CN102761888B - The sensor network abnormal detection method that a kind of feature based is selected and device - Google Patents

The sensor network abnormal detection method that a kind of feature based is selected and device Download PDF

Info

Publication number
CN102761888B
CN102761888B CN201210253661.6A CN201210253661A CN102761888B CN 102761888 B CN102761888 B CN 102761888B CN 201210253661 A CN201210253661 A CN 201210253661A CN 102761888 B CN102761888 B CN 102761888B
Authority
CN
China
Prior art keywords
characteristic attribute
characteristic
coefficient correlation
coefficient
correlation
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201210253661.6A
Other languages
Chinese (zh)
Other versions
CN102761888A (en
Inventor
李�瑞
刘克彬
赵季中
何源
刘云浩
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Ruan Internet Of Things Technology Group Co ltd
Run Technology Co ltd
Original Assignee
WUXI RUIAN TECHNOLOGY CO LTD
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by WUXI RUIAN TECHNOLOGY CO LTD filed Critical WUXI RUIAN TECHNOLOGY CO LTD
Priority to CN201210253661.6A priority Critical patent/CN102761888B/en
Publication of CN102761888A publication Critical patent/CN102761888A/en
Application granted granted Critical
Publication of CN102761888B publication Critical patent/CN102761888B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Landscapes

  • Data Exchanges In Wide-Area Networks (AREA)

Abstract

The invention discloses the sensor network abnormal detection method that a kind of feature based is selected, the method comprises: sorted according to the criterion based on coefficient correlation by the characteristic attribute of collection; Choosing of characteristic features property set is carried out according to the feature selecting result of calculation based on coefficient correlation; The reliability of the characteristic features property set selected by being proved by cross validation, described characteristic features property set is used for the running status of representative system.The abnormality detection that feature based is selected not only has simply, efficient, the characteristic that is easy to realization; Can fusion component and other sensor network diagnostic tool can also integrate as one.The invention also discloses the sensing network abnormal detector that a kind of feature based is selected.

