Judging whether a classification model matched with the at least one target parameter exists in the existing model library according to the parameter type and the numerical range of the at least one target parameter, and if so, executing step 330; if not, step 340 is performed.
330. And obtaining hidden danger categories of potential safety hazards existing in the electrical system based on the classification model matched with the at least one target parameter.
340. A new classification model established based on the at least one target parameter is received.
Specifically, human participation can be added, a new classification model is established based on the at least one target parameter, specifically, the hidden danger category corresponding to the target parameter can be determined through a manual investigation mode, then the target parameter and the corresponding hidden danger category are used as a new classification model to be uploaded to a cloud server, and the cloud server stores the new classification model.
350. And matching the new classification model with each model in the existing model library to judge whether the existing model with the same function as the new classification model exists, if so, continuing to execute the step 360a, otherwise, executing the step 360b.
Specifically, by matching the parameter type, the numerical range and the corresponding hidden danger type of the new classification model with the parameter type, the numerical range and the corresponding hidden danger type of each model in the existing model library, whether the existing model with the same function as the new classification model exists is judged. For example, the parameter type of the new classification model is current, the current value is 500mA, the corresponding hidden danger type is electric leakage, meanwhile, the parameter type of one classification model in the existing model library is current, the current value is 400mA, the corresponding hidden danger type is electric leakage, the existing classification model and the new classification model are considered to have the same function, the two models with the same function can be combined, the combined essence is that the two models with the same function are associated and stored, namely, the two models can be considered to be used for detecting the same hidden danger type, so that the storage mode of each classification model is standardized, the speed of matching and calling of each classification model in the model library is improved, and the detection efficiency of potential safety hazards is further improved.
Illustratively, matching the new classification model with each model in the existing model library to determine whether there is an existing model having the same function as the new classification model, including:
Matching the processing mode corresponding to the new classification model with the processing modes corresponding to the models in the existing model library, and determining that the existing model with the same function as the new classification model exists if the matching similarity reaches a set threshold value; and/or the number of the groups of groups,
and matching the parameter type and the numerical range of the target parameter corresponding to the new classification model with the parameter type and the numerical range of the target parameter corresponding to each model in the existing model library, and if the matching similarity reaches a set threshold, determining that the existing model with the same function as the new classification model exists.
The processing mode corresponding to the model is specifically, for example, if the hidden danger class corresponding to the model is overload, the corresponding processing mode is load reduction, and the like.
360a, merging the new classification model with the functionally identical existing model.
360b, matching the new classification model with each new classification model in the new classification model library to judge whether a new classification model with the same function as the new classification model exists, if so, executing step 370a, otherwise, executing step 370b.
If the existing model library does not have the existing model with the same function as the new classification model, the new classification model is stored in the new classification model library, the new classification model is matched with each new classification model in the new classification model library, whether the new classification model with the same function as the new classification model exists or not is judged, if yes, the new classification model is combined with the new classification model with the same function, otherwise, the new classification model is used as the new classification model to be added into the new classification model library.
370a, merging the new classification model with the same function, and continuing to execute step 380.
370b, adding the new classification model to a new model library.
380. And if the number of the newly added classification models with the same function reaches a set threshold value, adding the newly added classification models with the same function to the existing model library as mature classification models.
According to the potential safety hazard detection method for artificial intelligence self-learning, on the basis of the embodiment, when the classification model matched with the at least one target parameter does not exist in the existing model library, a new classification model is built based on the at least one target parameter, and the new classification model is added to the existing model library based on a certain rule, so that the real-time expansion of the existing model library is realized, and the detection function of the model library is improved.
Example III
Fig. 4 is a schematic structural diagram of an artificial intelligence self-learning potential safety hazard detection system according to a third embodiment of the present invention. Referring to fig. 4, the system includes: an acquisition module 410, a determination module 420, a judgment module 430, a detection module 440, and an establishment module 450;
wherein, the acquiring module 410 is configured to acquire monitoring data of the electrical system; a determining module 420, configured to determine at least one target parameter based on the monitoring data if the monitoring data meets a first preset condition; a judging module 430, configured to judge whether a classification model matched with the at least one target parameter exists in the existing model library according to the parameter type and the numerical range of the at least one target parameter; a detection module 440, configured to obtain a hidden danger category of a hidden danger existing in the electrical system based on the classification model matching the at least one target parameter if the classification model matching the at least one target parameter exists; and a building module 450, configured to build a new classification model based on the at least one target parameter if there is no classification model matching the at least one target parameter in the existing model library, and add the new classification model to the existing model library.