Description

The sensor network abnormal detection method that a kind of feature based is selected and device
Technical field
The present invention relates to sensing network diagnostic techniques field, particularly relate to sensor network abnormal detection method and the device of the selection of a kind of feature based.
Background technology
Sensing network is the wireless network that the transducer of static or movement is in a large number formed in the mode of self-organizing and multi-hop, its objective is that the perception of cooperation, collection, process and transmission network cover the monitoring information of perceptive object in geographic area, and is reported to user.The remarkable advantage of this technology be can low cost perception, monitor various complex environment.Sensing network has application prospect quite widely, and obtains a wide range of applications in multiple fields such as environmental monitoring, monitoring building safety, logistics, military battlefield, forest ecology monitoring.
The chief component of sensing network comprises sensor node (SensorNode) and base-station node (SinkNode).Usually, sensor node forms communication network by wireless multi-hop ad hoc form, passes gathered data back base station.Each sensor node is made up of data acquisition module (transducer, A/D converter), data processing and control module (microprocessor, memory), communication module (wireless transceiver) and supply module (battery, DC/AC energy converter) etc.
Network management and abnormality detection determine that can wireless sensor network the key issue of reliability service.At present, most exceptions and error detection all depend on the collection of wireless sensor network data, draw the reason of abnormal method from data packet analysis.And these method for detecting abnormality mainly comprise the generation by decision tree Wrong localization, the data that passive utilization observes carry out the reasoning etc. of model.It is collection initiatively or passive monitoring all needs collection information, and the cost of the existence of bulk redundancy information in network when making these detection systems detect abnormal is relatively high, we make the redundant information of network reduce in a large number by the method for feature selecting, make the data set after selecting can represent the running status of current network, and determine that the change of the representative attributive character collection after selecting can reflect the production of Network Abnormal.
Summary of the invention
The object of the invention is to the sensor network abnormal detection method and the device that propose the selection of a kind of feature based, the expense of abnormality detection can be greatly reduced, well can merge with traditional sensor network diagnostic tool simultaneously.
For reaching this object, the present invention by the following technical solutions:
The sensor network abnormal detection method that feature based is selected, the method comprises:
The characteristic attribute of collection is sorted according to the criterion based on coefficient correlation;
Choosing of characteristic features property set is carried out according to the feature selecting result of calculation based on coefficient correlation;
The reliability of the characteristic features property set selected by being proved by cross validation, described characteristic features property set is used for the running status of representative system.
Described the characteristic attribute collected is carried out sorting according to the criterion based on coefficient correlation comprise further:
The property value of the characteristic attribute collected is carried out to the preliminary treatment of negative value removal;
Utilize the coefficient correlation between pretreated property value calculating different characteristic attribute;
According to coefficient correlation and default ranking criteria, characteristic attribute is sorted.
Coefficient correlation between different characteristic attribute
Wherein, f iand f jrepresent two characteristic attributes respectively, cov represents covariance, and var represents standard deviation.
Described basis is carried out choosing of characteristic features property set based on the feature selecting result of calculation of coefficient correlation and is comprised further:
Get front k characteristic attribute after sequence as initial characteristics property set, calculate the coefficient correlation between described initial characteristics property set and all the other characteristic attributes, and the coefficient correlation between this k characteristic attribute;
Calculate the coefficient correlation between each characteristic attribute in described characteristic attribute collection and described characteristic attribute collection, according to result each characteristic attribute deleted or add.
The computing formula of each characteristic attribute in described calculated characteristics property set and the coefficient correlation between described characteristic attribute collection is: R ( f k , F ) = kr kf k + k ( k - 1 ) r kk ;
Wherein, average correlation coefficient between representation feature attribute and described characteristic attribute collection; represent the average correlation coefficient between different characteristic attribute; F represents the characteristic attribute collection of current selected.
The sensing network abnormal detector that feature based is selected, comprising:
Order module, for sorting the characteristic attribute of collection according to the criterion based on coefficient correlation;
Choose module, for carrying out choosing of characteristic features property set according to the feature selecting result of calculation based on coefficient correlation;
Authentication module, for the reliability of the characteristic features property set selected by being proved by cross validation.
Described order module comprises further:
Preliminary treatment submodule, for carrying out the preliminary treatment of negative value removal to the property value of the characteristic attribute collected;
First operator module, for utilizing the coefficient correlation between pretreated property value calculating different characteristic attribute;
Sorting sub-module, for according to coefficient correlation and default ranking criteria, sorts to characteristic attribute.
Described module of choosing comprises further:
Second operator module, as initial characteristics property set, calculates the coefficient correlation between described initial characteristics property set and all the other characteristic attributes for getting k characteristic attribute before after sequence, and the coefficient correlation between this k characteristic attribute;
Feature selecting submodule, for calculating the coefficient correlation between each characteristic attribute in described characteristic attribute collection and described characteristic attribute collection, to be deleted each characteristic attribute according to result or being added.
Adopt technical scheme of the present invention, the data exception achieved in sensing network detects, and has efficient abnormality detection ability; Provide characteristic attribute sub-set selection mechanism, ensure that the correctness of abnormality detection; The abnormality detection that feature based is selected not only has simply, efficient, the characteristic that is easy to realization; Can fusion component and other sensor network diagnostic tool can also integrate as one.
Accompanying drawing explanation
Fig. 1 is the flow chart of the sensor network abnormal detection method of the feature based selection that the embodiment of the present invention provides.
Fig. 2 is the account form schematic diagram of coefficient correlation between different characteristic attribute in the embodiment of the present invention.
Fig. 3 is the structural representation of the sensing network abnormal detector of the feature based selection that the embodiment of the present invention provides.
Embodiment
Technical scheme of the present invention is further illustrated by embodiment below in conjunction with accompanying drawing.
As shown in Figure 1, the sensor network abnormal detection method that the feature based that the embodiment of the present invention provides is selected comprises:
S101, sorts the characteristic attribute of collection according to the criterion based on coefficient correlation.
Refer to the characteristic attribute collected all state parameters that sensing network is returned by each sensor feedback, each parameter is a corresponding characteristic attribute just, and source data shown in Fig. 1 is these characteristic attributes.Especially, be described below shown in table for Partial Feature attribute:
After collecting above-mentioned characteristic attribute, carry out preliminary treatment to property value, described preliminary treatment comprises negative value and removes or nonnegative value reservation.
Utilize the coefficient correlation between pretreated property value calculating different characteristic attribute.Between different characteristic attribute, the account form of coefficient correlation as shown in Figure 2.Coefficient correlation between different characteristic attribute
ρ ( f i , f j ) = cov ( f i , f j ) var ( f i ) var ( f j ) .
Due to ρ (f i, f j)=ρ (f j, f i), the property set matrix therefore formed between this characteristic attribute is triangular matrix.
Wherein, f iand f jrepresent two characteristic attributes respectively, cov represents covariance, and var represents standard deviation; average correlation coefficient between representation feature attribute and described characteristic attribute collection; represent the average correlation coefficient between different characteristic attribute; F represents the characteristic attribute collection of current selected.
One is worth for x icharacteristic attribute f ibe worth for y with one jcharacteristic attribute f j, being estimated as of coefficient correlation: ρ ( f i , f j ) = Σ i ( x i - x ‾ ) ( y i - y ‾ ) Σ i ( x i - x ‾ ) 2 Σ j ( y i - y ‾ ) 2 .
User can choose definition for high correlation according to the Operation system setting of oneself.Such as, the threshold value that 0.95 is complete correlation attribute value can be chosen, if two property values exist such correlation, then can think the information of redundancy; And the value of correlation between [0.75,0.95] then can think that coefficient correlation is relatively high, but whether redundancy still needs further judgement to data at this moment.
According to coefficient correlation and default ranking criteria, characteristic attribute is sorted.
Ranking criteria comprises 2:
1) for characteristic attribute f i, before comprising the many characteristic attribute sequences more of high coefficient correlation
2) if there is two or more characteristic attribute to have identical high correlation coefficient value, the average correlation coefficient of which characteristic attribute is large, then sort more.
S102, carries out choosing of characteristic features property set according to the feature selecting result of calculation based on coefficient correlation.
K characteristic attribute before after sorting according to above-mentioned ranking criteria, as initial characteristic attribute collection.At this moment can calculate the coefficient correlation between this characteristic attribute collection and all the other characteristic attributes, comprise the coefficient correlation between this k characteristic attribute.
One group of attribute is correlated with, and refers to that its coefficient correlation increases along with the increase of the coefficient correlation between characteristic attribute and the property set comprising k characteristic attribute, along with the coefficient correlation between the property set comprising k characteristic attribute reduction and reduce.
Calculate the coefficient correlation between each characteristic attribute in described characteristic attribute collection and described characteristic attribute collection, according to result each characteristic attribute deleted or retain.
Average correlation coefficient between defined feature attribute and described characteristic attribute collection (the characteristic attribute collection of the energy representative system running status chosen) is average correlation coefficient between different characteristic attribute is then weigh being calculated as of the coefficient correlation of correlation between characteristic attribute group:
R ( f k , F ) = kr kf k + k ( k - 1 ) r kk .