Further, the establishing module 450 includes:
a receiving unit, configured to receive a new classification model established based on the at least one target parameter;
the judging unit is used for matching the new classification model with each model in the existing model library so as to judge whether the existing model with the same function as the new classification model exists or not;
and the merging unit is used for merging the new classification model with the existing model with the same function.
Further, the judging unit is specifically configured to match a processing manner corresponding to the new classification model with a processing manner corresponding to each model in the existing model library, and if the matching similarity reaches a set threshold, determine that an existing model with the same function as the new classification model exists; and/or the number of the groups of groups,
and matching the parameter type and the numerical range of the target parameter corresponding to the new classification model with the parameter type and the numerical range of the target parameter corresponding to each model in the existing model library, and if the matching similarity reaches a set threshold, determining that the existing model with the same function as the new classification model exists.
Further, the merging unit is specifically configured to:
and storing the new classification model in association with the existing model with the same function.
Further, the system further comprises: the matching module is used for matching the new classification model with each new classification model in the new classification model library when the existing model with the same function as the new classification model does not exist, so as to judge whether the new classification model with the same function as the new classification model exists or not;
the merging unit is further configured to merge the new classification model with a new classification model with the same function,
further, the system further comprises: and the adding module is used for adding the new classification model to a new model library when the new classification model with the same function as that of the new classification model does not exist.
Further, the adding module is further configured to add the new classification model with the same function to the existing model library after merging the new classification model with the same function, if the number of the new classification models with the same function reaches a set threshold.
Further, if the monitoring data does not meet the first preset condition, storing the monitoring data according to a preset rule; the target parameters include: at least one of phase temperature, phase current, reactive power, power factor, or ratio of phase temperature increase to phase current increase; the hidden trouble category comprises: at least one of poor contact, short circuit, leakage, overload, and circuit aging.
According to the artificial intelligence self-learning potential safety hazard detection system, detection of potential hazards of an electrical system is achieved by combining existing classification models in a model library with monitoring data of the front end of the electrical system, the purpose of timely carrying out fire early warning in an electrical fire incubation period is achieved, the occurrence rate of the electrical fire is reduced, meanwhile, when the classification model matched with the current target parameters does not exist in the model library, a new classification model is built based on the current target parameters and is added to the model library, real-time expansion of the model library is achieved, and the detection function of the model library is improved.
The artificial intelligence self-learning potential safety hazard detection system provided by the embodiment of the invention can execute the artificial intelligence self-learning potential safety hazard detection method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method. Technical details which are not described in detail in the above embodiments can be referred to the artificial intelligence self-learning potential safety hazard detection method provided in any embodiment of the present invention.
Example IV
Fig. 5 is a schematic structural diagram of an electronic device according to a fourth embodiment of the present invention. Fig. 5 illustrates a block diagram of an exemplary electronic device 12 suitable for use in implementing embodiments of the present invention. The electronic device 12 shown in fig. 5 is merely an example and should not be construed as limiting the functionality and scope of use of embodiments of the present invention.
As shown in fig. 5, the electronic device 12 is in the form of a general purpose computing device. Components of the electronic device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, a bus 18 that connects the various system components, including the system memory 28 and the processing units 16.
Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, and a local bus using any of a variety of bus architectures. By way of example, and not limitation, such architectures include Industry Standard Architecture (ISA) bus, micro channel architecture (MAC) bus, enhanced ISA bus, video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.
Electronic device 12 typically includes a variety of computer system readable media. Such media can be any available media that is accessible by electronic device 12 and includes both volatile and nonvolatile media, removable and non-removable media.
The system memory 28 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM) 30 and/or cache memory 32. The electronic device 12 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 34 may be used to read from or write to non-removable, nonvolatile magnetic media (not shown in FIG. 5, commonly referred to as a "hard disk drive"). Although not shown in fig. 5, a magnetic disk drive for reading from and writing to a removable non-volatile magnetic disk (e.g., a "floppy disk"), and an optical disk drive for reading from or writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In such cases, each drive may be coupled to bus 18 through one or more data medium interfaces. The memory 28 may include at least one program product having a set of program modules (e.g., acquisition module 410, determination module 420, determination module 430, detection module 440, and setup module 450 of an artificial intelligence self-learning safety hazard detection system) configured to perform the functions of various embodiments of the present invention.
The program/utility 40 having a set of program modules 42 (e.g., the acquisition module 410, determination module 420, determination module 430, detection module 440, and creation module 450 of the artificial intelligence self-learning security risk detection system) may be stored, for example, in the memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each or some combination of which may include an implementation of a network environment. Program modules 42 generally perform the functions and/or methods of the embodiments described herein.
The electronic device 12 may also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), one or more devices that enable a user to interact with the electronic device 12, and/or any devices (e.g., network card, modem, etc.) that enable the electronic device 12 to communicate with one or more other computing devices. Such communication may occur through an input/output (I/O) interface 22. Also, the electronic device 12 may communicate with one or more networks such as a Local Area Network (LAN), a Wide Area Network (WAN) and/or a public network, such as the Internet, through a network adapter 20. As shown, the network adapter 20 communicates with other modules of the electronic device 12 over the bus 18. It should be appreciated that although not shown, other hardware and/or software modules may be used in connection with electronic device 12, including, but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, data backup storage systems, and the like.
The processing unit 16 executes various functional applications and data processing by running programs stored in the system memory 28, for example, to implement the artificial intelligence self-learning security risk detection method provided by the embodiment of the present invention, and the method includes:
acquiring monitoring data of an electrical system;
if the monitoring data meet a first preset condition, determining at least one target parameter based on the monitoring data;
judging whether a classification model matched with the at least one target parameter exists in an existing model library according to the parameter type and the numerical range of the at least one target parameter, and if so, acquiring the hidden danger type of the potential safety hazard existing in the electrical system based on the classification model matched with the at least one target parameter;
if the existing model library does not have the classification model matched with the at least one target parameter, a new classification model is established based on the at least one target parameter, and the new classification model is added to the existing model library.
The processing unit 16 executes programs stored in the system memory 28 to perform various functional applications and data processing, such as implementing the artificial intelligence self-learning security risk detection method provided by embodiments of the present invention.
Of course, those skilled in the art will understand that the processor may also implement the technical scheme of the method for detecting potential safety hazards by artificial intelligence self-learning provided by any embodiment of the present invention.
Example five
The fifth embodiment of the present invention further provides a computer readable storage medium having a computer program stored thereon, the program when executed by a processor implementing the method for detecting potential safety hazards of artificial intelligence self-learning provided by the embodiment of the present invention, the method comprising:
acquiring monitoring data of an electrical system;
if the monitoring data meet a first preset condition, determining at least one target parameter based on the monitoring data;
judging whether a classification model matched with the at least one target parameter exists in an existing model library according to the parameter type and the numerical range of the at least one target parameter, and if so, acquiring the hidden danger type of the potential safety hazard existing in the electrical system based on the classification model matched with the at least one target parameter;
if the existing model library does not have the classification model matched with the at least one target parameter, a new classification model is established based on the at least one target parameter, and the new classification model is added to the existing model library.
Of course, the computer readable storage medium provided by the embodiment of the present invention, on which the computer program stored is not limited to the above-described method operations, but may also perform the related operations in the artificial intelligence self-learning potential safety hazard detection method provided by any embodiment of the present invention.
The computer storage media of embodiments of the invention may take the form of any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, or device.
The computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, either in baseband or as part of a carrier wave. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).
Note that the above is only a preferred embodiment of the present invention and the technical principle applied. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, while the invention has been described in connection with the above embodiments, the invention is not limited to the embodiments, but may be embodied in many other equivalent forms without departing from the spirit or scope of the invention, which is set forth in the following claims.
Claims (9)
1. The potential safety hazard detection method for artificial intelligence self-learning is characterized by comprising the following steps of:
acquiring monitoring data of an electrical system;
if the monitoring data meet a first preset condition, determining at least one target parameter based on the monitoring data;
if the monitoring data does not meet the first preset condition, determining that the monitoring data is abnormal data, and storing the abnormal data according to a preset rule;
judging whether a classification model matched with the at least one target parameter exists in an existing model library according to the parameter type and the numerical range of the at least one target parameter, and if so, acquiring the hidden danger type of the potential safety hazard existing in the electrical system based on the classification model matched with the at least one target parameter;
If the existing model library does not have the classification model matched with the at least one target parameter, establishing a new classification model based on the at least one target parameter, and adding the new classification model to the existing model library;
establishing a new classification model based on the at least one target parameter and adding the new classification model to the existing model library, comprising:
receiving a new classification model established based on the at least one target parameter;
matching the new classification model with each model in an existing model library to judge whether an existing model with the same function as the new classification model exists or not;
if so, combining the new classification model with the existing model with the same function, wherein the combination of the new classification model with the existing model with the same function is to store the abnormal data in association with the matched data.