Feature selection approach based on coefficient correlation is, according to above formula, characteristic attribute group (single characteristic attribute also can be used as a characteristic attribute group) and characteristic attribute collection are carried out the calculating of coefficient correlation, if coefficient correlation is more than or equal to the threshold values δ of user's setting, then delete this characteristic attribute, if coefficient correlation is less than the threshold values δ of user's setting, then add this characteristic attribute; Coefficient correlation is extremely low, lower than the characteristic attribute group (single characteristic attribute also can be used as a characteristic attribute group) of the threshold values ε of user's setting, is left in the basket because of not having correlation with this characteristic attribute group.
In addition, best-first search strategy now also can be utilized to search to the characteristic attribute carrying out this step, ensure the selected of characteristic attribute subset.Here, best-first search strategy is a kind of illumination scan, attempts to predict the solution closest to optimal path, and this specific search-type is called as greedy best-first search.
S103, the reliability of the characteristic features property set selected by being proved by cross validation.
Carry out leave one cross validation leave-one-out for selected characteristic attribute subset, this cross validation refers to that a characteristic attribute in a use characteristic property set is as checking material, and remaining characteristic attribute then stays as training material.This step is continued until that each characteristic attribute is by as till one-time authentication material.Be equal to and use k-to roll over cross validation.
By described leave one cross validation, determine whether the characteristic features attribute set exported meets ordering rule described in S101.Described characteristic features property set is used for the running status of representative system.
Most sensing network network diagnostic tool carries out in the process of network diagnosis, there is diagnostic data collection process, characteristic features attribute set in the embodiment of the present invention selects the diagnostic data collection phase that can be incorporated into other diagnostic tools, reduce the collection of diagnostic message as an assembly that can merge, reduce network overhead.
Accordingly, the sensing network abnormal detector that a kind of feature based is selected is embodiments provided.As shown in Figure 3, this device comprises: order module, choose module and authentication module.Wherein:
Order module, for sorting the characteristic attribute of collection according to the criterion based on coefficient correlation;
Choose module, for carrying out choosing of characteristic features property set according to the feature selecting result of calculation based on coefficient correlation;
Authentication module, for the reliability of the characteristic features property set selected by being proved by cross validation.
Described order module comprises further: preliminary treatment submodule, the first operator module and sorting sub-module.Wherein:
Preliminary treatment submodule, for carrying out the preliminary treatment of negative value removal to the property value of the characteristic attribute collected;
First operator module, is connected with preliminary treatment submodule, for utilizing the coefficient correlation between pretreated property value calculating different characteristic attribute;
Sorting sub-module, with the first operator model calling, for according to coefficient correlation and default ranking criteria, sorts to characteristic attribute.
Described module of choosing comprises further: the second operator module and feature selecting submodule.Wherein:
Second operator module, be connected with sorting sub-module, as initial characteristics property set, the coefficient correlation between described initial characteristics property set and all the other characteristic attributes is calculated for getting k characteristic attribute before after sequence, and the coefficient correlation between this k characteristic attribute;
Feature selecting submodule, is connected with the second operator module and authentication module, for calculating the coefficient correlation between each characteristic attribute in described characteristic attribute collection and described characteristic attribute collection, to be deleted or add according to result to each characteristic attribute.
Described first computing module and the second computing module, calculate the coefficient correlation between different characteristic attribute
ρ ( f i , f j ) = cov ( f i , f j ) var ( f i ) var ( f j ) ;
Wherein, f iand f jrepresent two characteristic attributes respectively, cov represents covariance, and var represents standard deviation.
Described feature selection module, the computing formula of each characteristic attribute in calculated characteristics property set and the coefficient correlation between described characteristic attribute collection is:
Wherein, average correlation coefficient between representation feature attribute and described characteristic attribute collection; represent the average correlation coefficient between different characteristic attribute; F represents the characteristic attribute collection of current selected.
Adopt technical scheme of the present invention, the data exception achieved in sensing network detects, and has efficient abnormality detection ability; Provide characteristic attribute sub-set selection mechanism, ensure that the correctness of abnormality detection; The abnormality detection that feature based is selected not only has simply, efficient, the characteristic that is easy to realization; Can fusion component and other sensing network network diagnostic tools can also integrate as one.
The above; be only the present invention's preferably embodiment, but protection scope of the present invention is not limited thereto, any people being familiar with this technology is in the technical scope disclosed by the present invention; the change that can expect easily or replacement, all should be encompassed within protection scope of the present invention.Therefore, protection scope of the present invention should be as the criterion with the protection range of claim.