2. The method of claim 1, wherein matching the new classification model with models in an existing model library to determine whether there is an existing model that functions identically to the new classification model comprises:
matching the processing mode corresponding to the new classification model with the processing modes corresponding to the models in the existing model library, and determining that the existing model with the same function as the new classification model exists if the matching similarity reaches a set threshold value; and/or the number of the groups of groups,
And matching the parameter type and the numerical range of the target parameter corresponding to the new classification model with the parameter type and the numerical range of the target parameter corresponding to each model in the existing model library, and if the matching similarity reaches a set threshold, determining that the existing model with the same function as the new classification model exists.
3. The method of claim 1, wherein merging the new classification model with an existing model that is functionally identical comprises:
and storing the new classification model in association with the existing model with the same function.
4. The method of claim 1, wherein if there is no existing model with the same function as the new classification model, matching the new classification model with each new classification model in a new model library to determine whether there is a new classification model with the same function as the new classification model;
if the new classification model exists, merging the new classification model with the same function, otherwise, adding the new classification model into a new classification model library.
5. The method of claim 4, wherein after merging the new classification model with the functionally identical new classification model, further comprising:
And if the number of the newly added classification models with the same function reaches a set threshold, adding the newly added classification models with the same function into the existing model library.
6. The method of any one of claims 1-5, wherein the target parameters include: at least one of phase temperature, phase current, reactive power, power factor, or ratio of phase temperature increase to phase current increase;
the hidden trouble category comprises: at least one of poor contact, short circuit, leakage, overload, and circuit aging.
7. An artificial intelligence self-learning security risk detection system, the system comprising:
the acquisition module is used for acquiring monitoring data of the electrical system;
the determining module is used for determining at least one target parameter based on the monitoring data if the monitoring data meet a first preset condition;
if the monitoring data does not meet the first preset condition, determining that the monitoring data is abnormal data, and storing the abnormal data according to a preset rule;
the judging module is used for judging whether a classification model matched with the at least one target parameter exists in the existing model library according to the parameter type and the numerical range of the at least one target parameter;
The detection module is used for acquiring hidden danger categories of potential safety hazards existing in the electrical system based on the classification model matched with the at least one target parameter if the classification model matched with the at least one target parameter exists;
the establishing module is used for establishing a new classification model based on the at least one target parameter if the classification model matched with the at least one target parameter does not exist in the existing model library, and adding the new classification model to the existing model library;
a setup module comprising:
a receiving unit, configured to receive a new classification model established based on the at least one target parameter;
the judging unit is used for matching the new classification model with each model in the existing model library so as to judge whether the existing model with the same function as the new classification model exists or not;
and the merging unit is used for merging the new classification model with an existing model with the same function, wherein the merging of the new classification model with the existing model with the same function is to store the abnormal data in association with the matched data.
8. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the artificial intelligence self-learning security risk detection method of any one of claims 1-6 when the computer program is executed by the processor.
9. A storage medium containing computer executable instructions that when executed by a computer processor implement the artificial intelligence self-learning security risk detection method of any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910228163.8A CN109948937B (en) | 2019-03-25 | 2019-03-25 | Method, system, equipment and medium for detecting potential safety hazard of artificial intelligence self-learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910228163.8A CN109948937B (en) | 2019-03-25 | 2019-03-25 | Method, system, equipment and medium for detecting potential safety hazard of artificial intelligence self-learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109948937A CN109948937A (en) | 2019-06-28 |