Claims (5)

1. a sensor network abnormal detection method for feature based selection, it is characterized in that, the method comprises:
The characteristic attribute of collection is sorted according to the criterion based on coefficient correlation;
Choosing of characteristic features property set is carried out according to the feature selecting result of calculation based on coefficient correlation;
The reliability of the characteristic features property set selected by being proved by cross validation, described characteristic features property set is used for the running status of representative system;
Wherein, described basis is carried out choosing of characteristic features property set based on the feature selecting result of calculation of coefficient correlation and is comprised further:
Get front k characteristic attribute after sequence as initial characteristics property set, calculate the coefficient correlation between described initial characteristics property set and all the other characteristic attributes, and the coefficient correlation between this k characteristic attribute;
Calculate the coefficient correlation between each characteristic attribute in described characteristic attribute collection and described characteristic attribute collection, according to result each characteristic attribute deleted or add;
Wherein, the computing formula of each characteristic attribute in described calculated characteristics property set and the coefficient correlation between described characteristic attribute collection is:
Wherein, average correlation coefficient between representation feature attribute and described characteristic attribute collection; represent the average correlation coefficient between different characteristic attribute; F represents the characteristic attribute collection of current selected;
Wherein, described the characteristic attribute of collection is carried out sorting according to the criterion based on coefficient correlation specifically comprise:
For characteristic attribute f i, before comprising the many characteristic attribute sequences more of high coefficient correlation; Or if there is two or more characteristic attribute to have identical high correlation coefficient value, the average correlation coefficient of which characteristic attribute is large, then sort more;
Wherein, described according to result each characteristic attribute deleted or added specifically comprise:
If coefficient correlation is more than or equal to the threshold values δ of user's setting, then delete this characteristic attribute, if coefficient correlation is less than the threshold values δ of user's setting, then add this characteristic attribute.
2. the method for claim 1, is characterized in that, described the characteristic attribute collected is carried out sorting according to the criterion based on coefficient correlation comprise further:
The property value of the characteristic attribute collected is carried out to the preliminary treatment of negative value removal;
Utilize the coefficient correlation between pretreated property value calculating different characteristic attribute;
According to coefficient correlation and default ranking criteria, characteristic attribute is sorted.
3. method as claimed in claim 2, is characterized in that, the coefficient correlation between different characteristic attribute
Wherein, f iand f jrepresent two characteristic attributes respectively, cov represents covariance, and var represents standard deviation.
4. a sensing network abnormal detector for feature based selection, is characterized in that, comprising:
Order module, for sorting the characteristic attribute of collection according to the criterion based on coefficient correlation;
Choose module, for carrying out choosing of characteristic features property set according to the feature selecting result of calculation based on coefficient correlation;
Authentication module, for the reliability of the characteristic features property set selected by being proved by cross validation;
Wherein, choose module described in comprise further:
Second operator module, as initial characteristics property set, calculates the coefficient correlation between described initial characteristics property set and all the other characteristic attributes for getting k characteristic attribute before after sequence, and the coefficient correlation between this k characteristic attribute;
Feature selecting submodule, for adopting each characteristic attribute in characteristic attribute collection described in following formulae discovery and the coefficient correlation between described characteristic attribute collection:
Wherein, average correlation coefficient between representation feature attribute and described characteristic attribute collection; represent the average correlation coefficient between different characteristic attribute; F represents the characteristic attribute collection of current selected; According to result each characteristic attribute deleted or added;
Wherein, described order module specifically for, for characteristic attribute f i, before comprising the many characteristic attribute sequences more of high coefficient correlation; Or if there is two or more characteristic attribute to have identical high correlation coefficient value, the average correlation coefficient of which characteristic attribute is large, then sort more;
Wherein, described feature selecting submodule specifically for, if coefficient correlation be more than or equal to user setting threshold values δ, then delete this characteristic attribute, if coefficient correlation be less than user setting threshold values δ, then add this characteristic attribute.
5. device as claimed in claim 4, it is characterized in that, described order module comprises further:
Preliminary treatment submodule, for carrying out the preliminary treatment of negative value removal to the property value of the characteristic attribute collected;
First operator module, for utilizing the coefficient correlation between pretreated property value calculating different characteristic attribute;
Sorting sub-module, for according to coefficient correlation and default ranking criteria, sorts to characteristic attribute.
CN201210253661.6A 2012-07-20 2012-07-20 The sensor network abnormal detection method that a kind of feature based is selected and device Active CN102761888B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201210253661.6A CN102761888B (en) 2012-07-20 2012-07-20 The sensor network abnormal detection method that a kind of feature based is selected and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201210253661.6A CN102761888B (en) 2012-07-20 2012-07-20 The sensor network abnormal detection method that a kind of feature based is selected and device

Publications (2)

Publication Number Publication Date
CN102761888A CN102761888A (en) 2012-10-31
CN102761888B true CN102761888B (en) 2016-01-13

Family

ID=47056176

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201210253661.6A Active CN102761888B (en) 2012-07-20 2012-07-20 The sensor network abnormal detection method that a kind of feature based is selected and device

Country Status (1)

Country Link
CN (1) CN102761888B (en)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106650228B (en) * 2016-11-08 2019-02-26 浙江理工大学 It improves the noise data minimizing technology of k-means algorithm and implements system
EP4052051A4 (en) * 2019-12-02 2023-11-22 Siemens Aktiengesellschaft Method and apparatus for sensor measurements processing
CN112785092B (en) * 2021-03-09 2024-05-07 中铁电气化局集团有限公司 Switch residual life prediction method based on self-adaptive deep feature extraction

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101610516A (en) * 2009-08-04 2009-12-23 华为技术有限公司 Intrusion detection method in the self-organizing network and equipment

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4413915B2 (en) * 2006-12-13 2010-02-10 株式会社東芝 Abnormal sign detection apparatus and method

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101610516A (en) * 2009-08-04 2009-12-23 华为技术有限公司 Intrusion detection method in the self-organizing network and equipment

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
何志文, 李夕海, 刘代志, 张斌.基于相关性分析的特征选择方法研究.《核电子学与探测技术》.2005, *

Also Published As

Publication number Publication date
CN102761888A (en) 2012-10-31

Similar Documents

Publication Publication Date Title
Pourrahmani et al. The applications of Internet of Things in the automotive industry: A review of the batteries, fuel cells, and engines
CN103426042B (en) The group technology of social networks and system
CN102761888B (en) The sensor network abnormal detection method that a kind of feature based is selected and device
CN106452513A (en) Mobile energy supplementation method in delay-constrained wireless sensor network
CN109408509A (en) Date storage method, device and computer equipment
Jafarali Jassbi et al. Fault tolerance and energy efficient clustering algorithm in wireless sensor networks: FTEC
CN101257355A (en) Method for detecting wireless sensor network node malfunction
CN104868843A (en) Solar photovoltaic module array data collection device and data processing method thereof
CN109165234A (en) Robot exception analysis method and device
CN103235263A (en) Online monitoring and fault diagnosing system of motor based on internet of things
CN103838806B (en) Analysis method for subject participation behaviors of user in social network
CN105373620A (en) Mass battery data exception detection method and system for large-scale battery energy storage power stations
CN104410981A (en) Method of credibility evaluation of beacon node in wireless sensor network
CN103823869A (en) Data extracting and predicting model establishing method for environment monitoring
CN102883333A (en) Wireless sensor network construction method based on location information
CN103399133A (en) IOT (internet of things)-based intelligent online multilevel monitoring system of urban sewage discharge points
CN107612806A (en) Energy of wireless sensor network based on mobile sink node perceives the method for data capture with path architecture
CN106292611A (en) A kind of wisdom agricultural control system based on cloud computing
CN102045707B (en) Trust construction method for accelerating trust convergence
CN105636081A (en) Improved EAST (Efficient Data Collection Aware of Spatio-Temporal Correlation) algorithm based on grey model prediction
CN106443130A (en) Voltage monitoring system
CN104615683A (en) Time and location sensing collaborative filtering technology with high expandability
CN105898700A (en) Energy-saving barrier coverage method for mobile sensing nodes on two-dimensional plane
CN102869006B (en) Wireless sensor network hierarchical invasion Fault Diagnostic Expert System and method thereof
CN106292612B (en) A kind of ladle baking facility on-line fault diagnosis system

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C14 Grant of patent or utility model
GR01 Patent grant
CP03 Change of name, title or address
CP03 Change of name, title or address

Address after: Room J1958, Building 6, No. 1288 Yecheng Road, Jiading District, Shanghai, 200000

Patentee after: Ruan Internet of things Technology Group Co.,Ltd.

Address before: 214000 No. 501, A District, Qingyuan Road, Qingyuan Road, Jiangsu science and Technology Park, Wuxi new district.

Patentee before: RUN TECHNOLOGY CO.,LTD.

Address after: 214000 No. 501, A District, Qingyuan Road, Qingyuan Road, Jiangsu science and Technology Park, Wuxi new district.

Patentee after: RUN TECHNOLOGY CO.,LTD.

Address before: No. 501, Zone A, Liye Building, Qingyuan Road, Taikeyuan University Science Park, Wuxi New Area, Wuxi City, Jiangsu Province, 214135

Patentee before: WUXI RUN TECHNOLOGY CO.,LTD.