| CN109948937B true CN109948937B (en) | 2024-01-09 |
Family
ID=67010834
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910228163.8A Active CN109948937B (en) | 2019-03-25 | 2019-03-25 | Method, system, equipment and medium for detecting potential safety hazard of artificial intelligence self-learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109948937B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112561866B (en) * | 2020-12-04 | 2022-03-01 | 重庆忽米网络科技有限公司 | Semiconductor substrate photoresist layer defect detection system based on AI and cloud computing technology |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103440725A (en) * | 2013-09-03 | 2013-12-11 | 苏州太谷电力股份有限公司 | Electrical fire warning service method and system |
| CN104573740A (en) * | 2014-12-22 | 2015-04-29 | 山东鲁能软件技术有限公司 | SVM classification model-based equipment fault diagnosing method |
| CN107341550A (en) * | 2017-05-03 | 2017-11-10 | 北京海顿中科技术有限公司 | Failure/hidden danger KBS and method for building up |
| CN108959034A (en) * | 2018-07-05 | 2018-12-07 | 北京木瓜移动科技股份有限公司 | A kind of monitoring alarm method, device, electronic equipment and storage medium |
| CN109345752A (en) * | 2018-12-05 | 2019-02-15 | 合肥能安科技有限公司 | A kind of electrical safety monitoring and pre-alarming method and device |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7941382B2 (en) * | 2007-10-12 | 2011-05-10 | Microsoft Corporation | Method of classifying and active learning that ranks entries based on multiple scores, presents entries to human analysts, and detects and/or prevents malicious behavior |
-
2019
- 2019-03-25 CN CN201910228163.8A patent/CN109948937B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103440725A (en) * | 2013-09-03 | 2013-12-11 | 苏州太谷电力股份有限公司 | Electrical fire warning service method and system |
| CN104573740A (en) * | 2014-12-22 | 2015-04-29 | 山东鲁能软件技术有限公司 | SVM classification model-based equipment fault diagnosing method |
| CN107341550A (en) * | 2017-05-03 | 2017-11-10 | 北京海顿中科技术有限公司 | Failure/hidden danger KBS and method for building up |
| CN108959034A (en) * | 2018-07-05 | 2018-12-07 | 北京木瓜移动科技股份有限公司 | A kind of monitoring alarm method, device, electronic equipment and storage medium |
| CN109345752A (en) * | 2018-12-05 | 2019-02-15 | 合肥能安科技有限公司 | A kind of electrical safety monitoring and pre-alarming method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109948937A (en) | 2019-06-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109920193B (en) | Intelligent detection method, system, equipment and medium for electrical fire hazard | |
| CN109859431B (en) | Method, system, equipment and medium for detecting fire safety hidden danger | |
| CN112380679A (en) | Battery thermal runaway simulation method, device, equipment and storage medium | |
| CN107426022A (en) | Security incident monitoring method and device, electronic equipment, storage medium | |
| WO2023098372A1 (en) | Self-diagnosis method and non-negative pressure additive pressure water supply device | |
| CN108872762A (en) | Electronic equipment electrical leakage detecting method, device, electronic equipment and storage medium | |
| KR102319083B1 (en) | Artificial intelligence based fire prevention device and method | |
| CN111739243B (en) | D-S evidence theory-based fire state detection method | |
| CN110147762A (en) | A kind of embedded type fire control wrong report elimination system | |
| CN111415107B (en) | Power distribution network area image generation method, device, computer equipment and storage medium | |
| CN112820066A (en) | Object-based alarm processing method, device, equipment and storage medium | |
| CN106549366A (en) | Electrical Safety detection protection circuit, switchgear or socket | |
| CN114238330A (en) | Data processing method and device, electronic equipment and storage medium | |
| CN109948937B (en) | Method, system, equipment and medium for detecting potential safety hazard of artificial intelligence self-learning | |
| CN111123009A (en) | Intelligent substation avalanche testing method and system based on SCD file and terminal equipment | |
| CN117110794A (en) | Intelligent diagnosis system and method for cable faults | |
| CN117409526A (en) | Electrical fire extremely early warning and monitoring system and fire extinguishing method | |
| CN112200998A (en) | Early fire early warning method and system applied to power equipment and storage medium thereof | |
| CN105277903A (en) | Method for performing remote monitoring on UPS | |
| Liu et al. | Application of aspirating smoke detectors at the fire earliest stage | |
| CN205209536U (en) | Online monitored control system of environment that block terminal was used | |
| CN212181599U (en) | Electric line fire early warning terminal | |
| CN113884943A (en) | Leakage fault analysis method, device, equipment and medium | |
| CN114446002A (en) | Fire on-line monitoring method, device, medium and system | |
| CN108199482B (en) | Maintenance prompting method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20240506 Address after: Building A, 2402, Zhongshe Plaza, No. 1028 Buji Road, Lvjing Community, Dongxiao Street, Luohu District, Shenzhen City, Guangdong Province, 518019 Patentee after: Shenzhen Ruantong Smart Technology Co.,Ltd. Country or region after: China Address before: 430070 Liqiao creative building, 553 Wenhua Road, Hongshan District, Wuhan City, Hubei Province (office only) Patentee before: ISS TECHNOLOGY Co.,Ltd. Country or region before: China |